diff --git a/built-in-nodes/APG.mdx b/built-in-nodes/APG.mdx index a11b660cc..9f0504096 100644 --- a/built-in-nodes/APG.mdx +++ b/built-in-nodes/APG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "APG" icon: "circle" mode: wide --- + The APG (Adaptive Projected Guidance) node modifies the sampling process by adjusting how guidance is applied during diffusion. It separates the guidance vector into parallel and orthogonal components relative to the conditional output, allowing for more controlled image generation. The node provides parameters to scale the guidance, normalize its magnitude, and apply momentum for smoother transitions between diffusion steps. ## Inputs diff --git a/built-in-nodes/ARVideoI2V.mdx b/built-in-nodes/ARVideoI2V.mdx index 524cf66cf..5bdfaa361 100644 --- a/built-in-nodes/ARVideoI2V.mdx +++ b/built-in-nodes/ARVideoI2V.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ARVideoI2V" icon: "circle" mode: wide --- + ## Overview This node prepares an image-to-video generation setup for AR (Auto-Regressive) video models. It takes a starting image, encodes it into the latent space using a VAE, and stores the encoded image in the model's configuration. This allows the video sampling process to use the image as the first frame, effectively seeding the generation without needing a separate image-to-video model architecture. diff --git a/built-in-nodes/AddNoise.mdx b/built-in-nodes/AddNoise.mdx index b1fbc3b8a..a87436ee7 100644 --- a/built-in-nodes/AddNoise.mdx +++ b/built-in-nodes/AddNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddNoise" icon: "circle" mode: wide --- + This node adds controlled noise to a latent image using a specified noise generator and sigma values. It processes the input through the model's sampling system to apply noise scaling appropriate for the given sigma range, returning a new latent representation with the noise applied. ## Inputs diff --git a/built-in-nodes/AddTextPrefix.mdx b/built-in-nodes/AddTextPrefix.mdx index d868c2307..ea57eab35 100644 --- a/built-in-nodes/AddTextPrefix.mdx +++ b/built-in-nodes/AddTextPrefix.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddTextPrefix" icon: "circle" mode: wide --- + The Add Text Prefix node modifies text by adding a specified string to the beginning of each input text. It takes the text and a prefix as input, then returns the combined result. **Note:** This node is deprecated and superseded by the Concatenate Text node. diff --git a/built-in-nodes/AddTextSuffix.mdx b/built-in-nodes/AddTextSuffix.mdx index b209b107e..391b7db3a 100644 --- a/built-in-nodes/AddTextSuffix.mdx +++ b/built-in-nodes/AddTextSuffix.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddTextSuffix" icon: "circle" mode: wide --- + This node appends a specified suffix to the end of an input text string. It takes the original text and the suffix as inputs, then returns the combined result. **This node is deprecated** and superseded by the Concatenate Text node. ## Inputs diff --git a/built-in-nodes/AdjustBrightness.mdx b/built-in-nodes/AdjustBrightness.mdx index 78e0132be..2ecfab3c1 100644 --- a/built-in-nodes/AdjustBrightness.mdx +++ b/built-in-nodes/AdjustBrightness.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AdjustBrightness" icon: "circle" mode: wide --- + The Adjust Brightness node modifies the brightness of an input image. It works by multiplying each pixel's value by a specified factor, then clamping the resulting values to stay within a valid range. A factor of 1.0 leaves the image unchanged, values below 1.0 make it darker, and values above 1.0 make it brighter. ## Inputs diff --git a/built-in-nodes/AdjustContrast.mdx b/built-in-nodes/AdjustContrast.mdx index 91f556e12..7695e4764 100644 --- a/built-in-nodes/AdjustContrast.mdx +++ b/built-in-nodes/AdjustContrast.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AdjustContrast" icon: "circle" mode: wide --- + The Adjust Contrast node modifies the contrast level of an input image. It works by adjusting the difference between the light and dark areas of the image. A factor of 1.0 leaves the image unchanged, values below 1.0 reduce contrast, and values above 1.0 increase it. ## Inputs diff --git a/built-in-nodes/AlignYourStepsScheduler.mdx b/built-in-nodes/AlignYourStepsScheduler.mdx index 27467c41d..39c16d85d 100644 --- a/built-in-nodes/AlignYourStepsScheduler.mdx +++ b/built-in-nodes/AlignYourStepsScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AlignYourStepsScheduler" icon: "circle" mode: wide --- + The AlignYourStepsScheduler node generates sigma values for the denoising process based on different model types. It calculates appropriate noise levels for each step of the sampling process and adjusts the total number of steps according to the denoise parameter. This helps align the sampling steps with the specific requirements of different diffusion models. ## Inputs diff --git a/built-in-nodes/AudioAdjustVolume.mdx b/built-in-nodes/AudioAdjustVolume.mdx index 848556a31..6873dcd56 100644 --- a/built-in-nodes/AudioAdjustVolume.mdx +++ b/built-in-nodes/AudioAdjustVolume.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioAdjustVolume" icon: "circle" mode: wide --- + The AudioAdjustVolume node modifies the loudness of audio by applying volume adjustments in decibels (dB). It takes an audio input and applies a gain factor based on the specified volume level, where positive values increase volume and negative values decrease it. The node returns the modified audio with the same sample rate as the original. ## Inputs diff --git a/built-in-nodes/AudioConcat.mdx b/built-in-nodes/AudioConcat.mdx index 5c54b50fc..5e9cdfdb7 100644 --- a/built-in-nodes/AudioConcat.mdx +++ b/built-in-nodes/AudioConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioConcat" icon: "circle" mode: wide --- + The AudioConcat node combines two audio inputs by joining them together. It takes two audio inputs and connects them in the order you specify, either placing the second audio before or after the first audio. The node automatically handles different audio formats by converting mono audio to stereo and matching sample rates between the two inputs. ## Inputs diff --git a/built-in-nodes/AudioEncoderEncode.mdx b/built-in-nodes/AudioEncoderEncode.mdx index 947b41fd7..803ab3a18 100644 --- a/built-in-nodes/AudioEncoderEncode.mdx +++ b/built-in-nodes/AudioEncoderEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEncoderEncode" icon: "circle" mode: wide --- + The AudioEncoderEncode node processes audio data by encoding it using an audio encoder model. It takes audio input and converts it into an encoded representation that can be used for further processing in the conditioning pipeline. This node transforms raw audio waveforms into a format suitable for audio-based machine learning applications. ## Inputs diff --git a/built-in-nodes/AudioEncoderLoader.mdx b/built-in-nodes/AudioEncoderLoader.mdx index 166103683..cb66fa97c 100644 --- a/built-in-nodes/AudioEncoderLoader.mdx +++ b/built-in-nodes/AudioEncoderLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEncoderLoader" icon: "circle" mode: wide --- + The AudioEncoderLoader node loads an audio encoder model from a file in your audio encoders folder. It takes the filename of an audio encoder model as input and returns the loaded model, which can then be used for audio processing tasks in your workflow. ## Inputs diff --git a/built-in-nodes/AudioEqualizer3Band.mdx b/built-in-nodes/AudioEqualizer3Band.mdx index 3b8f3d1ff..d4f21f78d 100644 --- a/built-in-nodes/AudioEqualizer3Band.mdx +++ b/built-in-nodes/AudioEqualizer3Band.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEqualizer3Band" icon: "circle" mode: wide --- + The Audio Equalizer (3-Band) node allows you to adjust the bass, mid, and treble frequencies of an audio waveform. It applies three separate filters: a low shelf for bass, a peaking filter for mids, and a high shelf for treble. Each band can be independently controlled with gain, frequency, and bandwidth settings. ## Inputs diff --git a/built-in-nodes/AudioMerge.mdx b/built-in-nodes/AudioMerge.mdx index b511fcadb..6562ad2ee 100644 --- a/built-in-nodes/AudioMerge.mdx +++ b/built-in-nodes/AudioMerge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioMerge" icon: "circle" mode: wide --- + The AudioMerge node combines two audio tracks by overlaying their waveforms. It automatically matches the sample rates of both audio inputs and adjusts their lengths to be equal before merging. The node provides several mathematical methods for combining the audio signals and ensures the output remains within acceptable volume levels. ## Inputs diff --git a/built-in-nodes/AutogrowNamesTestNode.mdx b/built-in-nodes/AutogrowNamesTestNode.mdx index bb4abc73a..7ddcd4c21 100644 --- a/built-in-nodes/AutogrowNamesTestNode.mdx +++ b/built-in-nodes/AutogrowNamesTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AutogrowNamesTestNode" icon: "circle" mode: wide --- + This node is a test for the Autogrow input feature. It takes a dynamic number of float inputs, each labeled with a specific name, and combines their values into a single comma-separated string. ## Inputs diff --git a/built-in-nodes/AutogrowPrefixTestNode.mdx b/built-in-nodes/AutogrowPrefixTestNode.mdx index 2b626ab24..1e9f4e40b 100644 --- a/built-in-nodes/AutogrowPrefixTestNode.mdx +++ b/built-in-nodes/AutogrowPrefixTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AutogrowPrefixTestNode" icon: "circle" mode: wide --- + The AutogrowPrefixTestNode is a logic node designed to test the autogrow input feature. It accepts a dynamic number of float inputs, combines their values into a comma-separated string, and outputs that string. ## Inputs diff --git a/built-in-nodes/BasicGuider.mdx b/built-in-nodes/BasicGuider.mdx index 3d707cb5f..8d203399a 100644 --- a/built-in-nodes/BasicGuider.mdx +++ b/built-in-nodes/BasicGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BasicGuider" icon: "circle" mode: wide --- + The BasicGuider node creates a simple guidance mechanism for the sampling process. It takes a model and conditioning data as inputs and produces a guider object that can be used to guide the generation process during sampling. This node provides the fundamental guidance functionality needed for controlled generation. ## Inputs diff --git a/built-in-nodes/BasicScheduler.mdx b/built-in-nodes/BasicScheduler.mdx index 14f151e3c..ae9196ed3 100755 --- a/built-in-nodes/BasicScheduler.mdx +++ b/built-in-nodes/BasicScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BasicScheduler" icon: "circle" mode: wide --- + The `BasicScheduler` node is designed to compute a sequence of sigma values for diffusion models based on the provided scheduler, model, and denoising parameters. It dynamically adjusts the total number of steps based on the denoise factor to fine-tune the diffusion process, providing precise "recipes" for different stages in advanced sampling processes that require fine control (such as multi-stage sampling). ## Inputs diff --git a/built-in-nodes/BatchImagesMasksLatentsNode.mdx b/built-in-nodes/BatchImagesMasksLatentsNode.mdx index 95193522b..ba25a1407 100644 --- a/built-in-nodes/BatchImagesMasksLatentsNode.mdx +++ b/built-in-nodes/BatchImagesMasksLatentsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchImagesMasksLatentsNode" icon: "circle" mode: wide --- + The Batch Images/Masks/Latents node combines multiple inputs of the same type into a single batch. It automatically detects whether the inputs are images, masks, or latent representations and uses the appropriate batching method. This is useful for preparing multiple items for processing by nodes that accept batched inputs. ## Inputs diff --git a/built-in-nodes/BatchImagesNode.mdx b/built-in-nodes/BatchImagesNode.mdx index fd5cb84e3..201610a49 100644 --- a/built-in-nodes/BatchImagesNode.mdx +++ b/built-in-nodes/BatchImagesNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchImagesNode" icon: "circle" mode: wide --- + The Batch Images node combines multiple individual images into a single batch. It takes a variable number of image inputs and outputs them as one batched image tensor, allowing them to be processed together in subsequent nodes. ## Inputs diff --git a/built-in-nodes/BatchLatentsNode.mdx b/built-in-nodes/BatchLatentsNode.mdx index 88562d323..42a11e622 100644 --- a/built-in-nodes/BatchLatentsNode.mdx +++ b/built-in-nodes/BatchLatentsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchLatentsNode" icon: "circle" mode: wide --- + The Batch Latents node combines multiple latent inputs into a single batch. It takes a variable number of latent samples and merges them along the batch dimension, allowing them to be processed together in subsequent nodes. This is useful for generating or processing multiple images in a single operation. ## Inputs diff --git a/built-in-nodes/BatchMasksNode.mdx b/built-in-nodes/BatchMasksNode.mdx index 0318bc2b9..10b421c56 100644 --- a/built-in-nodes/BatchMasksNode.mdx +++ b/built-in-nodes/BatchMasksNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchMasksNode" icon: "circle" mode: wide --- + The Batch Masks node combines multiple individual mask inputs into a single batch. It takes a variable number of mask inputs and outputs them as a single batched mask tensor, allowing for batch processing of masks in subsequent nodes. If the input masks have different sizes, they are automatically resized to match the dimensions of the first mask. ## Inputs diff --git a/built-in-nodes/BeebleSwitchXImageEdit.mdx b/built-in-nodes/BeebleSwitchXImageEdit.mdx index 12534f3eb..258d86ec1 100644 --- a/built-in-nodes/BeebleSwitchXImageEdit.mdx +++ b/built-in-nodes/BeebleSwitchXImageEdit.mdx @@ -5,14 +5,13 @@ sidebarTitle: "BeebleSwitchXImageEdit" icon: "circle" mode: wide --- -## Overview Edit a single image with Beeble SwitchX. This node can switch anything in the scene (background, lighting, costume) while preserving the original subject's pixels. Provide a reference image and/or text prompt to describe the new look. Maximum resolution is approximately 2.77 megapixels. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The source image to edit. | IMAGE | Yes | - | | `prompt` | A text description of the desired new look (e.g., "a knight in shining armor"). | STRING | Yes | - | | `alpha_mode` | How to handle the alpha matte. "select" uses a keyframe to select the subject, "fill" replaces the entire image without a separate matte, "custom" uses a user-provided mask. | COMBO | Yes | `"select"`
`"fill"`
`"custom"` | @@ -25,11 +24,11 @@ Edit a single image with Beeble SwitchX. This node can switch anything in the sc ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The edited image with the scene elements switched. | IMAGE | | `alpha` | The alpha matte used by Beeble. Empty for "fill" mode, which has no separate matte. | MASK | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BeebleSwitchXImageEdit/en.md) --- -**Source fingerprint (SHA-256):** `41f23435686626e3ade28708fcb1da192ded347b210080ee9b17834ea8b727fb` +**Source fingerprint (SHA-256):** `6fd10dff6ac4f1a15fd05de7a6ff6eda988e60dd4ef32bc8c792480fbbf0c92b` diff --git a/built-in-nodes/BeebleSwitchXVideoEdit.mdx b/built-in-nodes/BeebleSwitchXVideoEdit.mdx index 1c45f96ab..308792108 100644 --- a/built-in-nodes/BeebleSwitchXVideoEdit.mdx +++ b/built-in-nodes/BeebleSwitchXVideoEdit.mdx @@ -5,15 +5,14 @@ sidebarTitle: "BeebleSwitchXVideoEdit" icon: "circle" mode: wide --- -# Beeble SwitchX Video Edit -Edit a video with Beeble SwitchX. This node can switch anything in the scene (background, lighting, costume) while preserving the original subject's pixels and motion. Provide a reference image and/or text prompt to describe the new look. +Edit a video with Beeble SwitchX. This node can switch anything in the scene (background, lighting, costume) while preserving the original subject's pixels and motion. Provide a reference image and/or text prompt to describe the new look. Maximum 240 frames, maximum approximately 2.77 megapixels per frame. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `video` | The input video to edit. Maximum 240 frames, maximum ~2.77 megapixels per frame. | VIDEO | Yes | N/A | +|-----------|-------------|-----------|----------|-------| +| `video` | The input video to edit. | VIDEO | Yes | N/A | | `prompt` | A text description of the desired new look for the scene. | STRING | Yes | N/A | | `alpha_mode` | The alpha matte mode. "fill" mode has no separate matte and fills the entire frame. "select" mode uses a single keyframe image to define the area to edit. "custom" mode uses a full alpha video to define the area to edit frame by frame. | COMBO | Yes | `"fill"`
`"select"`
`"custom"` | | `max_resolution` | The maximum resolution for the output video (default: "1080p"). | COMBO | Yes | `"720p"`
`"1080p"` | @@ -33,11 +32,11 @@ When using `select` mode, you must provide the `alpha_keyframe` image. When usin ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The edited video with the scene changes applied. | VIDEO | | `alpha` | The alpha matte used by Beeble. This is empty for "fill" mode, which has no separate matte. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BeebleSwitchXVideoEdit/en.md) --- -**Source fingerprint (SHA-256):** `e2d67b037863f024f42c97943ec0d2daf32b547b232a7dfedd6de398f4b7ba28` +**Source fingerprint (SHA-256):** `a92e78e6a08ac01466d953562a250b812eb8b1a5fb37efce6fddd7aa1ef380a2` diff --git a/built-in-nodes/BerniniConditioning.mdx b/built-in-nodes/BerniniConditioning.mdx new file mode 100644 index 000000000..ff8b37759 --- /dev/null +++ b/built-in-nodes/BerniniConditioning.mdx @@ -0,0 +1,45 @@ +--- +title: "BerniniConditioning - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the BerniniConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "BerniniConditioning" +icon: "circle" +mode: wide +--- + +The BerniniConditioning node prepares video and image conditioning data for the Wan2.2-A14B model. It encodes source videos, reference videos, and reference images using the provided VAE, then attaches them to the conditioning data for in-context generation tasks. The task is automatically inferred from which inputs are connected. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `positive` | Positive conditioning data | CONDITIONING | Yes | - | +| `negative` | Negative conditioning data | CONDITIONING | Yes | - | +| `vae` | VAE model used to encode video and image inputs | VAE | Yes | - | +| `width` | Width of the output latent (default: 832) | INT | Yes | 16 to 8192 (step: 16) | +| `height` | Height of the output latent (default: 480) | INT | Yes | 16 to 8192 (step: 16) | +| `length` | Number of frames in the output latent (default: 81) | INT | Yes | 1 to 8192 (step: 4) | +| `batch_size` | Number of videos to generate in a single batch (default: 1) | INT | Yes | 1 to 4096 | +| `source_video` | Source video to edit or restyle (v2v, rv2v). Resized to width/height and trimmed to length. | IMAGE | No | - | +| `reference_video` | Video to insert into the source video (ads2v). | IMAGE | No | - | +| `reference_images` | Reference images injected as in-context tokens (r2v, rv2v). Up to 8 images can be provided. | IMAGE | No | 0 to 8 images | +| `ref_max_size` | Max size for the long edge of reference_video and reference_images. Resized with preserved aspect ratio and snapped to 16px (default: 848). | INT | No | 16 to 8192 (step: 16) | + +**Note:** The task is inferred from which inputs are connected: +- No inputs connected → text-to-video (t2v) +- `source_video` only → video-to-video (v2v) +- `source_video` + `reference_images` → reference-guided video editing (rv2v) +- `reference_images` only → reference-to-video (r2v) +- `source_video` + `reference_video` → insert image/video into video (ads2v) + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `positive` | Positive conditioning with context latents attached | CONDITIONING | +| `negative` | Negative conditioning with context latents attached | CONDITIONING | +| `latent` | Empty latent tensor with dimensions matching the specified width, height, length, and batch size | LATENT | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BerniniConditioning/en.md) + +--- +**Source fingerprint (SHA-256):** `70b5026f9479249bc5d1fe4695583193216e34e1b092764ac30e0ec3b7eba670` diff --git a/built-in-nodes/BetaSamplingScheduler.mdx b/built-in-nodes/BetaSamplingScheduler.mdx index dea4cfdf9..3b7d2bb22 100644 --- a/built-in-nodes/BetaSamplingScheduler.mdx +++ b/built-in-nodes/BetaSamplingScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BetaSamplingScheduler" icon: "circle" mode: wide --- + The BetaSamplingScheduler node generates a sequence of noise levels (sigmas) for the sampling process using a beta scheduling algorithm. It takes a model and configuration parameters to create a customized noise schedule that controls the denoising process during image generation. This scheduler allows fine-tuning of the noise reduction trajectory through alpha and beta parameters. ## Inputs diff --git a/built-in-nodes/BriaImageEditNode.mdx b/built-in-nodes/BriaImageEditNode.mdx index c57f6b233..cb1d18299 100644 --- a/built-in-nodes/BriaImageEditNode.mdx +++ b/built-in-nodes/BriaImageEditNode.mdx @@ -5,37 +5,37 @@ sidebarTitle: "BriaImageEditNode" icon: "circle" mode: wide --- + The Bria FIBO Image Edit node allows you to modify an existing image using a text instruction. It sends the image and your prompt to the Bria API, which uses the FIBO model to generate a new, edited version of the image based on your request. You can also provide a mask to limit the edits to a specific area. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The model version to use for image editing. | COMBO | Yes | `"FIBO"` | | `image` | The input image you want to edit. | IMAGE | Yes | - | -| `prompt` | The text instruction describing how to edit the image (default: empty). | STRING | No | - | +| `prompt` | Instruction to edit image (default: empty). | STRING | No | - | | `negative_prompt` | Text describing what you do not want to appear in the edited image (default: empty). | STRING | No | - | | `structured_prompt` | A string containing the structured edit prompt in JSON format. Use this instead of the usual prompt for precise, programmatic control (default: empty). | STRING | No | - | | `seed` | A number used to initialize the random generation, ensuring reproducible results (default: 1). | INT | Yes | 1 to 2147483647 | -| `guidance_scale` | Controls how closely the generated image follows the prompt. A higher value results in stronger adherence (default: 3.0). | FLOAT | Yes | 3.0 to 5.0 | +| `guidance_scale` | Higher value makes the image follow the prompt more closely (default: 3.0). | FLOAT | Yes | 3.0 to 5.0 | | `steps` | The number of denoising steps the model will perform (default: 50). | INT | Yes | 20 to 50 | -| `moderation` | Enables or disables content moderation. Selecting `"true"` reveals additional moderation options for prompt content, visual input, and visual output. | DYNAMICCOMBO | Yes | `"false"`
`"true"` | -| `mask` | An optional mask image. If provided, edits will only be applied to the masked areas of the image. | MASK | No | - | +| `moderation` | Moderation settings. Selecting `"true"` reveals additional moderation options for prompt content, visual input, and visual output. | DYNAMICCOMBO | Yes | `"false"`
`"true"` | +| `mask` | If omitted, the edit applies to the entire image. | MASK | No | - | **Important Constraints:** -* You must provide at least one of the `prompt` or `structured_prompt` inputs. They cannot both be empty. -* Exactly one input `image` is required. -* When the `moderation` parameter is set to `"true"`, three additional boolean inputs become available: `prompt_content_moderation` (default: false), `visual_input_moderation` (default: false), and `visual_output_moderation` (default: true). +- You must provide at least one of the `prompt` or `structured_prompt` inputs. They cannot both be empty. +- When the `moderation` parameter is set to `"true"`, three additional boolean inputs become available: `prompt_content_moderation` (default: false), `visual_input_moderation` (default: false), and `visual_output_moderation` (default: true). ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | The edited image returned by the Bria API. | IMAGE | | `structured_prompt` | The structured prompt that was used or generated during the editing process. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaImageEditNode/en.md) --- -**Source fingerprint (SHA-256):** `60a5f42392ba803380695f036f78d4b88436b3d216aea381b2e3c13eeb5c5456` +**Source fingerprint (SHA-256):** `e66aaa563a82407408f25b289011a491c8b158822fc2db8912daf73731750081` diff --git a/built-in-nodes/BriaRemoveImageBackground.mdx b/built-in-nodes/BriaRemoveImageBackground.mdx index 9fbff496c..3e579b9f0 100644 --- a/built-in-nodes/BriaRemoveImageBackground.mdx +++ b/built-in-nodes/BriaRemoveImageBackground.mdx @@ -5,27 +5,28 @@ sidebarTitle: "BriaRemoveImageBackground" icon: "circle" mode: wide --- + This node removes the background from an image using the Bria RMBG 2.0 service. It sends the image to an external API for processing and returns the result with the background removed. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image from which the background will be removed. | IMAGE | Yes | - | | `moderation` | Moderation settings. When set to `"true"`, additional moderation options become available. | COMBO | No | `"false"`
`"true"` | | `visual_input_moderation` | Enables visual content moderation on the input image. This parameter is only available when `moderation` is set to `"true"`. Default: `False`. | BOOLEAN | No | - | | `visual_output_moderation` | Enables visual content moderation on the output image. This parameter is only available when `moderation` is set to `"true"`. Default: `True`. | BOOLEAN | No | - | -| `seed` | A seed value that controls whether the node should re-run. The results are non-deterministic regardless of the seed value. Default: `0`. | INT | No | 0 to 2147483647 | +| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. Default: `0`. | INT | No | 0 to 2147483647 | -**Note:** The `visual_input_moderation` and `visual_output_moderation` parameters are dependent on the `moderation` parameter. They are only active and required if `moderation` is set to `"true"`. +**Note:** The `visual_input_moderation` and `visual_output_moderation` parameters are dependent on the `moderation` parameter. They are only active when `moderation` is set to `"true"`. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The processed image with its background removed. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaRemoveImageBackground/en.md) --- -**Source fingerprint (SHA-256):** `ba1626cbe1a98eb0b20d10a2857307b7589e05ea9f39564273dbb6ceeb8b2d41` +**Source fingerprint (SHA-256):** `f62dcd5c9406ec09f5aab44585dd7f25ae0f7d9a934faa10a58e46ef116df110` diff --git a/built-in-nodes/BriaRemoveVideoBackground.mdx b/built-in-nodes/BriaRemoveVideoBackground.mdx index 8aea1947e..d07c58c9a 100644 --- a/built-in-nodes/BriaRemoveVideoBackground.mdx +++ b/built-in-nodes/BriaRemoveVideoBackground.mdx @@ -5,25 +5,26 @@ sidebarTitle: "BriaRemoveVideoBackground" icon: "circle" mode: wide --- + This node removes the background from a video using the Bria AI service. It processes the input video and replaces the original background with a solid color of your choice. The operation is performed via an external API, and the result is returned as a new video file. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `video` | The input video file from which the background will be removed. | VIDEO | Yes | N/A | -| `background_color` | The solid color to use as the new background for the output video. | STRING | Yes | `"Black"`
`"White"`
`"Gray"`
`"Red"`
`"Green"`
`"Blue"`
`"Yellow"`
`"Cyan"`
`"Magenta"`
`"Orange"` | -| `seed` | A seed value that controls whether the node should re-run. The results are non-deterministic regardless of the seed value. (default: 0) | INT | No | 0 to 2147483647 | +| `background_color` | Background color for the output video. | STRING | Yes | `"Black"`
`"White"`
`"Gray"`
`"Red"`
`"Green"`
`"Blue"`
`"Yellow"`
`"Cyan"`
`"Magenta"`
`"Orange"` | +| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) | INT | No | 0 to 2147483647 | **Note:** The input video must have a duration of 60 seconds or less. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The processed video file with the background removed and replaced by the selected color. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaRemoveVideoBackground/en.md) --- -**Source fingerprint (SHA-256):** `bfff6362ab9c6664b7240926c4b84c7a1c05fd5ab450cf240a46db16e70cc6f7` +**Source fingerprint (SHA-256):** `7a6b357f104b14cce55f68a84b07970566db8c835703dd2fd6ca7d3216dec561` diff --git a/built-in-nodes/BriaTransparentVideoBackground.mdx b/built-in-nodes/BriaTransparentVideoBackground.mdx index e3ebe25d0..b009204ce 100644 --- a/built-in-nodes/BriaTransparentVideoBackground.mdx +++ b/built-in-nodes/BriaTransparentVideoBackground.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaTransparentVideoBackground" icon: "circle" mode: wide --- -# Bria Remove Video Background (Transparent) This node removes the background from a video using Bria's AI service and outputs the cut-out frames along with an alpha mask. Connect both outputs to a compositing node, or feed them to a Save WEBM node to write a transparent video. diff --git a/built-in-nodes/BriaVideoGreenScreen.mdx b/built-in-nodes/BriaVideoGreenScreen.mdx index 23fef71ee..0560f33c8 100644 --- a/built-in-nodes/BriaVideoGreenScreen.mdx +++ b/built-in-nodes/BriaVideoGreenScreen.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaVideoGreenScreen" icon: "circle" mode: wide --- -# Bria Video Green Screen This node replaces a video's background with a solid chroma-key screen using the Bria API. It processes the input video and returns a new video where the original background has been removed and replaced with a uniform green or blue screen color. diff --git a/built-in-nodes/BriaVideoReplaceBackground.mdx b/built-in-nodes/BriaVideoReplaceBackground.mdx index 890329a01..c07d356dc 100644 --- a/built-in-nodes/BriaVideoReplaceBackground.mdx +++ b/built-in-nodes/BriaVideoReplaceBackground.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaVideoReplaceBackground" icon: "circle" mode: wide --- -# Bria Video Replace Background This node replaces the background of a video with a supplied image or video using Bria's API. The output keeps the foreground video's resolution and frame rate; a background with a different aspect ratio is stretched to fit, so matching aspect ratios produces undistorted results. diff --git a/built-in-nodes/BuildJsonPromptIdeogram.mdx b/built-in-nodes/BuildJsonPromptIdeogram.mdx new file mode 100644 index 000000000..87748bcaf --- /dev/null +++ b/built-in-nodes/BuildJsonPromptIdeogram.mdx @@ -0,0 +1,37 @@ +--- +title: "BuildJsonPromptIdeogram - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the BuildJsonPromptIdeogram node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "BuildJsonPromptIdeogram" +icon: "circle" +mode: wide +--- + +This node constructs a structured JSON prompt specifically formatted for the Ideogram 4 image generation model. It organizes your text instructions, style preferences, and color palette into the required JSON structure that the model expects. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `element` | Prompt elements from the node Create Bounding Boxes. | ARRAY | Yes | - | +| `high_level_description` | Optional description of the image in one or two sentences. Strongly recommended. (default: empty) | STRING | No | - | +| `background` | Mandatory description of the image background or environment. (default: empty) | STRING | Yes | - | +| `style` | The visual style category for the generated image. (default: "none") | COMBO | Yes | `"none"`
`"photo"`
`"art_style"` | +| `photo` | Camera or lens details for photographic outputs (e.g. 35mm, f/1.4, bokeh). Only available when style is set to "photo". (default: empty) | STRING | No | - | +| `art_style` | Art style description (e.g. flat vector illustration, bold outlines). Only available when style is set to "art_style". (default: empty) | STRING | No | - | +| `aesthetics` | Mandatory aesthetic keywords (e.g. moody, cinematic, desaturated). (default: empty) | STRING | Yes | - | +| `lighting` | Mandatory lighting description (e.g. golden hour, rim light, dramatic shadows). (default: empty) | STRING | Yes | - | +| `medium` | Mandatory medium type (e.g. photograph, illustration, 3d_render, painting, graphic_design). When style = photo, set to photograph. (default: empty) | STRING | Yes | - | +| `color_palette` | Hex color codes that steer the image's dominant colors. Up to 16 entries. | COLORS | No | - | + +**Note:** When the `style` parameter is set to "photo", the `photo` input becomes available and you should set the `medium` parameter to "photograph". When `style` is set to "art_style", the `art_style` input becomes available. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `prompt` | A structured JSON dictionary containing the high-level description, style description (if applicable), and compositional deconstruction with background and elements. | DICT | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BuildJsonPromptIdeogram/en.md) + +--- +**Source fingerprint (SHA-256):** `56a045e0c7c19531e6443696c0bdf3946df066d03eea7d2d217b7d92f052592f` diff --git a/built-in-nodes/ByteDance2FirstLastFrameNode.mdx b/built-in-nodes/ByteDance2FirstLastFrameNode.mdx index 1c286a288..22e9e41a4 100644 --- a/built-in-nodes/ByteDance2FirstLastFrameNode.mdx +++ b/built-in-nodes/ByteDance2FirstLastFrameNode.mdx @@ -5,32 +5,35 @@ sidebarTitle: "ByteDance2FirstLastFrameNode" icon: "circle" mode: wide --- -This node uses ByteDance's Seedance 2.0 model to generate a video. It creates the video based on a text prompt and a required first frame image. You can optionally provide a last frame image to guide the ending of the video sequence. + +This node uses ByteDance's Seedance 2.0 model to generate a video from a required first frame image and an optional last frame image. It creates the video based on a text prompt and the provided frames, with the first frame guiding the start and the last frame guiding the end of the video sequence. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The model to use for video generation. Seedance 2.0 is for maximum quality, while Seedance 2.0 Fast is optimized for speed. Selecting a model will reveal additional inputs for `prompt`, `resolution`, `ratio`, `duration`, and `generate_audio`. | COMBO | Yes | `"Seedance 2.0"`
`"Seedance 2.0 Fast"` | | `first_frame` | The image to use as the first frame of the video. | IMAGE | No | - | | `last_frame` | The image to use as the last frame of the video. | IMAGE | No | - | | `first_frame_asset_id` | A Seedance asset_id to use as the first frame. This cannot be used at the same time as the `first_frame` image input. Default is an empty string. | STRING | No | - | | `last_frame_asset_id` | A Seedance asset_id to use as the last frame. This cannot be used at the same time as the `last_frame` image input. Default is an empty string. | STRING | No | - | -| `seed` | A seed value. Changing this seed will cause the node to re-run, but the results are non-deterministic. Default is 0. | INT | No | 0 to 2147483647 | +| `seed` | A seed value. Changing this seed will cause the node to re-run, but the results are non-deterministic regardless of seed value. Default is 0. | INT | No | 0 to 2147483647 | | `watermark` | Whether to add a watermark to the generated video. Default is False. | BOOLEAN | No | - | **Parameter Constraints:** * You must provide **either** a `first_frame` image **or** a `first_frame_asset_id`. Providing both will cause an error. +* You must provide at least one of `first_frame` or `first_frame_asset_id` — at least one is required. * You cannot provide both a `last_frame` image and a `last_frame_asset_id` for the same frame. * The `model` input is a dynamic combo. After selecting a model, you must also fill in the revealed `prompt` field (a text description) and configure the other revealed parameters (`resolution`, `ratio`, `duration`, `generate_audio`). +* When using local image inputs (not asset IDs), the images must have an aspect ratio between 0.4 and 2.5, and minimum dimensions of 300x300 pixels. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDance2FirstLastFrameNode/en.md) --- -**Source fingerprint (SHA-256):** `434d6ad8f005515677b0de73b57df916aa589adff94aad892827202e6ebcb6e1` +**Source fingerprint (SHA-256):** `74953cfc8f474a1b5ba7e4765682fd86693e43df87ba59e6d3e615e51293ab07` diff --git a/built-in-nodes/ByteDance2ReferenceNode.mdx b/built-in-nodes/ByteDance2ReferenceNode.mdx index a52f56e93..3db8bcf5c 100644 --- a/built-in-nodes/ByteDance2ReferenceNode.mdx +++ b/built-in-nodes/ByteDance2ReferenceNode.mdx @@ -5,31 +5,32 @@ sidebarTitle: "ByteDance2ReferenceNode" icon: "circle" mode: wide --- -The ByteDance Seedance 2.0 Reference to Video node uses the Seedance 2.0 AI model to create, edit, or extend videos based on your text prompt and provided reference materials. It can use images, videos, and audio as references to guide the generation process, supporting tasks like video editing and extension. + +The ByteDance Seedance 2.0 Reference to Video node uses the Seedance 2.0 AI model to create, edit, or extend videos based on your text prompt and provided reference materials. It can use images, videos, and audio as references to guide the generation process, supporting tasks like video editing and video extension. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The AI model to use. Seedance 2.0 is for maximum quality, while Seedance 2.0 Fast is optimized for speed. Selecting a model reveals additional required inputs for `prompt`, `resolution`, `duration`, `ratio`, `generate_audio`, and optional inputs for `reference_images`, `reference_videos`, `reference_audios`, `reference_assets`, and `auto_downscale`. | COMBO | Yes | `"Seedance 2.0"`
`"Seedance 2.0 Fast"` | | `seed` | A number used to control whether the node should re-run. The results are non-deterministic regardless of the seed value (default: 0). | INT | No | 0 to 2147483647 | | `watermark` | Whether to add a watermark to the generated video (default: False). | BOOLEAN | No | `True` / `False` | **Important Constraints:** -* At least one reference image or video (provided via the `reference_images`, `reference_videos`, or `reference_assets` inputs) is required for the node to work. -* A maximum of 9 reference images can be used in total (including those from `reference_images` and `reference_assets`). -* A maximum of 3 reference videos can be used in total (including those from `reference_videos` and `reference_assets`). -* A maximum of 3 reference audio clips can be used in total (including those from `reference_audios` and `reference_assets`). -* Each reference video must be at least 1.8 seconds long. The combined duration of all reference videos cannot exceed 15.1 seconds. -* Each reference audio clip must be at least 1.8 seconds long. The combined duration of all reference audio cannot exceed 15.1 seconds. +* At least one reference image or video (provided via the `reference_images`, `reference_videos`, or `reference_assets` inputs) is required for the node to work. +* A maximum of 9 reference images can be used in total (including those from `reference_images` and `reference_assets`). +* A maximum of 3 reference videos can be used in total (including those from `reference_videos` and `reference_assets`). +* A maximum of 3 reference audio clips can be used in total (including those from `reference_audios` and `reference_assets`). +* Each reference video must be at least 1.8 seconds long. The combined duration of all reference videos cannot exceed 15.1 seconds. +* Each reference audio clip must be at least 1.8 seconds long. The combined duration of all reference audio cannot exceed 15.1 seconds. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDance2ReferenceNode/en.md) --- -**Source fingerprint (SHA-256):** `4420682a5c2773ce1b4df2f4c9537754ec90ad8411d6332fa38d48f5ea88d66f` +**Source fingerprint (SHA-256):** `434b22e9d08b56583db6e35cea2b0348cd758f60acf218838277c97f05910a27` diff --git a/built-in-nodes/ByteDance2TextToVideoNode.mdx b/built-in-nodes/ByteDance2TextToVideoNode.mdx index 5dd43596d..fe2993c3b 100644 --- a/built-in-nodes/ByteDance2TextToVideoNode.mdx +++ b/built-in-nodes/ByteDance2TextToVideoNode.mdx @@ -5,25 +5,26 @@ sidebarTitle: "ByteDance2TextToVideoNode" icon: "circle" mode: wide --- + This node uses ByteDance's Seedance 2.0 API to generate a video from a text description. It sends your prompt to the selected model, waits for the video to be processed, and returns the final result. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The model to use for video generation. Selecting a model will reveal additional required inputs for the prompt, resolution, aspect ratio, duration, and audio generation. "Seedance 2.0" is for maximum quality; "Seedance 2.0 Fast" is for speed optimization. | COMBO | Yes | `"Seedance 2.0"`
`"Seedance 2.0 Fast"` | | `seed` | A seed value (default: 0). The node will re-run if this value changes, but the results are non-deterministic regardless of the seed. | INT | No | 0 to 2147483647 | | `watermark` | Whether to add a watermark to the video (default: False). This is an advanced setting. | BOOLEAN | No | True / False | -**Note:** The `model` parameter is a dynamic combo. When you select a model, it will reveal several required sub-parameters that must be filled in, including the text prompt, resolution, aspect ratio, duration, and whether to generate audio. The prompt text must be at least 1 character long after removing whitespace. +**Note:** The `model` parameter is a dynamic combo. When you select a model, it will reveal several required sub-parameters that must be filled in, including the text prompt, resolution, aspect ratio, duration, and whether to generate audio. The prompt text must be at least 1 character long after removing whitespace. The "Seedance 2.0" model supports 480p, 720p, and 1080p resolutions, while "Seedance 2.0 Fast" supports 480p and 720p resolutions. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDance2TextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `670a35641fa421fb67ea067cdf38aff0d0fb51056ecc26485b5594e944adbbc8` +**Source fingerprint (SHA-256):** `a540b96cf204f2af751da90cbbee30be9588069794ef833ccb0218a4ff0c2af5` diff --git a/built-in-nodes/ByteDanceCreateImageAsset.mdx b/built-in-nodes/ByteDanceCreateImageAsset.mdx index 675dda278..a286165ef 100644 --- a/built-in-nodes/ByteDanceCreateImageAsset.mdx +++ b/built-in-nodes/ByteDanceCreateImageAsset.mdx @@ -5,28 +5,29 @@ sidebarTitle: "ByteDanceCreateImageAsset" icon: "circle" mode: wide --- + This node creates a personal image asset for ByteDance's Seedance 2.0 service. It uploads an input image and registers it within a specified asset group. If no group ID is provided, it will initiate a real-person authentication process in your browser to create a new group before adding the asset. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The image to be registered as a personal asset. | IMAGE | Yes | | | `group_id` | Reuse an existing Seedance asset group ID to skip repeated human verification for the same person. Leave empty to run real-person authentication in the browser and create a new group (default: empty). | STRING | No | | **Image Constraints:** -* The image width must be between 300 and 6000 pixels. -* The image height must be between 300 and 6000 pixels. -* The image aspect ratio must be between 0.4:1 and 2.5:1. +- The image width must be between 300 and 6000 pixels. +- The image height must be between 300 and 6000 pixels. +- The image aspect ratio must be between 0.4:1 and 2.5:1. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `asset_id` | The unique identifier for the newly created image asset. | STRING | | `group_id` | The identifier for the asset group. This will be the provided `group_id` or a newly created one. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateImageAsset/en.md) --- -**Source fingerprint (SHA-256):** `16e55191af67306bf995c8508f56b64491d2a107e168a3dddb4a05f3468cf103` +**Source fingerprint (SHA-256):** `44d2bc880cbd8780ce1deb27eee5e41dc43973653751b0022a2631df725b155d` diff --git a/built-in-nodes/ByteDanceCreateVideoAsset.mdx b/built-in-nodes/ByteDanceCreateVideoAsset.mdx index b60f68943..68ec2d3c2 100644 --- a/built-in-nodes/ByteDanceCreateVideoAsset.mdx +++ b/built-in-nodes/ByteDanceCreateVideoAsset.mdx @@ -5,30 +5,31 @@ sidebarTitle: "ByteDanceCreateVideoAsset" icon: "circle" mode: wide --- + This node creates a personal video asset for Seedance 2.0. It uploads your input video and registers it within a specified asset group. If you don't provide a group ID, it will guide you through a real-person verification process in your browser to create a new group first. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `video` | Video to register as a personal asset. | VIDEO | Yes | - | | `group_id` | Reuse an existing Seedance asset group ID to skip repeated human verification for the same person. Leave empty to run real-person authentication in the browser and create a new group. (default: empty string) | STRING | No | - | **Video Constraints:** -* **Duration:** Must be between 2 and 15 seconds. -* **Dimensions:** Width and height must each be between 300 and 6000 pixels. -* **Aspect Ratio:** The width-to-height ratio must be between 0.4 and 2.5. -* **Total Pixels:** The total number of pixels (width × height) must be between 409,600 and 927,408. -* **Frame Rate:** Must be between 24 and 60 frames per second (FPS). +- **Duration:** Must be between 2 and 15 seconds. +- **Dimensions:** Width and height must each be between 300 and 6000 pixels. +- **Aspect Ratio:** The width-to-height ratio must be between 0.4 and 2.5. +- **Total Pixels:** The total number of pixels (width × height) must be between 409,600 and 927,408. +- **Frame Rate:** Must be between 24 and 60 frames per second (FPS). ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `asset_id` | The unique identifier for the newly created video asset. | STRING | | `group_id` | The identifier of the asset group containing the new video. This will be the provided `group_id` or a newly created one. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateVideoAsset/en.md) --- -**Source fingerprint (SHA-256):** `6598a586dae18811698bd505333ec45b7d2a60aa85728a38e5de790c5bacbdb7` +**Source fingerprint (SHA-256):** `2c7376185f3273a80c763c2c9bd41305575b58e7902200ff77bebb609aea58b8` diff --git a/built-in-nodes/ByteDanceFirstLastFrameNode.mdx b/built-in-nodes/ByteDanceFirstLastFrameNode.mdx index fc2e73325..9f5d98f0c 100644 --- a/built-in-nodes/ByteDanceFirstLastFrameNode.mdx +++ b/built-in-nodes/ByteDanceFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceFirstLastFrameNode" icon: "circle" mode: wide --- + This node generates a video using a text prompt along with first and last frame images. It takes your description and the two key frames to create a complete video sequence that transitions between them. The node provides various options to control the video's resolution, aspect ratio, duration, and other generation parameters. ## Inputs @@ -32,4 +33,4 @@ This node generates a video using a text prompt along with first and last frame > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceFirstLastFrameNode/en.md) --- -**Source fingerprint (SHA-256):** `ac16faf3aabcb06154c6a8815cc20c8a0e0c3a6b5b21e7d49813c10dce33d7be` +**Source fingerprint (SHA-256):** `56b619d191c0a78ac51eaddf93c86f6ec85a486cc4e6d0e021c1e58b4df29189` diff --git a/built-in-nodes/ByteDanceImageEditNode.mdx b/built-in-nodes/ByteDanceImageEditNode.mdx index 3f6d87068..4b528032d 100644 --- a/built-in-nodes/ByteDanceImageEditNode.mdx +++ b/built-in-nodes/ByteDanceImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageEditNode" icon: "circle" mode: wide --- + The ByteDance Image Edit node allows you to modify images using ByteDance's AI models through an API. You provide an input image and a text prompt describing the desired changes, and the node processes the image according to your instructions. The node handles the API communication automatically and returns the edited image. ## Inputs diff --git a/built-in-nodes/ByteDanceImageNode.mdx b/built-in-nodes/ByteDanceImageNode.mdx index aff04fd94..8e91c815b 100644 --- a/built-in-nodes/ByteDanceImageNode.mdx +++ b/built-in-nodes/ByteDanceImageNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ByteDanceImageNode" icon: "circle" mode: wide --- + The ByteDance Image node generates images using ByteDance models through an API based on text prompts. It allows you to select a model, specify image dimensions, and control various generation parameters like seed and guidance scale. The node connects to ByteDance's image generation service and returns the created image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The ByteDance model to use for image generation. Currently only one model option is available. | STRING | Yes | `"seedream-3-0-t2i-250415"` | | `prompt` | The text prompt used to generate the image. Must be at least 1 character long after stripping whitespace. | STRING | Yes | - | | `size_preset` | Pick a recommended size. Select Custom to use the width and height below. Available presets are defined by the `RECOMMENDED_PRESETS` list. | STRING | Yes | See description | @@ -25,10 +26,10 @@ The ByteDance Image node generates images using ByteDance models through an API ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | The generated image returned from the ByteDance API as a tensor. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageNode/en.md) --- -**Source fingerprint (SHA-256):** `69c1f6fd24e6e184b1a1d785b541c8962f3751d2bbd121d6a3b105d66d58d4b1` +**Source fingerprint (SHA-256):** `0b40c75ca43ef3cccbc644e64822f701a0d772decacd813c58d7d5ac60c230a1` diff --git a/built-in-nodes/ByteDanceImageReferenceNode.mdx b/built-in-nodes/ByteDanceImageReferenceNode.mdx index f7ac1669f..091bf0a0e 100644 --- a/built-in-nodes/ByteDanceImageReferenceNode.mdx +++ b/built-in-nodes/ByteDanceImageReferenceNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ByteDanceImageReferenceNode" icon: "circle" mode: wide --- + The ByteDance Image Reference Node generates videos using a text prompt and one to four reference images. It sends the images and prompt to an external API service that creates a video matching your description while incorporating the visual style and content from your reference images. The node provides various controls for video resolution, aspect ratio, duration, and other generation parameters. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The AI model to use for video generation (default: `"seedance-1-0-lite-i2v-250428"`). | STRING | Yes | `"seedance-1-0-pro-250528"`
`"seedance-1-0-lite-i2v-250428"` | | `prompt` | The text prompt used to generate the video. | STRING | Yes | - | | `images` | One to four images. Each image must be between 300x300 and 6000x6000 pixels, with an aspect ratio between 0.4 and 2.5. | IMAGE | Yes | - | @@ -25,10 +26,10 @@ The ByteDance Image Reference Node generates videos using a text prompt and one ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file based on the input prompt and reference images. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageReferenceNode/en.md) --- -**Source fingerprint (SHA-256):** `5365f846cafc80333bc8db5bce9101d83e69f3aae1625f275de7a172623a54b9` +**Source fingerprint (SHA-256):** `77a0f9aee920d07a1374eaec8489eed494a4505369246c16007765d67e52ef99` diff --git a/built-in-nodes/ByteDanceImageToVideoNode.mdx b/built-in-nodes/ByteDanceImageToVideoNode.mdx index ade73cbba..306da5430 100644 --- a/built-in-nodes/ByteDanceImageToVideoNode.mdx +++ b/built-in-nodes/ByteDanceImageToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ByteDanceImageToVideoNode" icon: "circle" mode: wide --- + The ByteDance Image to Video node generates videos using ByteDance models through an API based on an input image and text prompt. It takes a starting image frame and creates a video sequence that follows the provided description. The node offers various customization options for video resolution, aspect ratio, duration, and other generation parameters. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The ByteDance model to use for video generation (default: `"seedance-1-0-pro-fast-251015"`). | STRING | Yes | `"seedance-1-5-pro-251215"`
`"seedance-1-0-pro-250528"`
`"seedance-1-0-lite-i2v-250428"`
`"seedance-1-0-pro-fast-251015"` | | `prompt` | The text prompt used to generate the video. Must be at least 1 character long after trimming whitespace. | STRING | Yes | - | | `image` | First frame to be used for the video. Must be between 300x300 and 6000x6000 pixels, with an aspect ratio between 0.4 and 2.5. | IMAGE | Yes | - | @@ -27,10 +28,10 @@ The ByteDance Image to Video node generates videos using ByteDance models throug ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file based on the input image and prompt parameters. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `7b77df4ab83ef41164eff80a4c02478d5480c9368aa67bcd624fe2f8375d6e07` +**Source fingerprint (SHA-256):** `3f95a381c8df083ec4cb417de0146efa68c0251b14697f6cc727be66c87cc761` diff --git a/built-in-nodes/ByteDanceSeedAudio.mdx b/built-in-nodes/ByteDanceSeedAudio.mdx new file mode 100644 index 000000000..aa5b5816e --- /dev/null +++ b/built-in-nodes/ByteDanceSeedAudio.mdx @@ -0,0 +1,49 @@ +--- +title: "ByteDanceSeedAudio - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ByteDanceSeedAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ByteDanceSeedAudio" +icon: "circle" +mode: wide +--- + +Generate speech, music, sound effects and multi-speaker dialogue from a single prompt with ByteDance Seed Audio 1.0. Describe the voice(s), emotion, ambience, background music and sound effects in the prompt, and include the lines to speak. Optionally pick a built-in preset voice, clone voices from up to 3 reference clips (tagged @Audio1-3 in the prompt), or derive a voice from a character image. Up to 2 minutes of audio per run. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `text_prompt` | Describe the voice(s), emotion, pacing, ambience, background music and sound effects, and include the lines to speak (name characters inline for dialogue). In 'audio reference' mode, refer to connected clips by order as @Audio1, @Audio2, @Audio3. Maximum 3000 characters. | STRING | Yes | 1 to 3000 characters | +| `reference_mode` | How to condition the voice: 'text only' (describe everything in the prompt), 'audio reference' (clone up to 3 voices, tagged @Audio1-3), 'image reference' (derive a voice from one character image), or 'preset voice' (pick a built-in named voice that reads the prompt). | COMBO | Yes | `"text only"`
`"audio reference"`
`"image reference"`
`"preset voice"` | +| `reference_audio_1` | Reference clip for voice cloning, tagged @Audio1 in the prompt. Up to 30s. Only available when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds | +| `reference_audio_2` | Reference clip tagged @Audio2 in the prompt. Up to 30s. Only available when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds | +| `reference_audio_3` | Reference clip tagged @Audio3 in the prompt. Up to 30s. Only available when `reference_mode` is "audio reference". | AUDIO | No | Up to 30 seconds | +| `reference_image` | A single character image; the model derives a voice from it. Cannot be combined with reference audio. Only available when `reference_mode` is "image reference". | IMAGE | No | - | +| `preset_voice` | A built-in TTS 2.0 voice that reads the prompt. No reference clip needed, and @AudioN tags are not used in this mode. Only available when `reference_mode` is "preset voice". | COMBO | No | Multiple options available (see description) | +| `sample_rate` | Output sample rate in Hz. (default: "24000") | COMBO | Yes | `"8000"`
`"16000"`
`"24000"`
`"32000"`
`"44100"`
`"48000"` | +| `speech_rate` | Speaking speed. 0 = normal, 100 = 2.0x, -50 = 0.5x. (default: 0) | INT | Yes | -50 to 100 | +| `loudness_rate` | Loudness. 0 = normal, 100 = 2.0x, -50 = 0.5x. (default: 0) | INT | Yes | -50 to 100 | +| `pitch_rate` | Pitch shift in semitones (-12 to 12). (default: 0) | INT | Yes | -12 to 12 | +| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 42) | INT | Yes | 0 to 2147483647 | + +### Parameter Constraints + +- **Reference mode dependencies**: The `reference_mode` parameter determines which other inputs are required: + - **"text only"**: No additional inputs required. The prompt must not contain @AudioN tags. + - **"audio reference"**: Requires at least one of `reference_audio_1`, `reference_audio_2`, or `reference_audio_3` to be connected. Reference clips must be connected in order without gaps (e.g., _1, then _2, then _3). Each clip is limited to 30 seconds maximum duration. The prompt must reference connected clips using @Audio1, @Audio2, @Audio3 tags. + - **"image reference"**: Requires `reference_image` to be connected. The prompt must not contain @AudioN tags. + - **"preset voice"**: Requires `preset_voice` to be selected. The prompt must not contain @AudioN tags (the entire prompt is read in the selected voice). + +- **Audio reference ordering**: When using "audio reference" mode, reference audio inputs must be connected sequentially starting from `reference_audio_1` without gaps. For example, you can connect _1 and _2, but not _1 and _3 without _2. + +- **Maximum audio tags**: The prompt can reference up to 3 audio clips (@Audio1, @Audio2, @Audio3) when in "audio reference" mode. The highest numbered tag must not exceed the number of connected reference audio inputs. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `AUDIO` | The generated audio output from ByteDance Seed Audio 1.0, containing speech, music, sound effects, or multi-speaker dialogue as described in the prompt. | AUDIO | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedAudio/en.md) + +--- +**Source fingerprint (SHA-256):** `cefd5fca496b02c35022d25be3d99d3911c1304b6e3a751751b58841d5895ef7` diff --git a/built-in-nodes/ByteDanceSeedNode.mdx b/built-in-nodes/ByteDanceSeedNode.mdx index 71c32af64..a3f6c5399 100644 --- a/built-in-nodes/ByteDanceSeedNode.mdx +++ b/built-in-nodes/ByteDanceSeedNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceSeedNode" icon: "circle" mode: wide --- + ## Overview Generate text responses using ByteDance's Seed 2.0 models. Provide a text prompt and optionally include images or videos for multimodal context. @@ -12,7 +13,7 @@ Generate text responses using ByteDance's Seed 2.0 models. Provide a text prompt ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text input to the model. | STRING | Yes | N/A | | `model` | The Seed model used to generate the response. | COMBO | Yes | `"Seed 2.0 Pro"`
`"Seed 2.0 Lite"`
`"Seed 2.0 Mini"` | | `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) | INT | Yes | 0 to 2147483647 | @@ -23,10 +24,10 @@ Generate text responses using ByteDance's Seed 2.0 models. Provide a text prompt ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated text response from the Seed model. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedNode/en.md) --- -**Source fingerprint (SHA-256):** `d1ef73cf72e88216d40c0cf727f90c40cf783cecabe3be0e7530fe72dba6c172` +**Source fingerprint (SHA-256):** `676c53f00c5368e145a1241f376d2c1624a11e4c06f691c3416ae5e2e46d5c71` diff --git a/built-in-nodes/ByteDanceSeedreamNode.mdx b/built-in-nodes/ByteDanceSeedreamNode.mdx index 824f2b8c5..1b445fca9 100644 --- a/built-in-nodes/ByteDanceSeedreamNode.mdx +++ b/built-in-nodes/ByteDanceSeedreamNode.mdx @@ -5,16 +5,17 @@ sidebarTitle: "ByteDanceSeedreamNode" icon: "circle" mode: wide --- + The ByteDance Seedream 4.5 & 5.0 node provides unified text-to-image generation and precise single-sentence editing capabilities at up to 4K resolution. It can create new images from text prompts or edit existing images using text instructions. The node supports both single image generation and sequential generation of multiple related images. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The Seedream model to use for generation. | STRING | Yes | "seedream 5.0 lite"
"seedream-4-5-251128"
"seedream-4-0-250828" | | `prompt` | Text prompt for creating or editing an image. Must be at least 1 character long. | STRING | Yes | - | | `image` | Input image(s) for image-to-image generation. Reference image(s) for single or multi-reference generation. Maximum of 14 reference images for seedream-5-0-260128, or 10 for other models. | IMAGE | No | - | -| `size_preset` | Pick a recommended size. Select Custom to use the width and height below. Default: first preset from RECOMMENDED_PRESETS_SEEDREAM_4. | STRING | No | Multiple options available | +| `size_preset` | Pick a recommended size. Select Custom to use the width and height below. | STRING | No | Multiple options available | | `width` | Custom width for image. Value is working only if `size_preset` is set to `Custom`. Default: 2048. | INT | No | 1024 to 6240 (step 2) | | `height` | Custom height for image. Value is working only if `size_preset` is set to `Custom`. Default: 2048. | INT | No | 1024 to 4992 (step 2) | | `sequential_image_generation` | Group image generation mode. "disabled" generates a single image. "auto" lets the model decide whether to generate multiple related images (e.g., story scenes, character variations). Default: "disabled". | STRING | No | "disabled"
"auto" | @@ -33,10 +34,10 @@ The ByteDance Seedream 4.5 & 5.0 node provides unified text-to-image generation ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | Generated image(s) based on the input parameters and prompt. Returns a single image tensor or a batch of image tensors if multiple images are generated. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedreamNode/en.md) --- -**Source fingerprint (SHA-256):** `daddffc265ab7b24746337825239c25b633a923804b6e5ad11149aea15772a7f` +**Source fingerprint (SHA-256):** `942c75386abd5f2f352b584b51b0f9adbf2ccba2829ee8072173bdc1a407543f` diff --git a/built-in-nodes/ByteDanceSeedreamNodeV2.mdx b/built-in-nodes/ByteDanceSeedreamNodeV2.mdx index fa194242e..ec446ffd2 100644 --- a/built-in-nodes/ByteDanceSeedreamNodeV2.mdx +++ b/built-in-nodes/ByteDanceSeedreamNodeV2.mdx @@ -5,14 +5,13 @@ sidebarTitle: "ByteDanceSeedreamNodeV2" icon: "circle" mode: wide --- -## Overview This node generates or edits images using ByteDance's Seedream models (versions 4.0, 4.5, and 5.0 Lite). It can create new images from a text prompt or edit existing images by providing reference images, supporting resolutions up to 4K. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt for creating or editing an image. | STRING | Yes | N/A | | `model` | The Seedream model version to use for generation. Each model has different capabilities and pricing. | COMBO | Yes | `"seedream 5.0 lite"`
`"seedream-4-5-251128"`
`"seedream-4-0-250828"` | | `seed` | Seed to use for generation (default: 0). | INT | No | 0 to 2147483647 | @@ -44,10 +43,10 @@ When you select a model, additional parameters become available: ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The generated or edited image as a tensor. If multiple images were requested, they are concatenated into a single batch. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedreamNodeV2/en.md) --- -**Source fingerprint (SHA-256):** `6a98d2c1f1e73e304970115bc6dd3ea24ca3cdf440803eed862b7a1ea8d394ce` +**Source fingerprint (SHA-256):** `a5d58211c716f916b7920ee454d3f2aa3e2af6de666e783bb25d44700ba83569` diff --git a/built-in-nodes/ByteDanceTextToVideoNode.mdx b/built-in-nodes/ByteDanceTextToVideoNode.mdx index 36dcf5c79..bb9b52eed 100644 --- a/built-in-nodes/ByteDanceTextToVideoNode.mdx +++ b/built-in-nodes/ByteDanceTextToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ByteDanceTextToVideoNode" icon: "circle" mode: wide --- + The ByteDance Text to Video node generates videos using ByteDance models through an API based on text prompts. It takes a text description and various video settings as input, then creates a video that matches the provided specifications. The node handles the API communication and returns the generated video as output. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The ByteDance model to use for generation (default: `"seedance-1-0-pro-fast-251015"`). | STRING | Yes | `"seedance-1-5-pro-251215"`
`"seedance-1-0-pro-250528"`
`"seedance-1-0-lite-t2v-250428"`
`"seedance-1-0-pro-fast-251015"` | | `prompt` | The text prompt used to generate the video. | STRING | Yes | - | | `resolution` | The resolution of the output video. | STRING | Yes | `"480p"`
`"720p"`
`"1080p"` | @@ -32,10 +33,10 @@ The ByteDance Text to Video node generates videos using ByteDance models through ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceTextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `a16c07e920a0e96e3e14eec33e5b4e3393e924970528365b326ef32887d64766` +**Source fingerprint (SHA-256):** `b3c0de590278ebc95ff1f965f97b6c347cd507ee0900b0f9ce2acc1bf9af78b4` diff --git a/built-in-nodes/CFGGuider.mdx b/built-in-nodes/CFGGuider.mdx index d086b86ac..4fdf329d7 100644 --- a/built-in-nodes/CFGGuider.mdx +++ b/built-in-nodes/CFGGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGGuider" icon: "circle" mode: wide --- + The CFGGuider node creates a guidance system for controlling the sampling process in image generation. It takes a model along with positive and negative conditioning inputs, then applies a classifier-free guidance scale to steer the generation toward desired content while avoiding unwanted elements. This node outputs a guider object that can be used by sampling nodes to control the image generation direction. ## Inputs diff --git a/built-in-nodes/CFGNorm.mdx b/built-in-nodes/CFGNorm.mdx index ee0f2a16d..4f82e78c5 100644 --- a/built-in-nodes/CFGNorm.mdx +++ b/built-in-nodes/CFGNorm.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGNorm" icon: "circle" mode: wide --- + The CFGNorm node applies a normalization technique to the classifier-free guidance (CFG) process in diffusion models. It adjusts the scale of the denoised prediction by comparing the norms of the conditional and unconditional outputs, then applies a strength multiplier to control the effect. This helps stabilize the generation process by preventing extreme values in the guidance scaling. ## Inputs diff --git a/built-in-nodes/CFGOverride.mdx b/built-in-nodes/CFGOverride.mdx index 6eddd872b..8dc1a01b5 100644 --- a/built-in-nodes/CFGOverride.mdx +++ b/built-in-nodes/CFGOverride.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CFGOverride" icon: "circle" mode: wide --- -# CFG Override The CFG Override node allows you to set a fixed CFG (Classifier-Free Guidance) scale value for a specific range of the sampling process, defined as a percentage of the total steps. When multiple CFG Override nodes are connected, the one closest to the sampler in the chain takes priority for overlapping ranges. diff --git a/built-in-nodes/CFGZeroStar.mdx b/built-in-nodes/CFGZeroStar.mdx index d11e26978..1f91db8ba 100644 --- a/built-in-nodes/CFGZeroStar.mdx +++ b/built-in-nodes/CFGZeroStar.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGZeroStar" icon: "circle" mode: wide --- + The CFGZeroStar node applies a specialized guidance scaling technique to diffusion models. It modifies the classifier-free guidance process by calculating an optimized scale factor based on the difference between conditional and unconditional predictions. This approach adjusts the final output to provide enhanced control over the generation process while maintaining model stability. ## Inputs diff --git a/built-in-nodes/CLIPAttentionMultiply.mdx b/built-in-nodes/CLIPAttentionMultiply.mdx index c3e1ff2e1..7eb776f65 100644 --- a/built-in-nodes/CLIPAttentionMultiply.mdx +++ b/built-in-nodes/CLIPAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPAttentionMultiply" icon: "circle" mode: wide --- + The CLIPAttentionMultiply node allows you to adjust the attention mechanism in CLIP models by applying multiplication factors to different components of the self-attention layers. It works by modifying the query, key, value, and output projection weights and biases in the CLIP model's attention mechanism. This experimental node creates a modified copy of the input CLIP model with the specified scaling factors applied. ## Inputs diff --git a/built-in-nodes/CLIPMergeAdd.mdx b/built-in-nodes/CLIPMergeAdd.mdx index b5dd2d353..bcec7fb86 100644 --- a/built-in-nodes/CLIPMergeAdd.mdx +++ b/built-in-nodes/CLIPMergeAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeAdd" icon: "circle" mode: wide --- + The CLIPMergeAdd node combines two CLIP models by adding patches from the second model to the first model. It creates a copy of the first CLIP model and selectively incorporates key patches from the second model, excluding position IDs and logit scale parameters. This allows you to merge CLIP model components while preserving the structure of the base model. ## Inputs diff --git a/built-in-nodes/CLIPMergeSubtract.mdx b/built-in-nodes/CLIPMergeSubtract.mdx index c177af62c..9053f3da0 100644 --- a/built-in-nodes/CLIPMergeSubtract.mdx +++ b/built-in-nodes/CLIPMergeSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeSubtract" icon: "circle" mode: wide --- + The CLIPMergeSubtract node performs model merging by subtracting the weights of one CLIP model from another. It creates a new CLIP model by cloning the first model and then subtracting the key patches from the second model, with an adjustable multiplier to control the subtraction strength. This allows for fine-tuned model blending by removing specific characteristics from the base model. ## Inputs diff --git a/built-in-nodes/CLIPTextEncodeControlnet.mdx b/built-in-nodes/CLIPTextEncodeControlnet.mdx index 1795bd01f..2f5284914 100644 --- a/built-in-nodes/CLIPTextEncodeControlnet.mdx +++ b/built-in-nodes/CLIPTextEncodeControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeControlnet" icon: "circle" mode: wide --- + The CLIPTextEncodeControlnet node processes text input using a CLIP model and combines it with existing conditioning data to create enhanced conditioning output for controlnet applications. It tokenizes the input text, encodes it through the CLIP model, and adds the resulting embeddings to the provided conditioning data as cross-attention controlnet parameters. ## Inputs diff --git a/built-in-nodes/CLIPTextEncodeHiDream.mdx b/built-in-nodes/CLIPTextEncodeHiDream.mdx index f33ef7d08..d460384d1 100644 --- a/built-in-nodes/CLIPTextEncodeHiDream.mdx +++ b/built-in-nodes/CLIPTextEncodeHiDream.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeHiDream" icon: "circle" mode: wide --- + The CLIPTextEncodeHiDream node processes four separate text inputs using different language models (CLIP-L, CLIP-G, T5-XXL, and LLaMA) and combines them into a single conditioning output. It tokenizes each text input with its corresponding model and encodes them together using a scheduled encoding approach, enabling more sophisticated text conditioning by leveraging multiple language models simultaneously. ## Inputs diff --git a/built-in-nodes/CLIPTextEncodeKandinsky5.mdx b/built-in-nodes/CLIPTextEncodeKandinsky5.mdx index 1041fcc3e..e14358550 100644 --- a/built-in-nodes/CLIPTextEncodeKandinsky5.mdx +++ b/built-in-nodes/CLIPTextEncodeKandinsky5.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeKandinsky5" icon: "circle" mode: wide --- + The CLIPTextEncodeKandinsky5 node prepares text prompts for use with the Kandinsky 5 model. It takes two separate text inputs, tokenizes them using a provided CLIP model, and combines them into a single conditioning output. This output is used to guide the image generation process. ## Inputs diff --git a/built-in-nodes/CLIPTextEncodeLumina2.mdx b/built-in-nodes/CLIPTextEncodeLumina2.mdx index b3ec19a5c..b70395c41 100644 --- a/built-in-nodes/CLIPTextEncodeLumina2.mdx +++ b/built-in-nodes/CLIPTextEncodeLumina2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeLumina2" icon: "circle" mode: wide --- + The CLIP Text Encode for Lumina2 node encodes a system prompt and a user prompt using a CLIP model into an embedding that can guide the diffusion model to generate specific images. It combines a pre-defined system prompt with your custom text prompt and processes them through the CLIP model to create conditioning data for image generation. ## Inputs diff --git a/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx b/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx index 85a8c3d58..500f0b8af 100644 --- a/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx +++ b/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodePixArtAlpha" icon: "circle" mode: wide --- + Encodes text and sets the resolution conditioning for PixArt Alpha. This node processes text input and adds width and height information to create conditioning data specifically for PixArt Alpha models. It does not apply to PixArt Sigma models. ## Inputs diff --git a/built-in-nodes/CLIPTextEncodeSD3.mdx b/built-in-nodes/CLIPTextEncodeSD3.mdx index da18c0db7..9eb24d08e 100644 --- a/built-in-nodes/CLIPTextEncodeSD3.mdx +++ b/built-in-nodes/CLIPTextEncodeSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSD3" icon: "circle" mode: wide --- + The CLIPTextEncodeSD3 node processes text inputs for Stable Diffusion 3 models by encoding multiple text prompts using different CLIP models. It handles three separate text inputs (clip_g, clip_l, and t5xxl) and provides options for managing empty text padding. The node ensures proper token alignment between different text inputs and returns conditioning data suitable for SD3 generation pipelines. ## Inputs diff --git a/built-in-nodes/Canny.mdx b/built-in-nodes/Canny.mdx index 5ce44fbd0..6adcbc504 100755 --- a/built-in-nodes/Canny.mdx +++ b/built-in-nodes/Canny.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Canny" icon: "circle" mode: wide --- + Extract all edge lines from photos, like using a pen to outline a photo, drawing out the contours and detail boundaries of objects. ## Working Principle diff --git a/built-in-nodes/CaseConverter.mdx b/built-in-nodes/CaseConverter.mdx index e0eb106dc..b35bdce67 100644 --- a/built-in-nodes/CaseConverter.mdx +++ b/built-in-nodes/CaseConverter.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CaseConverter" icon: "circle" mode: wide --- + The Case Converter node transforms text strings into different letter case formats. It takes an input string and converts it based on the selected mode, producing an output string with the specified case formatting applied. The node supports four different case conversion options to modify the capitalization of your text. ## Inputs diff --git a/built-in-nodes/CenterCropImages.mdx b/built-in-nodes/CenterCropImages.mdx index 8f25c1955..5f0a23b1c 100644 --- a/built-in-nodes/CenterCropImages.mdx +++ b/built-in-nodes/CenterCropImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CenterCropImages" icon: "circle" mode: wide --- + The Center Crop Images node crops an image from its center to a specified width and height. It calculates the central region of the input image and extracts a rectangular area of the defined dimensions. If the requested crop size is larger than the image, the crop will be constrained to the image's boundaries. ## Inputs diff --git a/built-in-nodes/CheckpointLoader.mdx b/built-in-nodes/CheckpointLoader.mdx index 32b325706..511a1e47a 100644 --- a/built-in-nodes/CheckpointLoader.mdx +++ b/built-in-nodes/CheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointLoader" icon: "circle" mode: wide --- + The CheckpointLoader node loads a pre-trained model checkpoint along with its configuration file. It takes a configuration file and a checkpoint file as inputs and returns the loaded model components including the main model, CLIP model, and VAE model for use in the workflow. ## Inputs diff --git a/built-in-nodes/CheckpointLoaderSimple.mdx b/built-in-nodes/CheckpointLoaderSimple.mdx index a9efcfd93..005e5f49e 100755 --- a/built-in-nodes/CheckpointLoaderSimple.mdx +++ b/built-in-nodes/CheckpointLoaderSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointLoaderSimple" icon: "circle" mode: wide --- + ## Overview Loads a diffusion model checkpoint file and decomposes it into three core components: the main model used for denoising latents, the CLIP text encoder, and the VAE image encoder/decoder. This node automatically detects all model files in the `ComfyUI/models/checkpoints` folder and any additional paths configured in your `extra_model_paths.yaml` file. diff --git a/built-in-nodes/CheckpointSave.mdx b/built-in-nodes/CheckpointSave.mdx index 6b794a9c5..57343391f 100755 --- a/built-in-nodes/CheckpointSave.mdx +++ b/built-in-nodes/CheckpointSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointSave" icon: "circle" mode: wide --- + The `Save Checkpoint` node is designed to save a complete Stable Diffusion model (including UNet, CLIP, and VAE components) as a **.safetensors** format checkpoint file. The Save Checkpoint is primarily used in model merging workflows. After creating a new merged model through nodes like `ModelMergeSimple`, `ModelMergeBlocks`, etc., you can use this node to save the result as a reusable checkpoint file. diff --git a/built-in-nodes/ChromaRadianceOptions.mdx b/built-in-nodes/ChromaRadianceOptions.mdx index 572230ee5..a7b2b382c 100644 --- a/built-in-nodes/ChromaRadianceOptions.mdx +++ b/built-in-nodes/ChromaRadianceOptions.mdx @@ -5,27 +5,29 @@ sidebarTitle: "ChromaRadianceOptions" icon: "circle" mode: wide --- + The ChromaRadianceOptions node allows you to configure advanced settings for the Chroma Radiance model. It wraps an existing model and applies specific options during the denoising process based on sigma values, enabling fine-tuned control over NeRF tile size and other radiance-related parameters. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The model to apply Chroma Radiance options to | MODEL | Yes | - | | `preserve_wrapper` | When enabled, will delegate to an existing model function wrapper if it exists. Generally should be left enabled. (default: True) | BOOLEAN | No | - | | `start_sigma` | First sigma that these options will be in effect. (default: 1.0) | FLOAT | No | 0.0 to 1.0 | | `end_sigma` | Last sigma that these options will be in effect. (default: 0.0) | FLOAT | No | 0.0 to 1.0 | | `nerf_tile_size` | Allows overriding the default NeRF tile size. -1 means use the default (32). 0 means use non-tiling mode (may require a lot of VRAM). (default: -1) | INT | No | -1 and above | +| `force_sequential_txt_ids` | Force usage of sequential text token IDs instead of zeroes. Should be used for checkpoints from 2026-05-22 to 2026-06-01 that are trained in this way but do not contain the __sequential__ key in the state dict. (default: False) | BOOLEAN | No | - | -**Note:** The Chroma Radiance options only take effect when the current sigma value falls between `end_sigma` and `start_sigma` (inclusive). The `nerf_tile_size` parameter is only applied when set to 0 or higher values. +**Note:** The Chroma Radiance options only take effect when the current sigma value falls between `end_sigma` and `start_sigma` (inclusive). The `nerf_tile_size` parameter is only applied when set to 0 or higher values. The `force_sequential_txt_ids` parameter is only applied when set to True. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model` | The modified model with Chroma Radiance options applied | MODEL | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ChromaRadianceOptions/en.md) --- -**Source fingerprint (SHA-256):** `34e17791e3675c59b4a15b007e853eedcfa0cbbb975fb2f5e71d1115eb2b8781` +**Source fingerprint (SHA-256):** `4c93e4809e2948d633ccfc00460de470bdb125f7a2e9c3407f7dda178dd899b5` diff --git a/built-in-nodes/ClaudeNode.mdx b/built-in-nodes/ClaudeNode.mdx index 5244258f7..f3f3ac6f9 100644 --- a/built-in-nodes/ClaudeNode.mdx +++ b/built-in-nodes/ClaudeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ClaudeNode" icon: "circle" mode: wide --- + ## Overview Generate text responses from an Anthropic Claude model. This node sends a text prompt and optional images to a Claude model and returns the generated text response. @@ -12,7 +13,7 @@ Generate text responses from an Anthropic Claude model. This node sends a text p ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text input to the model. (default: empty string) | STRING | Yes | N/A | | `model` | The Claude model used to generate the response. | COMBO | Yes | `"Opus 4.7"`
`"Opus 4.6"`
`"Sonnet 4.6"`
`"Sonnet 4.5"`
`"Haiku 4.5"` | | `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) | INT | Yes | 0 to 2147483647 | @@ -28,10 +29,10 @@ Generate text responses from an Anthropic Claude model. This node sends a text p ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated text response from the Claude model. Returns "Empty response from Claude model." if no text is generated. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ClaudeNode/en.md) --- -**Source fingerprint (SHA-256):** `e3bab004535d4d406582aa42f28bb64a2988f8331788d51ec1fa4e943d8d4382` +**Source fingerprint (SHA-256):** `70fad3044edf9d1bc7cc82f3f6d89ca2d24857b039b829e7cc81265a7670430c` diff --git a/built-in-nodes/ClipLoader.mdx b/built-in-nodes/ClipLoader.mdx index bd923ec13..1fbaecfe2 100755 --- a/built-in-nodes/ClipLoader.mdx +++ b/built-in-nodes/ClipLoader.mdx @@ -5,14 +5,15 @@ sidebarTitle: "CLIPLoader" icon: "circle" mode: wide --- + The CLIPLoader node loads a text encoder model (CLIP, T5, or similar) from a file, making it available for use in other nodes that need to convert text prompts into numerical representations. It supports a wide variety of model architectures, each requiring a specific encoder type. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `clip_name` | The filename of the text encoder model to load. This must be a file located in the `ComfyUI/models/text_encoders/` or `ComfyUI/models/clip/` directory. | STRING | Yes | List of files found in the `text_encoders` folder | -| `type` | The architecture type of the model being loaded. This determines which specific encoder variant to use. The default is `"stable_diffusion"`. | STRING | Yes | `"stable_diffusion"`
`"stable_cascade"`
`"sd3"`
`"stable_audio"`
`"mochi"`
`"ltxv"`
`"pixart"`
`"cosmos"`
`"lumina2"`
`"wan"`
`"hidream"`
`"chroma"`
`"ace"`
`"omnigen2"`
`"qwen_image"`
`"hunyuan_image"`
`"flux2"`
`"ovis"`
`"longcat_image"`
`"cogvideox"` | +|-----------|-------------|-----------|----------|-------| +| `clip_name` | The filename of the text encoder model to load. This must be a file located in the `ComfyUI/models/text_encoders/` directory. | STRING | Yes | List of files found in the `text_encoders` folder | +| `type` | The architecture type of the model being loaded. This determines which specific encoder variant to use (default: `"stable_diffusion"`). | STRING | Yes | `"stable_diffusion"`
`"stable_cascade"`
`"sd3"`
`"stable_audio"`
`"mochi"`
`"ltxv"`
`"pixart"`
`"cosmos"`
`"lumina2"`
`"wan"`
`"hidream"`
`"chroma"`
`"ace"`
`"omnigen2"`
`"qwen_image"`
`"hunyuan_image"`
`"flux2"`
`"ovis"`
`"longcat_image"`
`"cogvideox"`
`"lens"`
`"pixeldit"`
`"ideogram4"` | | `device` | The device to load the model onto. `"default"` uses the GPU if available, while `"cpu"` forces CPU loading. This is an advanced option (default: `"default"`). | STRING | No | `"default"`
`"cpu"` | ### Supported Type-to-Encoder Mappings @@ -32,14 +33,16 @@ The `type` parameter selects the correct encoder for a given model architecture. | wan | umt5 xxl | | hidream | llama-3.1 (recommended) or t5 | | omnigen2 | qwen vl 2.5 3B | +| lens | gpt-oss-20b | +| pixeldit | gemma 2 2B elm | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `clip` | The loaded text encoder model, ready to be connected to other nodes for text encoding and conditioning. | CLIP | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPLoader/en.md) --- -**Source fingerprint (SHA-256):** `1051bfe5570dff81719682cb09938bae4c03e94e0e72f7a2be84867cccb48017` +**Source fingerprint (SHA-256):** `c6101104b4616b867ad228142bd758d1a3efa6c28deaf609a8d7bccdf8b2a6be` diff --git a/built-in-nodes/ClipMergeSimple.mdx b/built-in-nodes/ClipMergeSimple.mdx index 076964c4c..0601e6e7a 100755 --- a/built-in-nodes/ClipMergeSimple.mdx +++ b/built-in-nodes/ClipMergeSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeSimple" icon: "circle" mode: wide --- + `CLIPMergeSimple` is an advanced model merging node used to combine two CLIP text encoder models based on a specified ratio. This node specializes in merging two CLIP models based on a specified ratio, effectively blending their characteristics. It selectively applies patches from one model to another, excluding specific components like position IDs and logit scale, to create a hybrid model that combines features from both source models. diff --git a/built-in-nodes/ClipSave.mdx b/built-in-nodes/ClipSave.mdx index 883f7ca34..8e549b272 100755 --- a/built-in-nodes/ClipSave.mdx +++ b/built-in-nodes/ClipSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPSave" icon: "circle" mode: wide --- + The `CLIPSave` node saves a CLIP text encoder model to disk in SafeTensors format. It is designed for advanced model merging workflows and automatically separates the CLIP model into its component parts (such as CLIP-L, CLIP-G, or T5XXL) based on the model's internal structure, saving each component as a separate file. ## Inputs diff --git a/built-in-nodes/ClipSetLastLayer.mdx b/built-in-nodes/ClipSetLastLayer.mdx index 14835eead..04eabd0ad 100755 --- a/built-in-nodes/ClipSetLastLayer.mdx +++ b/built-in-nodes/ClipSetLastLayer.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPSetLastLayer" icon: "circle" mode: wide --- + `CLIP Set Last Layer` is a core node in ComfyUI for controlling the processing depth of CLIP models. It allows users to precisely control where the CLIP text encoder stops processing, affecting both the depth of text understanding and the style of generated images. Imagine the CLIP model as a 24-layer intelligent brain: diff --git a/built-in-nodes/ClipTextEncode.mdx b/built-in-nodes/ClipTextEncode.mdx index 939254c63..74202112d 100755 --- a/built-in-nodes/ClipTextEncode.mdx +++ b/built-in-nodes/ClipTextEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncode" icon: "circle" mode: wide --- + `CLIP Text Encode (CLIPTextEncode)` acts as a translator, converting your text descriptions into a format that AI can understand. This helps the AI interpret your input and generate the desired image. Think of it as communicating with an artist who speaks a different language. The CLIP model, trained on vast image-text pairs, bridges this gap by converting your descriptions into "instructions" that the AI model can follow. diff --git a/built-in-nodes/ClipTextEncodeFlux.mdx b/built-in-nodes/ClipTextEncodeFlux.mdx index 60a4b5dd5..93f762777 100644 --- a/built-in-nodes/ClipTextEncodeFlux.mdx +++ b/built-in-nodes/ClipTextEncodeFlux.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeFlux" icon: "circle" mode: wide --- + `CLIPTextEncodeFlux` is an advanced text encoding node designed for the Flux architecture. It processes two separate text inputs through different encoders—CLIP-L and T5XXL—and combines them with a guidance scale to produce a unified conditioning output for image generation. ## Inputs diff --git a/built-in-nodes/ClipTextEncodeHunyuanDit.mdx b/built-in-nodes/ClipTextEncodeHunyuanDit.mdx index faf707230..d4ec00674 100644 --- a/built-in-nodes/ClipTextEncodeHunyuanDit.mdx +++ b/built-in-nodes/ClipTextEncodeHunyuanDit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeHunyuanDiT" icon: "circle" mode: wide --- + The `CLIPTextEncodeHunyuanDiT` node converts text descriptions into a format that the HunyuanDiT model can understand. It is an advanced conditioning node designed for the dual text encoder architecture of HunyuanDiT, processing two separate text inputs through different tokenizers. ## Inputs diff --git a/built-in-nodes/ClipTextEncodeSdxl.mdx b/built-in-nodes/ClipTextEncodeSdxl.mdx index e26480c04..6861574fe 100755 --- a/built-in-nodes/ClipTextEncodeSdxl.mdx +++ b/built-in-nodes/ClipTextEncodeSdxl.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSDXL" icon: "circle" mode: wide --- + This node is designed to encode text input using a CLIP model specifically customized for the SDXL architecture. It uses a dual encoder system (CLIP-L and CLIP-G) to process text descriptions, resulting in more accurate image generation. ## Inputs diff --git a/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx b/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx index d47b0aed4..5d25941ea 100755 --- a/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx +++ b/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSDXLRefiner" icon: "circle" mode: wide --- + This node is specifically designed for the SDXL Refiner model to convert text prompts into conditioning information by incorporating aesthetic scores and dimensional information to enhance the conditions for generation tasks, thereby improving the final refinement effect. It acts like a professional art director, not only conveying your creative intent but also injecting precise aesthetic standards and specification requirements into the work. ## About SDXL Refiner diff --git a/built-in-nodes/ClipVisionEncode.mdx b/built-in-nodes/ClipVisionEncode.mdx index 92974be59..4fb342ebb 100755 --- a/built-in-nodes/ClipVisionEncode.mdx +++ b/built-in-nodes/ClipVisionEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPVisionEncode" icon: "circle" mode: wide --- + The `CLIP Vision Encode` node is an image encoding node in ComfyUI, used to convert input images into visual feature vectors through the CLIP Vision model. This node is an important bridge connecting image and text understanding, and is widely used in various AI image generation and processing workflows. **Node Functionality** diff --git a/built-in-nodes/ClipVisionLoader.mdx b/built-in-nodes/ClipVisionLoader.mdx index b6b67a6f7..bf202c0a5 100755 --- a/built-in-nodes/ClipVisionLoader.mdx +++ b/built-in-nodes/ClipVisionLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPVisionLoader" icon: "circle" mode: wide --- + This node automatically detects models located in the `ComfyUI/models/clip_vision` folder, as well as any additional model paths configured in the `extra_model_paths.yaml` file. If you add models after starting ComfyUI, please **refresh the ComfyUI interface** to ensure the latest model files are listed. ## Inputs diff --git a/built-in-nodes/ColorToRGBInt.mdx b/built-in-nodes/ColorToRGBInt.mdx index a8eb683a0..78501ade3 100644 --- a/built-in-nodes/ColorToRGBInt.mdx +++ b/built-in-nodes/ColorToRGBInt.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ColorToRGBInt" icon: "circle" mode: wide --- -The **ColorToRGBInt** node converts a color specified in hexadecimal format (like `#FF5733`) into a single integer value. It takes the red, green, and blue components from the color string and combines them into one RGB integer. + +The **ColorToRGBInt** node converts a color specified in hexadecimal format (like `#FF5733`) into a single integer value. It takes the red, green, and blue components from the color string and combines them into one RGB integer, while also returning the original hexadecimal representation. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `color` | A color value in the hexadecimal format `#RRGGBB`. Must be exactly 7 characters long and start with `#`. | STRING | Yes | N/A | **Note:** The input `color` string must follow the format `#RRGGBB` exactly. If the string is not 7 characters long or does not start with `#`, the node will raise an error. @@ -18,10 +19,11 @@ The **ColorToRGBInt** node converts a color specified in hexadecimal format (lik ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `rgb_int` | The calculated RGB integer value. This is derived from the formula: `(Red * 65536) + (Green * 256) + Blue`. | INT | +| `hex` | The original hexadecimal color string in the format `#RRGGBB`. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ColorToRGBInt/en.md) --- -**Source fingerprint (SHA-256):** `afbbdddb59eddf9e2cc8ab51765affff1676a589c2a2989ff90038ad0119dc9f` +**Source fingerprint (SHA-256):** `7ab6b8452b71d47e5b38d75c9b60d90d73c6b24e02d2c7d3694e05e1b2818edc` diff --git a/built-in-nodes/ColorTransfer.mdx b/built-in-nodes/ColorTransfer.mdx index 431201eb9..dccd9b663 100644 --- a/built-in-nodes/ColorTransfer.mdx +++ b/built-in-nodes/ColorTransfer.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ColorTransfer" icon: "circle" mode: wide --- + The ColorTransfer node adjusts the color palette of a target image to match the colors of a reference image. It uses different mathematical algorithms to analyze and transfer the color characteristics, such as brightness, contrast, and hue distribution, from the reference to the target. This is useful for creating visual consistency across multiple images or applying a specific color grade. ## Inputs diff --git a/built-in-nodes/CombineHooks.mdx b/built-in-nodes/CombineHooks.mdx index 961332156..159859ff9 100644 --- a/built-in-nodes/CombineHooks.mdx +++ b/built-in-nodes/CombineHooks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooks" icon: "circle" mode: wide --- + The Combine Hooks [2] node merges two hook groups into a single combined hook group. It takes two optional hook inputs and combines them using ComfyUI's hook combination functionality. This allows you to consolidate multiple hook configurations for streamlined processing. ## Inputs diff --git a/built-in-nodes/CombineHooksEight.mdx b/built-in-nodes/CombineHooksEight.mdx index 93783cadd..34f812f6d 100644 --- a/built-in-nodes/CombineHooksEight.mdx +++ b/built-in-nodes/CombineHooksEight.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooksEight" icon: "circle" mode: wide --- + The Combine Hooks [8] node merges up to eight different hook groups into a single combined hook group. It takes multiple hook inputs and combines them using ComfyUI's hook combination functionality. This allows you to consolidate multiple hook configurations for streamlined processing in advanced workflows. ## Inputs diff --git a/built-in-nodes/CombineHooksFour.mdx b/built-in-nodes/CombineHooksFour.mdx index cf18a5490..d9d220d30 100644 --- a/built-in-nodes/CombineHooksFour.mdx +++ b/built-in-nodes/CombineHooksFour.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooksFour" icon: "circle" mode: wide --- + The Combine Hooks [4] node merges up to four separate hook groups into a single combined hook group. It takes any combination of the four available hook inputs and combines them using ComfyUI's hook combination system. This allows you to consolidate multiple hook configurations for streamlined processing in advanced workflows. ## Inputs diff --git a/built-in-nodes/ComboOptionTestNode.mdx b/built-in-nodes/ComboOptionTestNode.mdx index 577af9c80..b07d99249 100644 --- a/built-in-nodes/ComboOptionTestNode.mdx +++ b/built-in-nodes/ComboOptionTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComboOptionTestNode" icon: "circle" mode: wide --- + The ComboOptionTestNode is a logic node designed to test and pass through combo box selections. It takes two combo box inputs, each with a predefined set of options, and outputs the selected values directly without modification. ## Inputs diff --git a/built-in-nodes/ComfyAndNode.mdx b/built-in-nodes/ComfyAndNode.mdx index 5f0fccb16..7e483a16c 100644 --- a/built-in-nodes/ComfyAndNode.mdx +++ b/built-in-nodes/ComfyAndNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyAndNode" icon: "circle" mode: wide --- + ## Overview The And node performs a logical AND operation on a set of input values. It returns `true` only if all of the provided values are considered truthy according to Python's truthiness rules. This node is useful for checking that multiple conditions are all met before proceeding. diff --git a/built-in-nodes/ComfyMathExpression.mdx b/built-in-nodes/ComfyMathExpression.mdx index dce8f3c26..83b053c63 100644 --- a/built-in-nodes/ComfyMathExpression.mdx +++ b/built-in-nodes/ComfyMathExpression.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ComfyMathExpression" icon: "circle" mode: wide --- + The ComfyMathExpression node evaluates a mathematical formula using a set of input values. You can write an expression using variable names (like `a`, `b`, `c`), and the node will calculate the result. It supports dynamically adding as many input values as needed for your calculation. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `expression` | The mathematical formula to evaluate. You can use variable names that correspond to the input values (default: "a + b"). | STRING | Yes | N/A | | `values` | A set of numeric or boolean inputs that can be dynamically added. Each input is assigned a letter from the alphabet (a, b, c, ...) to be used as a variable in the expression. At least one input value is required. | FLOAT, INT, BOOLEAN | No | N/A | @@ -23,7 +24,7 @@ The ComfyMathExpression node evaluates a mathematical formula using a set of inp ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `FLOAT` | The result of the mathematical expression as a floating-point number. | FLOAT | | `INT` | The result of the mathematical expression as an integer. | INT | | `BOOL` | The result of the mathematical expression as a boolean value. | BOOLEAN | @@ -31,4 +32,4 @@ The ComfyMathExpression node evaluates a mathematical formula using a set of inp > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfyMathExpression/en.md) --- -**Source fingerprint (SHA-256):** `bf6221a7e1e955bdb56482de0a86a782494b2775fdd2edfde9fd20a9df0fe1a7` +**Source fingerprint (SHA-256):** `d3b47ddb7bc40318d35ad09fb53793cea25e9a9b310ab47aaf937781e3ad2b73` diff --git a/built-in-nodes/ComfyNotNode.mdx b/built-in-nodes/ComfyNotNode.mdx index f2154296c..3c7bd0b37 100644 --- a/built-in-nodes/ComfyNotNode.mdx +++ b/built-in-nodes/ComfyNotNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyNotNode" icon: "circle" mode: wide --- + ## Overview The Not node performs a logical NOT operation on any input value. It returns True if the input value is considered falsy (like 0, empty string, None, False), and returns False if the input value is truthy. It uses Python's standard rules for determining truthiness. diff --git a/built-in-nodes/ComfyNumberConvert.mdx b/built-in-nodes/ComfyNumberConvert.mdx index 5ae2f4821..1edb09a29 100644 --- a/built-in-nodes/ComfyNumberConvert.mdx +++ b/built-in-nodes/ComfyNumberConvert.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyNumberConvert" icon: "circle" mode: wide --- + The Number Convert node transforms various input data types into numeric values. It accepts a single input of type integer, float, string, or boolean and produces two outputs: a floating-point number and an integer. This is useful for converting text or logical values into a format that can be used by other mathematical or processing nodes in your workflow. ## Inputs diff --git a/built-in-nodes/ComfyOrNode.mdx b/built-in-nodes/ComfyOrNode.mdx index 86e6c5fc4..9ec71308a 100644 --- a/built-in-nodes/ComfyOrNode.mdx +++ b/built-in-nodes/ComfyOrNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ComfyOrNode" icon: "circle" mode: wide --- -# ComfyOrNode The ComfyOrNode performs a logical OR operation on a set of input values. It returns `true` if any of the provided values are considered truthy according to Python's standard truthiness rules. diff --git a/built-in-nodes/ComfySoftSwitchNode.mdx b/built-in-nodes/ComfySoftSwitchNode.mdx index 3c6f555c3..f95dc378b 100644 --- a/built-in-nodes/ComfySoftSwitchNode.mdx +++ b/built-in-nodes/ComfySoftSwitchNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfySoftSwitchNode" icon: "circle" mode: wide --- + The Soft Switch node selects between two possible input values based on a boolean condition. It outputs the value from the `on_true` input when the `switch` is true, and the value from the `on_false` input when the `switch` is false. This node is designed to be lazy, meaning it only evaluates the input that is needed based on the switch state. ## Inputs diff --git a/built-in-nodes/ComfySwitchNode.mdx b/built-in-nodes/ComfySwitchNode.mdx index d3c230061..f8f0596f3 100644 --- a/built-in-nodes/ComfySwitchNode.mdx +++ b/built-in-nodes/ComfySwitchNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfySwitchNode" icon: "circle" mode: wide --- + The Switch node selects between two possible inputs based on a boolean condition. It outputs the `on_true` input when the `switch` is enabled, and the `on_false` input when the `switch` is disabled. This allows you to create conditional logic and choose different data paths in your workflow. ## Inputs diff --git a/built-in-nodes/ConditioningAverage.mdx b/built-in-nodes/ConditioningAverage.mdx index 02f77bc37..c49fade29 100644 --- a/built-in-nodes/ConditioningAverage.mdx +++ b/built-in-nodes/ConditioningAverage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningAverage" icon: "circle" mode: wide --- + The `ConditioningAverage` node is used to blend two different sets of conditioning (such as text prompts) according to a specified weight, generating a new conditioning vector that lies between the two. By adjusting the weight parameter, you can flexibly control the influence of each conditioning on the final result. This is especially suitable for prompt interpolation, style fusion, and other advanced use cases. As shown below, by adjusting the strength of `conditioning_to`, you can output a result between the two conditionings. diff --git a/built-in-nodes/ConditioningCombine.mdx b/built-in-nodes/ConditioningCombine.mdx index f36b6d19b..b49df5ae3 100644 --- a/built-in-nodes/ConditioningCombine.mdx +++ b/built-in-nodes/ConditioningCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningCombine" icon: "circle" mode: wide --- + This node combines two conditioning inputs into a single output, effectively merging their information. The two conditions are combined using list concatenation. ## Inputs diff --git a/built-in-nodes/ConditioningConcat.mdx b/built-in-nodes/ConditioningConcat.mdx index a1f8a5ada..d7ba8182b 100644 --- a/built-in-nodes/ConditioningConcat.mdx +++ b/built-in-nodes/ConditioningConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningConcat" icon: "circle" mode: wide --- + The ConditioningConcat node is designed to concatenate conditioning vectors, specifically merging the 'conditioning_from' vector into the 'conditioning_to' vector. This operation is fundamental in scenarios where the conditioning information from two sources needs to be combined into a single, unified representation. ## Inputs diff --git a/built-in-nodes/ConditioningMultiply.mdx b/built-in-nodes/ConditioningMultiply.mdx new file mode 100644 index 000000000..a4b301494 --- /dev/null +++ b/built-in-nodes/ConditioningMultiply.mdx @@ -0,0 +1,27 @@ +--- +title: "ConditioningMultiply - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConditioningMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConditioningMultiply" +icon: "circle" +mode: wide +--- + +This node multiplies the conditioning values by a specified factor, allowing you to scale the influence of the conditioning on the generation process. It works by applying the multiplier to both the main conditioning tensor and the pooled output values. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `conditioning` | The conditioning data to be scaled | CONDITIONING | Yes | - | +| `multiplier` | The factor to multiply the conditioning values by (default: 1.0) | FLOAT | Yes | -100.0 to 100.0 (step: 0.01) | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `CONDITIONING` | The scaled conditioning data with multiplied values | CONDITIONING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningMultiply/en.md) + +--- +**Source fingerprint (SHA-256):** `8d241e3d5d91e513c24ade5b4bece4bf879fe093a4be6d53dab11a5a0bf55616` diff --git a/built-in-nodes/ConditioningSetArea.mdx b/built-in-nodes/ConditioningSetArea.mdx index 94eb2f6d0..2ad0f6e6c 100644 --- a/built-in-nodes/ConditioningSetArea.mdx +++ b/built-in-nodes/ConditioningSetArea.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetArea" icon: "circle" mode: wide --- + This node is designed to modify the conditioning information by setting specific areas within the conditioning context. It allows for the precise spatial manipulation of conditioning elements, enabling targeted adjustments and enhancements based on specified dimensions and strength. ## Inputs diff --git a/built-in-nodes/ConditioningSetAreaPercentage.mdx b/built-in-nodes/ConditioningSetAreaPercentage.mdx index cd73ace1c..ef6f90335 100644 --- a/built-in-nodes/ConditioningSetAreaPercentage.mdx +++ b/built-in-nodes/ConditioningSetAreaPercentage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaPercentage" icon: "circle" mode: wide --- + The ConditioningSetAreaPercentage node specializes in adjusting the area of influence for conditioning elements based on percentage values. It allows for the specification of the area's dimensions and position as percentages of the total image size, alongside a strength parameter to modulate the intensity of the conditioning effect. ## Inputs diff --git a/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx b/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx index 8b880ffba..8cd197e77 100644 --- a/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx +++ b/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaPercentageVideo" icon: "circle" mode: wide --- + The ConditioningSetAreaPercentageVideo node modifies conditioning data by defining a specific area and temporal region for video generation. It allows you to set the position, size, and duration of the area where the conditioning will be applied using percentage values relative to the overall dimensions. This is useful for focusing the generation on specific parts of a video sequence. ## Inputs diff --git a/built-in-nodes/ConditioningSetAreaStrength.mdx b/built-in-nodes/ConditioningSetAreaStrength.mdx index d3ac86b0f..2f70a862f 100644 --- a/built-in-nodes/ConditioningSetAreaStrength.mdx +++ b/built-in-nodes/ConditioningSetAreaStrength.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaStrength" icon: "circle" mode: wide --- + This node is designed to modify the strength attribute of a given conditioning set, allowing for the adjustment of the influence or intensity of the conditioning on the generation process. ## Inputs diff --git a/built-in-nodes/ConditioningSetDefaultAndCombine.mdx b/built-in-nodes/ConditioningSetDefaultAndCombine.mdx index 77931390b..7c585b8ae 100644 --- a/built-in-nodes/ConditioningSetDefaultAndCombine.mdx +++ b/built-in-nodes/ConditioningSetDefaultAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetDefaultAndCombine" icon: "circle" mode: wide --- + This node combines a primary conditioning input with a default conditioning input using a hook-based system. It merges the two conditioning sources into a single output, allowing the default conditioning to serve as a fallback or base when the primary conditioning is incomplete. ## Inputs diff --git a/built-in-nodes/ConditioningSetMask.mdx b/built-in-nodes/ConditioningSetMask.mdx index 58c330652..1fcd60b7e 100644 --- a/built-in-nodes/ConditioningSetMask.mdx +++ b/built-in-nodes/ConditioningSetMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetMask" icon: "circle" mode: wide --- + This node is designed to modify the conditioning of a generative model by applying a mask with a specified strength to certain areas. It allows for targeted adjustments within the conditioning, enabling more precise control over the generation process. ## Inputs diff --git a/built-in-nodes/ConditioningSetProperties.mdx b/built-in-nodes/ConditioningSetProperties.mdx index 399f823c1..7179766d8 100644 --- a/built-in-nodes/ConditioningSetProperties.mdx +++ b/built-in-nodes/ConditioningSetProperties.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetProperties" icon: "circle" mode: wide --- + The ConditioningSetProperties node modifies the properties of conditioning data by adjusting strength, area settings, and applying optional masks, hooks, or timestep ranges. It allows you to control how conditioning influences the generation process by setting specific parameters that affect the application of conditioning data during image generation. ## Inputs diff --git a/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx b/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx index 6988da35d..192db26ea 100644 --- a/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx +++ b/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetPropertiesAndCombine" icon: "circle" mode: wide --- + The ConditioningSetPropertiesAndCombine node modifies conditioning data by applying properties from a new conditioning input to an existing conditioning input. It combines the two conditioning sets while controlling the strength of the new conditioning and specifying how the conditioning area should be applied. ## Inputs diff --git a/built-in-nodes/ConditioningSetTimestepRange.mdx b/built-in-nodes/ConditioningSetTimestepRange.mdx index 38226f9ee..080fe72c0 100644 --- a/built-in-nodes/ConditioningSetTimestepRange.mdx +++ b/built-in-nodes/ConditioningSetTimestepRange.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetTimestepRange" icon: "circle" mode: wide --- + This node is designed to adjust the temporal aspect of conditioning by setting a specific range of timesteps. It allows for the precise control over the start and end points of the conditioning process, enabling more targeted and efficient generation. ## Inputs diff --git a/built-in-nodes/ConditioningStableAudio.mdx b/built-in-nodes/ConditioningStableAudio.mdx index f02f4e175..2afbdadc7 100644 --- a/built-in-nodes/ConditioningStableAudio.mdx +++ b/built-in-nodes/ConditioningStableAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningStableAudio" icon: "circle" mode: wide --- + The ConditioningStableAudio node adds timing information to both positive and negative conditioning inputs for audio generation. It sets the start time and total duration parameters that help control when and how long audio content should be generated. This node modifies existing conditioning data by appending audio-specific timing metadata. ## Inputs diff --git a/built-in-nodes/ConditioningTimestepsRange.mdx b/built-in-nodes/ConditioningTimestepsRange.mdx index 125136207..d3767ce12 100644 --- a/built-in-nodes/ConditioningTimestepsRange.mdx +++ b/built-in-nodes/ConditioningTimestepsRange.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningTimestepsRange" icon: "circle" mode: wide --- + The ConditioningTimestepsRange node creates three distinct timestep ranges for controlling when conditioning effects are applied during the generation process. It takes start and end percentage values and divides the entire timestep range (0.0 to 1.0) into three segments: the main range between the specified percentages, the range before the start percentage, and the range after the end percentage. ## Inputs diff --git a/built-in-nodes/ConditioningZeroOut.mdx b/built-in-nodes/ConditioningZeroOut.mdx index b6dcfbc60..5531302c2 100644 --- a/built-in-nodes/ConditioningZeroOut.mdx +++ b/built-in-nodes/ConditioningZeroOut.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningZeroOut" icon: "circle" mode: wide --- + This node zeroes out specific elements within the conditioning data structure, effectively neutralizing their influence in subsequent processing steps. It's designed for advanced conditioning operations where direct manipulation of the conditioning's internal representation is required. ## Inputs diff --git a/built-in-nodes/ContextWindowsManual.mdx b/built-in-nodes/ContextWindowsManual.mdx index 8d1b8c925..be6f11ce0 100644 --- a/built-in-nodes/ContextWindowsManual.mdx +++ b/built-in-nodes/ContextWindowsManual.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ContextWindowsManual" icon: "circle" mode: wide --- + The Context Windows (Manual) node allows you to manually configure context windows for models during sampling. It creates overlapping context segments with specified length, overlap, and scheduling patterns to process data in manageable chunks while maintaining continuity between segments. This node provides advanced options for controlling how context windows are applied, including noise shuffling, conditioning retention, and causal window fixes. ## Inputs diff --git a/built-in-nodes/ControlNetApply.mdx b/built-in-nodes/ControlNetApply.mdx index 3d88d409d..fb502d1c6 100644 --- a/built-in-nodes/ControlNetApply.mdx +++ b/built-in-nodes/ControlNetApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApply" icon: "circle" mode: wide --- + Using controlNet requires preprocessing of input images. Since ComfyUI initial nodes do not come with preprocessors and controlNet models, please first install ControlNet preprocessors [download preprocessors here](https://github.com/Fannovel16/comfy_controlnet_preprocessors) and corresponding controlNet models. ## Inputs diff --git a/built-in-nodes/ControlNetApplyAdvanced.mdx b/built-in-nodes/ControlNetApplyAdvanced.mdx index 58f746d5e..b78b34792 100644 --- a/built-in-nodes/ControlNetApplyAdvanced.mdx +++ b/built-in-nodes/ControlNetApplyAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApplyAdvanced" icon: "circle" mode: wide --- + This node applies advanced control net transformations to conditioning data based on an image and a control net model. It allows for fine-tuned adjustments of the control net's influence over the generated content, enabling more precise and varied modifications to the conditioning. ## Inputs diff --git a/built-in-nodes/ControlNetApplySD3.mdx b/built-in-nodes/ControlNetApplySD3.mdx index 1f3073434..976374535 100644 --- a/built-in-nodes/ControlNetApplySD3.mdx +++ b/built-in-nodes/ControlNetApplySD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApplySD3" icon: "circle" mode: wide --- + This node applies ControlNet guidance to Stable Diffusion 3 conditioning. It takes positive and negative conditioning inputs along with a ControlNet model and image, then applies the control guidance with adjustable strength and timing parameters to influence the generation process. **Note:** This node has been marked as deprecated and may be removed in future versions. diff --git a/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx b/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx index 7b83edf52..716c8c6e1 100644 --- a/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx +++ b/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetInpaintingAliMamaApply" icon: "circle" mode: wide --- + The ControlNetInpaintingAliMamaApply node applies ControlNet conditioning for inpainting tasks by combining positive and negative conditioning with a control image and mask. It processes the input image and mask to create modified conditioning that guides the generation process, allowing for precise control over which areas of the image are inpainted. The node supports strength adjustment and timing controls to fine-tune the ControlNet's influence during different stages of the generation process. ## Inputs diff --git a/built-in-nodes/ControlNetLoader.mdx b/built-in-nodes/ControlNetLoader.mdx index 428f8f2f0..2eb27bf57 100644 --- a/built-in-nodes/ControlNetLoader.mdx +++ b/built-in-nodes/ControlNetLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetLoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/controlnet` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. The ControlNetLoader node is designed to load a ControlNet model from a specified path. It plays a crucial role in initializing ControlNet models, which are essential for applying control mechanisms over generated content or modifying existing content based on control signals. diff --git a/built-in-nodes/ConvertArrayToString.mdx b/built-in-nodes/ConvertArrayToString.mdx new file mode 100644 index 000000000..3ebabd9dc --- /dev/null +++ b/built-in-nodes/ConvertArrayToString.mdx @@ -0,0 +1,27 @@ +--- +title: "ConvertArrayToString - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConvertArrayToString node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConvertArrayToString" +icon: "circle" +mode: wide +--- + +The Convert Array to String node takes an array (list) of items and converts it into a formatted JSON string. This is useful when you need to serialize array data for display, logging, or passing to other systems that expect string input. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `array` | The array to convert to a JSON string | ARRAY | Yes | - | +| `indent` | Spaces per indent level. 0 produces compact single-line string (default: 2) | INT | No | 0 to 8 | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `STRING` | The array converted to a JSON-formatted string | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertArrayToString/en.md) + +--- +**Source fingerprint (SHA-256):** `ac8397fed0336f546403ee3e1f17d7e8f5973190b102e74943f098bf6905f726` diff --git a/built-in-nodes/ConvertDictionaryToString.mdx b/built-in-nodes/ConvertDictionaryToString.mdx new file mode 100644 index 000000000..ffcc8cc22 --- /dev/null +++ b/built-in-nodes/ConvertDictionaryToString.mdx @@ -0,0 +1,27 @@ +--- +title: "ConvertDictionaryToString - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConvertDictionaryToString node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConvertDictionaryToString" +icon: "circle" +mode: wide +--- + +This node converts a dictionary (a collection of key-value pairs) into a text string in JSON format. You can control the indentation level to make the output more readable or compact. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `dictionary` | The dictionary to convert to a string | DICT | Yes | - | +| `indent` | Spaces per indent level. 0 produces compact single-line string (default: 2) | INT | No | 0 to 8 | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `STRING` | The dictionary converted to a JSON-formatted string | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertDictionaryToString/en.md) + +--- +**Source fingerprint (SHA-256):** `ae4e9889d5347acfc69166bac66f2ba63f5cd37dafab25a9e0aff6bfe7381219` diff --git a/built-in-nodes/ConvertStringToComboNode.mdx b/built-in-nodes/ConvertStringToComboNode.mdx index 3a0b571b1..5faa9eca5 100644 --- a/built-in-nodes/ConvertStringToComboNode.mdx +++ b/built-in-nodes/ConvertStringToComboNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConvertStringToComboNode" icon: "circle" mode: wide --- + The Convert String to Combo node takes a text string as input and converts it into a Combo data type. This allows you to use a text value as a selection for other nodes that require a Combo input. It simply passes the string value through unchanged but changes its data type. ## Inputs diff --git a/built-in-nodes/CosmosImageToVideoLatent.mdx b/built-in-nodes/CosmosImageToVideoLatent.mdx index ee416c75e..f3c443558 100644 --- a/built-in-nodes/CosmosImageToVideoLatent.mdx +++ b/built-in-nodes/CosmosImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CosmosImageToVideoLatent" icon: "circle" mode: wide --- + The CosmosImageToVideoLatent node creates video latent representations from input images. It generates a blank video latent and optionally encodes start and/or end images into the beginning and/or end frames of the video sequence. When images are provided, it also creates corresponding noise masks to indicate which parts of the latent should be preserved during generation. ## Inputs diff --git a/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx b/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx index 3e63c9fb7..142acab79 100644 --- a/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx +++ b/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CosmosPredict2ImageToVideoLatent" icon: "circle" mode: wide --- + The CosmosPredict2ImageToVideoLatent node creates video latent representations from images for video generation. It can generate a blank video latent or incorporate start and end images to create video sequences with specified dimensions and duration. The node handles the encoding of images into the appropriate latent space format for video processing. ## Inputs diff --git a/built-in-nodes/CreateBoundingBoxes.mdx b/built-in-nodes/CreateBoundingBoxes.mdx new file mode 100644 index 000000000..873dff641 --- /dev/null +++ b/built-in-nodes/CreateBoundingBoxes.mdx @@ -0,0 +1,31 @@ +--- +title: "CreateBoundingBoxes - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the CreateBoundingBoxes node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "CreateBoundingBoxes" +icon: "circle" +mode: wide +--- + +This node provides a canvas interface for drawing bounding boxes around objects or text regions in an image. It outputs the bounding box coordinates in pixel space, structured element data compatible with Ideogram prompt formatting, and a preview image showing the drawn boxes with labels and color palettes. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `background` | Optional image used as background in the canvas and preview. | IMAGE | No | - | +| `width` | Width of the canvas and the pixel grid for the bounding boxes (default: 1024). | INT | Yes | 64 to 16384 (step: 16) | +| `height` | Height of the canvas and the pixel grid for the bounding boxes (default: 1024). | INT | Yes | 64 to 16384 (step: 16) | +| `editor_state` | Draw bounding boxes and set each box type, text, description, color palette. Start with background element first and foreground last. | BOUNDING_BOXES | Yes | - | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `preview` | An RGB image showing the canvas with all bounding boxes rendered, including labels, color palette swatches, and descriptive text. | IMAGE | +| `bboxes` | A list of bounding boxes in pixel coordinates, with each box containing x, y, width, and height values. | BOUNDING_BOX | +| `elements` | A structured array of element objects, each containing type, bounding box coordinates (normalized 0-1000), text (for text type), description, and color palette. | ARRAY | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateBoundingBoxes/en.md) + +--- +**Source fingerprint (SHA-256):** `a63939f13edc6c6507590a390dcd6d0a3321febb5831baab1655d9952228612c` diff --git a/built-in-nodes/CreateCameraInfo.mdx b/built-in-nodes/CreateCameraInfo.mdx index 87a20f4ad..9c91680c2 100644 --- a/built-in-nodes/CreateCameraInfo.mdx +++ b/built-in-nodes/CreateCameraInfo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateCameraInfo" icon: "circle" mode: wide --- -# Create Camera Info The Create Camera Info node builds a camera information structure for 3D rendering. It supports three modes for defining the camera: orbit (yaw/pitch/distance around a target), look_at (explicit world position), and quaternion (position plus rotation). The coordinate system is right-handed with Y as the up axis. diff --git a/built-in-nodes/CreateHookKeyframe.mdx b/built-in-nodes/CreateHookKeyframe.mdx index 71b39c0fe..e9672f490 100644 --- a/built-in-nodes/CreateHookKeyframe.mdx +++ b/built-in-nodes/CreateHookKeyframe.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframe" icon: "circle" mode: wide --- + The Create Hook Keyframe node allows you to define specific points in a generation process where hook behavior changes. It creates keyframes that modify the strength of hooks at particular percentages of the generation progress, and these keyframes can be chained together to create complex scheduling patterns. ## Inputs diff --git a/built-in-nodes/CreateHookKeyframesFromFloats.mdx b/built-in-nodes/CreateHookKeyframesFromFloats.mdx index dbd33217d..534221034 100644 --- a/built-in-nodes/CreateHookKeyframesFromFloats.mdx +++ b/built-in-nodes/CreateHookKeyframesFromFloats.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframesFromFloats" icon: "circle" mode: wide --- + This node creates hook keyframes from a list of floating-point strength values, distributing them evenly between specified start and end percentages. It generates a sequence of keyframes where each strength value is assigned to a specific percentage position in the animation timeline. The node can either create a new keyframe group or add to an existing one, with an option to print the generated keyframes for debugging purposes. ## Inputs diff --git a/built-in-nodes/CreateHookKeyframesInterpolated.mdx b/built-in-nodes/CreateHookKeyframesInterpolated.mdx index e51cccce8..42f786a8a 100644 --- a/built-in-nodes/CreateHookKeyframesInterpolated.mdx +++ b/built-in-nodes/CreateHookKeyframesInterpolated.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframesInterpolated" icon: "circle" mode: wide --- + Creates a sequence of hook keyframes with interpolated strength values between a start and end point. The node generates multiple keyframes that smoothly transition the strength parameter across a specified percentage range of the generation process, using various interpolation methods to control the transition curve. ## Inputs diff --git a/built-in-nodes/CreateHookLora.mdx b/built-in-nodes/CreateHookLora.mdx index 0f016ecff..82d104d4d 100644 --- a/built-in-nodes/CreateHookLora.mdx +++ b/built-in-nodes/CreateHookLora.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookLora" icon: "circle" mode: wide --- + The Create Hook LoRA node generates hook objects for applying LoRA (Low-Rank Adaptation) modifications to models. It loads a specified LoRA file and creates hooks that can adjust model and CLIP strengths, then combines these hooks with any existing hooks passed to it. The node efficiently manages LoRA loading by caching previously loaded LoRA files to avoid redundant operations. ## Inputs diff --git a/built-in-nodes/CreateHookLoraModelOnly.mdx b/built-in-nodes/CreateHookLoraModelOnly.mdx index d5ffffac6..4e3f1a3a1 100644 --- a/built-in-nodes/CreateHookLoraModelOnly.mdx +++ b/built-in-nodes/CreateHookLoraModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookLoraModelOnly" icon: "circle" mode: wide --- + This node creates a LoRA (Low-Rank Adaptation) hook that applies only to the model component, leaving the CLIP component completely unchanged. It loads a LoRA file and applies it with a specified strength to the model while setting the CLIP strength to zero. The node can be chained with previous hooks to build complex modification pipelines. ## Inputs diff --git a/built-in-nodes/CreateHookModelAsLora.mdx b/built-in-nodes/CreateHookModelAsLora.mdx index 2b2fe1e3a..3e68b8502 100644 --- a/built-in-nodes/CreateHookModelAsLora.mdx +++ b/built-in-nodes/CreateHookModelAsLora.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookModelAsLora" icon: "circle" mode: wide --- + This node creates a hook model as a LoRA (Low-Rank Adaptation) by loading checkpoint weights and applying strength adjustments to both the model and CLIP components. It allows you to apply LoRA-style modifications to existing models through a hook-based approach, enabling fine-tuning and adaptation without permanent model changes. The node can combine with previous hooks and caches loaded weights for efficiency. ## Inputs diff --git a/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx b/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx index 4661ecee0..94737c6de 100644 --- a/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx +++ b/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookModelAsLoraModelOnly" icon: "circle" mode: wide --- + This node creates a hook that applies a LoRA (Low-Rank Adaptation) model to modify only the model component of a neural network. It loads a checkpoint file and applies it with a specified strength to the model while leaving the CLIP component unchanged. This is an experimental node that extends the functionality of the base CreateHookModelAsLora class. ## Inputs diff --git a/built-in-nodes/CreateList.mdx b/built-in-nodes/CreateList.mdx index 20d832e27..3da86baf3 100644 --- a/built-in-nodes/CreateList.mdx +++ b/built-in-nodes/CreateList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateList" icon: "circle" mode: wide --- + The Create List node combines multiple inputs into a single, sequential list. It takes any number of inputs of the same data type and concatenates them in the order they are connected. This node is useful for preparing batches of data, such as images or text, to be processed by other nodes in a workflow. ## Inputs diff --git a/built-in-nodes/CreateVideo.mdx b/built-in-nodes/CreateVideo.mdx index e4b150cae..9a47f139b 100644 --- a/built-in-nodes/CreateVideo.mdx +++ b/built-in-nodes/CreateVideo.mdx @@ -5,23 +5,25 @@ sidebarTitle: "CreateVideo" icon: "circle" mode: wide --- + The Create Video node generates a video file from a sequence of images. You can specify the playback speed using frames per second and optionally add audio to the video. The node combines your images into a video format that can be played back with the specified frame rate. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `images` | The images to create a video from. | IMAGE | Yes | - | | `fps` | The frames per second for the video playback speed (default: 30.0). | FLOAT | Yes | 1.0 - 120.0 | | `audio` | The audio to add to the video. | AUDIO | No | - | +| `bit_depth` | Bit depth of the created video. 10-bit keeps smoother gradients with less banding, but some players and downstream nodes may not support it (default: 8). | INT | No | 8 - 10 | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file containing the input images and optional audio. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateVideo/en.md) --- -**Source fingerprint (SHA-256):** `b3effbbc380a3841ffbedd3c9561e783bc9f9a7887edc8965c38992cb370a812` +**Source fingerprint (SHA-256):** `7d9484da73946ee69608e16608307de7334a8f920b5c5ec5c7a6f227934e3318` diff --git a/built-in-nodes/CropByBBoxes.mdx b/built-in-nodes/CropByBBoxes.mdx index 4f80c49cf..7ec127214 100644 --- a/built-in-nodes/CropByBBoxes.mdx +++ b/built-in-nodes/CropByBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CropByBBoxes" icon: "circle" mode: wide --- + The CropByBBoxes node extracts and resizes specific rectangular regions from an input image batch. It uses provided bounding box coordinates to define the area to crop from each image. The cropped regions are then resized to a specified output dimension, with options to either stretch the crop or pad it to preserve its original aspect ratio. ## Inputs diff --git a/built-in-nodes/CropMask.mdx b/built-in-nodes/CropMask.mdx index 4064e5ec8..56b707778 100644 --- a/built-in-nodes/CropMask.mdx +++ b/built-in-nodes/CropMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CropMask" icon: "circle" mode: wide --- + The CropMask node is designed for cropping a specified area from a given mask. It allows users to define the region of interest by specifying coordinates and dimensions, effectively extracting a portion of the mask for further processing or analysis. ## Inputs diff --git a/built-in-nodes/CurveEditor.mdx b/built-in-nodes/CurveEditor.mdx index 12dd89451..42eea2add 100644 --- a/built-in-nodes/CurveEditor.mdx +++ b/built-in-nodes/CurveEditor.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CurveEditor" icon: "circle" mode: wide --- + The Curve Editor node provides a visual interface for adjusting and fine-tuning a curve. It allows you to modify the shape of an input curve and optionally visualize its distribution with a histogram. The node outputs the modified curve for use in other parts of your workflow. ## Inputs diff --git a/built-in-nodes/CustomCombo.mdx b/built-in-nodes/CustomCombo.mdx index 93be7f735..b3e5e5f44 100644 --- a/built-in-nodes/CustomCombo.mdx +++ b/built-in-nodes/CustomCombo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CustomCombo" icon: "circle" mode: wide --- + The Custom Combo node allows you to create a custom dropdown menu with your own list of text options. It is a frontend-focused node that provides a backend representation to ensure compatibility within your workflow. When you select an option from the dropdown, the node outputs that text as a string and its index position. ## Inputs diff --git a/built-in-nodes/DA3GeometryToMesh.mdx b/built-in-nodes/DA3GeometryToMesh.mdx new file mode 100644 index 000000000..4a916d972 --- /dev/null +++ b/built-in-nodes/DA3GeometryToMesh.mdx @@ -0,0 +1,32 @@ +--- +title: "DA3GeometryToMesh - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3GeometryToMesh node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3GeometryToMesh" +icon: "circle" +mode: wide +--- + +This node converts a DA3_GEOMETRY packet into a 3D mesh by unprojecting the depth map and triangulating the resulting point cloud. It processes a single image from a batch and produces a textured or untextured mesh suitable for 3D rendering. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | The DA3_GEOMETRY packet containing depth map, optional confidence map, optional sky map, and source image | DA3_GEOMETRY | Yes | - | +| `batch_index` | Which image of a batch to convert. Per-image vertex counts differ so batches cannot be stacked (default: 0) | INT | Yes | 0 to 4096 | +| `decimation` | Vertex stride. 1 = full resolution, 2 = half, etc. (default: 1) | INT | Yes | 1 to 8 | +| `discontinuity_threshold` | Drop triangles whose 3x3 depth span exceeds this fraction. 0 = off (default: 0.04) | FLOAT | Yes | 0.0 to 1.0 | +| `confidence_threshold` | Exclude pixels whose per-image normalised confidence is below this value. 0 = keep all, 1 = keep only the single most confident pixel. Used when the geometry has a confidence map (Small/Base models) (default: 0.1) | FLOAT | Yes | 0.0 to 1.0 | +| `use_sky_mask` | Exclude sky-probability pixels (sky >= 0.5) from the mesh. Used when the geometry has a sky map (Mono/Metric models) (default: True) | BOOLEAN | Yes | True or False | +| `texture` | Use the source image as a base color texture (default: True) | BOOLEAN | Yes | True or False | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `MESH` | A triangulated 3D mesh with vertices, faces, UV coordinates, and optional texture | MESH | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToMesh/en.md) + +--- +**Source fingerprint (SHA-256):** `1d311223a8d131030bcd4930d21852a21ac9dd5758e7f8b8d20b1cf68698893b` diff --git a/built-in-nodes/DA3GeometryToPointCloud.mdx b/built-in-nodes/DA3GeometryToPointCloud.mdx new file mode 100644 index 000000000..5c0c1d763 --- /dev/null +++ b/built-in-nodes/DA3GeometryToPointCloud.mdx @@ -0,0 +1,30 @@ +--- +title: "DA3GeometryToPointCloud - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3GeometryToPointCloud node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3GeometryToPointCloud" +icon: "circle" +mode: wide +--- + +This node converts a depth map from a DA3_GEOMETRY object into a 3D point cloud. It applies filtering based on confidence and sky masks, and transforms the points into a common world coordinate system suitable for multi-view scenes. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | The DA3_GEOMETRY object containing depth data and optional image, confidence, and sky maps | DA3_GEOMETRY | Yes | - | +| `batch_index` | Which image of a batch to convert (default: 0) | INT | Yes | 0 to 4096 | +| `confidence_threshold` | Exclude pixels whose per-image normalised confidence is below this value (0 = keep all). Used when the geometry has a confidence map (Small/Base models). (default: 0.1) | FLOAT | Yes | 0.0 to 1.0 | +| `use_sky_mask` | Exclude sky-probability pixels (sky >= 0.5). Used when the geometry has a sky map (Mono/Metric models). (default: True) | BOOLEAN | Yes | True or False | +| `downsample` | Take every Nth pixel (1 = full resolution). Higher values give fewer points and faster processing. (default: 1) | INT | Yes | 1 to 16 | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `point_cloud` | A point cloud object containing filtered 3D points, optional colors, and optional confidence values | DA3_POINT_CLOUD | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToPointCloud/en.md) + +--- +**Source fingerprint (SHA-256):** `3cf5bdbb8afdfcfc02f9832a8cbc5a3df49da755dea6df01792aa6ef9e5d7287` diff --git a/built-in-nodes/DA3Inference.mdx b/built-in-nodes/DA3Inference.mdx new file mode 100644 index 000000000..d3aa32ae3 --- /dev/null +++ b/built-in-nodes/DA3Inference.mdx @@ -0,0 +1,38 @@ +--- +title: "DA3Inference - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3Inference node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3Inference" +icon: "circle" +mode: wide +--- + +This node runs the Depth Anything 3 model on an image to estimate depth and geometry information. In multi-view mode, multiple images are processed together as separate views of the same scene to produce geometrically consistent depth maps and camera poses. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `da3_model` | The Depth Anything 3 model to use for inference | DA3_MODEL | Yes | - | +| `image` | Input image or images to process | IMAGE | Yes | - | +| `resolution` | Resolution the model runs at (longest side, multiple of 14). Lower values are faster and use less VRAM. Higher values produce more detail. The output is upsampled back to the original size (default: 504) | INT | Yes | 140 to 2520 (step: 14) | +| `resize_method` | upper_bound_resize: scale so the longest side equals the resolution (caps memory, default). lower_bound_resize: scale so the shortest side equals the resolution (preserves more detail on tall/wide images, uses more memory) | COMBO | Yes | `"upper_bound_resize"`
`"lower_bound_resize"` | +| `mode` | mono: single view image processing (works with any model variant). multiview: all images processed together for geometric consistency and camera pose estimation (for Small and Base models only) | COMBO | Yes | `"mono"`
`"multiview"` | +| `ref_view_strategy` | Which view acts as the geometric anchor in multi-view mode. saddle_balanced: the view most average across all others (best general choice). saddle_sim_range: the view most visually distinct from the others. first / middle: fixed positional picks (default: saddle_balanced) | COMBO | No (conditional) | `"saddle_balanced"`
`"saddle_sim_range"`
`"first"`
`"middle"` | +| `pose_method` | How the camera field-of-view is estimated (for Small and Base models only). cam_dec: learned from image features. ray_pose: derived geometrically from the model's 3D ray output. Affects perspective correctness of the 3D output (default: cam_dec) | COMBO | No (conditional) | `"cam_dec"`
`"ray_pose"` | + +**Notes on parameter constraints:** +- The `ref_view_strategy` and `pose_method` parameters are only available when `mode` is set to `"multiview"` +- Multi-view mode requires a Small or Base model variant. Models with other head types (such as Metric or Mono) do not support cross-view attention or camera pose estimation +- When `pose_method` is set to `"cam_dec"`, the model must have a camera decoder. If set to `"ray_pose"`, the model must have a DualDPT head +- If the selected `pose_method` is not compatible with the loaded model, an error will be raised + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `da3_geometry` | Dictionary of non-normalized tensors. Always contains the keys: depth, image, mode. Optional keys include: sky (for Mono/Metric models), confidence (for Small/Base models), extrinsics and intrinsics (for multi-view mode) | DA3_GEOMETRY | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3Inference/en.md) + +--- +**Source fingerprint (SHA-256):** `e91dd47e6a01719cdd6b6ce8a9bcc45933cac72c5e147ac42906d2f83ab7c250` diff --git a/built-in-nodes/DA3Render.mdx b/built-in-nodes/DA3Render.mdx new file mode 100644 index 000000000..f0413e2de --- /dev/null +++ b/built-in-nodes/DA3Render.mdx @@ -0,0 +1,54 @@ +--- +title: "DA3Render - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3Render node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3Render" +icon: "circle" +mode: wide +--- + +This node renders a visualization from Depth Anything 3 geometry data. It can output depth maps, confidence maps, or sky masks depending on the selected output mode. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | The Depth Anything 3 geometry data packet containing depth, and optionally sky and confidence tensors | DA3_GEOMETRY | Yes | - | +| `output` | The type of visualization to render. Options include depth, depth_colored, sky_mask, and confidence. Each option has its own set of sub-parameters. | COMBO | Yes | `"depth"`
`"depth_colored"`
`"sky_mask"`
`"confidence"` | + +### Sub-parameters for `output` options + +When `output` is set to `"depth"` or `"depth_colored"`: + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `normalization` | The depth normalization method. v2_style uses mean/std normalization for perceptually balanced results (default). min_max stretches the full depth range to [0, 1] for maximum contrast. raw preserves metric units for Metric model without scaling. | COMBO | Yes | `"v2_style"`
`"min_max"`
`"raw"` | +| `apply_sky_clip` | Clip sky-region depth to the 99th percentile of foreground depth before normalization. Requires a sky key in the da3_geometry input (for Mono/Metric models only). Default: False | BOOLEAN | Yes | True
False | + +When `output` is set to `"sky_mask"`: + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `colored` | Apply the Turbo colormap to the sky mask. Default: False | BOOLEAN | Yes | True
False | + +When `output` is set to `"confidence"`: + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `colored` | Apply the Turbo colormap to the confidence map. Default: False | BOOLEAN | Yes | True
False | + +### Parameter Constraints + +- When `apply_sky_clip` is set to True, the `da3_geometry` input must contain a sky tensor. This is only available when using Mono or Metric models. If the sky tensor is missing, the node will raise an error. +- The `sky_mask` output option requires a sky tensor in the `da3_geometry` input. This is only available with Mono or Metric models. +- The `confidence` output option requires a confidence tensor in the `da3_geometry` input. This is only available with Small or Base models. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `IMAGE` | The rendered visualization as an image tensor. For depth outputs, returns a greyscale or colored depth map. For sky_mask and confidence, returns either a greyscale or colored visualization depending on the colored parameter. | IMAGE | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3Render/en.md) + +--- +**Source fingerprint (SHA-256):** `54d4cde95a916cac26c8a2e19c5623e794d46c0d7652f1c8204f9f2a0deabe0c` diff --git a/built-in-nodes/DCTestNode.mdx b/built-in-nodes/DCTestNode.mdx index 5c0cb9ad7..8c64ced75 100644 --- a/built-in-nodes/DCTestNode.mdx +++ b/built-in-nodes/DCTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DCTestNode" icon: "circle" mode: wide --- + The DCTestNode is a logic node that returns different types of data based on a user's selection from a dynamic combo box. It acts as a conditional router, where the chosen option determines which input field is active and what type of value the node will output. ## Inputs diff --git a/built-in-nodes/DeprecatedCheckpointLoader.mdx b/built-in-nodes/DeprecatedCheckpointLoader.mdx index c33f74b15..2b7efe026 100644 --- a/built-in-nodes/DeprecatedCheckpointLoader.mdx +++ b/built-in-nodes/DeprecatedCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DeprecatedCheckpointLoader" icon: "circle" mode: wide --- + The CheckpointLoader node is designed for advanced loading operations, specifically to load model checkpoints along with their configurations. It facilitates the retrieval of model components necessary for initializing and running generative models, including configurations and checkpoints from specified directories. ## Inputs diff --git a/built-in-nodes/DeprecatedDiffusersLoader.mdx b/built-in-nodes/DeprecatedDiffusersLoader.mdx index eac2877d0..73476f6cf 100644 --- a/built-in-nodes/DeprecatedDiffusersLoader.mdx +++ b/built-in-nodes/DeprecatedDiffusersLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DeprecatedDiffusersLoader" icon: "circle" mode: wide --- + The DiffusersLoader node is designed for loading models from the diffusers library, specifically handling the loading of UNet, CLIP, and VAE models based on provided model paths. It facilitates the integration of these models into the ComfyUI framework, enabling advanced functionalities such as text-to-image generation, image manipulation, and more. ## Inputs diff --git a/built-in-nodes/DiffControlNetLoader.mdx b/built-in-nodes/DiffControlNetLoader.mdx index 8acdd24ea..9758178dc 100644 --- a/built-in-nodes/DiffControlNetLoader.mdx +++ b/built-in-nodes/DiffControlNetLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DiffControlNetLoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/controlnet` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. The DiffControlNetLoader node is designed for loading differential control networks, which are specialized models that can modify the behavior of another model based on control net specifications. This node allows for the dynamic adjustment of model behaviors by applying differential control nets, facilitating the creation of customized model outputs. diff --git a/built-in-nodes/DifferentialDiffusion.mdx b/built-in-nodes/DifferentialDiffusion.mdx index 83102912c..02ceece8c 100644 --- a/built-in-nodes/DifferentialDiffusion.mdx +++ b/built-in-nodes/DifferentialDiffusion.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DifferentialDiffusion" icon: "circle" mode: wide --- + The Differential Diffusion node modifies the denoising process by applying a binary mask based on timestep thresholds. It creates a mask that blends between the original denoise mask and a threshold-based binary mask, allowing controlled adjustment of the diffusion process strength. ## Inputs diff --git a/built-in-nodes/DiffusersLoader.mdx b/built-in-nodes/DiffusersLoader.mdx index f6b63ef64..4d26829c2 100644 --- a/built-in-nodes/DiffusersLoader.mdx +++ b/built-in-nodes/DiffusersLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DiffusersLoader" icon: "circle" mode: wide --- + The DiffusersLoader node loads pre-trained models from the diffusers format. It searches for valid diffusers model directories containing a `model_index.json` file and loads them as MODEL, CLIP, and VAE components for use in the pipeline. This node is part of the deprecated loaders category and provides compatibility with Hugging Face diffusers models. ## Inputs diff --git a/built-in-nodes/DisableNoise.mdx b/built-in-nodes/DisableNoise.mdx index 403ce2810..39a9295ee 100644 --- a/built-in-nodes/DisableNoise.mdx +++ b/built-in-nodes/DisableNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DisableNoise" icon: "circle" mode: wide --- + The DisableNoise node provides an empty noise configuration that can be used to disable noise generation in sampling processes. It returns a special noise object that contains no noise data, allowing other nodes to skip noise-related operations when connected to this output. ## Inputs diff --git a/built-in-nodes/DrawBBoxes.mdx b/built-in-nodes/DrawBBoxes.mdx index 30930ad44..db65c6ef8 100644 --- a/built-in-nodes/DrawBBoxes.mdx +++ b/built-in-nodes/DrawBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DrawBBoxes" icon: "circle" mode: wide --- + The DrawBBoxes node visualizes object detection results by drawing bounding boxes, labels, and confidence scores onto an image. If no input image is provided, it creates a blank canvas large enough to contain all the drawn boxes. It supports batch processing, allowing you to draw different sets of detections for multiple images or repeat the same detections across a batch. ## Inputs diff --git a/built-in-nodes/DualCFGGuider.mdx b/built-in-nodes/DualCFGGuider.mdx index 876ca21c1..9996796ed 100644 --- a/built-in-nodes/DualCFGGuider.mdx +++ b/built-in-nodes/DualCFGGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DualCFGGuider" icon: "circle" mode: wide --- + The DualCFGGuider node creates a guidance system for dual classifier-free guidance sampling. It combines two positive conditioning inputs with one negative conditioning input, applying different guidance scales to each conditioning pair to control the influence of each prompt on the generated output. ## Inputs diff --git a/built-in-nodes/DualCLIPLoader.mdx b/built-in-nodes/DualCLIPLoader.mdx index a71d26ef6..e9333ad13 100644 --- a/built-in-nodes/DualCLIPLoader.mdx +++ b/built-in-nodes/DualCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DualCLIPLoader" icon: "circle" mode: wide --- + The DualCLIPLoader node is designed for loading two CLIP models simultaneously, facilitating operations that require the integration or comparison of features from both models. This node will detect models located in the `ComfyUI/models/text_encoders` folder. diff --git a/built-in-nodes/DualModelGuider.mdx b/built-in-nodes/DualModelGuider.mdx index e25a2af0b..ac57839a8 100644 --- a/built-in-nodes/DualModelGuider.mdx +++ b/built-in-nodes/DualModelGuider.mdx @@ -5,7 +5,6 @@ sidebarTitle: "DualModelGuider" icon: "circle" mode: wide --- -# Dual Model CFG Guider This node allows you to use two different models during the guided CFG sampling process: one model for the positive (conditional) pass and a separate model for the negative (unconditional) pass. When no negative model is provided, it behaves like a standard CFG guider using a single model. diff --git a/built-in-nodes/EasyCache.mdx b/built-in-nodes/EasyCache.mdx index 1a3044c75..d2ebc2b68 100644 --- a/built-in-nodes/EasyCache.mdx +++ b/built-in-nodes/EasyCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EasyCache" icon: "circle" mode: wide --- + The EasyCache node implements a native caching system for models to improve performance by reusing previously computed steps during the sampling process. It adds EasyCache functionality to a model with configurable thresholds for when to start and stop using the cache during the sampling timeline. ## Inputs diff --git a/built-in-nodes/ElevenLabsAudioIsolation.mdx b/built-in-nodes/ElevenLabsAudioIsolation.mdx index 6f68f1cc0..9b71c3fbe 100644 --- a/built-in-nodes/ElevenLabsAudioIsolation.mdx +++ b/built-in-nodes/ElevenLabsAudioIsolation.mdx @@ -5,21 +5,22 @@ sidebarTitle: "ElevenLabsAudioIsolation" icon: "circle" mode: wide --- + The ElevenLabs Voice Isolation node removes background noise from an audio file, isolating the vocals or speech. It sends the audio to the ElevenLabs API for processing and returns the cleaned audio. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `audio` | Audio to process for background noise removal. | AUDIO | Yes | | +|-----------|-------------|-----------|----------|-------| +| `audio` | Audio to process for background noise removal. | AUDIO | Yes | | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The processed audio with background noise removed. | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsAudioIsolation/en.md) --- -**Source fingerprint (SHA-256):** `84f1ea16911b9b1d1ab60dd75fade8cc524ac3e39d44f60a242214f14006ff1e` +**Source fingerprint (SHA-256):** `9527f6cc976a72c787985d866dade272f3fcdc485d2bd9e3ceaaaf625822f3e1` diff --git a/built-in-nodes/ElevenLabsInstantVoiceClone.mdx b/built-in-nodes/ElevenLabsInstantVoiceClone.mdx index b22e75f51..22c6486fe 100644 --- a/built-in-nodes/ElevenLabsInstantVoiceClone.mdx +++ b/built-in-nodes/ElevenLabsInstantVoiceClone.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsInstantVoiceClone" icon: "circle" mode: wide --- + The ElevenLabs Instant Voice Clone node creates a new, unique voice model by analyzing 1 to 8 audio recordings of a person's voice. It sends these samples to the ElevenLabs API, which processes them to generate a voice clone that can be used for text-to-speech synthesis. ## Inputs @@ -25,4 +26,4 @@ The ElevenLabs Instant Voice Clone node creates a new, unique voice model by ana > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsInstantVoiceClone/en.md) --- -**Source fingerprint (SHA-256):** `760bd99ed8382eb875ab21739346d178130b02240526308b784332a59b048d78` +**Source fingerprint (SHA-256):** `5b109dfff8cdbc51d9e2684b9508b0998aaa014459b973acf29c204835a8db95` diff --git a/built-in-nodes/ElevenLabsSpeechToSpeech.mdx b/built-in-nodes/ElevenLabsSpeechToSpeech.mdx index 20cabdca0..61937d69d 100644 --- a/built-in-nodes/ElevenLabsSpeechToSpeech.mdx +++ b/built-in-nodes/ElevenLabsSpeechToSpeech.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ElevenLabsSpeechToSpeech" icon: "circle" mode: wide --- + The ElevenLabs Speech to Speech node transforms an input audio file from one voice to another. It uses the ElevenLabs API to convert speech while preserving the original content and emotional tone of the audio. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `voice` | Target voice for the transformation. Connect from Voice Selector or Instant Voice Clone. | CUSTOM | Yes | - | | `audio` | Source audio to transform. | AUDIO | Yes | - | | `stability` | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech (default: 0.5). | FLOAT | No | 0.0 - 1.0 | @@ -22,10 +23,10 @@ The ElevenLabs Speech to Speech node transforms an input audio file from one voi ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The transformed audio file in the specified output format. | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToSpeech/en.md) --- -**Source fingerprint (SHA-256):** `ef065ffa78a63398e746b52c6c8f2c336e6a4137722537c8026d292ed397a246` +**Source fingerprint (SHA-256):** `a3cd602181d134b9ab517bfac092ea30b62ef5a9942a905c0c3e6959b34370ca` diff --git a/built-in-nodes/ElevenLabsSpeechToText.mdx b/built-in-nodes/ElevenLabsSpeechToText.mdx index f0ba983de..ef333e6f6 100644 --- a/built-in-nodes/ElevenLabsSpeechToText.mdx +++ b/built-in-nodes/ElevenLabsSpeechToText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsSpeechToText" icon: "circle" mode: wide --- + The ElevenLabs Speech to Text node transcribes audio files into text. It uses ElevenLabs' API to convert spoken words into a written transcript, supporting features like automatic language detection, identifying different speakers, and tagging non-speech sounds like music or laughter. ## Inputs @@ -35,4 +36,4 @@ The ElevenLabs Speech to Text node transcribes audio files into text. It uses El > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToText/en.md) --- -**Source fingerprint (SHA-256):** `1541ae5542b83d80cb96ab0c8694c25b2bd9d4f10c1030902064d05319b2a520` +**Source fingerprint (SHA-256):** `7eb5d72615aa8a9e4a8014e45b39cf83dc8d8432d7ce0dccba20489be80a5830` diff --git a/built-in-nodes/ElevenLabsTextToDialogue.mdx b/built-in-nodes/ElevenLabsTextToDialogue.mdx index 169fe755f..512d022fa 100644 --- a/built-in-nodes/ElevenLabsTextToDialogue.mdx +++ b/built-in-nodes/ElevenLabsTextToDialogue.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ElevenLabsTextToDialogue" icon: "circle" mode: wide --- + The ElevenLabs Text to Dialogue node generates a multi-speaker audio dialogue from text. It allows you to create a conversation by specifying different text lines and distinct voices for each participant. The node sends the dialogue request to the ElevenLabs API and returns the generated audio. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `stability` | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech. (default: 0.5) | FLOAT | No | 0.0 - 1.0 | | `apply_text_normalization` | Text normalization mode. 'auto' lets the system decide, 'on' always applies normalization, 'off' skips it. | COMBO | No | `"auto"`
`"on"`
`"off"` | | `model` | Model to use for dialogue generation. | COMBO | No | `"eleven_v3"` | @@ -24,10 +25,10 @@ The ElevenLabs Text to Dialogue node generates a multi-speaker audio dialogue fr ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The generated multi-speaker dialogue audio in the selected output format. | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToDialogue/en.md) --- -**Source fingerprint (SHA-256):** `76eaa0ce55e1b542f4f2073405c707d686affd15202dc1adf1e1a81c542cbdb1` +**Source fingerprint (SHA-256):** `95b16143391a2282c58ebc66561b85338a8ce1f87e0ec769405225599d2c76ae` diff --git a/built-in-nodes/ElevenLabsTextToSoundEffects.mdx b/built-in-nodes/ElevenLabsTextToSoundEffects.mdx index d2f3a1475..2d0a9d7e0 100644 --- a/built-in-nodes/ElevenLabsTextToSoundEffects.mdx +++ b/built-in-nodes/ElevenLabsTextToSoundEffects.mdx @@ -5,13 +5,14 @@ sidebarTitle: "ElevenLabsTextToSoundEffects" icon: "circle" mode: wide --- + The ElevenLabs Text to Sound Effects node generates audio sound effects from a text description. It uses the ElevenLabs API to create sound effects based on your prompt, allowing you to control the duration, looping behavior, and how closely the sound follows the text. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `text` | Text description of the sound effect to generate. This is a required field. | STRING | Yes | N/A | +|-----------|-------------|-----------|----------|-------| +| `text` | Text description of the sound effect to generate. | STRING | Yes | N/A | | `model` | Model to use for sound effect generation. Selecting this model reveals additional parameters: `duration` (default: 5.0, range: 0.5 to 30.0 seconds), `loop` (default: False), and `prompt_influence` (default: 0.3, range: 0.0 to 1.0). | COMBO | Yes | `"eleven_sfx_v2"` | | `output_format` | Audio output format. | COMBO | Yes | `"mp3_44100_192"`
`"opus_48000_192"` | @@ -24,10 +25,10 @@ The ElevenLabs Text to Sound Effects node generates audio sound effects from a t ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The generated sound effect audio file. | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToSoundEffects/en.md) --- -**Source fingerprint (SHA-256):** `5868bfeb82c88b46587cbbce48266abd8b78ac05a24ae61a7c8dc978373c2c06` +**Source fingerprint (SHA-256):** `218ff617256cea33f310c1bcfc6407c46aaadc59201a0324b0ec64583166ce58` diff --git a/built-in-nodes/ElevenLabsTextToSpeech.mdx b/built-in-nodes/ElevenLabsTextToSpeech.mdx index 39c64c742..c615f949e 100644 --- a/built-in-nodes/ElevenLabsTextToSpeech.mdx +++ b/built-in-nodes/ElevenLabsTextToSpeech.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ElevenLabsTextToSpeech" icon: "circle" mode: wide --- + The ElevenLabs Text to Speech node converts written text into spoken audio using the ElevenLabs API. It allows you to select a specific voice and fine-tune various speech characteristics like stability, speed, and style to generate a customized audio output. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `voice` | Voice to use for speech synthesis. Connect from Voice Selector or Instant Voice Clone. | CUSTOM | Yes | N/A | | `text` | The text to convert to speech. | STRING | Yes | N/A | | `stability` | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech (default: 0.5). | FLOAT | No | 0.0 - 1.0 | @@ -21,25 +22,26 @@ The ElevenLabs Text to Speech node converts written text into spoken audio using | `output_format` | Audio output format. | COMBO | No | `"mp3_44100_192"`
`"opus_48000_192"` | **Model-Specific Parameters:** + When the `model` parameter is set to `"eleven_multilingual_v2"`, the following additional parameters become available: -* `speed`: Speech speed. 1.0 is normal, <1.0 slower, >1.0 faster (default: 1.0, range: 0.7 - 1.3). -* `similarity_boost`: Similarity boost. Higher values make the voice more similar to the original (default: 0.75, range: 0.0 - 1.0). -* `use_speaker_boost`: Boost similarity to the original speaker voice (default: False). -* `style`: Style exaggeration. Higher values increase stylistic expression but may reduce stability (default: 0.0, range: 0.0 - 0.2). +- `speed`: Speech speed. 1.0 is normal, <1.0 slower, >1.0 faster (default: 1.0, range: 0.7 - 1.3). +- `similarity_boost`: Similarity boost. Higher values make the voice more similar to the original (default: 0.75, range: 0.0 - 1.0). +- `use_speaker_boost`: Boost similarity to the original speaker voice (default: False). +- `style`: Style exaggeration. Higher values increase stylistic expression but may reduce stability (default: 0.0, range: 0.0 - 0.2). When the `model` parameter is set to `"eleven_v3"`, the following additional parameters become available: -* `speed`: Speech speed. 1.0 is normal, <1.0 slower, >1.0 faster (default: 1.0, range: 0.7 - 1.3). -* `similarity_boost`: Similarity boost. Higher values make the voice more similar to the original (default: 0.75, range: 0.0 - 1.0). +- `speed`: Speech speed. 1.0 is normal, <1.0 slower, >1.0 faster (default: 1.0, range: 0.7 - 1.3). +- `similarity_boost`: Similarity boost. Higher values make the voice more similar to the original (default: 0.75, range: 0.0 - 1.0). ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The generated audio from the text-to-speech conversion. | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsTextToSpeech/en.md) --- -**Source fingerprint (SHA-256):** `0cd570fbb152e07ba028e96df56abc08dde8941d043386fd076f42a1e1dc6016` +**Source fingerprint (SHA-256):** `78ed1c6af2d0b1cc0293d725492a8b104b6d0c6bc18d9971b75047db946cdd33` diff --git a/built-in-nodes/ElevenLabsVoiceSelector.mdx b/built-in-nodes/ElevenLabsVoiceSelector.mdx index af71f67fb..776c0997f 100644 --- a/built-in-nodes/ElevenLabsVoiceSelector.mdx +++ b/built-in-nodes/ElevenLabsVoiceSelector.mdx @@ -5,21 +5,22 @@ sidebarTitle: "ElevenLabsVoiceSelector" icon: "circle" mode: wide --- + The ElevenLabs Voice Selector node allows you to choose a specific voice from a predefined list of ElevenLabs text-to-speech voices. It takes a voice name as input and outputs the corresponding voice identifier needed for audio generation. This node simplifies the process of selecting a compatible voice for use with other ElevenLabs audio nodes. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `voice` | Choose a voice from the predefined ElevenLabs voices. | STRING | Yes | `"Adam (male, american)"`
`"Antoni (male, british)"`
`"Arnold (male, american)"`
`"Bella (female, american)"`
`"Domi (female, american)"`
`"Elli (female, american)"`
`"Josh (male, american)"`
`"Rachel (female, american)"`
`"Sam (male, american)"` | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `voice` | The unique identifier for the selected ElevenLabs voice, which can be passed to other nodes for text-to-speech generation. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsVoiceSelector/en.md) --- -**Source fingerprint (SHA-256):** `47adf5da14e65749c16ada389331c380a1e3a18ecc6f366c32d84ffe7c34990a` +**Source fingerprint (SHA-256):** `72e2239bb0da15a88cd346ede2051b4fb717f3bf49faaf5d63c0622b03ccd80d` diff --git a/built-in-nodes/EmptyARVideoLatent.mdx b/built-in-nodes/EmptyARVideoLatent.mdx index cef922b2c..3fcbac0e7 100644 --- a/built-in-nodes/EmptyARVideoLatent.mdx +++ b/built-in-nodes/EmptyARVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyARVideoLatent" icon: "circle" mode: wide --- + ## Overview The EmptyARVideoLatent node creates a blank, empty latent representation for video generation. It is used to initialize a video generation process by providing a tensor of zeros with the specified dimensions, aspect ratio, and length. diff --git a/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx b/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx index 5c563d5e8..d2f99b3ae 100644 --- a/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx +++ b/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAceStep1.5LatentAudio" icon: "circle" mode: wide --- + The Empty Ace Step 1.5 Latent Audio node creates an empty latent tensor designed for audio processing. It generates a silent audio latent of a specified duration and batch size, which can be used as a starting point for audio generation workflows in ComfyUI. The node calculates the latent length based on the input seconds and a fixed sample rate. ## Inputs diff --git a/built-in-nodes/EmptyAceStepLatentAudio.mdx b/built-in-nodes/EmptyAceStepLatentAudio.mdx index 81e52889b..e81f38238 100644 --- a/built-in-nodes/EmptyAceStepLatentAudio.mdx +++ b/built-in-nodes/EmptyAceStepLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAceStepLatentAudio" icon: "circle" mode: wide --- + The EmptyAceStepLatentAudio node creates empty latent audio samples of a specified duration. It generates a batch of silent audio latents filled with zeros, where the length is calculated based on the input seconds and audio processing parameters. This node is useful for initializing audio processing workflows that require latent representations. ## Inputs diff --git a/built-in-nodes/EmptyAudio.mdx b/built-in-nodes/EmptyAudio.mdx index d3f33b2e0..69ee3c76d 100644 --- a/built-in-nodes/EmptyAudio.mdx +++ b/built-in-nodes/EmptyAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAudio" icon: "circle" mode: wide --- + The EmptyAudio node generates a silent audio clip with specified duration, sample rate, and channel configuration. It creates a waveform containing all zeros, producing complete silence for the given duration. This node is useful for creating placeholder audio or generating silent segments in audio workflows. ## Inputs diff --git a/built-in-nodes/EmptyChromaRadianceLatentImage.mdx b/built-in-nodes/EmptyChromaRadianceLatentImage.mdx index c4e85f5ec..81afe6091 100644 --- a/built-in-nodes/EmptyChromaRadianceLatentImage.mdx +++ b/built-in-nodes/EmptyChromaRadianceLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyChromaRadianceLatentImage" icon: "circle" mode: wide --- + The EmptyChromaRadianceLatentImage node creates a blank latent image with specified dimensions for use in chroma radiance workflows. It generates a tensor filled with zeros that serves as a starting point for latent space operations. The node allows you to define the width, height, and batch size of the empty latent image. ## Inputs diff --git a/built-in-nodes/EmptyCosmosLatentVideo.mdx b/built-in-nodes/EmptyCosmosLatentVideo.mdx index c12714e99..758d7b1ed 100644 --- a/built-in-nodes/EmptyCosmosLatentVideo.mdx +++ b/built-in-nodes/EmptyCosmosLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyCosmosLatentVideo" icon: "circle" mode: wide --- + The EmptyCosmosLatentVideo node creates an empty latent video tensor with specified dimensions. It generates a zero-filled latent representation that can be used as a starting point for video generation workflows, with configurable width, height, length, and batch size parameters. ## Inputs diff --git a/built-in-nodes/EmptyFlux2LatentImage.mdx b/built-in-nodes/EmptyFlux2LatentImage.mdx index f7bc45c93..da6945371 100644 --- a/built-in-nodes/EmptyFlux2LatentImage.mdx +++ b/built-in-nodes/EmptyFlux2LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyFlux2LatentImage" icon: "circle" mode: wide --- + The EmptyFlux2LatentImage node creates a blank, empty latent representation. It generates a tensor filled with zeros, which serves as a starting point for the Flux model's denoising process. The dimensions of the latent are determined by the input width and height, scaled down by a factor of 16. ## Inputs diff --git a/built-in-nodes/EmptyHiDreamO1LatentImage.mdx b/built-in-nodes/EmptyHiDreamO1LatentImage.mdx index b55e18f51..b259655de 100644 --- a/built-in-nodes/EmptyHiDreamO1LatentImage.mdx +++ b/built-in-nodes/EmptyHiDreamO1LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHiDreamO1LatentImage" icon: "circle" mode: wide --- + ## Overview This node creates an empty latent image in pixel space, specifically designed for the HiDream-O1-Image model. It generates a blank tensor of zeros that serves as the starting point for image generation, with dimensions defined by the width, height, and batch size inputs. diff --git a/built-in-nodes/EmptyHunyuanImageLatent.mdx b/built-in-nodes/EmptyHunyuanImageLatent.mdx index 7eb8a94f5..8ffa5f299 100644 --- a/built-in-nodes/EmptyHunyuanImageLatent.mdx +++ b/built-in-nodes/EmptyHunyuanImageLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanImageLatent" icon: "circle" mode: wide --- + The EmptyHunyuanImageLatent node creates an empty latent tensor with specific dimensions for use with Hunyuan image generation models. It generates a blank starting point that can be processed through subsequent nodes in the workflow. The node allows you to specify the width, height, and batch size of the latent space. ## Inputs diff --git a/built-in-nodes/EmptyHunyuanLatentVideo.mdx b/built-in-nodes/EmptyHunyuanLatentVideo.mdx index fe770f6ae..76a856c0e 100644 --- a/built-in-nodes/EmptyHunyuanLatentVideo.mdx +++ b/built-in-nodes/EmptyHunyuanLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanLatentVideo" icon: "circle" mode: wide --- + The `EmptyHunyuanLatentVideo` node is similar to the `EmptyLatentImage` node. You can consider it as a blank canvas for video generation, where width, height, and length define the properties of the canvas, and the batch size determines the number of canvases to create. This node creates empty canvases ready for subsequent video generation tasks. ## Inputs diff --git a/built-in-nodes/EmptyHunyuanVideo15Latent.mdx b/built-in-nodes/EmptyHunyuanVideo15Latent.mdx index 15e3187d4..45bbd3edb 100644 --- a/built-in-nodes/EmptyHunyuanVideo15Latent.mdx +++ b/built-in-nodes/EmptyHunyuanVideo15Latent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanVideo15Latent" icon: "circle" mode: wide --- + This node creates an empty latent tensor specifically formatted for use with the HunyuanVideo 1.5 model. It generates a blank starting point for video generation by allocating a tensor of zeros with the correct channel count and spatial dimensions for the model's latent space. ## Inputs diff --git a/built-in-nodes/EmptyImage.mdx b/built-in-nodes/EmptyImage.mdx index 77ac195dc..2230a95b1 100644 --- a/built-in-nodes/EmptyImage.mdx +++ b/built-in-nodes/EmptyImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyImage" icon: "circle" mode: wide --- + ## Function Description The EmptyImage node is used to create blank images with specified dimensions and colors. It can generate solid-color background images, commonly used as starting points or background images for image processing workflows. diff --git a/built-in-nodes/EmptyLTXVLatentVideo.mdx b/built-in-nodes/EmptyLTXVLatentVideo.mdx index 539167f2e..7c226e4b1 100644 --- a/built-in-nodes/EmptyLTXVLatentVideo.mdx +++ b/built-in-nodes/EmptyLTXVLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLTXVLatentVideo" icon: "circle" mode: wide --- + The EmptyLTXVLatentVideo node creates an empty latent tensor for video processing. It generates a blank starting point with specified dimensions that can be used as input for video generation workflows. The node produces a zero-filled latent representation with the configured width, height, length, and batch size. ## Inputs diff --git a/built-in-nodes/EmptyLatentAudio.mdx b/built-in-nodes/EmptyLatentAudio.mdx index c148fa12e..dc552f282 100644 --- a/built-in-nodes/EmptyLatentAudio.mdx +++ b/built-in-nodes/EmptyLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentAudio" icon: "circle" mode: wide --- + The EmptyLatentAudio node creates an empty latent tensor for audio processing. It generates a blank audio latent representation with a specified duration and batch size, which can be used as a starting point for audio generation or processing workflows. The node automatically calculates the appropriate latent dimensions based on the audio duration and sample rate. ## Inputs diff --git a/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx b/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx index 3730c9525..d69694d95 100644 --- a/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx +++ b/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentHunyuan3Dv2" icon: "circle" mode: wide --- + The EmptyLatentHunyuan3Dv2 node creates blank latent tensors specifically formatted for Hunyuan3Dv2 3D generation models. It generates empty latent spaces with the correct dimensions and structure required by the Hunyuan3Dv2 architecture, allowing you to start 3D generation workflows from scratch. The node produces latent tensors filled with zeros that serve as the foundation for subsequent 3D generation processes. ## Inputs diff --git a/built-in-nodes/EmptyLatentImage.mdx b/built-in-nodes/EmptyLatentImage.mdx index 6b302830a..b9f258700 100644 --- a/built-in-nodes/EmptyLatentImage.mdx +++ b/built-in-nodes/EmptyLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentImage" icon: "circle" mode: wide --- + The `EmptyLatentImage` node is designed to generate a blank latent space representation with specified dimensions and batch size. This node serves as a foundational step in generating or manipulating images in latent space, providing a starting point for further image synthesis or modification processes. ## Inputs diff --git a/built-in-nodes/EmptyMochiLatentVideo.mdx b/built-in-nodes/EmptyMochiLatentVideo.mdx index e845ffe57..8d5caf361 100644 --- a/built-in-nodes/EmptyMochiLatentVideo.mdx +++ b/built-in-nodes/EmptyMochiLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyMochiLatentVideo" icon: "circle" mode: wide --- + The EmptyMochiLatentVideo node creates an empty latent video tensor with specified dimensions. It generates a zero-filled latent representation that can be used as a starting point for video generation workflows. The node allows you to define the width, height, length, and batch size for the latent video tensor. ## Inputs diff --git a/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx b/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx index f93797748..8be7d3179 100644 --- a/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx +++ b/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyQwenImageLayeredLatentImage" icon: "circle" mode: wide --- + The Empty Qwen Image Layered Latent node creates a blank, multi-layered latent representation for use with Qwen image models. It generates a tensor filled with zeros, structured with a specified number of layers, batch size, and spatial dimensions. This empty latent serves as a starting point for subsequent image generation or manipulation workflows. ## Inputs diff --git a/built-in-nodes/EmptySD3LatentImage.mdx b/built-in-nodes/EmptySD3LatentImage.mdx index 9c501942b..9068f6134 100644 --- a/built-in-nodes/EmptySD3LatentImage.mdx +++ b/built-in-nodes/EmptySD3LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptySD3LatentImage" icon: "circle" mode: wide --- + The EmptySD3LatentImage node creates a blank latent image tensor specifically formatted for Stable Diffusion 3 models. It generates a tensor filled with zeros that has the correct dimensions and structure expected by SD3 pipelines. This is commonly used as a starting point for image generation workflows. ## Inputs diff --git a/built-in-nodes/Epsilon Scaling.mdx b/built-in-nodes/Epsilon Scaling.mdx index c46143860..ff966c854 100644 --- a/built-in-nodes/Epsilon Scaling.mdx +++ b/built-in-nodes/Epsilon Scaling.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Epsilon Scaling" icon: "circle" mode: wide --- + This node implements the Epsilon Scaling method from the research paper "Elucidating the Exposure Bias in Diffusion Models" (arxiv.org/abs/2308.15321v6). It works by scaling the predicted noise during the sampling process to help reduce exposure bias, which can lead to improved quality in the generated images. This implementation uses the "uniform schedule" recommended by the paper for its practicality and effectiveness. ## Inputs diff --git a/built-in-nodes/ExponentialScheduler.mdx b/built-in-nodes/ExponentialScheduler.mdx index 1a05776aa..79e05f07a 100644 --- a/built-in-nodes/ExponentialScheduler.mdx +++ b/built-in-nodes/ExponentialScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ExponentialScheduler" icon: "circle" mode: wide --- + The `ExponentialScheduler` node is designed to generate a sequence of sigma values following an exponential schedule for diffusion sampling processes. It provides a customizable approach to control the noise levels applied at each step of the diffusion process, allowing for fine-tuning of the sampling behavior. ## Inputs diff --git a/built-in-nodes/ExtendIntermediateSigmas.mdx b/built-in-nodes/ExtendIntermediateSigmas.mdx index 0ece9aed0..6478a0309 100644 --- a/built-in-nodes/ExtendIntermediateSigmas.mdx +++ b/built-in-nodes/ExtendIntermediateSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ExtendIntermediateSigmas" icon: "circle" mode: wide --- + The ExtendIntermediateSigmas node takes an existing sequence of sigma values and inserts additional intermediate sigma values between them. It allows you to specify how many extra steps to add, the spacing method for interpolation, and optional start and end sigma boundaries to control where the extension occurs within the sigma sequence. ## Inputs diff --git a/built-in-nodes/FeatherMask.mdx b/built-in-nodes/FeatherMask.mdx index 52f1db063..d31278237 100644 --- a/built-in-nodes/FeatherMask.mdx +++ b/built-in-nodes/FeatherMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FeatherMask" icon: "circle" mode: wide --- + The `FeatherMask` node applies a feathering effect to the edges of a given mask, smoothly transitioning the mask's edges by adjusting their opacity based on specified distances from each edge. This creates a softer, more blended edge effect. ## Inputs diff --git a/built-in-nodes/File3DToSplat.mdx b/built-in-nodes/File3DToSplat.mdx index a59b7260d..0ac3eb99b 100644 --- a/built-in-nodes/File3DToSplat.mdx +++ b/built-in-nodes/File3DToSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "File3DToSplat" icon: "circle" mode: wide --- -# File3DToSplat This node converts a 3D file containing gaussian splat data into a gaussian splat format that can be used in the node graph. It supports PLY, SPLAT, KSPLAT, and SPZ file formats, with the file format automatically detected from the file contents. diff --git a/built-in-nodes/FlipSigmas.mdx b/built-in-nodes/FlipSigmas.mdx index a8f4c2f1f..da95e6359 100644 --- a/built-in-nodes/FlipSigmas.mdx +++ b/built-in-nodes/FlipSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FlipSigmas" icon: "circle" mode: wide --- + The `FlipSigmas` node is designed to manipulate the sequence of sigma values used in diffusion models by reversing their order and ensuring the first value is non-zero if originally zero. This operation is crucial for adapting the noise levels in reverse order, facilitating the generation process in models that operate by gradually reducing noise from data. ## Inputs diff --git a/built-in-nodes/Flux2ImageNode.mdx b/built-in-nodes/Flux2ImageNode.mdx index 8c2a389c3..0282eef61 100644 --- a/built-in-nodes/Flux2ImageNode.mdx +++ b/built-in-nodes/Flux2ImageNode.mdx @@ -5,14 +5,13 @@ sidebarTitle: "Flux2ImageNode" icon: "circle" mode: wide --- -## Overview Generate images using the Flux.2 [pro] or Flux.2 [max] model from a text prompt and optional reference images. This node sends your request to the BFL API, polls for the result, and returns the generated image as a tensor. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation or edit (default: empty string). | STRING | Yes | N/A | | `model` | The Flux.2 model version to use. Selecting a model unlocks additional parameters for width, height, and optional reference images. | COMBO | Yes | `"Flux.2 [pro]"`
`"Flux.2 [max]"` | | `seed` | The random seed used for creating the noise. Can be set to randomize after each generation (default: 0). | INT | Yes | 0 to 18446744073709551615 | @@ -22,22 +21,22 @@ Generate images using the Flux.2 [pro] or Flux.2 [max] model from a text prompt When you select a model, the following parameters become available: | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model.width` | The width of the generated image in pixels. | INT | Yes | 256 to 1440 | | `model.height` | The height of the generated image in pixels. | INT | Yes | 256 to 1440 | | `model.images` | Optional reference images to guide the generation. A maximum of 8 images is supported. | IMAGE | No | 0 to 8 images | **Constraints:** - The maximum number of reference images is 8. If more than 8 images are provided, an error will be raised. -- The `model.width` and `model.height` values affect the cost of the generation (see price badge logic in source code). +- The `model.width` and `model.height` values affect the cost of the generation. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The generated image as a tensor, downloaded from the BFL API result. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Flux2ImageNode/en.md) --- -**Source fingerprint (SHA-256):** `ce3ee97d5ccb746892f3bfdb0dd5450d79cb4e0775a88d1f8c09569ce43ecbbb` +**Source fingerprint (SHA-256):** `9627f120df5aedfef1203db2baf39926e1d6891ef30e56b4eac4c2baf5e032e8` diff --git a/built-in-nodes/Flux2Scheduler.mdx b/built-in-nodes/Flux2Scheduler.mdx index 98f71c9fc..c4a80c84f 100644 --- a/built-in-nodes/Flux2Scheduler.mdx +++ b/built-in-nodes/Flux2Scheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Flux2Scheduler" icon: "circle" mode: wide --- + The Flux2Scheduler node generates a sequence of noise levels (sigmas) for the denoising process, specifically tailored for the Flux model. It calculates a schedule based on the number of denoising steps and the dimensions of the target image, which influences the progression of noise removal during image generation. ## Inputs diff --git a/built-in-nodes/FluxDisableGuidance.mdx b/built-in-nodes/FluxDisableGuidance.mdx index 1ecac72d3..c0608ffeb 100644 --- a/built-in-nodes/FluxDisableGuidance.mdx +++ b/built-in-nodes/FluxDisableGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxDisableGuidance" icon: "circle" mode: wide --- + This node completely disables the guidance embed functionality for Flux and similar models. It takes conditioning data as input and removes the guidance component by setting it to None, effectively turning off guidance-based conditioning for the generation process. ## Inputs diff --git a/built-in-nodes/FluxEraseNode.mdx b/built-in-nodes/FluxEraseNode.mdx index d0c68ad12..0bcf7c330 100644 --- a/built-in-nodes/FluxEraseNode.mdx +++ b/built-in-nodes/FluxEraseNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxEraseNode" icon: "circle" mode: wide --- -# Flux Erase Node Removes the masked object from an image and reconstructs the background. Paint the mask over what you want to erase, and the node fills in the area with plausible background content. diff --git a/built-in-nodes/FluxGuidance.mdx b/built-in-nodes/FluxGuidance.mdx index 668403355..6929c23c8 100644 --- a/built-in-nodes/FluxGuidance.mdx +++ b/built-in-nodes/FluxGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxGuidance" icon: "circle" mode: wide --- + ## Inputs | Parameter | Description | Data Type | diff --git a/built-in-nodes/FluxKVCache.mdx b/built-in-nodes/FluxKVCache.mdx index ec78cbaf2..1febcef01 100644 --- a/built-in-nodes/FluxKVCache.mdx +++ b/built-in-nodes/FluxKVCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKVCache" icon: "circle" mode: wide --- + The Flux KV Cache node enables a Key-Value (KV) Cache optimization for Flux family models. This optimization improves performance when using reference images by caching certain computations, which can speed up the generation process. ## Inputs diff --git a/built-in-nodes/FluxKontextImageScale.mdx b/built-in-nodes/FluxKontextImageScale.mdx index 3172ceaad..29126e61a 100644 --- a/built-in-nodes/FluxKontextImageScale.mdx +++ b/built-in-nodes/FluxKontextImageScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKontextImageScale" icon: "circle" mode: wide --- + This node scales the input image to an optimal size used during Flux Kontext model training using the Lanczos algorithm, based on the input image's aspect ratio. This node is particularly useful when inputting large-sized images, as oversized inputs may lead to degraded model output quality or issues such as multiple subjects appearing in the output. ## Inputs diff --git a/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx b/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx index 296bd300e..55e3311aa 100644 --- a/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx +++ b/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKontextMultiReferenceLatentMethod" icon: "circle" mode: wide --- + The FluxKontextMultiReferenceLatentMethod node modifies conditioning data by setting a specific reference latents method. It appends the chosen method to the conditioning input, which affects how reference latents are processed in subsequent generation steps. This node is marked as experimental and is part of the Flux conditioning system. ## Inputs diff --git a/built-in-nodes/FluxProCannyNode.mdx b/built-in-nodes/FluxProCannyNode.mdx index 4326b2a88..844ce32fe 100644 --- a/built-in-nodes/FluxProCannyNode.mdx +++ b/built-in-nodes/FluxProCannyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProCannyNode" icon: "circle" mode: wide --- + Generate image using a control image (canny). This node takes a control image and generates a new image based on the provided prompt while following the edge structure detected in the control image. ## Inputs diff --git a/built-in-nodes/FluxProDepthNode.mdx b/built-in-nodes/FluxProDepthNode.mdx index 4cf1e607b..002a985c3 100644 --- a/built-in-nodes/FluxProDepthNode.mdx +++ b/built-in-nodes/FluxProDepthNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProDepthNode" icon: "circle" mode: wide --- + This node generates images using a depth control image as guidance. It takes a control image and a text prompt, then creates a new image that follows both the depth information from the control image and the description in the prompt. The node connects to an external API to perform the image generation process. ## Inputs diff --git a/built-in-nodes/FluxProExpandNode.mdx b/built-in-nodes/FluxProExpandNode.mdx index c05b56129..e467a5852 100644 --- a/built-in-nodes/FluxProExpandNode.mdx +++ b/built-in-nodes/FluxProExpandNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "FluxProExpandNode" icon: "circle" mode: wide --- + Outpaints image based on prompt. This node expands an image by adding pixels to the top, bottom, left, and right sides while generating new content that matches the provided text description. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be expanded | IMAGE | Yes | - | | `prompt` | Prompt for the image generation (default: "") | STRING | No | - | | `prompt_upsampling` | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False) | BOOLEAN | No | - | @@ -25,10 +26,10 @@ Outpaints image based on prompt. This node expands an image by adding pixels to ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The expanded output image | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProExpandNode/en.md) --- -**Source fingerprint (SHA-256):** `d8ef7e28fecd0d08fa8f61c714ada054162668bb961008230bd4d342564af713` +**Source fingerprint (SHA-256):** `faff1e1311a3208066a499a358923c6e335ea1785baeafe3761484641f7f12d6` diff --git a/built-in-nodes/FluxProFillNode.mdx b/built-in-nodes/FluxProFillNode.mdx index a9c20b037..ff44726fa 100644 --- a/built-in-nodes/FluxProFillNode.mdx +++ b/built-in-nodes/FluxProFillNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "FluxProFillNode" icon: "circle" mode: wide --- + Inpaints image based on mask and prompt. This node uses the Flux.1 model to fill in masked areas of an image according to the provided text description, generating new content that matches the surrounding image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be inpainted | IMAGE | Yes | - | | `mask` | The mask defining which areas of the image should be filled | MASK | Yes | - | | `prompt` | Prompt for the image generation (default: empty string) | STRING | No | - | @@ -22,10 +23,10 @@ Inpaints image based on mask and prompt. This node uses the Flux.1 model to fill ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output_image` | The generated image with the masked areas filled according to the prompt | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProFillNode/en.md) --- -**Source fingerprint (SHA-256):** `68f9834a58d6e2d14743adafb1f791880f0af30fdb65cb6201af5616945bb56b` +**Source fingerprint (SHA-256):** `11aa071c52897788d9d7dae4105ffdf747d3cb91d75a0ad7cfacd7ca1ddd2ac1` diff --git a/built-in-nodes/FluxProImageNode.mdx b/built-in-nodes/FluxProImageNode.mdx index 3e4b49130..b016d88f3 100644 --- a/built-in-nodes/FluxProImageNode.mdx +++ b/built-in-nodes/FluxProImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProImageNode" icon: "circle" mode: wide --- + Generates images synchronously based on prompt and resolution. This node creates images using the Flux 1.1 Pro model by sending requests to an API endpoint and waiting for the complete response before returning the generated image. ## Inputs diff --git a/built-in-nodes/FluxProUltraImageNode.mdx b/built-in-nodes/FluxProUltraImageNode.mdx index adeda337a..d1b5e8410 100644 --- a/built-in-nodes/FluxProUltraImageNode.mdx +++ b/built-in-nodes/FluxProUltraImageNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "FluxProUltraImageNode" icon: "circle" mode: wide --- + Generates images using Flux Pro 1.1 Ultra via API based on prompt and resolution. This node connects to an external service to create images according to your text description and specified dimensions. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation (default: empty string) | STRING | Yes | - | | `prompt_upsampling` | Whether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False) | BOOLEAN | No | - | | `seed` | The random seed used for creating the noise. (default: 0) | INT | No | 0 to 18446744073709551615 | @@ -24,10 +25,10 @@ Generates images using Flux Pro 1.1 Ultra via API based on prompt and resolution ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output_image` | The generated image from Flux Pro 1.1 Ultra | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProUltraImageNode/en.md) --- -**Source fingerprint (SHA-256):** `9a0e3c676456da395845a2bd869abaaca30ed63ee3faf56449a2548fbab46b5c` +**Source fingerprint (SHA-256):** `6c9292ea666055ccd309d9e5d6d7cf8985f7b8f1e1faeda1e961b429b249f494` diff --git a/built-in-nodes/FluxVTONode.mdx b/built-in-nodes/FluxVTONode.mdx index a8b82f9cd..290732c9b 100644 --- a/built-in-nodes/FluxVTONode.mdx +++ b/built-in-nodes/FluxVTONode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxVTONode" icon: "circle" mode: wide --- -# Flux Virtual Try-On This node performs virtual try-on by dressing a person in a provided garment image. It uses the BFL Flux VTO API to generate a realistic image of the person wearing the specified garment. diff --git a/built-in-nodes/FrameInterpolate.mdx b/built-in-nodes/FrameInterpolate.mdx index 7bc8f5dff..61c4aefbd 100644 --- a/built-in-nodes/FrameInterpolate.mdx +++ b/built-in-nodes/FrameInterpolate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FrameInterpolate" icon: "circle" mode: wide --- + ## Overview The Frame Interpolate node creates new frames between existing ones in a sequence of images, effectively increasing the frame rate. It uses an AI model to predict what the intermediate frames should look like, which can be used to create smooth slow-motion effects or to increase the smoothness of a video. diff --git a/built-in-nodes/FrameInterpolationModelLoader.mdx b/built-in-nodes/FrameInterpolationModelLoader.mdx index 82b43a946..7b9c842b3 100644 --- a/built-in-nodes/FrameInterpolationModelLoader.mdx +++ b/built-in-nodes/FrameInterpolationModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FrameInterpolationModelLoader" icon: "circle" mode: wide --- + ## Overview This node loads a frame interpolation model from a file and prepares it for use in the workflow. It automatically detects the model type (FILM or RIFE) and configures the model for optimal performance on your hardware. diff --git a/built-in-nodes/FreSca.mdx b/built-in-nodes/FreSca.mdx index 24f07e4df..179a707cb 100644 --- a/built-in-nodes/FreSca.mdx +++ b/built-in-nodes/FreSca.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreSca" icon: "circle" mode: wide --- + The FreSca node applies frequency-dependent scaling to the guidance during the sampling process. It separates the guidance signal into low-frequency and high-frequency components using Fourier filtering, then applies different scaling factors to each frequency range before recombining them. This allows for more nuanced control over how guidance affects different aspects of the generated output. ## Inputs diff --git a/built-in-nodes/FreeU.mdx b/built-in-nodes/FreeU.mdx index bb323ba66..0394d5f0f 100644 --- a/built-in-nodes/FreeU.mdx +++ b/built-in-nodes/FreeU.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreeU" icon: "circle" mode: wide --- + The FreeU node applies frequency-domain modifications to a model's output blocks to enhance image generation quality. It works by scaling different channel groups and applying Fourier filtering to specific feature maps, allowing for fine-tuned control over the model's behavior during the generation process. ## Inputs diff --git a/built-in-nodes/FreeU_V2.mdx b/built-in-nodes/FreeU_V2.mdx index cfbb6983b..60165cdca 100644 --- a/built-in-nodes/FreeU_V2.mdx +++ b/built-in-nodes/FreeU_V2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreeU_V2" icon: "circle" mode: wide --- + The FreeU_V2 node enhances image generation quality by applying frequency-based modifications to a diffusion model's U-Net architecture. It uses configurable scaling factors to adjust feature channels in different blocks, improving output without requiring additional training. ## Inputs diff --git a/built-in-nodes/GITSScheduler.mdx b/built-in-nodes/GITSScheduler.mdx index c1f677e8c..323bb2265 100644 --- a/built-in-nodes/GITSScheduler.mdx +++ b/built-in-nodes/GITSScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GITSScheduler" icon: "circle" mode: wide --- + The GITSScheduler node generates noise schedule sigmas for the GITS (Generative Iterative Time Steps) sampling method. It calculates sigma values based on a coefficient parameter and number of steps, with an optional denoising factor that can reduce the total steps used. The node uses pre-defined noise levels and interpolation to create the final sigma schedule. ## Inputs diff --git a/built-in-nodes/GLIGENLoader.mdx b/built-in-nodes/GLIGENLoader.mdx index ba7417499..2579a7ca7 100644 --- a/built-in-nodes/GLIGENLoader.mdx +++ b/built-in-nodes/GLIGENLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLIGENLoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/gligen` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. The `GLIGENLoader` node is designed for loading GLIGEN models, which are specialized generative models. It facilitates the process of retrieving and initializing these models from specified paths, making them ready for further generative tasks. diff --git a/built-in-nodes/GLIGENTextBoxApply.mdx b/built-in-nodes/GLIGENTextBoxApply.mdx index 32d727720..bf10b1c5d 100644 --- a/built-in-nodes/GLIGENTextBoxApply.mdx +++ b/built-in-nodes/GLIGENTextBoxApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLIGENTextBoxApply" icon: "circle" mode: wide --- + The `GLIGENTextBoxApply` node is designed to integrate text-based conditioning into a generative model's input, specifically by applying text box parameters and encoding them using a CLIP model. This process enriches the conditioning with spatial and textual information, facilitating more precise and context-aware generation. ## Inputs diff --git a/built-in-nodes/GLSLShader.mdx b/built-in-nodes/GLSLShader.mdx index 6c5f0e961..1cfb56c21 100644 --- a/built-in-nodes/GLSLShader.mdx +++ b/built-in-nodes/GLSLShader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLSLShader" icon: "circle" mode: wide --- + The **GLSL Shader** node lets you write custom fragment shaders in **GLSL ES 3.00** (WebGL 2.0 compatible) to process images directly on the GPU. You can create image effects like blurs, color grading, film grain, glow, and much more - all running at GPU speed. diff --git a/built-in-nodes/GeminiImage2Node.mdx b/built-in-nodes/GeminiImage2Node.mdx index 4dcb5946b..5c0939367 100644 --- a/built-in-nodes/GeminiImage2Node.mdx +++ b/built-in-nodes/GeminiImage2Node.mdx @@ -5,12 +5,13 @@ sidebarTitle: "GeminiImage2Node" icon: "circle" mode: wide --- + The GeminiImage2Node generates or edits images using Google's Vertex AI Gemini model. It sends a text prompt and optional reference images or files to the API and returns the generated image and/or a text description. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt describing the image to generate or the edits to apply. Include any constraints, styles, or details the model should follow. | STRING | Yes | N/A | | `model` | The specific Gemini model to use for generation. The "Nano Banana 2" option maps to the `gemini-3.1-flash-image-preview` model internally. | COMBO | Yes | `"gemini-3-pro-image-preview"`
`"Nano Banana 2 (Gemini 3.1 Flash Image)"` | | `seed` | When fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Changing the model or other settings can cause variations even with the same seed. Default: 42. | INT | Yes | 0 to 18446744073709551615 | @@ -29,11 +30,11 @@ The GeminiImage2Node generates or edits images using Google's Vertex AI Gemini m ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The image generated or edited by the Gemini model. | IMAGE | | `string` | The text response from the model. This output will be empty if `response_modalities` is set to "IMAGE". | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImage2Node/en.md) --- -**Source fingerprint (SHA-256):** `5814a952815288c0b4b5962f646c69b0e618bfb9ab92b31ba60eab313c68a01c` +**Source fingerprint (SHA-256):** `3483c2b157c7359a571e2478d8709019b42b895195bc5fa14c44d6ba2950234d` diff --git a/built-in-nodes/GeminiImageNode.mdx b/built-in-nodes/GeminiImageNode.mdx index cc3cdacf8..542f9e6cd 100644 --- a/built-in-nodes/GeminiImageNode.mdx +++ b/built-in-nodes/GeminiImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiImageNode" icon: "circle" mode: wide --- + The GeminiImage node generates text and image responses from Google's Gemini AI models. It allows you to provide multimodal inputs including text prompts, images, and files to create coherent text and image outputs. The node handles all API communication and response parsing with the latest Gemini models. ## Inputs diff --git a/built-in-nodes/GeminiInputFiles.mdx b/built-in-nodes/GeminiInputFiles.mdx index c2478d65b..e6c159a70 100644 --- a/built-in-nodes/GeminiInputFiles.mdx +++ b/built-in-nodes/GeminiInputFiles.mdx @@ -5,12 +5,13 @@ sidebarTitle: "GeminiInputFiles" icon: "circle" mode: wide --- + Loads and formats input files for use with the Gemini API. This node allows users to include text (.txt) and PDF (.pdf) files as input context for the Gemini model. Files are converted to the appropriate format required by the API and can be chained together to include multiple files in a single request. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `file` | Input files to include as context for the model. Only accepts text (.txt) and PDF (.pdf) files for now. Files must be smaller than the maximum input file size limit (20 MB). | COMBO | Yes | Multiple options available (only .txt and .pdf files under 20 MB) | | `GEMINI_INPUT_FILES` | An optional additional file(s) to batch together with the file loaded from this node. Allows chaining of input files so that a single message can include multiple input files. | GEMINI_INPUT_FILES | No | N/A | @@ -19,10 +20,10 @@ Loads and formats input files for use with the Gemini API. This node allows user ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `GEMINI_INPUT_FILES` | Formatted file data ready for use with Gemini LLM nodes, containing the loaded file content in the appropriate API format. | GEMINI_INPUT_FILES | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiInputFiles/en.md) --- -**Source fingerprint (SHA-256):** `dc8ddfffc13984b2d0cc08a50f2a8c26f9608724f632ab49fdeff12bc2e5424a` +**Source fingerprint (SHA-256):** `1c80a87746c7ac73379f5c1e2d5c4d22f0fc44d3241fafb0297e087e436df7d6` diff --git a/built-in-nodes/GeminiNanoBanana2.mdx b/built-in-nodes/GeminiNanoBanana2.mdx index 55f674c43..579816046 100644 --- a/built-in-nodes/GeminiNanoBanana2.mdx +++ b/built-in-nodes/GeminiNanoBanana2.mdx @@ -5,12 +5,13 @@ sidebarTitle: "GeminiNanoBanana2" icon: "circle" mode: wide --- + The GeminiNanoBanana2 node generates or edits images using Google's Vertex AI Gemini model. It works by sending a text prompt, along with optional reference images or files, to the API and returns the generated image and any accompanying text. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt describing the image to generate or the edits to apply. Include any constraints, styles, or details the model should follow. | STRING | Yes | N/A | | `model` | The specific Gemini model to use for image generation. | COMBO | Yes | `"Nano Banana 2 (Gemini 3.1 Flash Image)"` | | `seed` | When the seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. (default: 42) | INT | Yes | 0 to 18446744073709551615 | @@ -27,7 +28,7 @@ The GeminiNanoBanana2 node generates or edits images using Google's Vertex AI Ge ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The primary image generated or edited by the model. | IMAGE | | `string` | Any text content returned by the model. | STRING | | `thought_image` | First image from the model's thinking process. Only available with thinking_level HIGH and IMAGE+TEXT modality. | IMAGE | @@ -35,4 +36,4 @@ The GeminiNanoBanana2 node generates or edits images using Google's Vertex AI Ge > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiNanoBanana2/en.md) --- -**Source fingerprint (SHA-256):** `6dae505011e2860cbf2ec6ccb5a32949d5daa3fe3546e85181050fd9ac92b9e5` +**Source fingerprint (SHA-256):** `3564bef74329f7019a2c9a67047d45e7342ee2e532126d597d0d21c995e1a5be` diff --git a/built-in-nodes/GeminiNanoBanana2V2.mdx b/built-in-nodes/GeminiNanoBanana2V2.mdx index bb6cb556a..aefb387d9 100644 --- a/built-in-nodes/GeminiNanoBanana2V2.mdx +++ b/built-in-nodes/GeminiNanoBanana2V2.mdx @@ -5,19 +5,22 @@ sidebarTitle: "GeminiNanoBanana2V2" icon: "circle" mode: wide --- + ## Overview -This node generates or edits images by sending a text prompt to Google's Vertex AI API. It uses a specific Gemini model to create new images or modify existing ones based on your instructions. +This node generates or edits images by sending a text prompt to Google's Vertex AI API. It uses the Gemini 3.1 Flash Image model to create new images or modify existing ones based on your instructions. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt describing the image to generate or the edits to apply. Include any constraints, styles, or details the model should follow. | STRING | Yes | N/A | -| `model` | Selects the Gemini model to use for image generation. Currently only one option is available. This parameter includes additional sub-parameters for resolution, aspect ratio, thinking level, and image input. | COMBO | Yes | `"Nano Banana 2 (Gemini 3.1 Flash Image)"` | +| `model` | Selects the Gemini model to use for image generation. This parameter includes additional sub-parameters for resolution, aspect ratio, thinking level, and image input. | COMBO | Yes | `"Nano Banana 2 (Gemini 3.1 Flash Image)"` | | `seed` | When the seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. (default: 42) | INT | Yes | 0 to 18446744073709551615 | | `response_modalities` | Determines the format of the response. Choose "IMAGE" to receive only an image, or "IMAGE+TEXT" to receive both an image and a text description. (default: "IMAGE") | COMBO | Yes | `"IMAGE"`
`"IMAGE+TEXT"` | | `system_prompt` | Foundational instructions that dictate an AI's behavior. This is an advanced parameter. (default: A pre-defined system prompt instructing the model to always produce an image) | STRING | No | N/A | +| `temperature` | Controls randomness in generation. Lower values produce more focused and deterministic results. This is an advanced parameter. (default: 1.0) | FLOAT | No | 0.0 to 2.0 | +| `top_p` | Nucleus sampling threshold. Lower values produce more focused results, higher values produce more diverse results. This is an advanced parameter. (default: 0.95) | FLOAT | No | 0.0 to 1.0 | **Note on `model` parameter:** The `model` parameter is a dynamic combo that includes additional sub-parameters for resolution, aspect ratio, thinking level, and image input. These sub-parameters are defined within the model selection and are not listed as separate inputs in this table. @@ -26,7 +29,7 @@ This node generates or edits images by sending a text prompt to Google's Vertex ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | The generated or edited image. | IMAGE | | `STRING` | A text description or caption generated by the model. | STRING | | `thought_image` | First image from the model's thinking process. Only available with thinking_level HIGH and IMAGE+TEXT modality. | IMAGE | @@ -34,4 +37,4 @@ This node generates or edits images by sending a text prompt to Google's Vertex > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiNanoBanana2V2/en.md) --- -**Source fingerprint (SHA-256):** `0b9af4e937874f2e192f3dc0b67f8e769b37d6595fbddb7a326b1f13e3e444d3` +**Source fingerprint (SHA-256):** `e3806713e8c58ac9ba0fe41875ef7162b7e18d276c63be53e46865efcc359079` diff --git a/built-in-nodes/GeminiNode.mdx b/built-in-nodes/GeminiNode.mdx index e9d60dadb..bc828f405 100644 --- a/built-in-nodes/GeminiNode.mdx +++ b/built-in-nodes/GeminiNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "GeminiNode" icon: "circle" mode: wide --- + This node allows users to interact with Google's Gemini AI models to generate text responses. You can provide multiple types of inputs including text, images, audio, video, and files as context for the model to generate more relevant and meaningful responses. The node handles all API communication and response parsing automatically. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text inputs to the model, used to generate a response. You can include detailed instructions, questions, or context for the model. Default: empty string. | STRING | Yes | - | | `model` | The Gemini model to use for generating responses. Default: gemini-3-1-pro. | COMBO | Yes | `gemini-2.5-pro-preview-05-06`
`gemini-2.5-flash-preview-04-17`
`gemini-2.5-pro`
`gemini-2.5-flash`
`gemini-3-pro-preview`
`gemini-3-1-pro`
`gemini-3-1-flash-lite` | | `seed` | When seed is fixed to a specific value, the model makes a best effort to provide the same response for repeated requests. Deterministic output isn't guaranteed. Also, changing the model or parameter settings, such as the temperature, can cause variations in the response even when you use the same seed value. By default, a random seed value is used. Default: 42. | INT | Yes | 0 to 18446744073709551615 | @@ -23,10 +24,10 @@ This node allows users to interact with Google's Gemini AI models to generate te ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `STRING` | The text response generated by the Gemini model. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiNode/en.md) --- -**Source fingerprint (SHA-256):** `c7f01d4d4f748a3a80c6e68ccd509cc1da03ed041bd2eaa8124887e7d02eb576` +**Source fingerprint (SHA-256):** `06d3894292600e7106b38b476443ceac21480878fa2933eb18eee7a0b9ca3c6a` diff --git a/built-in-nodes/GeminiNodeV2.mdx b/built-in-nodes/GeminiNodeV2.mdx index 4d83125f0..43aa5ee66 100644 --- a/built-in-nodes/GeminiNodeV2.mdx +++ b/built-in-nodes/GeminiNodeV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GeminiNodeV2" icon: "circle" mode: wide --- -# Google Gemini Generate text responses with Google's Gemini models. Provide a text prompt and, optionally, one or more images, audio clips, videos, or files as multimodal context. diff --git a/built-in-nodes/GeminiVideoOmni.mdx b/built-in-nodes/GeminiVideoOmni.mdx new file mode 100644 index 000000000..b2678b471 --- /dev/null +++ b/built-in-nodes/GeminiVideoOmni.mdx @@ -0,0 +1,33 @@ +--- +title: "GeminiVideoOmni - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the GeminiVideoOmni node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "GeminiVideoOmni" +icon: "circle" +mode: wide +--- + +Generate a video with audio from a text prompt using Google's Gemini Omni Flash model. Optionally provide reference images and/or videos to guide or edit the result. Describe the desired length (3-10s) and aspect ratio (16:9 or 9:16) directly in the prompt. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model` | The Gemini video model used to generate the video. | MODEL | Yes | "Omni Flash" | +| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed (default: 42). | INT | Yes | 0 to 2147483647 | +| `prompt` | The text prompt describing the video to generate. | STRING | Yes | Minimum 1 character after stripping whitespace | +| `images` | Optional reference images to guide the video generation. Maximum of 14 images total. | IMAGE | No | Multiple images allowed (max 14) | +| `videos` | Optional reference videos to guide or edit the video generation. Maximum of 3 videos, each up to 10 seconds. | VIDEO | No | Multiple videos allowed (max 3, each max 10s) | +| `temperature` | Controls randomness in generation (default: 1.0). | FLOAT | No | 0.0 to 2.0 | +| `top_p` | Nucleus sampling parameter (default: 0.95). | FLOAT | No | 0.0 to 1.0 | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `VIDEO` | The generated video with audio from the Gemini model. | VIDEO | +| `STRING` | Any text response from the model, such as reasoning or explanations. | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiVideoOmni/en.md) + +--- +**Source fingerprint (SHA-256):** `046842b7ec736283bba355aaa038b02fcf2416020f5f7aee7b0150d2a05bcbe6` diff --git a/built-in-nodes/GenerateTracks.mdx b/built-in-nodes/GenerateTracks.mdx index d8557e9e8..e5f10b26a 100644 --- a/built-in-nodes/GenerateTracks.mdx +++ b/built-in-nodes/GenerateTracks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GenerateTracks" icon: "circle" mode: wide --- + The `GenerateTracks` node creates multiple parallel motion paths for video generation. It defines a primary path from a start point to an end point, then generates a set of tracks that run parallel to this path, spaced evenly apart. You can control the shape of the path (straight line or Bezier curve), the speed of movement along it, and which frames the tracks are visible in. ## Inputs diff --git a/built-in-nodes/GetICLoRAParameters.mdx b/built-in-nodes/GetICLoRAParameters.mdx index 64e4517a4..0d4943af7 100644 --- a/built-in-nodes/GetICLoRAParameters.mdx +++ b/built-in-nodes/GetICLoRAParameters.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetICLoRAParameters" icon: "circle" mode: wide --- + ## Overview This node extracts IC-LoRA parameters from the metadata of a LoRA-loaded model. It reads the safetensors metadata to find values like the reference downscale factor and outputs them as a structured parameter object, which can be connected to the LTXVAddGuide node for special guide handling. diff --git a/built-in-nodes/GetImageSize.mdx b/built-in-nodes/GetImageSize.mdx index e8f517bb6..164e735fc 100644 --- a/built-in-nodes/GetImageSize.mdx +++ b/built-in-nodes/GetImageSize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetImageSize" icon: "circle" mode: wide --- + The GetImageSize node extracts the dimensions and batch information from an input image. It returns the width, height, and batch size of the image while also displaying this information as progress text on the node interface. The original image data passes through unchanged. ## Inputs diff --git a/built-in-nodes/GetSplatCount.mdx b/built-in-nodes/GetSplatCount.mdx index d3b608688..ed1154584 100644 --- a/built-in-nodes/GetSplatCount.mdx +++ b/built-in-nodes/GetSplatCount.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GetSplatCount" icon: "circle" mode: wide --- -# Get Splat Count The Get Splat Count node returns the total number of splats (gaussian points) in a splat batch, summed across all items in the batch. It passes the original splat data through unchanged while providing a count of how many individual splats it contains. diff --git a/built-in-nodes/GetVideoComponents.mdx b/built-in-nodes/GetVideoComponents.mdx index 08fb2fc73..bb699f9ae 100644 --- a/built-in-nodes/GetVideoComponents.mdx +++ b/built-in-nodes/GetVideoComponents.mdx @@ -5,23 +5,25 @@ sidebarTitle: "GetVideoComponents" icon: "circle" mode: wide --- -The Get Video Components node extracts all the main elements from a video file. It separates the video into individual frames, extracts the audio track, and provides the video's framerate information. This allows you to work with each component independently for further processing or analysis. + +The Get Video Components node extracts all the main elements from a video file. It separates the video into individual frames, extracts the audio track, and provides the video's framerate and bit depth information. This allows you to work with each component independently for further processing or analysis. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `video` | The video to extract components from. | VIDEO | Yes | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `images` | The individual frames extracted from the video as separate images. | IMAGE | | `audio` | The audio track extracted from the video. | AUDIO | | `fps` | The framerate of the video in frames per second. | FLOAT | +| `bit_depth` | The bit depth of the video. | INT | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetVideoComponents/en.md) --- -**Source fingerprint (SHA-256):** `de129130ed4b82d875c4e8c660209b88172e3cdd41fed8c822fb7e807c92ed47` +**Source fingerprint (SHA-256):** `b2232b2c558b472226418d56910b9b763d8398612b31c4019d4881d0c4717b8d` diff --git a/built-in-nodes/GrokImageEditNode.mdx b/built-in-nodes/GrokImageEditNode.mdx index 313bab03d..7748287a7 100644 --- a/built-in-nodes/GrokImageEditNode.mdx +++ b/built-in-nodes/GrokImageEditNode.mdx @@ -5,13 +5,14 @@ sidebarTitle: "GrokImageEditNode" icon: "circle" mode: wide --- + The Grok Image Edit node modifies an existing image based on a text prompt. It uses the Grok API to generate one or more new images that are variations of the input, guided by your description. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `model` | The specific AI model to use for image editing. | COMBO | Yes | `"grok-imagine-image-quality"`
`"grok-imagine-image-pro"`
`"grok-imagine-image"`
`"grok-imagine-image-beta"` | +|-----------|-------------|-----------|----------|-------| +| `model` | The specific AI model to use for image editing. | COMBO | Yes | `"grok-imagine-image-quality"`
`"grok-imagine-image-pro"`
`"grok-imagine-image"` | | `image` | The input image(s) to be edited. Supports up to 3 input images, except for the "pro" model which supports only 1. | IMAGE | Yes | | | `prompt` | The text prompt used to generate the edited image. Must be at least 1 character after stripping whitespace. | STRING | Yes | | | `resolution` | The resolution for the output image. | COMBO | Yes | `"1K"`
`"2K"` | @@ -26,10 +27,10 @@ The Grok Image Edit node modifies an existing image based on a text prompt. It u ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The edited image(s) generated by the node. If `number_of_images` is greater than 1, the outputs are concatenated into a batch. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokImageEditNode/en.md) --- -**Source fingerprint (SHA-256):** `31cfe7ad382033f69330ed4de1ec831ccc25156498563e1541368e2662ed3ddb` +**Source fingerprint (SHA-256):** `5b2eb9418302bba0e18f43edeab7dc73c9b14ebc78b1ce6cc8a3e5bb411f0351` diff --git a/built-in-nodes/GrokImageEditNodeV2.mdx b/built-in-nodes/GrokImageEditNodeV2.mdx index 55a87ebe4..908cce24c 100644 --- a/built-in-nodes/GrokImageEditNodeV2.mdx +++ b/built-in-nodes/GrokImageEditNodeV2.mdx @@ -5,14 +5,13 @@ sidebarTitle: "GrokImageEditNodeV2" icon: "circle" mode: wide --- -## Overview Modify an existing image based on a text prompt. This node sends your images and a text description to the Grok API, which edits the images according to your instructions and returns the result. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | The text prompt used to generate the image. Must be at least 1 character long after stripping whitespace. | STRING | Yes | N/A | | `model` | The Grok image model to use. This parameter has multiple sub-options that appear after selecting a model. Available models: `grok-imagine-image-quality`
`grok-imagine-image-pro`
`grok-imagine-image`. Each model has different capabilities (see note below). | MODEL | Yes | See Description | | `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. (default: 0) | INT | Yes | 0 to 2147483647 | @@ -28,10 +27,10 @@ Modify an existing image based on a text prompt. This node sends your images and ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | The edited image(s) returned by the Grok API. If a single image is generated, it is returned directly. If multiple images are generated, they are concatenated into a single batch tensor. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokImageEditNodeV2/en.md) --- -**Source fingerprint (SHA-256):** `90ace53f5f2e40da315d4940fa801d84950de6db2d8ed1cf9d715d88a2b1ebf0` +**Source fingerprint (SHA-256):** `60ff1c0dd97398130aee3cbab46ab273b99ec0a41b105eb1cdb7bd08a7d2c038` diff --git a/built-in-nodes/GrokImageNode.mdx b/built-in-nodes/GrokImageNode.mdx index 22a83f550..fd8c08af6 100644 --- a/built-in-nodes/GrokImageNode.mdx +++ b/built-in-nodes/GrokImageNode.mdx @@ -5,17 +5,18 @@ sidebarTitle: "GrokImageNode" icon: "circle" mode: wide --- + The Grok Image node generates one or more images based on a text description using the Grok AI model. It sends your prompt to an external service and returns the generated images as tensors that can be used in your workflow. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `model` | The specific Grok model to use for image generation. Different models may offer varying quality, speed, or features. | COMBO | Yes | `"grok-imagine-image-quality"`
`"grok-imagine-image-pro"`
`"grok-imagine-image"`
`"grok-imagine-image-beta"` | +|-----------|-------------|-----------|----------|-------| +| `model` | The specific Grok model to use for image generation. Different models may offer varying quality, speed, or features. | COMBO | Yes | `"grok-imagine-image-quality"`
`"grok-imagine-image-pro"`
`"grok-imagine-image"` | | `prompt` | The text prompt used to generate the image. This description guides the AI on what to create. Must be at least 1 character long. | STRING | Yes | N/A | | `aspect_ratio` | The desired width-to-height ratio for the generated image. | COMBO | Yes | `"1:1"`
`"2:3"`
`"3:2"`
`"3:4"`
`"4:3"`
`"9:16"`
`"16:9"`
`"9:19.5"`
`"19.5:9"`
`"9:20"`
`"20:9"`
`"1:2"`
`"2:1"` | | `number_of_images` | Number of images to generate (default: 1). | INT | No | 1 to 10 | -| `seed` | A seed value to determine if the node should re-run. The actual image results are nondeterministic and will vary even with the same seed (default: 0). | INT | No | 0 to 2147483647 | +| `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0). | INT | No | 0 to 2147483647 | | `resolution` | The desired output resolution for the generated images (default: "1K"). | COMBO | No | `"1K"`
`"2K"` | **Note:** The `seed` parameter is primarily used to control when the node re-executes within a workflow. Due to the nature of the external AI service, the generated images will not be reproducible or identical across runs, even with an identical seed. @@ -25,10 +26,10 @@ The Grok Image node generates one or more images based on a text description usi ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated image or a batch of images. If `number_of_images` is 1, a single image tensor is returned. If greater than 1, a batch of image tensors is returned. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokImageNode/en.md) --- -**Source fingerprint (SHA-256):** `f4af858c6b94fd74be1856849417609f3d45fc0f139e8f2e56cdabb6e3521076` +**Source fingerprint (SHA-256):** `e7f3e249c56ee0f9f4e703d6c478cc0f160f95ee605acd5176f4f62212b8b3cf` diff --git a/built-in-nodes/GrokVideoEditNode.mdx b/built-in-nodes/GrokVideoEditNode.mdx index f0b86a9c1..79cb3764c 100644 --- a/built-in-nodes/GrokVideoEditNode.mdx +++ b/built-in-nodes/GrokVideoEditNode.mdx @@ -5,16 +5,17 @@ sidebarTitle: "GrokVideoEditNode" icon: "circle" mode: wide --- + This node uses the Grok API to edit an existing video based on a text prompt. It uploads your video, sends a request to the AI model to modify it according to your description, and returns the newly generated video. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `model` | The AI model to use for video editing (default: `"grok-imagine-video"`). | COMBO | Yes | `"grok-imagine-video"`
`"grok-imagine-video-beta"` | +|-----------|-------------|-----------|----------|-------| +| `model` | The AI model to use for video editing (default: `"grok-imagine-video"`). | STRING | Yes | `"grok-imagine-video"` | | `prompt` | Text description of the desired video. | STRING | Yes | N/A | | `video` | The input video to be edited. Maximum supported duration is 8.7 seconds and 50MB file size. | VIDEO | Yes | N/A | -| `seed` | A seed value to determine if the node should re-run. The actual results are nondeterministic regardless of the seed value (default: 0). | INT | No | 0 to 2147483647 | +| `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0). | INT | No | 0 to 2147483647 | **Constraints:** @@ -25,10 +26,10 @@ This node uses the Grok API to edit an existing video based on a text prompt. It ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The edited video generated by the AI model. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoEditNode/en.md) --- -**Source fingerprint (SHA-256):** `04cdc989b48445562017cd2c2066c773473c5c241ed94ff6eca00b8aadf4c6df` +**Source fingerprint (SHA-256):** `488aa152744e5a17a9fbc55f8cbc3e863e1212f58544e47aa377276e8990834c` diff --git a/built-in-nodes/GrokVideoExtendNode.mdx b/built-in-nodes/GrokVideoExtendNode.mdx index 9702465a7..4a1222193 100644 --- a/built-in-nodes/GrokVideoExtendNode.mdx +++ b/built-in-nodes/GrokVideoExtendNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "GrokVideoExtendNode" icon: "circle" mode: wide --- + The Grok Video Extend node uses an AI model to create a seamless continuation of an existing video. You provide a short video and a text prompt describing what should happen next, and the node generates a new video clip that follows on from the original. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text description of what should happen next in the video. | STRING | Yes | N/A | | `video` | Source video to extend. MP4 format, 2-15 seconds. | VIDEO | Yes | N/A | | `model` | The model to use for video extension. When selected, it reveals a nested `duration` parameter. | COMBO | Yes | `"grok-imagine-video"` | @@ -24,10 +25,10 @@ The Grok Video Extend node uses an AI model to create a seamless continuation of ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The newly generated video extension. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoExtendNode/en.md) --- -**Source fingerprint (SHA-256):** `7e56ecb0cb31795b4124671e074ef274d6de61ec2cd734b6edd5e76a3cb6a7ba` +**Source fingerprint (SHA-256):** `bfaf56dd12afab13c820345587db9ee871db87d60b8dc003f00f035513dbdf61` diff --git a/built-in-nodes/GrokVideoNode.mdx b/built-in-nodes/GrokVideoNode.mdx index 069659955..fec37d0a5 100644 --- a/built-in-nodes/GrokVideoNode.mdx +++ b/built-in-nodes/GrokVideoNode.mdx @@ -5,29 +5,30 @@ sidebarTitle: "GrokVideoNode" icon: "circle" mode: wide --- + The Grok Video node generates a short video from a text description. It can create a video from scratch using a prompt or animate a single input image based on a prompt. The node sends a request to an external API and returns the generated video. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `model` | The model to use for video generation. | COMBO | Yes | `"grok-imagine-video"`
`"grok-imagine-video-beta"` | +|-----------|-------------|-----------|----------|-------| +| `model` | The model to use for video generation. | COMBO | Yes | `"grok-imagine-video"`
`"grok-imagine-video-1.5"` | | `prompt` | Text description of the desired video. | STRING | Yes | - | | `resolution` | The resolution of the output video. | COMBO | Yes | `"480p"`
`"720p"` | | `aspect_ratio` | The aspect ratio of the output video (default: "auto"). | COMBO | Yes | `"auto"`
`"16:9"`
`"4:3"`
`"3:2"`
`"1:1"`
`"2:3"`
`"3:4"`
`"9:16"` | | `duration` | The duration of the output video in seconds (default: 6). | INT | Yes | 1 to 15 | | `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0). | INT | Yes | 0 to 2147483647 | -| `image` | An optional input image to animate. | IMAGE | No | - | +| `image` | Optional starting image for grok-imagine-video. Required for grok-imagine-video-1.5. | IMAGE | No | - | -**Note:** If an `image` is provided, only one image is supported. Providing multiple images will cause an error. The `prompt` must be at least 1 character long after stripping whitespace. +**Note:** The `grok-imagine-video-1.5` model always requires an input image. If an `image` is provided, only one image is supported. Providing multiple images will cause an error. The `prompt` must be at least 1 character long after stripping whitespace. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `7b4bcd25cfe620b4593c16a2cb2a288e47f9791ae2c60d56b79009bc62bac6e2` +**Source fingerprint (SHA-256):** `1f9bdd4698f01a36b0bd9a696a7acb04330073794c11ede229949999ffce5be4` diff --git a/built-in-nodes/GrokVideoReferenceNode.mdx b/built-in-nodes/GrokVideoReferenceNode.mdx index 3375790ac..1cae9f221 100644 --- a/built-in-nodes/GrokVideoReferenceNode.mdx +++ b/built-in-nodes/GrokVideoReferenceNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "GrokVideoReferenceNode" icon: "circle" mode: wide --- + The Grok Reference-to-Video node generates a video based on a text prompt, using up to seven reference images to guide the style and content of the output. It connects to an external API to create the video, which is then downloaded and returned. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text description of the desired video. | STRING | Yes | N/A | | `model` | The model to use for video generation. | COMBO | Yes | `"grok-imagine-video"` | | `model.reference_images` | Up to 7 reference images to guide the video generation. | IMAGE | Yes | 1 to 7 images | @@ -24,10 +25,10 @@ The Grok Reference-to-Video node generates a video based on a text prompt, using ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoReferenceNode/en.md) --- -**Source fingerprint (SHA-256):** `df50e80ca403d05469881e1c456ca4777d70989d8950c5e3844271c3ff8df85a` +**Source fingerprint (SHA-256):** `4945105faa7dc97012f08e1e1a8f2ca2161045122a6b73c7768f1268d1d0d68b` diff --git a/built-in-nodes/GrowMask.mdx b/built-in-nodes/GrowMask.mdx index 5082ff7aa..43455b076 100644 --- a/built-in-nodes/GrowMask.mdx +++ b/built-in-nodes/GrowMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrowMask" icon: "circle" mode: wide --- + The `GrowMask` node is designed to modify the size of a given mask, either expanding or contracting it, while optionally applying a tapered effect to the corners. This functionality is crucial for dynamically adjusting mask boundaries in image processing tasks, allowing for more flexible and precise control over the area of interest. ## Inputs diff --git a/built-in-nodes/HappyHorseImageToVideoApi.mdx b/built-in-nodes/HappyHorseImageToVideoApi.mdx index 9711d1355..993f46211 100644 --- a/built-in-nodes/HappyHorseImageToVideoApi.mdx +++ b/built-in-nodes/HappyHorseImageToVideoApi.mdx @@ -5,14 +5,13 @@ sidebarTitle: "HappyHorseImageToVideoApi" icon: "circle" mode: wide --- -## Overview This node generates a short video from a single starting image using the HappyHorse model. You provide a first frame image and a text prompt describing the desired motion and scene, and the node creates a video that continues from that image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The HappyHorse model to use for video generation. | COMBO | Yes | `"happyhorse-1.0-i2v"` | | `model.prompt` | Prompt describing the elements and visual features. Supports English and Chinese. (default: "") | STRING | No | N/A | | `model.resolution` | The output video resolution. (default: "720P") | COMBO | Yes | `"720P"`
`"1080P"` | @@ -24,10 +23,10 @@ This node generates a short video from a single starting image using the HappyHo ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HappyHorseImageToVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `b8764d68024b7d2a526b6cc3e1e56c3240b1aa55f31a07263e7014d4f6c67509` +**Source fingerprint (SHA-256):** `bba88bba1028475b26d56ec960a3f7dc160b5f3fa3f2c8f52ffdf4b70863e9a1` diff --git a/built-in-nodes/HappyHorseReferenceVideoApi.mdx b/built-in-nodes/HappyHorseReferenceVideoApi.mdx index ed0056433..18439188e 100644 --- a/built-in-nodes/HappyHorseReferenceVideoApi.mdx +++ b/built-in-nodes/HappyHorseReferenceVideoApi.mdx @@ -5,30 +5,29 @@ sidebarTitle: "HappyHorseReferenceVideoApi" icon: "circle" mode: wide --- -## Overview -This node generates a video featuring a person or object based on reference images using the HappyHorse model. It supports creating videos with a single character or multiple characters interacting with each other. +This node generates a video featuring a person or object from reference images using the HappyHorse model. It supports creating videos with single-character performances and multi-character interactions. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The HappyHorse model to use for video generation. | COMBO | Yes | `"happyhorse-1.0-r2v"` | -| `prompt` | A text description of the video you want to generate. Use identifiers like 'character1' and 'character2' to refer to the reference characters. | STRING | Yes | N/A | +| `prompt` | Prompt describing the video. Use identifiers such as 'character1' and 'character2' to refer to the reference characters. | STRING | Yes | N/A | | `resolution` | The resolution of the generated video. | COMBO | Yes | `"720P"`
`"1080P"` | | `ratio` | The aspect ratio of the generated video. | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"`
`"4:3"`
`"3:4"` | | `duration` | The duration of the generated video in seconds (default: 5). | INT | Yes | 3 to 15 | -| `reference_images` | One or more reference images of the person or object to feature in the video. You must provide at least one image. | IMAGE | Yes | 1 to 9 | -| `seed` | A seed value for reproducible generation (default: 0). The seed can be set to automatically change after each generation. | INT | No | 0 to 2147483647 | -| `watermark` | Whether to add an AI-generated watermark to the resulting video (default: False). | BOOLEAN | No | True or False | +| `reference_images` | One or more reference images of the person or object to feature in the video. At least one image must be provided. | IMAGE | Yes | 1 to 9 | +| `seed` | Seed to use for generation (default: 0). Can be set to automatically change after each generation. | INT | No | 0 to 2147483647 | +| `watermark` | Whether to add an AI-generated watermark to the result (default: False). | BOOLEAN | No | True or False | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `VIDEO` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HappyHorseReferenceVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `42c844db22ed2284bd16bd28fe0060652248ada0d5d31003134768ed5e44356c` +**Source fingerprint (SHA-256):** `61e22c2424191b59b3c6f6be1917e47d26436eba5360c1e173b59b4de40216f2` diff --git a/built-in-nodes/HappyHorseTextToVideoApi.mdx b/built-in-nodes/HappyHorseTextToVideoApi.mdx index a0745a5ad..2f0f47795 100644 --- a/built-in-nodes/HappyHorseTextToVideoApi.mdx +++ b/built-in-nodes/HappyHorseTextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseTextToVideoApi" icon: "circle" mode: wide --- + ## Overview Generates a video based on a text prompt using the HappyHorse model. This node sends your prompt and settings to the HappyHorse API, waits for the video to be generated, and then downloads the result. @@ -12,7 +13,7 @@ Generates a video based on a text prompt using the HappyHorse model. This node s ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | A dictionary containing the model selection and its associated parameters. The model must be `"happyhorse-1.0-t2v"`. This dictionary includes the following sub-parameters:

**`prompt`** (STRING): The text description of the video you want to generate. Supports English and Chinese. (default: "").
**`resolution`** (COMBO): The resolution of the output video. Options: `"720P"`
`"1080P"`.
**`ratio`** (COMBO): The aspect ratio of the output video. Options: `"16:9"`
`"9:16"`
`"1:1"`
`"4:3"`
`"3:4"`.
**`duration`** (INT): The length of the video in seconds. (default: 5, min: 3, max: 15, step: 1). | DICT | Yes | See Description | | `seed` | Seed to use for generation. Using the same seed with the same inputs will produce the same result. (default: 0). | INT | Yes | 0 to 2147483647 | | `watermark` | Whether to add an AI-generated watermark to the result. (default: False). | BOOLEAN | No | True / False | @@ -20,10 +21,10 @@ Generates a video based on a text prompt using the HappyHorse model. This node s ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `VIDEO` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HappyHorseTextToVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `8e2c0aaab2c8918079c5ec02916375e9a11b0e745d3296155f37c0128a9dbc3c` +**Source fingerprint (SHA-256):** `2ef0dbac9a3c35ca67364530a9c6bb4693266e093456dc1a2c95e499b3b2d493` diff --git a/built-in-nodes/HappyHorseVideoEditApi.mdx b/built-in-nodes/HappyHorseVideoEditApi.mdx index d23fe0a51..3d7cfda2d 100644 --- a/built-in-nodes/HappyHorseVideoEditApi.mdx +++ b/built-in-nodes/HappyHorseVideoEditApi.mdx @@ -5,25 +5,24 @@ sidebarTitle: "HappyHorseVideoEditApi" icon: "circle" mode: wide --- -## Overview -Edit a video using text instructions or reference images with the HappyHorse model. The output duration is 3-15 seconds and matches the input video; inputs longer than 15 seconds are truncated. +Edit a video using text instructions or reference images with the HappyHorse model. Output duration is 3-15 seconds and matches the input video; inputs longer than 15 seconds are truncated. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model configuration containing the model selection, prompt, resolution, aspect ratio, and optional reference images. | DICT | Yes | See below | | `video` | The video to edit. | VIDEO | Yes | - | | `seed` | Seed to use for generation (default: 0). | INT | Yes | 0 to 2147483647 | -| `watermark` | Whether to add an AI-generated watermark to the result (default: False). | BOOLEAN | No | True / False | +| `watermark` | Whether to add an AI-generated watermark to the result (default: False). | BOOLEAN | No | True
False | ### `model` Parameter Details The `model` parameter is a dictionary with the following fields: | Field | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-------|-------------|-----------|----------|-------| | `model` | The HappyHorse video editing model to use. | STRING | Yes | `"happyhorse-1.0-video-edit"` | | `prompt` | Editing instructions or style transfer requirements. Must be at least 1 character long. | STRING | Yes | - | | `resolution` | The output resolution. | STRING | Yes | `"720P"`
`"1080P"` | @@ -33,10 +32,10 @@ The `model` parameter is a dictionary with the following fields: ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The edited video output. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HappyHorseVideoEditApi/en.md) --- -**Source fingerprint (SHA-256):** `eadb446a8dbcc524a8bb6a2ee48941136f8c1ec2cb64aa9061fb1fa22e1b683d` +**Source fingerprint (SHA-256):** `396cad4b5a06d457746a421050df98c892fa9db6019e3de983b4d0c417842b57` diff --git a/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx b/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx index 6dd15a94d..44e9216e6 100644 --- a/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx +++ b/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HiDreamO1PatchSeamSmoothing" icon: "circle" mode: wide --- + ## Overview This node reduces visible seams in images generated by the HiDream-O1 model by averaging the model's output across multiple shifted patch-grid positions during the later part of the sampling process. It works by running the model several times with slightly different image alignments and blending the results together, which helps cancel out the grid-like artifacts that can appear at patch boundaries. diff --git a/built-in-nodes/HiDreamO1ReferenceImages.mdx b/built-in-nodes/HiDreamO1ReferenceImages.mdx index c17d9f7a7..746b870cc 100644 --- a/built-in-nodes/HiDreamO1ReferenceImages.mdx +++ b/built-in-nodes/HiDreamO1ReferenceImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HiDreamO1ReferenceImages" icon: "circle" mode: wide --- + ## Overview Attach reference images to both positive and negative conditioning. This node allows you to provide one or more reference images that will be used to guide the image generation process, either for editing based on an instruction or for subject-driven personalization. diff --git a/built-in-nodes/HitPawGeneralImageEnhance.mdx b/built-in-nodes/HitPawGeneralImageEnhance.mdx index 279cabfdc..02bf74fc2 100644 --- a/built-in-nodes/HitPawGeneralImageEnhance.mdx +++ b/built-in-nodes/HitPawGeneralImageEnhance.mdx @@ -5,12 +5,13 @@ sidebarTitle: "HitPawGeneralImageEnhance" icon: "circle" mode: wide --- + This node enhances low-resolution images by upscaling them to super-resolution, removing artifacts and noise. It uses an external API to process the image and can automatically adjust the input size to stay within processing limits. The maximum allowed output size is 32 megapixels. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The enhancement model to use. The `generative_portrait` model is optimized for portraits, while `generative` is a general-purpose model. | STRING | Yes | `"generative_portrait"`
`"generative"` | | `image` | The input image to be enhanced. | IMAGE | Yes | - | | `upscale_factor` | The factor by which to upscale the image's dimensions. A factor of 1 means no upscaling, 2 doubles the dimensions, and 4 quadruples them. | INT | Yes | `1`
`2`
`4` | @@ -21,10 +22,10 @@ This node enhances low-resolution images by upscaling them to super-resolution, ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The enhanced and upscaled output image. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HitPawGeneralImageEnhance/en.md) --- -**Source fingerprint (SHA-256):** `1cb59c04e517b6ecce3a4cb809d3cad26bb7a0fe6d16ddf72b9729e186e25d53` +**Source fingerprint (SHA-256):** `effdb98c6400d3b4e3ad238be7049187af6512efacad45996f2a49a0b18b67b3` diff --git a/built-in-nodes/HitPawVideoEnhance.mdx b/built-in-nodes/HitPawVideoEnhance.mdx index 23d94cc05..22426723b 100644 --- a/built-in-nodes/HitPawVideoEnhance.mdx +++ b/built-in-nodes/HitPawVideoEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HitPawVideoEnhance" icon: "circle" mode: wide --- + The HitPaw Video Enhance node uses an external API to improve the quality of videos. It upscales low-resolution videos to a higher resolution, removes visual artifacts, and reduces noise. The processing cost is calculated per second of the input video. ## Inputs @@ -29,4 +30,4 @@ The HitPaw Video Enhance node uses an external API to improve the quality of vid > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HitPawVideoEnhance/en.md) --- -**Source fingerprint (SHA-256):** `49291b3c610d32cf60fb4786333cb7e3d18c9de39c15577dabbd9f27bc9eac75` +**Source fingerprint (SHA-256):** `3326833e8e542e0642e34a6cc444115376fd03c26e3c8f27592fe8e3a72d593b` diff --git a/built-in-nodes/Hunyuan3Dv2Conditioning.mdx b/built-in-nodes/Hunyuan3Dv2Conditioning.mdx index 47eb503da..3d9214305 100644 --- a/built-in-nodes/Hunyuan3Dv2Conditioning.mdx +++ b/built-in-nodes/Hunyuan3Dv2Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Hunyuan3Dv2Conditioning" icon: "circle" mode: wide --- + The Hunyuan3Dv2Conditioning node processes CLIP vision output to generate conditioning data for 3D models. It extracts the last hidden state embeddings from the vision output and creates both positive and negative conditioning pairs. The positive conditioning uses the actual embeddings while the negative conditioning uses zero-valued embeddings of the same shape. ## Inputs diff --git a/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx b/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx index e0fa0f1ec..9be0b59f2 100644 --- a/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx +++ b/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Hunyuan3Dv2ConditioningMultiView" icon: "circle" mode: wide --- + The Hunyuan3Dv2ConditioningMultiView node processes multi-view CLIP vision embeddings for 3D video generation. It takes optional front, left, back, and right view embeddings and combines them with positional encoding to create conditioning data for video models. The node outputs both positive conditioning from the combined embeddings and negative conditioning with zero values. ## Inputs diff --git a/built-in-nodes/HunyuanImageToVideo.mdx b/built-in-nodes/HunyuanImageToVideo.mdx index 7ca2fe242..644965ee7 100644 --- a/built-in-nodes/HunyuanImageToVideo.mdx +++ b/built-in-nodes/HunyuanImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanImageToVideo" icon: "circle" mode: wide --- + The HunyuanImageToVideo node converts images into video latent representations using the Hunyuan video model. It takes conditioning inputs and optional starting images to generate video latents that can be further processed by video generation models. The node supports different guidance types for controlling how the starting image influences the video generation process. ## Inputs diff --git a/built-in-nodes/HunyuanRefinerLatent.mdx b/built-in-nodes/HunyuanRefinerLatent.mdx index 3e4936a7e..dab1e2d9a 100644 --- a/built-in-nodes/HunyuanRefinerLatent.mdx +++ b/built-in-nodes/HunyuanRefinerLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanRefinerLatent" icon: "circle" mode: wide --- + The HunyuanRefinerLatent node processes conditioning and latent inputs for refinement operations. It applies noise augmentation to both positive and negative conditioning while incorporating latent image data, and generates a new latent output with specific dimensions for further processing. ## Inputs diff --git a/built-in-nodes/HunyuanVideo15ImageToVideo.mdx b/built-in-nodes/HunyuanVideo15ImageToVideo.mdx index 645b6bba1..25fd001d8 100644 --- a/built-in-nodes/HunyuanVideo15ImageToVideo.mdx +++ b/built-in-nodes/HunyuanVideo15ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15ImageToVideo" icon: "circle" mode: wide --- + The HunyuanVideo15ImageToVideo node prepares conditioning and latent space data for video generation based on the HunyuanVideo 1.5 model. It creates an initial latent representation for a video sequence and can optionally integrate a starting image or a CLIP vision output to guide the generation process. ## Inputs diff --git a/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx b/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx index 5ca85bace..3e3ee5049 100644 --- a/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx +++ b/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15LatentUpscaleWithModel" icon: "circle" mode: wide --- + The Hunyuan Video 15 Latent Upscale With Model node increases the resolution of a latent image representation. It first upscales the latent samples to a specified size using a chosen interpolation method, then refines the upscaled result using a specialized Hunyuan Video 1.5 upscale model to improve quality. ## Inputs diff --git a/built-in-nodes/HunyuanVideo15SuperResolution.mdx b/built-in-nodes/HunyuanVideo15SuperResolution.mdx index ac7994c2b..f4e4d5b4b 100644 --- a/built-in-nodes/HunyuanVideo15SuperResolution.mdx +++ b/built-in-nodes/HunyuanVideo15SuperResolution.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15SuperResolution" icon: "circle" mode: wide --- + The HunyuanVideo15SuperResolution node prepares conditioning data for a video super-resolution process. It takes a latent representation of a video and, optionally, a starting image, and packages them along with noise augmentation and CLIP vision data into a format that can be used by a model to generate a higher-resolution output. ## Inputs diff --git a/built-in-nodes/HyperTile.mdx b/built-in-nodes/HyperTile.mdx index d8234e639..ccdd52825 100644 --- a/built-in-nodes/HyperTile.mdx +++ b/built-in-nodes/HyperTile.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HyperTile" icon: "circle" mode: wide --- + The HyperTile node applies a tiling technique to the attention mechanism in diffusion models to optimize memory usage during image generation. It divides the latent space into smaller tiles and processes them separately, then reassembles the results. This allows for working with larger image sizes without running out of memory. ## Inputs diff --git a/built-in-nodes/HypernetworkLoader.mdx b/built-in-nodes/HypernetworkLoader.mdx index 2b85ebe65..51a42970d 100644 --- a/built-in-nodes/HypernetworkLoader.mdx +++ b/built-in-nodes/HypernetworkLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HypernetworkLoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/hypernetworks` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. The HypernetworkLoader node is designed to enhance or modify the capabilities of a given model by applying a hypernetwork. It loads a specified hypernetwork and applies it to the model, potentially altering its behavior or performance based on the strength parameter. This process allows for dynamic adjustments to the model's architecture or parameters, enabling more flexible and adaptive AI systems. diff --git a/built-in-nodes/Ideogram4Scheduler.mdx b/built-in-nodes/Ideogram4Scheduler.mdx index 701849c34..4ba8e13a0 100644 --- a/built-in-nodes/Ideogram4Scheduler.mdx +++ b/built-in-nodes/Ideogram4Scheduler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Ideogram4Scheduler" icon: "circle" mode: wide --- -# Ideogram 4 Scheduler The Ideogram 4 Scheduler node generates a sequence of sigma values (noise levels) for the diffusion sampling process, based on the Ideogram 4 reference schedule. It creates a custom noise schedule that adapts to the image dimensions and allows fine-tuning through statistical parameters. diff --git a/built-in-nodes/IdeogramV1.mdx b/built-in-nodes/IdeogramV1.mdx index bf50c9404..8b270edd2 100644 --- a/built-in-nodes/IdeogramV1.mdx +++ b/built-in-nodes/IdeogramV1.mdx @@ -5,12 +5,13 @@ sidebarTitle: "IdeogramV1" icon: "circle" mode: wide --- + The IdeogramV1 node generates images using the Ideogram V1 model through an API. It takes text prompts and various generation settings to create one or more images based on your input. The node supports different aspect ratios and generation modes to customize the output. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation (default: empty) | STRING | Yes | - | | `turbo` | Whether to use turbo mode (faster generation, potentially lower quality) (default: False) | BOOLEAN | Yes | - | | `aspect_ratio` | The aspect ratio for image generation (default: "1:1") | COMBO | No | "1:1"
"4:3"
"3:4"
"16:9"
"9:16"
"2:1"
"1:2"
"3:2"
"2:3"
"4:5"
"5:4" | @@ -24,10 +25,10 @@ The IdeogramV1 node generates images using the Ideogram V1 model through an API. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated image(s) from the Ideogram V1 model | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV1/en.md) --- -**Source fingerprint (SHA-256):** `a42654aea292811c5f872911d6ea7303a83ea058c7132737375d81c5c8a77740` +**Source fingerprint (SHA-256):** `c9b336054cf5d66228aeccab615985d2e9c9bdf7dce5d607212fed8a35c2c793` diff --git a/built-in-nodes/IdeogramV2.mdx b/built-in-nodes/IdeogramV2.mdx index 022d54bf8..84938418d 100644 --- a/built-in-nodes/IdeogramV2.mdx +++ b/built-in-nodes/IdeogramV2.mdx @@ -5,12 +5,13 @@ sidebarTitle: "IdeogramV2" icon: "circle" mode: wide --- + The Ideogram V2 node generates images using the Ideogram V2 AI model. It takes text prompts and various generation settings to create images through an API service. The node supports different aspect ratios, resolutions, and style options to customize the output images. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation (default: empty string) | STRING | Yes | - | | `turbo` | Whether to use turbo mode (faster generation, potentially lower quality) (default: False) | BOOLEAN | No | - | | `aspect_ratio` | The aspect ratio for image generation. Ignored if resolution is not set to AUTO. (default: "1:1") | COMBO | No | "1:1"
"4:3"
"3:4"
"16:9"
"9:16"
"2:1"
"1:2"
"3:2"
"2:3"
"4:5"
"5:4" | @@ -26,10 +27,10 @@ The Ideogram V2 node generates images using the Ideogram V2 AI model. It takes t ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated image(s) from the Ideogram V2 model | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV2/en.md) --- -**Source fingerprint (SHA-256):** `6d1f0d536756252434a1a831cd96228ee2386bfcaa60555acfe4bab7d16b61e3` +**Source fingerprint (SHA-256):** `a034a57996ac0b3902cab36096ac6b8401bb544faa00b8ed213bf752fdd423e2` diff --git a/built-in-nodes/IdeogramV3.mdx b/built-in-nodes/IdeogramV3.mdx index 8e8588988..b0cf3a9b8 100644 --- a/built-in-nodes/IdeogramV3.mdx +++ b/built-in-nodes/IdeogramV3.mdx @@ -5,12 +5,13 @@ sidebarTitle: "IdeogramV3" icon: "circle" mode: wide --- + The Ideogram V3 node generates images using the Ideogram V3 model. It supports both regular image generation from text prompts and image editing when both an image and mask are provided. The node offers various controls for aspect ratio, resolution, generation speed, and optional character reference images. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation or editing (default: empty) | STRING | Yes | - | | `image` | Optional reference image for image editing | IMAGE | No | - | | `mask` | Optional mask for inpainting (white areas will be replaced) | MASK | No | - | @@ -35,10 +36,10 @@ The Ideogram V3 node generates images using the Ideogram V3 model. It supports b ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated or edited image(s) | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/IdeogramV3/en.md) --- -**Source fingerprint (SHA-256):** `b3ddd489ee96b4b378ae432254d8e97bccafc20e38055b213c0ad3b7818cb4c0` +**Source fingerprint (SHA-256):** `d5005a9cdbdad79762dfd24eaa73e6c293d28b72813e96883ecdfccb8339ca75` diff --git a/built-in-nodes/IdeogramV4.mdx b/built-in-nodes/IdeogramV4.mdx index 2b41a8dd3..a71dde703 100644 --- a/built-in-nodes/IdeogramV4.mdx +++ b/built-in-nodes/IdeogramV4.mdx @@ -5,7 +5,6 @@ sidebarTitle: "IdeogramV4" icon: "circle" mode: wide --- -# Ideogram V4 Generates images using the Ideogram 4.0 model from a text prompt. This node sends your text description to the Ideogram API and returns the generated image as an output tensor. diff --git a/built-in-nodes/ImageAddNoise.mdx b/built-in-nodes/ImageAddNoise.mdx index d78cdbb12..420a72e32 100644 --- a/built-in-nodes/ImageAddNoise.mdx +++ b/built-in-nodes/ImageAddNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageAddNoise" icon: "circle" mode: wide --- + The ImageAddNoise node adds random noise to an input image. It uses a specified random seed to generate consistent noise patterns and allows controlling the intensity of the noise effect. The resulting image maintains the same dimensions as the input but with added visual texture. ## Inputs diff --git a/built-in-nodes/ImageBatch.mdx b/built-in-nodes/ImageBatch.mdx index 2473c95ba..5d4f25eba 100644 --- a/built-in-nodes/ImageBatch.mdx +++ b/built-in-nodes/ImageBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBatch" icon: "circle" mode: wide --- + The `ImageBatch` node is designed for combining two images into a single batch. If the dimensions of the images do not match, it automatically rescales the second image to match the first one's dimensions before combining them. ## Inputs diff --git a/built-in-nodes/ImageBlend.mdx b/built-in-nodes/ImageBlend.mdx index 62833350d..f5d847ddf 100644 --- a/built-in-nodes/ImageBlend.mdx +++ b/built-in-nodes/ImageBlend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBlend" icon: "circle" mode: wide --- + The `ImageBlend` node is designed to blend two images together based on a specified blending mode and blend factor. It supports various blending modes such as normal, multiply, screen, overlay, soft light, and difference, allowing for versatile image manipulation and compositing techniques. This node is essential for creating composite images by adjusting the visual interaction between two image layers. ## Inputs diff --git a/built-in-nodes/ImageBlur.mdx b/built-in-nodes/ImageBlur.mdx index fe0043da4..756d61b95 100644 --- a/built-in-nodes/ImageBlur.mdx +++ b/built-in-nodes/ImageBlur.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBlur" icon: "circle" mode: wide --- + The `ImageBlur` node applies a Gaussian blur to an image, allowing for the softening of edges and reduction of detail and noise. It provides control over the intensity and spread of the blur through parameters. ## Inputs diff --git a/built-in-nodes/ImageColorToMask.mdx b/built-in-nodes/ImageColorToMask.mdx index 9eebd9664..d29229d95 100644 --- a/built-in-nodes/ImageColorToMask.mdx +++ b/built-in-nodes/ImageColorToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageColorToMask" icon: "circle" mode: wide --- + The `ImageColorToMask` node is designed to convert a specified color in an image to a mask. It processes an image and a target color, generating a mask where the specified color is highlighted, facilitating operations like color-based segmentation or object isolation. ## Inputs diff --git a/built-in-nodes/ImageCompare.mdx b/built-in-nodes/ImageCompare.mdx index 4e6b801e1..ba7f9b3de 100644 --- a/built-in-nodes/ImageCompare.mdx +++ b/built-in-nodes/ImageCompare.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCompare" icon: "circle" mode: wide --- + The Image Compare node provides a visual interface to compare two images side-by-side using a draggable slider. It is designed as an output node, meaning it does not pass data to other nodes but instead displays the images directly in the user interface for inspection. ## Inputs diff --git a/built-in-nodes/ImageCompositeMasked.mdx b/built-in-nodes/ImageCompositeMasked.mdx index 7c17a6a5c..9db241f65 100644 --- a/built-in-nodes/ImageCompositeMasked.mdx +++ b/built-in-nodes/ImageCompositeMasked.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCompositeMasked" icon: "circle" mode: wide --- + The `ImageCompositeMasked` node is designed for compositing images, allowing for the overlay of a source image onto a destination image at specified coordinates, with optional resizing and masking. ## Inputs diff --git a/built-in-nodes/ImageCrop.mdx b/built-in-nodes/ImageCrop.mdx index 9af59da73..721b387ca 100644 --- a/built-in-nodes/ImageCrop.mdx +++ b/built-in-nodes/ImageCrop.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCrop" icon: "circle" mode: wide --- + The `ImageCrop` node is designed for cropping images to a specified width and height starting from a given x and y coordinate. This functionality is essential for focusing on specific regions of an image or for adjusting the image size to meet certain requirements. ## Inputs diff --git a/built-in-nodes/ImageCropV2.mdx b/built-in-nodes/ImageCropV2.mdx index ff7716bec..14ba3b27d 100644 --- a/built-in-nodes/ImageCropV2.mdx +++ b/built-in-nodes/ImageCropV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCropV2" icon: "circle" mode: wide --- + The Crop Image node extracts a rectangular section from an input image. You define the region to keep by specifying its top-left corner coordinates and its width and height. The node then returns the cropped portion of the original image. ## Inputs diff --git a/built-in-nodes/ImageDeduplication.mdx b/built-in-nodes/ImageDeduplication.mdx index 745f7fcbf..af7c1ab8b 100644 --- a/built-in-nodes/ImageDeduplication.mdx +++ b/built-in-nodes/ImageDeduplication.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageDeduplication" icon: "circle" mode: wide --- + This node removes duplicate or very similar images from a batch. It works by creating a perceptual hash for each image—a simple numerical fingerprint based on its visual content—and then comparing them. Images whose hashes are more similar than a set threshold are considered duplicates and filtered out. ## Inputs diff --git a/built-in-nodes/ImageFlip.mdx b/built-in-nodes/ImageFlip.mdx index be3396976..b2ff42a77 100644 --- a/built-in-nodes/ImageFlip.mdx +++ b/built-in-nodes/ImageFlip.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageFlip" icon: "circle" mode: wide --- + The ImageFlip node flips images along different axes. It can flip images vertically along the x-axis or horizontally along the y-axis. The node uses torch.flip operations to perform the flipping based on the selected method. ## Inputs diff --git a/built-in-nodes/ImageFromBatch.mdx b/built-in-nodes/ImageFromBatch.mdx index 89f54510a..74d617cb6 100644 --- a/built-in-nodes/ImageFromBatch.mdx +++ b/built-in-nodes/ImageFromBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageFromBatch" icon: "circle" mode: wide --- + The `ImageFromBatch` node is designed for extracting a specific segment of images from a batch based on the provided index and length. It allows for more granular control over the batched images, enabling operations on individual or subsets of images within a larger batch. ## Inputs diff --git a/built-in-nodes/ImageGrid.mdx b/built-in-nodes/ImageGrid.mdx index a60f5334c..4e7b303f9 100644 --- a/built-in-nodes/ImageGrid.mdx +++ b/built-in-nodes/ImageGrid.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageGrid" icon: "circle" mode: wide --- + The Image Grid node combines multiple images into a single, organized grid or collage. It takes a list of images and arranges them into a specified number of columns, resizing each image to fit a defined cell size and adding optional padding between them. The result is a single, new image containing all the input images in a grid layout. ## Inputs diff --git a/built-in-nodes/ImageHistogram.mdx b/built-in-nodes/ImageHistogram.mdx index a056ab1f3..4a0af1318 100644 --- a/built-in-nodes/ImageHistogram.mdx +++ b/built-in-nodes/ImageHistogram.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageHistogram" icon: "circle" mode: wide --- + The ImageHistogram node analyzes the color distribution of an input image. It calculates and outputs several histograms, which are graphs showing how many pixels in the image have each possible intensity value. It generates separate histograms for the red, green, and blue color channels, a composite RGB histogram, and a luminance histogram based on a standard brightness formula. ## Inputs diff --git a/built-in-nodes/ImageInvert.mdx b/built-in-nodes/ImageInvert.mdx index 73f50724f..8121e813d 100644 --- a/built-in-nodes/ImageInvert.mdx +++ b/built-in-nodes/ImageInvert.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageInvert" icon: "circle" mode: wide --- + The `ImageInvert` node is designed to invert the colors of an image, effectively transforming each pixel's color value to its complementary color on the color wheel. This operation is useful for creating negative images or for visual effects that require color inversion. ## Inputs diff --git a/built-in-nodes/ImageMergeTileList.mdx b/built-in-nodes/ImageMergeTileList.mdx index d81762715..2dc62eec7 100644 --- a/built-in-nodes/ImageMergeTileList.mdx +++ b/built-in-nodes/ImageMergeTileList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageMergeTileList" icon: "circle" mode: wide --- + This node takes a list of image tiles and merges them back into a single, larger image. It is designed to reconstruct an image that was previously split into a grid of overlapping tiles, using a weighted blending technique to create a seamless final result. ## Inputs diff --git a/built-in-nodes/ImageOnlyCheckpointLoader.mdx b/built-in-nodes/ImageOnlyCheckpointLoader.mdx index a7e9ddcfb..e6f78ef3b 100644 --- a/built-in-nodes/ImageOnlyCheckpointLoader.mdx +++ b/built-in-nodes/ImageOnlyCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageOnlyCheckpointLoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/checkpoints` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. This node specializes in loading checkpoints specifically for image-based models within video generation workflows. It efficiently retrieves and configures the necessary components from a given checkpoint, focusing on image-related aspects of the model. diff --git a/built-in-nodes/ImageOnlyCheckpointSave.mdx b/built-in-nodes/ImageOnlyCheckpointSave.mdx index a2d1c5cd3..0c3e2ddd6 100644 --- a/built-in-nodes/ImageOnlyCheckpointSave.mdx +++ b/built-in-nodes/ImageOnlyCheckpointSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageOnlyCheckpointSave" icon: "circle" mode: wide --- + The ImageOnlyCheckpointSave node saves a checkpoint file containing a model, CLIP vision encoder, and VAE. It creates a safetensors file with the specified filename prefix and stores it in the output directory. This node is specifically designed for saving image-related model components together in a single checkpoint file. ## Inputs diff --git a/built-in-nodes/ImagePadForOutpaint.mdx b/built-in-nodes/ImagePadForOutpaint.mdx index df2f0bc49..f62239f37 100644 --- a/built-in-nodes/ImagePadForOutpaint.mdx +++ b/built-in-nodes/ImagePadForOutpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImagePadForOutpaint" icon: "circle" mode: wide --- + This node is designed for preparing images for the outpainting process by adding padding around them. It adjusts the image dimensions to ensure compatibility with outpainting algorithms, facilitating the generation of extended image areas beyond the original boundaries. ## Inputs diff --git a/built-in-nodes/ImageQuantize.mdx b/built-in-nodes/ImageQuantize.mdx index ce9fbb596..69f410ea3 100644 --- a/built-in-nodes/ImageQuantize.mdx +++ b/built-in-nodes/ImageQuantize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageQuantize" icon: "circle" mode: wide --- + The ImageQuantize node is designed to reduce the number of colors in an image to a specified number, optionally applying dithering techniques to maintain visual quality. This process is useful for creating palette-based images or reducing the color complexity for certain applications. ## Inputs diff --git a/built-in-nodes/ImageRGBToYUV.mdx b/built-in-nodes/ImageRGBToYUV.mdx index 2028c9c1b..5d98dac39 100644 --- a/built-in-nodes/ImageRGBToYUV.mdx +++ b/built-in-nodes/ImageRGBToYUV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageRGBToYUV" icon: "circle" mode: wide --- + The ImageRGBToYUV node converts an RGB image into the YUV color space. It separates the image into three channels: Y (luminance, or brightness), U (blue-difference), and V (red-difference), and returns each as a separate image. ## Inputs diff --git a/built-in-nodes/ImageRotate.mdx b/built-in-nodes/ImageRotate.mdx index d95fd4f15..5a3fe37dd 100644 --- a/built-in-nodes/ImageRotate.mdx +++ b/built-in-nodes/ImageRotate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageRotate" icon: "circle" mode: wide --- + The ImageRotate node rotates an input image by specified angles. It supports four rotation options: no rotation, 90 degrees clockwise, 180 degrees, and 270 degrees clockwise. The rotation is performed using efficient tensor operations that maintain the image data integrity. ## Inputs diff --git a/built-in-nodes/ImageScale.mdx b/built-in-nodes/ImageScale.mdx index 1dcbb29c4..55ebe6cd3 100644 --- a/built-in-nodes/ImageScale.mdx +++ b/built-in-nodes/ImageScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScale" icon: "circle" mode: wide --- + The ImageScale node is designed for resizing images to specific dimensions, offering a selection of upscale methods and the ability to crop the resized image. It abstracts the complexity of image upscaling and cropping, providing a straightforward interface for modifying image dimensions according to user-defined parameters. ## Inputs diff --git a/built-in-nodes/ImageScaleBy.mdx b/built-in-nodes/ImageScaleBy.mdx index 4bc4e092c..90cd83dde 100644 --- a/built-in-nodes/ImageScaleBy.mdx +++ b/built-in-nodes/ImageScaleBy.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleBy" icon: "circle" mode: wide --- + The ImageScaleBy node is designed for upscaling images by a specified scale factor using various interpolation methods. It allows for the adjustment of the image size in a flexible manner, catering to different upscaling needs. ## Inputs diff --git a/built-in-nodes/ImageScaleToMaxDimension.mdx b/built-in-nodes/ImageScaleToMaxDimension.mdx index db6278288..4fead6d97 100644 --- a/built-in-nodes/ImageScaleToMaxDimension.mdx +++ b/built-in-nodes/ImageScaleToMaxDimension.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleToMaxDimension" icon: "circle" mode: wide --- + The ImageScaleToMaxDimension node resizes images to fit within a specified maximum dimension while maintaining the original aspect ratio. It calculates whether the image is portrait or landscape oriented, then scales the larger dimension to match the target size while proportionally adjusting the smaller dimension. The node supports multiple upscaling methods for different quality and performance requirements. ## Inputs diff --git a/built-in-nodes/ImageScaleToTotalPixels.mdx b/built-in-nodes/ImageScaleToTotalPixels.mdx index 01f8524bd..c32a3fb89 100644 --- a/built-in-nodes/ImageScaleToTotalPixels.mdx +++ b/built-in-nodes/ImageScaleToTotalPixels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleToTotalPixels" icon: "circle" mode: wide --- + The ImageScaleToTotalPixels node is designed for resizing images to a specified total number of pixels while maintaining the aspect ratio. It provides various methods for upscaling the image to achieve the desired pixel count. ## Inputs diff --git a/built-in-nodes/ImageSharpen.mdx b/built-in-nodes/ImageSharpen.mdx index 5f99252ba..48998438f 100644 --- a/built-in-nodes/ImageSharpen.mdx +++ b/built-in-nodes/ImageSharpen.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageSharpen" icon: "circle" mode: wide --- + The ImageSharpen node enhances the clarity of an image by accentuating its edges and details. It applies a sharpening filter to the image, which can be adjusted in intensity and radius, thereby making the image appear more defined and crisp. ## Inputs diff --git a/built-in-nodes/ImageStitch.mdx b/built-in-nodes/ImageStitch.mdx index 6dfa23c93..d71ba28d8 100644 --- a/built-in-nodes/ImageStitch.mdx +++ b/built-in-nodes/ImageStitch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageStitch" icon: "circle" mode: wide --- + This node allows you to stitch two images together in a specified direction (up, down, left, right), with support for size matching and spacing between images. ## Inputs diff --git a/built-in-nodes/ImageToMask.mdx b/built-in-nodes/ImageToMask.mdx index 4634ef041..7bd7a551a 100644 --- a/built-in-nodes/ImageToMask.mdx +++ b/built-in-nodes/ImageToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageToMask" icon: "circle" mode: wide --- + The ImageToMask node is designed to convert an image into a mask based on a specified color channel. It allows for the extraction of mask layers corresponding to the red, green, blue, or alpha channels of an image, facilitating operations that require channel-specific masking or processing. ## Inputs diff --git a/built-in-nodes/ImageUpscaleWithModel.mdx b/built-in-nodes/ImageUpscaleWithModel.mdx index 2e309b316..8ea2d6291 100644 --- a/built-in-nodes/ImageUpscaleWithModel.mdx +++ b/built-in-nodes/ImageUpscaleWithModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageUpscaleWithModel" icon: "circle" mode: wide --- + This node is designed for upscaling images using a specified upscale model. It efficiently manages the upscaling process by adjusting the image to the appropriate device, optimizing memory usage, and applying the upscale model in a tiled manner to prevent potential out-of-memory errors. ## Inputs diff --git a/built-in-nodes/ImageYUVToRGB.mdx b/built-in-nodes/ImageYUVToRGB.mdx index b00459c8c..ab7ee1829 100644 --- a/built-in-nodes/ImageYUVToRGB.mdx +++ b/built-in-nodes/ImageYUVToRGB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageYUVToRGB" icon: "circle" mode: wide --- + The ImageYUVToRGB node converts YUV color space images to RGB color space. It takes three separate input images representing the Y (luma), U (blue projection), and V (red projection) channels and combines them into a single RGB image using color space conversion. ## Inputs diff --git a/built-in-nodes/InpaintModelConditioning.mdx b/built-in-nodes/InpaintModelConditioning.mdx index 892297d13..7282d4a0b 100644 --- a/built-in-nodes/InpaintModelConditioning.mdx +++ b/built-in-nodes/InpaintModelConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InpaintModelConditioning" icon: "circle" mode: wide --- + The InpaintModelConditioning node is designed to facilitate the conditioning process for inpainting models, enabling the integration and manipulation of various conditioning inputs to tailor the inpainting output. It encompasses a broad range of functionalities, from loading specific model checkpoints and applying style or control net models, to encoding and combining conditioning elements, thereby serving as a comprehensive tool for customizing inpainting tasks. ## Inputs diff --git a/built-in-nodes/InstructPixToPixConditioning.mdx b/built-in-nodes/InstructPixToPixConditioning.mdx index 5930e1652..29fded93f 100644 --- a/built-in-nodes/InstructPixToPixConditioning.mdx +++ b/built-in-nodes/InstructPixToPixConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InstructPixToPixConditioning" icon: "circle" mode: wide --- + The InstructPixToPixConditioning node prepares conditioning data for InstructPix2Pix image editing by combining positive and negative text prompts with image data. It processes input images through a VAE encoder to create latent representations and attaches these latents to both positive and negative conditioning data. The node automatically handles image dimensions by cropping to multiples of 8 pixels for compatibility with the VAE encoding process. ## Inputs diff --git a/built-in-nodes/InvertBooleanNode.mdx b/built-in-nodes/InvertBooleanNode.mdx index 0884a5948..7f4ecca4c 100644 --- a/built-in-nodes/InvertBooleanNode.mdx +++ b/built-in-nodes/InvertBooleanNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InvertBooleanNode" icon: "circle" mode: wide --- + This node takes a single boolean (true/false) input and outputs the opposite value. It performs a logical NOT operation, turning `true` into `false` and `false` into `true`. ## Inputs diff --git a/built-in-nodes/InvertMask.mdx b/built-in-nodes/InvertMask.mdx index f0dd6d8c2..435281ba8 100644 --- a/built-in-nodes/InvertMask.mdx +++ b/built-in-nodes/InvertMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InvertMask" icon: "circle" mode: wide --- + The InvertMask node is designed to invert the values of a given mask, effectively flipping the masked and unmasked areas. This operation is fundamental in image processing tasks where the focus of interest needs to be switched between the foreground and the background. ## Inputs diff --git a/built-in-nodes/JoinAudioChannels.mdx b/built-in-nodes/JoinAudioChannels.mdx index ae7225712..b32eefa99 100644 --- a/built-in-nodes/JoinAudioChannels.mdx +++ b/built-in-nodes/JoinAudioChannels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JoinAudioChannels" icon: "circle" mode: wide --- + The Join Audio Channels node combines two separate mono audio inputs into a single stereo audio output. It takes a left channel and a right channel, ensures they have compatible sample rates and lengths, and merges them into a two-channel audio waveform. ## Inputs diff --git a/built-in-nodes/JoinImageWithAlpha.mdx b/built-in-nodes/JoinImageWithAlpha.mdx index cf6950b24..8d10a6bb0 100644 --- a/built-in-nodes/JoinImageWithAlpha.mdx +++ b/built-in-nodes/JoinImageWithAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JoinImageWithAlpha" icon: "circle" mode: wide --- + This node is designed for compositing operations, specifically to join an image with its corresponding alpha mask to produce a single output image. It effectively combines visual content with transparency information, enabling the creation of images where certain areas are transparent or semi-transparent. ## Inputs diff --git a/built-in-nodes/JsonExtractString.mdx b/built-in-nodes/JsonExtractString.mdx index e948a6c79..e976c9878 100644 --- a/built-in-nodes/JsonExtractString.mdx +++ b/built-in-nodes/JsonExtractString.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JsonExtractString" icon: "circle" mode: wide --- + The JsonExtractString node reads a text string containing JSON data and extracts the value associated with a specific key. It converts the extracted value into a string. If the JSON is invalid, the key is not found, or the value is null, the node returns an empty string. ## Inputs diff --git a/built-in-nodes/KSampler.mdx b/built-in-nodes/KSampler.mdx index b2f065e47..6f6848b23 100644 --- a/built-in-nodes/KSampler.mdx +++ b/built-in-nodes/KSampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSampler" icon: "circle" mode: wide --- + The KSampler works like this: it modifies the provided original latent image information based on a specific model and both positive and negative conditions. First, it adds noise to the original image data according to the set **seed** and **denoise strength**, then inputs the preset **Model** combined with **positive** and **negative** guidance conditions to generate the image. diff --git a/built-in-nodes/KSamplerAdvanced.mdx b/built-in-nodes/KSamplerAdvanced.mdx index d188ce8c5..3f36a845e 100644 --- a/built-in-nodes/KSamplerAdvanced.mdx +++ b/built-in-nodes/KSamplerAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSamplerAdvanced" icon: "circle" mode: wide --- + The KSamplerAdvanced node is designed to enhance the sampling process by providing advanced configurations and techniques. It aims to offer more sophisticated options for generating samples from a model, improving upon the basic KSampler functionalities. ## Inputs diff --git a/built-in-nodes/KSamplerSelect.mdx b/built-in-nodes/KSamplerSelect.mdx index fd05208b7..795fd4ea1 100644 --- a/built-in-nodes/KSamplerSelect.mdx +++ b/built-in-nodes/KSamplerSelect.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSamplerSelect" icon: "circle" mode: wide --- + The KSamplerSelect node is designed to select a specific sampler based on the provided sampler name. It abstracts the complexity of sampler selection, allowing users to easily switch between different sampling strategies for their tasks. ## Inputs diff --git a/built-in-nodes/Kandinsky5ImageToVideo.mdx b/built-in-nodes/Kandinsky5ImageToVideo.mdx index cd1e2a94a..8c880d7f4 100644 --- a/built-in-nodes/Kandinsky5ImageToVideo.mdx +++ b/built-in-nodes/Kandinsky5ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Kandinsky5ImageToVideo" icon: "circle" mode: wide --- + The Kandinsky5ImageToVideo node prepares conditioning and latent space data for video generation using the Kandinsky model. It creates an empty video latent tensor and can optionally encode a starting image to guide the initial frames of the generated video, modifying the positive and negative conditioning accordingly. ## Inputs diff --git a/built-in-nodes/KarrasScheduler.mdx b/built-in-nodes/KarrasScheduler.mdx index 9d613e3f5..4f697a116 100644 --- a/built-in-nodes/KarrasScheduler.mdx +++ b/built-in-nodes/KarrasScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KarrasScheduler" icon: "circle" mode: wide --- + The KarrasScheduler node is designed to generate a sequence of noise levels (sigmas) based on the Karras et al. (2022) noise schedule. This scheduler is useful for controlling the diffusion process in generative models, allowing for fine-tuned adjustments to the noise levels applied at each step of the generation process. ## Inputs diff --git a/built-in-nodes/KlingAvatarNode.mdx b/built-in-nodes/KlingAvatarNode.mdx index 12078b984..0688c121d 100644 --- a/built-in-nodes/KlingAvatarNode.mdx +++ b/built-in-nodes/KlingAvatarNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingAvatarNode" icon: "circle" mode: wide --- + The Kling Avatar 2.0 node generates broadcast-style digital human videos from a single reference photo and an audio file. It creates a talking avatar video with an optional text prompt to define the avatar's actions, emotions, and camera movements. ## Inputs @@ -28,4 +29,4 @@ The Kling Avatar 2.0 node generates broadcast-style digital human videos from a > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingAvatarNode/en.md) --- -**Source fingerprint (SHA-256):** `d9264e250c578dcb38612c192f8567a8f48c6624e030d8765b13bb71aae2d0b8` +**Source fingerprint (SHA-256):** `34f64d168d6c407d9ab474e2637513c172090a0f0c219675d32f8e70ff84f2ae` diff --git a/built-in-nodes/KlingCameraControlI2VNode.mdx b/built-in-nodes/KlingCameraControlI2VNode.mdx index d78b26381..a7f1cae9c 100644 --- a/built-in-nodes/KlingCameraControlI2VNode.mdx +++ b/built-in-nodes/KlingCameraControlI2VNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingCameraControlI2VNode" icon: "circle" mode: wide --- + The Kling Image to Video Camera Control Node transforms still images into cinematic videos with professional camera movements. This specialized image-to-video node allows you to control virtual camera actions including zoom, rotation, pan, tilt, and first-person view while maintaining focus on your original image. Camera control is currently only supported in pro mode with the kling-v1-5 model at 5-second duration. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `start_frame` | Reference Image - URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300x300px, aspect ratio between 1:2.5 and 2.5:1. Base64 should not include data:image prefix. | IMAGE | Yes | - | | `prompt` | Positive text prompt describing the desired video content. Maximum length is 500 characters. | STRING | Yes | - | | `negative_prompt` | Negative text prompt describing what to avoid in the generated video. Maximum length is 500 characters. | STRING | Yes | - | @@ -21,7 +22,7 @@ The Kling Image to Video Camera Control Node transforms still images into cinema ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video output | VIDEO | | `video_id` | Unique identifier for the generated video | STRING | | `duration` | Duration of the generated video | STRING | @@ -29,4 +30,4 @@ The Kling Image to Video Camera Control Node transforms still images into cinema > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlI2VNode/en.md) --- -**Source fingerprint (SHA-256):** `c7c0ef732a97d60b03c6942a9f026a23982ea5d86746520772cc6bf2f450865c` +**Source fingerprint (SHA-256):** `65b1e4a46c2de1558c8f27ebe031f1736e84d532908170c91fb70121c350347e` diff --git a/built-in-nodes/KlingCameraControlT2VNode.mdx b/built-in-nodes/KlingCameraControlT2VNode.mdx index 3a498485c..9ef8f71e6 100644 --- a/built-in-nodes/KlingCameraControlT2VNode.mdx +++ b/built-in-nodes/KlingCameraControlT2VNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingCameraControlT2VNode" icon: "circle" mode: wide --- + Kling Text to Video Camera Control Node transforms text into cinematic videos with professional camera movements that simulate real-world cinematography. This node supports controlling virtual camera actions including zoom, rotation, pan, tilt, and first-person view while maintaining focus on your original text. The duration, mode, and model name are hard-coded because camera control is only supported in pro mode with the kling-v1-5 model at 5-second duration. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Positive text prompt | STRING | Yes | - | | `negative_prompt` | Negative text prompt | STRING | Yes | - | | `cfg_scale` | Controls how closely the output follows the prompt (default: 0.75) | FLOAT | No | 0.0-1.0 | @@ -20,7 +21,7 @@ Kling Text to Video Camera Control Node transforms text into cinematic videos wi ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video with camera control effects | VIDEO | | `video_id` | The unique identifier for the generated video | STRING | | `duration` | The duration of the generated video | STRING | @@ -28,4 +29,4 @@ Kling Text to Video Camera Control Node transforms text into cinematic videos wi > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlT2VNode/en.md) --- -**Source fingerprint (SHA-256):** `c2e6ea8f136d3bb82d6627b3362a8a4dfb9cb0414f6d846e5283e49a0ba6d357` +**Source fingerprint (SHA-256):** `7975d97c4f9242a9ae3c17be03696d174a2495bd53fb9fc4405f86c44167fa21` diff --git a/built-in-nodes/KlingCameraControls.mdx b/built-in-nodes/KlingCameraControls.mdx index a41c06c2f..8df7f3863 100644 --- a/built-in-nodes/KlingCameraControls.mdx +++ b/built-in-nodes/KlingCameraControls.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingCameraControls" icon: "circle" mode: wide --- + The Kling Camera Controls node allows you to configure various camera movement and rotation parameters for creating motion control effects in video generation. It provides controls for camera positioning, rotation, and zoom to simulate different camera movements. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `camera_control_type` | Specifies the type of camera control configuration to use | COMBO | Yes | `"simple"`
`"advanced"` | | `horizontal_movement` | Controls camera's movement along horizontal axis (x-axis). Negative indicates left, positive indicates right (default: 0.0) | FLOAT | No | -10.0 to 10.0 | | `vertical_movement` | Controls camera's movement along vertical axis (y-axis). Negative indicates downward, positive indicates upward (default: 0.0) | FLOAT | No | -10.0 to 10.0 | @@ -24,10 +25,10 @@ The Kling Camera Controls node allows you to configure various camera movement a ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `camera_control` | Returns the configured camera control settings for use in video generation | CAMERA_CONTROL | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControls/en.md) --- -**Source fingerprint (SHA-256):** `35bc9a47bb58f847e73b87156d099e821bd791546f6126dc78e47c5494a7851c` +**Source fingerprint (SHA-256):** `dbba1083b662bb2563c77dec857e4f3123e4e53d58a1d51f2646288af28ebba0` diff --git a/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx b/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx index ddc9a8b74..34be9207e 100644 --- a/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx +++ b/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingDualCharacterVideoEffectNode" icon: "circle" mode: wide --- + The Kling Dual Character Video Effect Node creates videos with special effects based on the selected scene. It takes two images and positions the first image on the left side and the second image on the right side of the composite video. Different visual effects are applied depending on the chosen effect scene. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image_left` | Left side image | IMAGE | Yes | - | | `image_right` | Right side image | IMAGE | Yes | - | | `effect_scene` | The type of special effect scene to apply to the video generation | COMBO | Yes | `"chat"`
`"dance"`
`"hug"`
`"kill"`
`"kiss"`
`"pat"`
`"punch"`
`"shrug"`
`"slap"`
`"tickle"` | @@ -21,11 +22,11 @@ The Kling Dual Character Video Effect Node creates videos with special effects b ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video with dual character effects | VIDEO | | `duration` | The duration information of the generated video | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingDualCharacterVideoEffectNode/en.md) --- -**Source fingerprint (SHA-256):** `995616159d0b61a5398ec93e847b04fed8133a28a37f597427f0335ca17920b9` +**Source fingerprint (SHA-256):** `314fc23940225eb4559ecc74f333bb23e9a4939bbb884c93341f4d6f6e7b64df` diff --git a/built-in-nodes/KlingFirstLastFrameNode.mdx b/built-in-nodes/KlingFirstLastFrameNode.mdx index 788bc5f94..70a53ab24 100644 --- a/built-in-nodes/KlingFirstLastFrameNode.mdx +++ b/built-in-nodes/KlingFirstLastFrameNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingFirstLastFrameNode" icon: "circle" mode: wide --- + This node uses the Kling 3.0 model to generate a video. It creates the video based on a text prompt, a specified duration, and two provided images: a starting frame and an ending frame. The node can also generate accompanying audio for the video. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | The text description that guides the video generation. Must be between 1 and 2500 characters long. | STRING | Yes | N/A | | `duration` | The length of the video in seconds (default: 5). | INT | No | 3 to 15 | | `first_frame` | The starting image for the video. Must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1. | IMAGE | Yes | N/A | @@ -25,10 +26,10 @@ This node uses the Kling 3.0 model to generate a video. It creates the video bas ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingFirstLastFrameNode/en.md) --- -**Source fingerprint (SHA-256):** `def99b6a37962b5a28be1025ce41ae50bf7b90246c50894fcf3419365f807b2f` +**Source fingerprint (SHA-256):** `b71119c3267e2a74d2180e5182463c78828e892bfcf1eeb7c33a0f4d7019997f` diff --git a/built-in-nodes/KlingImage2VideoNode.mdx b/built-in-nodes/KlingImage2VideoNode.mdx index 33b8d39aa..7af2e292c 100644 --- a/built-in-nodes/KlingImage2VideoNode.mdx +++ b/built-in-nodes/KlingImage2VideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingImage2VideoNode" icon: "circle" mode: wide --- + The Kling Image to Video Node generates a video from a starting reference image using text prompts. It takes an image as the first frame and creates a video sequence based on positive and negative text descriptions, with configurable options for model, duration, aspect ratio, and generation mode. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `start_frame` | The reference image used to generate the video. The image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1. | IMAGE | Yes | - | | `prompt` | Positive text prompt. Maximum 500 characters. | STRING | Yes | - | | `negative_prompt` | Negative text prompt. Maximum 500 characters. | STRING | Yes | - | @@ -23,7 +24,7 @@ The Kling Image to Video Node generates a video from a starting reference image ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video output. | VIDEO | | `video_id` | Unique identifier for the generated video. | STRING | | `duration` | Duration information for the generated video. | STRING | @@ -31,4 +32,4 @@ The Kling Image to Video Node generates a video from a starting reference image > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImage2VideoNode/en.md) --- -**Source fingerprint (SHA-256):** `2845117c840372d457c58bfb8da077ccac32a9398e5679120104d8ee597d4855` +**Source fingerprint (SHA-256):** `e5731be52e00b6e80a6323417f927d0d6ba5e8147aa149f7ec9dd902d77bc70d` diff --git a/built-in-nodes/KlingImageGenerationNode.mdx b/built-in-nodes/KlingImageGenerationNode.mdx index 04c298928..e4edc5dfb 100644 --- a/built-in-nodes/KlingImageGenerationNode.mdx +++ b/built-in-nodes/KlingImageGenerationNode.mdx @@ -5,14 +5,15 @@ sidebarTitle: "KlingImageGenerationNode" icon: "circle" mode: wide --- + Kling Image Generation Node generates images from text prompts with the option to use a reference image for guidance. It creates one or more images based on your text description and reference settings, then returns the generated images as output. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `prompt` | Positive text prompt | STRING | Yes | - | -| `negative_prompt` | Negative text prompt | STRING | Yes | - | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Positive text prompt | STRING | Yes | Maximum 500 characters | +| `negative_prompt` | Negative text prompt | STRING | Yes | Maximum 500 characters | | `image_type` | Image reference type selection (advanced). Required when a reference image is provided. | COMBO | Yes | `"subject_reference"`
`"style_reference"` | | `image_fidelity` | Reference intensity for user-uploaded images (default: 0.5, advanced) | FLOAT | Yes | 0.0 - 1.0 | | `human_fidelity` | Subject reference similarity (default: 0.45, advanced) | FLOAT | Yes | 0.0 - 1.0 | @@ -32,10 +33,10 @@ Kling Image Generation Node generates images from text prompts with the option t ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | Generated image(s) based on the input parameters | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImageGenerationNode/en.md) --- -**Source fingerprint (SHA-256):** `3c029920c966ac9a3588a790e83e1350021a0864a02677258a25af46a0770dce` +**Source fingerprint (SHA-256):** `65bd6ea842877a9af9a7b554fe020418291d06ae6cc35e86127ab524aadd48c1` diff --git a/built-in-nodes/KlingImageToVideoWithAudio.mdx b/built-in-nodes/KlingImageToVideoWithAudio.mdx index 27bf924fc..92624a1cb 100644 --- a/built-in-nodes/KlingImageToVideoWithAudio.mdx +++ b/built-in-nodes/KlingImageToVideoWithAudio.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingImageToVideoWithAudio" icon: "circle" mode: wide --- + The Kling Image(First Frame) to Video with Audio node uses the Kling AI model to generate a short video from a single starting image and a text prompt. It creates a video sequence that begins with the provided image and can optionally include AI-generated audio to accompany the visuals. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_name` | The specific version of the Kling AI model to use for video generation. | COMBO | Yes | `"kling-v2-6"` | | `start_frame` | The image that will serve as the first frame of the generated video. The image must be at least 300x300 pixels and have an aspect ratio between 1:2.5 and 2.5:1. | IMAGE | Yes | - | | `prompt` | Positive text prompt. This describes the video content you want to generate. The prompt must be between 1 and 2500 characters long. | STRING | Yes | - | @@ -21,10 +22,10 @@ The Kling Image(First Frame) to Video with Audio node uses the Kling AI model to ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The generated video file, which may include audio depending on the `generate_audio` input. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImageToVideoWithAudio/en.md) --- -**Source fingerprint (SHA-256):** `c994748fdfa6d79f81aaf864ec174a6b608c4f05943a7e23edd345608122d9a1` +**Source fingerprint (SHA-256):** `e0b834a297f7afd72cfb779a92557f0dc680eacd4d0e18bab0e7c59ae8624965` diff --git a/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx b/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx index a6f99f2fe..a5988ce8c 100644 --- a/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx +++ b/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingLipSyncAudioToVideoNode" icon: "circle" mode: wide --- + Kling Lip Sync Audio to Video Node synchronizes mouth movements in a video file to match the audio content of an audio file. This node analyzes the vocal patterns in the audio and adjusts the facial movements in the video to create realistic lip-syncing. The process requires both a video containing a distinct face and an audio file with clearly distinguishable vocals. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `video` | The video file containing a face to be lip-synced | VIDEO | Yes | - | | `audio` | The audio file containing vocals to sync with the video | AUDIO | Yes | - | | `voice_language` | The language of the voice in the audio file (default: "en") | COMBO | Yes | `"en"`
`"zh"`
`"es"`
`"fr"`
`"de"`
`"it"`
`"pt"`
`"pl"`
`"tr"`
`"ru"`
`"nl"`
`"cs"`
`"ar"`
`"ja"`
`"hu"`
`"ko"` | @@ -27,7 +28,7 @@ Kling Lip Sync Audio to Video Node synchronizes mouth movements in a video file ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The processed video with lip-synced mouth movements | VIDEO | | `video_id` | The unique identifier for the processed video | STRING | | `duration` | The duration of the processed video | STRING | @@ -35,4 +36,4 @@ Kling Lip Sync Audio to Video Node synchronizes mouth movements in a video file > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncAudioToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `bc6dcc5a1e3b873edc0c65cc156bb622992866920a4975a308d8cdb8a3c0e71a` +**Source fingerprint (SHA-256):** `2f88af3191ac4f9c5c9fa1aaa5b744a12620b66e55a1fe0ab16b8b3b61110128` diff --git a/built-in-nodes/KlingLipSyncTextToVideoNode.mdx b/built-in-nodes/KlingLipSyncTextToVideoNode.mdx index 2bee3aad0..b6db3f868 100644 --- a/built-in-nodes/KlingLipSyncTextToVideoNode.mdx +++ b/built-in-nodes/KlingLipSyncTextToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingLipSyncTextToVideoNode" icon: "circle" mode: wide --- + Kling Lip Sync Text to Video Node synchronizes mouth movements in a video file to match a text prompt. It takes an input video and generates a new video where the character's lip movements are aligned with the provided text. The node uses voice synthesis to create natural-looking speech synchronization. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `video` | Input video file for lip synchronization. Video must be between 720px and 1920px in height/width, between 2s and 10s in duration, and no larger than 100MB. | VIDEO | Yes | - | | `text` | Text Content for Lip-Sync Video Generation. Required when mode is text2video. Maximum length is 120 characters. | STRING | Yes | - | | `voice` | Voice selection for the lip-sync audio (default: "Melody"). Includes both English and Chinese voice options. | COMBO | No | "Melody"
"Sunny"
"Sage"
"Ace"
"Blossom"
"Peppy"
"Dove"
"Shine"
"Anchor"
"Lyric"
"Tender"
"Siren"
"Zippy"
"Bud"
"Sprite"
"Candy"
"Beacon"
"Rock"
"Titan"
"Grace"
"Helen"
"Lore"
"Crag"
"Prattle"
"Hearth"
"The Reader"
"Commercial Lady"
"阳光少年"
"懂事小弟"
"运动少年"
"青春少女"
"温柔小妹"
"元气少女"
"阳光男生"
"幽默小哥"
"文艺小哥"
"甜美邻家"
"温柔姐姐"
"职场女青"
"活泼男童"
"俏皮女童"
"稳重老爸"
"温柔妈妈"
"严肃上司"
"优雅贵妇"
"慈祥爷爷"
"唠叨爷爷"
"唠叨奶奶"
"和蔼奶奶"
"东北老铁"
"重庆小伙"
"四川妹子"
"潮汕大叔"
"台湾男生"
"西安掌柜"
"天津姐姐"
"新闻播报男"
"译制片男"
"撒娇女友"
"刀片烟嗓"
"乖巧正太" | @@ -25,7 +26,7 @@ Kling Lip Sync Text to Video Node synchronizes mouth movements in a video file t ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | Generated video with lip-synchronized audio | VIDEO | | `video_id` | Unique identifier for the generated video | STRING | | `duration` | Duration information for the generated video | STRING | @@ -33,4 +34,4 @@ Kling Lip Sync Text to Video Node synchronizes mouth movements in a video file t > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncTextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `fb6d208be684f8fc38f692c0439bcfebafc8c448932bc54fa4730da87113f376` +**Source fingerprint (SHA-256):** `28a7be92d7e8a57efeb7e2913124e4373dfc75fbdba6ff7036fafb3a8ae43a60` diff --git a/built-in-nodes/KlingMotionControl.mdx b/built-in-nodes/KlingMotionControl.mdx index 936ccd0df..be57f6a5e 100644 --- a/built-in-nodes/KlingMotionControl.mdx +++ b/built-in-nodes/KlingMotionControl.mdx @@ -5,15 +5,16 @@ sidebarTitle: "KlingMotionControl" icon: "circle" mode: wide --- + The Kling Motion Control node generates a video by applying the motion, expressions, and camera movements from a reference video to a character defined by a reference image and a text prompt. It allows you to control whether the character's final orientation comes from the reference video or the reference image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | A text description of the desired video. Maximum length is 2500 characters. | STRING | Yes | N/A | | `reference_image` | An image of the character to animate. Minimum dimensions are 340x340 pixels. The aspect ratio must be between 1:2.5 and 2.5:1. | IMAGE | Yes | N/A | -| `reference_video` | A motion reference video used to drive the character's movement and expression. Minimum dimensions are 340x340 pixels, maximum dimensions are 3850x3850 pixels. Duration limits depend on the `character_orientation` setting. | VIDEO | Yes | N/A | +| `reference_video` | Motion reference video used to drive movement/expression. Duration limits depend on `character_orientation` setting. Minimum dimensions are 340x340 pixels, maximum dimensions are 3850x3850 pixels. | VIDEO | Yes | N/A | | `keep_original_sound` | Determines if the original audio from the reference video is kept in the output. Default is `True`. | BOOLEAN | No | N/A | | `character_orientation` | Controls where the character's facing/orientation comes from. `"video"`: movements, expressions, camera moves, and orientation follow the motion reference video (other details via prompt). `"image"`: movements and expressions still follow the motion reference video, but the character orientation matches the reference image (camera/other details via prompt). | COMBO | No | `"video"`
`"image"` | | `mode` | The generation mode to use. | COMBO | No | `"pro"`
`"std"` | @@ -21,16 +22,16 @@ The Kling Motion Control node generates a video by applying the motion, expressi **Constraints:** -* The `reference_video` duration must be between 3 and 30 seconds when `character_orientation` is set to `"video"`. -* The `reference_video` duration must be between 3 and 10 seconds when `character_orientation` is set to `"image"`. +- The `reference_video` duration must be between 3 and 30 seconds when `character_orientation` is set to `"video"`. +- The `reference_video` duration must be between 3 and 10 seconds when `character_orientation` is set to `"image"`. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video with the character performing the motion from the reference video. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingMotionControl/en.md) --- -**Source fingerprint (SHA-256):** `3e350ca448a927367edfc90c5abb572be7ffa589c9e8e8734066af280233bd60` +**Source fingerprint (SHA-256):** `a61e55fabe53f4e13fa993c3d891db40024709ea4fb6b16b5716d893b2bd23b5` diff --git a/built-in-nodes/KlingOmniProEditVideoNode.mdx b/built-in-nodes/KlingOmniProEditVideoNode.mdx index 461b7a2fa..3bc4bc873 100644 --- a/built-in-nodes/KlingOmniProEditVideoNode.mdx +++ b/built-in-nodes/KlingOmniProEditVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingOmniProEditVideoNode" icon: "circle" mode: wide --- + The Kling Omni Edit Video (Pro) node uses an AI model to edit an existing video based on a text description. You provide a source video and a prompt, and the node generates a new video of the same length with the requested changes. It can optionally use reference images to guide the style and keep the original audio from the source video. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_name` | The AI model to use for video editing (default: `"kling-v3-omni"`). | COMBO | Yes | `"kling-v3-omni"`
`"kling-video-o1"` | | `prompt` | A text prompt describing the video content. This can include both positive and negative descriptions. | STRING | Yes | | | `video` | Video for editing. The output video length will be the same. | VIDEO | Yes | | @@ -31,10 +32,10 @@ The Kling Omni Edit Video (Pro) node uses an AI model to edit an existing video ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The edited video generated by the AI model. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProEditVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `770f1944738c06523a537a1add85340ea9264771f62e463f4985ca6bcacddf78` +**Source fingerprint (SHA-256):** `4aa7779a30183c80f025e15ae693ba23021013c68d247753e7e9a4c3a64762da` diff --git a/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx b/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx index 4dfe9df91..7c23744a2 100644 --- a/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx +++ b/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingOmniProFirstLastFrameNode" icon: "circle" mode: wide --- + This node uses the latest Kling AI model to generate a video from a start frame, an optional end frame, or reference images. It can create a single video or a multi-shot storyboard with individual prompts and durations for each segment. The node processes these inputs to produce a video of a specified length and resolution, with optional audio generation. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_name` | The specific Kling AI model to use for video generation. | COMBO | Yes | `"kling-v3-omni"`
`"kling-video-o1"` | | `prompt` | A text prompt describing the video content. This can include both positive and negative descriptions. Ignored when storyboards are enabled. | STRING | Yes | - | | `duration` | The desired length of the generated video in seconds (default: 5). | INT | Yes | 3 to 15 | @@ -38,10 +39,10 @@ This node uses the latest Kling AI model to generate a video from a start frame, ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProFirstLastFrameNode/en.md) --- -**Source fingerprint (SHA-256):** `caa8c321124c70cb9cbeedee13cdde4c37c7e107c04265b4baf2dd8864a1fc65` +**Source fingerprint (SHA-256):** `2b26914ba29c3d877a981e41acb44d15dfacc604d86d7cc232ebfa7fda0ae3b8` diff --git a/built-in-nodes/KlingOmniProImageNode.mdx b/built-in-nodes/KlingOmniProImageNode.mdx index 6f58799ec..1740374d8 100644 --- a/built-in-nodes/KlingOmniProImageNode.mdx +++ b/built-in-nodes/KlingOmniProImageNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingOmniProImageNode" icon: "circle" mode: wide --- + The Kling Omni Image (Pro) node creates or edits images using the latest Kling AI model. It generates images based on a text description and can optionally use reference images to guide the style or content. The node sends a request to an external API, which processes the task and returns the final image(s). ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_name` | The specific Kling AI model to use for image generation. | COMBO | Yes | `"kling-v3-omni"`
`"kling-image-o1"` | | `prompt` | A text prompt describing the image content. This can include both positive and negative descriptions. The text must be between 1 and 2500 characters long. You can use `@image`, `@image1`, `@image2`, etc. or `@video`, `@video1`, `@video2`, etc. to reference uploaded images or videos in the prompt. | STRING | Yes | - | | `resolution` | The target resolution for the generated image. Note: 4K resolution is not supported for the `kling-image-o1` model. | COMBO | Yes | `"1K"`
`"2K"`
`"4K"` | @@ -22,10 +23,10 @@ The Kling Omni Image (Pro) node creates or edits images using the latest Kling A ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The final image(s) generated or edited by the Kling AI model. If a series was requested, multiple images are returned as a batch. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProImageNode/en.md) --- -**Source fingerprint (SHA-256):** `b1d25806bc3b8eaa5ee8677a32b1f1f45189b800a2bfe1664635eaa851c34032` +**Source fingerprint (SHA-256):** `923db96e956e0f11c9290478ceb105304893f28d35af9f0e13077ca0f88dff79` diff --git a/built-in-nodes/KlingOmniProImageToVideoNode.mdx b/built-in-nodes/KlingOmniProImageToVideoNode.mdx index 1cfc9da6b..fe95c5368 100644 --- a/built-in-nodes/KlingOmniProImageToVideoNode.mdx +++ b/built-in-nodes/KlingOmniProImageToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingOmniProImageToVideoNode" icon: "circle" mode: wide --- + This node uses the Kling AI model to generate a video based on a text prompt and up to seven reference images. It allows you to control the video's aspect ratio, duration, resolution, and optionally use storyboards or generate audio. The node sends the request to an external API and returns the generated video. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_name` | The specific Kling model to use for video generation (default: "kling-v3-omni"). | COMBO | Yes | `"kling-v3-omni"`
`"kling-video-o1"` | | `prompt` | A text prompt describing the video content. This can include both positive and negative descriptions. The text is automatically normalized and must be between 1 and 2500 characters. Ignored when storyboards are enabled. | STRING | Yes | - | | `aspect_ratio` | The desired aspect ratio for the generated video. | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"` | @@ -32,10 +33,10 @@ This node uses the Kling AI model to generate a video based on a text prompt and ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProImageToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `e1fe0433a604fbc071fdd426121a1f4ff10bb0aa6d3eb2d702306b7206dae4c0` +**Source fingerprint (SHA-256):** `ccf7881065d2a365cdaa0e164b8b1d46c67985067866ab0fe91d492a62015f07` diff --git a/built-in-nodes/KlingOmniProTextToVideoNode.mdx b/built-in-nodes/KlingOmniProTextToVideoNode.mdx index 6698a3d23..a5a9d6db0 100644 --- a/built-in-nodes/KlingOmniProTextToVideoNode.mdx +++ b/built-in-nodes/KlingOmniProTextToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingOmniProTextToVideoNode" icon: "circle" mode: wide --- + This node uses the latest Kling AI model to generate a video from a text description. It sends your prompt to a remote API and returns the generated video. The node allows you to control the video's length, shape, quality, and even create multi-shot storyboards. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_name` | The specific Kling model to use for video generation (default: `"kling-v3-omni"`). | COMBO | Yes | `"kling-v3-omni"`
`"kling-video-o1"` | | `prompt` | A text prompt describing the video content. This can include both positive and negative descriptions. Ignored when storyboards are enabled. | STRING | Yes | 0 to 2500 characters | | `aspect_ratio` | The shape or dimensions of the video to generate. | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"` | @@ -38,10 +39,10 @@ This node uses the latest Kling AI model to generate a video from a text descrip ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The video generated based on the provided text prompt and settings. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProTextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `8789c78184356c8ca1d84e046a2c8db644b6e47822d909d95e9d7417f2311109` +**Source fingerprint (SHA-256):** `d2fbbe7c6aae283eb3fa7f73d788b809098a9a4dd6e8ada54697d43fd5bf10f2` diff --git a/built-in-nodes/KlingOmniProVideoToVideoNode.mdx b/built-in-nodes/KlingOmniProVideoToVideoNode.mdx index b739b0213..d3285378f 100644 --- a/built-in-nodes/KlingOmniProVideoToVideoNode.mdx +++ b/built-in-nodes/KlingOmniProVideoToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingOmniProVideoToVideoNode" icon: "circle" mode: wide --- + This node uses the Kling AI model to generate a new video based on an input video and optional reference images. You provide a text prompt describing the desired content, and the node transforms the reference video accordingly. It can also incorporate up to four additional reference images to guide the style and content of the output. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_name` | The specific Kling model to use for video generation (default: "kling-v3-omni"). | COMBO | Yes | `"kling-v3-omni"`
`"kling-video-o1"` | | `prompt` | A text prompt describing the video content. This can include both positive and negative descriptions. | STRING | Yes | N/A | | `aspect_ratio` | The desired aspect ratio for the generated video. | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"` | @@ -31,10 +32,10 @@ This node uses the Kling AI model to generate a new video based on an input vide ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The newly generated video. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProVideoToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `aa99b865ca96ec5c2d5535d3392e8dc94dd5e56ebf624f8fdff09302767ab300` +**Source fingerprint (SHA-256):** `3dc2e3d153ddd9e6da705b764c51b4a859d66464b893fdebb0689d2ad5e870c7` diff --git a/built-in-nodes/KlingSingleImageVideoEffectNode.mdx b/built-in-nodes/KlingSingleImageVideoEffectNode.mdx index 95d10408b..f7d228f14 100644 --- a/built-in-nodes/KlingSingleImageVideoEffectNode.mdx +++ b/built-in-nodes/KlingSingleImageVideoEffectNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingSingleImageVideoEffectNode" icon: "circle" mode: wide --- + The Kling Single Image Video Effect Node creates videos with different special effects based on a single reference image. It applies various visual effects and scenes to transform static images into dynamic video content. The node supports different effect scenes, model options, and video durations to achieve the desired visual outcome. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | Reference Image. URL or Base64 encoded string (without data:image prefix). File size cannot exceed 10MB, resolution not less than 300x300px, aspect ratio between 1:2.5 to 2.5:1 | IMAGE | Yes | - | | `effect_scene` | The type of special effect scene to apply to the video generation. Some effects may have different pricing. | COMBO | Yes | `"dizzydizzy"`
`"bloombloom"`
`"neon"`
`"cartoon"`
`"sketch"`
`"oil"`
`"watercolor"`
`"3d"` | | `model_name` | The specific model version to use for generating the video effect. | COMBO | Yes | `"kling-v1-5"`
`"kling-v1-6"` | @@ -21,7 +22,7 @@ The Kling Single Image Video Effect Node creates videos with different special e ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video with applied effects | VIDEO | | `video_id` | The unique identifier for the generated video | STRING | | `duration` | The duration of the generated video | STRING | @@ -29,4 +30,4 @@ The Kling Single Image Video Effect Node creates videos with different special e > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingSingleImageVideoEffectNode/en.md) --- -**Source fingerprint (SHA-256):** `7e9d1e2830f16361587d3d1f082fb2536d36ca9d933aa9e2ced32eeb65a161ea` +**Source fingerprint (SHA-256):** `fb4a8b044daa99154a58d6926ff746bd2397b71ea32f1fafc851589f163ab51a` diff --git a/built-in-nodes/KlingStartEndFrameNode.mdx b/built-in-nodes/KlingStartEndFrameNode.mdx index 8fb94104a..cbfd41aea 100644 --- a/built-in-nodes/KlingStartEndFrameNode.mdx +++ b/built-in-nodes/KlingStartEndFrameNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingStartEndFrameNode" icon: "circle" mode: wide --- -Kling Start-End Frame to Video node creates a video sequence that transitions between your provided start and end images. It generates all the frames in between to produce a smooth transformation from the first frame to the last frame. This node calls the image-to-video API but only supports the input options that work with the `image_tail` request field. + +This node creates a video sequence that transitions between your provided start and end images. It generates all the frames in between to produce a smooth transformation from the first frame to the last frame. This node calls the image-to-video API but only supports the input options that work with the `image_tail` request field. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `start_frame` | Reference Image - URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px, aspect ratio between 1:2.5 ~ 2.5:1. Base64 should not include data:image prefix. | IMAGE | Yes | - | | `end_frame` | Reference Image - End frame control. URL or Base64 encoded string, cannot exceed 10MB, resolution not less than 300*300px. Base64 should not include data:image prefix. | IMAGE | Yes | - | | `prompt` | Positive text prompt | STRING | Yes | - | @@ -29,7 +30,7 @@ Kling Start-End Frame to Video node creates a video sequence that transitions be ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video sequence | VIDEO | | `video_id` | Unique identifier for the generated video | STRING | | `duration` | Duration of the generated video | STRING | @@ -37,4 +38,4 @@ Kling Start-End Frame to Video node creates a video sequence that transitions be > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingStartEndFrameNode/en.md) --- -**Source fingerprint (SHA-256):** `e0bf25103e72ea3f56651adf64c0712f32c055f2b870448dcbbe82b546be8f37` +**Source fingerprint (SHA-256):** `7e3a6a4b04b7ad01708a0664a6bed9d817103206074ef41a747ef8193a8ce348` diff --git a/built-in-nodes/KlingTextToVideoNode.mdx b/built-in-nodes/KlingTextToVideoNode.mdx index a47fb4594..0073ec6a7 100644 --- a/built-in-nodes/KlingTextToVideoNode.mdx +++ b/built-in-nodes/KlingTextToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingTextToVideoNode" icon: "circle" mode: wide --- + The Kling Text to Video Node converts text descriptions into video content. It takes text prompts and generates corresponding video sequences based on the specified configuration settings. The node supports different aspect ratios, generation modes, and model versions to produce videos of varying durations and quality. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Positive text prompt describing the desired video content | STRING | Yes | Maximum 2500 characters | | `negative_prompt` | Negative text prompt describing what to avoid in the video | STRING | Yes | Maximum 2500 characters | | `cfg_scale` | Configuration scale value that controls how closely the video follows the prompt (default: 1.0) | FLOAT | No | 0.0 to 1.0 | @@ -20,7 +21,7 @@ The Kling Text to Video Node converts text descriptions into video content. It t ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video output | VIDEO | | `video_id` | Unique identifier for the generated video | STRING | | `duration` | Duration information for the generated video | STRING | @@ -28,4 +29,4 @@ The Kling Text to Video Node converts text descriptions into video content. It t > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `2ec33023f023e8e6fbef04df4f6038a95b88205dbb9d170e88a964cf1ef03a27` +**Source fingerprint (SHA-256):** `02860325301936682a8e4e49f2a3d7c18d4915edbf61f58ded513564c5e85f7a` diff --git a/built-in-nodes/KlingTextToVideoWithAudio.mdx b/built-in-nodes/KlingTextToVideoWithAudio.mdx index d470d69d9..c0aedb39c 100644 --- a/built-in-nodes/KlingTextToVideoWithAudio.mdx +++ b/built-in-nodes/KlingTextToVideoWithAudio.mdx @@ -5,26 +5,27 @@ sidebarTitle: "KlingTextToVideoWithAudio" icon: "circle" mode: wide --- + The Kling Text to Video with Audio node generates a short video from a text description. It sends a request to the Kling AI service, which processes the prompt and returns a video file. The node can also generate accompanying audio for the video based on the text. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_name` | The specific AI model to use for video generation. | COMBO | Yes | `"kling-v2-6"` | | `prompt` | Positive text prompt. The description used to generate the video. Must be between 1 and 2500 characters. | STRING | Yes | - | | `mode` | The operational mode for the video generation. | COMBO | Yes | `"pro"` | | `aspect_ratio` | The desired width-to-height ratio for the generated video. | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"` | | `duration` | The length of the video in seconds. | COMBO | Yes | `5`
`10` | -| `generate_audio` | Controls whether audio is generated for the video. When enabled, the AI will create sound based on the prompt. (default: `True`) | BOOLEAN | No | - | +| `generate_audio` | Controls whether audio is generated for the video. When enabled, the AI will create sound based on the prompt (default: `True`). | BOOLEAN | No | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoWithAudio/en.md) --- -**Source fingerprint (SHA-256):** `60c76cc66b02552cfbf63dda35e8422349c0b6989ca07631d2d8321bb5686cca` +**Source fingerprint (SHA-256):** `ddd2f3c1799abac067a05f3f5d6442ad4fe023d2f4f9afbde2894ca66854977e` diff --git a/built-in-nodes/KlingVideoExtendNode.mdx b/built-in-nodes/KlingVideoExtendNode.mdx index 4d7e52a41..3f379c094 100644 --- a/built-in-nodes/KlingVideoExtendNode.mdx +++ b/built-in-nodes/KlingVideoExtendNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingVideoExtendNode" icon: "circle" mode: wide --- + The Kling Video Extend Node allows you to extend videos created by other Kling nodes. It takes an existing video identified by its video ID and generates additional content based on your text prompts. The node works by sending your extension request to the Kling API and returning the extended video along with its new ID and duration. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Positive text prompt for guiding the video extension | STRING | No | - | | `negative_prompt` | Negative text prompt for elements to avoid in the extended video | STRING | No | - | | `cfg_scale` | Controls the strength of prompt guidance (default: 0.5) | FLOAT | No | 0.0 - 1.0 | @@ -21,7 +22,7 @@ The Kling Video Extend Node allows you to extend videos created by other Kling n ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The extended video generated by the Kling API | VIDEO | | `video_id` | The unique identifier for the extended video | STRING | | `duration` | The duration of the extended video | STRING | @@ -29,4 +30,4 @@ The Kling Video Extend Node allows you to extend videos created by other Kling n > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoExtendNode/en.md) --- -**Source fingerprint (SHA-256):** `31f9d394845412d92b9e9ad7e032acea9c686fe54e32b53dac3848ab54ff9287` +**Source fingerprint (SHA-256):** `56674dee721a1784138852f5fd1cce137acf0b5e09bd9ee17353dde6fb251b5e` diff --git a/built-in-nodes/KlingVideoNode.mdx b/built-in-nodes/KlingVideoNode.mdx index af1bab791..2b6ecf607 100644 --- a/built-in-nodes/KlingVideoNode.mdx +++ b/built-in-nodes/KlingVideoNode.mdx @@ -5,27 +5,28 @@ sidebarTitle: "KlingVideoNode" icon: "circle" mode: wide --- -This node generates videos using the Kling V3 model. It supports two primary modes: text-to-video, where a video is created from a text description, and image-to-video, where an existing image is animated. It also offers advanced features like creating multi-segment videos with different prompts for each part (storyboards) and optionally generating accompanying audio. + +This node generates videos using the Kling V3 model. It supports text-to-video mode, where a video is created from a text description, and image-to-video mode, where an existing image is animated. It also offers advanced features like creating multi-segment videos with individual prompts for each part (storyboards) and optionally generating accompanying audio. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `multi_shot` | Controls whether to generate a single video or a series of segments with individual prompts and durations. When not "disabled," additional inputs for each storyboard's prompt and duration appear. | COMBO | Yes | `"disabled"`
`"1 storyboard"`
`"2 storyboards"`
`"3 storyboards"`
`"4 storyboards"`
`"5 storyboards"`
`"6 storyboards"` | -| `generate_audio` | When enabled, the node will generate audio for the video. Default is `True`. | BOOLEAN | Yes | `True` / `False` | +| `generate_audio` | When enabled, the node will generate audio for the video. Default is True. | BOOLEAN | Yes | True / False | | `model` | The model and its associated settings. Selecting this option reveals the `resolution` and `aspect_ratio` sub-parameters. | COMBO | Yes | `"kling-v3"` | -| `model.resolution` | The resolution for the generated video. This setting is available when the `model` is set to "kling-v3". | COMBO | Yes | `"4k"`
`"1080p"`
`"720p"` | -| `model.aspect_ratio` | The aspect ratio for the generated video. This setting is ignored when an image is provided for `start_frame` (image-to-video mode). Available when the `model` is set to "kling-v3". | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"` | -| `seed` | A seed value for generation. Changing this value will cause the node to re-run, but the results are non-deterministic. Default is `0`. | INT | Yes | 0 to 2147483647 | -| `start_frame` | An optional starting image. When connected, the node switches from text-to-video to image-to-video mode, animating the provided image. | IMAGE | No | - | +| `model.resolution` | The resolution for the generated video. | COMBO | Yes | `"4k"`
`"1080p"`
`"720p"` | +| `model.aspect_ratio` | The aspect ratio for the generated video. This setting is ignored when an image is provided for `start_frame` (image-to-video mode). | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"` | +| `seed` | A seed value for generation. Changing this value will cause the node to re-run, but results are non-deterministic regardless of seed. Default is 0. | INT | Yes | 0 to 2147483647 | +| `start_frame` | Optional start frame image. When connected, switches to image-to-video mode. | IMAGE | No | - | **Inputs for `multi_shot` mode:** * When `multi_shot` is set to **"disabled"**, the following inputs appear: - * `prompt` (STRING): The main text description for the video. Required. Must be between 1 and 2500 characters. - * `negative_prompt` (STRING): Text describing what should not appear in the video. Optional. - * `duration` (INT): The length of the video in seconds. Must be between 3 and 15. Default is `5`. -* When `multi_shot` is set to a storyboard option (e.g., `"3 storyboards"`), inputs for each storyboard segment appear (e.g., `storyboard_1_prompt`, `storyboard_1_duration`). Each prompt must be between 1 and 512 characters. The **total sum of all storyboard durations** must be between 3 and 15 seconds. + * `prompt` (STRING): The main text description for the video. Must be between 1 and 2500 characters. + * `negative_prompt` (STRING): Text describing what should not appear in the video. + * `duration` (INT): The length of the video in seconds. Must be between 3 and 15. Default is 5. +* When `multi_shot` is set to a storyboard option (e.g., `"3 storyboards"`), inputs for each storyboard segment appear (e.g., `storyboard_1_prompt`, `storyboard_1_duration`). Each storyboard prompt must be between 1 and 512 characters. The **total sum of all storyboard durations** must be between 3 and 15 seconds. **Constraints:** @@ -36,10 +37,10 @@ This node generates videos using the Kling V3 model. It supports two primary mod ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `c329fa5a8609ccd2caec96fc23afae9ba79bdf835faa05450d4e20a7380087f5` +**Source fingerprint (SHA-256):** `62a336f957836693fbcfbc097fe909e3efbceaf77102c960e00dc890ba9b5757` diff --git a/built-in-nodes/KlingVirtualTryOnNode.mdx b/built-in-nodes/KlingVirtualTryOnNode.mdx index d1c019eaf..a586c88fc 100644 --- a/built-in-nodes/KlingVirtualTryOnNode.mdx +++ b/built-in-nodes/KlingVirtualTryOnNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "KlingVirtualTryOnNode" icon: "circle" mode: wide --- + Kling Virtual Try On Node. Input a human image and a cloth image to try on the cloth on the human. You can merge multiple clothing item pictures into one image with a white background. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `human_image` | The human image to try clothes on | IMAGE | Yes | - | | `cloth_image` | The clothing image to try on the human | IMAGE | Yes | - | | `model_name` | The virtual try-on model to use (default: "kolors-virtual-try-on-v1") | STRING | Yes | `"kolors-virtual-try-on-v1"` | @@ -18,10 +19,10 @@ Kling Virtual Try On Node. Input a human image and a cloth image to try on the c ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The resulting image showing the human with the clothing item tried on | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVirtualTryOnNode/en.md) --- -**Source fingerprint (SHA-256):** `b642ea6583e971f47a580212030f564e24b055caf77dc99764b79ee21e2988f9` +**Source fingerprint (SHA-256):** `bf256d8732f4c6acf65838812fc322e48ef886257bbb48c02b0cc6ab5d78dce5` diff --git a/built-in-nodes/Krea2ImageNode.mdx b/built-in-nodes/Krea2ImageNode.mdx index 3ab47134f..0702c3ec7 100644 --- a/built-in-nodes/Krea2ImageNode.mdx +++ b/built-in-nodes/Krea2ImageNode.mdx @@ -5,14 +5,15 @@ sidebarTitle: "Krea2ImageNode" icon: "circle" mode: wide --- + ## Overview -The Krea 2 Image node generates images using the Krea 2 AI model. It supports two model variants: Medium for expressive illustrations and Large for expressive photorealism. You can optionally include a moodboard and up to 10 image style references to influence the generated image. +The Krea 2 Image node generates images using the Krea 2 AI model. It supports two model variants: Medium for expressive illustrations and Large for expressive photorealism, with an additional Medium Turbo option for faster generation. You can optionally include a moodboard and up to 10 image style references to influence the generated image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt for the image. | STRING | Yes | N/A | | `model` | Krea 2 Medium is best for expressive illustrations; Krea 2 Large is best for expressive photorealism. | DICT | Yes | See below | | `seed` | Random seed for reproducibility (default: 0). | INT | Yes | 0 to 2147483647 | @@ -20,8 +21,8 @@ The Krea 2 Image node generates images using the Krea 2 AI model. It supports tw The `model` parameter is a dictionary with the following sub-parameters: | Sub-Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `model` | Selects the Krea 2 model variant. | STRING | Yes | `"krea 2 medium"`
`"krea 2 large"` | +|---------------|-------------|-----------|----------|-------| +| `model` | Selects the Krea 2 model variant. | STRING | Yes | `"krea 2 medium turbo"`
`"krea 2 medium"`
`"krea 2 large"` | | `aspect_ratio` | The aspect ratio for the generated image. | STRING | Yes | N/A | | `resolution` | The resolution for the generated image. | STRING | Yes | N/A | | `creativity` | Controls the creativity level of the generation. | FLOAT | Yes | N/A | @@ -37,10 +38,10 @@ The `model` parameter is a dictionary with the following sub-parameters: ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The generated image as a tensor. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Krea2ImageNode/en.md) --- -**Source fingerprint (SHA-256):** `6aeb2d935ef5df5699a19271c9ceb766892ef4b0e4f67bfa540bf12ffadf362d` +**Source fingerprint (SHA-256):** `645b404fe2c7653662803f1630125bdef912429c95d7b3a1268b0e0d7f533277` diff --git a/built-in-nodes/Krea2StyleReferenceNode.mdx b/built-in-nodes/Krea2StyleReferenceNode.mdx index 5f517aaed..c2fd5ff9c 100644 --- a/built-in-nodes/Krea2StyleReferenceNode.mdx +++ b/built-in-nodes/Krea2StyleReferenceNode.mdx @@ -5,14 +5,13 @@ sidebarTitle: "Krea2StyleReferenceNode" icon: "circle" mode: wide --- -## Overview The Krea 2 Style Reference node lets you add a reference image to influence the style of a Krea 2 image generation. You can chain multiple style references together (up to 10 total) and feed the combined result into a Krea 2 Image node. Each image you provide is uploaded to ComfyAPI storage and passed as a URL. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | Reference image whose style influences the generation. | IMAGE | Yes | - | | `strength` | Reference strength; negative values invert the style influence (default: 1.0). | FLOAT | Yes | -2.0 to 2.0 (step: 0.05) | | `style_reference` | Optional incoming chain of style references; this node appends one more. | STYLE_REF | No | - | @@ -22,10 +21,10 @@ The Krea 2 Style Reference node lets you add a reference image to influence the ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `style_reference` | A list of style reference entries, each containing a URL and strength value. Feed this output into a Krea 2 Image node. | STYLE_REF | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Krea2StyleReferenceNode/en.md) --- -**Source fingerprint (SHA-256):** `7f87568a1cd5038571f3188cfb1d71e15533ea19eee01d7826fe574a1a4dc88d` +**Source fingerprint (SHA-256):** `a7e52408245b6a3caaca558c8d4d07d090686f32f5d5c7df77ab07311c9c1c6e` diff --git a/built-in-nodes/LTXAVTextEncoderLoader.mdx b/built-in-nodes/LTXAVTextEncoderLoader.mdx index 35d6ad03b..ae7b14212 100644 --- a/built-in-nodes/LTXAVTextEncoderLoader.mdx +++ b/built-in-nodes/LTXAVTextEncoderLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXAVTextEncoderLoader" icon: "circle" mode: wide --- + This node loads a specialized text encoder for the LTXV audio model. It combines a specific text encoder file with a checkpoint file to create a CLIP model that can be used for audio-related text conditioning tasks. ## Inputs diff --git a/built-in-nodes/LTXVAddGuide.mdx b/built-in-nodes/LTXVAddGuide.mdx index f8df08404..b47bab87c 100644 --- a/built-in-nodes/LTXVAddGuide.mdx +++ b/built-in-nodes/LTXVAddGuide.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAddGuide" icon: "circle" mode: wide --- + The LTXVAddGuide node adds video conditioning guidance to latent sequences by encoding input images or videos and incorporating them as keyframes into the conditioning data. It processes the input through a VAE encoder and strategically places the resulting latents at specified frame positions while updating both positive and negative conditioning with keyframe information. The node handles frame alignment constraints and allows control over the strength of the conditioning influence. ## Inputs diff --git a/built-in-nodes/LTXVAudioVAEDecode.mdx b/built-in-nodes/LTXVAudioVAEDecode.mdx index 4c4164033..f9cd349d7 100644 --- a/built-in-nodes/LTXVAudioVAEDecode.mdx +++ b/built-in-nodes/LTXVAudioVAEDecode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAEDecode" icon: "circle" mode: wide --- + The LTXV Audio VAE Decode node converts a latent representation of audio back into an audio waveform. It uses a specialized Audio VAE model to perform this decoding process, producing an audio output with a specific sample rate. ## Inputs diff --git a/built-in-nodes/LTXVAudioVAEEncode.mdx b/built-in-nodes/LTXVAudioVAEEncode.mdx index 6931a45b7..e3bb954c1 100644 --- a/built-in-nodes/LTXVAudioVAEEncode.mdx +++ b/built-in-nodes/LTXVAudioVAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAEEncode" icon: "circle" mode: wide --- + The LTXV Audio VAE Encode node takes an audio input and compresses it into a smaller, latent representation using a specified Audio VAE model. This process is essential for generating or manipulating audio within a latent space workflow, as it converts raw audio data into a format that other nodes in the pipeline can understand and process. ## Inputs diff --git a/built-in-nodes/LTXVAudioVAELoader.mdx b/built-in-nodes/LTXVAudioVAELoader.mdx index c9bf24e64..66dc4f3e1 100644 --- a/built-in-nodes/LTXVAudioVAELoader.mdx +++ b/built-in-nodes/LTXVAudioVAELoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAELoader" icon: "circle" mode: wide --- + The LTXV Audio VAE Loader node loads a pre-trained Audio Variational Autoencoder (VAE) model from a checkpoint file. It reads the specified checkpoint, loads its weights and metadata, and prepares the model for use in audio generation or processing workflows within ComfyUI. ## Inputs diff --git a/built-in-nodes/LTXVConcatAVLatent.mdx b/built-in-nodes/LTXVConcatAVLatent.mdx index 93b5a6b91..4ced86f44 100644 --- a/built-in-nodes/LTXVConcatAVLatent.mdx +++ b/built-in-nodes/LTXVConcatAVLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVConcatAVLatent" icon: "circle" mode: wide --- + The LTXVConcatAVLatent node combines a video latent representation and an audio latent representation into a single, concatenated latent output. It merges the `samples` tensors from both inputs and, if present, their `noise_mask` tensors as well, preparing them for further processing in a video generation pipeline. ## Inputs diff --git a/built-in-nodes/LTXVConditioning.mdx b/built-in-nodes/LTXVConditioning.mdx index e34da8c55..20f1d0e13 100644 --- a/built-in-nodes/LTXVConditioning.mdx +++ b/built-in-nodes/LTXVConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVConditioning" icon: "circle" mode: wide --- + The LTXVConditioning node adds frame rate information to both positive and negative conditioning inputs for video generation models. It takes existing conditioning data and applies the specified frame rate value to both conditioning sets, making them suitable for video model processing. ## Inputs diff --git a/built-in-nodes/LTXVContextWindows.mdx b/built-in-nodes/LTXVContextWindows.mdx new file mode 100644 index 000000000..28d68a332 --- /dev/null +++ b/built-in-nodes/LTXVContextWindows.mdx @@ -0,0 +1,37 @@ +--- +title: "LTXVContextWindows - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LTXVContextWindows node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LTXVContextWindows" +icon: "circle" +mode: wide +--- + +This node sets context windows for LTXV-like models during sampling. It divides the video generation process into overlapping windows to manage memory usage and improve temporal coherence. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model` | The model to apply context windows to during sampling. | MODEL | Yes | - | +| `context_length` | The length of the context window in real frames. Must be 8*n + 1. (default: 145) | INT | Yes | Minimum: 1
Maximum: nodes.MAX_RESOLUTION
Step: 8 | +| `context_overlap` | The overlap of the context window in real frames. (default: 40) | INT | Yes | Minimum: 0
Step: 8 | +| `context_schedule` | Step-dependent scheduling algorithm for context windows. (default: UNIFORM_STANDARD) | COMBO | Yes | `STATIC_STANDARD`
`UNIFORM_STANDARD`
`UNIFORM_LOOPED`
`BATCHED` | +| `context_stride` | The stride of the context window; only applicable to uniform schedules. (default: 1) | INT | No | Minimum: 1 | +| `closed_loop` | Whether to close the context window loop; only applicable to looped schedules. (default: False) | BOOLEAN | No | True
False | +| `fuse_method` | The method to use to fuse the context windows. (default: PYRAMID) | COMBO | Yes | Options from comfy.context_windows.ContextFuseMethods.LIST_STATIC | +| `freenoise` | Whether to apply FreeNoise noise shuffling, improves window blending. (default: True) | BOOLEAN | No | True
False | +| `retain_first_frame` | Retain the first latent frame in every context window (may help retain initial reference). (default: False) | BOOLEAN | No | True
False | +| `split_conds_to_windows` | Whether to split multiple conditionings (created by ConditionCombine) to each window based on region index. (default: False) | BOOLEAN | No | True
False | + +**Note:** The `context_length` parameter must follow the formula 8*n + 1, where n is a positive integer. The node automatically adjusts the value to meet this requirement by converting real frames to latent frames. The `context_overlap` is also converted from real frames to latent frames (divided by 8). + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `MODEL` | The model with context windows applied for sampling. | MODEL | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVContextWindows/en.md) + +--- +**Source fingerprint (SHA-256):** `ad0b8c54acaab1853f6fe98dbad675478f033caf867df954b40b7db5208f5ae4` diff --git a/built-in-nodes/LTXVCropGuides.mdx b/built-in-nodes/LTXVCropGuides.mdx index 977c6238e..d1dc06790 100644 --- a/built-in-nodes/LTXVCropGuides.mdx +++ b/built-in-nodes/LTXVCropGuides.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVCropGuides" icon: "circle" mode: wide --- + The LTXVCropGuides node processes conditioning and latent inputs for video generation by removing keyframe information and adjusting the latent dimensions. It crops the latent image and noise mask to exclude keyframe sections while clearing keyframe indices from both positive and negative conditioning inputs. This prepares the data for video generation workflows that don't require keyframe guidance. ## Inputs diff --git a/built-in-nodes/LTXVEmptyLatentAudio.mdx b/built-in-nodes/LTXVEmptyLatentAudio.mdx index 948155198..dd1d70ff2 100644 --- a/built-in-nodes/LTXVEmptyLatentAudio.mdx +++ b/built-in-nodes/LTXVEmptyLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVEmptyLatentAudio" icon: "circle" mode: wide --- + The LTXV Empty Latent Audio node creates a batch of empty (zero-filled) latent audio tensors. It uses the configuration from a provided Audio VAE model to determine the correct dimensions for the latent space, such as the number of channels and frequency bins. This empty latent serves as a starting point for audio generation or manipulation workflows within ComfyUI. ## Inputs diff --git a/built-in-nodes/LTXVImgToVideo.mdx b/built-in-nodes/LTXVImgToVideo.mdx index c56ae7a9f..90572a90b 100644 --- a/built-in-nodes/LTXVImgToVideo.mdx +++ b/built-in-nodes/LTXVImgToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVImgToVideo" icon: "circle" mode: wide --- + The LTXVImgToVideo node converts an input image into a video latent representation for video generation models. It takes a single image and extends it into a sequence of frames using the VAE encoder, then applies conditioning with strength control to determine how much of the original image content is preserved versus modified during video generation. ## Inputs diff --git a/built-in-nodes/LTXVImgToVideoInplace.mdx b/built-in-nodes/LTXVImgToVideoInplace.mdx index e9ec3a003..4615a5a60 100644 --- a/built-in-nodes/LTXVImgToVideoInplace.mdx +++ b/built-in-nodes/LTXVImgToVideoInplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVImgToVideoInplace" icon: "circle" mode: wide --- + The LTXVImgToVideoInplace node conditions a video latent representation by encoding an input image into its initial frames. It works by using a VAE to encode the image into the latent space and then blending it with the existing latent samples based on a specified strength. This allows an image to serve as a starting point or conditioning signal for video generation. ## Inputs diff --git a/built-in-nodes/LTXVLatentUpsampler.mdx b/built-in-nodes/LTXVLatentUpsampler.mdx index aa5a820d8..247517285 100644 --- a/built-in-nodes/LTXVLatentUpsampler.mdx +++ b/built-in-nodes/LTXVLatentUpsampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVLatentUpsampler" icon: "circle" mode: wide --- + The LTXVLatentUpsampler node increases the spatial resolution of a video latent representation by a factor of two. It uses a specialized upscale model to process the latent data, which is first un-normalized and then re-normalized using the provided VAE's channel statistics. This node is designed for video workflows within the latent space. ## Inputs diff --git a/built-in-nodes/LTXVPreprocess.mdx b/built-in-nodes/LTXVPreprocess.mdx index 6bd657331..24e9a9525 100644 --- a/built-in-nodes/LTXVPreprocess.mdx +++ b/built-in-nodes/LTXVPreprocess.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVPreprocess" icon: "circle" mode: wide --- + The LTXVPreprocess node applies video compression preprocessing to images. It simulates the quality loss of video compression by encoding an image as a single-frame MP4 video and then decoding it back, allowing you to control the compression level. ## Inputs diff --git a/built-in-nodes/LTXVReferenceAudio.mdx b/built-in-nodes/LTXVReferenceAudio.mdx index 0b8bb8557..f272f60b6 100644 --- a/built-in-nodes/LTXVReferenceAudio.mdx +++ b/built-in-nodes/LTXVReferenceAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVReferenceAudio" icon: "circle" mode: wide --- + The LTXV Reference Audio node is used for speaker identity transfer in audio generation. It encodes a reference audio clip into the conditioning for a model, allowing the generated audio to adopt the speaker's voice characteristics. It can also apply identity guidance, which runs an extra processing step to amplify the speaker identity effect. ## Inputs diff --git a/built-in-nodes/LTXVScheduler.mdx b/built-in-nodes/LTXVScheduler.mdx index 6f038b161..67b66f9f7 100644 --- a/built-in-nodes/LTXVScheduler.mdx +++ b/built-in-nodes/LTXVScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVScheduler" icon: "circle" mode: wide --- + The LTXVScheduler node generates sigma values for custom sampling processes. It calculates noise schedule parameters based on the number of tokens in the input latent and applies a sigmoid transformation to create the sampling schedule. The node can optionally stretch the resulting sigmas to match a specified terminal value. ## Inputs diff --git a/built-in-nodes/LTXVSeparateAVLatent.mdx b/built-in-nodes/LTXVSeparateAVLatent.mdx index 29eb0ff20..60ef973f4 100644 --- a/built-in-nodes/LTXVSeparateAVLatent.mdx +++ b/built-in-nodes/LTXVSeparateAVLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVSeparateAVLatent" icon: "circle" mode: wide --- + The LTXVSeparateAVLatent node takes a combined audio-visual latent representation and splits it into two distinct parts: one for video and one for audio. It separates the samples and, if present, the noise masks from the input latent, creating two new latent objects. ## Inputs diff --git a/built-in-nodes/LaplaceScheduler.mdx b/built-in-nodes/LaplaceScheduler.mdx index f6a814250..741e201ae 100644 --- a/built-in-nodes/LaplaceScheduler.mdx +++ b/built-in-nodes/LaplaceScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LaplaceScheduler" icon: "circle" mode: wide --- + The LaplaceScheduler node generates a sequence of sigma values following a Laplace distribution for use in diffusion sampling. It creates a schedule of noise levels that gradually decrease from a maximum to minimum value, using Laplace distribution parameters to control the progression. This scheduler is commonly used in custom sampling workflows to define the noise schedule for diffusion models. ## Inputs diff --git a/built-in-nodes/LatentAdd.mdx b/built-in-nodes/LatentAdd.mdx index 9d46d92c5..43bbe2d05 100644 --- a/built-in-nodes/LatentAdd.mdx +++ b/built-in-nodes/LatentAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentAdd" icon: "circle" mode: wide --- + The LatentAdd node is designed for the addition of two latent representations. It facilitates the combination of features or characteristics encoded in these representations by performing element-wise addition. ## Inputs diff --git a/built-in-nodes/LatentApplyOperation.mdx b/built-in-nodes/LatentApplyOperation.mdx index 9493cc2cb..7afd43c00 100644 --- a/built-in-nodes/LatentApplyOperation.mdx +++ b/built-in-nodes/LatentApplyOperation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentApplyOperation" icon: "circle" mode: wide --- + The LatentApplyOperation node applies a specified operation to latent samples. It takes latent data and an operation as inputs, processes the latent samples using the provided operation, and returns the modified latent data. This node allows you to transform or manipulate latent representations in your workflow. ## Inputs diff --git a/built-in-nodes/LatentApplyOperationCFG.mdx b/built-in-nodes/LatentApplyOperationCFG.mdx index 03f629b36..a3e67bb3e 100644 --- a/built-in-nodes/LatentApplyOperationCFG.mdx +++ b/built-in-nodes/LatentApplyOperationCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentApplyOperationCFG" icon: "circle" mode: wide --- + The LatentApplyOperationCFG node applies a latent operation to modify the conditioning guidance process in a model. It works by intercepting the conditioning outputs during the classifier-free guidance (CFG) sampling process and applying the specified operation to the latent representations before they are used for generation. ## Inputs diff --git a/built-in-nodes/LatentBatch.mdx b/built-in-nodes/LatentBatch.mdx index e3fcccd96..cb1f3d66f 100644 --- a/built-in-nodes/LatentBatch.mdx +++ b/built-in-nodes/LatentBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBatch" icon: "circle" mode: wide --- + The LatentBatch node is designed to merge two sets of latent samples into a single batch, potentially resizing one set to match the dimensions of the other before concatenation. This operation facilitates the combination of different latent representations for further processing or generation tasks. ## Inputs diff --git a/built-in-nodes/LatentBatchSeedBehavior.mdx b/built-in-nodes/LatentBatchSeedBehavior.mdx index 67dca98cb..959c8d7e7 100644 --- a/built-in-nodes/LatentBatchSeedBehavior.mdx +++ b/built-in-nodes/LatentBatchSeedBehavior.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBatchSeedBehavior" icon: "circle" mode: wide --- + The LatentBatchSeedBehavior node is designed to modify the seed behavior of a batch of latent samples. It allows for either randomizing or fixing the seed across the batch, thereby influencing the generation process by either introducing variability or maintaining consistency in the generated outputs. ## Inputs diff --git a/built-in-nodes/LatentBlend.mdx b/built-in-nodes/LatentBlend.mdx index 26aa4931e..d7159bbc0 100644 --- a/built-in-nodes/LatentBlend.mdx +++ b/built-in-nodes/LatentBlend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBlend" icon: "circle" mode: wide --- + The LatentBlend node combines two latent samples by blending them together using a specified blend factor. It takes two latent inputs and creates a new output where the first sample is weighted by the blend factor and the second sample is weighted by the inverse. If the input samples have different shapes, the second sample is automatically resized to match the first sample's dimensions. ## Inputs diff --git a/built-in-nodes/LatentComposite.mdx b/built-in-nodes/LatentComposite.mdx index 37a251fe9..24337984d 100644 --- a/built-in-nodes/LatentComposite.mdx +++ b/built-in-nodes/LatentComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentComposite" icon: "circle" mode: wide --- + The LatentComposite node is designed to blend or merge two latent representations into a single output. This process is essential for creating composite images or features by combining the characteristics of the input latents in a controlled manner. ## Inputs diff --git a/built-in-nodes/LatentCompositeMasked.mdx b/built-in-nodes/LatentCompositeMasked.mdx index 6c04b95d7..1099649b2 100644 --- a/built-in-nodes/LatentCompositeMasked.mdx +++ b/built-in-nodes/LatentCompositeMasked.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCompositeMasked" icon: "circle" mode: wide --- + The LatentCompositeMasked node is designed for blending two latent representations together at specified coordinates, optionally using a mask for more controlled compositing. This node enables the creation of complex latent images by overlaying parts of one image onto another, with the ability to resize the source image for a perfect fit. ## Inputs diff --git a/built-in-nodes/LatentConcat.mdx b/built-in-nodes/LatentConcat.mdx index 9d91bdb6d..56c918e9d 100644 --- a/built-in-nodes/LatentConcat.mdx +++ b/built-in-nodes/LatentConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentConcat" icon: "circle" mode: wide --- + The LatentConcat node combines two latent samples by joining them together along a chosen dimension. It takes two latent inputs and concatenates them along the x, y, or t axis, with the option to control which sample comes first. The node automatically adjusts the batch size of the second input to match the first before performing the concatenation. ## Inputs diff --git a/built-in-nodes/LatentCrop.mdx b/built-in-nodes/LatentCrop.mdx index 443ec468e..c0f0d9041 100644 --- a/built-in-nodes/LatentCrop.mdx +++ b/built-in-nodes/LatentCrop.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCrop" icon: "circle" mode: wide --- + The LatentCrop node is designed to perform cropping operations on latent representations of images. It allows for the specification of the crop dimensions and position, enabling targeted modifications of the latent space. ## Inputs diff --git a/built-in-nodes/LatentCut.mdx b/built-in-nodes/LatentCut.mdx index 10b26dfcc..2960c8dce 100644 --- a/built-in-nodes/LatentCut.mdx +++ b/built-in-nodes/LatentCut.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCut" icon: "circle" mode: wide --- + The LatentCut node extracts a specific section from latent samples along a chosen dimension. It allows you to cut out a portion of the latent representation by specifying the dimension (x, y, or t), starting position, and amount to extract. The node handles both positive and negative indexing and automatically adjusts the extraction amount to stay within the available bounds. ## Inputs diff --git a/built-in-nodes/LatentCutToBatch.mdx b/built-in-nodes/LatentCutToBatch.mdx index e15848315..ced2114f6 100644 --- a/built-in-nodes/LatentCutToBatch.mdx +++ b/built-in-nodes/LatentCutToBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCutToBatch" icon: "circle" mode: wide --- + The LatentCutToBatch node splits a latent representation along a chosen dimension into multiple slices and stacks them into a new batch. This allows you to process different parts of a latent sample independently. ## Inputs diff --git a/built-in-nodes/LatentFlip.mdx b/built-in-nodes/LatentFlip.mdx index 430e46194..d608eb250 100644 --- a/built-in-nodes/LatentFlip.mdx +++ b/built-in-nodes/LatentFlip.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentFlip" icon: "circle" mode: wide --- + The LatentFlip node is designed to manipulate latent representations by flipping them either vertically or horizontally. This operation allows for the transformation of the latent space, potentially uncovering new variations or perspectives within the data. ## Inputs diff --git a/built-in-nodes/LatentFromBatch.mdx b/built-in-nodes/LatentFromBatch.mdx index 4aa8eb787..61f64d77f 100644 --- a/built-in-nodes/LatentFromBatch.mdx +++ b/built-in-nodes/LatentFromBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentFromBatch" icon: "circle" mode: wide --- + This node is designed to extract a specific subset of latent samples from a given batch based on the specified batch index and length. It allows for selective processing of latent samples, facilitating operations on smaller segments of the batch for efficiency or targeted manipulation. ## Inputs diff --git a/built-in-nodes/LatentInterpolate.mdx b/built-in-nodes/LatentInterpolate.mdx index d4e637a4f..de781e5c2 100644 --- a/built-in-nodes/LatentInterpolate.mdx +++ b/built-in-nodes/LatentInterpolate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentInterpolate" icon: "circle" mode: wide --- + The LatentInterpolate node is designed to perform interpolation between two sets of latent samples based on a specified ratio, blending the characteristics of both sets to produce a new, intermediate set of latent samples. ## Inputs diff --git a/built-in-nodes/LatentMultiply.mdx b/built-in-nodes/LatentMultiply.mdx index 41e03158c..dde2fbb83 100644 --- a/built-in-nodes/LatentMultiply.mdx +++ b/built-in-nodes/LatentMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentMultiply" icon: "circle" mode: wide --- + The LatentMultiply node is designed to scale the latent representation of samples by a specified multiplier. This operation allows for the adjustment of the intensity or magnitude of features within the latent space, enabling fine-tuning of generated content or the exploration of variations within a given latent direction. ## Inputs diff --git a/built-in-nodes/LatentOperationSharpen.mdx b/built-in-nodes/LatentOperationSharpen.mdx index 3aba4f240..78b50c211 100644 --- a/built-in-nodes/LatentOperationSharpen.mdx +++ b/built-in-nodes/LatentOperationSharpen.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentOperationSharpen" icon: "circle" mode: wide --- + The LatentOperationSharpen node applies a sharpening effect to latent representations using a Gaussian kernel. It works by normalizing the latent data, applying a convolution with a custom sharpening kernel, and then restoring the original luminance. This enhances the details and edges in the latent space representation. ## Inputs diff --git a/built-in-nodes/LatentOperationTonemapReinhard.mdx b/built-in-nodes/LatentOperationTonemapReinhard.mdx index 6c52b98c4..96c23d463 100644 --- a/built-in-nodes/LatentOperationTonemapReinhard.mdx +++ b/built-in-nodes/LatentOperationTonemapReinhard.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentOperationTonemapReinhard" icon: "circle" mode: wide --- + The LatentOperationTonemapReinhard node applies Reinhard tonemapping to latent vectors. This technique normalizes the latent vectors and adjusts their magnitude using a statistical approach based on mean and standard deviation, with the intensity controlled by a multiplier parameter. ## Inputs diff --git a/built-in-nodes/LatentRotate.mdx b/built-in-nodes/LatentRotate.mdx index eeae6d5fa..807eb8811 100644 --- a/built-in-nodes/LatentRotate.mdx +++ b/built-in-nodes/LatentRotate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentRotate" icon: "circle" mode: wide --- + The LatentRotate node is designed to rotate latent representations of images by specified angles. It abstracts the complexity of manipulating latent space to achieve rotation effects, enabling users to easily transform images in a generative model's latent space. ## Inputs diff --git a/built-in-nodes/LatentSubtract.mdx b/built-in-nodes/LatentSubtract.mdx index c6aa88be4..e573814d4 100644 --- a/built-in-nodes/LatentSubtract.mdx +++ b/built-in-nodes/LatentSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentSubtract" icon: "circle" mode: wide --- + The LatentSubtract node is designed for subtracting one latent representation from another. This operation can be used to manipulate or modify the characteristics of generative models' outputs by effectively removing features or attributes represented in one latent space from another. ## Inputs diff --git a/built-in-nodes/LatentUpscale.mdx b/built-in-nodes/LatentUpscale.mdx index be2d38403..7c49c63be 100644 --- a/built-in-nodes/LatentUpscale.mdx +++ b/built-in-nodes/LatentUpscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscale" icon: "circle" mode: wide --- + The LatentUpscale node is designed for upscaling latent representations of images. It allows for the adjustment of the output image's dimensions and the method of upscaling, providing flexibility in enhancing the resolution of latent images. ## Inputs diff --git a/built-in-nodes/LatentUpscaleBy.mdx b/built-in-nodes/LatentUpscaleBy.mdx index e273a3de8..17caad6f7 100644 --- a/built-in-nodes/LatentUpscaleBy.mdx +++ b/built-in-nodes/LatentUpscaleBy.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscaleBy" icon: "circle" mode: wide --- + The LatentUpscaleBy node is designed for upscaling latent representations of images. It allows for the adjustment of the scale factor and the method of upscaling, providing flexibility in enhancing the resolution of latent samples. ## Inputs diff --git a/built-in-nodes/LatentUpscaleModelLoader.mdx b/built-in-nodes/LatentUpscaleModelLoader.mdx index 29e5620a1..c4a296e83 100644 --- a/built-in-nodes/LatentUpscaleModelLoader.mdx +++ b/built-in-nodes/LatentUpscaleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscaleModelLoader" icon: "circle" mode: wide --- + The LatentUpscaleModelLoader node loads a specialized model designed for upscaling latent representations. It reads a model file from the system's designated folder and automatically detects its type (720p, 1080p, or other) to instantiate and configure the correct internal model architecture. The loaded model is then ready to be used by other nodes for latent space super-resolution tasks. ## Inputs diff --git a/built-in-nodes/LazyCache.mdx b/built-in-nodes/LazyCache.mdx index adb93110f..fb05e5627 100644 --- a/built-in-nodes/LazyCache.mdx +++ b/built-in-nodes/LazyCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LazyCache" icon: "circle" mode: wide --- + LazyCache is a homebrew version of EasyCache that provides an even easier implementation. It works with any model in ComfyUI and adds caching functionality to reduce computation during sampling. While it generally performs worse than EasyCache, it can be more effective in some rare cases and offers universal compatibility. ## Inputs diff --git a/built-in-nodes/Load3D.mdx b/built-in-nodes/Load3D.mdx index 4e5970369..21ac45aa6 100644 --- a/built-in-nodes/Load3D.mdx +++ b/built-in-nodes/Load3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Load3D" icon: "circle" mode: wide --- + The Load3D node is a core node for loading and processing 3D model files. When loading the node, it automatically retrieves available 3D resources from `ComfyUI/input/3d/`. You can also upload supported 3D files for preview using the upload function. **Supported Formats** diff --git a/built-in-nodes/Load3DAdvanced.mdx b/built-in-nodes/Load3DAdvanced.mdx new file mode 100644 index 000000000..da2511330 --- /dev/null +++ b/built-in-nodes/Load3DAdvanced.mdx @@ -0,0 +1,38 @@ +--- +title: "Load3DAdvanced - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the Load3DAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "Load3DAdvanced" +icon: "circle" +mode: wide +--- + +This node loads a 3D model file from your ComfyUI input directory and provides the model data along with camera and viewport information. It supports common 3D file formats and allows you to specify the output image dimensions for rendering. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model_file` | The 3D model file to load. Select "none" to skip loading a model. | STRING | Yes | `"none"`
List of available 3D files in the input/3d directory | +| `viewport_state` | The current viewport state containing camera and model information from the 3D viewer. | LOAD3D | Yes | - | +| `width` | The width of the output image in pixels (default: 1024) | INT | Yes | Min: 1
Max: 4096
Step: 1 | +| `height` | The height of the output image in pixels (default: 1024) | INT | Yes | Min: 1
Max: 4096
Step: 1 | + +**Notes on Parameters:** +- The `model_file` parameter only shows files with the following extensions: .gltf, .glb, .obj, .fbx, .stl +- Files must be placed in the `input/3d` directory of your ComfyUI installation +- If `model_file` is set to "none", no 3D model data will be loaded (the output `model_3d` will be empty) + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `model_3d` | The loaded 3D model data, or empty if no model file was selected | FILE3DANY | +| `model_3d_info` | Information about the loaded 3D model from the viewport state | LOAD3DMODELINFO | +| `camera_info` | Camera information from the viewport state | LOAD3DCAMERA | +| `width` | The specified output image width | INT | +| `height` | The specified output image height | INT | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Load3DAdvanced/en.md) + +--- +**Source fingerprint (SHA-256):** `fdacea8abf627621150e1196743e36f61534333837c33cc9a7416a6d11700c4d` diff --git a/built-in-nodes/Load3DAnimation.mdx b/built-in-nodes/Load3DAnimation.mdx index b6d996cc6..c56a81b22 100644 --- a/built-in-nodes/Load3DAnimation.mdx +++ b/built-in-nodes/Load3DAnimation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Load3DAnimation" icon: "circle" mode: wide --- + The Load3DAnimation node is a core node for loading and processing 3D model files. When loading the node, it automatically retrieves available 3D resources from `ComfyUI/input/3d/`. You can also upload supported 3D files for preview using the upload function. > - Most of the functions of this node are the same as the Load 3D node, but this node supports loading models with animations, and you can preview the corresponding animations in the node. diff --git a/built-in-nodes/LoadAudio.mdx b/built-in-nodes/LoadAudio.mdx index 044acfa3f..5b186fb40 100644 --- a/built-in-nodes/LoadAudio.mdx +++ b/built-in-nodes/LoadAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadAudio" icon: "circle" mode: wide --- + The LoadAudio node loads audio files from the input directory and converts them into a format that can be processed by other audio nodes in ComfyUI. It reads audio files and extracts both the waveform data and sample rate, making them available for downstream audio processing tasks. ## Inputs diff --git a/built-in-nodes/LoadBackgroundRemovalModel.mdx b/built-in-nodes/LoadBackgroundRemovalModel.mdx index efb4657ce..2f43d96fc 100644 --- a/built-in-nodes/LoadBackgroundRemovalModel.mdx +++ b/built-in-nodes/LoadBackgroundRemovalModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadBackgroundRemovalModel" icon: "circle" mode: wide --- + ## Overview Loads a background removal model from a file. This node prepares the model for use in removing backgrounds from images. diff --git a/built-in-nodes/LoadDA3Model.mdx b/built-in-nodes/LoadDA3Model.mdx new file mode 100644 index 000000000..7430bb557 --- /dev/null +++ b/built-in-nodes/LoadDA3Model.mdx @@ -0,0 +1,27 @@ +--- +title: "LoadDA3Model - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LoadDA3Model node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LoadDA3Model" +icon: "circle" +mode: wide +--- + +This node loads a Depth Anything 3 model from a file, preparing it for use in depth estimation tasks. It allows you to select the model file and optionally specify the numerical precision (data type) for the model's weights. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model_name` | The name of the Depth Anything 3 model file to load. | STRING | Yes | List of available model files in the `geometry_estimation` folder | +| `weight_dtype` | The numerical precision (data type) for the model's weights. The "default" option uses the model's original precision. (default: "default") | STRING | No | `"default"`
`"fp16"`
`"bf16"`
`"fp32"` | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `DA3_MODEL` | The loaded Depth Anything 3 model, ready for use in depth estimation workflows. | DA3_MODEL | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadDA3Model/en.md) + +--- +**Source fingerprint (SHA-256):** `b1b3f4075cd9172bc1f274848b9300bca20d3cbd53b23d3c4a9f0986b36e409e` diff --git a/built-in-nodes/LoadImage.mdx b/built-in-nodes/LoadImage.mdx index 51af9bdf2..78821242e 100644 --- a/built-in-nodes/LoadImage.mdx +++ b/built-in-nodes/LoadImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImage" icon: "circle" mode: wide --- + The LoadImage node is designed to load and preprocess images from a specified path. It handles image formats with multiple frames, applies necessary transformations such as rotation based on EXIF data, normalizes pixel values, and optionally generates a mask for images with an alpha channel. This node is essential for preparing images for further processing or analysis within a pipeline. ## Inputs diff --git a/built-in-nodes/LoadImageDataSetFromFolder.mdx b/built-in-nodes/LoadImageDataSetFromFolder.mdx index 952692f51..8fcbd489c 100644 --- a/built-in-nodes/LoadImageDataSetFromFolder.mdx +++ b/built-in-nodes/LoadImageDataSetFromFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageDataSetFromFolder" icon: "circle" mode: wide --- + This node loads multiple images from a specified subfolder within ComfyUI's input directory. It scans the chosen folder for common image file types and returns them as a list, making it useful for batch processing or dataset preparation. ## Inputs diff --git a/built-in-nodes/LoadImageMask.mdx b/built-in-nodes/LoadImageMask.mdx index f22b6cfc7..df690d91e 100644 --- a/built-in-nodes/LoadImageMask.mdx +++ b/built-in-nodes/LoadImageMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageMask" icon: "circle" mode: wide --- + The LoadImageMask node is designed to load images and their associated masks from a specified path, processing them to ensure compatibility with further image manipulation or analysis tasks. It focuses on handling various image formats and conditions, such as presence of an alpha channel for masks, and prepares the images and masks for downstream processing by converting them to a standardized format. ## Inputs diff --git a/built-in-nodes/LoadImageOutput.mdx b/built-in-nodes/LoadImageOutput.mdx index b0c1a2288..fb2d52234 100644 --- a/built-in-nodes/LoadImageOutput.mdx +++ b/built-in-nodes/LoadImageOutput.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageOutput" icon: "circle" mode: wide --- + The LoadImageOutput node loads images from the output folder. When you click the refresh button, it updates the list of available images and automatically selects the first one, making it easy to iterate through your generated images. ## Inputs diff --git a/built-in-nodes/LoadImageSetFromFolderNode.mdx b/built-in-nodes/LoadImageSetFromFolderNode.mdx index 839cb040f..8d07b9b05 100644 --- a/built-in-nodes/LoadImageSetFromFolderNode.mdx +++ b/built-in-nodes/LoadImageSetFromFolderNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageSetFromFolderNode" icon: "circle" mode: wide --- + The LoadImageSetFromFolderNode loads multiple images from a specified folder directory for training purposes. It automatically detects common image formats and can optionally resize the images using different methods before returning them as a batch. ## Inputs diff --git a/built-in-nodes/LoadImageSetNode.mdx b/built-in-nodes/LoadImageSetNode.mdx index 3f4647614..dcaa23bcb 100644 --- a/built-in-nodes/LoadImageSetNode.mdx +++ b/built-in-nodes/LoadImageSetNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageSetNode" icon: "circle" mode: wide --- + The LoadImageSetNode loads multiple images from the input directory for batch processing and training purposes. It supports various image formats and can optionally resize the images using different methods. This node processes all selected images as a batch and returns them as a single tensor. ## Inputs diff --git a/built-in-nodes/LoadImageTextDataSetFromFolder.mdx b/built-in-nodes/LoadImageTextDataSetFromFolder.mdx index b7e0ef8ed..e8045e8b6 100644 --- a/built-in-nodes/LoadImageTextDataSetFromFolder.mdx +++ b/built-in-nodes/LoadImageTextDataSetFromFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageTextDataSetFromFolder" icon: "circle" mode: wide --- + This node loads a dataset of images and their corresponding text captions from a specified folder. It searches for image files and automatically looks for matching `.txt` files with the same base name to use as captions. The node also supports a specific folder structure where subfolders can be named with a number prefix (like `10_folder_name`) to indicate that the images inside should be repeated multiple times in the output. ## Inputs diff --git a/built-in-nodes/LoadImageTextSetFromFolderNode.mdx b/built-in-nodes/LoadImageTextSetFromFolderNode.mdx index 2e1d1e737..1a36b7090 100644 --- a/built-in-nodes/LoadImageTextSetFromFolderNode.mdx +++ b/built-in-nodes/LoadImageTextSetFromFolderNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageTextSetFromFolderNode" icon: "circle" mode: wide --- + Loads a batch of images and their corresponding text captions from a specified directory for training purposes. The node automatically searches for image files and their associated caption text files, processes the images according to specified resize settings, and encodes the captions using the provided CLIP model. ## Inputs diff --git a/built-in-nodes/LoadLatent.mdx b/built-in-nodes/LoadLatent.mdx index 1f35b532d..6c9fba7a2 100644 --- a/built-in-nodes/LoadLatent.mdx +++ b/built-in-nodes/LoadLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadLatent" icon: "circle" mode: wide --- + The LoadLatent node loads previously saved latent representations from .latent files in the input directory. It reads the latent tensor data from the file and applies any necessary scaling adjustments before returning the latent data for use in other nodes. ## Inputs diff --git a/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx b/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx index fc65c231f..283b4ffd3 100644 --- a/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx +++ b/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadMediaPipeFaceLandmarker" icon: "circle" mode: wide --- + ## Overview This node loads a MediaPipe Face Landmarker v2 model, which can detect faces and facial landmarks (like eyes, nose, and mouth) in images. It contains two detection variants (short-range and full-range) along with shared mesh data, blendshapes, and canonical geometry for facial analysis. diff --git a/built-in-nodes/LoadMoGeModel.mdx b/built-in-nodes/LoadMoGeModel.mdx index 26fdfb5d4..6d29f1edc 100644 --- a/built-in-nodes/LoadMoGeModel.mdx +++ b/built-in-nodes/LoadMoGeModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadMoGeModel" icon: "circle" mode: wide --- + ## Overview Loads a MoGe (Monocular Geometry) model from a file and prepares it for use in geometry estimation tasks. This node reads a model file from the `geometry_estimation` folder and initializes the MoGe model with its trained weights. diff --git a/built-in-nodes/LoadTrainingDataset.mdx b/built-in-nodes/LoadTrainingDataset.mdx index 85ee570af..f2481729a 100644 --- a/built-in-nodes/LoadTrainingDataset.mdx +++ b/built-in-nodes/LoadTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadTrainingDataset" icon: "circle" mode: wide --- + This node loads an encoded training dataset that has been previously saved to disk. It searches for and reads all data shard files from a specified folder within the ComfyUI output directory, then returns the combined latent vectors and conditioning data for use in training workflows. ## Inputs diff --git a/built-in-nodes/LoadVideo.mdx b/built-in-nodes/LoadVideo.mdx index 87a75f526..2234a0a13 100644 --- a/built-in-nodes/LoadVideo.mdx +++ b/built-in-nodes/LoadVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadVideo" icon: "circle" mode: wide --- + The Load Video node loads video files from the input directory and makes them available for processing in the workflow. It reads video files from the designated input folder and outputs them as video data that can be connected to other video processing nodes. ## Inputs diff --git a/built-in-nodes/LoraLoader.mdx b/built-in-nodes/LoraLoader.mdx index 614765574..c9a11b5d4 100644 --- a/built-in-nodes/LoraLoader.mdx +++ b/built-in-nodes/LoraLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoader" icon: "circle" mode: wide --- + This node automatically detects models located in the LoRA folder (including subfolders) with the corresponding model path being `ComfyUI\models\loras`. For more information, please refer to Installing LoRA Models The LoRA Loader node is primarily used to load LoRA models. You can think of LoRA models as filters that can give your images specific styles, content, and details: diff --git a/built-in-nodes/LoraLoaderBypass.mdx b/built-in-nodes/LoraLoaderBypass.mdx index 9630b4319..c9b7141cb 100644 --- a/built-in-nodes/LoraLoaderBypass.mdx +++ b/built-in-nodes/LoraLoaderBypass.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderBypass" icon: "circle" mode: wide --- + The LoraLoaderBypass node applies a LoRA (Low-Rank Adaptation) to a diffusion model and a CLIP model in a special "bypass" mode. Unlike a standard LoRA loader, this method does not permanently modify the base model's weights. Instead, it computes the output by adding the LoRA's effect to the model's normal forward pass, which is useful for training or when working with models that have their weights offloaded. ## Inputs diff --git a/built-in-nodes/LoraLoaderBypassModelOnly.mdx b/built-in-nodes/LoraLoaderBypassModelOnly.mdx index 64b14997e..580193561 100644 --- a/built-in-nodes/LoraLoaderBypassModelOnly.mdx +++ b/built-in-nodes/LoraLoaderBypassModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderBypassModelOnly" icon: "circle" mode: wide --- + This node applies a LoRA (Low-Rank Adaptation) to a model to modify its behavior, but only affects the model component itself. It loads a specified LoRA file and adjusts the model's weights by a given strength, leaving other components like the CLIP text encoder unchanged. ## Inputs diff --git a/built-in-nodes/LoraLoaderModelOnly.mdx b/built-in-nodes/LoraLoaderModelOnly.mdx index 80258e91f..9bbd47ee7 100644 --- a/built-in-nodes/LoraLoaderModelOnly.mdx +++ b/built-in-nodes/LoraLoaderModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderModelOnly" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/loras` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. This node specializes in loading a LoRA model without requiring a CLIP model, focusing on enhancing or modifying a given model based on LoRA parameters. It allows for the dynamic adjustment of the model's strength through LoRA parameters, facilitating fine-tuned control over the model's behavior. diff --git a/built-in-nodes/LoraModelLoader.mdx b/built-in-nodes/LoraModelLoader.mdx index 69a36937c..067788379 100644 --- a/built-in-nodes/LoraModelLoader.mdx +++ b/built-in-nodes/LoraModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraModelLoader" icon: "circle" mode: wide --- + The LoraModelLoader node applies trained LoRA (Low-Rank Adaptation) weights to a diffusion model. It modifies the base model by loading LoRA weights from a trained LoRA model and adjusting their influence strength. This allows you to customize the behavior of diffusion models without retraining them from scratch. ## Inputs diff --git a/built-in-nodes/LoraSave.mdx b/built-in-nodes/LoraSave.mdx index 74af80ac8..03dcb3c2b 100644 --- a/built-in-nodes/LoraSave.mdx +++ b/built-in-nodes/LoraSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraSave" icon: "circle" mode: wide --- + The LoraSave node extracts and saves LoRA (Low-Rank Adaptation) files from model differences. It can process diffusion model differences, text encoder differences, or both, converting them into LoRA format with specified rank and type. The resulting LoRA file is saved to the output directory for later use. ## Inputs diff --git a/built-in-nodes/LossGraphNode.mdx b/built-in-nodes/LossGraphNode.mdx index 5dbd19baf..5f55aaa95 100644 --- a/built-in-nodes/LossGraphNode.mdx +++ b/built-in-nodes/LossGraphNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LossGraphNode" icon: "circle" mode: wide --- + The LossGraphNode creates a visual graph of training loss values over time and displays it as a preview image. It takes loss data from training processes and generates a line chart showing how the loss changes across training steps. The resulting graph includes axis labels and min/max loss values. ## Inputs diff --git a/built-in-nodes/LotusConditioning.mdx b/built-in-nodes/LotusConditioning.mdx index 6c333e3f9..b12fdc376 100644 --- a/built-in-nodes/LotusConditioning.mdx +++ b/built-in-nodes/LotusConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LotusConditioning" icon: "circle" mode: wide --- + The LotusConditioning node provides pre-computed conditioning embeddings for the Lotus model. It uses a frozen encoder with null conditioning and returns hardcoded prompt embeddings to achieve parity with the reference implementation without requiring inference or loading large tensor files. This node outputs a fixed conditioning tensor that can be used directly in the generation pipeline. ## Inputs diff --git a/built-in-nodes/LtxvApiImageToVideo.mdx b/built-in-nodes/LtxvApiImageToVideo.mdx index 5c4dfd9bf..932bf84c8 100644 --- a/built-in-nodes/LtxvApiImageToVideo.mdx +++ b/built-in-nodes/LtxvApiImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LtxvApiImageToVideo" icon: "circle" mode: wide --- + The LTXV Image To Video node generates a professional-quality video from a single starting image. It uses an external API to create a video sequence based on your text prompt, allowing you to customize the duration, resolution, and frame rate. ## Inputs @@ -34,4 +35,4 @@ The LTXV Image To Video node generates a professional-quality video from a singl > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LtxvApiImageToVideo/en.md) --- -**Source fingerprint (SHA-256):** `a4c6109ba8f70b0e80cf1888f940190c7a3e3994867e37f00669ae12742a94f8` +**Source fingerprint (SHA-256):** `5c62025059cc0c583de3e0ae8721b8f8adb6929bb03cbcec5875bbc1fdaf20c3` diff --git a/built-in-nodes/LtxvApiTextToVideo.mdx b/built-in-nodes/LtxvApiTextToVideo.mdx index 268b62edc..9ee281547 100644 --- a/built-in-nodes/LtxvApiTextToVideo.mdx +++ b/built-in-nodes/LtxvApiTextToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LtxvApiTextToVideo" icon: "circle" mode: wide --- + The LTXV Text To Video node generates professional-quality videos from a text description. It connects to an external API to create videos with customizable duration, resolution, and frame rate. You can also choose to have AI-generated audio added to the video. ## Inputs @@ -32,4 +33,4 @@ The LTXV Text To Video node generates professional-quality videos from a text de > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LtxvApiTextToVideo/en.md) --- -**Source fingerprint (SHA-256):** `8da5616f195dc4dea7d46d56b71dead6fb7a5dfa74bb7d8909bf6bd792540feb` +**Source fingerprint (SHA-256):** `11e358bdf9ff9b799b428768c10504f450d81d12f81b2ec0749f9d2d88e82f91` diff --git a/built-in-nodes/LumaConceptsNode.mdx b/built-in-nodes/LumaConceptsNode.mdx index 8a60d234b..065f1a956 100644 --- a/built-in-nodes/LumaConceptsNode.mdx +++ b/built-in-nodes/LumaConceptsNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "LumaConceptsNode" icon: "circle" mode: wide --- + Holds one or more Camera Concepts for use with Luma Text to Video and Luma Image to Video nodes. This node allows you to select up to four camera concepts and optionally combine them with existing concept chains. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `concept1` | First camera concept selection from available Luma concepts | STRING | Yes | Multiple options available
Includes "None" option | | `concept2` | Second camera concept selection from available Luma concepts | STRING | Yes | Multiple options available
Includes "None" option | | `concept3` | Third camera concept selection from available Luma concepts | STRING | Yes | Multiple options available
Includes "None" option | @@ -22,10 +23,10 @@ Holds one or more Camera Concepts for use with Luma Text to Video and Luma Image ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `luma_concepts` | Combined camera concept chain containing all selected concepts | LUMA_CONCEPTS | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaConceptsNode/en.md) --- -**Source fingerprint (SHA-256):** `37e292aee8316e165e0069b1080479fed049d5bf754de90ef830f6400ca7e5c8` +**Source fingerprint (SHA-256):** `e684f7d9d2975d4168701e4f6a79dc6b22854d62b58ce016477a05c66dd6e058` diff --git a/built-in-nodes/LumaImageEditNode2.mdx b/built-in-nodes/LumaImageEditNode2.mdx index c84c750a5..4c889318f 100644 --- a/built-in-nodes/LumaImageEditNode2.mdx +++ b/built-in-nodes/LumaImageEditNode2.mdx @@ -5,16 +5,15 @@ sidebarTitle: "LumaImageEditNode2" icon: "circle" mode: wide --- -## Overview This node edits an existing image using a text prompt, powered by the Luma UNI-1 model. It takes a source image and a description of the desired change, then generates a new edited version of the image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `source` | Source image to edit. | IMAGE | Yes | - | -| `prompt` | Description of the desired edit. Default: "" (empty string). | STRING | Yes | 1–6000 characters | +| `prompt` | Description of the desired edit. 1–6000 characters. Default: "" (empty string). | STRING | Yes | 1 to 6000 characters | | `model` | Model to use for editing. | MODEL | Yes | `"uni-1"`
`"uni-1-max"` | | `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. Default: 0. | INT | Yes | 0 to 2147483647 | @@ -25,10 +24,10 @@ This node edits an existing image using a text prompt, powered by the Luma UNI-1 ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The edited image generated by the Luma UNI-1 model. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageEditNode2/en.md) --- -**Source fingerprint (SHA-256):** `7d658d8e11b54dbad38d8d679553d55299313dacbdcc76d91079c5f92275d07e` +**Source fingerprint (SHA-256):** `4febbf1688f9b0ce2128265ddcc2e8a80c996821c41488e86594a6216993bccd` diff --git a/built-in-nodes/LumaImageModifyNode.mdx b/built-in-nodes/LumaImageModifyNode.mdx index ea192cfed..a6dd1ade9 100644 --- a/built-in-nodes/LumaImageModifyNode.mdx +++ b/built-in-nodes/LumaImageModifyNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "LumaImageModifyNode" icon: "circle" mode: wide --- + Modifies images synchronously based on a text prompt and the original image's aspect ratio. This node takes an input image and transforms it according to the provided prompt, using a configurable image weight to control how much the original image is altered. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be modified | IMAGE | Yes | - | | `prompt` | Prompt for the image generation (default: "") | STRING | Yes | - | | `image_weight` | Weight of the image; the closer to 1.0, the less the image will be modified (default: 0.1). Internally, this value is inverted (1.0 - image_weight) and clamped between 0.0 and 0.98. | FLOAT | No | 0.0-0.98 | @@ -20,10 +21,10 @@ Modifies images synchronously based on a text prompt and the original image's as ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The modified image generated by the Luma model | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageModifyNode/en.md) --- -**Source fingerprint (SHA-256):** `9798382092f179fe55972568687285bd728981ca59f1b0a5e4e2ca4bd9b7c981` +**Source fingerprint (SHA-256):** `56b13600f6fb8cd6ff80bc8c8184db059273c2ef648630ff1ef10a7ed6b04b7c` diff --git a/built-in-nodes/LumaImageNode.mdx b/built-in-nodes/LumaImageNode.mdx index ec91eb4c9..ffb0f1396 100644 --- a/built-in-nodes/LumaImageNode.mdx +++ b/built-in-nodes/LumaImageNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "LumaImageNode" icon: "circle" mode: wide --- + Generates images synchronously based on a text prompt and aspect ratio. This node creates images using text descriptions and allows you to control the image dimensions and style through various reference inputs, including character and style images. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation (default: empty string). Must be at least 3 characters long. | STRING | Yes | - | | `model` | Model selection for image generation. Different models have different costs. | COMBO | Yes | `photon-flash-1`
`photon-1`
`photon` | | `aspect_ratio` | Aspect ratio for the generated image (default: `16:9`) | COMBO | Yes | `16:9`
`1:1`
`4:3`
`3:2`
`21:9`
`9:16`
`3:4`
`2:3`
`9:21` | @@ -31,10 +32,10 @@ Generates images synchronously based on a text prompt and aspect ratio. This nod ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated image based on the input parameters. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageNode/en.md) --- -**Source fingerprint (SHA-256):** `353d99868c8c09edfab212e49f127585a6cbe1a24d6ee8fe584169adcded2961` +**Source fingerprint (SHA-256):** `cde0fc1ace28523d658b757d7f829b0d20071bed391964d2d8caa81801265b46` diff --git a/built-in-nodes/LumaImageNode2.mdx b/built-in-nodes/LumaImageNode2.mdx index 1392019bd..c6572b022 100644 --- a/built-in-nodes/LumaImageNode2.mdx +++ b/built-in-nodes/LumaImageNode2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageNode2" icon: "circle" mode: wide --- + ## Overview This node generates images from text descriptions using the Luma UNI-1 model. It takes a text prompt and optional settings like aspect ratio and style, then sends the request to the Luma API to create an image. @@ -13,7 +14,7 @@ This node generates images from text descriptions using the Luma UNI-1 model. It | Parameter | Description | Data Type | Required | Range | | --- | --- | --- | --- | --- | -| `prompt` | Text description of the desired image. | STRING | Yes | 1–6000 characters | +| `prompt` | Text description of the desired image. 1–6000 characters. | STRING | Yes | 1 to 6000 characters | | `model` | Model to use for generation. Selecting a model reveals additional settings for that model. | COMBO | Yes | `"uni-1"`
`"uni-1-max"` | | `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) | INT | Yes | 0 to 2147483647 | @@ -39,4 +40,4 @@ When `"uni-1"` or `"uni-1-max"` is selected for the `model` parameter, the follo > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageNode2/en.md) --- -**Source fingerprint (SHA-256):** `cd680f8b9e6bcf5fa415aa2d9ec3126bf8873d14bd6f4cd127491cfa242e5548` +**Source fingerprint (SHA-256):** `8157d2e4717e196056bd6821526ccb49df3f0fdf48e36c87a18742c3f5fe63bf` diff --git a/built-in-nodes/LumaImageToVideoNode.mdx b/built-in-nodes/LumaImageToVideoNode.mdx index 60f7ff5c8..4080f77fa 100644 --- a/built-in-nodes/LumaImageToVideoNode.mdx +++ b/built-in-nodes/LumaImageToVideoNode.mdx @@ -5,15 +5,16 @@ sidebarTitle: "LumaImageToVideoNode" icon: "circle" mode: wide --- + Generates videos synchronously based on a text prompt and optional starting/ending images. This node uses the Luma API to create videos, allowing you to define the video's content through a prompt and optionally specify the first and/or last frame to control the video's structure. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the video generation (default: "") | STRING | Yes | - | | `model` | Selects the video generation model from available Luma models | COMBO | Yes | `"ray-1-6"`
`"ray-2"` | -| `resolution` | Output resolution for the generated video (default: "540p"). This parameter is ignored when using the `ray-1-6` model. | COMBO | Yes | `"540p"`
`"720p"
`"1080p"`
`"4k"` | +| `resolution` | Output resolution for the generated video (default: "540p"). This parameter is ignored when using the `ray-1-6` model. | COMBO | Yes | `"540p"`
`"720p"`
`"1080p"`
`"4k"` | | `duration` | Duration of the generated video. This parameter is ignored when using the `ray-1-6` model. | COMBO | Yes | `"5s"`
`"9s"` | | `loop` | Whether the generated video should loop (default: False) | BOOLEAN | Yes | - | | `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. (default: 0) | INT | Yes | 0 to 18446744073709551615 | @@ -26,10 +27,10 @@ Generates videos synchronously based on a text prompt and optional starting/endi ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `0ef0e33f4822b522909a9732b333710197cd6e28ed6012c791f4268f8e995a84` +**Source fingerprint (SHA-256):** `2eea8934bcce20b093b88c52e430d21077705d57ab259bf620a94e46eac65e6e` diff --git a/built-in-nodes/LumaRay32ExtendVideoNode.mdx b/built-in-nodes/LumaRay32ExtendVideoNode.mdx new file mode 100644 index 000000000..17af132be --- /dev/null +++ b/built-in-nodes/LumaRay32ExtendVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32ExtendVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32ExtendVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32ExtendVideoNode" +icon: "circle" +mode: wide +--- + +This node extends a previous Luma Ray 3.2 video generation by adding new content either after it (forward extension) or before it (backward extension). Connect the generation ID output from a prior Luma Ray 3.2 node to create a seamless 5-second extension of your video. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `source_generation_id` | Generation ID of the prior Ray 3.2 video to extend. Connect the generation_id output of another Luma Ray 3.2 node. | STRING | Yes | - | +| `direction` | Forward continues after the prior clip; backward is prepended before it. When "Forward (continue after)" is selected, you can optionally enable loop mode. | COMBO | Yes | "Forward (continue after)"
"Backward (lead-in before)" | +| `loop` | Loop the extended video seamlessly (forward extend only). | BOOLEAN | No | True
False | +| `prompt` | Text prompt for the new content. | STRING | Yes | - | +| `resolution` | Output resolution for the extended video segment. | COMBO | Yes | "540p"
"720p"
"1080p" | +| `seed` | Random seed for reproducible generation results. | INT | Yes | - | + +**Note:** The `loop` parameter is only available when `direction` is set to "Forward (continue after)". When using "Backward (lead-in before)", the loop option is not available. The `prompt` must be between 1 and 6000 characters. The `source_generation_id` is required and must be connected from a prior Luma Ray 3.2 node's generation_id output. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `VIDEO` | The generated 5-second extended video segment. | VIDEO | +| `generation_id` | Unique identifier for this generation, which can be connected to another Luma Ray 3.2 Extend Video node for further extensions. | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32ExtendVideoNode/en.md) + +--- +**Source fingerprint (SHA-256):** `a67ca53d4bcb9f3fd82bc0482b579f5f7fe4bf866f8d83cb922e1082ad320057` diff --git a/built-in-nodes/LumaRay32ImageToVideoNode.mdx b/built-in-nodes/LumaRay32ImageToVideoNode.mdx new file mode 100644 index 000000000..f2c29351b --- /dev/null +++ b/built-in-nodes/LumaRay32ImageToVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32ImageToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32ImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32ImageToVideoNode" +icon: "circle" +mode: wide +--- + +Generate a video from a start and/or end frame using Luma's Ray 3.2 model. Image-anchored generations are always 5 seconds in duration. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Text prompt for the video generation. | STRING | Yes | 1 to 6000 characters | +| `resolution` | The output resolution of the generated video (default: "720p"). | COMBO | Yes | "360p"
"540p"
"720p"
"1080p" | +| `loop` | Make the video loop seamlessly. Not available when an end_frame is set. | BOOLEAN | Yes | True
False | +| `seed` | Seed value for reproducible generation. | INT | Yes | 0 to 2147483647 | +| `start_frame` | First frame of the generated video. | IMAGE | No | - | +| `end_frame` | Last frame of the generated video. | IMAGE | No | - | + +**Note:** At least one of `start_frame` or `end_frame` must be provided. If both are provided, the generated video will transition from the start frame to the end frame. The `loop` option cannot be enabled when an `end_frame` is set. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `video` | The generated video output. | VIDEO | +| `generation_id` | The unique identifier for the generation request. | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32ImageToVideoNode/en.md) + +--- +**Source fingerprint (SHA-256):** `ff479c196f10153ffa09af6acfb4e286d1934aa28a5e9b413613097a2cfb5f2a` diff --git a/built-in-nodes/LumaRay32KeyframeNode.mdx b/built-in-nodes/LumaRay32KeyframeNode.mdx new file mode 100644 index 000000000..21e73caac --- /dev/null +++ b/built-in-nodes/LumaRay32KeyframeNode.mdx @@ -0,0 +1,32 @@ +--- +title: "LumaRay32KeyframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32KeyframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32KeyframeNode" +icon: "circle" +mode: wide +--- + +This node anchors a guide image to a specific position on the Luma Ray 3.2 output video timeline. Connect this node to the "keyframes" input of the Luma Ray 3.2 Keyframes to Video node, and chain several keyframes together by connecting the optional "keyframes" input. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `image` | Guide image to place at the chosen moment of the output video. | IMAGE | Yes | - | +| `position` | How to place this image on the output video's timeline. | COMBO | Yes | "Fraction of duration (0.0-1.0)"
"Absolute time (seconds)" | +| `keyframes` | Optional earlier keyframes to chain with this one. | LUMA_RAY32_KEYFRAME | No | - | + +When "Fraction of duration (0.0-1.0)" is selected for the `position` parameter, you can specify a `fraction` value (default: 0.0, range: 0.0 to 1.0, step: 0.01) that determines where in the output video this image applies (0.0 = start, 1.0 = end). + +When "Absolute time (seconds)" is selected for the `position` parameter, you can specify a `seconds` value (default: 0.0, range: 0.0 to 10.0, step: 0.1) that determines the time in seconds from the start of the output video where this image applies. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `keyframes` | A keyframe chain that includes the new keyframe combined with any optional earlier keyframes. | LUMA_RAY32_KEYFRAME | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32KeyframeNode/en.md) + +--- +**Source fingerprint (SHA-256):** `b49d879888e6e83d6937068e799ea583ed5c90284e829ac496821eea330fe9c7` diff --git a/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx b/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx new file mode 100644 index 000000000..a19b43974 --- /dev/null +++ b/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32KeyframesToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32KeyframesToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32KeyframesToVideoNode" +icon: "circle" +mode: wide +--- + +This node generates a video that interpolates through a sequence of guide images, each anchored to a specific position on the timeline, using Luma Ray 3.2. Build the keyframe sequence using Luma Ray 3.2 Keyframe nodes, connecting at least 2 keyframes to define the animation. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Text prompt for the video generation. | STRING | Yes | 1 to 6000 characters | +| `resolution` | The output resolution of the generated video (default: "720p"). | STRING | Yes | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `duration` | The duration of the generated video (default: "5s"). | STRING | Yes | `"5s"`
`"10s"` | +| `seed` | Seed for random number generation to control reproducibility. | INT | Yes | 0 to 4294967295 | +| `keyframes` | Keyframe sequence from Luma Ray 3.2 Keyframe nodes (at least 2). | LUMA_RAY32_KEYFRAME | Yes | 2 to 64 keyframes | + +**Note:** The keyframe sequence must contain at least 2 keyframes and at most 64 keyframes. Each keyframe must have a distinct position on the timeline. Keyframe positions are resolved to output frame indices based on the selected duration (120 frames for 5s, 240 frames for 10s). Keyframe positions in seconds mode must not exceed the total video duration. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `video` | The generated video output. | VIDEO | +| `generation_id` | The unique identifier for the generation request. | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32KeyframesToVideoNode/en.md) + +--- +**Source fingerprint (SHA-256):** `28099e5990942860a20e23cfd5c71a36b23a6264b44097ca617f8bdd06e7857a` diff --git a/built-in-nodes/LumaRay32TextToVideoNode.mdx b/built-in-nodes/LumaRay32TextToVideoNode.mdx new file mode 100644 index 000000000..d6f5449ed --- /dev/null +++ b/built-in-nodes/LumaRay32TextToVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32TextToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32TextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32TextToVideoNode" +icon: "circle" +mode: wide +--- + +This node generates a video from a text prompt using Luma's Ray 3.2 model. It sends your prompt and video settings to the Luma API and returns the generated video along with a generation ID. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Text prompt for the video generation. | STRING | Yes | 1-6000 characters | +| `aspect_ratio` | The aspect ratio of the generated video. | STRING | Yes | `"16:9"`
`"9:16"`
`"1:1"`
`"4:3"`
`"3:4"`
`"21:9"` | +| `resolution` | The output resolution of the video (default: "720p"). | STRING | Yes | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `duration` | The duration of the generated video. | STRING | Yes | `"5s"`
`"10s"` | +| `loop` | Make the video loop seamlessly. Only available with 5s duration. | BOOLEAN | No | True/False (default: False) | +| `seed` | Seed for reproducible generation. | INT | No | 0 to 2147483647 | + +**Note:** The `loop` parameter can only be enabled when `duration` is set to "5s". If you select "10s" duration and enable looping, the node will return an error. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `VIDEO` | The generated video file. | VIDEO | +| `generation_id` | The unique identifier for the video generation request. | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32TextToVideoNode/en.md) + +--- +**Source fingerprint (SHA-256):** `04358a872530e5a2622bf0f148a694f2c707ce8535586d8f860bdf9911e1fa6a` diff --git a/built-in-nodes/LumaRay32VideoEditNode.mdx b/built-in-nodes/LumaRay32VideoEditNode.mdx new file mode 100644 index 000000000..450527ab7 --- /dev/null +++ b/built-in-nodes/LumaRay32VideoEditNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32VideoEditNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32VideoEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32VideoEditNode" +icon: "circle" +mode: wide +--- + +This node re-renders an existing video under a new prompt using Luma Ray 3.2, allowing you to restyle, relight, add, or remove elements while keeping the original motion. The source video can be up to 18 seconds, and the edited video retains the source's original length. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `video` | Source video to edit. Up to 18 seconds. | VIDEO | Yes | - | +| `prompt` | Describes the desired edit. | STRING | Yes | - | +| `resolution` | The output resolution for the edited video. | COMBO | Yes | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `strength` | How strongly to preserve vs. reimagine the source. "auto" lets Ray 3.2 choose; adhere_* preserves the most, flex_* is balanced, reimagine_* changes the most. (default: "auto") | COMBO | Yes | `"auto"`
`"adhere_1"`
`"adhere_2"`
`"adhere_3"`
`"flex_1"`
`"flex_2"`
`"flex_3"`
`"reimagine_1"`
`"reimagine_2"`
`"reimagine_3"` | +| `seed` | Seed for reproducibility. | INT | Yes | - | + +**Note:** The `prompt` must be between 1 and 6000 characters. The source video must not exceed 18 seconds in duration. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `VIDEO` | The edited video output. | VIDEO | +| `generation_id` | The unique identifier for the generation request. | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32VideoEditNode/en.md) + +--- +**Source fingerprint (SHA-256):** `936d9d7da3fdee9b0b468781fd470751db01f772f3c5c20582da7fb1ff85e6e6` diff --git a/built-in-nodes/LumaRay32VideoReframeNode.mdx b/built-in-nodes/LumaRay32VideoReframeNode.mdx new file mode 100644 index 000000000..24e9daa47 --- /dev/null +++ b/built-in-nodes/LumaRay32VideoReframeNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32VideoReframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32VideoReframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32VideoReframeNode" +icon: "circle" +mode: wide +--- + +This node changes the aspect ratio of an existing video using Luma Ray 3.2, which fills the newly exposed canvas areas with generated content. The source video can be up to 30 seconds long, and billing is per second of output. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `video` | Source video to reframe. Up to 30 seconds. | VIDEO | Yes | - | +| `prompt` | Describes how the newly exposed canvas areas should be filled. | STRING | Yes | Min length: 1 character
Max length: 6000 characters | +| `aspect_ratio` | The target aspect ratio for the reframed video (default: "16:9"). | STRING | Yes | "16:9"
"9:16"
"1:1"
"4:3"
"3:4"
"21:9" | +| `resolution` | The output resolution of the reframed video (default: "720p"). | STRING | Yes | "360p"
"540p"
"720p"
"1080p" | +| `seed` | Seed for reproducible generation. | INT | Yes | - | + +**Note:** The `1080p` resolution is not available for vertical aspect ratios (`9:16` and `3:4`) when reframing. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `video` | The reframed video with the new aspect ratio and filled canvas areas. | VIDEO | +| `generation_id` | The unique identifier for the generation request. | STRING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32VideoReframeNode/en.md) + +--- +**Source fingerprint (SHA-256):** `d35ff5b63a850e4e44a40857188918ab5cde00b9159e3720a189a81807cfa7cb` diff --git a/built-in-nodes/LumaReferenceNode.mdx b/built-in-nodes/LumaReferenceNode.mdx index b2da2cfd4..ff73c5646 100644 --- a/built-in-nodes/LumaReferenceNode.mdx +++ b/built-in-nodes/LumaReferenceNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "LumaReferenceNode" icon: "circle" mode: wide --- + This node holds an image and weight value for use with the Luma Generate Image node. It creates a reference chain that can be passed to other Luma nodes to influence image generation. The node can either start a new reference chain or add to an existing one. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | Image to use as reference. | IMAGE | Yes | - | | `weight` | Weight of image reference (default: 1.0). | FLOAT | Yes | 0.0 - 1.0 | | `luma_ref` | Optional existing Luma reference chain to add to. | LUMA_REF | No | - | @@ -18,10 +19,10 @@ This node holds an image and weight value for use with the Luma Generate Image n ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `luma_ref` | The Luma reference chain containing the image and weight. | LUMA_REF | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaReferenceNode/en.md) --- -**Source fingerprint (SHA-256):** `1cca0ddc397a72c03bb7d6d24135c09795934f566b23368298a89b90a14dc8cc` +**Source fingerprint (SHA-256):** `f7e7789f2f19cac41cb9e55d21f10fef3012b10dcdbd59eb79f97fe5c2a944b7` diff --git a/built-in-nodes/LumaVideoNode.mdx b/built-in-nodes/LumaVideoNode.mdx index 3aa70f693..aa1802e06 100644 --- a/built-in-nodes/LumaVideoNode.mdx +++ b/built-in-nodes/LumaVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "LumaVideoNode" icon: "circle" mode: wide --- + Generates videos synchronously based on a text prompt and output settings. This node creates video content using text descriptions and various generation parameters, producing the final video output once the generation process is complete. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the video generation (default: empty string). Must be at least 3 characters long. | STRING | Yes | - | | `model` | The video generation model to use. | COMBO | Yes | `"ray_1_6"`
`"ray_2"` | | `aspect_ratio` | The aspect ratio for the generated video (default: "16:9"). | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"`
`"4:3"`
`"3:4"`
`"21:9"`
`"9:21"` | @@ -25,10 +26,10 @@ Generates videos synchronously based on a text prompt and output settings. This ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `3e7fb20aebee034e2055d87e7c1c24a995aece152b0271de48c81ce82cf2911a` +**Source fingerprint (SHA-256):** `3ce9db0780dbe7a752a6b1c35a02b9511f532e81a28d5d83b2bf3be9e35e2e6b` diff --git a/built-in-nodes/MagnificImageRelightNode.mdx b/built-in-nodes/MagnificImageRelightNode.mdx index 1f00b7ef3..382e36b6d 100644 --- a/built-in-nodes/MagnificImageRelightNode.mdx +++ b/built-in-nodes/MagnificImageRelightNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageRelightNode" icon: "circle" mode: wide --- + The Magnific Image Relight node adjusts the lighting of an input image. It can apply stylistic lighting based on a text prompt or transfer the lighting characteristics from an optional reference image. The node offers various controls for fine-tuning the brightness, contrast, and overall mood of the final output. ## Inputs @@ -42,4 +43,4 @@ The Magnific Image Relight node adjusts the lighting of an input image. It can a > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageRelightNode/en.md) --- -**Source fingerprint (SHA-256):** `52d6a2c2ab8b03397ed78222c4da936f96f816cde01e2c9cccc3d4915042330f` +**Source fingerprint (SHA-256):** `45fe68b21e1da7c367800915c803ad4cf1c5b80e9a2e91d80cae51b8a9531144` diff --git a/built-in-nodes/MagnificImageSkinEnhancerNode.mdx b/built-in-nodes/MagnificImageSkinEnhancerNode.mdx index 48599da26..8984048cc 100644 --- a/built-in-nodes/MagnificImageSkinEnhancerNode.mdx +++ b/built-in-nodes/MagnificImageSkinEnhancerNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "MagnificImageSkinEnhancerNode" icon: "circle" mode: wide --- + The Magnific Image Skin Enhancer node applies specialized AI processing to portrait images to improve skin appearance. It offers three distinct modes for different enhancement goals: creative for artistic effects, faithful for preserving the original look, and flexible for targeted improvements like lighting or realism. The node uploads the image to an external API for processing and returns the enhanced result. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The portrait image to enhance. | IMAGE | Yes | - | | `sharpen` | Sharpening intensity level (default: 0). | INT | No | 0 to 100 | | `smart_grain` | Smart grain intensity level (default: 2). | INT | No | 0 to 100 | @@ -29,10 +30,10 @@ The Magnific Image Skin Enhancer node applies specialized AI processing to portr ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The enhanced portrait image. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageSkinEnhancerNode/en.md) --- -**Source fingerprint (SHA-256):** `1c87ba8a71ccac4fd17c35ad5bf2ee9b27c8bcb45a9d76cd077d6c0614f1ecc1` +**Source fingerprint (SHA-256):** `2430cc0fb1d2042a8eda78f7f5a5794fa6b4e555d3957616ae6891374b556a76` diff --git a/built-in-nodes/MagnificImageStyleTransferNode.mdx b/built-in-nodes/MagnificImageStyleTransferNode.mdx index 3dc13f477..b4cdde27f 100644 --- a/built-in-nodes/MagnificImageStyleTransferNode.mdx +++ b/built-in-nodes/MagnificImageStyleTransferNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "MagnificImageStyleTransferNode" icon: "circle" mode: wide --- + This node applies the visual style from a reference image to your input image. It uses an external AI service to process the images, allowing you to control the strength of the style transfer and the preservation of the original image's structure. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The image to apply style transfer to. | IMAGE | Yes | - | | `reference_image` | The reference image to extract style from. | IMAGE | Yes | - | | `prompt` | An optional text prompt to guide the style transfer. | STRING | No | - | @@ -33,10 +34,10 @@ This node applies the visual style from a reference image to your input image. I ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The resulting image after style transfer has been applied. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageStyleTransferNode/en.md) --- -**Source fingerprint (SHA-256):** `2a008de2ad1345360c8313da90721c1118b1d7447647a0a9a4676ff71461e142` +**Source fingerprint (SHA-256):** `edffec024ebe7cbf7c42008e14c1b99d6fafcf5b9da62b0b560d194a585dc9ad` diff --git a/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx b/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx index 598e824ee..efd896a52 100644 --- a/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx +++ b/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "MagnificImageUpscalerCreativeNode" icon: "circle" mode: wide --- + This node uses the Magnific AI service to upscale and creatively enhance an image. It allows you to guide the enhancement with a text prompt, choose a specific style to optimize for, and control various aspects of the creative process like detail, resemblance to the original, and stylization strength. The node outputs an upscaled image at your chosen factor (2x, 4x, 8x, or 16x), with a maximum output size of 25.3 megapixels. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be upscaled and enhanced. | IMAGE | Yes | - | | `prompt` | A text description to guide the creative enhancement of the image. This is optional (default: empty). | STRING | No | - | | `scale_factor` | The factor by which to upscale the image's dimensions. | COMBO | Yes | `"2x"`
`"4x"`
`"8x"`
`"16x"` | @@ -32,10 +33,10 @@ This node uses the Magnific AI service to upscale and creatively enhance an imag ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The creatively enhanced and upscaled output image. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageUpscalerCreativeNode/en.md) --- -**Source fingerprint (SHA-256):** `3eb5ce7887ba67a3a49d06820851df90d1c1c73f28ded62288054154bcb2d7e8` +**Source fingerprint (SHA-256):** `88362dd9630f0f9420bd7caf3f82ace73d5d2b979bd71939298b84ceff288dc8` diff --git a/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx b/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx index c54b75eaf..6c93f2b90 100644 --- a/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx +++ b/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx @@ -5,29 +5,30 @@ sidebarTitle: "MagnificImageUpscalerPreciseV2Node" icon: "circle" mode: wide --- + The Magnific Image Upscale (Precise V2) node performs high-fidelity image upscaling with precise control over sharpness, grain, and detail enhancement. It processes images through an external API, supporting up to a maximum output resolution of 10060×10060 pixels. The node offers different processing styles and can automatically downscale the input if the requested output would exceed the maximum allowed size. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be upscaled. Exactly one image is required. Minimum dimensions are 160x160 pixels. The aspect ratio must be between 1:3 and 3:1. | IMAGE | Yes | - | | `scale_factor` | The desired upscaling multiplier. | STRING | Yes | `"2x"`
`"4x"`
`"8x"`
`"16x"` | -| `flavor` | The processing style. "sublime" is for general use, "photo" is optimized for photographs, and "photo_denoiser" is for noisy photos. | STRING | Yes | `"sublime"`
`"photo"`
`"photo_denoiser"` | -| `sharpen` | Controls the intensity of image sharpening to increase edge definition and clarity. Higher values produce a sharper result. Default: 7. | INT | No | 0 to 100 | -| `smart_grain` | Adds intelligent grain or texture enhancement to prevent the upscaled image from looking too smooth or artificial. Default: 7. | INT | No | 0 to 100 | -| `ultra_detail` | Controls the amount of fine detail, textures, and micro-details added during the upscaling process. Default: 30. | INT | No | 0 to 100 | -| `auto_downscale` | When enabled, the node will automatically downscale the input image if the calculated output dimensions would exceed the maximum allowed resolution of 10060x10060 pixels. This helps prevent errors but may affect quality. Default: False. | BOOLEAN | No | - | +| `flavor` | Processing style: sublime for general use, photo for photographs, photo_denoiser for noisy photos. | STRING | Yes | `"sublime"`
`"photo"`
`"photo_denoiser"` | +| `sharpen` | Image sharpness intensity. Higher values increase edge definition and clarity. Default: 7. | INT | No | 0 to 100 | +| `smart_grain` | Intelligent grain/texture enhancement to prevent the image from looking too smooth or artificial. Default: 7. | INT | No | 0 to 100 | +| `ultra_detail` | Controls fine detail, textures, and micro-details added during upscaling. Default: 30. | INT | No | 0 to 100 | +| `auto_downscale` | Automatically downscale input image if output would exceed maximum resolution. Default: False. | BOOLEAN | No | - | -**Note:** If `auto_downscale` is disabled and the requested output size (input dimensions × `scale_factor`) exceeds 10060x10060 pixels, the node will raise an error. +**Note:** If `auto_downscale` is disabled and the requested output size (input dimensions × `scale_factor`) exceeds 10060x10060 pixels, the node will raise an error. When `auto_downscale` is enabled, the node will attempt to find an optimal scale factor that keeps quality loss minimal. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The resulting upscaled image. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageUpscalerPreciseV2Node/en.md) --- -**Source fingerprint (SHA-256):** `83559e99f86398b894c659996bdde48633a49f857a4769127fdf7ab6e80d6b0d` +**Source fingerprint (SHA-256):** `b4de8780c46d113fd043930daa6d4b91df3dca493afef486a0ecf2ee9e0ae708` diff --git a/built-in-nodes/Mahiro.mdx b/built-in-nodes/Mahiro.mdx index 298fdffcd..619580b9e 100644 --- a/built-in-nodes/Mahiro.mdx +++ b/built-in-nodes/Mahiro.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Mahiro" icon: "circle" mode: wide --- + The Mahiro node modifies the guidance function to focus more on the direction of the positive prompt rather than the difference between positive and negative prompts. It creates a patched model that applies a custom guidance scaling approach using cosine similarity between normalized conditional and unconditional denoised outputs. This experimental node helps steer the generation more strongly toward the positive prompt's intended direction. ## Inputs diff --git a/built-in-nodes/MakeTrainingDataset.mdx b/built-in-nodes/MakeTrainingDataset.mdx index 6e15b4d46..44e4bbda3 100644 --- a/built-in-nodes/MakeTrainingDataset.mdx +++ b/built-in-nodes/MakeTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MakeTrainingDataset" icon: "circle" mode: wide --- + This node prepares data for training by encoding images and text. It takes a list of images and a corresponding list of text captions, then uses a VAE model to convert the images into latent representations and a CLIP model to convert the text into conditioning data. The resulting paired latents and conditioning are output as lists, ready for use in training workflows. ## Inputs diff --git a/built-in-nodes/ManualSigmas.mdx b/built-in-nodes/ManualSigmas.mdx index de108bcdd..d373c4f3e 100644 --- a/built-in-nodes/ManualSigmas.mdx +++ b/built-in-nodes/ManualSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ManualSigmas" icon: "circle" mode: wide --- + The ManualSigmas node allows you to manually define a custom sequence of noise levels (sigmas) for the sampling process. You input a list of numbers as a string, and the node converts them into a tensor that can be used by other sampling nodes. This is useful for testing or creating specific noise schedules. ## Inputs diff --git a/built-in-nodes/MarkdownNote.mdx b/built-in-nodes/MarkdownNote.mdx index 6b916b113..b7c727369 100644 --- a/built-in-nodes/MarkdownNote.mdx +++ b/built-in-nodes/MarkdownNote.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MarkdownNote" icon: "circle" mode: wide --- + Node to add annotations to a workflow. It supports text formatting using Markdown syntax. ## Inputs diff --git a/built-in-nodes/MaskComposite.mdx b/built-in-nodes/MaskComposite.mdx index 5f93742f7..f1f988e5e 100644 --- a/built-in-nodes/MaskComposite.mdx +++ b/built-in-nodes/MaskComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskComposite" icon: "circle" mode: wide --- + This node specializes in combining two mask inputs through a variety of operations such as addition, subtraction, and logical operations, to produce a new, modified mask. It abstractly handles the manipulation of mask data to achieve complex masking effects, serving as a crucial component in mask-based image editing and processing workflows. ## Inputs diff --git a/built-in-nodes/MaskPreview.mdx b/built-in-nodes/MaskPreview.mdx index e9a6a8906..5859798c0 100644 --- a/built-in-nodes/MaskPreview.mdx +++ b/built-in-nodes/MaskPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskPreview" icon: "circle" mode: wide --- + The MaskPreview node saves mask data as a preview image to your ComfyUI output directory, allowing you to visually inspect mask data during workflow execution. It converts the input mask into a format suitable for image display and saves it with a configurable filename prefix. ## Inputs diff --git a/built-in-nodes/MaskToImage.mdx b/built-in-nodes/MaskToImage.mdx index eb65fe36a..79dbd1c7a 100644 --- a/built-in-nodes/MaskToImage.mdx +++ b/built-in-nodes/MaskToImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskToImage" icon: "circle" mode: wide --- + The `MaskToImage` node is designed to convert a mask into an image format. This transformation allows for the visualization and further processing of masks as images, facilitating a bridge between mask-based operations and image-based applications. ## Inputs diff --git a/built-in-nodes/MediaPipeFaceLandmarker.mdx b/built-in-nodes/MediaPipeFaceLandmarker.mdx index 70d4980ad..bc827573d 100644 --- a/built-in-nodes/MediaPipeFaceLandmarker.mdx +++ b/built-in-nodes/MediaPipeFaceLandmarker.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceLandmarker" icon: "circle" mode: wide --- + ## Overview Detects faces in an image and identifies 468 facial landmarks (key points) on each face using MediaPipe's BlazeFace and FaceMesh models. It also calculates ARKit-52 blendshape coefficients for facial expression analysis. The node can process multiple images in a batch and outputs both the landmark data and bounding boxes for each detected face. diff --git a/built-in-nodes/MediaPipeFaceMask.mdx b/built-in-nodes/MediaPipeFaceMask.mdx index 37d01e968..1a55d2adb 100644 --- a/built-in-nodes/MediaPipeFaceMask.mdx +++ b/built-in-nodes/MediaPipeFaceMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceMask" icon: "circle" mode: wide --- + ## Overview This node creates a binary mask (a black and white image) based on face landmarks detected by MediaPipe. It draws filled polygon shapes for each detected face region, producing one mask per frame in a batch. When multiple faces are detected in the same frame, their masks are combined into a single mask. diff --git a/built-in-nodes/MediaPipeFaceMeshVisualize.mdx b/built-in-nodes/MediaPipeFaceMeshVisualize.mdx index 03d3c6cfc..f9c998a93 100644 --- a/built-in-nodes/MediaPipeFaceMeshVisualize.mdx +++ b/built-in-nodes/MediaPipeFaceMeshVisualize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceMeshVisualize" icon: "circle" mode: wide --- + ## Overview Draws face landmark points and connection lines (a face mesh) on top of an input image. This node uses the landmark data produced by a face detection node to visualize the detected facial features, such as the eyes, nose, mouth, and face outline. diff --git a/built-in-nodes/MergeImageLists.mdx b/built-in-nodes/MergeImageLists.mdx index e6718b52c..7c9025eca 100644 --- a/built-in-nodes/MergeImageLists.mdx +++ b/built-in-nodes/MergeImageLists.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MergeImageLists" icon: "circle" mode: wide --- + The Merge Image Lists node combines multiple separate lists of images into a single, continuous list. It works by taking all the images from each connected input and appending them together in the order they are received. This is useful for organizing or batching images from different sources for further processing. **Note:** This node is deprecated and superseded by the Create List node. diff --git a/built-in-nodes/MergeSplat.mdx b/built-in-nodes/MergeSplat.mdx index b02e0cd01..00b42d2f6 100644 --- a/built-in-nodes/MergeSplat.mdx +++ b/built-in-nodes/MergeSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MergeSplat" icon: "circle" mode: wide --- -# Merge Splats The Merge Splats node combines multiple gaussian splat models into a single splat by concatenating their data. This is useful for merging several decodes of the same latent generated with different seeds, which can densify the surface and improve quality when creating 3D meshes. diff --git a/built-in-nodes/MergeTextLists.mdx b/built-in-nodes/MergeTextLists.mdx index bf09c0f6c..f9289d635 100644 --- a/built-in-nodes/MergeTextLists.mdx +++ b/built-in-nodes/MergeTextLists.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MergeTextLists" icon: "circle" mode: wide --- + This node merges multiple text lists into a single, combined list. It is designed to receive text inputs as lists and concatenates them together. The node logs the total number of texts in the merged list. ## Inputs diff --git a/built-in-nodes/MeshyAnimateModelNode.mdx b/built-in-nodes/MeshyAnimateModelNode.mdx index 7859b7ae8..5ea648a9f 100644 --- a/built-in-nodes/MeshyAnimateModelNode.mdx +++ b/built-in-nodes/MeshyAnimateModelNode.mdx @@ -5,19 +5,20 @@ sidebarTitle: "MeshyAnimateModelNode" icon: "circle" mode: wide --- + This node applies a specific animation to a 3D character model that has already been rigged using the Meshy service. It takes a task ID from a previous rigging operation and an action ID to select the desired animation from the library. The node then processes the request and returns the animated model in both GLB and FBX file formats. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `rig_task_id` | The unique task ID from a previously completed Meshy character rigging operation. | STRING | Yes | N/A | | `action_id` | The ID number of the animation action to apply. Visit https://docs.meshy.ai/en/api/animation-library for a list of available values. (default: 0) | INT | Yes | 0 to 696 | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | A string identifier for the animated model. This output is provided for backward compatibility only. | STRING | | `GLB` | The animated 3D model file in GLB format. | FILE3DGLB | | `FBX` | The animated 3D model file in FBX format. | FILE3DFBX | @@ -25,4 +26,4 @@ This node applies a specific animation to a 3D character model that has already > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyAnimateModelNode/en.md) --- -**Source fingerprint (SHA-256):** `0af4e96d031025fdb5e11d6dd35e408b61dcdd4ca64f88464a6510426485dac2` +**Source fingerprint (SHA-256):** `e773145f8f08e80f3cef8ce70becc3b593aea8e02a888a0005353f1bc8e3b909` diff --git a/built-in-nodes/MeshyImageToModelNode.mdx b/built-in-nodes/MeshyImageToModelNode.mdx index 2092e1586..155ab6de6 100644 --- a/built-in-nodes/MeshyImageToModelNode.mdx +++ b/built-in-nodes/MeshyImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyImageToModelNode" icon: "circle" mode: wide --- + The Meshy: Image to Model node uses the Meshy API to generate a 3D model from a single input image. It uploads your image, submits a processing task, and returns the generated 3D model files (GLB and FBX) along with the task ID for reference. ## Inputs @@ -42,4 +43,4 @@ The Meshy: Image to Model node uses the Meshy API to generate a 3D model from a > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyImageToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `87825d9d78ccfb1efdf07da0e9c8cfca39a8446dd99d346c732e4d1470194205` +**Source fingerprint (SHA-256):** `9f7abcb0db3c78715e4ba7370efe294caf186590f7ab62da8568778848fc838c` diff --git a/built-in-nodes/MeshyMultiImageToModelNode.mdx b/built-in-nodes/MeshyMultiImageToModelNode.mdx index 52b4fed43..da5daeb08 100644 --- a/built-in-nodes/MeshyMultiImageToModelNode.mdx +++ b/built-in-nodes/MeshyMultiImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyMultiImageToModelNode" icon: "circle" mode: wide --- + This node uses the Meshy API to generate a 3D model from multiple input images. It uploads the provided images, submits a processing task, and returns the resulting 3D model files (GLB and FBX) along with the task ID for reference. ## Inputs @@ -14,7 +15,7 @@ This node uses the Meshy API to generate a 3D model from multiple input images. | `model` | Specifies the AI model version to use. | COMBO | Yes | `"latest"` | | `images` | A set of images used to generate the 3D model. You must provide between 2 and 4 images. | IMAGE | Yes | 2 to 4 images | | `should_remesh` | Determines if the generated mesh should be processed. When set to `"false"`, the node returns an unprocessed triangular mesh. | COMBO | Yes | `"true"`
`"false"` | -| `topology` | The target polygon type for the remeshed output. This parameter is only available and required when `should_remesh` is set to `"true"`. | COMBO | No | `"triangle"`
`"quad"` | +| `topology` | The target polygon type for the remeshed output. This parameter is only available when `should_remesh` is set to `"true"`. | COMBO | No | `"triangle"`
`"quad"` | | `target_polycount` | The target number of polygons for the remeshed model (default: 300000). This parameter is only available when `should_remesh` is set to `"true"`. | INT | No | 100 to 300000 | | `symmetry_mode` | Controls whether symmetry is applied to the generated model. | COMBO | Yes | `"auto"`
`"on"`
`"off"` | | `should_texture` | Determines whether textures are generated. Setting it to `"false"` skips the texture phase and returns a mesh without textures. | COMBO | Yes | `"true"`
`"false"` | @@ -43,4 +44,4 @@ This node uses the Meshy API to generate a 3D model from multiple input images. > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyMultiImageToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `7118368e2d9c1a7df9866d19a033c6e2efd632381624a9ee537552502185d444` +**Source fingerprint (SHA-256):** `c2282cad611bbbc8c0a618df6a68fcd9f6e3c29c6d08b2c96a117c29765d8a7a` diff --git a/built-in-nodes/MeshyRefineNode.mdx b/built-in-nodes/MeshyRefineNode.mdx index 75e71ec42..4cc1f5220 100644 --- a/built-in-nodes/MeshyRefineNode.mdx +++ b/built-in-nodes/MeshyRefineNode.mdx @@ -5,15 +5,16 @@ sidebarTitle: "MeshyRefineNode" icon: "circle" mode: wide --- + The Meshy: Refine Draft Model node takes a previously generated 3D draft model and improves its quality, optionally adding textures. It submits a refinement task to the Meshy API and returns the final 3D model files once processing is complete. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Specifies the AI model to use for refinement. Currently, only the "latest" model is available. | COMBO | Yes | `"latest"` | | `meshy_task_id` | The unique task ID of the draft model you want to refine. | MESHY_TASK_ID | Yes | - | -| `enable_pbr` | Generate PBR Maps (metallic, roughness, normal) in addition to the base color. Note: this should be set to false when using Sculpture style, as Sculpture style generates its own set of PBR maps. (default: `False`) | BOOLEAN | No | - | +| `enable_pbr` | Generate PBR Maps (metallic, roughness, normal) in addition to the base color. Note: this should be set to false when using Sculpture style, as Sculpture style generates its own set of PBR maps. (default: False) | BOOLEAN | No | - | | `texture_prompt` | Provide a text prompt to guide the texturing process. Maximum 600 characters. Cannot be used at the same time as `texture_image`. (default: empty string) | STRING | No | - | | `texture_image` | Only one of `texture_image` or `texture_prompt` may be used at the same time. | IMAGE | No | - | @@ -22,7 +23,7 @@ The Meshy: Refine Draft Model node takes a previously generated 3D draft model a ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The filename of the generated GLB model. (For backward compatibility only) | STRING | | `meshy_task_id` | The unique task ID for the submitted refinement job. | MESHY_TASK_ID | | `GLB` | The final refined 3D model in GLB format. | FILE3DGLB | @@ -31,4 +32,4 @@ The Meshy: Refine Draft Model node takes a previously generated 3D draft model a > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRefineNode/en.md) --- -**Source fingerprint (SHA-256):** `b1cfdeb12d1f79c4c18f96b4f8a92de227210e369b22356fe7232e025956696e` +**Source fingerprint (SHA-256):** `dc4e8c43e16132b3928d21c94c6648cdc8df46e671ecd5686ac811cde69123aa` diff --git a/built-in-nodes/MeshyRigModelNode.mdx b/built-in-nodes/MeshyRigModelNode.mdx index 0ff5188ac..eebe69644 100644 --- a/built-in-nodes/MeshyRigModelNode.mdx +++ b/built-in-nodes/MeshyRigModelNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "MeshyRigModelNode" icon: "circle" mode: wide --- + The Meshy: Rig Model node takes a 3D model from a previous Meshy task and automatically creates a skeleton for it, producing a rigged character that can be posed and animated. The node outputs the rigged model in both GLB and FBX file formats. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `meshy_task_id` | The unique task ID from a previous Meshy operation (e.g., text-to-3D or image-to-3D) that generated the model to be rigged. | STRING | Yes | N/A | | `height_meters` | The approximate height of the character model in meters. This aids in scaling and rigging accuracy (default: 1.7). | FLOAT | Yes | 0.1 to 15.0 | | `texture_image` | The model's UV-unwrapped base color texture image. | IMAGE | No | N/A | @@ -20,7 +21,7 @@ The Meshy: Rig Model node takes a 3D model from a previous Meshy task and automa ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | A legacy output for backward compatibility, containing the filename of the GLB model. | STRING | | `rig_task_id` | The unique task ID for this rigging operation, which can be used to reference the result. | STRING | | `GLB` | The rigged 3D character model saved in the GLB file format. | FILE3DGLB | @@ -29,4 +30,4 @@ The Meshy: Rig Model node takes a 3D model from a previous Meshy task and automa > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRigModelNode/en.md) --- -**Source fingerprint (SHA-256):** `de47454600293b647fd6e244ad7e53de66169bb0d2b65df517a85bc6bc3ee6e0` +**Source fingerprint (SHA-256):** `c7817278d4269d6a507937691529e063cb470e5123d33a726307bff7e1813344` diff --git a/built-in-nodes/MeshyTextToModelNode.mdx b/built-in-nodes/MeshyTextToModelNode.mdx index 3450d0157..5c003da12 100644 --- a/built-in-nodes/MeshyTextToModelNode.mdx +++ b/built-in-nodes/MeshyTextToModelNode.mdx @@ -5,28 +5,29 @@ sidebarTitle: "MeshyTextToModelNode" icon: "circle" mode: wide --- + The Meshy: Text to Model node uses the Meshy API to generate a 3D model from a text description. It sends a request to the API with your prompt and settings, then waits for the generation to complete and downloads the resulting model files. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Specifies the AI model version to use. Currently, only the "latest" version is available. | COMBO | Yes | `"latest"` | | `prompt` | The text description of the 3D model you want to generate. Must be between 1 and 600 characters long. | STRING | Yes | - | | `style` | The artistic style for the generated 3D model. | COMBO | Yes | `"realistic"`
`"sculpture"` | | `should_remesh` | Controls whether the generated mesh is processed. When set to "false", the node returns an unprocessed triangular mesh. Selecting "true" reveals additional parameters for topology and polycount. | DYNAMIC COMBO | Yes | `"true"`
`"false"` | -| `topology` | The target polygon type for the remeshed model. This parameter is only available and required when `should_remesh` is set to "true". | COMBO | No* | `"triangle"`
`"quad"` | -| `target_polycount` | The target number of polygons for the remeshed model. Default is 300000. This parameter is only available and required when `should_remesh` is set to "true". | INT | No* | 100 - 300000 | +| `topology` | The target polygon type for the remeshed model. This parameter is only available when `should_remesh` is set to "true". | COMBO | No* | `"triangle"`
`"quad"` | +| `target_polycount` | The target number of polygons for the remeshed model. Default is 300000. This parameter is only available when `should_remesh` is set to "true". | INT | No* | 100 - 300000 | | `symmetry_mode` | Controls symmetry in the generated model. | COMBO | Yes | `"auto"`
`"on"`
`"off"` | | `pose_mode` | Specifies the pose mode for the generated model. An empty string means no specific pose is requested. | COMBO | Yes | `""`
`"A-pose"`
`"T-pose"` | | `seed` | A seed value for generation. Setting this controls whether the node should re-run, but results are non-deterministic regardless of the seed value. Default is 0. | INT | Yes | 0 - 2147483647 | -*Note: The `topology` and `target_polycount` parameters are conditionally required. They only appear and must be set when the `should_remesh` parameter is set to "true". +*Note: The `topology` and `target_polycount` parameters are conditionally available. They only appear when the `should_remesh` parameter is set to "true". ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The filename of the generated GLB model. This output is provided for backward compatibility. | STRING | | `meshy_task_id` | The unique identifier for the Meshy API task. | MESHY_TASK_ID | | `GLB` | The generated 3D model file in GLB format. | FILE3DGLB | @@ -35,4 +36,4 @@ The Meshy: Text to Model node uses the Meshy API to generate a 3D model from a t > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `4b02709a29d3df85e0ab1741b46d3ac74b0fe04135afa435f882b5a02114cc97` +**Source fingerprint (SHA-256):** `1860b2d760aa81d611d4f44114591b4d98ccb85075bd1e06beabf462fb58bd53` diff --git a/built-in-nodes/MeshyTextureNode.mdx b/built-in-nodes/MeshyTextureNode.mdx index e5a830a2a..704868d06 100644 --- a/built-in-nodes/MeshyTextureNode.mdx +++ b/built-in-nodes/MeshyTextureNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyTextureNode" icon: "circle" mode: wide --- + The Meshy: Texture Node applies AI-generated textures to a 3D model. It takes a task ID from a previous Meshy 3D generation or conversion node and uses either a text description or a reference image to create new textures for the model. The node outputs the textured model in GLB and FBX file formats. ## Inputs @@ -35,4 +36,4 @@ The Meshy: Texture Node applies AI-generated textures to a 3D model. It takes a > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextureNode/en.md) --- -**Source fingerprint (SHA-256):** `ac14eadd89c884abb8cb4800093fca93c8da5d8c86beec94bbdd40d34368ca09` +**Source fingerprint (SHA-256):** `b98ba2d88adcc55c4b708f9222007d61911fbec9454f3f2e912e42a0b485c61c` diff --git a/built-in-nodes/MinimaxHailuoVideoNode.mdx b/built-in-nodes/MinimaxHailuoVideoNode.mdx index d9a63a78f..476100ad5 100644 --- a/built-in-nodes/MinimaxHailuoVideoNode.mdx +++ b/built-in-nodes/MinimaxHailuoVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "MinimaxHailuoVideoNode" icon: "circle" mode: wide --- + Generates videos from text prompts using the MiniMax Hailuo-02 model. You can optionally provide a starting image as the first frame to create a video that continues from that image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt_text` | Text prompt to guide the video generation. | STRING | Yes | - | | `seed` | The random seed used for creating the noise (default: 0). | INT | No | 0 to 18446744073709551615 | | `first_frame_image` | Optional image to use as the first frame to generate a video. | IMAGE | No | - | @@ -23,10 +24,10 @@ Generates videos from text prompts using the MiniMax Hailuo-02 model. You can op ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxHailuoVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `180e8d3c739e34094a12a719d3187378a4c360a5799a4b23029edf164d0c55a3` +**Source fingerprint (SHA-256):** `7b6c78459bb1347ca61cb16fb6c5e9c88c6a0896dda90f48bb1b6397b99e8ca0` diff --git a/built-in-nodes/MinimaxImageToVideoNode.mdx b/built-in-nodes/MinimaxImageToVideoNode.mdx index 657b21b98..6e4868c29 100644 --- a/built-in-nodes/MinimaxImageToVideoNode.mdx +++ b/built-in-nodes/MinimaxImageToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "MinimaxImageToVideoNode" icon: "circle" mode: wide --- + Generates videos synchronously based on an image and prompt, and optional parameters using MiniMax's API. This node takes an input image and text description to create a video sequence, with various model options and configuration settings available. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | Image to use as first frame of video generation | IMAGE | Yes | - | | `prompt_text` | Text prompt to guide the video generation (default: empty string) | STRING | Yes | - | | `model` | Model to use for video generation (default: "I2V-01") | COMBO | Yes | "I2V-01-Director"
"I2V-01"
"I2V-01-live" | @@ -19,10 +20,10 @@ Generates videos synchronously based on an image and prompt, and optional parame ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video output | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxImageToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `8e5ae93cc214b541665f057c66d3203ef0ffdb10021fed2c05607df1b1a27844` +**Source fingerprint (SHA-256):** `90eef1d58fa0ae4897ab19d702ecad707948eb79181ac4927dba650056e954c8` diff --git a/built-in-nodes/MinimaxSubjectToVideoNode.mdx b/built-in-nodes/MinimaxSubjectToVideoNode.mdx index b82045b39..64c4037b0 100644 --- a/built-in-nodes/MinimaxSubjectToVideoNode.mdx +++ b/built-in-nodes/MinimaxSubjectToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "MinimaxSubjectToVideoNode" icon: "circle" mode: wide --- + Generates a video synchronously based on a subject image and a text prompt using MiniMax's API. This node takes an image of a subject and a description to create a video that animates or features that subject according to the prompt. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `subject` | Image of subject to reference for video generation | IMAGE | Yes | - | | `prompt_text` | Text prompt to guide the video generation (default: empty string) | STRING | Yes | - | | `model` | Model to use for video generation (default: "S2V-01") | COMBO | No | `"S2V-01"` | @@ -19,10 +20,10 @@ Generates a video synchronously based on a subject image and a text prompt using ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video based on the input subject image and prompt | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxSubjectToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `0dbdb1bb92850f4eac7c30017643a49ad932b2542bdf5c5c521ba875a0e341ca` +**Source fingerprint (SHA-256):** `e7d496d8e24a776bbea4afe102858e7d31c4f2e273889703eb02cc61e8389055` diff --git a/built-in-nodes/MinimaxTextToVideoNode.mdx b/built-in-nodes/MinimaxTextToVideoNode.mdx index dc72daf0f..0c4eb5f45 100644 --- a/built-in-nodes/MinimaxTextToVideoNode.mdx +++ b/built-in-nodes/MinimaxTextToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "MinimaxTextToVideoNode" icon: "circle" mode: wide --- + Generates videos synchronously based on a text prompt and optional parameters using MiniMax's API. This node creates video content from text descriptions by connecting to MiniMax's text-to-video service. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt_text` | Text prompt to guide the video generation | STRING | Yes | - | | `model` | Model to use for video generation (default: "T2V-01") | COMBO | No | "T2V-01"
"T2V-01-Director" | | `seed` | The random seed used for creating the noise (default: 0) | INT | No | 0 to 18446744073709551615 | @@ -18,10 +19,10 @@ Generates videos synchronously based on a text prompt and optional parameters us ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video based on the input prompt | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxTextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `603b6407446f4f7c5ea9520126f960a52c498d16b59f66fe022fd439b59c39ba` +**Source fingerprint (SHA-256):** `1d389bdcc48f903e04dad043a8609250f34466b9084b1319c411e155a8040422` diff --git a/built-in-nodes/MoGeInference.mdx b/built-in-nodes/MoGeInference.mdx index 8215b9e71..5434bf33e 100644 --- a/built-in-nodes/MoGeInference.mdx +++ b/built-in-nodes/MoGeInference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGeInference" icon: "circle" mode: wide --- + ## Overview Run MoGe on a single image to estimate depth and geometry. This node processes an input image through the MoGe model to generate a 3D point cloud, depth map, camera intrinsics, a mask, and surface normals. diff --git a/built-in-nodes/MoGePanoramaInference.mdx b/built-in-nodes/MoGePanoramaInference.mdx index 3ad975e2d..03a4d0f6d 100644 --- a/built-in-nodes/MoGePanoramaInference.mdx +++ b/built-in-nodes/MoGePanoramaInference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGePanoramaInference" icon: "circle" mode: wide --- + ## Overview This node performs depth estimation on equirectangular panorama images. It works by splitting the panorama into 12 perspective views, running the MoGe depth estimation model on each view, and then merging the results back into a single, complete depth map for the original panorama. diff --git a/built-in-nodes/MoGePointMapToMesh.mdx b/built-in-nodes/MoGePointMapToMesh.mdx index 0e68d4cd9..a365787ac 100644 --- a/built-in-nodes/MoGePointMapToMesh.mdx +++ b/built-in-nodes/MoGePointMapToMesh.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGePointMapToMesh" icon: "circle" mode: wide --- + ## Overview This node converts a MoGe point map into a 3D mesh. It takes the geometry data produced by a MoGe depth estimation node and triangulates it into a mesh with UV coordinates and an optional texture. diff --git a/built-in-nodes/MoGeRender.mdx b/built-in-nodes/MoGeRender.mdx index 3508f512f..4f30632c5 100644 --- a/built-in-nodes/MoGeRender.mdx +++ b/built-in-nodes/MoGeRender.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGeRender" icon: "circle" mode: wide --- + ## Overview This node takes a MOGE_GEOMETRY packet (produced by a MoGe depth/normal estimation node) and renders it into a standard image format. You can choose to output a depth map, a colored depth map, a normal map, or a mask. diff --git a/built-in-nodes/ModelComputeDtype.mdx b/built-in-nodes/ModelComputeDtype.mdx index 055b8d64a..c47bff459 100644 --- a/built-in-nodes/ModelComputeDtype.mdx +++ b/built-in-nodes/ModelComputeDtype.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelComputeDtype" icon: "circle" mode: wide --- + The ModelComputeDtype node changes the computational data type (precision) used by a model during processing. It creates a copy of the input model and applies the selected precision setting, which can help optimize memory usage and performance depending on your hardware. This is useful for debugging and testing different precision configurations. ## Inputs diff --git a/built-in-nodes/ModelMergeAdd.mdx b/built-in-nodes/ModelMergeAdd.mdx index c78cd770d..c5f4c0c35 100644 --- a/built-in-nodes/ModelMergeAdd.mdx +++ b/built-in-nodes/ModelMergeAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeAdd" icon: "circle" mode: wide --- + The ModelMergeAdd node is designed for merging two models by adding key patches from one model to another. This process involves cloning the first model and then applying patches from the second model, allowing for the combination of features or behaviors from both models. ## Inputs diff --git a/built-in-nodes/ModelMergeAuraflow.mdx b/built-in-nodes/ModelMergeAuraflow.mdx index 4b0322906..1224099c4 100644 --- a/built-in-nodes/ModelMergeAuraflow.mdx +++ b/built-in-nodes/ModelMergeAuraflow.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeAuraflow" icon: "circle" mode: wide --- + The ModelMergeAuraflow node allows you to blend two different models together by adjusting specific blending weights for various model components. It provides fine-grained control over how different parts of the models are merged, from initial layers to final outputs. This node is particularly useful for creating custom model combinations with precise control over the merging process. ## Inputs diff --git a/built-in-nodes/ModelMergeBlocks.mdx b/built-in-nodes/ModelMergeBlocks.mdx index 31b31a0fb..0ec33782a 100644 --- a/built-in-nodes/ModelMergeBlocks.mdx +++ b/built-in-nodes/ModelMergeBlocks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeBlocks" icon: "circle" mode: wide --- + ModelMergeBlocks is designed for advanced model merging operations, allowing for the integration of two models with customizable blending ratios for different parts of the models. This node facilitates the creation of hybrid models by selectively merging components from two source models based on specified parameters. ## Inputs diff --git a/built-in-nodes/ModelMergeCosmos14B.mdx b/built-in-nodes/ModelMergeCosmos14B.mdx index 10308e1ad..d6c22cfad 100644 --- a/built-in-nodes/ModelMergeCosmos14B.mdx +++ b/built-in-nodes/ModelMergeCosmos14B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmos14B" icon: "circle" mode: wide --- + The **ModelMergeCosmos14B** node merges two AI models using a block-based approach specifically designed for the Cosmos 14B model architecture. It allows you to blend different components of the models by adjusting weight values between 0.0 and 1.0 for each model block and embedding layer. ## Inputs diff --git a/built-in-nodes/ModelMergeCosmos7B.mdx b/built-in-nodes/ModelMergeCosmos7B.mdx index 300a09743..c3498e20a 100644 --- a/built-in-nodes/ModelMergeCosmos7B.mdx +++ b/built-in-nodes/ModelMergeCosmos7B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmos7B" icon: "circle" mode: wide --- + The ModelMergeCosmos7B node merges two AI models together using weighted blending of specific components. It allows fine-grained control over how different parts of the models are combined by adjusting individual weights for position embeddings, transformer blocks, and final layers. ## Inputs diff --git a/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx b/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx index 26b4bc4a9..60c47c53e 100644 --- a/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx +++ b/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmosPredict2_14B" icon: "circle" mode: wide --- + The ModelMergeCosmosPredict2_14B node merges two AI models by blending their internal components. It gives you precise control over how much each part of the second model influences the final merged result, using adjustable weight values for specific layers and components. ## Inputs diff --git a/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx b/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx index 66c5e1aa1..ed38d9ce9 100644 --- a/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx +++ b/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmosPredict2_2B" icon: "circle" mode: wide --- + The ModelMergeCosmosPredict2_2B node merges two diffusion models using a block-based approach with fine-grained control over different model components. It allows you to blend specific parts of two models by adjusting interpolation weights for position embedders, time embedders, transformer blocks, and final layers. This provides precise control over how different architectural components from each model contribute to the final merged result. ## Inputs diff --git a/built-in-nodes/ModelMergeFlux1.mdx b/built-in-nodes/ModelMergeFlux1.mdx index 9ff2995f7..8ed2b7c1f 100644 --- a/built-in-nodes/ModelMergeFlux1.mdx +++ b/built-in-nodes/ModelMergeFlux1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeFlux1" icon: "circle" mode: wide --- + The ModelMergeFlux1 node merges two diffusion models by blending their components using weighted interpolation. It allows fine-grained control over how different parts of the models are combined, including image processing blocks, time embedding layers, guidance mechanisms, vector inputs, text encoders, and various transformer blocks. This enables creating hybrid models with customized characteristics from two source models. ## Inputs diff --git a/built-in-nodes/ModelMergeKrea2.mdx b/built-in-nodes/ModelMergeKrea2.mdx new file mode 100644 index 000000000..053e18c41 --- /dev/null +++ b/built-in-nodes/ModelMergeKrea2.mdx @@ -0,0 +1,40 @@ +--- +title: "ModelMergeKrea2 - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ModelMergeKrea2 node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ModelMergeKrea2" +icon: "circle" +mode: wide +--- + +This node merges two models by blending their internal components at a fine-grained level, allowing you to control how much of each model's specific parts influence the final result. It works by taking two input models and applying separate blend ratios to different sections of their architecture. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model1` | The first model to merge | MODEL | Yes | - | +| `model2` | The second model to merge | MODEL | Yes | - | +| `first.` | Blend ratio for the first layer block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `tmlp.` | Blend ratio for the time MLP block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `txtmlp.` | Blend ratio for the text MLP block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `tproj.` | Blend ratio for the time projection block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `txtfusion.layerwise_blocks.0.` | Blend ratio for the first text fusion layerwise block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `txtfusion.layerwise_blocks.1.` | Blend ratio for the second text fusion layerwise block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `txtfusion.projector.` | Blend ratio for the text fusion projector block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `txtfusion.refiner_blocks.0.` | Blend ratio for the first text fusion refiner block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `txtfusion.refiner_blocks.1.` | Blend ratio for the second text fusion refiner block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `blocks.0.` through `blocks.27.` | Blend ratio for each of the 28 main blocks (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | +| `last.` | Blend ratio for the last block (default: 1.0) | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | + +Each blend ratio controls how much of `model2` is used for that specific component, where 0.0 means use only `model1`, 1.0 means use only `model2`, and values in between create a weighted blend. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `MODEL` | The merged model resulting from blending the two input models according to the specified ratios | MODEL | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeKrea2/en.md) + +--- +**Source fingerprint (SHA-256):** `ece35524f77fd906dc3109a0818d4d7d3986ec9debb518fd04893048843d7e88` diff --git a/built-in-nodes/ModelMergeLTXV.mdx b/built-in-nodes/ModelMergeLTXV.mdx index 4dee62476..84ec68b3b 100644 --- a/built-in-nodes/ModelMergeLTXV.mdx +++ b/built-in-nodes/ModelMergeLTXV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeLTXV" icon: "circle" mode: wide --- + The ModelMergeLTXV node performs advanced model merging operations specifically designed for LTXV model architectures. It allows you to blend two different models together by adjusting interpolation weights for various model components including transformer blocks, projection layers, and other specialized modules. ## Inputs diff --git a/built-in-nodes/ModelMergeMochiPreview.mdx b/built-in-nodes/ModelMergeMochiPreview.mdx index d55ff677a..11641be22 100644 --- a/built-in-nodes/ModelMergeMochiPreview.mdx +++ b/built-in-nodes/ModelMergeMochiPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeMochiPreview" icon: "circle" mode: wide --- + This node merges two AI models using a block-based approach with fine-grained control over different model components. It allows you to blend models by adjusting interpolation weights for specific sections including positional frequencies, embedding layers, and individual transformer blocks. The merging process combines the architectures and parameters from both input models according to the specified weight values. ## Inputs diff --git a/built-in-nodes/ModelMergeQwenImage.mdx b/built-in-nodes/ModelMergeQwenImage.mdx index 4d3264544..84c1a48aa 100644 --- a/built-in-nodes/ModelMergeQwenImage.mdx +++ b/built-in-nodes/ModelMergeQwenImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeQwenImage" icon: "circle" mode: wide --- + The ModelMergeQwenImage node merges two AI models by combining their components with adjustable weights. It allows you to blend specific parts of Qwen image models, including transformer blocks, positional embeddings, and text processing components. You can control how much influence each model has on different sections of the merged result. ## Inputs diff --git a/built-in-nodes/ModelMergeSD1.mdx b/built-in-nodes/ModelMergeSD1.mdx index fe90d3186..80aae507d 100644 --- a/built-in-nodes/ModelMergeSD1.mdx +++ b/built-in-nodes/ModelMergeSD1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD1" icon: "circle" mode: wide --- + The ModelMergeSD1 node allows you to blend two Stable Diffusion 1.x models together by adjusting the influence of different model components. It provides individual control over time embedding, label embedding, and all input, middle, and output blocks, enabling fine-tuned model merging for specific use cases. ## Inputs diff --git a/built-in-nodes/ModelMergeSD35_Large.mdx b/built-in-nodes/ModelMergeSD35_Large.mdx index c4bc5c43d..94a085c75 100644 --- a/built-in-nodes/ModelMergeSD35_Large.mdx +++ b/built-in-nodes/ModelMergeSD35_Large.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD35_Large" icon: "circle" mode: wide --- + The ModelMergeSD35_Large node allows you to blend two Stable Diffusion 3.5 Large models together by adjusting the influence of different model components. It provides precise control over how much each part of the second model contributes to the final merged model, from embedding layers to joint blocks and final layers. ## Inputs diff --git a/built-in-nodes/ModelMergeSD3_2B.mdx b/built-in-nodes/ModelMergeSD3_2B.mdx index 35808d698..760d0b1e9 100644 --- a/built-in-nodes/ModelMergeSD3_2B.mdx +++ b/built-in-nodes/ModelMergeSD3_2B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD3_2B" icon: "circle" mode: wide --- + The ModelMergeSD3_2B node allows you to merge two Stable Diffusion 3 2B models by blending their components with adjustable weights. It provides individual control over embedding layers and transformer blocks, enabling fine-tuned model combinations for specialized generation tasks. ## Inputs diff --git a/built-in-nodes/ModelMergeSDXL.mdx b/built-in-nodes/ModelMergeSDXL.mdx index c28ae9065..3b7e0a7ff 100644 --- a/built-in-nodes/ModelMergeSDXL.mdx +++ b/built-in-nodes/ModelMergeSDXL.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSDXL" icon: "circle" mode: wide --- + The ModelMergeSDXL node allows you to blend two SDXL models together by adjusting the influence of each model on different parts of the architecture. You can control how much each model contributes to time embeddings, label embeddings, and various blocks within the model structure. This creates a hybrid model that combines characteristics from both input models. ## Inputs diff --git a/built-in-nodes/ModelMergeSimple.mdx b/built-in-nodes/ModelMergeSimple.mdx index 7fe27848e..2deea5d88 100644 --- a/built-in-nodes/ModelMergeSimple.mdx +++ b/built-in-nodes/ModelMergeSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSimple" icon: "circle" mode: wide --- + The ModelMergeSimple node is designed for merging two models by blending their parameters based on a specified ratio. This node facilitates the creation of hybrid models that combine the strengths or characteristics of both input models. The `ratio` parameter determines the blending ratio between the two models. When this value is 1, the output model is 100% `model1`, and when this value is 0, the output model is 100% `model2`. diff --git a/built-in-nodes/ModelMergeSubtract.mdx b/built-in-nodes/ModelMergeSubtract.mdx index 7da596e6c..316449cdd 100644 --- a/built-in-nodes/ModelMergeSubtract.mdx +++ b/built-in-nodes/ModelMergeSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSubtract" icon: "circle" mode: wide --- + This node is designed for advanced model merging operations, specifically to subtract the parameters of one model from another based on a specified multiplier. It enables the customization of model behaviors by adjusting the influence of one model's parameters over another, facilitating the creation of new, hybrid models. ## Inputs diff --git a/built-in-nodes/ModelMergeWAN2_1.mdx b/built-in-nodes/ModelMergeWAN2_1.mdx index f2058aae3..342d3c049 100644 --- a/built-in-nodes/ModelMergeWAN2_1.mdx +++ b/built-in-nodes/ModelMergeWAN2_1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeWAN2_1" icon: "circle" mode: wide --- + The ModelMergeWAN2_1 node merges two WAN2.1 models by blending their components using weighted averages. It supports different model sizes including 1.3B models with 30 blocks and 14B models with 40 blocks, with special handling for image to video models that include an extra image embedding component. Each component of the models can be individually weighted to control the blending ratio between the two input models. ## Inputs diff --git a/built-in-nodes/ModelNoiseScale.mdx b/built-in-nodes/ModelNoiseScale.mdx index b72672b45..3373ef66d 100644 --- a/built-in-nodes/ModelNoiseScale.mdx +++ b/built-in-nodes/ModelNoiseScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelNoiseScale" icon: "circle" mode: wide --- + ## Overview This node adjusts the noise scale used during model sampling. It allows you to set a specific noise scale value, which controls the amount of noise applied to the model's sampling process. diff --git a/built-in-nodes/ModelPatchLoader.mdx b/built-in-nodes/ModelPatchLoader.mdx index 78f8ef409..086f6d6be 100644 --- a/built-in-nodes/ModelPatchLoader.mdx +++ b/built-in-nodes/ModelPatchLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelPatchLoader" icon: "circle" mode: wide --- + The ModelPatchLoader node loads specialized model patches from the model_patches folder. It automatically detects the type of patch file and loads the appropriate model architecture, then wraps it in a ModelPatcher for use in the workflow. This node supports different patch types including controlnet blocks, feature embedder models, and other specialized architectures. ## Inputs diff --git a/built-in-nodes/ModelSamplingAuraFlow.mdx b/built-in-nodes/ModelSamplingAuraFlow.mdx index a14435861..c998cb36e 100644 --- a/built-in-nodes/ModelSamplingAuraFlow.mdx +++ b/built-in-nodes/ModelSamplingAuraFlow.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingAuraFlow" icon: "circle" mode: wide --- + The ModelSamplingAuraFlow node applies a specialized sampling configuration to diffusion models, specifically designed for AuraFlow model architectures. It modifies the model's sampling behavior by applying a shift parameter that adjusts the sampling distribution. This node inherits from the SD3 model sampling framework and provides fine control over the sampling process. ## Inputs diff --git a/built-in-nodes/ModelSamplingContinuousEDM.mdx b/built-in-nodes/ModelSamplingContinuousEDM.mdx index 70eb85516..c5417559c 100644 --- a/built-in-nodes/ModelSamplingContinuousEDM.mdx +++ b/built-in-nodes/ModelSamplingContinuousEDM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingContinuousEDM" icon: "circle" mode: wide --- + This node is designed to enhance a model's sampling capabilities by integrating continuous EDM (Energy-based Diffusion Models) sampling techniques. It allows for the dynamic adjustment of the noise levels within the model's sampling process, offering a more refined control over the generation quality and diversity. ## Inputs diff --git a/built-in-nodes/ModelSamplingContinuousV.mdx b/built-in-nodes/ModelSamplingContinuousV.mdx index 768703897..9c66d3742 100644 --- a/built-in-nodes/ModelSamplingContinuousV.mdx +++ b/built-in-nodes/ModelSamplingContinuousV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingContinuousV" icon: "circle" mode: wide --- + The ModelSamplingContinuousV node modifies a model's sampling behavior by applying continuous V-prediction sampling parameters. It creates a clone of the input model and configures it with custom sigma range settings for advanced sampling control. This allows users to fine-tune the sampling process with specific minimum and maximum sigma values. ## Inputs diff --git a/built-in-nodes/ModelSamplingDiscrete.mdx b/built-in-nodes/ModelSamplingDiscrete.mdx index dd317e266..6697b9408 100644 --- a/built-in-nodes/ModelSamplingDiscrete.mdx +++ b/built-in-nodes/ModelSamplingDiscrete.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingDiscrete" icon: "circle" mode: wide --- + This node is designed to modify the sampling behavior of a model by applying a discrete sampling strategy. It allows for the selection of different sampling methods, such as epsilon, v_prediction, lcm, or x0, and optionally adjusts the model's noise reduction strategy based on the zero-shot noise ratio (zsnr) setting. ## Inputs diff --git a/built-in-nodes/ModelSamplingFlux.mdx b/built-in-nodes/ModelSamplingFlux.mdx index de9cf8748..4cbf75048 100644 --- a/built-in-nodes/ModelSamplingFlux.mdx +++ b/built-in-nodes/ModelSamplingFlux.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingFlux" icon: "circle" mode: wide --- + The ModelSamplingFlux node applies Flux model sampling to a given model by calculating a shift parameter based on image dimensions. It creates a specialized sampling configuration that adjusts the model's behavior according to the specified width, height, and shift parameters, then returns the modified model with the new sampling settings applied. ## Inputs diff --git a/built-in-nodes/ModelSamplingLTXV.mdx b/built-in-nodes/ModelSamplingLTXV.mdx index 72d42e99a..e8ed2230b 100644 --- a/built-in-nodes/ModelSamplingLTXV.mdx +++ b/built-in-nodes/ModelSamplingLTXV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingLTXV" icon: "circle" mode: wide --- + The ModelSamplingLTXV node applies advanced sampling parameters to a model based on token count. It calculates a shift value using a linear interpolation between base and maximum shift values, with the calculation depending on the number of tokens in the input latent. The node then creates a specialized model sampling configuration and applies it to the input model. ## Inputs diff --git a/built-in-nodes/ModelSamplingSD3.mdx b/built-in-nodes/ModelSamplingSD3.mdx index 4b85a840b..fd73d0f73 100644 --- a/built-in-nodes/ModelSamplingSD3.mdx +++ b/built-in-nodes/ModelSamplingSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingSD3" icon: "circle" mode: wide --- + The ModelSamplingSD3 node applies Stable Diffusion 3 sampling parameters to a model. It modifies the model's sampling behavior by adjusting the shift parameter, which controls the sampling distribution characteristics. The node creates a modified copy of the input model with the specified sampling configuration applied. ## Inputs diff --git a/built-in-nodes/ModelSamplingStableCascade.mdx b/built-in-nodes/ModelSamplingStableCascade.mdx index 57bd396f0..19cf1772f 100644 --- a/built-in-nodes/ModelSamplingStableCascade.mdx +++ b/built-in-nodes/ModelSamplingStableCascade.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingStableCascade" icon: "circle" mode: wide --- + The ModelSamplingStableCascade node applies stable cascade sampling to a model by adjusting the sampling parameters with a shift value. It creates a modified version of the input model with custom sampling configuration for stable cascade generation. ## Inputs diff --git a/built-in-nodes/ModelSave.mdx b/built-in-nodes/ModelSave.mdx index f0d67a212..04ed6fcea 100644 --- a/built-in-nodes/ModelSave.mdx +++ b/built-in-nodes/ModelSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSave" icon: "circle" mode: wide --- + The ModelSave node saves trained or modified models to your computer's storage. It takes a model as input and writes it to a file with your specified filename. This allows you to preserve your work and reuse models in future projects. ## Inputs diff --git a/built-in-nodes/MoonvalleyImg2VideoNode.mdx b/built-in-nodes/MoonvalleyImg2VideoNode.mdx index fd5aa4c96..a6b35e98d 100644 --- a/built-in-nodes/MoonvalleyImg2VideoNode.mdx +++ b/built-in-nodes/MoonvalleyImg2VideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoonvalleyImg2VideoNode" icon: "circle" mode: wide --- + The Moonvalley Marey Image to Video node transforms a reference image into a video using the Moonvalley API. It takes an input image and a text prompt to generate a video with specified resolution, quality settings, and creative controls. The node handles the entire process from image upload to video generation and download. ## Inputs diff --git a/built-in-nodes/MoonvalleyTxt2VideoNode.mdx b/built-in-nodes/MoonvalleyTxt2VideoNode.mdx index 87cabb0c9..32674a5f9 100644 --- a/built-in-nodes/MoonvalleyTxt2VideoNode.mdx +++ b/built-in-nodes/MoonvalleyTxt2VideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoonvalleyTxt2VideoNode" icon: "circle" mode: wide --- + The Moonvalley Marey Text to Video node generates video content from text descriptions using the Moonvalley API. It takes a text prompt and converts it into a video with customizable settings for resolution, quality, and style. The node handles the entire process from sending the generation request to downloading the final video output. ## Inputs diff --git a/built-in-nodes/MoonvalleyVideo2VideoNode.mdx b/built-in-nodes/MoonvalleyVideo2VideoNode.mdx index 782491173..63613e3a5 100644 --- a/built-in-nodes/MoonvalleyVideo2VideoNode.mdx +++ b/built-in-nodes/MoonvalleyVideo2VideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoonvalleyVideo2VideoNode" icon: "circle" mode: wide --- + The Moonvalley Marey Video to Video node transforms an input video into a new video based on a text description. It uses the Moonvalley API to generate videos that match your prompt while preserving motion or pose characteristics from the original video. You can control the style and content of the output video through text prompts and various generation parameters. ## Inputs diff --git a/built-in-nodes/Morphology.mdx b/built-in-nodes/Morphology.mdx index 4fe99cf5e..3d7b3d18f 100644 --- a/built-in-nodes/Morphology.mdx +++ b/built-in-nodes/Morphology.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Morphology" icon: "circle" mode: wide --- + The Morphology node applies various morphological operations to images, which are mathematical operations used to process and analyze shapes in images. It can perform operations like erosion, dilation, opening, closing, and more using a customizable kernel size to control the effect strength. ## Inputs diff --git a/built-in-nodes/MultiGPU_Options.mdx b/built-in-nodes/MultiGPU_Options.mdx index 840f8bbff..7685cf7c5 100644 --- a/built-in-nodes/MultiGPU_Options.mdx +++ b/built-in-nodes/MultiGPU_Options.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MultiGPU_Options" icon: "circle" mode: wide --- + ## Overview This node allows you to specify the relative performance of each GPU when using multiple graphics cards with different speeds. It creates a group of GPU options that can be used to distribute work across devices, though the actual speed-based workload distribution is not yet implemented in the current version. diff --git a/built-in-nodes/MultiGPU_WorkUnits.mdx b/built-in-nodes/MultiGPU_WorkUnits.mdx index a3fa38fc7..195c4151a 100644 --- a/built-in-nodes/MultiGPU_WorkUnits.mdx +++ b/built-in-nodes/MultiGPU_WorkUnits.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MultiGPU_WorkUnits" icon: "circle" mode: wide --- -# COMFYUI MultiGPU CFG Split Node ## Overview: diff --git a/built-in-nodes/NAGuidance.mdx b/built-in-nodes/NAGuidance.mdx index b6172b434..6a36dbd94 100644 --- a/built-in-nodes/NAGuidance.mdx +++ b/built-in-nodes/NAGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NAGuidance" icon: "circle" mode: wide --- + The NAGuidance node applies Normalized Attention Guidance to a model. This technique enables the use of negative prompts with distilled or schnell models by modifying the model's attention mechanism during the sampling process to steer the generation away from undesired concepts. ## Inputs diff --git a/built-in-nodes/NormalizeImages.mdx b/built-in-nodes/NormalizeImages.mdx index 63c8de05b..ee0f6eb15 100644 --- a/built-in-nodes/NormalizeImages.mdx +++ b/built-in-nodes/NormalizeImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NormalizeImages" icon: "circle" mode: wide --- + This node adjusts the pixel values of an input image using a mathematical normalization process. It subtracts a specified mean value from each pixel and then divides the result by a specified standard deviation. This is a common preprocessing step to prepare image data for other machine learning models. ## Inputs diff --git a/built-in-nodes/NormalizeVideoLatentStart.mdx b/built-in-nodes/NormalizeVideoLatentStart.mdx index 701bfc016..06c40b9a1 100644 --- a/built-in-nodes/NormalizeVideoLatentStart.mdx +++ b/built-in-nodes/NormalizeVideoLatentStart.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NormalizeVideoLatentStart" icon: "circle" mode: wide --- + This node adjusts the first few frames of a video latent to make them look more like the frames that come after. It calculates the average and variation from a set of reference frames later in the video and applies those same characteristics to the starting frames. This helps create a smoother and more consistent visual transition at the beginning of a video. ## Inputs diff --git a/built-in-nodes/Note.mdx b/built-in-nodes/Note.mdx index 20f5902f4..631a7aef4 100644 --- a/built-in-nodes/Note.mdx +++ b/built-in-nodes/Note.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Note" icon: "circle" mode: wide --- + Node to add annotations to a workflow. ## Inputs diff --git a/built-in-nodes/OpenAIChatConfig.mdx b/built-in-nodes/OpenAIChatConfig.mdx index e8f6763b6..ea3a88147 100644 --- a/built-in-nodes/OpenAIChatConfig.mdx +++ b/built-in-nodes/OpenAIChatConfig.mdx @@ -5,23 +5,24 @@ sidebarTitle: "OpenAIChatConfig" icon: "circle" mode: wide --- + The OpenAIChatConfig node allows setting additional configuration options for the OpenAI Chat Node. It provides advanced settings that control how the model generates responses, including truncation behavior, output length limits, and custom instructions. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `truncation` | The truncation strategy to use for the model response. auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation. disabled: If a model response will exceed the context window size for a model, the request will fail with a 400 error (default: "auto") | COMBO | Yes | `"auto"`
`"disabled"` | +|-----------|-------------|-----------|----------|-------| +| `truncation` | The truncation strategy to use for the model response. auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation. disabled: If a model response will exceed the context window size for a model, the request will fail with a 400 error (default: "auto") | STRING | Yes | "auto"
"disabled" | | `max_output_tokens` | An upper bound for the number of tokens that can be generated for a response, including visible output tokens (default: 4096) | INT | No | 16 to 16384 | | `instructions` | Instructions for the model on how to generate the response (multiline input supported) | STRING | No | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `OPENAI_CHAT_CONFIG` | Configuration object containing the specified settings for use with OpenAI Chat Nodes | OPENAI_CHAT_CONFIG | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIChatConfig/en.md) --- -**Source fingerprint (SHA-256):** `f9ae6d3b2818ea37543156c2f209fc4d093e40e446907deb4be327ca0c9d70e1` +**Source fingerprint (SHA-256):** `5690c4b6490b7fea3674e4c61dadce8dc7cdb49048d34b0b417b9e00c6f7ddb4` diff --git a/built-in-nodes/OpenAIChatNode.mdx b/built-in-nodes/OpenAIChatNode.mdx index 68e471e4a..7c002eefd 100644 --- a/built-in-nodes/OpenAIChatNode.mdx +++ b/built-in-nodes/OpenAIChatNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "OpenAIChatNode" icon: "circle" mode: wide --- + This node generates text responses from an OpenAI model. It sends your text prompt (and optionally images or files) to an OpenAI model and returns the generated text response. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text inputs to the model, used to generate a response (default: empty) | STRING | Yes | - | | `persist_context` | This parameter is deprecated and has no effect (default: False) | BOOLEAN | Yes | - | | `model` | The model used to generate the response (default: `gpt-5`) | COMBO | Yes | `gpt-5.5-pro`
`gpt-5.5`
`gpt-5`
`gpt-5-mini`
`gpt-5-nano`
`gpt-4.1`
`gpt-4.1-mini`
`gpt-4.1-nano`
`o4-mini`
`o3`
`o1-pro`
`o1` | @@ -21,10 +22,10 @@ This node generates text responses from an OpenAI model. It sends your text prom ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output_text` | The text response generated by the OpenAI model | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIChatNode/en.md) --- -**Source fingerprint (SHA-256):** `9adc9685d7fc31fba95bf43fa9e041289b6dbb9ab8f5ed30dc85e0acc015fe5c` +**Source fingerprint (SHA-256):** `517c4825fa1047fb7411f8c822a53f818c9559c94736874592f61d0bdcfea6b7` diff --git a/built-in-nodes/OpenAIDalle2.mdx b/built-in-nodes/OpenAIDalle2.mdx index 4e33e9b12..abb913dbd 100644 --- a/built-in-nodes/OpenAIDalle2.mdx +++ b/built-in-nodes/OpenAIDalle2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "OpenAIDalle2" icon: "circle" mode: wide --- -# OpenAIDalle2 Generates images synchronously via OpenAI's DALL·E 2 endpoint. diff --git a/built-in-nodes/OpenAIDalle3.mdx b/built-in-nodes/OpenAIDalle3.mdx index 111bc6df9..70c50dcc7 100644 --- a/built-in-nodes/OpenAIDalle3.mdx +++ b/built-in-nodes/OpenAIDalle3.mdx @@ -5,12 +5,13 @@ sidebarTitle: "OpenAIDalle3" icon: "circle" mode: wide --- + Generates images synchronously via OpenAI's DALL·E 3 endpoint. This node takes a text prompt and creates corresponding images using OpenAI's DALL·E 3 model, allowing you to specify image quality, style, and dimensions. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt for DALL·E (default: "") | STRING | Yes | - | | `seed` | Not implemented yet in backend (default: 0) | INT | No | 0 to 2147483647 | | `quality` | Image quality (default: "standard") | COMBO | No | "standard"
"hd" | @@ -20,10 +21,10 @@ Generates images synchronously via OpenAI's DALL·E 3 endpoint. This node takes ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | The generated image from DALL·E 3 | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIDalle3/en.md) --- -**Source fingerprint (SHA-256):** `f100a8564689c2c54cc5c22df554af7e5c166bd4f15bc9234bade4d0819a09dd` +**Source fingerprint (SHA-256):** `9077628610503d8c0afdd04e30dadac46106bd577d10f2d7aa10864db4430605` diff --git a/built-in-nodes/OpenAIGPTImage1.mdx b/built-in-nodes/OpenAIGPTImage1.mdx index a06123b6b..3f22eee1b 100644 --- a/built-in-nodes/OpenAIGPTImage1.mdx +++ b/built-in-nodes/OpenAIGPTImage1.mdx @@ -5,12 +5,13 @@ sidebarTitle: "OpenAIGPTImage1" icon: "circle" mode: wide --- + Generates images synchronously via OpenAI's GPT Image endpoint. This node can create new images from text prompts or edit existing images when provided with an input image and optional mask. It supports multiple GPT Image models, including gpt-image-1, gpt-image-1.5, and gpt-image-2. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt for GPT Image (default: "") | STRING | Yes | - | | `seed` | Random seed for generation (default: 0) - not implemented yet in backend | INT | No | 0 to 2147483647 | | `quality` | Image quality, affects cost and generation time (default: "low") | COMBO | No | "low"
"medium"
"high" | @@ -39,10 +40,10 @@ Generates images synchronously via OpenAI's GPT Image endpoint. This node can cr ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | Generated or edited image(s) | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIGPTImage1/en.md) --- -**Source fingerprint (SHA-256):** `826d393831ee38e97dad3ea238877d0aeb5bf16778612c51cdc0ca4816efead2` +**Source fingerprint (SHA-256):** `e7f460fccb6c372558f9a012632804a6047ee5be78b1fc3209f255a55fe13d7c` diff --git a/built-in-nodes/OpenAIGPTImageNodeV2.mdx b/built-in-nodes/OpenAIGPTImageNodeV2.mdx index 2bbe2c16c..d7912d7d7 100644 --- a/built-in-nodes/OpenAIGPTImageNodeV2.mdx +++ b/built-in-nodes/OpenAIGPTImageNodeV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIGPTImageNodeV2" icon: "circle" mode: wide --- + ## Overview This node generates images using OpenAI's GPT Image API. It supports multiple models, allows you to provide input images for editing, and can use a mask to specify which parts of an image to modify. @@ -27,7 +28,7 @@ This node generates images using OpenAI's GPT Image API. It supports multiple mo **Parameter Constraints and Limitations:** -- When using `gpt-image-2` with a `model.size` of "Custom", the `custom_width` and `custom_height` must be multiples of 16, the maximum edge must be `<= 3840`, the aspect ratio must not exceed 3:1, and the total pixel count must be between 655,360 and 8,294,400. +- When using `gpt-image-2` with a `model.size` of "Custom", the `custom_width` and `custom_height` must be multiples of 16, the maximum edge must be <= 3840, the aspect ratio must not exceed 3:1, and the total pixel count must be between 655,360 and 8,294,400. - If a `mask` is provided, an input image (`model.images`) is required. A mask cannot be used without an input image. - A mask cannot be used with multiple input images. - When a mask is provided, the mask dimensions must match the input image dimensions. @@ -42,4 +43,4 @@ This node generates images using OpenAI's GPT Image API. It supports multiple mo > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIGPTImageNodeV2/en.md) --- -**Source fingerprint (SHA-256):** `dcea500ebbbbfe87f8b0dd2d714cf2356edf2030312c2cc6e41d64bd2ad04ea6` +**Source fingerprint (SHA-256):** `d0544a2d0f9e9cdd4b121bbf18eb6e43d508b2230e44dfa814649f6a4999e543` diff --git a/built-in-nodes/OpenAIInputFiles.mdx b/built-in-nodes/OpenAIInputFiles.mdx index 836dfdbff..5f3d1e7de 100644 --- a/built-in-nodes/OpenAIInputFiles.mdx +++ b/built-in-nodes/OpenAIInputFiles.mdx @@ -5,12 +5,13 @@ sidebarTitle: "OpenAIInputFiles" icon: "circle" mode: wide --- + Loads and formats input files for the OpenAI API. This node prepares text (.txt) and PDF (.pdf) files to include as context inputs for the OpenAI Chat Node. The files will be read by the OpenAI model when generating a response. Multiple OpenAI Input Files nodes can be chained together to include several files in a single message. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `file` | Input files to include as context for the model. Only accepts text (.txt) and PDF (.pdf) files for now. Files must be smaller than 32MB. | COMBO | Yes | Multiple options available (all .txt and .pdf files in the input directory under 32MB) | | `OPENAI_INPUT_FILES` | An optional additional file(s) to batch together with the file loaded from this node. Allows chaining of input files so that a single message can include multiple input files. | OPENAI_INPUT_FILES | No | N/A | @@ -23,10 +24,10 @@ Loads and formats input files for the OpenAI API. This node prepares text (.txt) ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `OPENAI_INPUT_FILES` | Formatted input files ready to be used as context for OpenAI API calls. | OPENAI_INPUT_FILES | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIInputFiles/en.md) --- -**Source fingerprint (SHA-256):** `9e1a60feb48d39646c4247dd12b15c3eb392e1b85b3db2f254571d568d772de0` +**Source fingerprint (SHA-256):** `6554e685184ced830ee27aa96efefc8bb9616bd0504685bdb643c715ebc6dd98` diff --git a/built-in-nodes/OpenAIVideoSora2.mdx b/built-in-nodes/OpenAIVideoSora2.mdx index 75578e21f..51819ff03 100644 --- a/built-in-nodes/OpenAIVideoSora2.mdx +++ b/built-in-nodes/OpenAIVideoSora2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIVideoSora2" icon: "circle" mode: wide --- + The OpenAIVideoSora2 node generates videos using OpenAI's Sora models. It creates video content based on text prompts and optional input images, then returns the generated video output. The node supports different video durations and resolutions depending on the selected model. **DEPRECATION NOTICE:** OpenAI will stop serving the Sora v2 API in September 2026. This node will be removed from ComfyUI at that time. @@ -35,4 +36,4 @@ The OpenAIVideoSora2 node generates videos using OpenAI's Sora models. It create > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIVideoSora2/en.md) --- -**Source fingerprint (SHA-256):** `b632ef33ca5f01a7aed780a9eeea9b2fcbf4ab85ccb8f026e6175ceaafbda47b` +**Source fingerprint (SHA-256):** `132b98ce6473c7870053800bc2886293ab88292f40327e541fc053cdcc2f36cd` diff --git a/built-in-nodes/OpenRouterLLMNode.mdx b/built-in-nodes/OpenRouterLLMNode.mdx index c433830fe..ddbb97f7b 100644 --- a/built-in-nodes/OpenRouterLLMNode.mdx +++ b/built-in-nodes/OpenRouterLLMNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenRouterLLMNode" icon: "circle" mode: wide --- + ## Overview The OpenRouter LLM node sends a text prompt to a curated set of popular language models available through the OpenRouter service and returns the generated text response. It supports models from providers like xAI, DeepSeek, Qwen, Mistral, Z.AI (GLM), Moonshot (Kimi), and Perplexity Sonar, and can optionally include images or videos in the request. @@ -12,7 +13,7 @@ The OpenRouter LLM node sends a text prompt to a curated set of popular language ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text input to the model. | STRING | Yes | N/A | | `model` | The OpenRouter model used to generate the response. | STRING | Yes | Multiple options available (see note below) | | `seed` | Seed for sampling. Set to 0 to omit. Most models treat this as a hint only. (default: 0) | INT | Yes | 0 to 2147483647 | @@ -24,13 +25,15 @@ The OpenRouter LLM node sends a text prompt to a curated set of popular language **Note on `system_prompt`:** This parameter is optional and is marked as an advanced parameter in the user interface. +**Note on image and video constraints:** Some models support image and video inputs. The maximum number of images and videos allowed depends on the selected model. The node will raise an error if the number of images or videos exceeds the model's limit. + ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated text response from the OpenRouter model. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenRouterLLMNode/en.md) --- -**Source fingerprint (SHA-256):** `24757e36bf2356cc1805a6f071db88ca455e17944695672f19845a4cd1826c8a` +**Source fingerprint (SHA-256):** `d6a807299f476427edfb67b756bb88a6678f6f3fcaf79d20e934f02caf72cb6c` diff --git a/built-in-nodes/OpticalFlowLoader.mdx b/built-in-nodes/OpticalFlowLoader.mdx index 27b291dc1..2fe15437f 100644 --- a/built-in-nodes/OpticalFlowLoader.mdx +++ b/built-in-nodes/OpticalFlowLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpticalFlowLoader" icon: "circle" mode: wide --- + ## Overview Loads an optical flow model from the `models/optical_flow/` folder. Currently, only torchvision's RAFT-large format is supported, which is the model used by the VOIDWarpedNoise node. ComfyUI does not download optical flow weights automatically; you must place the checkpoint file manually in the `models/optical_flow/` directory. diff --git a/built-in-nodes/OptimalStepsScheduler.mdx b/built-in-nodes/OptimalStepsScheduler.mdx index cb7889bff..8d9112c76 100644 --- a/built-in-nodes/OptimalStepsScheduler.mdx +++ b/built-in-nodes/OptimalStepsScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OptimalStepsScheduler" icon: "circle" mode: wide --- + The OptimalStepsScheduler node calculates noise schedule sigmas for diffusion models based on the selected model type and step configuration. It adjusts the total number of steps according to the denoise parameter and interpolates the noise levels to match the requested step count. The node returns a sequence of sigma values that determine the noise levels used during the diffusion sampling process. ## Inputs diff --git a/built-in-nodes/Painter.mdx b/built-in-nodes/Painter.mdx index 94a4f50d3..f68d66f0e 100644 --- a/built-in-nodes/Painter.mdx +++ b/built-in-nodes/Painter.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Painter" icon: "circle" mode: wide --- + The Painter node provides an interactive canvas for creating or editing images and masks directly within ComfyUI. It allows you to start with a blank canvas or an existing image, paint on it using a brush tool, and outputs both the resulting image and a corresponding alpha mask. The mask defines the painted areas, which are then composited over the base image or background color. ## Inputs diff --git a/built-in-nodes/PairConditioningCombine.mdx b/built-in-nodes/PairConditioningCombine.mdx index c621f2dd5..de7ed22e1 100644 --- a/built-in-nodes/PairConditioningCombine.mdx +++ b/built-in-nodes/PairConditioningCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningCombine" icon: "circle" mode: wide --- + The PairConditioningCombine node merges two separate conditioning pairs (each consisting of a positive and negative conditioning) into a single combined pair. It takes the positive and negative conditioning from two different sources and combines them using ComfyUI's internal logic, outputting one final positive and one final negative conditioning. This node is experimental and designed for advanced conditioning manipulation workflows. ## Inputs diff --git a/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx b/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx index 75d6a59bf..25c5f41dd 100644 --- a/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx +++ b/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetDefaultAndCombine" icon: "circle" mode: wide --- + The **PairConditioningSetDefaultAndCombine** node sets default conditioning values and combines them with input conditioning data. It takes positive and negative conditioning inputs along with their default counterparts, then processes them through ComfyUI's hook system to produce final conditioning outputs that incorporate the default values. ## Inputs diff --git a/built-in-nodes/PairConditioningSetProperties.mdx b/built-in-nodes/PairConditioningSetProperties.mdx index 1d24eaa8e..c75486259 100644 --- a/built-in-nodes/PairConditioningSetProperties.mdx +++ b/built-in-nodes/PairConditioningSetProperties.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetProperties" icon: "circle" mode: wide --- + The **PairConditioningSetProperties** node allows you to modify properties of both positive and negative conditioning pairs at the same time. It applies strength adjustments, conditioning area settings, and optional masking or timing controls to both conditioning inputs, returning the modified positive and negative conditioning data. ## Inputs diff --git a/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx b/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx index 47230da37..ce79d7b5f 100644 --- a/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx +++ b/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetPropertiesAndCombine" icon: "circle" mode: wide --- + The PairConditioningSetPropertiesAndCombine node modifies and combines conditioning pairs by applying new conditioning data to existing positive and negative conditioning inputs. It allows you to adjust the strength of the applied conditioning and control how the conditioning area is set. This node is particularly useful for advanced conditioning manipulation workflows where you need to blend multiple conditioning sources together. ## Inputs diff --git a/built-in-nodes/PatchModelAddDownscale.mdx b/built-in-nodes/PatchModelAddDownscale.mdx index d1d82d13b..32306c150 100644 --- a/built-in-nodes/PatchModelAddDownscale.mdx +++ b/built-in-nodes/PatchModelAddDownscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PatchModelAddDownscale" icon: "circle" mode: wide --- + The PatchModelAddDownscale node implements Kohya Deep Shrink functionality by applying downscaling and upscaling operations to specific blocks in a model. It reduces the resolution of intermediate features during processing and then restores them to their original size, which can improve performance while maintaining quality. The node allows precise control over when and how these scaling operations occur during the model's execution. ## Inputs diff --git a/built-in-nodes/PerpNeg.mdx b/built-in-nodes/PerpNeg.mdx index 372e558cf..f23a0a615 100644 --- a/built-in-nodes/PerpNeg.mdx +++ b/built-in-nodes/PerpNeg.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerpNeg" icon: "circle" mode: wide --- + The PerpNeg node applies perpendicular negative guidance to a model's sampling process. This node modifies the model's configuration function to adjust noise predictions using negative conditioning and scaling factors. It has been deprecated and replaced by the PerpNegGuider node for improved functionality. ## Inputs diff --git a/built-in-nodes/PerpNegGuider.mdx b/built-in-nodes/PerpNegGuider.mdx index b31a27310..8c7854d4c 100644 --- a/built-in-nodes/PerpNegGuider.mdx +++ b/built-in-nodes/PerpNegGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerpNegGuider" icon: "circle" mode: wide --- + The PerpNegGuider node creates a guidance system for controlling image generation using perpendicular negative conditioning. It takes positive, negative, and empty conditioning inputs and applies a specialized guidance algorithm that computes all three noise predictions in a single batch for efficiency. This node is designed for experimental testing and provides fine control over the guidance strength and negative scaling. ## Inputs diff --git a/built-in-nodes/PerturbedAttentionGuidance.mdx b/built-in-nodes/PerturbedAttentionGuidance.mdx index 20e2e46ae..f4472fc47 100644 --- a/built-in-nodes/PerturbedAttentionGuidance.mdx +++ b/built-in-nodes/PerturbedAttentionGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerturbedAttentionGuidance" icon: "circle" mode: wide --- + The PerturbedAttentionGuidance node applies perturbed attention guidance to a diffusion model to enhance generation quality. It modifies the model's self-attention mechanism during sampling by replacing it with a simplified version that focuses on value projections. This technique helps improve the coherence and quality of generated images by adjusting the conditional denoising process. ## Inputs diff --git a/built-in-nodes/PhotoMakerEncode.mdx b/built-in-nodes/PhotoMakerEncode.mdx index 92e2257d0..a74d6ccc1 100644 --- a/built-in-nodes/PhotoMakerEncode.mdx +++ b/built-in-nodes/PhotoMakerEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PhotoMakerEncode" icon: "circle" mode: wide --- + The PhotoMakerEncode node processes a reference image and a text prompt to generate conditioning data for AI image generation. It uses the PhotoMaker model to combine visual characteristics from the image with text embeddings, specifically looking for the "photomaker" token in the text to determine where to apply the image-based conditioning. ## Inputs diff --git a/built-in-nodes/PhotoMakerLoader.mdx b/built-in-nodes/PhotoMakerLoader.mdx index 42aa2f34f..70be667b8 100644 --- a/built-in-nodes/PhotoMakerLoader.mdx +++ b/built-in-nodes/PhotoMakerLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PhotoMakerLoader" icon: "circle" mode: wide --- + The PhotoMakerLoader node loads a PhotoMaker model from the available model files. It reads the specified model file and prepares the PhotoMaker ID encoder for use in identity-based image generation tasks. This node is marked as experimental and is intended for testing purposes. ## Inputs diff --git a/built-in-nodes/PiDConditioning.mdx b/built-in-nodes/PiDConditioning.mdx index 3693d9af9..62c97ef9a 100644 --- a/built-in-nodes/PiDConditioning.mdx +++ b/built-in-nodes/PiDConditioning.mdx @@ -5,26 +5,25 @@ sidebarTitle: "PiDConditioning" icon: "circle" mode: wide --- -## Overview Attaches a latent image and a degrade sigma value to a CONDITIONING data. This is used for PiD (Pixel-in-Detail) decoding or upscaling, allowing you to control how much the latent is degraded before processing. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `positive` | The conditioning data to attach the latent and degrade sigma to. | CONDITIONING | Yes | - | | `latent` | The latent image (from VAEEncode or a KSampler) to attach to the conditioning. | LATENT | Yes | - | -| `latent_format` | The format of the latent. Flux1 and Flux2 latents are auto-detected from the channel dimension. SD3 must be selected manually (default: "flux"). | COMBO | Yes | `"flux"`
`"sd3"` | +| `latent_format` | The format of the latent. Flux1 (16-ch) and Flux2 (128-ch) latents are auto-detected from the channel dimension under "flux". For SD3 (16-ch), SDXL (4-ch), or QwenImage (16-ch), select manually (default: "flux"). | COMBO | Yes | `"flux"`
`"sd3"`
`"sdxl"`
`"qwenimage"` | | `degrade_sigma` | The amount of degradation to apply. 0 means a clean latent. Increase this value to denoise corrupted latent outputs (default: 0.0). | FLOAT | Yes | 0.0 to 1.0 (step: 0.01) | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `CONDITIONING` | The original conditioning data with the latent and degrade sigma values attached. | CONDITIONING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PiDConditioning/en.md) --- -**Source fingerprint (SHA-256):** `7c8de543629c2299fc2c1e035e433dfc249af594773a77e65c69dde67eb104d7` +**Source fingerprint (SHA-256):** `5785e2edc3c49006bf6b9faa2f245ea5e0e0f3540306dba015a843b06a48ff92` diff --git a/built-in-nodes/PikaImageToVideoNode2_2.mdx b/built-in-nodes/PikaImageToVideoNode2_2.mdx index e16b5cec0..a26a84eed 100644 --- a/built-in-nodes/PikaImageToVideoNode2_2.mdx +++ b/built-in-nodes/PikaImageToVideoNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaImageToVideoNode2_2" icon: "circle" mode: wide --- + The Pika Image to Video node sends an image and text prompt to the Pika API version 2.2 to generate a video. It converts your input image into video format based on the provided description and settings. The node handles the API communication and returns the generated video as output. ## Inputs diff --git a/built-in-nodes/PikaScenesV2_2.mdx b/built-in-nodes/PikaScenesV2_2.mdx index 9581ad5d2..25cfde360 100644 --- a/built-in-nodes/PikaScenesV2_2.mdx +++ b/built-in-nodes/PikaScenesV2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaScenesV2_2" icon: "circle" mode: wide --- + The PikaScenes v2.2 node combines multiple images to create a video that incorporates objects from all the input images. You can upload up to five different images as ingredients and generate a high-quality video that blends them together seamlessly. ## Inputs diff --git a/built-in-nodes/PikaStartEndFrameNode2_2.mdx b/built-in-nodes/PikaStartEndFrameNode2_2.mdx index 3dbabd541..49368394e 100644 --- a/built-in-nodes/PikaStartEndFrameNode2_2.mdx +++ b/built-in-nodes/PikaStartEndFrameNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaStartEndFrameNode2_2" icon: "circle" mode: wide --- + The PikaFrames v2.2 Node generates a video by combining your first and last frame. You upload two images to define the start and end points, and the AI creates a smooth transition between them to produce a complete video. ## Inputs diff --git a/built-in-nodes/PikaTextToVideoNode2_2.mdx b/built-in-nodes/PikaTextToVideoNode2_2.mdx index 5d7e78837..51657167f 100644 --- a/built-in-nodes/PikaTextToVideoNode2_2.mdx +++ b/built-in-nodes/PikaTextToVideoNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaTextToVideoNode2_2" icon: "circle" mode: wide --- + The Pika Text2Video v2.2 Node sends a text prompt to the Pika API version 2.2 to generate a video. It converts your text description into a video using Pika's AI video generation service. The node allows you to customize various aspects of the video generation process including aspect ratio, duration, and resolution. ## Inputs diff --git a/built-in-nodes/Pikadditions.mdx b/built-in-nodes/Pikadditions.mdx index 2d6e41609..72277977f 100644 --- a/built-in-nodes/Pikadditions.mdx +++ b/built-in-nodes/Pikadditions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikadditions" icon: "circle" mode: wide --- + The Pikadditions node allows you to add any object or image into your video. You upload a video and specify what you'd like to add to create a seamlessly integrated result. This node uses the Pika API to insert images into videos with natural-looking integration. ## Inputs diff --git a/built-in-nodes/Pikaffects.mdx b/built-in-nodes/Pikaffects.mdx index d3db72cf4..c08fea7a4 100644 --- a/built-in-nodes/Pikaffects.mdx +++ b/built-in-nodes/Pikaffects.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikaffects" icon: "circle" mode: wide --- + The Pikaffects node generates videos with various visual effects applied to an input image. It uses Pika's video generation API to transform static images into animated videos with specific effects like melting, exploding, or levitating. The node requires an API key and authentication token to access the Pika service. ## Inputs diff --git a/built-in-nodes/Pikaswaps.mdx b/built-in-nodes/Pikaswaps.mdx index 59c43a53d..3dbb1be28 100644 --- a/built-in-nodes/Pikaswaps.mdx +++ b/built-in-nodes/Pikaswaps.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikaswaps" icon: "circle" mode: wide --- + The Pika Swaps node replaces objects or regions in your video with a new image. You define the areas to replace using a mask, and the node seamlessly swaps the specified content throughout the video sequence. ## Inputs diff --git a/built-in-nodes/PixverseImageToVideoNode.mdx b/built-in-nodes/PixverseImageToVideoNode.mdx index 6443b0a03..e87b0dde1 100644 --- a/built-in-nodes/PixverseImageToVideoNode.mdx +++ b/built-in-nodes/PixverseImageToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "PixverseImageToVideoNode" icon: "circle" mode: wide --- + Generates videos based on an input image and text prompt. This node takes an image and creates an animated video by applying the specified motion and quality settings to transform the static image into a moving sequence. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | Input image to transform into video | IMAGE | Yes | - | | `prompt` | Prompt for the video generation | STRING | Yes | - | | `quality` | Video quality setting (default: res_540p) | COMBO | Yes | `res_540p`
`res_1080p` | @@ -25,10 +26,10 @@ Generates videos based on an input image and text prompt. This node takes an ima ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | Generated video based on the input image and parameters | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseImageToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `4ca1624efc87e87de75c33aab850c84a0c8c786229930695fce479fe50455cb0` +**Source fingerprint (SHA-256):** `e95db00401aaa81959a93b2111b6395e3ff34baf55857dc3453a174328012a82` diff --git a/built-in-nodes/PixverseTemplateNode.mdx b/built-in-nodes/PixverseTemplateNode.mdx index c70a35bab..803fb72e8 100644 --- a/built-in-nodes/PixverseTemplateNode.mdx +++ b/built-in-nodes/PixverseTemplateNode.mdx @@ -5,21 +5,22 @@ sidebarTitle: "PixverseTemplateNode" icon: "circle" mode: wide --- + The PixVerse Template node allows you to select from available templates for PixVerse video generation. It converts your selected template name into the corresponding template ID that the PixVerse API requires for video creation. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `template` | The template to use for PixVerse video generation. The available options correspond to predefined templates in the PixVerse system. | STRING | Yes | Multiple options available | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `pixverse_template` | The template ID corresponding to the selected template name, which can be used by other PixVerse nodes for video generation. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTemplateNode/en.md) --- -**Source fingerprint (SHA-256):** `34daaf036f28b676b1048e8e4174ab34bf69328a94dd9e51696f6298936b4e84` +**Source fingerprint (SHA-256):** `618f9203127c55e8b65802fe3711c6d7c7dc6b631e9050f9685419c1b23bc138` diff --git a/built-in-nodes/PixverseTextToVideoNode.mdx b/built-in-nodes/PixverseTextToVideoNode.mdx index e30872b4d..fd48e93d6 100644 --- a/built-in-nodes/PixverseTextToVideoNode.mdx +++ b/built-in-nodes/PixverseTextToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "PixverseTextToVideoNode" icon: "circle" mode: wide --- + Generates videos based on a text prompt and various generation parameters. This node creates video content using the PixVerse API, allowing control over aspect ratio, quality, duration, motion style, and more. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the video generation (default: "") | STRING | Yes | - | | `aspect_ratio` | Aspect ratio for the generated video | COMBO | Yes | `"16:9"`
`"9:16"`
`"1:1"` | | `quality` | Video quality setting (default: "540p") | COMBO | Yes | `"540p"`
`"1080p"` | @@ -25,10 +26,10 @@ Generates videos based on a text prompt and various generation parameters. This ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `dd065e218e3e8ca3d70b58f4d8afdecc33094635663c87f79467452ca47881c7` +**Source fingerprint (SHA-256):** `9b0bf0d863243b5a9840c21c7f82caea32d30395a22290e323b63d86eabd0721` diff --git a/built-in-nodes/PixverseTransitionVideoNode.mdx b/built-in-nodes/PixverseTransitionVideoNode.mdx index 25734c702..5af3a9d28 100644 --- a/built-in-nodes/PixverseTransitionVideoNode.mdx +++ b/built-in-nodes/PixverseTransitionVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTransitionVideoNode" icon: "circle" mode: wide --- + Generates a transition video between two input images using the PixVerse API. You provide a starting image and an ending image, and the node creates a smooth video that transitions from one to the other, guided by your text prompt and chosen settings. ## Inputs @@ -31,4 +32,4 @@ Generates a transition video between two input images using the PixVerse API. Yo > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTransitionVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `941ba26ffdd5cc93d800066ccd75adc4ccdb9a1c9f93ae0ccd28a11ba5f3c567` +**Source fingerprint (SHA-256):** `dca56852dc24e6bc9f011888495952beed16b4dcc8995bb8d35e3b6a421933d9` diff --git a/built-in-nodes/PolyexponentialScheduler.mdx b/built-in-nodes/PolyexponentialScheduler.mdx index 245df9817..8c4a3fb67 100644 --- a/built-in-nodes/PolyexponentialScheduler.mdx +++ b/built-in-nodes/PolyexponentialScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PolyexponentialScheduler" icon: "circle" mode: wide --- + The PolyexponentialScheduler node is designed to generate a sequence of noise levels (sigmas) based on a polyexponential noise schedule. This schedule is a polynomial function in the logarithm of sigma, allowing for a flexible and customizable progression of noise levels throughout the diffusion process. ## Inputs diff --git a/built-in-nodes/PorterDuffImageComposite.mdx b/built-in-nodes/PorterDuffImageComposite.mdx index ae2a68d0d..56e444382 100644 --- a/built-in-nodes/PorterDuffImageComposite.mdx +++ b/built-in-nodes/PorterDuffImageComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PorterDuffImageComposite" icon: "circle" mode: wide --- + The PorterDuffImageComposite node is designed to perform image compositing using the Porter-Duff compositing operators. It allows for the combination of source and destination images according to various blending modes, enabling the creation of complex visual effects by manipulating image transparency and overlaying images in creative ways. ## Inputs diff --git a/built-in-nodes/Preview3D.mdx b/built-in-nodes/Preview3D.mdx index 2c34b3087..96c7893c8 100644 --- a/built-in-nodes/Preview3D.mdx +++ b/built-in-nodes/Preview3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Preview3D" icon: "circle" mode: wide --- + Preview3D node is mainly used to preview 3D model outputs. This node takes two inputs: one is the `camera_info` from the Load3D node, and the other is the path to the 3D model file. The model file path must be located in the `ComfyUI/output` folder. **Supported Formats** diff --git a/built-in-nodes/Preview3DAdvanced.mdx b/built-in-nodes/Preview3DAdvanced.mdx index 179b8f8a7..f0f6cd315 100644 --- a/built-in-nodes/Preview3DAdvanced.mdx +++ b/built-in-nodes/Preview3DAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Preview3DAdvanced" icon: "circle" mode: wide --- -# Preview 3D (Advanced) This node provides an advanced 3D model preview with camera and model information output. It saves the 3D model to a temporary file and displays it in the UI, while also passing through the model data, camera information, and viewport dimensions for further processing downstream. diff --git a/built-in-nodes/Preview3DAnimation.mdx b/built-in-nodes/Preview3DAnimation.mdx index 741a58fd2..978b7e957 100644 --- a/built-in-nodes/Preview3DAnimation.mdx +++ b/built-in-nodes/Preview3DAnimation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Preview3DAnimation" icon: "circle" mode: wide --- + Preview3DAnimation node is mainly used to preview 3D model outputs. This node takes two inputs: one is the `camera_info` from the Load3D node, and the other is the path to the 3D model file. The model file path must be located in the `ComfyUI/output` folder. **Supported Formats** diff --git a/built-in-nodes/PreviewAny.mdx b/built-in-nodes/PreviewAny.mdx index 15e1a661b..28e756e33 100644 --- a/built-in-nodes/PreviewAny.mdx +++ b/built-in-nodes/PreviewAny.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewAny" icon: "circle" mode: wide --- + The PreviewAny node displays a preview of any input data type in text format. It accepts any data type as input and converts it to a readable string representation for viewing. The node automatically handles different data types including strings, numbers, booleans, and complex objects by attempting to serialize them to JSON format. ## Inputs diff --git a/built-in-nodes/PreviewAudio.mdx b/built-in-nodes/PreviewAudio.mdx index 0b0739962..df9951001 100644 --- a/built-in-nodes/PreviewAudio.mdx +++ b/built-in-nodes/PreviewAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewAudio" icon: "circle" mode: wide --- + The PreviewAudio node creates a temporary audio preview that can be played directly in the interface. It takes audio data as input and generates a preview widget, allowing users to listen to audio outputs without saving permanent files. ## Inputs diff --git a/built-in-nodes/PreviewGaussianSplat.mdx b/built-in-nodes/PreviewGaussianSplat.mdx index 59fffef36..269641064 100644 --- a/built-in-nodes/PreviewGaussianSplat.mdx +++ b/built-in-nodes/PreviewGaussianSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PreviewGaussianSplat" icon: "circle" mode: wide --- -# PreviewGaussianSplat The PreviewGaussianSplat node allows you to preview a 3D gaussian splat file within the ComfyUI interface. It accepts a 3D model file in various gaussian splat formats and renders it in a 3D preview window, passing through the model data for further processing. diff --git a/built-in-nodes/PreviewImage.mdx b/built-in-nodes/PreviewImage.mdx index 7997240e5..16cca7eea 100644 --- a/built-in-nodes/PreviewImage.mdx +++ b/built-in-nodes/PreviewImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewImage" icon: "circle" mode: wide --- + The PreviewImage node is designed for creating temporary preview images. It automatically generates a unique temporary file name for each image, compresses the image to a specified level, and saves it to a temporary directory. This functionality is particularly useful for generating previews of images during processing without affecting the original files. ## Inputs diff --git a/built-in-nodes/PreviewPointCloud.mdx b/built-in-nodes/PreviewPointCloud.mdx index 13c60e9cf..4cff874b6 100644 --- a/built-in-nodes/PreviewPointCloud.mdx +++ b/built-in-nodes/PreviewPointCloud.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PreviewPointCloud" icon: "circle" mode: wide --- -# Preview Point Cloud The Preview Point Cloud node allows you to view a 3D point cloud file within the ComfyUI interface. It saves the point cloud to a temporary file and displays it in a 3D preview window, passing through the model data and viewport settings for further processing. diff --git a/built-in-nodes/PrimitiveBoolean.mdx b/built-in-nodes/PrimitiveBoolean.mdx index dc8f9db2f..f902007b3 100644 --- a/built-in-nodes/PrimitiveBoolean.mdx +++ b/built-in-nodes/PrimitiveBoolean.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveBoolean" icon: "circle" mode: wide --- + The Boolean node provides a simple way to pass boolean (true/false) values through your workflow. It takes a boolean input value and outputs the same value unchanged, allowing you to control boolean parameters in other nodes. ## Inputs diff --git a/built-in-nodes/PrimitiveBoundingBox.mdx b/built-in-nodes/PrimitiveBoundingBox.mdx index 8df0abb6e..1b8261ffd 100644 --- a/built-in-nodes/PrimitiveBoundingBox.mdx +++ b/built-in-nodes/PrimitiveBoundingBox.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveBoundingBox" icon: "circle" mode: wide --- + The PrimitiveBoundingBox node creates a simple rectangular area defined by its position and size. It takes X and Y coordinates for the top-left corner, along with width and height values, and outputs a bounding box data structure that can be used by other nodes in a workflow. ## Inputs diff --git a/built-in-nodes/PrimitiveFloat.mdx b/built-in-nodes/PrimitiveFloat.mdx index 7fd5fc2a2..e0408ecbc 100644 --- a/built-in-nodes/PrimitiveFloat.mdx +++ b/built-in-nodes/PrimitiveFloat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveFloat" icon: "circle" mode: wide --- + The PrimitiveFloat node creates a floating-point number value that can be used in your workflow. It takes a single numeric input and outputs that same value, allowing you to define and pass float values between different nodes in your ComfyUI pipeline. ## Inputs diff --git a/built-in-nodes/PrimitiveInt.mdx b/built-in-nodes/PrimitiveInt.mdx index 14b432194..e6bab1f57 100644 --- a/built-in-nodes/PrimitiveInt.mdx +++ b/built-in-nodes/PrimitiveInt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveInt" icon: "circle" mode: wide --- + The PrimitiveInt node provides a simple way to work with integer values in your workflow. It takes an integer input and outputs the same value, making it useful for passing integer parameters between nodes or setting specific numeric values for other operations. ## Inputs diff --git a/built-in-nodes/PrimitiveString.mdx b/built-in-nodes/PrimitiveString.mdx index ebe3f0974..737247b06 100644 --- a/built-in-nodes/PrimitiveString.mdx +++ b/built-in-nodes/PrimitiveString.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveString" icon: "circle" mode: wide --- + The String node provides a simple way to input and pass through text data in your workflow. It takes a text string as input and outputs the same string unchanged, making it useful for providing text inputs to other nodes that require string parameters. ## Inputs diff --git a/built-in-nodes/PrimitiveStringMultiline.mdx b/built-in-nodes/PrimitiveStringMultiline.mdx index 1b5b45221..791ce07e9 100644 --- a/built-in-nodes/PrimitiveStringMultiline.mdx +++ b/built-in-nodes/PrimitiveStringMultiline.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveStringMultiline" icon: "circle" mode: wide --- + The PrimitiveStringMultiline node provides a multiline text input field for entering and passing string values through your workflow. It accepts text input with multiple lines and outputs the same string value unchanged. This node is useful when you need to input longer text content or formatted text that spans multiple lines. ## Inputs diff --git a/built-in-nodes/QuadrupleCLIPLoader.mdx b/built-in-nodes/QuadrupleCLIPLoader.mdx index fe48df587..252c46f32 100644 --- a/built-in-nodes/QuadrupleCLIPLoader.mdx +++ b/built-in-nodes/QuadrupleCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QuadrupleCLIPLoader" icon: "circle" mode: wide --- + The Quadruple CLIP Loader, QuadrupleCLIPLoader, is one of the core nodes of ComfyUI, first added to support the HiDream I1 version model. If you find this node missing, try updating ComfyUI to the latest version to ensure node support. It requires 4 CLIP models, corresponding to the parameters `clip_name1`, `clip_name2`, `clip_name3`, and `clip_name4`, and will provide a CLIP model output for subsequent nodes. diff --git a/built-in-nodes/QuiverImageToSVGNode.mdx b/built-in-nodes/QuiverImageToSVGNode.mdx index e403742d0..ca7bb9f99 100644 --- a/built-in-nodes/QuiverImageToSVGNode.mdx +++ b/built-in-nodes/QuiverImageToSVGNode.mdx @@ -5,24 +5,25 @@ sidebarTitle: "QuiverImageToSVGNode" icon: "circle" mode: wide --- + This node converts a raster image into a scalable vector graphic (SVG) using Quiver AI's vectorization models. It sends the image to an external API which processes it and returns the vectorized result. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | Input image to vectorize. | IMAGE | Yes | N/A | -| `auto_crop` | Automatically crop to the dominant subject. This is an advanced parameter (default: `False`). | BOOLEAN | No | `True`
`False` | +| `auto_crop` | Automatically crop to the dominant subject (default: False). | BOOLEAN | No | True
False | | `model` | Model to use for SVG vectorization. Selecting a model reveals additional parameters specific to that model: `target_size` (square resize target in pixels, default: 1024, range: 128-4096), `temperature`, `top_p`, and `presence_penalty`. | DYNAMICCOMBO | Yes | Multiple options available | | `seed` | Seed to determine if the node should re-run; the actual results are nondeterministic regardless of the seed value. This parameter has "control after generate" functionality (default: 0). | INT | No | 0 to 2147483647 | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `SVG` | The vectorized SVG output. | SVG | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/QuiverImageToSVGNode/en.md) --- -**Source fingerprint (SHA-256):** `f2e411bd3ed235d04a94cb3e5c26990eb30404c3329e9c91e705d3039d2d8089` +**Source fingerprint (SHA-256):** `178655d7b92a5b6823eefc2e75952fc8a12128da68786ba60bcfca1c7b464147` diff --git a/built-in-nodes/QuiverTextToSVGNode.mdx b/built-in-nodes/QuiverTextToSVGNode.mdx index 7cc6ce9fa..945ffe325 100644 --- a/built-in-nodes/QuiverTextToSVGNode.mdx +++ b/built-in-nodes/QuiverTextToSVGNode.mdx @@ -5,16 +5,17 @@ sidebarTitle: "QuiverTextToSVGNode" icon: "circle" mode: wide --- + The Quiver Text to SVG node generates a Scalable Vector Graphic (SVG) image from a text description using Quiver AI's models. You can optionally provide reference images and style instructions to guide the generation process. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text description of the desired SVG output. This is the main instruction for what to generate. | STRING | Yes | N/A | | `instructions` | Additional style or formatting guidance. This is an optional, advanced parameter. | STRING | No | N/A | | `reference_images` | Up to 4 reference images to guide the generation. This is an optional input. | IMAGE | No | 0 to 4 images | -| `model` | Model to use for SVG generation. The available options are determined by the Quiver API. | COMBO | Yes | `"Quiver SVG v1"`
`"Quiver SVG v1 Max"`
`"Quiver SVG v1 Preview"` | +| `model` | Model to use for SVG generation. | COMBO | Yes | `"Quiver SVG v1"`
`"Quiver SVG v1 Max"`
`"Quiver SVG v1 Preview"` | | `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. Default: 0. | INT | Yes | 0 to 2147483647 | **Note:** The `reference_images` input accepts a maximum of 4 images. If more are provided, the node will raise an error. @@ -22,10 +23,10 @@ The Quiver Text to SVG node generates a Scalable Vector Graphic (SVG) image from ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `SVG` | The generated Scalable Vector Graphic (SVG) image. | SVG | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/QuiverTextToSVGNode/en.md) --- -**Source fingerprint (SHA-256):** `dd5edd1be1c3cfd4b651896a1b020da7005f72097e0dcf09b947be0b771b8756` +**Source fingerprint (SHA-256):** `68401d15367a78fa9349a72c18572994ae1615983ddfe04b4f744695057f2a94` diff --git a/built-in-nodes/QwenImageDiffsynthControlnet.mdx b/built-in-nodes/QwenImageDiffsynthControlnet.mdx index 8d76ea88d..d14774241 100644 --- a/built-in-nodes/QwenImageDiffsynthControlnet.mdx +++ b/built-in-nodes/QwenImageDiffsynthControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QwenImageDiffsynthControlnet" icon: "circle" mode: wide --- + The QwenImageDiffsynthControlnet node applies a diffusion synthesis control network patch to modify a base model's behavior. It uses an image input and optional mask to guide the model's generation process with adjustable strength, creating a patched model that incorporates the control network's influence for more controlled image synthesis. ## Inputs diff --git a/built-in-nodes/RTDETR_detect.mdx b/built-in-nodes/RTDETR_detect.mdx index b3a506068..da1054142 100644 --- a/built-in-nodes/RTDETR_detect.mdx +++ b/built-in-nodes/RTDETR_detect.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RTDETR_detect" icon: "circle" mode: wide --- + The RT-DETR Detect node performs object detection on input images using an RT-DETR model. It identifies objects, draws bounding boxes around them, and labels them according to the COCO dataset classes. You can filter the results by confidence score, object class, and limit the total number of detections. ## Inputs diff --git a/built-in-nodes/RandomCropImages.mdx b/built-in-nodes/RandomCropImages.mdx index 7bdb23f6f..f7d1b5c05 100644 --- a/built-in-nodes/RandomCropImages.mdx +++ b/built-in-nodes/RandomCropImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RandomCropImages" icon: "circle" mode: wide --- + The Random Crop Images node randomly selects a rectangular section from each input image and crops it to a specified width and height. This is commonly used for data augmentation to create variations of training images. The random position for the crop is determined by a seed value, ensuring the same crop can be reproduced. ## Inputs diff --git a/built-in-nodes/RandomNoise.mdx b/built-in-nodes/RandomNoise.mdx index 7291bcaf1..7d9c1c3bb 100644 --- a/built-in-nodes/RandomNoise.mdx +++ b/built-in-nodes/RandomNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RandomNoise" icon: "circle" mode: wide --- + The RandomNoise node generates random noise patterns based on a seed value. It creates reproducible noise that can be used for various image processing and generation tasks. The same seed will always produce the same noise pattern, allowing for consistent results across multiple runs. ## Inputs diff --git a/built-in-nodes/RebatchImages.mdx b/built-in-nodes/RebatchImages.mdx index 48afe6b23..2be825bb3 100644 --- a/built-in-nodes/RebatchImages.mdx +++ b/built-in-nodes/RebatchImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RebatchImages" icon: "circle" mode: wide --- + The RebatchImages node is designed to reorganize a batch of images into a new batch configuration, adjusting the batch size as specified. This process is essential for managing and optimizing the processing of image data in batch operations, ensuring that images are grouped according to the desired batch size for efficient handling. ## Inputs diff --git a/built-in-nodes/RebatchLatents.mdx b/built-in-nodes/RebatchLatents.mdx index 3fa48c2c0..949b733b6 100644 --- a/built-in-nodes/RebatchLatents.mdx +++ b/built-in-nodes/RebatchLatents.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RebatchLatents" icon: "circle" mode: wide --- + The RebatchLatents node is designed to reorganize a batch of latent representations into a new batch configuration, based on a specified batch size. It ensures that the latent samples are grouped appropriately, handling variations in dimensions and sizes, to facilitate further processing or model inference. ## Inputs diff --git a/built-in-nodes/RecordAudio.mdx b/built-in-nodes/RecordAudio.mdx index 4e15c741b..637969a97 100644 --- a/built-in-nodes/RecordAudio.mdx +++ b/built-in-nodes/RecordAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecordAudio" icon: "circle" mode: wide --- + The RecordAudio node loads audio files that have been recorded or selected through the audio recording interface. It processes the audio file and converts it into a waveform format that can be used by other audio processing nodes in the workflow. The node automatically detects the sample rate and prepares the audio data for further manipulation. ## Inputs diff --git a/built-in-nodes/RecraftColorRGB.mdx b/built-in-nodes/RecraftColorRGB.mdx index c3bf71c19..cf94ef073 100644 --- a/built-in-nodes/RecraftColorRGB.mdx +++ b/built-in-nodes/RecraftColorRGB.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftColorRGB" icon: "circle" mode: wide --- + Create a Recraft color by specifying individual red, green, and blue values. This node takes RGB integer values (0-255) and converts them into a Recraft color format that can be used in other Recraft operations. You can also optionally provide an existing Recraft color chain to extend it with the new color. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `r` | Red value of color (default: 0) | INT | Yes | 0-255 | | `g` | Green value of color (default: 0) | INT | Yes | 0-255 | | `b` | Blue value of color (default: 0) | INT | Yes | 0-255 | @@ -19,10 +20,10 @@ Create a Recraft color by specifying individual red, green, and blue values. Thi ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `recraft_color` | The created Recraft color object containing the specified RGB values, or the extended color chain if an existing one was provided | COLOR | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftColorRGB/en.md) --- -**Source fingerprint (SHA-256):** `3c645f17232a1c646b6b64dab658a48dc4aa4c10c2daee9451977f824c3bf2c2` +**Source fingerprint (SHA-256):** `2246d266bc36d1aa7f115402b049f895f2b15d0085b84d1b0a813cdfb1b6e2fc` diff --git a/built-in-nodes/RecraftControls.mdx b/built-in-nodes/RecraftControls.mdx index c047d48ff..fe12863f4 100644 --- a/built-in-nodes/RecraftControls.mdx +++ b/built-in-nodes/RecraftControls.mdx @@ -5,22 +5,23 @@ sidebarTitle: "RecraftControls" icon: "circle" mode: wide --- + Creates Recraft Controls for customizing Recraft generation. This node allows you to configure color settings that will be used during the Recraft image generation process. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `colors` | Color settings for the main elements | COLOR | No | - | | `background_color` | Background color setting | COLOR | No | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `recraft_controls` | The configured Recraft controls containing color settings | CONTROLS | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftControls/en.md) --- -**Source fingerprint (SHA-256):** `3d07c8ca226e19849ebe5d37d93f129c77930a6971e58fe73abc2a47a58ee42e` +**Source fingerprint (SHA-256):** `d6237821472e5305303c25119601b1c8eb5781d3e1aee4f6b3b80060a4fdc8cf` diff --git a/built-in-nodes/RecraftCreateStyleNode.mdx b/built-in-nodes/RecraftCreateStyleNode.mdx index fd28926cf..94b8ce40f 100644 --- a/built-in-nodes/RecraftCreateStyleNode.mdx +++ b/built-in-nodes/RecraftCreateStyleNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftCreateStyleNode" icon: "circle" mode: wide --- + This node creates a custom style for image generation by uploading reference images. You can upload between 1 and 5 images to define the new style, and the node will return a unique style ID that can be used with other Recraft nodes. The total combined file size of all uploaded images must not exceed 5 MB. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `style` | The base style of the generated images. | STRING | Yes | `"realistic_image"`
`"digital_illustration"` | | `images` | A set of 1 to 5 reference images used to create the custom style. | IMAGE | Yes | 1 to 5 images | @@ -19,10 +20,10 @@ This node creates a custom style for image generation by uploading reference ima ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `style_id` | The unique identifier for the newly created custom style. | STRING | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreateStyleNode/en.md) --- -**Source fingerprint (SHA-256):** `9f6d6f87621b72fcbf19200e7b2461c9a22160311c77411e9ddd06ee2053dc63` +**Source fingerprint (SHA-256):** `36edcb0b96eed5930d9d7ff00a1812d129b7cd9b7ab0f0d758594a20791826b2` diff --git a/built-in-nodes/RecraftCreativeUpscaleNode.mdx b/built-in-nodes/RecraftCreativeUpscaleNode.mdx index 96e4cbe6c..df8014b1e 100644 --- a/built-in-nodes/RecraftCreativeUpscaleNode.mdx +++ b/built-in-nodes/RecraftCreativeUpscaleNode.mdx @@ -5,21 +5,22 @@ sidebarTitle: "RecraftCreativeUpscaleNode" icon: "circle" mode: wide --- + The Recraft Creative Upscale Image node enhances a raster image by increasing its resolution. It uses a "creative upscale" process that focuses on improving small details and faces within the image. This operation is performed synchronously through an external API. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `image` | The input image to be upscaled. | IMAGE | Yes | | +|-----------|-------------|-----------|----------|-------| +| `image` | The input image to be upscaled. | IMAGE | Yes | | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The resulting upscaled image with enhanced details. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreativeUpscaleNode/en.md) --- -**Source fingerprint (SHA-256):** `1dc5cd9d6f0c5a269d20ad94e417d31abc20c4ef8dd673f926ab4aceb2b6d924` +**Source fingerprint (SHA-256):** `52e19f6dfb3846cdea2b150f3008fa49c98bc5fced94ffb362846d3a5fba57df` diff --git a/built-in-nodes/RecraftCrispUpscaleNode.mdx b/built-in-nodes/RecraftCrispUpscaleNode.mdx index a044863f5..cb4f36d92 100644 --- a/built-in-nodes/RecraftCrispUpscaleNode.mdx +++ b/built-in-nodes/RecraftCrispUpscaleNode.mdx @@ -5,21 +5,22 @@ sidebarTitle: "RecraftCrispUpscaleNode" icon: "circle" mode: wide --- + Upscale image synchronously. Enhances a given raster image using the 'crisp upscale' tool, increasing image resolution, making the image sharper and cleaner. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be upscaled. Accepts a batch of images. | IMAGE | Yes | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The upscaled image with enhanced resolution and clarity. Returns a batch of images if a batch was provided as input. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCrispUpscaleNode/en.md) --- -**Source fingerprint (SHA-256):** `4683d62ca72ce624ad96b41e4abbbcf3df8c8e11f473f1729a675fba78a9ccc0` +**Source fingerprint (SHA-256):** `0a5efef73c86ef24825055af39601576e4ae465e641783b524d347325a5c5982` diff --git a/built-in-nodes/RecraftImageInpaintingNode.mdx b/built-in-nodes/RecraftImageInpaintingNode.mdx index 2f6bed322..11b0151f7 100644 --- a/built-in-nodes/RecraftImageInpaintingNode.mdx +++ b/built-in-nodes/RecraftImageInpaintingNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftImageInpaintingNode" icon: "circle" mode: wide --- + This node modifies specific areas of an image based on a text prompt and a mask. It uses the Recraft API to intelligently edit only the masked regions while keeping the rest of the image unchanged. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be modified | IMAGE | Yes | - | | `mask` | The mask defining which areas of the image should be modified | MASK | Yes | - | | `prompt` | Prompt for the image generation (default: empty string, maximum length: 1000 characters) | STRING | Yes | - | @@ -24,10 +25,10 @@ This node modifies specific areas of an image based on a text prompt and a mask. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The modified image(s) generated based on the prompt and mask. Returns one image per input image multiplied by the `n` parameter | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageInpaintingNode/en.md) --- -**Source fingerprint (SHA-256):** `c0871ae6510d42f5525701dd622f2f84a65103a7eec053635c4bd64102a2a4e6` +**Source fingerprint (SHA-256):** `64493a418224f4a01c6b6511581d31f92189852a32b41d9748629e57782bd511` diff --git a/built-in-nodes/RecraftImageToImageNode.mdx b/built-in-nodes/RecraftImageToImageNode.mdx index 38482a8b9..2f2ca3b3f 100644 --- a/built-in-nodes/RecraftImageToImageNode.mdx +++ b/built-in-nodes/RecraftImageToImageNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftImageToImageNode" icon: "circle" mode: wide --- + This node modifies an existing image based on a text prompt and strength parameter. It uses the Recraft API to transform the input image according to the provided description while maintaining some similarity to the original image based on the strength setting. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be modified | IMAGE | Yes | - | | `prompt` | Prompt for the image generation (default: "", max length: 1000 characters) | STRING | Yes | - | | `n` | The number of images to generate (default: 1) | INT | Yes | 1-6 | @@ -25,10 +26,10 @@ This node modifies an existing image based on a text prompt and strength paramet ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The generated image(s) based on the input image and prompt | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageToImageNode/en.md) --- -**Source fingerprint (SHA-256):** `15f0f42a1c217abcffeff3836ec77d8a94b37143fdff45d69e1a645f5ffac939` +**Source fingerprint (SHA-256):** `5e5b675c5122fd4b3c754590b18d4cdf2ec995b4d14c1b9150050599071b38bb` diff --git a/built-in-nodes/RecraftRemoveBackgroundNode.mdx b/built-in-nodes/RecraftRemoveBackgroundNode.mdx index f526f63b9..9292cb300 100644 --- a/built-in-nodes/RecraftRemoveBackgroundNode.mdx +++ b/built-in-nodes/RecraftRemoveBackgroundNode.mdx @@ -5,22 +5,23 @@ sidebarTitle: "RecraftRemoveBackgroundNode" icon: "circle" mode: wide --- + This node removes the background from images using the Recraft API service. It processes each image in the input batch and returns both the processed images with transparent backgrounds and corresponding alpha masks that indicate the removed background areas. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image(s) to process for background removal | IMAGE | Yes | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | Processed images with transparent backgrounds | IMAGE | | `mask` | Alpha channel masks indicating the removed background areas | MASK | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftRemoveBackgroundNode/en.md) --- -**Source fingerprint (SHA-256):** `8bced9bb96c179101a2122fb5990cb3015313ad6ca888adf7a37b082b2e8a656` +**Source fingerprint (SHA-256):** `b71006e6b276329c2652483a06ac57ab817135a9d2d2625a971bef9dcb870d5c` diff --git a/built-in-nodes/RecraftReplaceBackgroundNode.mdx b/built-in-nodes/RecraftReplaceBackgroundNode.mdx index 32fed5008..608b27177 100644 --- a/built-in-nodes/RecraftReplaceBackgroundNode.mdx +++ b/built-in-nodes/RecraftReplaceBackgroundNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftReplaceBackgroundNode" icon: "circle" mode: wide --- + Replace background on image, based on provided prompt. This node uses the Recraft API to generate new backgrounds for your images according to your text description, allowing you to completely transform the background while keeping the main subject intact. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to process | IMAGE | Yes | - | | `prompt` | Prompt for the image generation (default: empty) | STRING | Yes | - | | `n` | The number of images to generate (default: 1) | INT | Yes | 1-6 | @@ -23,10 +24,10 @@ Replace background on image, based on provided prompt. This node uses the Recraf ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | The generated image(s) with replaced background | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftReplaceBackgroundNode/en.md) --- -**Source fingerprint (SHA-256):** `ce14005093aaac30de3de84c43bd46c0a3327d0ba8de4ea7ec62afa2028c1cae` +**Source fingerprint (SHA-256):** `3b97298469f0b116da260f444df4d1c174e04720938e3701f964a4aefda2213b` diff --git a/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx b/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx index d77243a95..50dcc1b41 100644 --- a/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx +++ b/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx @@ -5,21 +5,22 @@ sidebarTitle: "RecraftStyleV3DigitalIllustration" icon: "circle" mode: wide --- + This node configures a style for use with the Recraft API, specifically selecting the "digital_illustration" style. It allows you to choose an optional substyle to further refine the artistic direction of the generated image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `substyle` | An optional substyle to specify a particular type of digital illustration. If not selected, the base "digital_illustration" style is used. | STRING | No | `"digital_illustration"`
`"digital_illustration_anime"`
`"digital_illustration_cartoon"`
`"digital_illustration_comic"`
`"digital_illustration_concept_art"`
`"digital_illustration_fantasy"`
`"digital_illustration_futuristic"`
`"digital_illustration_graffiti"`
`"digital_illustration_graphic_novel"`
`"digital_illustration_hyperrealistic"`
`"digital_illustration_ink"`
`"digital_illustration_manga"`
`"digital_illustration_minimalist"`
`"digital_illustration_pixel_art"`
`"digital_illustration_pop_art"`
`"digital_illustration_retro"`
`"digital_illustration_sci_fi"`
`"digital_illustration_sticker"`
`"digital_illustration_street_art"`
`"digital_illustration_surreal"`
`"digital_illustration_vector"` | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `recraft_style` | A configured style object containing the selected "digital_illustration" style and optional substyle, ready to be passed to other Recraft API nodes. | STYLEV3 | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3DigitalIllustration/en.md) --- -**Source fingerprint (SHA-256):** `167b5f875e1d9ec39dd830d98349fe34b23a3ac870cff8329bc834fe13a5fc8f` +**Source fingerprint (SHA-256):** `b6901d81bc11c3226d847ed61386b9bcf4ece90f6a95b6ad9888f102ef355594` diff --git a/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx b/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx index b7e1879bb..fcea00b56 100644 --- a/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx +++ b/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftStyleV3InfiniteStyleLibrary" icon: "circle" mode: wide --- + This node allows you to select a style from Recraft's Infinite Style Library using a preexisting UUID. It retrieves the style information based on the provided style identifier and returns it for use in other Recraft nodes. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `style_id` | UUID of style from Infinite Style Library. | STRING | Yes | Any valid UUID | **Note:** The `style_id` input cannot be empty. If an empty string is provided, the node will raise an exception. @@ -18,10 +19,10 @@ This node allows you to select a style from Recraft's Infinite Style Library usi ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `recraft_style` | The selected style object from Recraft's Infinite Style Library | STYLEV3 | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3InfiniteStyleLibrary/en.md) --- -**Source fingerprint (SHA-256):** `c613e153fa56f403367f132a2592b853327a28cc640faab061dfe373b0202e21` +**Source fingerprint (SHA-256):** `4554acaaba9e83373d6fb44ea5465175182efcf7c9220c2328c4749c2febd40f` diff --git a/built-in-nodes/RecraftStyleV3LogoRaster.mdx b/built-in-nodes/RecraftStyleV3LogoRaster.mdx index 7dd23f256..3c8f56010 100644 --- a/built-in-nodes/RecraftStyleV3LogoRaster.mdx +++ b/built-in-nodes/RecraftStyleV3LogoRaster.mdx @@ -5,21 +5,22 @@ sidebarTitle: "RecraftStyleV3LogoRaster" icon: "circle" mode: wide --- + This node selects the logo raster style and an optional substyle for generating logo images. It specializes in creating logo designs with raster-based visual treatments. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `substyle` | The specific logo raster substyle to apply for logo generation (default: `"none"`) | STRING | Yes | `"none"`
`"bold"`
`"minimal"`
`"vibrant"`
`"handdrawn"`
`"geometric"`
`"vintage"`
`"neon"`
`"gradient"`
`"flat"`
`"outline"`
`"mascot"`
`"badge"`
`"abstract"`
`"retro"`
`"modern"`
`"playful"`
`"luxury"`
`"tech"`
`"nature"`
`"food"`
`"sport"`
`"fashion"`
`"music"`
`"travel"`
`"education"`
`"health"`
`"finance"`
`"realestate"`
`"nonprofit"` | +|-----------|-------------|-----------|----------|-------| +| `substyle` | The specific logo raster substyle to apply for logo generation | STRING | Yes | `"bold"`
`"minimal"`
`"vibrant"`
`"handdrawn"`
`"geometric"`
`"vintage"`
`"neon"`
`"gradient"`
`"flat"`
`"outline"`
`"mascot"`
`"badge"`
`"abstract"`
`"retro"`
`"modern"`
`"playful"`
`"luxury"`
`"tech"`
`"nature"`
`"food"`
`"sport"`
`"fashion"`
`"music"`
`"travel"`
`"education"`
`"health"`
`"finance"`
`"realestate"`
`"nonprofit"` | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `recraft_style` | The selected Recraft style configuration, including the logo raster style and chosen substyle | CUSTOM | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3LogoRaster/en.md) --- -**Source fingerprint (SHA-256):** `a9912e3a9f634cf3e4402cc71e934a636a448ecbfa7664f5167289d4526e4d4f` +**Source fingerprint (SHA-256):** `f3eedb43237c1b594ff5a2127f4ed67c9d700c1d26e7615350e7876003b0d577` diff --git a/built-in-nodes/RecraftStyleV3RealisticImage.mdx b/built-in-nodes/RecraftStyleV3RealisticImage.mdx index 34710ef4f..3b1df98cc 100644 --- a/built-in-nodes/RecraftStyleV3RealisticImage.mdx +++ b/built-in-nodes/RecraftStyleV3RealisticImage.mdx @@ -5,21 +5,22 @@ sidebarTitle: "RecraftStyleV3RealisticImage" icon: "circle" mode: wide --- + This node creates a style configuration for generating realistic images using Recraft's API. It selects the `realistic_image` style and lets you choose an optional substyle to fine-tune the output appearance. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `substyle` | The specific substyle to apply to the realistic_image style. If set to "None", no substyle will be applied. | STRING | Yes | Multiple options available (determined by Recraft API) | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `recraft_style` | A Recraft style configuration object containing the `realistic_image` style and the selected substyle settings. This output can be connected to other Recraft nodes that accept a style input. | STYLEV3 | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3RealisticImage/en.md) --- -**Source fingerprint (SHA-256):** `967e52e32456299da342a3d87f46f180f17aa1505cb2a3d22ee5f50cda79e8e3` +**Source fingerprint (SHA-256):** `df3a09ae0956dd5807b7475248359085fdbe5abb5c40291e37db3ceabafef2ac` diff --git a/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx b/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx index a2b0700fb..e7ae5042b 100644 --- a/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx +++ b/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx @@ -5,21 +5,22 @@ sidebarTitle: "RecraftStyleV3VectorIllustrationNode" icon: "circle" mode: wide --- + This node configures a style for use with the Recraft API, specifically selecting the `vector_illustration` style. It allows you to optionally choose a more specific substyle within that category. The node outputs a style configuration object that can be passed to other Recraft API nodes. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `substyle` | An optional, more specific style within the `vector_illustration` category. If not selected, the base `vector_illustration` style is used. | STRING | No | `"vector_illustration"`
`"vector_illustration_flat"`
`"vector_illustration_3d"`
`"vector_illustration_hand_drawn"`
`"vector_illustration_retro"`
`"vector_illustration_modern"`
`"vector_illustration_abstract"`
`"vector_illustration_geometric"`
`"vector_illustration_organic"`
`"vector_illustration_minimalist"`
`"vector_illustration_detailed"`
`"vector_illustration_colorful"`
`"vector_illustration_monochrome"`
`"vector_illustration_grayscale"`
`"vector_illustration_pastel"`
`"vector_illustration_vibrant"`
`"vector_illustration_muted"`
`"vector_illustration_warm"`
`"vector_illustration_cool"`
`"vector_illustration_neutral"`
`"vector_illustration_bold"`
`"vector_illustration_subtle"`
`"vector_illustration_playful"`
`"vector_illustration_serious"`
`"vector_illustration_elegant"`
`"vector_illustration_rustic"`
`"vector_illustration_urban"`
`"vector_illustration_nature"`
`"vector_illustration_fantasy"`
`"vector_illustration_sci_fi"`
`"vector_illustration_historical"`
`"vector_illustration_futuristic"`
`"vector_illustration_whimsical"`
`"vector_illustration_surreal"`
`"vector_illustration_realistic"`
`"vector_illustration_stylized"`
`"vector_illustration_cartoony"`
`"vector_illustration_anime"`
`"vector_illustration_comic"`
`"vector_illustration_pixel"`
`"vector_illustration_low_poly"`
`"vector_illustration_high_poly"`
`"vector_illustration_isometric"`
`"vector_illustration_orthographic"`
`"vector_illustration_perspective"`
`"vector_illustration_2d"`
`"vector_illustration_2.5d"`
`"vector_illustration_3d"`
`"vector_illustration_4d"` | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `recraft_style` | A Recraft API style configuration object containing the selected `vector_illustration` style and optional substyle. This can be connected to other Recraft nodes. | STYLEV3 | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3VectorIllustrationNode/en.md) --- -**Source fingerprint (SHA-256):** `c57ffa5504fff8430f8193f97d4d991b9373e688a4b412ff4926ef356aef0dc9` +**Source fingerprint (SHA-256):** `4aa9946fc9918d2a16eafe21f9b77cdada35ca8a12010fc6f1adb8f46f41cad0` diff --git a/built-in-nodes/RecraftTextToImageNode.mdx b/built-in-nodes/RecraftTextToImageNode.mdx index bd87eb7c2..1babbac4b 100644 --- a/built-in-nodes/RecraftTextToImageNode.mdx +++ b/built-in-nodes/RecraftTextToImageNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftTextToImageNode" icon: "circle" mode: wide --- + Generates images synchronously based on prompt and resolution. This node connects to the Recraft API to create images from text descriptions with specified dimensions and optional style and control parameters. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation. (default: "") | STRING | Yes | - | | `size` | The size of the generated image. (default: "1024x1024") | COMBO | Yes | "1024x1024"
"1152x896"
"896x1152"
"1216x832"
"832x1216"
"1344x768"
"768x1344"
"1536x640"
"640x1536" | | `n` | The number of images to generate. (default: 1) | INT | Yes | 1-6 | @@ -28,10 +29,10 @@ Generates images synchronously based on prompt and resolution. This node connect ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `IMAGE` | The generated image(s) as a batched tensor output. When multiple images are generated (n > 1), they are concatenated along the batch dimension. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftTextToImageNode/en.md) --- -**Source fingerprint (SHA-256):** `946010fbb6a5b99eed11e74de0733f64a270fa62910acf942749c76e0b5448f3` +**Source fingerprint (SHA-256):** `9e9607f6c122a5560680302287b677a4aced626443bc782641177a4ecdaef65a` diff --git a/built-in-nodes/RecraftTextToVectorNode.mdx b/built-in-nodes/RecraftTextToVectorNode.mdx index f463c36a9..9297995f4 100644 --- a/built-in-nodes/RecraftTextToVectorNode.mdx +++ b/built-in-nodes/RecraftTextToVectorNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftTextToVectorNode" icon: "circle" mode: wide --- + Generates SVG vector illustrations synchronously based on a text prompt and resolution. This node sends your prompt to the Recraft API and returns the generated SVG content. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation. (default: "") | STRING | Yes | - | | `substyle` | The specific vector illustration style to use for generation. | COMBO | Yes | `"2d_character"`
`"2d_gradient"`
`"2d_illustration"`
`"2d_flat_character"`
`"2d_flat_illustration"`
`"2d_art"`
`"2d_art_character"`
`"2d_pattern"`
`"2d_pixel_art"`
`"2d_cyberpunk"`
`"2d_engraving"`
`"2d_black_and_white"`
`"2d_ink"`
`"2d_sketch"`
`"2d_watercolor"`
`"2d_animation"`
`"2d_comic"`
`"2d_children_illustration"`
`"2d_vintage"`
`"2d_retro"`
`"2d_hand_drawn"`
`"2d_psychedelic"`
`"2d_graffiti"`
`"2d_ukiyo_e"`
`"2d_woodcut"`
`"2d_art_deco"`
`"2d_art_nouveau"`
`"2d_bauhaus"`
`"2d_constructivism"`
`"2d_cubism"`
`"2d_futurism"`
`"2d_glitch"`
`"2d_impressionism"`
`"2d_naive"`
`"2d_pointillism"`
`"2d_pop_art"`
`"2d_realism"`
`"2d_renaissance"`
`"2d_rococo"`
`"2d_romanticism"`
`"2d_surrealism"`
`"2d_suprematism"`
`"2d_symbolism"`
`"2d_expressionism"`
`"2d_abstract"`
`"2d_minimalism"`
`"2d_contemporary"`
`"2d_modern"`
`"2d_brutalism"`
`"2d_metaphysical"`
`"2d_mannerism"`
`"2d_baroque"`
`"2d_neoclassicism"`
`"2d_orientalism"`
`"2d_primitivism"`
`"2d_fauvism"`
`"2d_rayonism"`
`"2d_orphism"`
`"2d_vorticism"`
`"2d_dadaism"`
`"2d_neo_expressionism"`
`"2d_transavantgarde"`
`"2d_new_wild"`
`"2d_graffiti_classic"`
`"2d_graffiti_modern"`
`"2d_graffiti_wildstyle"`
`"2d_graffiti_bubble"`
`"2d_graffiti_throwup"`
`"2d_graffiti_tag"`
`"2d_graffiti_blockbuster"`
`"2d_graffiti_mural"`
`"2d_graffiti_stencil"`
`"2d_graffiti_3d"`
`"2d_graffiti_character"`
`"2d_graffiti_abstract"`
`"2d_graffiti_urban"`
`"2d_graffiti_neo_muralism"`
`"2d_graffiti_post_graffiti"`
`"2d_graffiti_street_art"` | | `size` | The size of the generated image. (default: "1024x1024") | COMBO | Yes | `"1024x1024"`
`"1024x2048"`
`"2048x1024"`
`"2048x2048"`
`"512x512"`
`"512x1024"`
`"1024x512"`
`"2048x512"`
`"512x2048"` | @@ -24,10 +25,10 @@ Generates SVG vector illustrations synchronously based on a text prompt and reso ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `SVG` | The generated vector illustration in SVG format | SVG | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftTextToVectorNode/en.md) --- -**Source fingerprint (SHA-256):** `b7b89e929a6d8dba78c0078962c9dde5c803bcff51350b0fb21c0cbd4c725ffe` +**Source fingerprint (SHA-256):** `4385c843d4ea312e9f35574bff6f75ae4ffd052486b787426ec37b0f8a6316e8` diff --git a/built-in-nodes/RecraftV4TextToImageNode.mdx b/built-in-nodes/RecraftV4TextToImageNode.mdx index 6712aa01f..5d9aeed99 100644 --- a/built-in-nodes/RecraftV4TextToImageNode.mdx +++ b/built-in-nodes/RecraftV4TextToImageNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RecraftV4TextToImageNode" icon: "circle" mode: wide --- + This node generates images from text descriptions using the Recraft V4 or V4 Pro AI models. It sends your prompt to an external API and returns the generated images. You can control the output by specifying the model, image size, and number of images to create. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation. Maximum 10,000 characters. | STRING | Yes | N/A | | `negative_prompt` | An optional text description of undesired elements on an image. | STRING | No | N/A | | `model` | The model to use for generation. Selecting a model determines the available image sizes. | COMBO | Yes | `"recraftv4"`
`"recraftv4_pro"` | @@ -19,15 +20,15 @@ This node generates images from text descriptions using the Recraft V4 or V4 Pro | `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0). | INT | Yes | 0 to 18446744073709551615 | | `recraft_controls` | Optional additional controls over the generation via the Recraft Controls node. | CUSTOM | No | N/A | -**Note:** The `size` parameter is a dynamic input whose available options change based on the selected `model`. The `seed` value does not guarantee reproducible image outputs. +**Note:** The `size` parameter is a dynamic input whose available options change based on the selected `model`. The `seed` value does not guarantee reproducible image outputs. If you use a style ID from the Infinite Style Library, make sure it is not a Vector art style, as this may return SVG data instead of an image. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated image or batch of images. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftV4TextToImageNode/en.md) --- -**Source fingerprint (SHA-256):** `b116fc35810d9cd246742b3ee1e3ce5472e79a467981ffb994cd1e2c53f0f086` +**Source fingerprint (SHA-256):** `aa23cb2627407350b79ed38d9b6a5487802ddda5c7050df7a7bfb167a707cb79` diff --git a/built-in-nodes/RecraftV4TextToVectorNode.mdx b/built-in-nodes/RecraftV4TextToVectorNode.mdx index e30935338..91b7a15f6 100644 --- a/built-in-nodes/RecraftV4TextToVectorNode.mdx +++ b/built-in-nodes/RecraftV4TextToVectorNode.mdx @@ -5,16 +5,17 @@ sidebarTitle: "RecraftV4TextToVectorNode" icon: "circle" mode: wide --- + The Recraft V4 Text to Vector node generates Scalable Vector Graphics (SVG) illustrations from a text description. It connects to an external API to use either the Recraft V4 or Recraft V4 Pro model for image generation. The node outputs one or more SVG images based on your prompt. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Prompt for the image generation. Maximum 10,000 characters. | STRING | Yes | N/A | | `negative_prompt` | An optional text description of undesired elements on an image. | STRING | No | N/A | | `model` | The model to use for generation. Selecting a model changes the available `size` options. | COMBO | Yes | `"recraftv4"`
`"recraftv4_pro"` | -| `size` | The size of the generated image. The available options depend on the selected `model`. Default is `"1024x1024"` for `recraftv4` and `"2048x2048"` for `recraftv4_pro`. | COMBO | Yes | For `recraftv4`: `"1024x1024"`, `"1152x896"`, `"896x1152"`, `"1216x832"`, `"832x1216"`, `"1344x768"`, `"768x1344"`, `"1536x640"`, `"640x1536"`
For `recraftv4_pro`: `"2048x2048"`, `"2304x1792"`, `"1792x2304"`, `"2432x1664"`, `"1664x2432"`, `"2688x1536"`, `"1536x2688"`, `"3072x1280"`, `"1280x3072"` | +| `size` | The size of the generated image. The available options depend on the selected `model`. Default is `"1024x1024"` for `recraftv4` and `"2048x2048"` for `recraftv4_pro`. | COMBO | Yes | For `recraftv4`: `"1024x1024"`
`"1152x896"`
`"896x1152"`
`"1216x832"`
`"832x1216"`
`"1344x768"`
`"768x1344"`
`"1536x640"`
`"640x1536"`
For `recraftv4_pro`: `"2048x2048"`
`"2304x1792"`
`"1792x2304"`
`"2432x1664"`
`"1664x2432"`
`"2688x1536"`
`"1536x2688"`
`"3072x1280"`
`"1280x3072"` | | `n` | The number of images to generate (default: 1). | INT | Yes | 1 to 6 | | `seed` | Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. | INT | Yes | 0 to 18446744073709551615 | | `recraft_controls` | Optional additional controls over the generation via the Recraft Controls node. | CUSTOM | No | N/A | @@ -24,10 +25,10 @@ The Recraft V4 Text to Vector node generates Scalable Vector Graphics (SVG) illu ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated Scalable Vector Graphics (SVG) image(s). | SVG | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftV4TextToVectorNode/en.md) --- -**Source fingerprint (SHA-256):** `e2524f2607068f2115cf7a192cb9a4f77fbe4e2535108e3c7167923d599fd212` +**Source fingerprint (SHA-256):** `0e0214036b6a8f9f6aeaad0533e014ef429a94ff55613095acb4317fc69ad934` diff --git a/built-in-nodes/RecraftVectorizeImageNode.mdx b/built-in-nodes/RecraftVectorizeImageNode.mdx index e1d6f56fc..dea25de30 100644 --- a/built-in-nodes/RecraftVectorizeImageNode.mdx +++ b/built-in-nodes/RecraftVectorizeImageNode.mdx @@ -5,21 +5,22 @@ sidebarTitle: "RecraftVectorizeImageNode" icon: "circle" mode: wide --- + Generates SVG vector graphics from an input image. This node converts raster images into scalable vector format by sending each image to the Recraft API and combining the results into a single SVG output. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to convert to SVG format. Supports batch processing of multiple images. | IMAGE | Yes | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `SVG` | The generated vector graphics output combining all processed images into a single SVG document. | SVG | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftVectorizeImageNode/en.md) --- -**Source fingerprint (SHA-256):** `de221f8156396cd3c95b30840e446811c2a5f8f09d66028cbc2dbe2a551fc4cd` +**Source fingerprint (SHA-256):** `bda74d9f11cc79217c61ecb8ba597a671133baa4380386428c4d9e9b68006713` diff --git a/built-in-nodes/ReferenceLatent.mdx b/built-in-nodes/ReferenceLatent.mdx index e3db13d05..4e14b356b 100644 --- a/built-in-nodes/ReferenceLatent.mdx +++ b/built-in-nodes/ReferenceLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReferenceLatent" icon: "circle" mode: wide --- + This node sets the guiding latent for an edit model. It takes conditioning data and an optional latent input, then modifies the conditioning to include reference latent information. If the model supports it, you can chain multiple ReferenceLatent nodes to set multiple reference images. ## Inputs diff --git a/built-in-nodes/ReferenceTimbreAudio.mdx b/built-in-nodes/ReferenceTimbreAudio.mdx index 918dcce29..60a12dee5 100644 --- a/built-in-nodes/ReferenceTimbreAudio.mdx +++ b/built-in-nodes/ReferenceTimbreAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReferenceTimbreAudio" icon: "circle" mode: wide --- + This node sets a reference audio timbre for use in the "ace step 1.5" process. It works by taking a conditioning input and optionally a latent representation of audio, then attaches that latent data to the conditioning for use by subsequent nodes in the workflow. ## Inputs diff --git a/built-in-nodes/RegexExtract.mdx b/built-in-nodes/RegexExtract.mdx index 9b44cd803..a343e7a74 100644 --- a/built-in-nodes/RegexExtract.mdx +++ b/built-in-nodes/RegexExtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexExtract" icon: "circle" mode: wide --- + The RegexExtract node searches for patterns in text using regular expressions. It can find the first match, all matches, specific groups from matches, or all groups across multiple matches. The node supports various regex flags for case sensitivity, multiline matching, and dotall behavior. ## Inputs diff --git a/built-in-nodes/RegexMatch.mdx b/built-in-nodes/RegexMatch.mdx index 0f13e68a5..fa4eb61b8 100644 --- a/built-in-nodes/RegexMatch.mdx +++ b/built-in-nodes/RegexMatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexMatch" icon: "circle" mode: wide --- + The RegexMatch node checks if a text string contains a match for a given regular expression pattern. It searches the input string and returns a simple yes/no result indicating whether the pattern was found anywhere in the text. You can adjust how the search works by enabling options like case-insensitive matching or multiline mode. ## Inputs diff --git a/built-in-nodes/RegexReplace.mdx b/built-in-nodes/RegexReplace.mdx index 8d226bd29..636374175 100644 --- a/built-in-nodes/RegexReplace.mdx +++ b/built-in-nodes/RegexReplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexReplace" icon: "circle" mode: wide --- + The RegexReplace node finds and replaces text in strings using regular expression patterns. It allows you to search for text patterns and replace them with new text, with options to control how the pattern matching works including case sensitivity, multiline matching, and limiting the number of replacements. ## Inputs diff --git a/built-in-nodes/RemoveBackground.mdx b/built-in-nodes/RemoveBackground.mdx index ef942c956..b385a1b8c 100644 --- a/built-in-nodes/RemoveBackground.mdx +++ b/built-in-nodes/RemoveBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RemoveBackground" icon: "circle" mode: wide --- + ## Overview The Remove Background node generates a foreground mask that separates the main subject from the background of an input image. It uses a background removal model to analyze the image and produce a mask highlighting the foreground elements. @@ -12,17 +13,17 @@ The Remove Background node generates a foreground mask that separates the main s ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `image` | Input image to remove the background from | IMAGE | Yes | N/A | +|-----------|-------------|-----------|----------|-------| | `bg_removal_model` | Background removal model used to generate the mask | BACKGROUND_REMOVAL_MODEL | Yes | N/A | +| `image` | Input image to remove the background from | IMAGE | Yes | N/A | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | -| `mask` | Generated foreground mask that highlights the main subject of the input image | MASK | +|-------------|-------------|-----------| +| `mask` | Generated foreground mask | MASK | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RemoveBackground/en.md) --- -**Source fingerprint (SHA-256):** `6b0e31792dc8a5c949944680129e91790ca396336a43ac67b7816b9d6c5b9049` +**Source fingerprint (SHA-256):** `75b415acedaeaa1a694aeba2e4b0367524c6878e3e4a1f48b2a62898c68109f9` diff --git a/built-in-nodes/RenderSplat.mdx b/built-in-nodes/RenderSplat.mdx index 3a95e1df7..b6f785471 100644 --- a/built-in-nodes/RenderSplat.mdx +++ b/built-in-nodes/RenderSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RenderSplat" icon: "circle" mode: wide --- -# Render Splat Render a gaussian splat as an image using an anisotropic EWA rasterizer with oriented elliptical splats, antialiasing, and depth-sorted front-to-back rendering. The camera comes from a camera_info input, or you can leave it empty to auto-frame the splat. Set frames greater than 1 for a turntable batch of images to feed a Video node. diff --git a/built-in-nodes/RenormCFG.mdx b/built-in-nodes/RenormCFG.mdx index e074272a1..d96df57b4 100644 --- a/built-in-nodes/RenormCFG.mdx +++ b/built-in-nodes/RenormCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RenormCFG" icon: "circle" mode: wide --- + The RenormCFG node modifies the classifier-free guidance (CFG) process in diffusion models by applying conditional scaling and normalization. It adjusts the denoising process based on specified timestep thresholds and renormalization factors to control the influence of conditional versus unconditional predictions during image generation. ## Inputs diff --git a/built-in-nodes/RepeatImageBatch.mdx b/built-in-nodes/RepeatImageBatch.mdx index 9b19e3e93..62c64685d 100644 --- a/built-in-nodes/RepeatImageBatch.mdx +++ b/built-in-nodes/RepeatImageBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RepeatImageBatch" icon: "circle" mode: wide --- + The RepeatImageBatch node is designed to replicate a given image a specified number of times, creating a batch of identical images. This functionality is useful for operations that require multiple instances of the same image, such as batch processing or data augmentation. ## Inputs diff --git a/built-in-nodes/RepeatLatentBatch.mdx b/built-in-nodes/RepeatLatentBatch.mdx index 48394ccbc..450e7436c 100644 --- a/built-in-nodes/RepeatLatentBatch.mdx +++ b/built-in-nodes/RepeatLatentBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RepeatLatentBatch" icon: "circle" mode: wide --- + The RepeatLatentBatch node is designed to replicate a given batch of latent representations a specified number of times, potentially including additional data like noise masks and batch indices. This functionality is crucial for operations that require multiple instances of the same latent data, such as data augmentation or specific generative tasks. ## Inputs diff --git a/built-in-nodes/ReplaceText.mdx b/built-in-nodes/ReplaceText.mdx index 0275d95ac..0581e3e0e 100644 --- a/built-in-nodes/ReplaceText.mdx +++ b/built-in-nodes/ReplaceText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReplaceText" icon: "circle" mode: wide --- + The Replace Text node performs a simple text substitution. It searches for a specified piece of text within the input and replaces every occurrence with a new piece of text. The operation is applied to all text inputs provided to the node. **Note:** This node is deprecated and superseded by the other Replace Text node. diff --git a/built-in-nodes/ReplaceVideoLatentFrames.mdx b/built-in-nodes/ReplaceVideoLatentFrames.mdx index 43eb70752..b8f7ffa39 100644 --- a/built-in-nodes/ReplaceVideoLatentFrames.mdx +++ b/built-in-nodes/ReplaceVideoLatentFrames.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReplaceVideoLatentFrames" icon: "circle" mode: wide --- + The ReplaceVideoLatentFrames node inserts frames from a source latent video into a destination latent video, starting at a specified frame index. If the source latent is not provided, the destination latent is returned unchanged. The node handles negative indexing and will issue a warning if the source frames do not fit within the destination. ## Inputs diff --git a/built-in-nodes/Reroute.mdx b/built-in-nodes/Reroute.mdx index 25051e395..3c819b9bf 100644 --- a/built-in-nodes/Reroute.mdx +++ b/built-in-nodes/Reroute.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Reroute" icon: "circle" mode: wide --- + Node Name: Reroute Node Node Purpose: Mainly used to organize the logic of overly long connection lines in the ComfyUI workflow. diff --git a/built-in-nodes/RescaleCFG.mdx b/built-in-nodes/RescaleCFG.mdx index 264d9763c..e7cac6eb4 100644 --- a/built-in-nodes/RescaleCFG.mdx +++ b/built-in-nodes/RescaleCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RescaleCFG" icon: "circle" mode: wide --- + The RescaleCFG node is designed to adjust the conditioning and unconditioning scales of a model's output based on a specified multiplier, aiming to achieve a more balanced and controlled generation process. It operates by rescaling the model's output to modify the influence of conditioned and unconditioned components, thereby potentially enhancing the model's performance or output quality. ## Inputs diff --git a/built-in-nodes/ResizeAndPadImage.mdx b/built-in-nodes/ResizeAndPadImage.mdx index 5bb65e173..58c563107 100644 --- a/built-in-nodes/ResizeAndPadImage.mdx +++ b/built-in-nodes/ResizeAndPadImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeAndPadImage" icon: "circle" mode: wide --- + The ResizeAndPadImage node resizes an image to fit within specified dimensions while maintaining its original aspect ratio. It scales the image down proportionally to fit within the target width and height, then adds padding around the edges to fill any remaining space. The padding color and interpolation method can be customized to control the appearance of the padded areas and the quality of the resizing. ## Inputs diff --git a/built-in-nodes/ResizeImageMaskNode.mdx b/built-in-nodes/ResizeImageMaskNode.mdx index 2f1ea8f29..2948e344c 100644 --- a/built-in-nodes/ResizeImageMaskNode.mdx +++ b/built-in-nodes/ResizeImageMaskNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImageMaskNode" icon: "circle" mode: wide --- + The Resize Image/Mask node provides multiple methods to change the dimensions of an input image or mask. It can scale by a multiplier, set specific dimensions, match the size of another input, or adjust based on pixel count, using various interpolation methods for quality. ## Inputs diff --git a/built-in-nodes/ResizeImagesByLongerEdge.mdx b/built-in-nodes/ResizeImagesByLongerEdge.mdx index 54f5a831e..e8a98ae25 100644 --- a/built-in-nodes/ResizeImagesByLongerEdge.mdx +++ b/built-in-nodes/ResizeImagesByLongerEdge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImagesByLongerEdge" icon: "circle" mode: wide --- + The Resize Images by Longer Edge node resizes one or more images so that their longest side matches a specified target length. It automatically determines whether the width or height is longer and scales the other dimension proportionally to preserve the original aspect ratio. This node is deprecated and superseded by the Resize Image/Mask node with the resize type set to "scale longer dimension". ## Inputs diff --git a/built-in-nodes/ResizeImagesByShorterEdge.mdx b/built-in-nodes/ResizeImagesByShorterEdge.mdx index 8062cf1d8..6cd4803a2 100644 --- a/built-in-nodes/ResizeImagesByShorterEdge.mdx +++ b/built-in-nodes/ResizeImagesByShorterEdge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImagesByShorterEdge" icon: "circle" mode: wide --- + This node resizes images so that the shorter edge matches a specified length while preserving the original aspect ratio. It calculates new dimensions based on the target length for the shorter side and returns the resized image. ## Inputs diff --git a/built-in-nodes/ResolutionBucket.mdx b/built-in-nodes/ResolutionBucket.mdx index 1b4376046..1c86579f9 100644 --- a/built-in-nodes/ResolutionBucket.mdx +++ b/built-in-nodes/ResolutionBucket.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResolutionBucket" icon: "circle" mode: wide --- + This node organizes a list of latent images and their corresponding conditioning data by their resolution. It groups together items that share the same height and width, creating separate batches for each unique resolution. This process is useful for preparing data for efficient training, as it allows models to process multiple items of the same size together. ## Inputs diff --git a/built-in-nodes/ResolutionSelector.mdx b/built-in-nodes/ResolutionSelector.mdx index 24b67c6e9..3f7b1b277 100644 --- a/built-in-nodes/ResolutionSelector.mdx +++ b/built-in-nodes/ResolutionSelector.mdx @@ -5,23 +5,25 @@ sidebarTitle: "ResolutionSelector" icon: "circle" mode: wide --- -The Resolution Selector node calculates the pixel width and height for an image based on a chosen aspect ratio and a target total resolution in megapixels. It is useful for generating consistent dimensions for other nodes, such as the Empty Latent Image node. The output dimensions are always rounded to the nearest multiple of 8. + +The Resolution Selector node calculates pixel width and height based on a chosen aspect ratio and a target total resolution in megapixels. It is useful for generating consistent dimensions for other nodes, such as the Empty Latent Image node. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `aspect_ratio` | The aspect ratio for the output dimensions (default: `"1:1 (Square)"`). | COMBO | Yes | `"1:1 (Square)"`
`"3:2 (Photo)"`
`"4:3 (Standard)"`
`"16:9 (Widescreen)"`
`"21:9 (Ultrawide)"`
`"2:3 (Portrait Photo)"`
`"3:4 (Portrait Standard)"`
`"9:16 (Portrait Widescreen)"` | -| `megapixels` | Target total megapixels. 1.0 MP ≈ 1024×1024 for a square aspect ratio (default: 1.0). | FLOAT | Yes | 0.1 - 16.0 | +|-----------|-------------|-----------|----------|-------| +| `aspect_ratio` | The aspect ratio for the output dimensions (default: `"1:1 (Square)"`). | COMBO | Yes | `"1:1 (Square)"`
`"2:3 (Portrait Photo)"`
`"3:2 (Photo)"`
`"3:4 (Portrait Standard)"`
`"4:3 (Standard)"`
`"9:16 (Portrait Widescreen)"`
`"16:9 (Widescreen)"`
`"21:9 (Ultrawide)"` | +| `megapixels` | Target total megapixels. 1.0 MP ≈ 1024x1024 for square (default: 1.0). | FLOAT | Yes | 0.1 - 16.0 | +| `multiple` | Nearest multiple of the result to set the selected resolution to (default: 8). | INT | No | 8 - 128 (step: 4) | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | -| `width` | The calculated width in pixels, which is a multiple of 8. | INT | -| `height` | The calculated height in pixels, which is a multiple of 8. | INT | +|-------------|-------------|-----------| +| `width` | Calculated width in pixels multiplied by the selected multiple. | INT | +| `height` | Calculated height in pixels multiplied by the selected multiple. | INT | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResolutionSelector/en.md) --- -**Source fingerprint (SHA-256):** `7b27f0ffaaa1740a6371e53f10fa6a0ead3237ecec656b9148a2ecd11de7aaa5` +**Source fingerprint (SHA-256):** `2060bbeb6583f09014045a19462cf22a231975831b1b3b6d9374753030857e1b` diff --git a/built-in-nodes/ReveImageCreateNode.mdx b/built-in-nodes/ReveImageCreateNode.mdx index 34e5d7391..064585ae8 100644 --- a/built-in-nodes/ReveImageCreateNode.mdx +++ b/built-in-nodes/ReveImageCreateNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReveImageCreateNode" icon: "circle" mode: wide --- + The Reve Image Create node generates images from text descriptions using the Reve AI model. It sends a text prompt to the Reve API and returns the generated image. You can control the image's aspect ratio and apply optional post-processing effects like upscaling and background removal. ## Inputs @@ -12,15 +13,12 @@ The Reve Image Create node generates images from text descriptions using the Rev | Parameter | Description | Data Type | Required | Range | | --- | --- | --- | --- | --- | | `prompt` | Text description of the desired image. Maximum 2560 characters. | STRING | Yes | N/A | -| `model` | Model version to use for generation. The aspect ratio is selected from the available options within this parameter. | COMBO | Yes | `"reve-create@20250915"` | -| `aspect_ratio` | The desired aspect ratio for the generated image. | COMBO | Yes | `"3:2"`
`"16:9"`
`"9:16"`
`"2:3"`
`"4:3"`
`"3:4"`
`"1:1"` | -| `test_time_scaling` | Enables or disables test-time scaling, which can improve image quality at the cost of longer generation time. | COMBO | Yes | `"disabled"`
`"enabled"` | +| `model` | Model version to use for generation. Includes aspect ratio selection within this parameter. | COMBO | Yes | `"reve-create@20250915"` | +| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. Default: 0. | INT | No | 0 to 2147483647 | | `upscale` | Enables or disables the upscaling post-processing step. When enabled, you must also select an upscale factor. | COMBO | No | `"disabled"`
`"enabled"` | -| `upscale_factor` | The factor by which to increase the image's resolution. This parameter is only active when `upscale` is set to `"enabled"`. | COMBO | No | `2`
`3`
`4` | | `remove_background` | When enabled, applies a background removal post-processing step to the generated image. | BOOLEAN | No | N/A | -| `seed` | A seed value that controls whether the node should re-run. Note: Results are non-deterministic regardless of the seed value. Default: 0. | INT | No | 0 to 2147483647 | -**Note:** The `upscale_factor` parameter is dependent on the `upscale` parameter being set to `"enabled"`. The `seed` parameter does not guarantee deterministic outputs. +**Note:** The `seed` parameter does not guarantee deterministic outputs. The `upscale` parameter controls whether upscaling is applied as a post-processing step. ## Outputs @@ -31,4 +29,4 @@ The Reve Image Create node generates images from text descriptions using the Rev > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReveImageCreateNode/en.md) --- -**Source fingerprint (SHA-256):** `69c81413cb345b7ecd92055e244f89d5b33f2bd67ee83e4225dd7c2168b55d5a` +**Source fingerprint (SHA-256):** `d4e233fb94afa248503ec34fc4c1d4de48759c33632b35e139083e34929cecf3` diff --git a/built-in-nodes/ReveImageEditNode.mdx b/built-in-nodes/ReveImageEditNode.mdx index fcbcd2552..ca1055db4 100644 --- a/built-in-nodes/ReveImageEditNode.mdx +++ b/built-in-nodes/ReveImageEditNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ReveImageEditNode" icon: "circle" mode: wide --- + The Reve Image Edit node allows you to modify an existing image based on a text description. It uses the Reve API to interpret your instructions and apply the requested changes to the image you provide. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The image to edit. | IMAGE | Yes | - | | `edit_instruction` | Text description of how to edit the image. Maximum 2560 characters. | STRING | Yes | - | | `model` | Model version to use for editing. | MODEL | Yes | `"reve-edit@20250915"`
`"reve-edit-fast@20251030"` | @@ -26,10 +27,10 @@ The Reve Image Edit node allows you to modify an existing image based on a text ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The edited image generated based on the instruction. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReveImageEditNode/en.md) --- -**Source fingerprint (SHA-256):** `21fbe9e23e952eb0132d31a295505a38a6d3640396865d00b999135d0722166f` +**Source fingerprint (SHA-256):** `067ef57802f549bc475c07eed43b14e567d6a0bdacd468825f084846b7cfddfd` diff --git a/built-in-nodes/ReveImageRemixNode.mdx b/built-in-nodes/ReveImageRemixNode.mdx index 32372e60e..156601a79 100644 --- a/built-in-nodes/ReveImageRemixNode.mdx +++ b/built-in-nodes/ReveImageRemixNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ReveImageRemixNode" icon: "circle" mode: wide --- + The Reve Image Remix node uses the Reve API to generate a new image. It combines one or more reference images with a text prompt to create a new, remixed image based on the provided description. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `reference_images` | One or more reference images to use as a base for the remix. You can add between 1 and 6 images. | IMAGE | Yes | 1 to 6 images | | `prompt` | A text description of the desired image. You can include XML `` tags to reference specific images by their index (e.g., `0`, `1`). (default: empty) | STRING | Yes | 1 to 2560 characters | | `model` | The model version to use for remixing. Each model option includes configurable aspect ratios and test-time scaling. | COMBO | Yes | `reve-remix@20250915`
`reve-remix-fast@20251030` | @@ -23,10 +24,10 @@ The Reve Image Remix node uses the Reve API to generate a new image. It combines ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The new image generated by the Reve remix process. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReveImageRemixNode/en.md) --- -**Source fingerprint (SHA-256):** `eb69d653812ecd63c66be9290233a820a4d0145bdd5be1e23601d8cdd5eb228a` +**Source fingerprint (SHA-256):** `095e286f5badcdc1cdc034b2b91545f136f37550819888ac19d7ac808aec7641` diff --git a/built-in-nodes/Rodin3D_Detail.mdx b/built-in-nodes/Rodin3D_Detail.mdx index aad0426c0..a1298afa9 100644 --- a/built-in-nodes/Rodin3D_Detail.mdx +++ b/built-in-nodes/Rodin3D_Detail.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Rodin3D_Detail" icon: "circle" mode: wide --- + The Rodin 3D Detail node generates detailed 3D assets using the Rodin API. It takes input images and processes them through the Rodin service to create high-quality 3D models with detailed geometry and materials. The node handles the entire workflow from task creation to downloading the final 3D model file. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `Images` | Input images used for 3D model generation. A minimum of 1 image is required, and a maximum of 5 images can be provided. | IMAGE | Yes | - | | `Seed` | Random seed value for reproducible results (default: 0) | INT | No | 0 to 65535 | | `Material_Type` | Type of material to apply to the 3D model (default: "PBR") | STRING | No | `"PBR"`
`"Shaded"` | @@ -19,11 +20,11 @@ The Rodin 3D Detail node generates detailed 3D assets using the Rodin API. It ta ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `3D Model Path` | File path to the generated 3D model (for backward compatibility only) | STRING | | `GLB` | The generated 3D model in GLB format | FILE3DGLB | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Detail/en.md) --- -**Source fingerprint (SHA-256):** `ccdee80eb972c13a8849488080c08ba7276cec0b77a2089c7a9ad5b8adc5937b` +**Source fingerprint (SHA-256):** `941265733c20d27d67621a83a05be822731696f4dd376299510d4279a35f51ee` diff --git a/built-in-nodes/Rodin3D_Gen2.mdx b/built-in-nodes/Rodin3D_Gen2.mdx index 71286e7b0..adee37603 100644 --- a/built-in-nodes/Rodin3D_Gen2.mdx +++ b/built-in-nodes/Rodin3D_Gen2.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Rodin3D_Gen2" icon: "circle" mode: wide --- + The Rodin3D_Gen2 node generates 3D assets using the Rodin API. It takes input images and converts them into 3D models with various material types and polygon counts. The node handles the entire generation process including task creation, status polling, and file downloading automatically. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `Images` | Input images to use for 3D model generation. Accepts 1 to 5 images. | IMAGE | Yes | - | | `Seed` | Random seed value for generation (default: 0) | INT | No | 0-65535 | | `Material_Type` | Type of material to apply to the 3D model (default: "PBR") | COMBO | No | "PBR"
"Shaded" | @@ -20,11 +21,11 @@ The Rodin3D_Gen2 node generates 3D assets using the Rodin API. It takes input im ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `3D Model Path` | File path to the generated 3D model (for backward compatibility) | STRING | | `GLB` | The generated 3D model in GLB format | FILE3DGLB | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen2/en.md) --- -**Source fingerprint (SHA-256):** `98e183ba480d2ef8dc1930132ea4edf83481cf6bf7ee18a22972b71dd532c7ea` +**Source fingerprint (SHA-256):** `6ee8b52152e84cca48c7875ce066ab19805a42e5cccc84865c6027a4f6fd3b16` diff --git a/built-in-nodes/Rodin3D_Gen25_Image.mdx b/built-in-nodes/Rodin3D_Gen25_Image.mdx index 49c61e238..625fa8cc2 100644 --- a/built-in-nodes/Rodin3D_Gen25_Image.mdx +++ b/built-in-nodes/Rodin3D_Gen25_Image.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen25_Image" icon: "circle" mode: wide --- + ## Overview This node generates a 3D model from one to five reference images using the Rodin Gen-2.5 API. You can choose between Fast, Regular, or Extreme-High quality modes to balance generation speed and cost. @@ -12,7 +13,7 @@ This node generates a 3D model from one to five reference images using the Rodin ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `images` | One to five input images. The first image is used for materials when multiple images are provided. | IMAGE | Yes | 1 to 5 images | | `mode` | The generation quality mode. Higher quality modes produce better results but cost more. | COMBO | Yes | `"Fast"`
`"Regular"`
`"Extreme-High"` | | `material` | The material type for the generated 3D model. | COMBO | Yes | `"PBR"`
`"Matte"` | @@ -34,10 +35,10 @@ This node generates a 3D model from one to five reference images using the Rodin ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The generated 3D model file in the selected geometry format. | FILE3D | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen25_Image/en.md) --- -**Source fingerprint (SHA-256):** `65f755a2c3bd2317eb61c4681a406b51b06f960e36864d3602c3d03a44aa4878` +**Source fingerprint (SHA-256):** `6437f8d34624fccfb92505bcdc627db2df2f4159c929a4f7b00352906c609a25` diff --git a/built-in-nodes/Rodin3D_Gen25_Text.mdx b/built-in-nodes/Rodin3D_Gen25_Text.mdx index db45a92f1..16b3c779c 100644 --- a/built-in-nodes/Rodin3D_Gen25_Text.mdx +++ b/built-in-nodes/Rodin3D_Gen25_Text.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen25_Text" icon: "circle" mode: wide --- + ## Overview Generate a 3D model from a text prompt using the Rodin Gen-2.5 API. You can choose between different quality modes (Fast, Regular, or Extreme-High) to balance generation speed and output quality. @@ -12,8 +13,8 @@ Generate a 3D model from a text prompt using the Rodin Gen-2.5 API. You can choo ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `prompt` | Text prompt describing the 3D model you want to generate. | STRING | Yes | Max 2500 characters | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Text prompt for the 3D model. | STRING | Yes | 1 to 2500 characters | | `mode` | The generation quality and speed mode. "Fast" is quickest, "Extreme-High" produces the highest quality but takes longer. | COMBO | Yes | `"Fast"`
`"Regular"`
`"Extreme-High"` | | `material` | The material style for the generated 3D model. | COMBO | Yes | `"PBR"`
`"Matte"`
`"Shiny"` | | `geometry_file_format` | The file format for the output 3D model. | COMBO | Yes | `"glb"`
`"obj"`
`"stl"`
`"usdz"` | @@ -33,10 +34,10 @@ Generate a 3D model from a text prompt using the Rodin Gen-2.5 API. You can choo ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The generated 3D model file in the specified format. | FILE3DANY | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen25_Text/en.md) --- -**Source fingerprint (SHA-256):** `79fbaf466e9af88cdfdac0f9136a2df17ba4bc2e5bb65a35b9ad2b1181da94db` +**Source fingerprint (SHA-256):** `7e71532203290e21e13d345b09330a1c00aff9d3754e63f5eff65f37f3fa2403` diff --git a/built-in-nodes/Rodin3D_Regular.mdx b/built-in-nodes/Rodin3D_Regular.mdx index 05843bfd4..8361b6cd0 100644 --- a/built-in-nodes/Rodin3D_Regular.mdx +++ b/built-in-nodes/Rodin3D_Regular.mdx @@ -5,16 +5,17 @@ sidebarTitle: "Rodin3D_Regular" icon: "circle" mode: wide --- + The Rodin 3D Regular node generates 3D assets using the Rodin API. It takes input images and processes them through the Rodin service to create 3D models. The node handles the entire workflow from task creation to downloading the final 3D model files. ## Inputs | Parameter | Description | Data Type | Required | Range | | --- | --- | --- | --- | --- | -| `Images` | Input images used for 3D model generation. Up to 5 images can be provided. | IMAGE | Yes | - | +| `Images` | Input images used for 3D model generation. Up to 5 images can be provided. At least 1 image is required. | IMAGE | Yes | - | | `Seed` | Random seed value for reproducible results (default: 0). | INT | No | 0 to 65535 | | `Material_Type` | Type of material to apply to the 3D model (default: "PBR"). | STRING | No | `"PBR"`
`"Shaded"` | -| `Polygon_count` | Target polygon count and mesh type for the generated 3D model (default: "18K-Quad"). | STRING | No | `"4K-Quad"`
`"8K-Quad"`
`"18K-Quad"`
`"50K-Quad"`
`"200K-Triangle"` | +| `Polygon_count` | Target polygon count and mesh type for the generated 3D model (default: "18K-Quad"). | STRING | No | `"4K-Quad"`
`"8K-Quad"`
`"18K-Quad"`
`"50K-Quad"
`"200K-Triangle"` | **Note:** At least 1 image is required for 3D model generation. A maximum of 5 images can be provided. @@ -28,4 +29,4 @@ The Rodin 3D Regular node generates 3D assets using the Rodin API. It takes inpu > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Regular/en.md) --- -**Source fingerprint (SHA-256):** `5d65be9cb92da615690df5665ca02c98e98e95510e002502a33fd869c31e7419` +**Source fingerprint (SHA-256):** `e0bd8ef311f33481fec877801dea80302eba076f2d9e12f52467e889242a9637` diff --git a/built-in-nodes/Rodin3D_Sketch.mdx b/built-in-nodes/Rodin3D_Sketch.mdx index f96aed3f3..4385bfb67 100644 --- a/built-in-nodes/Rodin3D_Sketch.mdx +++ b/built-in-nodes/Rodin3D_Sketch.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Rodin3D_Sketch" icon: "circle" mode: wide --- + This node generates 3D assets using the Rodin API. It takes input images and converts them into 3D models through an external service. The node handles the entire process from task creation to downloading the final 3D model files. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `Images` | Input images to be converted into 3D models. You can provide between 1 and 5 images. | IMAGE | Yes | 1 to 5 images | | `Seed` | Random seed value for generation (default: 0). Set to 0 for a random seed. | INT | No | 0 to 65535 | @@ -19,11 +20,11 @@ This node generates 3D assets using the Rodin API. It takes input images and con ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `3D Model Path` | File path to the generated 3D model (for backward compatibility only) | STRING | | `GLB` | The generated 3D model in GLB format | FILE3DGLB | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Sketch/en.md) --- -**Source fingerprint (SHA-256):** `7030e6966a13b62055a17fc1eb39f34aa228fa37bbdcf7c2d5dbbbc1ca96c819` +**Source fingerprint (SHA-256):** `0b77ce871e267450af63f3e2fe0e36fe81ababc25cbb11498546ad8f487b65e5` diff --git a/built-in-nodes/Rodin3D_Smooth.mdx b/built-in-nodes/Rodin3D_Smooth.mdx index 995f7b2c2..32f1f872b 100644 --- a/built-in-nodes/Rodin3D_Smooth.mdx +++ b/built-in-nodes/Rodin3D_Smooth.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Rodin3D_Smooth" icon: "circle" mode: wide --- + The Rodin 3D Smooth node generates 3D assets using the Rodin API by processing input images and converting them into smooth 3D models. It takes multiple images as input and produces a downloadable 3D model file. The node handles the entire generation process including task creation, status polling, and file downloading automatically. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `Images` | Input images to use for 3D model generation. Multiple images can be provided (up to 5). | IMAGE | Yes | - | | `Seed` | Random seed value for generation consistency (default: 0). | INT | No | 0 to 65535 | | `Material_Type` | Type of material to apply to the 3D model (default: "PBR"). | STRING | No | "PBR"
"Shaded" | @@ -21,11 +22,11 @@ The Rodin 3D Smooth node generates 3D assets using the Rodin API by processing i ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `3D Model Path` | File path to the downloaded 3D model (for backward compatibility only). | STRING | | `GLB` | The generated 3D model in GLB format. | FILE3DGLB | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Smooth/en.md) --- -**Source fingerprint (SHA-256):** `60a5d70fa095b46f221ce452e290739852b1ebeba34ab7ec21b0b4e3c8e6d164` +**Source fingerprint (SHA-256):** `c7dc23d2a7a8e2d425fc389476ef381f4ebf974f522c6e3774222866eee064e9` diff --git a/built-in-nodes/RunwayAleph2KeyframeNode.mdx b/built-in-nodes/RunwayAleph2KeyframeNode.mdx new file mode 100644 index 000000000..17dacf826 --- /dev/null +++ b/built-in-nodes/RunwayAleph2KeyframeNode.mdx @@ -0,0 +1,35 @@ +--- +title: "RunwayAleph2KeyframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2KeyframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2KeyframeNode" +icon: "circle" +mode: wide +--- + +This node anchors a guidance image to a specific moment of your input video, so the Aleph2 model steers the edit at that point in your footage. Connect this node to the "keyframes" input of the Runway Aleph2 Video to Video node, and chain several together (up to 5) via the optional "keyframes" input. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `image` | The guidance image to apply at the chosen moment of the input video. | IMAGE | Yes | - | +| `timing` | How to place this image on the input video's timeline. | COMBO | Yes | "Absolute seconds"
"Fraction of duration" | +| `keyframes` | Optional earlier keyframes to chain with this one. | KEYFRAME | No | - | + +### Timing Parameter Details + +The `timing` parameter has two modes: + +- **"Absolute seconds"**: When selected, a `seconds` sub-parameter appears. This specifies the time in seconds from the start of the input video where the image applies (default: 0.0, range: 0.0 to 30.0, step 0.1). +- **"Fraction of duration"**: When selected, a `fraction` sub-parameter appears. This specifies where in the input video the image applies as a fraction of its duration, where 0.0 is the start and 1.0 is the end (default: 0.0, range: 0.0 to 1.0, step 0.01). + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `keyframes` | A chain of keyframes including this one and any previously connected keyframes. | KEYFRAME | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2KeyframeNode/en.md) + +--- +**Source fingerprint (SHA-256):** `b5ac6553166b7366fd35f97740861be163f91bc2353f5f83bdc2f04bf40f8478` diff --git a/built-in-nodes/RunwayAleph2PromptImageNode.mdx b/built-in-nodes/RunwayAleph2PromptImageNode.mdx new file mode 100644 index 000000000..3b6b9cf72 --- /dev/null +++ b/built-in-nodes/RunwayAleph2PromptImageNode.mdx @@ -0,0 +1,34 @@ +--- +title: "RunwayAleph2PromptImageNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2PromptImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2PromptImageNode" +icon: "circle" +mode: wide +--- + +This node anchors a guidance image to a specific moment in the output video, controlling what the edited video looks like at that point. Connect this node to the `prompt_images` input of the Runway Aleph2 Video to Video node, and chain several together (up to 5) using the optional `prompt_images` input. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `image` | The guidance image to place at the chosen moment of the output video. | IMAGE | Yes | - | +| `position` | How to place this image on the output video's timeline. Choose between absolute timing (seconds from start) or fractional timing (percentage of video duration). | COMBO | Yes | `Absolute (seconds)`
`Fraction (0.0 to 1.0)` | +| `prompt_images` | Optional earlier prompt images to chain with this one. Connect the output of another Runway Aleph2 Prompt Image node here to build a chain of up to 5 guidance images. | PROMPT_IMAGE_CHAIN | No | - | + +**Position Mode Details:** + +When `position` is set to `Absolute (seconds)`, you must provide a `seconds` value (default: 0.0, range: 0.0 to 30.0, step: 0.1). This specifies the exact time in seconds from the start of the output video where this image applies. + +When `position` is set to `Fraction (0.0 to 1.0)`, you must provide a `fraction` value (default: 0.0, range: 0.0 to 1.0, step: 0.01). This specifies where in the output video this image applies as a fraction of its total duration (0.0 = start, 1.0 = end). + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `prompt_images` | A chain of prompt images that can be connected to the `prompt_images` input of the Runway Aleph2 Video to Video node. | PROMPT_IMAGE_CHAIN | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2PromptImageNode/en.md) + +--- +**Source fingerprint (SHA-256):** `a8b86fb5d73d27cc58aa59c195ca058eec8a5c9433ea09522ff3e905f6b88193` diff --git a/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx b/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx new file mode 100644 index 000000000..3661f77f8 --- /dev/null +++ b/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx @@ -0,0 +1,37 @@ +--- +title: "RunwayAleph2VideoToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2VideoToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2VideoToVideoNode" +icon: "circle" +mode: wide +--- + +This node edits a video using a text prompt with Runway's Aleph2 model. It transforms your footage by restyling, relighting, adding or removing elements, or changing the viewpoint while preserving the original motion and timing. The output resolution matches the input video. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Describes what should appear in the output (1-1000 characters). | STRING | Yes | 1-1000 characters | +| `video` | Input video to edit. Must be 2-30 seconds at 30 fps or lower. | VIDEO | Yes | 2-30 seconds duration, 30 fps max | +| `seed` | Random seed for generation (default: 0). | INT | Yes | 0 to 4294967295 | +| `public_figure_threshold` | Content moderation for recognizable public figures (default: "low"). | COMBO | Yes | "auto"
"low" | +| `keyframes` | Guidance images anchored to the input video, from Aleph2 Keyframe nodes (up to 5). Use keyframes or prompt images, not both. | KEYFRAME | No | Up to 5 items | +| `prompt_images` | Guidance images anchored to the output video, from Aleph2 Prompt Image nodes (up to 5). Use keyframes or prompt images, not both. | PROMPT_IMAGE | No | Up to 5 items | + +**Important constraints:** +- The input video must be between 2 and 30 seconds long and have a frame rate of 30 fps or lower. +- You can use either `keyframes` or `prompt_images` for guidance, but not both at the same time. +- Each guidance input (keyframes or prompt images) supports a maximum of 5 items. +- Keyframe timestamps and prompt image timestamps must not exceed the input video duration. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `video` | The edited video generated by the Aleph2 model. | VIDEO | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2VideoToVideoNode/en.md) + +--- +**Source fingerprint (SHA-256):** `bda4d0f49843c1a8f311ddbce5911a2a157cae798a26f7a183b31fe41686d0b7` diff --git a/built-in-nodes/RunwayFirstLastFrameNode.mdx b/built-in-nodes/RunwayFirstLastFrameNode.mdx index 8e854b5a1..cc472f963 100644 --- a/built-in-nodes/RunwayFirstLastFrameNode.mdx +++ b/built-in-nodes/RunwayFirstLastFrameNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RunwayFirstLastFrameNode" icon: "circle" mode: wide --- + The Runway First-Last-Frame to Video node generates videos by uploading first and last keyframes along with a text prompt. It creates smooth transitions between the provided start and end frames using Runway's Gen-3 model. This is particularly useful for complex transitions where the end frame differs significantly from the start frame. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt for the generation (default: empty string) | STRING | Yes | N/A | | `start_frame` | Start frame to be used for the video | IMAGE | Yes | N/A | | `end_frame` | End frame to be used for the video. Supported for gen3a_turbo only. | IMAGE | Yes | N/A | @@ -28,10 +29,10 @@ The Runway First-Last-Frame to Video node generates videos by uploading first an ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video transitioning between the start and end frames | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayFirstLastFrameNode/en.md) --- -**Source fingerprint (SHA-256):** `a2d4839bf30bff3e3199a18129eb32c8495b8ea0c9ce209e9b3d00574de35399` +**Source fingerprint (SHA-256):** `469814fa2ac6d3fb539a4e4fb8a7e952c610f715816c7179a0c918edd47051eb` diff --git a/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx b/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx index 1904afae7..6a41652a4 100644 --- a/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx +++ b/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RunwayImageToVideoNodeGen3a" icon: "circle" mode: wide --- + The Runway Image to Video (Gen3a Turbo) node generates a video from a single starting frame using Runway's Gen3a Turbo model. It takes a text prompt and an initial image frame, then creates a video sequence based on the specified duration and aspect ratio. This node connects to Runway's API to process the generation remotely. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt for the generation (default: "") | STRING | Yes | N/A | | `start_frame` | Start frame to be used for the video | IMAGE | Yes | N/A | | `duration` | Video duration in seconds (default: "5") | COMBO | Yes | `"5"`
`"10"` | @@ -26,10 +27,10 @@ The Runway Image to Video (Gen3a Turbo) node generates a video from a single sta ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video sequence | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayImageToVideoNodeGen3a/en.md) --- -**Source fingerprint (SHA-256):** `ff88d2486746ab3ddf1b7a0c3184c54abd6bcb01e9743bc04c93e9c3a9e8d9ff` +**Source fingerprint (SHA-256):** `86d4c5468ca1a192e71f502d4d409a9813769c68aa464d113a012052a55d760e` diff --git a/built-in-nodes/RunwayImageToVideoNodeGen4.mdx b/built-in-nodes/RunwayImageToVideoNodeGen4.mdx index 9d32c81db..cb53b147b 100644 --- a/built-in-nodes/RunwayImageToVideoNodeGen4.mdx +++ b/built-in-nodes/RunwayImageToVideoNodeGen4.mdx @@ -5,15 +5,16 @@ sidebarTitle: "RunwayImageToVideoNodeGen4" icon: "circle" mode: wide --- + The Runway Image to Video (Gen4 Turbo) node generates a video from a single starting frame using Runway's Gen4 Turbo model. It takes a text prompt and an initial image frame, then creates a video sequence based on the provided duration and aspect ratio settings. The node handles uploading the starting frame to Runway's API and returns the generated video. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt for the generation (default: empty string) | STRING | Yes | - | | `start_frame` | Start frame to be used for the video | IMAGE | Yes | - | -| `duration` | Video duration in seconds (default: "5") | COMBO | Yes | `"5"`
`"10"` | +| `duration` | Video duration in seconds | COMBO | Yes | `"5"`
`"10"` | | `ratio` | Aspect ratio for the generated video (default: "1280:720") | COMBO | Yes | `"1280:720"`
`"720:1280"`
`"1104:832"`
`"832:1104"`
`"960:960"`
`"1584:672"` | | `seed` | Random seed for generation (default: 0) | INT | No | 0 to 4294967295 | @@ -26,10 +27,10 @@ The Runway Image to Video (Gen4 Turbo) node generates a video from a single star ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video based on the input frame and prompt | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayImageToVideoNodeGen4/en.md) --- -**Source fingerprint (SHA-256):** `0b5a2c351277b8c2247b4625fd030dd6f4de8dafd92f59a969575db1ba2f7fe9` +**Source fingerprint (SHA-256):** `1cbf70391f1dfd0f40a3085dad68b98ec20e964eab7d4a17b2fb3cd07a035277` diff --git a/built-in-nodes/RunwayTextToImageNode.mdx b/built-in-nodes/RunwayTextToImageNode.mdx index 500f003b3..dc72cc624 100644 --- a/built-in-nodes/RunwayTextToImageNode.mdx +++ b/built-in-nodes/RunwayTextToImageNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "RunwayTextToImageNode" icon: "circle" mode: wide --- + The Runway Text to Image node generates images from text prompts using Runway's Gen 4 model. You can provide a text description and optionally include a reference image to guide the image generation process. The node handles the API communication and returns the generated image. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text prompt for the generation (default: "") | STRING | Yes | - | | `ratio` | Aspect ratio for the generated image | COMBO | Yes | "16:9"
"1:1"
"21:9"
"2:3"
"3:2"
"4:5"
"5:4"
"9:16"
"9:21" | | `reference_image` | Optional reference image to guide the generation | IMAGE | No | - | @@ -20,10 +21,10 @@ The Runway Text to Image node generates images from text prompts using Runway's ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated image based on the text prompt and optional reference image | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayTextToImageNode/en.md) --- -**Source fingerprint (SHA-256):** `212eec9ae7ae3df06cefacae361cfd1f623ea7b6b1ca0e4beb4f5b7df76226e5` +**Source fingerprint (SHA-256):** `c9403da2e9ad8f663d3eea32eb549843696262e4472fc8d58c1f56ef9cc5aa7d` diff --git a/built-in-nodes/SAM3_Detect.mdx b/built-in-nodes/SAM3_Detect.mdx index 7569abb22..3b1f41ff7 100644 --- a/built-in-nodes/SAM3_Detect.mdx +++ b/built-in-nodes/SAM3_Detect.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SAM3_Detect" icon: "circle" mode: wide --- -# SAM3 Detect Node ## Overview diff --git a/built-in-nodes/SAM3_TrackPreview.mdx b/built-in-nodes/SAM3_TrackPreview.mdx index ce8195c23..07143e3e3 100644 --- a/built-in-nodes/SAM3_TrackPreview.mdx +++ b/built-in-nodes/SAM3_TrackPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_TrackPreview" icon: "circle" mode: wide --- + ## Overview This node creates a video preview of tracked objects, drawing each tracked object with a distinct color overlay and a number label. It does not output any image or video tensors — instead, it saves the resulting preview video directly to a temporary file. diff --git a/built-in-nodes/SAM3_TrackToMask.mdx b/built-in-nodes/SAM3_TrackToMask.mdx index f887dfd1a..aa9d3cf4f 100644 --- a/built-in-nodes/SAM3_TrackToMask.mdx +++ b/built-in-nodes/SAM3_TrackToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_TrackToMask" icon: "circle" mode: wide --- + ## Overview Selects specific tracked objects from a SAM3 tracking session by their index numbers and combines them into a single output mask. This allows you to choose which objects to keep and which to ignore from the tracking results. diff --git a/built-in-nodes/SAM3_VideoTrack.mdx b/built-in-nodes/SAM3_VideoTrack.mdx index 948a88457..d7cf9d28a 100644 --- a/built-in-nodes/SAM3_VideoTrack.mdx +++ b/built-in-nodes/SAM3_VideoTrack.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_VideoTrack" icon: "circle" mode: wide --- + ## Overview Track objects across video frames using SAM3's memory-based tracker. This node processes a sequence of video frames and maintains object identities across frames, using either initial masks or text prompts to define what to track. diff --git a/built-in-nodes/SCAIL2ColoredMask.mdx b/built-in-nodes/SCAIL2ColoredMask.mdx new file mode 100644 index 000000000..798f71447 --- /dev/null +++ b/built-in-nodes/SCAIL2ColoredMask.mdx @@ -0,0 +1,31 @@ +--- +title: "SCAIL2ColoredMask - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the SCAIL2ColoredMask node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "SCAIL2ColoredMask" +icon: "circle" +mode: wide +--- + +This node renders SAM3 tracking data into colored masks that are consumed by the WanSCAILToVideo node. It processes tracking data from a driving pose video and optionally a reference image, assigning consistent colors to each tracked person across both outputs. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `driving_track_data` | SAM3 track of the driving pose video. Will be rendered into the pose_video_mask output. | SAM3_TRACK_DATA | Yes | - | +| `ref_track_data` | SAM3 track of the reference image(s) (one identity per object, colored in batch order), or a plain MASK of the reference subject (rendered as a single identity). | SAM3_TRACK_DATA or MASK | No | - | +| `object_indices` | Comma-separated list of person indices to include (e.g. '0,2,3'). Applied to both reference and pose video masks. Empty = all. (default: "") | STRING | Yes | - | +| `sort_by` | Order in which palette colors are assigned to the tracked objects (applied to both reference and pose video so each identity keeps the same color). Objects that appear in earlier frames always come first; within a frame, left_to_right = leftmost object (by centroid at first appearance) gets the first color, area = biggest object (by mask area at first appearance) gets the first color; none = keep SAM3's order. (default: "left_to_right") | COMBO | Yes | `"none"`
`"left_to_right"`
`"area"` | +| `replacement_mode` | False = Animation Mode (pose_video_mask has black background, reference_image_mask has white background). True = Replacement Mode (pose_video_mask has white background, reference_image_mask has black background). (default: False) | BOOLEAN | Yes | False
True | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `pose_video_mask` | Colored mask rendered from the driving pose video tracking data. Background color follows replacement_mode setting. | IMAGE | +| `reference_image_mask` | Colored mask rendered from the reference image tracking data. Background is black in Replacement Mode, white in Animation Mode. If no reference data is provided, returns a solid fill matching the reference background color. | IMAGE | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SCAIL2ColoredMask/en.md) + +--- +**Source fingerprint (SHA-256):** `ce0669ad0ed3c76cc18ef0ee7b620f5aa6eaa1e5b96c189941c0a5b744c3351f` diff --git a/built-in-nodes/SDPoseDrawKeypoints.mdx b/built-in-nodes/SDPoseDrawKeypoints.mdx index d41fe5e9d..cadf7a8c8 100644 --- a/built-in-nodes/SDPoseDrawKeypoints.mdx +++ b/built-in-nodes/SDPoseDrawKeypoints.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDPoseDrawKeypoints" icon: "circle" mode: wide --- + The SDPoseDrawKeypoints node takes pose estimation data (keypoints) and draws them as a visual skeleton on a blank canvas. It allows you to selectively draw different parts of the pose, such as the body, hands, face, and feet, with customizable line widths and point sizes. The resulting image can be used for visualization or as input for other nodes that require a pose image. ## Inputs diff --git a/built-in-nodes/SDPoseFaceBBoxes.mdx b/built-in-nodes/SDPoseFaceBBoxes.mdx index d5bb3b3ff..b1935e291 100644 --- a/built-in-nodes/SDPoseFaceBBoxes.mdx +++ b/built-in-nodes/SDPoseFaceBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDPoseFaceBBoxes" icon: "circle" mode: wide --- + The SDPoseFaceBBoxes node processes pose keypoint data to detect and generate bounding boxes around human faces. It analyzes the 2D face keypoints for each person in a frame, calculates a bounding box based on those points, and can adjust the box's size and shape. The resulting bounding boxes are formatted to be compatible with other nodes in the SDPose workflow, such as the SDPoseKeypointExtractor. ## Inputs diff --git a/built-in-nodes/SDPoseKeypointExtractor.mdx b/built-in-nodes/SDPoseKeypointExtractor.mdx index 74e7f47f5..25f10e9c5 100644 --- a/built-in-nodes/SDPoseKeypointExtractor.mdx +++ b/built-in-nodes/SDPoseKeypointExtractor.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDPoseKeypointExtractor" icon: "circle" mode: wide --- + The SDPoseKeypointExtractor node detects human pose keypoints from input images using the SDPose model. It can process full images or specific regions defined by bounding boxes and outputs the detected keypoints in the OpenPose format, which includes the coordinates for each person and a confidence score for each keypoint. ## Inputs diff --git a/built-in-nodes/SDTurboScheduler.mdx b/built-in-nodes/SDTurboScheduler.mdx index 3a7a51f62..f4bc5d5e6 100644 --- a/built-in-nodes/SDTurboScheduler.mdx +++ b/built-in-nodes/SDTurboScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDTurboScheduler" icon: "circle" mode: wide --- + SDTurboScheduler is designed to generate a sequence of sigma values for image sampling, adjusting the sequence based on the denoise level and the number of steps specified. It leverages a specific model's sampling capabilities to produce these sigma values, which are crucial for controlling the denoising process during image generation. ## Inputs diff --git a/built-in-nodes/SD_4XUpscale_Conditioning.mdx b/built-in-nodes/SD_4XUpscale_Conditioning.mdx index 726116918..3cb9976d9 100644 --- a/built-in-nodes/SD_4XUpscale_Conditioning.mdx +++ b/built-in-nodes/SD_4XUpscale_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SD_4XUpscale_Conditioning" icon: "circle" mode: wide --- + The SD_4XUpscale_Conditioning node prepares conditioning data for upscaling images using diffusion models. It takes input images and conditioning data, then applies scaling and noise augmentation to create modified conditioning that guides the upscaling process. The node outputs both positive and negative conditioning along with latent representations for the upscaled dimensions. ## Inputs diff --git a/built-in-nodes/SUPIRApply.mdx b/built-in-nodes/SUPIRApply.mdx index f932261c7..1b2e6544a 100644 --- a/built-in-nodes/SUPIRApply.mdx +++ b/built-in-nodes/SUPIRApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SUPIRApply" icon: "circle" mode: wide --- + The SUPIRApply node applies a SUPIR model patch to a diffusion model. It uses the patch to modify the model's behavior, allowing it to incorporate guidance from an input image during the sampling process. The node also provides controls for adjusting the strength of this guidance over time and includes an optional feature to help maintain fidelity to the original input. ## Inputs diff --git a/built-in-nodes/SV3D_Conditioning.mdx b/built-in-nodes/SV3D_Conditioning.mdx index e909e0a81..0e460629a 100644 --- a/built-in-nodes/SV3D_Conditioning.mdx +++ b/built-in-nodes/SV3D_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SV3D_Conditioning" icon: "circle" mode: wide --- + The SV3D_Conditioning node prepares conditioning data for 3D video generation using the SV3D model. It takes an initial image and processes it through CLIP vision and VAE encoders to create positive and negative conditioning, along with a latent representation. The node generates camera elevation and azimuth sequences for multi-frame video generation based on the specified number of video frames. ## Inputs diff --git a/built-in-nodes/SVD_img2vid_Conditioning.mdx b/built-in-nodes/SVD_img2vid_Conditioning.mdx index c2770fac9..df2617508 100644 --- a/built-in-nodes/SVD_img2vid_Conditioning.mdx +++ b/built-in-nodes/SVD_img2vid_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SVD_img2vid_Conditioning" icon: "circle" mode: wide --- + The SVD_img2vid_Conditioning node prepares conditioning data for video generation using Stable Video Diffusion. It takes an initial image and processes it through CLIP vision and VAE encoders to create positive and negative conditioning pairs, along with an empty latent space for video generation. This node sets up the necessary parameters for controlling motion, frame rate, and augmentation levels in the generated video. ## Inputs diff --git a/built-in-nodes/SamplerARVideo.mdx b/built-in-nodes/SamplerARVideo.mdx index 324c764c5..63e1d270e 100644 --- a/built-in-nodes/SamplerARVideo.mdx +++ b/built-in-nodes/SamplerARVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerARVideo" icon: "circle" mode: wide --- + The Sampler AR Video node provides a specialized sampling method for autoregressive video models, such as those using Causal Forcing or Self-Forcing techniques. It manages all parameters related to the autoregressive (AR) loop directly within the workflow, making it easy to configure how the model generates video frames one step at a time. ## Inputs diff --git a/built-in-nodes/SamplerCustom.mdx b/built-in-nodes/SamplerCustom.mdx index 451756916..42d8767ea 100644 --- a/built-in-nodes/SamplerCustom.mdx +++ b/built-in-nodes/SamplerCustom.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerCustom" icon: "circle" mode: wide --- + The SamplerCustom node is designed to provide a flexible and customizable sampling mechanism for various applications. It enables users to select and configure different sampling strategies tailored to their specific needs, enhancing the adaptability and efficiency of the sampling process. ## Inputs diff --git a/built-in-nodes/SamplerCustomAdvanced.mdx b/built-in-nodes/SamplerCustomAdvanced.mdx index 0ebe37cd5..7f098c6cd 100644 --- a/built-in-nodes/SamplerCustomAdvanced.mdx +++ b/built-in-nodes/SamplerCustomAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerCustomAdvanced" icon: "circle" mode: wide --- + The SamplerCustomAdvanced node performs advanced latent space sampling using custom noise, guidance, and sampling configurations. It processes a latent image through a guided sampling process with customizable noise generation and sigma schedules, producing both the final sampled output and a denoised version when available. ## Inputs diff --git a/built-in-nodes/SamplerDPMAdaptative.mdx b/built-in-nodes/SamplerDPMAdaptative.mdx index 8c715e7f9..6bda2fcd1 100644 --- a/built-in-nodes/SamplerDPMAdaptative.mdx +++ b/built-in-nodes/SamplerDPMAdaptative.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMAdaptative" icon: "circle" mode: wide --- + The SamplerDPMAdaptative node implements an adaptive DPM (Diffusion Probabilistic Model) sampler that automatically adjusts step sizes during the sampling process. It uses tolerance-based error control to determine optimal step sizes, balancing computational efficiency with sampling accuracy. This adaptive approach helps maintain quality while potentially reducing the number of steps needed. ## Inputs diff --git a/built-in-nodes/SamplerDPMPP_2M_SDE.mdx b/built-in-nodes/SamplerDPMPP_2M_SDE.mdx index 4bac6588c..09f6fa4ce 100644 --- a/built-in-nodes/SamplerDPMPP_2M_SDE.mdx +++ b/built-in-nodes/SamplerDPMPP_2M_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_2M_SDE" icon: "circle" mode: wide --- + The SamplerDPMPP_2M_SDE node creates a DPM++ 2M SDE sampler for diffusion models. This sampler uses second-order differential equation solvers with stochastic differential equations to generate samples. It provides different solver types and noise handling options to control the sampling process. ## Inputs diff --git a/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx b/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx index 0d308ead5..f681b42f8 100644 --- a/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx +++ b/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_2S_Ancestral" icon: "circle" mode: wide --- + The SamplerDPMPP_2S_Ancestral node creates a sampler that uses the DPM++ 2S Ancestral sampling method for generating images. This sampler combines deterministic and stochastic elements to produce varied results while maintaining some consistency. It allows you to control the randomness and noise levels during the sampling process. ## Inputs diff --git a/built-in-nodes/SamplerDPMPP_3M_SDE.mdx b/built-in-nodes/SamplerDPMPP_3M_SDE.mdx index eee57724a..fc943e88a 100644 --- a/built-in-nodes/SamplerDPMPP_3M_SDE.mdx +++ b/built-in-nodes/SamplerDPMPP_3M_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_3M_SDE" icon: "circle" mode: wide --- + The SamplerDPMPP_3M_SDE node creates a DPM++ 3M SDE sampler for use in the sampling process. This sampler uses a third-order multistep stochastic differential equation method with configurable noise parameters. The node allows you to choose whether noise calculations are performed on the GPU or CPU. ## Inputs diff --git a/built-in-nodes/SamplerDPMPP_SDE.mdx b/built-in-nodes/SamplerDPMPP_SDE.mdx index 4e9506b31..d75621d21 100644 --- a/built-in-nodes/SamplerDPMPP_SDE.mdx +++ b/built-in-nodes/SamplerDPMPP_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_SDE" icon: "circle" mode: wide --- + The SamplerDPMPP_SDE node creates a DPM++ SDE (Stochastic Differential Equation) sampler for use in the sampling process. This sampler provides a stochastic sampling method with configurable noise parameters and device selection. It returns a sampler object that can be used in the sampling pipeline. ## Inputs diff --git a/built-in-nodes/SamplerDpmpp2mSde.mdx b/built-in-nodes/SamplerDpmpp2mSde.mdx index f528a4e52..32a24a8db 100644 --- a/built-in-nodes/SamplerDpmpp2mSde.mdx +++ b/built-in-nodes/SamplerDpmpp2mSde.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDpmpp2mSde" icon: "circle" mode: wide --- + This node is designed to generate a sampler for the DPMPP_2M_SDE model, allowing for the creation of samples based on specified solver types, noise levels, and computational device preferences. It abstracts the complexities of sampler configuration, providing a streamlined interface for generating samples with customized settings. ## Inputs diff --git a/built-in-nodes/SamplerDpmppSde.mdx b/built-in-nodes/SamplerDpmppSde.mdx index 7668faf35..af659f18f 100644 --- a/built-in-nodes/SamplerDpmppSde.mdx +++ b/built-in-nodes/SamplerDpmppSde.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDpmppSde" icon: "circle" mode: wide --- + This node is designed to generate a sampler for the DPM++ SDE (Stochastic Differential Equation) model. It adapts to both CPU and GPU execution environments, optimizing the sampler's implementation based on the available hardware. ## Inputs diff --git a/built-in-nodes/SamplerER_SDE.mdx b/built-in-nodes/SamplerER_SDE.mdx index ff101ec99..f3a348f92 100644 --- a/built-in-nodes/SamplerER_SDE.mdx +++ b/built-in-nodes/SamplerER_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerER_SDE" icon: "circle" mode: wide --- + The SamplerER_SDE node provides specialized sampling methods for diffusion models, offering different solver types including ER-SDE, Reverse-time SDE, and ODE approaches. It allows control over the stochastic behavior and computational stages of the sampling process. The node automatically adjusts parameters based on the selected solver type to ensure proper functionality. ## Inputs diff --git a/built-in-nodes/SamplerEulerAncestral.mdx b/built-in-nodes/SamplerEulerAncestral.mdx index 1b4106d05..f117596c3 100644 --- a/built-in-nodes/SamplerEulerAncestral.mdx +++ b/built-in-nodes/SamplerEulerAncestral.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerAncestral" icon: "circle" mode: wide --- + The SamplerEulerAncestral node creates an Euler Ancestral sampler for generating images. This sampler uses a specific mathematical approach that combines Euler integration with ancestral sampling techniques to produce image variations. The node allows you to configure the sampling behavior by adjusting parameters that control the randomness and step size during the generation process. ## Inputs diff --git a/built-in-nodes/SamplerEulerAncestralCFGPP.mdx b/built-in-nodes/SamplerEulerAncestralCFGPP.mdx index 4441b3f1b..77e7c3711 100644 --- a/built-in-nodes/SamplerEulerAncestralCFGPP.mdx +++ b/built-in-nodes/SamplerEulerAncestralCFGPP.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerAncestralCFGPP" icon: "circle" mode: wide --- + The SamplerEulerAncestralCFGPP node creates a sampler that uses the Euler Ancestral method with classifier-free guidance (CFG++) for image generation. This sampler combines ancestral sampling techniques with guidance conditioning to produce diverse image variations while maintaining coherence, and allows fine-tuning through parameters that control noise and step size adjustments. ## Inputs diff --git a/built-in-nodes/SamplerEulerCFGpp.mdx b/built-in-nodes/SamplerEulerCFGpp.mdx index 78b3ce60c..7e67dce06 100644 --- a/built-in-nodes/SamplerEulerCFGpp.mdx +++ b/built-in-nodes/SamplerEulerCFGpp.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerCFGpp" icon: "circle" mode: wide --- + The SamplerEulerCFGpp node provides an Euler CFG++ sampling method for generating outputs. This node offers two different implementation versions of the Euler CFG++ sampler that can be selected based on user preference. ## Inputs diff --git a/built-in-nodes/SamplerLCM.mdx b/built-in-nodes/SamplerLCM.mdx index 65f7fe076..39b16dd57 100644 --- a/built-in-nodes/SamplerLCM.mdx +++ b/built-in-nodes/SamplerLCM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLCM" icon: "circle" mode: wide --- + The SamplerLCM node provides an LCM (Latent Consistency Model) sampler with tunable per-step noise parameters. It allows you to control the noise applied at each sampling step, enabling fine-grained adjustment of the sampling process. ## Inputs diff --git a/built-in-nodes/SamplerLCMUpscale.mdx b/built-in-nodes/SamplerLCMUpscale.mdx index 9ba7b3847..d07aff6bb 100644 --- a/built-in-nodes/SamplerLCMUpscale.mdx +++ b/built-in-nodes/SamplerLCMUpscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLCMUpscale" icon: "circle" mode: wide --- + The SamplerLCMUpscale node provides a specialized sampling method that combines Latent Consistency Model (LCM) sampling with image upscaling capabilities. It allows you to upscale images during the sampling process using various interpolation methods, making it useful for generating higher resolution outputs while maintaining image quality. ## Inputs diff --git a/built-in-nodes/SamplerLMS.mdx b/built-in-nodes/SamplerLMS.mdx index aa7200cd1..64f1276a8 100644 --- a/built-in-nodes/SamplerLMS.mdx +++ b/built-in-nodes/SamplerLMS.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLMS" icon: "circle" mode: wide --- + The SamplerLMS node creates a Least Mean Squares (LMS) sampler for use in diffusion models. It generates a sampler object that can be used in the sampling process, allowing you to control the order of the LMS algorithm for numerical stability and accuracy. ## Inputs diff --git a/built-in-nodes/SamplerSASolver.mdx b/built-in-nodes/SamplerSASolver.mdx index 9306138c3..d3c42a5f2 100644 --- a/built-in-nodes/SamplerSASolver.mdx +++ b/built-in-nodes/SamplerSASolver.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerSASolver" icon: "circle" mode: wide --- + The SamplerSASolver node implements a custom sampling algorithm for diffusion models. It uses a predictor-corrector approach with configurable order settings and stochastic differential equation (SDE) parameters to generate samples from the input model. ## Inputs diff --git a/built-in-nodes/SamplerSEEDS2.mdx b/built-in-nodes/SamplerSEEDS2.mdx index b1c199154..8009220d3 100644 --- a/built-in-nodes/SamplerSEEDS2.mdx +++ b/built-in-nodes/SamplerSEEDS2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerSEEDS2" icon: "circle" mode: wide --- + This node provides a configurable sampler for generating images. It implements the SEEDS-2 algorithm, which is a stochastic differential equation (SDE) solver. By adjusting its parameters, you can configure it to behave like several specific samplers, including `seeds_2`, `exp_heun_2_x0`, and `exp_heun_2_x0_sde`. ## Inputs diff --git a/built-in-nodes/SamplingPercentToSigma.mdx b/built-in-nodes/SamplingPercentToSigma.mdx index 4ca3fa259..71432080f 100644 --- a/built-in-nodes/SamplingPercentToSigma.mdx +++ b/built-in-nodes/SamplingPercentToSigma.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplingPercentToSigma" icon: "circle" mode: wide --- + The SamplingPercentToSigma node converts a sampling percentage value to a corresponding sigma value using the model's sampling parameters. It takes a percentage value between 0.0 and 1.0 and maps it to the appropriate sigma value in the model's noise schedule, with options to return either the calculated sigma or the actual maximum/minimum sigma values at the boundaries. ## Inputs diff --git a/built-in-nodes/SaveAnimatedPNG.mdx b/built-in-nodes/SaveAnimatedPNG.mdx index e97e8ff04..ba1f6c025 100644 --- a/built-in-nodes/SaveAnimatedPNG.mdx +++ b/built-in-nodes/SaveAnimatedPNG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAnimatedPNG" icon: "circle" mode: wide --- + The SaveAnimatedPNG node is designed for creating and saving animated PNG images from a sequence of frames. It handles the assembly of individual image frames into a cohesive animation, allowing for customization of frame duration, looping, and metadata inclusion. ## Inputs diff --git a/built-in-nodes/SaveAnimatedWEBP.mdx b/built-in-nodes/SaveAnimatedWEBP.mdx index f8df91f39..03f956df5 100644 --- a/built-in-nodes/SaveAnimatedWEBP.mdx +++ b/built-in-nodes/SaveAnimatedWEBP.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAnimatedWEBP" icon: "circle" mode: wide --- + This node is designed for saving a sequence of images as an animated WEBP file. It handles the aggregation of individual frames into a cohesive animation, applying specified metadata, and optimizing the output based on quality and compression settings. ## Inputs diff --git a/built-in-nodes/SaveAudio.mdx b/built-in-nodes/SaveAudio.mdx index 7510c8ac9..2ddf8840d 100644 --- a/built-in-nodes/SaveAudio.mdx +++ b/built-in-nodes/SaveAudio.mdx @@ -5,12 +5,13 @@ sidebarTitle: "SaveAudio" icon: "circle" mode: wide --- -The SaveAudio node saves audio data to a file in FLAC format. It takes audio input and writes it to the specified output directory with the given filename prefix. The node automatically handles file naming and ensures the audio is properly saved for later use. + +The SaveAudio node saves audio data to a file in FLAC format. It takes audio input and writes it to the specified output directory with the given filename prefix. This node is deprecated and should be replaced with the current Save Audio node. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `audio` | The audio data to be saved | AUDIO | Yes | - | | `filename_prefix` | The prefix for the output filename (default: "audio/ComfyUI") | STRING | No | - | @@ -19,10 +20,10 @@ The SaveAudio node saves audio data to a file in FLAC format. It takes audio inp ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | *None* | This node does not return any output data but saves the audio file to the output directory | - | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudio/en.md) --- -**Source fingerprint (SHA-256):** `fddb5b1b2e103efa18cd367969193b25753a08e9a56420c39df4645894006ac2` +**Source fingerprint (SHA-256):** `7c8b7aefb438ce8463cb277e044a118af1a8e8a9f7e90aac4d33ad60544903bd` diff --git a/built-in-nodes/SaveAudioAdvanced.mdx b/built-in-nodes/SaveAudioAdvanced.mdx index 0a7a446c6..96ecd64c5 100644 --- a/built-in-nodes/SaveAudioAdvanced.mdx +++ b/built-in-nodes/SaveAudioAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveAudioAdvanced" icon: "circle" mode: wide --- -# Save Audio (Advanced) Saves the input audio to your ComfyUI output directory. This node allows you to export audio in various formats including FLAC, MP3, and Opus with configurable quality settings. diff --git a/built-in-nodes/SaveAudioMP3.mdx b/built-in-nodes/SaveAudioMP3.mdx index 93b73bb16..1a56356aa 100644 --- a/built-in-nodes/SaveAudioMP3.mdx +++ b/built-in-nodes/SaveAudioMP3.mdx @@ -5,25 +5,28 @@ sidebarTitle: "SaveAudioMP3" icon: "circle" mode: wide --- -The SaveAudioMP3 node saves audio data as an MP3 file. It takes audio input and exports it to the specified output directory with customizable filename and quality settings. The node automatically handles file naming and format conversion to create a playable MP3 file. + +The SaveAudioMP3 node saves audio data as an MP3 file. It takes audio input and exports it to the specified output directory with customizable filename and quality settings. The node automatically handles file naming and format conversion to create a playable MP3 file. **This node is deprecated and may be removed in future versions.** ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `audio` | The audio data to be saved as an MP3 file | AUDIO | Yes | - | | `filename_prefix` | The prefix for the output filename (default: "audio/ComfyUI") | STRING | No | - | -| `quality` | The audio quality setting for the MP3 file (default: "V0") | STRING | No | "V0"
"128k"
"320k" | +| `quality` | The audio quality setting for the MP3 file (default: "V0") | STRING | No | `"V0"`
`"128k"`
`"320k"` | | `prompt` | Internal prompt data (automatically provided by the system) | PROMPT | No | - | | `extra_pnginfo` | Additional PNG information (automatically provided by the system) | EXTRA_PNGINFO | No | - | +**Note:** If the input `audio` is None (for example, when the source video has no audio track), the node will raise a ValueError. + ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | *None* | This node does not return any output data, but saves the audio file to the output directory | - | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioMP3/en.md) --- -**Source fingerprint (SHA-256):** `b238008410f7e8d65b07d79f12cad2cf2ead1fd105bc881a3bef87ab4e71f484` +**Source fingerprint (SHA-256):** `7274988c40c063e1bb4f46010ec722bb9e660d8f9414ec7a618a07b808f89208` diff --git a/built-in-nodes/SaveAudioOpus.mdx b/built-in-nodes/SaveAudioOpus.mdx index 70b89a4d6..1f0c38562 100644 --- a/built-in-nodes/SaveAudioOpus.mdx +++ b/built-in-nodes/SaveAudioOpus.mdx @@ -5,12 +5,13 @@ sidebarTitle: "SaveAudioOpus" icon: "circle" mode: wide --- -The SaveAudioOpus node saves audio data to an Opus format file. It takes audio input and exports it as a compressed Opus file with configurable quality settings. The node automatically handles file naming and saves the output to the designated output directory. + +The SaveAudioOpus node saves audio data to an Opus format file. It takes audio input and exports it as a compressed Opus file with configurable quality settings. This node is deprecated and may be removed in future versions. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `audio` | The audio data to be saved as an Opus file | AUDIO | Yes | - | | `filename_prefix` | The prefix for the output filename (default: "audio/ComfyUI") | STRING | No | - | | `quality` | The audio quality setting for the Opus file (default: "128k") | COMBO | No | "64k"
"96k"
"128k"
"192k"
"320k" | @@ -18,10 +19,10 @@ The SaveAudioOpus node saves audio data to an Opus format file. It takes audio i ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | - | This node does not return any output values. It saves the audio file to disk as its primary function. | - | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioOpus/en.md) --- -**Source fingerprint (SHA-256):** `d793d9ef7da6bd3f9257ad16ab9dc5b31a16354a2dff1449afcb6980b9e1dc63` +**Source fingerprint (SHA-256):** `37b6eaa7961d6602e9bb7f3233ad8542ca6cc694247ccd2d1334db8b96338071` diff --git a/built-in-nodes/SaveGLB.mdx b/built-in-nodes/SaveGLB.mdx index e7180d17b..1ddc28f10 100644 --- a/built-in-nodes/SaveGLB.mdx +++ b/built-in-nodes/SaveGLB.mdx @@ -5,22 +5,23 @@ sidebarTitle: "SaveGLB" icon: "circle" mode: wide --- -The SaveGLB node saves 3D mesh data or 3D files to the output directory. It accepts mesh data or various 3D file formats (GLB, GLTF, OBJ, FBX, STL, USDZ) and exports them with a specified filename prefix. When saving mesh data, it can handle multiple meshes and automatically adds workflow metadata to the files when metadata is enabled. + +The SaveGLB node saves 3D mesh data or 3D files to the output directory. It accepts mesh data or various 3D file formats and exports them with a specified filename prefix. When saving mesh data, it can handle multiple meshes and automatically adds workflow metadata to the files when metadata is enabled. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `mesh` | Mesh or 3D file to save. Accepts mesh data or 3D file formats including GLB, GLTF, OBJ, FBX, STL, and USDZ | MESH or FILE3D | Yes | - | +|-----------|-------------|-----------|----------|-------| +| `mesh` | Mesh or 3D file to save. Accepts mesh data or 3D file formats including GLB, GLTF, OBJ, FBX, STL, USDZ, PLY, SPLAT, SPZ, KSPLAT, and any splat or point cloud format | MESH or FILE3D | Yes | - | | `filename_prefix` | The prefix for the output filename (default: "3d/ComfyUI") | STRING | No | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `ui` | Displays the saved 3D files in the user interface with filename, subfolder, and type information | UI | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveGLB/en.md) --- -**Source fingerprint (SHA-256):** `ed56f61f60afea7dfbcae8b222aa7129608e3b10bc0daa27934b8c0cbeb1c0e8` +**Source fingerprint (SHA-256):** `bee2497160a7fbd2cd43900e66faca4b3b5797cdc7c7f99b85ca063836616430` diff --git a/built-in-nodes/SaveImage.mdx b/built-in-nodes/SaveImage.mdx index ef6e85908..3c1e47019 100644 --- a/built-in-nodes/SaveImage.mdx +++ b/built-in-nodes/SaveImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImage" icon: "circle" mode: wide --- + The SaveImage node saves the images it receives to your `ComfyUI/output` directory. It saves each image as a PNG file and can embed workflow metadata, such as the prompt, into the saved file for future reference. ## Inputs diff --git a/built-in-nodes/SaveImageAdvanced.mdx b/built-in-nodes/SaveImageAdvanced.mdx index 7c4becdcd..dbf075b4e 100644 --- a/built-in-nodes/SaveImageAdvanced.mdx +++ b/built-in-nodes/SaveImageAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveImageAdvanced" icon: "circle" mode: wide --- -# SaveImageAdvanced The **SaveImageAdvanced** node saves images to your ComfyUI output directory with advanced control over file format, bit depth, and color space. It supports saving as PNG or EXR files and can embed workflow metadata into the saved files. diff --git a/built-in-nodes/SaveImageDataSetToFolder.mdx b/built-in-nodes/SaveImageDataSetToFolder.mdx index ce18cbaf8..fb36d40ae 100644 --- a/built-in-nodes/SaveImageDataSetToFolder.mdx +++ b/built-in-nodes/SaveImageDataSetToFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImageDataSetToFolder" icon: "circle" mode: wide --- + This node saves a list of images to a specified folder within ComfyUI's output directory. It takes multiple images as input and writes them to disk with a customizable filename prefix. ## Inputs diff --git a/built-in-nodes/SaveImageTextDataSetToFolder.mdx b/built-in-nodes/SaveImageTextDataSetToFolder.mdx index 8abf03048..c47211b32 100644 --- a/built-in-nodes/SaveImageTextDataSetToFolder.mdx +++ b/built-in-nodes/SaveImageTextDataSetToFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImageTextDataSetToFolder" icon: "circle" mode: wide --- + The Save Image and Text Dataset to Folder node saves a list of images and their corresponding text captions to a specified folder within ComfyUI's output directory. For each image saved as a PNG file, a matching text file with the same base name is created to store its caption. This is useful for creating organized datasets of generated images and their descriptions. ## Inputs diff --git a/built-in-nodes/SaveLatent.mdx b/built-in-nodes/SaveLatent.mdx index 35007e462..a43ec3930 100644 --- a/built-in-nodes/SaveLatent.mdx +++ b/built-in-nodes/SaveLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLatent" icon: "circle" mode: wide --- + The SaveLatent node saves latent tensors to disk as files for later use or sharing. It takes latent samples and saves them to the output directory with optional metadata including prompt information. The node automatically handles file naming and organization while preserving the latent data structure. ## Inputs diff --git a/built-in-nodes/SaveLoRA.mdx b/built-in-nodes/SaveLoRA.mdx index 73b3af586..8ed2eb996 100644 --- a/built-in-nodes/SaveLoRA.mdx +++ b/built-in-nodes/SaveLoRA.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLoRA" icon: "circle" mode: wide --- + The SaveLoRA node saves a LoRA (Low-Rank Adaptation) model to a file. It takes a LoRA model as input and writes it to a `.safetensors` file in the output directory. You can specify a filename prefix and an optional step count to be included in the final filename. ## Inputs diff --git a/built-in-nodes/SaveLoRANode.mdx b/built-in-nodes/SaveLoRANode.mdx index 06464b48b..5a5fa464d 100644 --- a/built-in-nodes/SaveLoRANode.mdx +++ b/built-in-nodes/SaveLoRANode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLoRANode" icon: "circle" mode: wide --- + The SaveLoRA node saves LoRA (Low-Rank Adaptation) models to your output directory. It takes a LoRA model as input and creates a safetensors file with an automatically generated filename. You can customize the filename prefix and optionally include the training step count in the filename for better organization. ## Inputs diff --git a/built-in-nodes/SaveSVGNode.mdx b/built-in-nodes/SaveSVGNode.mdx index 21d8ced83..8823f7d48 100644 --- a/built-in-nodes/SaveSVGNode.mdx +++ b/built-in-nodes/SaveSVGNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveSVGNode" icon: "circle" mode: wide --- + Save SVG files on disk. This node takes SVG data as input and saves it to your output directory with optional metadata embedding. The node automatically handles file naming with counter suffixes and can embed workflow prompt information directly into the SVG file. ## Inputs diff --git a/built-in-nodes/SaveTrainingDataset.mdx b/built-in-nodes/SaveTrainingDataset.mdx index 7eed23a8d..49baeddbb 100644 --- a/built-in-nodes/SaveTrainingDataset.mdx +++ b/built-in-nodes/SaveTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveTrainingDataset" icon: "circle" mode: wide --- + This node saves a prepared training dataset to your computer's hard drive. It takes encoded data, which includes image latents and their corresponding text conditioning, and organizes them into multiple smaller files called shards for easier management. The node automatically creates a folder in your output directory and saves both the data files and a metadata file describing the dataset. ## Inputs diff --git a/built-in-nodes/SaveVideo.mdx b/built-in-nodes/SaveVideo.mdx index cc7a9b92d..8ee01bbfe 100644 --- a/built-in-nodes/SaveVideo.mdx +++ b/built-in-nodes/SaveVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveVideo" icon: "circle" mode: wide --- + The SaveVideo node saves input video content to your ComfyUI output directory. It allows you to specify the filename prefix, video format, and codec for the saved file. The node automatically handles file naming with counter increments and can include workflow metadata in the saved video. ## Inputs diff --git a/built-in-nodes/SaveWEBM.mdx b/built-in-nodes/SaveWEBM.mdx index a96149164..c20b0dcff 100644 --- a/built-in-nodes/SaveWEBM.mdx +++ b/built-in-nodes/SaveWEBM.mdx @@ -5,25 +5,28 @@ sidebarTitle: "SaveWEBM" icon: "circle" mode: wide --- + The SaveWEBM node saves a sequence of images as a WEBM video file. It takes multiple input images and encodes them into a video using either VP9 or AV1 codec with configurable quality settings and frame rate. The resulting video file is saved to the output directory with metadata including prompt information. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `images` | Sequence of input images to encode as video frames | IMAGE | Yes | - | +|-----------|-------------|-----------|----------|-------| +| `images` | RGBA images are saved with their alpha channel as transparency (vp9 codec only) | IMAGE | Yes | - | | `filename_prefix` | Prefix for the output filename (default: "ComfyUI") | STRING | No | - | | `codec` | Video codec to use for encoding | COMBO | Yes | "vp9"
"av1" | | `fps` | Frame rate for the output video (default: 24.0) | FLOAT | No | 0.01-1000.0 | -| `crf` | Quality setting where higher crf means lower quality with smaller file size, lower crf means higher quality with larger file size (default: 32.0) | FLOAT | No | 0-63.0 | +| `crf` | Higher crf means lower quality with a smaller file size, lower crf means higher quality higher filesize (default: 32.0) | FLOAT | No | 0-63.0 | + +**Note on alpha channel:** The alpha channel from RGBA images is only preserved when using the VP9 codec. When using the AV1 codec, the alpha channel is ignored and only RGB data is encoded. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `ui` | Video preview showing the saved WEBM file | PREVIEW | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveWEBM/en.md) --- -**Source fingerprint (SHA-256):** `7ed734af0f4af835c5b52a91389666ec1e0101458aa0f639ef5eeabf1968bfcc` +**Source fingerprint (SHA-256):** `8125a855dc2626eaae99ff63e6e0ae907e3187a1f5110e59b63733216de75073` diff --git a/built-in-nodes/ScaleROPE.mdx b/built-in-nodes/ScaleROPE.mdx index b99cdf396..1ae737227 100644 --- a/built-in-nodes/ScaleROPE.mdx +++ b/built-in-nodes/ScaleROPE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ScaleROPE" icon: "circle" mode: wide --- + The ScaleROPE node allows you to modify the Rotary Position Embedding (ROPE) of a model by applying separate scaling and shifting factors to its X, Y, and T (time) components. This is an advanced, experimental node used to adjust the model's positional encoding behavior. ## Inputs diff --git a/built-in-nodes/Sd4xupscaleConditioning.mdx b/built-in-nodes/Sd4xupscaleConditioning.mdx index 10d278028..1aab9bcc1 100644 --- a/built-in-nodes/Sd4xupscaleConditioning.mdx +++ b/built-in-nodes/Sd4xupscaleConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Sd4xupscaleConditioning" icon: "circle" mode: wide --- + This node specializes in enhancing the resolution of images through a 4x upscale process, incorporating conditioning elements to refine the output. It leverages diffusion techniques to upscale images while allowing for the adjustment of scale ratio and noise augmentation to fine-tune the enhancement process. ## Inputs diff --git a/built-in-nodes/SeedNode.mdx b/built-in-nodes/SeedNode.mdx new file mode 100644 index 000000000..33ff4c40d --- /dev/null +++ b/built-in-nodes/SeedNode.mdx @@ -0,0 +1,26 @@ +--- +title: "SeedNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the SeedNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "SeedNode" +icon: "circle" +mode: wide +--- + +The Seed node generates a fixed or random integer value. It is commonly used to control the reproducibility of random operations in other nodes by providing a consistent starting point for their random number generation. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `seed` | The seed value to use. The control after generate option determines whether the value stays fixed or changes after each generation. | INT | Yes | 0 to 9223372036854775807 | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `seed` | The generated seed value. | INT | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SeedNode/en.md) + +--- +**Source fingerprint (SHA-256):** `19f9b22945bb152ff5066195067f1b6b4c006589f26c7533fad905044ac3b7fa` diff --git a/built-in-nodes/SeedVR2Conditioning.mdx b/built-in-nodes/SeedVR2Conditioning.mdx index e8275c042..0dc56871f 100644 --- a/built-in-nodes/SeedVR2Conditioning.mdx +++ b/built-in-nodes/SeedVR2Conditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2Conditioning" icon: "circle" mode: wide --- -# Apply SeedVR2 Conditioning This node builds positive and negative conditioning from a VAE latent for use with the SeedVR2 model. It prepares the conditioning data that guides the image or video generation process. diff --git a/built-in-nodes/SeedVR2PostProcessing.mdx b/built-in-nodes/SeedVR2PostProcessing.mdx index 1cc700dc4..ea0b0ac15 100644 --- a/built-in-nodes/SeedVR2PostProcessing.mdx +++ b/built-in-nodes/SeedVR2PostProcessing.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2PostProcessing" icon: "circle" mode: wide --- -# Post-Process SeedVR2 Output This node aligns the generated image with the original resized image and applies optional color correction. It takes the output from a SeedVR2 upscaling process and adjusts it to match the colors and dimensions of the original reference image. diff --git a/built-in-nodes/SeedVR2Preprocess.mdx b/built-in-nodes/SeedVR2Preprocess.mdx index 198dcf9d2..24129df17 100644 --- a/built-in-nodes/SeedVR2Preprocess.mdx +++ b/built-in-nodes/SeedVR2Preprocess.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2Preprocess" icon: "circle" mode: wide --- -# Pre-Process SeedVR2 Input This node pads a resized image to prepare it for the SeedVR2 model. It removes the alpha channel during processing, which is later restored by the companion Post-Process SeedVR2 Output node using the original resized image. diff --git a/built-in-nodes/SeedVR2ProgressiveSampler.mdx b/built-in-nodes/SeedVR2ProgressiveSampler.mdx index 78a5673ee..bafd2e759 100644 --- a/built-in-nodes/SeedVR2ProgressiveSampler.mdx +++ b/built-in-nodes/SeedVR2ProgressiveSampler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2ProgressiveSampler" icon: "circle" mode: wide --- -# SeedVR2ProgressiveSampler Sequential temporal chunking sampler for SeedVR2 native workflows. This node processes long video latents by splitting them into smaller temporal chunks, sampling each chunk sequentially, and blending the results together. It serves as a drop-in replacement for the standard KSampler when working with SeedVR2 models on sequences that would otherwise cause out-of-memory errors. diff --git a/built-in-nodes/SelectCLIPDevice.mdx b/built-in-nodes/SelectCLIPDevice.mdx index 0dff964a6..f087c25cb 100644 --- a/built-in-nodes/SelectCLIPDevice.mdx +++ b/built-in-nodes/SelectCLIPDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectCLIPDevice" icon: "circle" mode: wide --- + ## Overview The Select CLIP Device node lets you choose which device (CPU or a specific GPU) the CLIP text encoder runs on. By default, the device is assigned by the model loader, but you can override it to use the CPU or a particular GPU. If the requested device doesn't exist on your machine, the node simply passes the CLIP through unchanged and logs a message instead of causing an error. diff --git a/built-in-nodes/SelectModelDevice.mdx b/built-in-nodes/SelectModelDevice.mdx index d38a8a9e8..709abb17a 100644 --- a/built-in-nodes/SelectModelDevice.mdx +++ b/built-in-nodes/SelectModelDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectModelDevice" icon: "circle" mode: wide --- + ## Overview The SelectModelDevice node allows you to manually choose which device (CPU or a specific GPU) a diffusion model runs on. It can move a model to a different device, and it handles conflicts with other multi-GPU nodes automatically. diff --git a/built-in-nodes/SelectVAEDevice.mdx b/built-in-nodes/SelectVAEDevice.mdx index 29dfcc77b..4bf9c8b5a 100644 --- a/built-in-nodes/SelectVAEDevice.mdx +++ b/built-in-nodes/SelectVAEDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectVAEDevice" icon: "circle" mode: wide --- + ## Overview This node allows you to manually select which GPU device the VAE model should be placed on. By default, the VAE is placed on the device assigned by the model loader, but you can pin it to a specific GPU (e.g., `gpu:0`, `gpu:1`). If the selected device is not available on your machine, the node will pass the VAE through unchanged and log a message instead of failing. diff --git a/built-in-nodes/SelfAttentionGuidance.mdx b/built-in-nodes/SelfAttentionGuidance.mdx index 1e770827e..3d82f18e7 100644 --- a/built-in-nodes/SelfAttentionGuidance.mdx +++ b/built-in-nodes/SelfAttentionGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelfAttentionGuidance" icon: "circle" mode: wide --- + The Self-Attention Guidance node applies guidance to diffusion models by modifying the attention mechanism during the sampling process. It captures attention scores from unconditional denoising steps and uses them to create blurred guidance maps that influence the final output. This technique helps guide the generation process by leveraging the model's own attention patterns. ## Inputs diff --git a/built-in-nodes/SetClipHooks.mdx b/built-in-nodes/SetClipHooks.mdx index eb851e9e4..e7194df60 100644 --- a/built-in-nodes/SetClipHooks.mdx +++ b/built-in-nodes/SetClipHooks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetClipHooks" icon: "circle" mode: wide --- + The SetClipHooks node allows you to apply custom hooks to a CLIP model, enabling advanced modifications to its behavior. It can apply hooks to conditioning outputs and optionally enable clip scheduling functionality. This node creates a cloned copy of the input CLIP model with the specified hook configurations applied. ## Inputs diff --git a/built-in-nodes/SetFirstSigma.mdx b/built-in-nodes/SetFirstSigma.mdx index 26ca5e156..be8cfa8bd 100644 --- a/built-in-nodes/SetFirstSigma.mdx +++ b/built-in-nodes/SetFirstSigma.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetFirstSigma" icon: "circle" mode: wide --- + The SetFirstSigma node modifies a sequence of sigma values by replacing the first sigma value in the sequence with a custom value. It takes an existing sigma sequence and a new sigma value as inputs, then returns a new sigma sequence where only the first element has been changed while keeping all other sigma values unchanged. ## Inputs diff --git a/built-in-nodes/SetHookKeyframes.mdx b/built-in-nodes/SetHookKeyframes.mdx index f114b2632..74bdbdc5b 100644 --- a/built-in-nodes/SetHookKeyframes.mdx +++ b/built-in-nodes/SetHookKeyframes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetHookKeyframes" icon: "circle" mode: wide --- + The Set Hook Keyframes node allows you to apply keyframe scheduling to existing hook groups. It takes a hook group and optionally applies keyframe timing information to control when different hooks are executed during the generation process. When keyframes are provided, the node clones the hook group and sets the keyframe timing on all hooks within the group. ## Inputs diff --git a/built-in-nodes/SetLatentNoiseMask.mdx b/built-in-nodes/SetLatentNoiseMask.mdx index 067db636e..f45c96810 100644 --- a/built-in-nodes/SetLatentNoiseMask.mdx +++ b/built-in-nodes/SetLatentNoiseMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetLatentNoiseMask" icon: "circle" mode: wide --- + This node is designed to apply a noise mask to a set of latent samples. It modifies the input samples by integrating a specified mask, thereby altering their noise characteristics. ## Inputs diff --git a/built-in-nodes/SetModelHooksOnCond.mdx b/built-in-nodes/SetModelHooksOnCond.mdx index cdb174e78..74e791224 100644 --- a/built-in-nodes/SetModelHooksOnCond.mdx +++ b/built-in-nodes/SetModelHooksOnCond.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetModelHooksOnCond" icon: "circle" mode: wide --- + This node attaches custom hooks to conditioning data, allowing you to intercept and modify the conditioning process during model execution. It takes a set of hooks and applies them to the provided conditioning data, enabling advanced customization of the text-to-image generation workflow. The modified conditioning with attached hooks is then returned for use in subsequent processing steps. ## Inputs diff --git a/built-in-nodes/SetUnionControlNetType.mdx b/built-in-nodes/SetUnionControlNetType.mdx index 0c939adb2..e4d8fe13e 100644 --- a/built-in-nodes/SetUnionControlNetType.mdx +++ b/built-in-nodes/SetUnionControlNetType.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetUnionControlNetType" icon: "circle" mode: wide --- + The SetUnionControlNetType node allows you to specify the type of control network to use for conditioning. It takes an existing control network and sets its control type based on your selection, creating a modified copy of the control network with the specified type configuration. ## Inputs diff --git a/built-in-nodes/ShuffleDataset.mdx b/built-in-nodes/ShuffleDataset.mdx index 4303bfb40..909d2eb5d 100644 --- a/built-in-nodes/ShuffleDataset.mdx +++ b/built-in-nodes/ShuffleDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ShuffleDataset" icon: "circle" mode: wide --- + The Shuffle Dataset node takes a list of images and randomly changes their order. It uses a seed value to control the randomness, ensuring the same shuffle order can be reproduced. This is useful for randomizing the sequence of images in a dataset before processing. ## Inputs diff --git a/built-in-nodes/ShuffleImageTextDataset.mdx b/built-in-nodes/ShuffleImageTextDataset.mdx index ea6566f04..44c36f2bb 100644 --- a/built-in-nodes/ShuffleImageTextDataset.mdx +++ b/built-in-nodes/ShuffleImageTextDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ShuffleImageTextDataset" icon: "circle" mode: wide --- + This node shuffles a list of images and a list of texts together, keeping their pairings intact. It uses a random seed to determine the shuffle order, ensuring the same input lists will be shuffled in the same way each time the seed is reused. ## Inputs diff --git a/built-in-nodes/SkipLayerGuidanceDiT.mdx b/built-in-nodes/SkipLayerGuidanceDiT.mdx index 256be244f..394840efd 100644 --- a/built-in-nodes/SkipLayerGuidanceDiT.mdx +++ b/built-in-nodes/SkipLayerGuidanceDiT.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceDiT" icon: "circle" mode: wide --- + Enhances guidance towards detailed structure by using another set of CFG negative with skipped layers. This generic version of SkipLayerGuidance can be used on every DiT model and is inspired by Perturbed Attention Guidance. The original experimental implementation was created for SD3. ## Inputs diff --git a/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx b/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx index 5fbd90707..1058780af 100644 --- a/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx +++ b/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceDiTSimple" icon: "circle" mode: wide --- + Simple version of the SkipLayerGuidanceDiT node that only modifies the unconditional pass during the denoising process. This node applies skip layer guidance to specific transformer layers in DiT (Diffusion Transformer) models by selectively skipping certain layers during the unconditional pass based on specified timing and layer parameters. ## Inputs diff --git a/built-in-nodes/SkipLayerGuidanceSD3.mdx b/built-in-nodes/SkipLayerGuidanceSD3.mdx index 4ef186515..d45b93555 100644 --- a/built-in-nodes/SkipLayerGuidanceSD3.mdx +++ b/built-in-nodes/SkipLayerGuidanceSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceSD3" icon: "circle" mode: wide --- + The SkipLayerGuidanceSD3 node enhances guidance towards detailed structure by applying an additional set of classifier-free guidance with skipped layers. This experimental implementation is inspired by Perturbed Attention Guidance and works by selectively bypassing certain layers during the negative conditioning process to improve structural details in the generated output. ## Inputs diff --git a/built-in-nodes/SolidMask.mdx b/built-in-nodes/SolidMask.mdx index a44e3e274..a64e301b0 100644 --- a/built-in-nodes/SolidMask.mdx +++ b/built-in-nodes/SolidMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SolidMask" icon: "circle" mode: wide --- + The SolidMask node generates a uniform mask with a specified value across its entire area. It's designed to create masks of specific dimensions and intensity, useful in various image processing and masking tasks. ## Inputs diff --git a/built-in-nodes/SoniloTextToMusic.mdx b/built-in-nodes/SoniloTextToMusic.mdx index 891159f5d..147635678 100644 --- a/built-in-nodes/SoniloTextToMusic.mdx +++ b/built-in-nodes/SoniloTextToMusic.mdx @@ -5,14 +5,15 @@ sidebarTitle: "SoniloTextToMusic" icon: "circle" mode: wide --- + The Sonilo Text to Music node generates music from a text description using Sonilo's AI model. You provide a prompt describing the music you want, and the node sends a request to the Sonilo service to create an audio file. You can specify a target duration or let the model infer it from your prompt. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `prompt` | Text prompt describing the music to generate. This is a required field. | STRING | Yes | N/A | -| `duration` | Target duration in seconds. Set to 0 to let the model infer the duration from the prompt. Maximum: 6 minutes (360 seconds). Default: 0. | INT | No | 0 to 360 | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Text prompt describing the music to generate. | STRING | Yes | N/A | +| `duration` | Target duration in seconds. Set to 0 to let the model infer the duration from the prompt. Maximum: 6 minutes. Default: 0. | INT | No | 0 to 360 | | `seed` | Seed for reproducibility. Currently ignored by the Sonilo service but kept for graph consistency. Default: 0. | INT | No | 0 to 18446744073709551615 | **Note:** The `seed` input is provided for workflow consistency but does not currently affect the output of the Sonilo service. @@ -20,10 +21,10 @@ The Sonilo Text to Music node generates music from a text description using Soni ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The generated music as an audio file. | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SoniloTextToMusic/en.md) --- -**Source fingerprint (SHA-256):** `3c94a2f1004d01d410be089e5dbb926246cca38fdadadee0597c1843ba53883c` +**Source fingerprint (SHA-256):** `ffb4c5b5c81d12d67ed1db2b65111ffb78bb31104b4bcb55dd7ec60fb7758e86` diff --git a/built-in-nodes/SoniloVideoToMusic.mdx b/built-in-nodes/SoniloVideoToMusic.mdx index 3d3aa00fe..7501bf9d2 100644 --- a/built-in-nodes/SoniloVideoToMusic.mdx +++ b/built-in-nodes/SoniloVideoToMusic.mdx @@ -5,12 +5,13 @@ sidebarTitle: "SoniloVideoToMusic" icon: "circle" mode: wide --- + Generate music from video using Sonilo's AI model. This node analyzes the content of an input video and creates a matching piece of music. It uses an external AI service to process the video and generate the audio. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `video` | Input video to generate music from. Maximum duration: 6 minutes. | VIDEO | Yes | - | | `prompt` | Optional text prompt to guide music generation. Leave empty for best quality - the model will fully analyze the video content. (default: empty string) | STRING | No | - | | `seed` | Seed for reproducibility. Currently ignored by the Sonilo service but kept for graph consistency. (default: 0) | INT | No | 0 to 18446744073709551615 | @@ -18,10 +19,10 @@ Generate music from video using Sonilo's AI model. This node analyzes the conten ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The generated music as an audio file. | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SoniloVideoToMusic/en.md) --- -**Source fingerprint (SHA-256):** `6c7965a4cc31d9fce6711b57052fdfbff37ba9decd086b18587ff39cc4fc3a0b` +**Source fingerprint (SHA-256):** `ed118d346add099f41a99635638ecb9aa4026b2210b17628c34cdad6bb919767` diff --git a/built-in-nodes/SplatToFile3D.mdx b/built-in-nodes/SplatToFile3D.mdx index a3b69d2fe..00d26f2c7 100644 --- a/built-in-nodes/SplatToFile3D.mdx +++ b/built-in-nodes/SplatToFile3D.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SplatToFile3D" icon: "circle" mode: wide --- -# SplatToFile3D Node Documentation ## Overview diff --git a/built-in-nodes/SplatToMesh.mdx b/built-in-nodes/SplatToMesh.mdx index ebbdbcc49..5b7d5c29d 100644 --- a/built-in-nodes/SplatToMesh.mdx +++ b/built-in-nodes/SplatToMesh.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SplatToMesh" icon: "circle" mode: wide --- -# Extract Mesh from Splat This node converts a 3D Gaussian splat into a colored mesh surface. It works by rasterizing the gaussians onto a density grid, extracting an iso-surface at a chosen density level, and then applying optional smoothing and cleanup to produce a clean, colored triangle mesh. diff --git a/built-in-nodes/SplitAudioChannels.mdx b/built-in-nodes/SplitAudioChannels.mdx index b9017cdad..624f2ef7c 100644 --- a/built-in-nodes/SplitAudioChannels.mdx +++ b/built-in-nodes/SplitAudioChannels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitAudioChannels" icon: "circle" mode: wide --- + The SplitAudioChannels node separates stereo audio into individual left and right channels. It takes a stereo audio input with two channels and outputs two separate audio streams, one for the left channel and one for the right channel. ## Inputs diff --git a/built-in-nodes/SplitImageToTileList.mdx b/built-in-nodes/SplitImageToTileList.mdx index c32769ffd..72a4013e9 100644 --- a/built-in-nodes/SplitImageToTileList.mdx +++ b/built-in-nodes/SplitImageToTileList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitImageToTileList" icon: "circle" mode: wide --- + The Split Image into List of Tiles node divides a single input image into a series of smaller, overlapping rectangular sections called tiles. It creates a batched list of these tiles, which can be processed individually by other nodes. The size of each tile and the amount of overlap between them can be specified. ## Inputs diff --git a/built-in-nodes/SplitImageWithAlpha.mdx b/built-in-nodes/SplitImageWithAlpha.mdx index ff7b207d4..1f84d1b37 100644 --- a/built-in-nodes/SplitImageWithAlpha.mdx +++ b/built-in-nodes/SplitImageWithAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitImageWithAlpha" icon: "circle" mode: wide --- + The SplitImageWithAlpha node is designed to separate the color and alpha components of an image. It processes an input image tensor, extracting the RGB channels as the color component and the alpha channel as the transparency component, facilitating operations that require manipulation of these distinct image aspects. ## Inputs diff --git a/built-in-nodes/SplitSigmas.mdx b/built-in-nodes/SplitSigmas.mdx index 0902c5399..92d1a3244 100644 --- a/built-in-nodes/SplitSigmas.mdx +++ b/built-in-nodes/SplitSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitSigmas" icon: "circle" mode: wide --- + The SplitSigmas node is designed for dividing a sequence of sigma values into two parts based on a specified step. This functionality is crucial for operations that require different handling or processing of the initial and subsequent parts of the sigma sequence, enabling more flexible and targeted manipulation of these values. ## Inputs diff --git a/built-in-nodes/SplitSigmasDenoise.mdx b/built-in-nodes/SplitSigmasDenoise.mdx index 9e77599f9..d9defbff7 100644 --- a/built-in-nodes/SplitSigmasDenoise.mdx +++ b/built-in-nodes/SplitSigmasDenoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitSigmasDenoise" icon: "circle" mode: wide --- + The SplitSigmasDenoise node divides a sequence of sigma values into two parts based on a denoising strength parameter. It splits the input sigmas into high and low sigma sequences, where the split point is determined by multiplying the total steps by the denoise factor. This allows for separating the noise schedule into different intensity ranges for specialized processing. ## Inputs diff --git a/built-in-nodes/StabilityAudioInpaint.mdx b/built-in-nodes/StabilityAudioInpaint.mdx index 5e2d98204..56ef591cf 100644 --- a/built-in-nodes/StabilityAudioInpaint.mdx +++ b/built-in-nodes/StabilityAudioInpaint.mdx @@ -5,12 +5,13 @@ sidebarTitle: "StabilityAudioInpaint" icon: "circle" mode: wide --- + Transforms part of an existing audio sample using text instructions. This node allows you to modify specific sections of audio by providing descriptive prompts, effectively "inpainting" or regenerating selected portions while preserving the rest of the audio. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The AI model to use for audio inpainting. | STRING | Yes | `"stable-audio-2.5"` | | `prompt` | Text description guiding how the audio should be transformed (default: empty). Maximum length is 10,000 characters. | STRING | Yes | | | `audio` | Input audio file to transform. Audio must be between 6 and 190 seconds long. | AUDIO | Yes | | @@ -25,10 +26,10 @@ Transforms part of an existing audio sample using text instructions. This node a ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The transformed audio output with the specified section modified according to the prompt. | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityAudioInpaint/en.md) --- -**Source fingerprint (SHA-256):** `c00d84db73dfcd708495d7a04e21a2378880ca6ceb906473a45dcc1dae20bf79` +**Source fingerprint (SHA-256):** `3c180043c538311b1808cddd84b0c0ab22a6fa1d943b7f9ddc9edab0fb3413ad` diff --git a/built-in-nodes/StabilityAudioToAudio.mdx b/built-in-nodes/StabilityAudioToAudio.mdx index 9035e7c1c..12df2dc92 100644 --- a/built-in-nodes/StabilityAudioToAudio.mdx +++ b/built-in-nodes/StabilityAudioToAudio.mdx @@ -5,15 +5,16 @@ sidebarTitle: "StabilityAudioToAudio" icon: "circle" mode: wide --- + Transforms existing audio samples into new high-quality compositions using text instructions. This node takes an input audio file and modifies it based on your text prompt to create new audio content. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The AI model to use for audio transformation | COMBO | Yes | "stable-audio-2.5" | -| `prompt` | Text instructions describing how to transform the audio (default: empty, max length: 10000 characters) | STRING | Yes | | -| `audio` | Audio must be between 6 and 190 seconds long | AUDIO | Yes | | +| `prompt` | Text instructions describing how to transform the audio (default: empty, max length: 10000 characters) | STRING | Yes | | +| `audio` | Audio must be between 6 and 190 seconds long | AUDIO | Yes | | | `duration` | Controls the duration in seconds of the generated audio (default: 190) | INT | No | 1-190 | | `seed` | The random seed used for generation (default: 0) | INT | No | 0-4294967294 | | `steps` | Controls the number of sampling steps (default: 8) | INT | No | 4-8 | @@ -24,10 +25,10 @@ Transforms existing audio samples into new high-quality compositions using text ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The transformed audio generated based on the input audio and text prompt | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityAudioToAudio/en.md) --- -**Source fingerprint (SHA-256):** `4d320c851a58b58d1a744ca64295fe0cf3002455944ea1c5484b0c2df3ecd4d5` +**Source fingerprint (SHA-256):** `3df67797bf2eccf9d7464a1dd00ea5b6c5a9527f7290911c60a9ebff69302241` diff --git a/built-in-nodes/StabilityStableImageSD_3_5Node.mdx b/built-in-nodes/StabilityStableImageSD_3_5Node.mdx index 544f9ba4b..fe30b3e39 100644 --- a/built-in-nodes/StabilityStableImageSD_3_5Node.mdx +++ b/built-in-nodes/StabilityStableImageSD_3_5Node.mdx @@ -5,12 +5,13 @@ sidebarTitle: "StabilityStableImageSD_3_5Node" icon: "circle" mode: wide --- + This node generates images synchronously using Stability AI's Stable Diffusion 3.5 model. It creates images based on text prompts and can also modify existing images when provided as input. The node supports various aspect ratios and style presets to customize the output. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. (default: empty string) | STRING | Yes | - | | `model` | The Stable Diffusion 3.5 model to use for generation. | COMBO | Yes | `sd3.5-large`
`sd3.5-large-turbo`
`sd3.5-medium` | | `aspect_ratio` | Aspect ratio of generated image. (default: 1:1) | COMBO | Yes | `16:9`
`1:1`
`21:9`
`2:3`
`3:2`
`4:5`
`5:4`
`9:16`
`9:21` | @@ -26,10 +27,10 @@ This node generates images synchronously using Stability AI's Stable Diffusion 3 ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The generated or modified image. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityStableImageSD_3_5Node/en.md) --- -**Source fingerprint (SHA-256):** `aa071616da3ff645dfbc885c84706324d555c18772d3cc0d603b5699a0e7dfff` +**Source fingerprint (SHA-256):** `0ef029d4651fb4a9132899a6df1a2c2de6152dd9091129573f366a2aac39bbae` diff --git a/built-in-nodes/StabilityStableImageUltraNode.mdx b/built-in-nodes/StabilityStableImageUltraNode.mdx index 1324de547..0442aa282 100644 --- a/built-in-nodes/StabilityStableImageUltraNode.mdx +++ b/built-in-nodes/StabilityStableImageUltraNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "StabilityStableImageUltraNode" icon: "circle" mode: wide --- + Generates images synchronously based on prompt and resolution. This node creates images using Stability AI's Stable Image Ultra model, processing your text prompt and generating a corresponding image with the specified aspect ratio and style. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. To control the weight of a given word use the format `(word:weight)`, where `word` is the word you'd like to control the weight of and `weight` is a value between 0 and 1. For example: `The sky was a crisp (blue:0.3) and (green:0.8)` would convey a sky that was blue and green, but more green than blue. | STRING | Yes | - | | `aspect_ratio` | Aspect ratio of generated image (default: "1:1"). | COMBO | Yes | `"1:1"`
`"16:9"`
`"21:9"`
`"2:3"`
`"3:2"`
`"4:5"`
`"5:4"`
`"9:16"`
`"9:21"` | | `style_preset` | Optional desired style of generated image. Select "None" to not apply any style preset. | COMBO | No | `"3d-model"`
`"analog-film"`
`"anime"`
`"cinematic"`
`"comic-book"`
`"digital-art"`
`"enhance"`
`"fantasy-art"`
`"isometric"`
`"line-art"`
`"low-poly"`
`"modeling-compound"`
`"neon-punk"`
`"origami"`
`"photographic"`
`"pixel-art"`
`"tile-texture"` | @@ -24,10 +25,10 @@ Generates images synchronously based on prompt and resolution. This node creates ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated image based on the input parameters. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityStableImageUltraNode/en.md) --- -**Source fingerprint (SHA-256):** `4d516f67a0e2a8c02f601b4da9fe466b7376d50bb96d6e0dc6ca2cc034c79585` +**Source fingerprint (SHA-256):** `86a9ace60a1f9f2b872865381c695bd0e3e3578e0dd3453f1ab3be58bae2e2f0` diff --git a/built-in-nodes/StabilityTextToAudio.mdx b/built-in-nodes/StabilityTextToAudio.mdx index 0cd700e92..bd3d297fa 100644 --- a/built-in-nodes/StabilityTextToAudio.mdx +++ b/built-in-nodes/StabilityTextToAudio.mdx @@ -5,12 +5,13 @@ sidebarTitle: "StabilityTextToAudio" icon: "circle" mode: wide --- + Generates high-quality music and sound effects from text descriptions. This node uses Stability AI's audio generation technology to create audio content based on your text prompts. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The audio generation model to use (default: "stable-audio-2.5") | COMBO | Yes | `"stable-audio-2.5"` | | `prompt` | The text description used to generate audio content (default: empty string) | STRING | Yes | - | | `duration` | Controls the duration in seconds of the generated audio (default: 190) | INT | No | 1-190 | @@ -20,10 +21,10 @@ Generates high-quality music and sound effects from text descriptions. This node ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `audio` | The generated audio file based on the text prompt | AUDIO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityTextToAudio/en.md) --- -**Source fingerprint (SHA-256):** `123b166c3879b18854b8d3cf039576d76925664baac63a816a1639d764d869f7` +**Source fingerprint (SHA-256):** `8dfe0eafb6157bc458c2ba3053a98e2bb5dfe896921cf90a70a88c695f8c5edc` diff --git a/built-in-nodes/StabilityUpscaleConservativeNode.mdx b/built-in-nodes/StabilityUpscaleConservativeNode.mdx index 005e7296c..60dcc746e 100644 --- a/built-in-nodes/StabilityUpscaleConservativeNode.mdx +++ b/built-in-nodes/StabilityUpscaleConservativeNode.mdx @@ -5,25 +5,26 @@ sidebarTitle: "StabilityUpscaleConservativeNode" icon: "circle" mode: wide --- + Upscale image with minimal alterations to 4K resolution. This node uses Stability AI's conservative upscaling to increase image resolution while preserving the original content and making only subtle changes. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be upscaled | IMAGE | Yes | - | | `prompt` | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. (default: empty string) | STRING | Yes | - | -| `creativity` | Controls the likelihood of creating additional details not heavily conditioned by the init image. (default: 0.35) | FLOAT | Yes | 0.2-0.5 | -| `seed` | The random seed used for creating the noise. (default: 0) | INT | Yes | 0-4294967294 | +| `creativity` | Controls the likelihood of creating additional details not heavily conditioned by the init image. (default: 0.35) | FLOAT | Yes | 0.2 - 0.5 | +| `seed` | The random seed used for creating the noise. (default: 0) | INT | Yes | 0 - 4294967294 | | `negative_prompt` | Keywords of what you do not wish to see in the output image. This is an advanced feature. (default: empty string) | STRING | No | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The upscaled image at 4K resolution | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleConservativeNode/en.md) --- -**Source fingerprint (SHA-256):** `7fc0cdf98b4edd991070252d8d9736b48acca6038804209ab7163e5516e1ca34` +**Source fingerprint (SHA-256):** `e4faa795d5a197cdc85c6985b99e8a7229b2b64f929eea3fefff3aff32558c18` diff --git a/built-in-nodes/StabilityUpscaleCreativeNode.mdx b/built-in-nodes/StabilityUpscaleCreativeNode.mdx index a96ba851f..e7673452a 100644 --- a/built-in-nodes/StabilityUpscaleCreativeNode.mdx +++ b/built-in-nodes/StabilityUpscaleCreativeNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "StabilityUpscaleCreativeNode" icon: "circle" mode: wide --- + Upscale image with minimal alterations to 4K resolution. This node uses Stability AI's creative upscaling technology to enhance image resolution while preserving the original content and adding subtle creative details. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be upscaled | IMAGE | Yes | - | | `prompt` | What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. (default: empty string) | STRING | Yes | - | | `creativity` | Controls the likelihood of creating additional details not heavily conditioned by the init image. (default: 0.3) | FLOAT | Yes | 0.1-0.5 | @@ -21,10 +22,10 @@ Upscale image with minimal alterations to 4K resolution. This node uses Stabilit ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The upscaled image at 4K resolution | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleCreativeNode/en.md) --- -**Source fingerprint (SHA-256):** `1720cc44cc6273b00b3061b44581ba00853e9da32616bc02584335eb6156632c` +**Source fingerprint (SHA-256):** `dc9bfacee3bfa663cff22cd0bcef6759f7808e2ae8e19526de28d55a3bef26e6` diff --git a/built-in-nodes/StabilityUpscaleFastNode.mdx b/built-in-nodes/StabilityUpscaleFastNode.mdx index 7add4ccc3..32fe1578b 100644 --- a/built-in-nodes/StabilityUpscaleFastNode.mdx +++ b/built-in-nodes/StabilityUpscaleFastNode.mdx @@ -5,21 +5,22 @@ sidebarTitle: "StabilityUpscaleFastNode" icon: "circle" mode: wide --- + Quickly upscales an image via Stability API call to 4x its original size. This node is specifically intended for upscaling low-quality or compressed images by sending them to Stability AI's fast upscaling service. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to be upscaled | IMAGE | Yes | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The upscaled image returned from the Stability AI API | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleFastNode/en.md) --- -**Source fingerprint (SHA-256):** `fd3b033c3454e3b795806f2759f8416ea091df24cb2878b701983e4286da98c9` +**Source fingerprint (SHA-256):** `2d24f44fdd96a528a48869ca9c1343ca03311e982dfdbc4a8841bc147c9a621e` diff --git a/built-in-nodes/StableCascade_EmptyLatentImage.mdx b/built-in-nodes/StableCascade_EmptyLatentImage.mdx index be95a251d..cce923fe1 100644 --- a/built-in-nodes/StableCascade_EmptyLatentImage.mdx +++ b/built-in-nodes/StableCascade_EmptyLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_EmptyLatentImage" icon: "circle" mode: wide --- + The StableCascade_EmptyLatentImage node creates empty latent tensors for Stable Cascade models. It generates two separate latent representations - one for stage C and another for stage B - with appropriate dimensions based on the input resolution and compression settings. This node provides the starting point for the Stable Cascade generation pipeline. ## Inputs diff --git a/built-in-nodes/StableCascade_StageB_Conditioning.mdx b/built-in-nodes/StableCascade_StageB_Conditioning.mdx index 1529f2b70..ae1180e2e 100644 --- a/built-in-nodes/StableCascade_StageB_Conditioning.mdx +++ b/built-in-nodes/StableCascade_StageB_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_StageB_Conditioning" icon: "circle" mode: wide --- + The StableCascade_StageB_Conditioning node prepares conditioning data for Stable Cascade Stage B generation by combining existing conditioning information with prior latent representations from Stage C. It modifies the conditioning data to include the latent samples from Stage C, enabling the generation process to leverage the prior information for more coherent outputs. ## Inputs diff --git a/built-in-nodes/StableCascade_StageC_VAEEncode.mdx b/built-in-nodes/StableCascade_StageC_VAEEncode.mdx index 3fdeb4efc..c7d5838d5 100644 --- a/built-in-nodes/StableCascade_StageC_VAEEncode.mdx +++ b/built-in-nodes/StableCascade_StageC_VAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_StageC_VAEEncode" icon: "circle" mode: wide --- + The StableCascade_StageC_VAEEncode node processes an input image through a VAE encoder to generate latent representations for the Stable Cascade model. It first resizes the image based on a compression factor and the VAE's downscale ratio, then encodes the resized image. The node outputs two latent tensors: one for stage C (the actual encoded result) and one for stage B (a zero-filled placeholder). ## Inputs diff --git a/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx b/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx index e03576008..389eed548 100644 --- a/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx +++ b/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_SuperResolutionControlnet" icon: "circle" mode: wide --- + The StableCascade_SuperResolutionControlnet node prepares inputs for Stable Cascade super-resolution processing. It takes an input image and encodes it using a VAE to create controlnet input, while also generating placeholder latent representations for stage C and stage B of the Stable Cascade pipeline. ## Inputs diff --git a/built-in-nodes/StableZero123_Conditioning.mdx b/built-in-nodes/StableZero123_Conditioning.mdx index 90e009398..17f9d5356 100644 --- a/built-in-nodes/StableZero123_Conditioning.mdx +++ b/built-in-nodes/StableZero123_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableZero123_Conditioning" icon: "circle" mode: wide --- + The StableZero123_Conditioning node processes an input image and camera angles to generate conditioning data and latent representations for 3D model generation. It uses a CLIP vision model to encode the image features, combines them with camera embedding information based on elevation and azimuth angles, and produces positive and negative conditioning along with a latent representation for downstream 3D generation tasks. ## Inputs diff --git a/built-in-nodes/StableZero123_Conditioning_Batched.mdx b/built-in-nodes/StableZero123_Conditioning_Batched.mdx index c3759c509..062043185 100644 --- a/built-in-nodes/StableZero123_Conditioning_Batched.mdx +++ b/built-in-nodes/StableZero123_Conditioning_Batched.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableZero123_Conditioning_Batched" icon: "circle" mode: wide --- + The StableZero123_Conditioning_Batched node processes an input image and generates conditioning data for 3D model generation. It encodes the image using CLIP vision and VAE models, then creates camera embeddings based on elevation and azimuth angles to produce positive and negative conditioning along with latent representations for batch processing. ## Inputs diff --git a/built-in-nodes/Stablezero123Conditioning.mdx b/built-in-nodes/Stablezero123Conditioning.mdx index 0b559d17d..466fa2284 100644 --- a/built-in-nodes/Stablezero123Conditioning.mdx +++ b/built-in-nodes/Stablezero123Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Stablezero123Conditioning" icon: "circle" mode: wide --- + This node is designed to process and condition data for use in StableZero123 models, focusing on preparing the input in a specific format that is compatible and optimized for these models. ## Inputs diff --git a/built-in-nodes/Stablezero123ConditioningBatched.mdx b/built-in-nodes/Stablezero123ConditioningBatched.mdx index b97fad24b..8fb55988b 100644 --- a/built-in-nodes/Stablezero123ConditioningBatched.mdx +++ b/built-in-nodes/Stablezero123ConditioningBatched.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Stablezero123ConditioningBatched" icon: "circle" mode: wide --- + This node is designed to process conditioning information in a batched manner specifically tailored for the StableZero123 model. It focuses on efficiently handling multiple sets of conditioning data simultaneously, optimizing the workflow for scenarios where batch processing is crucial. ## Inputs diff --git a/built-in-nodes/StringCompare.mdx b/built-in-nodes/StringCompare.mdx index 7e31a788c..8cfe2a90a 100644 --- a/built-in-nodes/StringCompare.mdx +++ b/built-in-nodes/StringCompare.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringCompare" icon: "circle" mode: wide --- + The StringCompare node compares two text strings using different comparison methods. It can check if one string starts with another, ends with another, or if both strings are exactly equal. The comparison can be performed with or without considering letter case differences. ## Inputs diff --git a/built-in-nodes/StringConcatenate.mdx b/built-in-nodes/StringConcatenate.mdx index b8afd11a8..9a9177294 100644 --- a/built-in-nodes/StringConcatenate.mdx +++ b/built-in-nodes/StringConcatenate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringConcatenate" icon: "circle" mode: wide --- + The StringConcatenate node combines two text strings into one by joining them with a specified delimiter. It takes two input strings and a delimiter character or string, then outputs a single string where the two inputs are connected with the delimiter placed between them. ## Inputs diff --git a/built-in-nodes/StringContains.mdx b/built-in-nodes/StringContains.mdx index 6000aa9a6..0d3380008 100644 --- a/built-in-nodes/StringContains.mdx +++ b/built-in-nodes/StringContains.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringContains" icon: "circle" mode: wide --- + The StringContains node checks if a given string contains a specified substring. It can perform this check with either case-sensitive or case-insensitive matching, returning a boolean result indicating whether the substring was found within the main string. ## Inputs diff --git a/built-in-nodes/StringFormat.mdx b/built-in-nodes/StringFormat.mdx index 1207dd508..c3f13087e 100644 --- a/built-in-nodes/StringFormat.mdx +++ b/built-in-nodes/StringFormat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringFormat" icon: "circle" mode: wide --- + ## Overview This node formats text using Python's string format method. It works like a template where you define a text pattern with placeholders, and then provide values to fill those placeholders. It supports all of Python's format options and features. diff --git a/built-in-nodes/StringLength.mdx b/built-in-nodes/StringLength.mdx index 189c4ad88..01665df7a 100644 --- a/built-in-nodes/StringLength.mdx +++ b/built-in-nodes/StringLength.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringLength" icon: "circle" mode: wide --- + The StringLength node calculates the number of characters in a text string. It takes any text input and returns the total count of characters, including spaces and punctuation. This is useful for measuring text length or validating string size requirements. ## Inputs diff --git a/built-in-nodes/StringReplace.mdx b/built-in-nodes/StringReplace.mdx index 4c5fd440f..f8d34b809 100644 --- a/built-in-nodes/StringReplace.mdx +++ b/built-in-nodes/StringReplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringReplace" icon: "circle" mode: wide --- + The StringReplace node performs text replacement operations on input strings. It searches for a specified substring within the input text and replaces all occurrences with a different substring. This node returns the modified string with all replacements applied. ## Inputs diff --git a/built-in-nodes/StringSubstring.mdx b/built-in-nodes/StringSubstring.mdx index 547480f1f..ec616b3a8 100644 --- a/built-in-nodes/StringSubstring.mdx +++ b/built-in-nodes/StringSubstring.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringSubstring" icon: "circle" mode: wide --- + The StringSubstring node extracts a portion of text from a larger string. It takes a starting position and ending position to define the section you want to extract, then returns the text between those two positions. ## Inputs diff --git a/built-in-nodes/StringTrim.mdx b/built-in-nodes/StringTrim.mdx index 0d8f86daa..8eaf5f698 100644 --- a/built-in-nodes/StringTrim.mdx +++ b/built-in-nodes/StringTrim.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringTrim" icon: "circle" mode: wide --- + The StringTrim node removes whitespace characters (such as spaces, tabs, and newlines) from the beginning, end, or both sides of a text string. You can choose to trim from the left side, right side, or both sides of the string. This is useful for cleaning up text inputs by removing unwanted whitespace. ## Inputs diff --git a/built-in-nodes/StripWhitespace.mdx b/built-in-nodes/StripWhitespace.mdx index 1268eef4a..b83faa910 100644 --- a/built-in-nodes/StripWhitespace.mdx +++ b/built-in-nodes/StripWhitespace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StripWhitespace" icon: "circle" mode: wide --- + This node removes any extra spaces, tabs, or newlines from the beginning and end of a text string. It takes a text input and returns a cleaned version with the leading and trailing whitespace trimmed off. **Note: This node is deprecated and superseded by the Trim Text node.** diff --git a/built-in-nodes/StyleModelApply.mdx b/built-in-nodes/StyleModelApply.mdx index 0bbc8d8b1..7eece831f 100644 --- a/built-in-nodes/StyleModelApply.mdx +++ b/built-in-nodes/StyleModelApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StyleModelApply" icon: "circle" mode: wide --- + This node applies a style model to a given conditioning, enhancing or altering its style based on the output of a CLIP vision model. It integrates the style model's conditioning into the existing conditioning, allowing for a seamless blend of styles in the generation process. ## Inputs diff --git a/built-in-nodes/StyleModelLoader.mdx b/built-in-nodes/StyleModelLoader.mdx index eff898bfb..9524c883f 100644 --- a/built-in-nodes/StyleModelLoader.mdx +++ b/built-in-nodes/StyleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StyleModelLoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/style_models` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. The StyleModelLoader node is designed to load a style model from a specified path. It focuses on retrieving and initializing style models that can be used to apply specific artistic styles to images, thereby enabling the customization of visual outputs based on the loaded style model. diff --git a/built-in-nodes/SvdImg2vidConditioning.mdx b/built-in-nodes/SvdImg2vidConditioning.mdx index cd48e2e31..1c491fb72 100644 --- a/built-in-nodes/SvdImg2vidConditioning.mdx +++ b/built-in-nodes/SvdImg2vidConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SvdImg2vidConditioning" icon: "circle" mode: wide --- + This node is designed for generating conditioning data for video generation tasks, specifically tailored for use with SVD_img2vid models. It takes various inputs including initial images, video parameters, and a VAE model to produce conditioning data that can be used to guide the generation of video frames. ## Inputs diff --git a/built-in-nodes/T5TokenizerOptions.mdx b/built-in-nodes/T5TokenizerOptions.mdx index 9b83e2e72..67f5b3270 100644 --- a/built-in-nodes/T5TokenizerOptions.mdx +++ b/built-in-nodes/T5TokenizerOptions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "T5TokenizerOptions" icon: "circle" mode: wide --- + The T5TokenizerOptions node allows you to configure tokenizer settings for various T5 model types. It sets minimum padding and minimum length parameters for multiple T5 model variants including t5xxl, pile_t5xl, t5base, mt5xl, and umt5xxl. The node takes a CLIP input and returns a modified CLIP with the specified tokenizer options applied. ## Inputs diff --git a/built-in-nodes/TCFG.mdx b/built-in-nodes/TCFG.mdx index cc0390b15..e14a0bfd6 100644 --- a/built-in-nodes/TCFG.mdx +++ b/built-in-nodes/TCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TCFG" icon: "circle" mode: wide --- + TCFG (Tangential Damping CFG) refines the unconditional (negative) predictions to better align with the conditional (positive) predictions during the sampling process. This technique improves output quality by applying tangential damping to the unconditional guidance, based on the research paper 2503.18137. The node modifies the model's sampling behavior by adjusting how unconditional predictions are processed during classifier-free guidance. ## Inputs diff --git a/built-in-nodes/TemporalScoreRescaling.mdx b/built-in-nodes/TemporalScoreRescaling.mdx index cdb6f8506..ef7bfd62a 100644 --- a/built-in-nodes/TemporalScoreRescaling.mdx +++ b/built-in-nodes/TemporalScoreRescaling.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TemporalScoreRescaling" icon: "circle" mode: wide --- + This node applies Temporal Score Rescaling (TSR) to a diffusion model. It modifies the model's sampling behavior by rescaling the predicted noise or score during the denoising process, which can steer the diversity of the generated output. This is implemented as a post-CFG (Classifier-Free Guidance) function. ## Inputs diff --git a/built-in-nodes/Tencent3DPartNode.mdx b/built-in-nodes/Tencent3DPartNode.mdx index 8b709e38f..9466316ee 100644 --- a/built-in-nodes/Tencent3DPartNode.mdx +++ b/built-in-nodes/Tencent3DPartNode.mdx @@ -5,24 +5,25 @@ sidebarTitle: "Tencent3DPartNode" icon: "circle" mode: wide --- + This node uses the Tencent Hunyuan3D API to automatically analyze a 3D model and generate or identify its components based on its structure. It processes the model and returns a new FBX file. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `model_3d` | The 3D model to process. The model should be in FBX format and have less than 30000 faces. | FILE3D | Yes | FBX, Any | -| `seed` | A seed value to control whether the node should re-run. The results are non-deterministic regardless of the seed value. (default: 0) | INT | No | 0 to 2147483647 | +|-----------|-------------|-----------|----------|-------| +| `model_3d` | 3D model in FBX format. Model should have less than 30000 faces. | FILE3D | Yes | FBX, Any | +| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) | INT | No | 0 to 2147483647 | **Note:** The `model_3d` input only supports files in the FBX format. If a different 3D file format is provided, the node will raise an error. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `FBX` | The processed 3D model, returned as an FBX file. | FILE3DFBX | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DPartNode/en.md) --- -**Source fingerprint (SHA-256):** `094ed587f2989312c0eea86105e8c2bdf48a2c626e424eaa07ba528c2e8b4f89` +**Source fingerprint (SHA-256):** `33f8b3d6b34198d0d59e2de2ad9f33d357f88ddaf6f986756be4c3b5f855cec3` diff --git a/built-in-nodes/Tencent3DTextureEditNode.mdx b/built-in-nodes/Tencent3DTextureEditNode.mdx index 37c1d0f93..7828e1a5c 100644 --- a/built-in-nodes/Tencent3DTextureEditNode.mdx +++ b/built-in-nodes/Tencent3DTextureEditNode.mdx @@ -5,22 +5,23 @@ sidebarTitle: "Tencent3DTextureEditNode" icon: "circle" mode: wide --- + This node uses the Tencent Hunyuan3D API to edit the textures of a 3D model. You provide a 3D model and a text description of the desired changes, and the node returns a new version of the model with its textures redrawn according to your prompt. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_3d` | 3D model in FBX format. Model should have less than 100000 faces. | FILE3D | Yes | FBX, Any | | `prompt` | Describes texture editing. Supports up to 1024 UTF-8 characters. | STRING | Yes | | | `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0) | INT | No | 0 to 2147483647 | -**Note:** The `model_3d` input must be a file in the FBX format. Other 3D file formats are not supported by this node. +**Note:** The `model_3d` input must be a file in the FBX format. Other 3D file formats are not supported by this node. The `prompt` parameter is required and must be between 1 and 1024 characters in length. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `GLB` | The processed 3D model in GLB format. | FILE3D | | `OBJ` | The processed 3D model in OBJ format. | FILE3D | | `texture_image` | The newly generated texture image for the 3D model. | IMAGE | @@ -28,4 +29,4 @@ This node uses the Tencent Hunyuan3D API to edit the textures of a 3D model. You > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DTextureEditNode/en.md) --- -**Source fingerprint (SHA-256):** `e8d3f9fbd49b0e641ed4bb415d6ee6a34018623eb717ac54c0588383f9caed44` +**Source fingerprint (SHA-256):** `eedddc8bd47a4af6e45a516f2817e7c1dded575d9e28ea9b66a1d7a39b93526c` diff --git a/built-in-nodes/TencentImageToModelNode.mdx b/built-in-nodes/TencentImageToModelNode.mdx index 5778030fd..7231506f3 100644 --- a/built-in-nodes/TencentImageToModelNode.mdx +++ b/built-in-nodes/TencentImageToModelNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TencentImageToModelNode" icon: "circle" mode: wide --- + This node uses Tencent's Hunyuan3D Pro API to generate a 3D model from one or more input images. It processes the images, sends them to the API, and returns the generated 3D model files in GLB and OBJ formats, along with optional texture maps. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The version of the Hunyuan3D model to use. The LowPoly option is unavailable for the `3.1` model. | COMBO | Yes | `"3.0"`
`"3.1"` | | `image` | The primary input image used to generate the 3D model. Must be at least 128x128 pixels. | IMAGE | Yes | - | | `image_left` | An optional image of the object's left side for multi-view generation. Must be at least 128x128 pixels. | IMAGE | No | - | @@ -27,7 +28,7 @@ This node uses Tencent's Hunyuan3D Pro API to generate a 3D model from one or mo ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | A legacy output for backward compatibility. | STRING | | `GLB` | The generated 3D model in the GLB (Binary GL Transmission Format) file format. | FILE3DGLB | | `OBJ` | The generated 3D model in the OBJ (Wavefront) file format. | FILE3DOBJ | @@ -39,4 +40,4 @@ This node uses Tencent's Hunyuan3D Pro API to generate a 3D model from one or mo > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentImageToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `b4cb268fe3b2f5890e5460d5e69897ccc47e205b05546aea18a85ad15717f12a` +**Source fingerprint (SHA-256):** `fe422cfa714dbff7cd5dabb286d93d59afe9a01daf711ca09ebcf47ef100a52e` diff --git a/built-in-nodes/TencentModelTo3DUVNode.mdx b/built-in-nodes/TencentModelTo3DUVNode.mdx index 7ea530462..bfbb68e22 100644 --- a/built-in-nodes/TencentModelTo3DUVNode.mdx +++ b/built-in-nodes/TencentModelTo3DUVNode.mdx @@ -5,19 +5,20 @@ sidebarTitle: "TencentModelTo3DUVNode" icon: "circle" mode: wide --- + This node uses the Tencent Hunyuan3D API to perform UV unfolding on a 3D model. It takes a 3D model file as input, sends it to the API for processing, and returns the processed model in OBJ and FBX formats along with a generated UV texture image. The input model must have fewer than 30,000 faces. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_3d` | Input 3D model (GLB, OBJ, or FBX). The model must have less than 30000 faces. | FILE3D | Yes | GLB
OBJ
FBX | -| `seed` | A seed value (default: 1). This controls whether the node should re-run, but results are non-deterministic regardless of the seed value. | INT | No | 0 to 2147483647 | +| `seed` | Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 1) | INT | No | 0 to 2147483647 | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `OBJ` | The processed 3D model file in OBJ format. | FILE3D | | `FBX` | The processed 3D model file in FBX format. | FILE3D | | `uv_image` | The generated UV texture image. | IMAGE | @@ -25,4 +26,4 @@ This node uses the Tencent Hunyuan3D API to perform UV unfolding on a 3D model. > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentModelTo3DUVNode/en.md) --- -**Source fingerprint (SHA-256):** `f09167ca1aacf299ff278817a50b6c311b6211fe447cfbe7c3a0ccc481058cf6` +**Source fingerprint (SHA-256):** `b69519df055043555ab7f4d75cfb3b77b9011d5a8e93d0b3ba30c7a8674bd2cb` diff --git a/built-in-nodes/TencentSmartTopologyNode.mdx b/built-in-nodes/TencentSmartTopologyNode.mdx index 873450955..1c7cef027 100644 --- a/built-in-nodes/TencentSmartTopologyNode.mdx +++ b/built-in-nodes/TencentSmartTopologyNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TencentSmartTopologyNode" icon: "circle" mode: wide --- + This node performs smart retopology on a 3D model, automatically creating a new, cleaner mesh with optimized polygon count. It connects to a Tencent Hunyuan 3D API to process the model, supporting GLB and OBJ file formats up to 200MB. The node returns the processed model as an OBJ file. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_3d` | Input 3D model (GLB or OBJ). The file must be in GLB or OBJ format and cannot exceed 200MB. | FILE3D | Yes | - | | `polygon_type` | Surface composition type. | STRING | Yes | `"triangle"`
`"quadrilateral"` | | `face_level` | Polygon reduction level. | STRING | Yes | `"medium"`
`"high"`
`"low"` | @@ -21,10 +22,10 @@ This node performs smart retopology on a 3D model, automatically creating a new, ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `OBJ` | The processed 3D model with optimized topology, returned in OBJ format. | FILE3D | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentSmartTopologyNode/en.md) --- -**Source fingerprint (SHA-256):** `41f52d3553c2c0773d539d029f21fe405ffac739a5a43d89da1c55c5a4d75e5b` +**Source fingerprint (SHA-256):** `effbccb4d239ffb6b575fc547dd54cbb61aa4508502345cb5bef1d66b320926b` diff --git a/built-in-nodes/TencentTextToModelNode.mdx b/built-in-nodes/TencentTextToModelNode.mdx index 75d98a69e..677fc84a1 100644 --- a/built-in-nodes/TencentTextToModelNode.mdx +++ b/built-in-nodes/TencentTextToModelNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TencentTextToModelNode" icon: "circle" mode: wide --- + This node uses Tencent's Hunyuan3D Pro API to generate a 3D model from a text description. It sends a request to create a generation task, polls for the result, and downloads the final model files in GLB and OBJ formats. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The version of the Hunyuan3D model to use. The LowPoly option is unavailable for the `3.1` model. | COMBO | Yes | `"3.0"`
`"3.1"` | | `prompt` | The text description of the 3D model to generate. Supports up to 1024 characters. | STRING | Yes | - | | `face_count` | The target number of faces for the generated 3D model. Default: 500000. | INT | Yes | 3000 - 1500000 | @@ -24,7 +25,7 @@ This node uses Tencent's Hunyuan3D Pro API to generate a 3D model from a text de ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | A legacy output for backward compatibility. | STRING | | `GLB` | The generated 3D model in the GLB file format. | FILE3DGLB | | `OBJ` | The generated 3D model in the OBJ file format. | FILE3DOBJ | @@ -33,4 +34,4 @@ This node uses Tencent's Hunyuan3D Pro API to generate a 3D model from a text de > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentTextToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `2e8799d6863a0a7113d22f1637251735a217797679d7a97268910b88d9864e4a` +**Source fingerprint (SHA-256):** `8110b6a70cdd26d5d0dcb791e654a6292895693e25076b982951c65f787422d6` diff --git a/built-in-nodes/TerminalLog.mdx b/built-in-nodes/TerminalLog.mdx index 5fc54d813..9e358ce81 100644 --- a/built-in-nodes/TerminalLog.mdx +++ b/built-in-nodes/TerminalLog.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TerminalLog" icon: "circle" mode: wide --- + Terminal Log (Manager) node is primarily used to display the running information of ComfyUI in the terminal within the ComfyUI interface. To use it, you need to set the `mode` to **logging** mode. This will allow it to record corresponding log information during the image generation task. If the `mode` is set to **stop** mode, it will not record log information. When you access and use ComfyUI via remote connections or local area network connections, Terminal Log (Manager) node becomes particularly useful. It allows you to directly view error messages from the CMD within the ComfyUI interface, making it easier to understand the current status of ComfyUI's operation. diff --git a/built-in-nodes/TextEncodeAceStepAudio.mdx b/built-in-nodes/TextEncodeAceStepAudio.mdx index 6a5135f56..25589f1cb 100644 --- a/built-in-nodes/TextEncodeAceStepAudio.mdx +++ b/built-in-nodes/TextEncodeAceStepAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeAceStepAudio" icon: "circle" mode: wide --- + The TextEncodeAceStepAudio node processes text inputs for audio conditioning by combining tags and lyrics into tokens, then encoding them with adjustable lyrics strength. It takes a CLIP model along with text descriptions and lyrics, tokenizes them together, and generates conditioning data suitable for audio generation tasks. The node allows fine-tuning the influence of lyrics through a strength parameter that controls their impact on the final output. ## Inputs diff --git a/built-in-nodes/TextEncodeAceStepAudio1.5.mdx b/built-in-nodes/TextEncodeAceStepAudio1.5.mdx index f74e623b4..af397e3b2 100644 --- a/built-in-nodes/TextEncodeAceStepAudio1.5.mdx +++ b/built-in-nodes/TextEncodeAceStepAudio1.5.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeAceStepAudio1.5" icon: "circle" mode: wide --- + The TextEncodeAceStepAudio1.5 node prepares text and audio-related metadata for use with the AceStepAudio 1.5 model. It takes descriptive tags, lyrics, and musical parameters, then uses a CLIP model to convert them into a conditioning format suitable for audio generation. ## Inputs diff --git a/built-in-nodes/TextEncodeBooguEdit.mdx b/built-in-nodes/TextEncodeBooguEdit.mdx new file mode 100644 index 000000000..48a22a8a8 --- /dev/null +++ b/built-in-nodes/TextEncodeBooguEdit.mdx @@ -0,0 +1,31 @@ +--- +title: "TextEncodeBooguEdit - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the TextEncodeBooguEdit node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "TextEncodeBooguEdit" +icon: "circle" +mode: wide +--- + +This node prepares conditioning for image editing with Boogu. It processes reference images to create both positive and negative conditioning outputs. The reference image is used twice: vision tokens from the image are added only to the positive conditioning to amplify the edit instruction, while a VAE reference latent is added to both positive and negative conditioning so it cancels out under CFG, preserving the original image identity. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `clip` | The CLIP model used for text encoding | CLIP | Yes | | +| `prompt` | The text prompt describing the desired edit | STRING | Yes | | +| `negative_prompt` | The text prompt describing what to avoid in the edit | STRING | No | | +| `vae` | The VAE model used to encode reference images into latent space | VAE | No | | +| `images` | Reference image(s) to edit. Boogu focuses on one reference per sample; more are allowed. | IMAGE | No | Up to 16 images | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `positive` | Conditioning containing both the text prompt with vision tokens and the reference latents | CONDITIONING | +| `negative` | Conditioning containing the negative text prompt and the reference latents | CONDITIONING | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeBooguEdit/en.md) + +--- +**Source fingerprint (SHA-256):** `170979acf5b2e9f25f96231a4b23a4376cfddcd4bda2fdd6e03528417e6931b0` diff --git a/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx b/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx index 46ffa5159..e574bb37a 100644 --- a/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx +++ b/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeHunyuanVideo_ImageToVideo" icon: "circle" mode: wide --- + The TextEncodeHunyuanVideo_ImageToVideo node creates conditioning data for video generation by combining text prompts with image embeddings. It uses a CLIP model to process both the text input and visual information from a CLIP vision output, then generates tokens that blend these two sources according to the specified image interleave setting. ## Inputs diff --git a/built-in-nodes/TextEncodeQwenImageEdit.mdx b/built-in-nodes/TextEncodeQwenImageEdit.mdx index f2d53a931..199366531 100644 --- a/built-in-nodes/TextEncodeQwenImageEdit.mdx +++ b/built-in-nodes/TextEncodeQwenImageEdit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeQwenImageEdit" icon: "circle" mode: wide --- + The TextEncodeQwenImageEdit node processes text prompts and optional images to generate conditioning data for image generation or editing. It uses a CLIP model to tokenize the input and can optionally encode reference images using a VAE to create reference latents. When an image is provided, it automatically resizes the image to maintain consistent processing dimensions. ## Inputs diff --git a/built-in-nodes/TextEncodeQwenImageEditPlus.mdx b/built-in-nodes/TextEncodeQwenImageEditPlus.mdx index b6ae884f7..11a1c97d3 100644 --- a/built-in-nodes/TextEncodeQwenImageEditPlus.mdx +++ b/built-in-nodes/TextEncodeQwenImageEditPlus.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeQwenImageEditPlus" icon: "circle" mode: wide --- + The TextEncodeQwenImageEditPlus node processes text prompts and optional images to generate conditioning data for image generation or editing tasks. It uses a specialized template to analyze input images and understand how text instructions should modify them, then encodes this information for use in subsequent generation steps. The node can handle up to three input images and optionally generate reference latents when a VAE is provided. ## Inputs diff --git a/built-in-nodes/TextEncodeZImageOmni.mdx b/built-in-nodes/TextEncodeZImageOmni.mdx index 3e1fa73f8..784822b47 100644 --- a/built-in-nodes/TextEncodeZImageOmni.mdx +++ b/built-in-nodes/TextEncodeZImageOmni.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeZImageOmni" icon: "circle" mode: wide --- + The TextEncodeZImageOmni node is an advanced conditioning node that encodes a text prompt along with optional reference images into a conditioning format suitable for image generation models. It can process up to three images, optionally encoding them with a vision encoder and/or a VAE to produce reference latents, and integrates these visual references with the text prompt using a specific template structure. ## Inputs diff --git a/built-in-nodes/TextGenerate.mdx b/built-in-nodes/TextGenerate.mdx index 85943f122..68d74c717 100644 --- a/built-in-nodes/TextGenerate.mdx +++ b/built-in-nodes/TextGenerate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextGenerate" icon: "circle" mode: wide --- + The TextGenerate node uses a CLIP model to create text based on a user's prompt. It can optionally use images, video, or audio as additional context to guide the text generation. You can control the length of the output, enable a thinking mode for supported models, and choose whether to use random sampling with various settings or to generate text without sampling. ## Inputs diff --git a/built-in-nodes/TextGenerateLTX2Prompt.mdx b/built-in-nodes/TextGenerateLTX2Prompt.mdx index 4d4410867..0f4c5b022 100644 --- a/built-in-nodes/TextGenerateLTX2Prompt.mdx +++ b/built-in-nodes/TextGenerateLTX2Prompt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextGenerateLTX2Prompt" icon: "circle" mode: wide --- + The TextGenerateLTX2Prompt node is a specialized version of a text generation node. It takes a user's text prompt and automatically formats it with specific system instructions before sending it to a language model for enhancement or completion. The node can operate in two modes: text-only or with an image reference, using different system prompts for each case. ## Inputs diff --git a/built-in-nodes/TextToLowercase.mdx b/built-in-nodes/TextToLowercase.mdx index 2229066d5..f99c6b650 100644 --- a/built-in-nodes/TextToLowercase.mdx +++ b/built-in-nodes/TextToLowercase.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextToLowercase" icon: "circle" mode: wide --- + The Text to Lowercase node takes a text string as input and converts all of its characters to lowercase. It is a simple utility for standardizing text case. > **Note:** This node is deprecated and superseded by the Convert Text Case node. diff --git a/built-in-nodes/TextToUppercase.mdx b/built-in-nodes/TextToUppercase.mdx index 5e0a689e7..708ac9ae7 100644 --- a/built-in-nodes/TextToUppercase.mdx +++ b/built-in-nodes/TextToUppercase.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextToUppercase" icon: "circle" mode: wide --- + The Text to Uppercase node takes a text input and converts all of its characters to uppercase. It is a simple text processing utility that modifies the case of the provided string. **Note:** This node is deprecated and superseded by the Convert Text Case node. diff --git a/built-in-nodes/ThresholdMask.mdx b/built-in-nodes/ThresholdMask.mdx index 7907b3764..2ff3c4145 100644 --- a/built-in-nodes/ThresholdMask.mdx +++ b/built-in-nodes/ThresholdMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ThresholdMask" icon: "circle" mode: wide --- + The ThresholdMask node converts a mask to a binary mask by applying a threshold value. It compares each pixel in the input mask against the specified threshold value and creates a new mask where pixels above the threshold become 1 (white) and pixels below or equal to the threshold become 0 (black). ## Inputs diff --git a/built-in-nodes/TomePatchModel.mdx b/built-in-nodes/TomePatchModel.mdx index 6ac115d9a..d157995e5 100644 --- a/built-in-nodes/TomePatchModel.mdx +++ b/built-in-nodes/TomePatchModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TomePatchModel" icon: "circle" mode: wide --- + The TomePatchModel node applies Token Merging (ToMe) to a diffusion model to reduce computational requirements during inference. It works by selectively merging similar tokens in the attention mechanism, allowing the model to process fewer tokens while maintaining image quality. This technique helps speed up generation without significant quality loss. ## Inputs diff --git a/built-in-nodes/TopazImageEnhance.mdx b/built-in-nodes/TopazImageEnhance.mdx index 305342957..0f23eae70 100644 --- a/built-in-nodes/TopazImageEnhance.mdx +++ b/built-in-nodes/TopazImageEnhance.mdx @@ -5,35 +5,36 @@ sidebarTitle: "TopazImageEnhance" icon: "circle" mode: wide --- + The Topaz Image Enhance node provides industry-standard upscaling and image enhancement. It processes a single input image using a cloud-based AI model to improve quality, detail, and resolution. The node offers fine-grained control over the enhancement process, including options for creative guidance, subject focus, and facial preservation. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The AI model to use for image enhancement. | COMBO | Yes | `"Reimagine"` | | `image` | The input image to be enhanced. Only one image is supported. | IMAGE | Yes | - | -| `prompt` | An optional text prompt for creative upscaling guidance (default: empty). | STRING | No | - | +| `prompt` | Optional text prompt for creative upscaling guidance (default: empty). | STRING | No | - | | `subject_detection` | Controls which part of the image the enhancement focuses on (default: "All"). | COMBO | No | `"All"`
`"Foreground"`
`"Background"` | -| `face_enhancement` | Enable to enhance faces if they are present in the image (default: True). | BOOLEAN | No | - | -| `face_enhancement_creativity` | Sets the creativity level for face enhancement (default: 0.0). | FLOAT | No | 0.0 - 1.0 | +| `face_enhancement` | Enhance faces (if present) during processing (default: True). | BOOLEAN | No | - | +| `face_enhancement_creativity` | Set the creativity level for face enhancement (default: 0.0). | FLOAT | No | 0.0 - 1.0 | | `face_enhancement_strength` | Controls how sharp enhanced faces are relative to the background (default: 1.0). | FLOAT | No | 0.0 - 1.0 | -| `crop_to_fill` | By default, the image is letterboxed when the output aspect ratio differs. Enable to crop the image to fill the output dimensions instead (default: False). | BOOLEAN | No | - | -| `output_width` | The desired width of the output image. A value of 0 means it will be calculated automatically, usually based on the original size or the `output_height` if specified (default: 0). | INT | No | 0 - 32000 | -| `output_height` | The desired height of the output image. A value of 0 means it will be calculated automatically, usually based on the original size or the `output_width` if specified (default: 0). | INT | No | 0 - 32000 | +| `crop_to_fill` | By default, the image is letterboxed when the output aspect ratio differs. Enable to crop the image to fill the output dimensions (default: False). | BOOLEAN | No | - | +| `output_width` | Zero value means to calculate automatically (usually it will be original size or output_height if specified) (default: 0). | INT | No | 0 - 32000 | +| `output_height` | Zero value means to output in the same height as original or output width (default: 0). | INT | No | 0 - 32000 | | `creativity` | Controls the overall creativity level of the enhancement (default: 3). | INT | No | 1 - 9 | -| `face_preservation` | Preserve the facial identity of subjects in the image (default: True). | BOOLEAN | No | - | -| `color_preservation` | Preserve the original colors of the input image (default: True). | BOOLEAN | No | - | +| `face_preservation` | Preserve subjects' facial identity (default: True). | BOOLEAN | No | - | +| `color_preservation` | Preserve the original colors (default: True). | BOOLEAN | No | - | **Note:** This node can only process a single input image. Providing a batch of multiple images will result in an error. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The enhanced output image. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazImageEnhance/en.md) --- -**Source fingerprint (SHA-256):** `c569f4873f5e008f62ccae9a93ef40fe79554c003e7e52c5ac91241b0d08978a` +**Source fingerprint (SHA-256):** `586ebc6aafa40c8bebf1e24904ebf5653b8d3b46b202d9a6850f625ac8845bcf` diff --git a/built-in-nodes/TopazVideoEnhance.mdx b/built-in-nodes/TopazVideoEnhance.mdx index 580b685f8..afd2b4d6d 100644 --- a/built-in-nodes/TopazVideoEnhance.mdx +++ b/built-in-nodes/TopazVideoEnhance.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TopazVideoEnhance" icon: "circle" mode: wide --- + The Topaz Video Enhance node uses an external API to improve video quality. It can upscale video resolution, increase frame rate through interpolation, and apply compression. The node processes an input MP4 video and returns an enhanced version based on the selected settings. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `video` | The input video file to be enhanced. | VIDEO | Yes | - | | `upscaler_enabled` | Enables or disables the video upscaling feature (default: True). | BOOLEAN | Yes | - | | `upscaler_model` | The AI model used for upscaling the video. | COMBO | Yes | `"Starlight (Astra) Fast"`
`"Starlight (Astra) Creative"`
`"Starlight Precise 2.5"` | @@ -24,15 +25,15 @@ The Topaz Video Enhance node uses an external API to improve video quality. It c | `interpolation_duplicate_threshold` | Detection sensitivity for duplicate frames. (default: 0.01) | FLOAT | No | 0.001 to 0.1 | | `dynamic_compression_level` | CQP level. (default: "Low") | COMBO | No | `"Low"`
`"Mid"`
`"High"` | -**Note:** At least one enhancement feature must be enabled. The node will raise an error if both `upscaler_enabled` and `interpolation_enabled` are set to `False`. The input video must be in MP4 format. +**Note:** At least one enhancement feature must be enabled. The node will raise an error if both `upscaler_enabled` and `interpolation_enabled` are set to False. The input video must be in MP4 format. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The enhanced output video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazVideoEnhance/en.md) --- -**Source fingerprint (SHA-256):** `ef2d1e62c0000f4d9a99014317db2f1c4e0b8a77334024cf614ec0376058a2f7` +**Source fingerprint (SHA-256):** `29db853812759574d775041e8984088774bc06f1349ca5390ee53ba668fd12fe` diff --git a/built-in-nodes/TopazVideoEnhanceV2.mdx b/built-in-nodes/TopazVideoEnhanceV2.mdx index 66797d45b..ff895de29 100644 --- a/built-in-nodes/TopazVideoEnhanceV2.mdx +++ b/built-in-nodes/TopazVideoEnhanceV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TopazVideoEnhanceV2" icon: "circle" mode: wide --- -# Topaz Video Enhance V2 The **Topaz Video Enhance V2** node allows you to upscale and enhance video using Topaz Labs' AI models. It can increase resolution, adjust frame rate through interpolation, and apply creative or realistic enhancements to breathe new life into your video footage. @@ -43,4 +42,4 @@ The **Topaz Video Enhance V2** node allows you to upscale and enhance video usin > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazVideoEnhanceV2/en.md) --- -**Source fingerprint (SHA-256):** `3b3df144ecd7de6e0c141cffa30fc7b303e0edc991e714c2f0aaf0e4be903166` +**Source fingerprint (SHA-256):** `d955e5bae683fa4d7e09e23f7cd06bc077ec5e4ab0b5c4f6d712b8358027998c` diff --git a/built-in-nodes/TorchCompileModel.mdx b/built-in-nodes/TorchCompileModel.mdx index 5d40117ef..200648721 100644 --- a/built-in-nodes/TorchCompileModel.mdx +++ b/built-in-nodes/TorchCompileModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TorchCompileModel" icon: "circle" mode: wide --- + The TorchCompileModel node applies PyTorch compilation to a model to optimize its performance. It creates a copy of the input model and wraps it with PyTorch's compilation functionality using the specified backend. This can improve the model's execution speed during inference. ## Inputs diff --git a/built-in-nodes/TrainLoraNode.mdx b/built-in-nodes/TrainLoraNode.mdx index 8ebd86597..46e7c0c24 100644 --- a/built-in-nodes/TrainLoraNode.mdx +++ b/built-in-nodes/TrainLoraNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TrainLoraNode" icon: "circle" mode: wide --- + The TrainLoraNode creates and trains a LoRA (Low-Rank Adaptation) model on a diffusion model using provided latents and conditioning data. It allows you to fine-tune a model with custom training parameters, optimizers, and loss functions. The node outputs the trained LoRA weights, a loss history map, and the total training steps completed. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The model to train the LoRA on. | MODEL | Yes | - | | `latents` | The Latents to use for training, serve as dataset/input of the model. | LATENT | Yes | - | | `positive` | The positive conditioning to use for training. | CONDITIONING | Yes | - | @@ -44,7 +45,7 @@ The TrainLoraNode creates and trains a LoRA (Low-Rank Adaptation) model on a dif ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `lora` | The trained LoRA weights that can be saved or applied to other models. | LORA_MODEL | | `loss_map` | A dictionary containing the training loss values over time. | LOSS_MAP | | `steps` | The total number of training steps completed (including any previous steps from existing LoRA). | INT | @@ -52,4 +53,4 @@ The TrainLoraNode creates and trains a LoRA (Low-Rank Adaptation) model on a dif > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrainLoraNode/en.md) --- -**Source fingerprint (SHA-256):** `e145145306330099293c8b4bb344ec0a38de690040bd796b84225f54638900c3` +**Source fingerprint (SHA-256):** `39e88045270d36855442024b62d6a225a58b34842f45ac04fbc6c1ade6768a76` diff --git a/built-in-nodes/TransformSplat.mdx b/built-in-nodes/TransformSplat.mdx index 8144213db..249881885 100644 --- a/built-in-nodes/TransformSplat.mdx +++ b/built-in-nodes/TransformSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TransformSplat" icon: "circle" mode: wide --- -# Transform Splat The Transform Splat node applies translation, rotation, and scaling transformations to a gaussian splat. It moves, rotates, and resizes the entire splat as a single object, and when non-uniform scaling is applied, it also reshapes each individual gaussian splat for accurate results. diff --git a/built-in-nodes/TrimAudioDuration.mdx b/built-in-nodes/TrimAudioDuration.mdx index be42edf8b..3f009c4b9 100644 --- a/built-in-nodes/TrimAudioDuration.mdx +++ b/built-in-nodes/TrimAudioDuration.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrimAudioDuration" icon: "circle" mode: wide --- + The TrimAudioDuration node allows you to cut a specific time segment from an audio file. You can specify when to start the trim and how long the resulting audio clip should be. The node works by converting time values to audio frame positions and extracting the corresponding portion of the audio waveform. ## Inputs diff --git a/built-in-nodes/TrimVideoLatent.mdx b/built-in-nodes/TrimVideoLatent.mdx index 01e8dadc0..29784d928 100644 --- a/built-in-nodes/TrimVideoLatent.mdx +++ b/built-in-nodes/TrimVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrimVideoLatent" icon: "circle" mode: wide --- + The TrimVideoLatent node removes frames from the beginning of a video latent representation. It takes a latent video sample and trims off a specified number of frames from the start, returning the remaining portion of the video. This allows you to shorten video sequences by removing the initial frames. ## Inputs diff --git a/built-in-nodes/TripleCLIPLoader.mdx b/built-in-nodes/TripleCLIPLoader.mdx index dc6f485bd..c411635f1 100644 --- a/built-in-nodes/TripleCLIPLoader.mdx +++ b/built-in-nodes/TripleCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripleCLIPLoader" icon: "circle" mode: wide --- + The TripleCLIPLoader node loads three different text encoder models simultaneously and combines them into a single CLIP model. This is useful for advanced text encoding scenarios where multiple text encoders are needed, such as in SD3 workflows that require clip-l, clip-g, and t5 models working together. ## Inputs diff --git a/built-in-nodes/TripoConversionNode.mdx b/built-in-nodes/TripoConversionNode.mdx index 6dcf89215..c0e28fd08 100644 --- a/built-in-nodes/TripoConversionNode.mdx +++ b/built-in-nodes/TripoConversionNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TripoConversionNode" icon: "circle" mode: wide --- + The TripoConversionNode converts 3D models between different file formats using the Tripo API. It takes a task ID from a previous Tripo operation (model generation, rigging, or retargeting) and converts the resulting model to your desired format with various export options. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `original_model_task_id` | The task ID from a previous Tripo operation (model generation, rigging, or retargeting) | MODEL_TASK_ID,RIG_TASK_ID,RETARGET_TASK_ID | Yes | MODEL_TASK_ID
RIG_TASK_ID
RETARGET_TASK_ID | | `format` | The target file format for the converted 3D model | COMBO | Yes | GLTF
USDZ
FBX
OBJ
STL
3MF | | `quad` | Whether to convert triangles to quads (default: False) | BOOLEAN | No | True/False | @@ -36,10 +37,10 @@ The TripoConversionNode converts 3D models between different file formats using ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | *No named outputs* | This node processes the conversion asynchronously and returns the result through the Tripo API system | - | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoConversionNode/en.md) --- -**Source fingerprint (SHA-256):** `7542fd7ee2307b06e5caa78ce427140fbcb56e8ea383ce327828040330ea1b01` +**Source fingerprint (SHA-256):** `14aafa9c5fc430eb125bb946eb634dc0e65d63688413fc1cd079677e78b83cbd` diff --git a/built-in-nodes/TripoImageToModelNode.mdx b/built-in-nodes/TripoImageToModelNode.mdx index 3bb33e3b4..9ff3cb69b 100644 --- a/built-in-nodes/TripoImageToModelNode.mdx +++ b/built-in-nodes/TripoImageToModelNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TripoImageToModelNode" icon: "circle" mode: wide --- + Generates 3D models synchronously based on a single image using Tripo's API. This node takes an input image and converts it into a 3D model with various customization options for texture, quality, and model properties. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | Input image used to generate the 3D model | IMAGE | Yes | - | | `model_version` | The model version to use for generation | COMBO | No | `"v1.4"`
`"v3.0"`
`"v3.5"`
`"v3.6"` | | `style` | Style setting for the generated model (default: "None") | COMBO | No | `"None"`
`"realistic"`
`"cartoon"`
`"sculpture"`
`"low_poly"` | @@ -30,7 +31,7 @@ Generates 3D models synchronously based on a single image using Tripo's API. Thi ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The generated 3D model file (for backward compatibility only) | STRING | | `model task_id` | The task ID for tracking the model generation process | MODEL_TASK_ID | | `GLB` | The generated 3D model in GLB format | FILE3DGLB | @@ -38,4 +39,4 @@ Generates 3D models synchronously based on a single image using Tripo's API. Thi > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImageToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `f12bae7cc766b7ac208243a10970da7719a13d6283d6b6c39444b577cafc7f04` +**Source fingerprint (SHA-256):** `020243931c5a05655804ce601f23821731725734dc7abd49bba2a554a0a272f6` diff --git a/built-in-nodes/TripoImportModelNode.mdx b/built-in-nodes/TripoImportModelNode.mdx new file mode 100644 index 000000000..fbe615904 --- /dev/null +++ b/built-in-nodes/TripoImportModelNode.mdx @@ -0,0 +1,28 @@ +--- +title: "TripoImportModelNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the TripoImportModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "TripoImportModelNode" +icon: "circle" +mode: wide +--- + +This node imports an external 3D model file into Tripo's system so you can use it with Tripo's post-processing nodes like Texture, Rig, and Convert. It uploads your model and returns a task ID that other Tripo nodes can use to reference the imported model. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model_3d` | 3D model to import (GLB / FBX / OBJ / STL, up to 150 MB). OBJ and STL files carry no embedded textures. | FILE3D | Yes | GLB
FBX
OBJ
STL
Any 3D format | + +**Note:** GLB format is recommended because textures are preserved only when embedded directly in the file. OBJ and STL files do not support embedded textures. GLTF (.gltf) format is not supported because it references external files; use a single-file GLB instead. The file size must not exceed 150 MB. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `model task_id` | A task ID that identifies the imported model for use with Tripo post-processing nodes | MODEL_TASK_ID | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImportModelNode/en.md) + +--- +**Source fingerprint (SHA-256):** `4fa13a108804f2a52190a85b5b5d58ff18190e9d182b556abada444788012fab` diff --git a/built-in-nodes/TripoMultiviewToModelNode.mdx b/built-in-nodes/TripoMultiviewToModelNode.mdx index b69b744d6..662190c21 100644 --- a/built-in-nodes/TripoMultiviewToModelNode.mdx +++ b/built-in-nodes/TripoMultiviewToModelNode.mdx @@ -5,13 +5,14 @@ sidebarTitle: "TripoMultiviewToModelNode" icon: "circle" mode: wide --- + This node generates 3D models synchronously using Tripo's API by processing up to four images showing different views of an object. It requires a front image and at least one additional view (left, back, or right) to create a complete 3D model with texture and material options. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `image` | Front view image of the object (required) | IMAGE | Yes | - | +|-----------|-------------|-----------|----------|-------| +| `image` | Front view image of the object | IMAGE | Yes | - | | `image_left` | Left view image of the object | IMAGE | No | - | | `image_back` | Back view image of the object | IMAGE | No | - | | `image_right` | Right view image of the object | IMAGE | No | - | @@ -32,7 +33,7 @@ This node generates 3D models synchronously using Tripo's API by processing up t ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | File path or identifier for the generated 3D model (for backward compatibility only) | STRING | | `model task_id` | Task identifier for tracking the model generation process | MODEL_TASK_ID | | `GLB` | The generated 3D model file in GLB format | FILE3DGLB | @@ -40,4 +41,4 @@ This node generates 3D models synchronously using Tripo's API by processing up t > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoMultiviewToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `f44a39bd15dfd6111be191de81490136280491930ec0aa7159849f137479b089` +**Source fingerprint (SHA-256):** `17e8b7a72b6d98585daf5c4839f6fdea08f236fb06287dedc4bf8723bdf5c885` diff --git a/built-in-nodes/TripoP1ImageToModelNode.mdx b/built-in-nodes/TripoP1ImageToModelNode.mdx index 931527e70..c7c985e00 100644 --- a/built-in-nodes/TripoP1ImageToModelNode.mdx +++ b/built-in-nodes/TripoP1ImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoP1ImageToModelNode" icon: "circle" mode: wide --- + ## Overview This node converts a single 2D image into a 3D model using the Tripo P1 API. It is optimized for generating low-polygon, game-ready meshes. @@ -12,7 +13,7 @@ This node converts a single 2D image into a 3D model using the Tripo P1 API. It ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | The input image to convert to a 3D model. | IMAGE | Yes | - | | `output_mode` | A dictionary specifying the output mode and quality settings. This parameter controls the type of model generated and its texture quality. The available options are defined by the `_build_p1_output_mode` helper function and include settings for `texture_quality` (e.g., "standard", "high", "ultra") and `image_alignment`. | DICT | Yes | See description | | `enable_image_autofix` | Pre-process the input image for better generation quality. (default: False) | BOOLEAN | No | True
False | @@ -25,7 +26,7 @@ This node converts a single 2D image into a 3D model using the Tripo P1 API. It ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The file path to the generated 3D model. This output is provided for backward compatibility only. | STRING | | `model task_id` | The unique task ID for the model generation request. | MODEL_TASK_ID | | `GLB` | The generated 3D model in GLB format. | FILE3DGLB | @@ -33,4 +34,4 @@ This node converts a single 2D image into a 3D model using the Tripo P1 API. It > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoP1ImageToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `2ac611603dd6eb88700a8105c19f97a8c4eefe5f4efb23d8854ccc27af590626` +**Source fingerprint (SHA-256):** `e45f8b77bf5240852c9ad7d065811a4b580ca4f38849d67c7bd62964fb2768b1` diff --git a/built-in-nodes/TripoP1MultiviewToModelNode.mdx b/built-in-nodes/TripoP1MultiviewToModelNode.mdx index 3fd5f63e1..3de1aaf81 100644 --- a/built-in-nodes/TripoP1MultiviewToModelNode.mdx +++ b/built-in-nodes/TripoP1MultiviewToModelNode.mdx @@ -5,14 +5,13 @@ sidebarTitle: "TripoP1MultiviewToModelNode" icon: "circle" mode: wide --- -## Overview This node generates a 3D model from 2 to 4 reference images of an object or character. You provide images from different angles (front, left, back, right), and the node creates a 3D mesh in GLB format. The front view is required, and you can optionally add any combination of the other three views for better results. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `image` | Front view (0°). Required. | IMAGE | Yes | - | | `image_left` | Left view (90°), i.e. the subject's left side. | IMAGE | No | - | | `image_back` | Back view (180°). | IMAGE | No | - | @@ -29,7 +28,7 @@ This node generates a 3D model from 2 to 4 reference images of an object or char ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The filename of the generated GLB model (for backward compatibility only). | STRING | | `model_task_id` | The unique task ID for this model generation request. | MODEL_TASK_ID | | `GLB` | The generated 3D model in GLB format. | FILE3DGLB | @@ -37,4 +36,4 @@ This node generates a 3D model from 2 to 4 reference images of an object or char > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoP1MultiviewToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `29bb87cdc5d3eef891a653c622e8876a37d6e6dc1a43e5c248b184060ead9029` +**Source fingerprint (SHA-256):** `a9f1b334ca425631b5f841328ff993df82636cf3e3b7d1269c46f2b396155970` diff --git a/built-in-nodes/TripoP1TextToModelNode.mdx b/built-in-nodes/TripoP1TextToModelNode.mdx index dc42705aa..8b201af4f 100644 --- a/built-in-nodes/TripoP1TextToModelNode.mdx +++ b/built-in-nodes/TripoP1TextToModelNode.mdx @@ -5,14 +5,13 @@ sidebarTitle: "TripoP1TextToModelNode" icon: "circle" mode: wide --- -## Overview This node generates a 3D model from a text description using the Tripo P1 API. It is optimized for creating low-poly, game-ready meshes with stable topology, making it suitable for real-time applications. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | The text description of the 3D model you want to generate. | STRING | Yes | Up to 1024 characters | | `negative_prompt` | A text description of what you do not want in the generated model. | STRING | No | Up to 255 characters | | `output_mode` | Controls the output model's quality and texture settings. This parameter is a dictionary with the following keys:

`texture_quality`: STRING, Range: `"standard"`
`pbr`: BOOLEAN, default: True
`texture`: BOOLEAN, default: True
`subdivision`: INT, default: 0, Range: 0 to 2
`texture_size`: INT, default: 2048, Range: 512 to 4096 (must be a power of 2)
`texture_format`: STRING, Range: `"png"`
`texture_clean`: BOOLEAN, default: False
`texture_seamless`: BOOLEAN, default: False

Default: `{"texture_quality": "standard", "pbr": True, "texture": True, "subdivision": 0, "texture_size": 2048, "texture_format": "png", "texture_clean": False, "texture_seamless": False}` | DICT | Yes | See description | @@ -26,7 +25,7 @@ This node generates a 3D model from a text description using the Tripo P1 API. I ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The file path to the generated 3D model (for backward compatibility only). | STRING | | `model task_id` | The unique task ID for the model generation request. | MODEL_TASK_ID | | `GLB` | The generated 3D model in GLB format. | FILE3DGLB | @@ -34,4 +33,4 @@ This node generates a 3D model from a text description using the Tripo P1 API. I > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoP1TextToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `154e75209d65c823d5681b74cd12fe7b2ed37d7b94bf51cac86f343c68f85722` +**Source fingerprint (SHA-256):** `189b0c301daf29e57962038f5cd8b7045baf12a6903877f155c0befcb5abd297` diff --git a/built-in-nodes/TripoRefineNode.mdx b/built-in-nodes/TripoRefineNode.mdx index e83126d2f..29918a562 100644 --- a/built-in-nodes/TripoRefineNode.mdx +++ b/built-in-nodes/TripoRefineNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TripoRefineNode" icon: "circle" mode: wide --- + The TripoRefineNode refines draft 3D models created specifically by Tripo v1.4 models. It takes a model task ID and processes it through the Tripo API to generate an improved version of the model. This node is designed to work exclusively with draft models produced by Tripo v1.4 models. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_task_id` | Must be a v1.4 Tripo model | MODEL_TASK_ID | Yes | - | **Note:** This node only accepts draft models created by Tripo v1.4 models. Using models from other versions may result in errors. @@ -18,7 +19,7 @@ The TripoRefineNode refines draft 3D models created specifically by Tripo v1.4 m ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The file path or reference to the refined model (for backward compatibility only) | STRING | | `model task_id` | The task identifier for the refined model operation | MODEL_TASK_ID | | `GLB` | The refined 3D model in GLB format | FILE3DGLB | @@ -26,4 +27,4 @@ The TripoRefineNode refines draft 3D models created specifically by Tripo v1.4 m > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/en.md) --- -**Source fingerprint (SHA-256):** `bb4b17652fd05c489e6151f23461fa79ae090f3b59491775768b32ca2b61d33c` +**Source fingerprint (SHA-256):** `502064a5f153ed05b985f859f27b26eb5219427a17b876cfebedfdcf3194fe12` diff --git a/built-in-nodes/TripoRetargetNode.mdx b/built-in-nodes/TripoRetargetNode.mdx index 8e5dd8eb8..f3fa43921 100644 --- a/built-in-nodes/TripoRetargetNode.mdx +++ b/built-in-nodes/TripoRetargetNode.mdx @@ -5,14 +5,15 @@ sidebarTitle: "TripoRetargetNode" icon: "circle" mode: wide --- + The TripoRetargetNode applies predefined animations to 3D character models by retargeting motion data. It takes a previously rigged 3D model and applies one of several preset animations, generating an animated 3D model file as output. The node communicates with the Tripo API to process the animation retargeting operation. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `original_model_task_id` | The task ID of the previously processed rigged 3D model to apply animation to | RIG_TASK_ID | Yes | - | -| `animation` | The animation preset to apply to the 3D model. Options include humanoid animations (idle, walk, run, dive, climb, jump, slash, shoot, hurt, fall, turn) and creature animations (quadruped walk, hexapod walk, octopod walk, serpentine march, aquatic march). | STRING | Yes | "preset:idle"
"preset:walk"
"preset:run"
"preset:dive"
"preset:climb"
"preset:jump"
"preset:slash"
"preset:shoot"
"preset:hurt"
"preset:fall"
"preset:turn"
"preset:quadruped:walk"
"preset:hexapod:walk"
"preset:octopod:walk"
"preset:serpentine:march"
"preset:aquatic:march" | +| `animation` | The animation preset to apply to the 3D model. Options include humanoid animations (idle, walk, run, dive, climb, jump, slash, shoot, hurt, fall, turn) and creature animations (quadruped walk, hexapod walk, octopod walk, serpentine march, aquatic march). | STRING | Yes | `"preset:idle"`
`"preset:walk"`
`"preset:run"`
`"preset:dive"`
`"preset:climb"`
`"preset:jump"`
`"preset:slash"`
`"preset:shoot"`
`"preset:hurt"`
`"preset:fall"`
`"preset:turn"`
`"preset:quadruped:walk"`
`"preset:hexapod:walk"`
`"preset:octopod:walk"`
`"preset:serpentine:march"`
`"preset:aquatic:march"` | | `auth_token_comfy_org` | Authentication token for Comfy.org API access (hidden parameter) | AUTH_TOKEN_COMFY_ORG | No | - | | `api_key_comfy_org` | API key for Comfy.org service access (hidden parameter) | API_KEY_COMFY_ORG | No | - | | `unique_id` | Unique identifier for tracking the operation (hidden parameter) | UNIQUE_ID | No | - | @@ -20,7 +21,7 @@ The TripoRetargetNode applies predefined animations to 3D character models by re ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The generated animated 3D model file (for backward compatibility only) | STRING | | `retarget task_id` | The task ID for tracking the retargeting operation | RETARGET_TASK_ID | | `GLB` | The animated 3D model in GLB format | FILE3DGLB | @@ -28,4 +29,4 @@ The TripoRetargetNode applies predefined animations to 3D character models by re > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRetargetNode/en.md) --- -**Source fingerprint (SHA-256):** `31d90c0a11a6a57fbc55f2c3b8e0e8e73943f048734e5f2d68711bf000730e0b` +**Source fingerprint (SHA-256):** `c20ad0b1f59058cbb866e83e236f01ba480b41951ff9486190cb311e6636b33c` diff --git a/built-in-nodes/TripoRigNode.mdx b/built-in-nodes/TripoRigNode.mdx index 7c832dac9..ee33b1868 100644 --- a/built-in-nodes/TripoRigNode.mdx +++ b/built-in-nodes/TripoRigNode.mdx @@ -5,18 +5,19 @@ sidebarTitle: "TripoRigNode" icon: "circle" mode: wide --- + The TripoRigNode generates a rigged 3D model from an original model task ID. It sends a request to the Tripo API to create an animated rig in GLB format using the Tripo specification, then polls the API until the rig generation task is complete. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `original_model_task_id` | The task ID of the original 3D model to be rigged | MODEL_TASK_ID | Yes | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The generated rigged 3D model file (kept for backward compatibility) | STRING | | `rig task_id` | The task ID for tracking the rig generation process | RIG_TASK_ID | | `GLB` | The generated rigged 3D model in GLB format | FILE3DGLB | @@ -24,4 +25,4 @@ The TripoRigNode generates a rigged 3D model from an original model task ID. It > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRigNode/en.md) --- -**Source fingerprint (SHA-256):** `c00053314112cf1a403d7bf1cf77dcb6cede6b4db83046d459069f2b57bb6de9` +**Source fingerprint (SHA-256):** `01b2b71097b5bbac33e09e2d81e655a145db1ae30bd704e2cc0cbdd215f0a0a0` diff --git a/built-in-nodes/TripoSplatConditioning.mdx b/built-in-nodes/TripoSplatConditioning.mdx index 1321d9377..5f337ec8b 100644 --- a/built-in-nodes/TripoSplatConditioning.mdx +++ b/built-in-nodes/TripoSplatConditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatConditioning" icon: "circle" mode: wide --- -# TripoSplat Conditioning This node encodes an input image using DINOv3 and the Flux2 VAE to create positive and negative conditioning data for the TripoSplat model. It also generates a fixed-size noise target (latent plus camera data) that serves as the starting point for the KSampler. diff --git a/built-in-nodes/TripoSplatPreprocessImage.mdx b/built-in-nodes/TripoSplatPreprocessImage.mdx index 19c144907..1d9fb2a25 100644 --- a/built-in-nodes/TripoSplatPreprocessImage.mdx +++ b/built-in-nodes/TripoSplatPreprocessImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatPreprocessImage" icon: "circle" mode: wide --- -# TripoSplat Preprocess Image This node crops each input image to a centered square on a black background, then adds padding to reach the specified output size. It is designed to prepare images for the TripoSplat 3D model by ensuring consistent square framing and optional alpha matte erosion to prevent border artifacts. diff --git a/built-in-nodes/TripoSplatSamplingPreview.mdx b/built-in-nodes/TripoSplatSamplingPreview.mdx index e2a1f4507..27efa25ff 100644 --- a/built-in-nodes/TripoSplatSamplingPreview.mdx +++ b/built-in-nodes/TripoSplatSamplingPreview.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatSamplingPreview" icon: "circle" mode: wide --- -# TripoSplat Sampling Preview This node patches a TripoSplat model so that when used with the standard KSampler node, a live preview of the decoded gaussian splat is shown at each sampling step. It works by wrapping the sampler's callback to decode the model's output into a preview image after every step. diff --git a/built-in-nodes/TripoTextToModelNode.mdx b/built-in-nodes/TripoTextToModelNode.mdx index 366ddc991..454e0f993 100644 --- a/built-in-nodes/TripoTextToModelNode.mdx +++ b/built-in-nodes/TripoTextToModelNode.mdx @@ -5,16 +5,17 @@ sidebarTitle: "TripoTextToModelNode" icon: "circle" mode: wide --- + Generates 3D models synchronously based on a text prompt using Tripo's API. This node takes a text description and creates a 3D model with optional texture and material properties. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text description for generating the 3D model (multiline input) | STRING | Yes | - | | `negative_prompt` | Text description of what to avoid in the generated model (multiline input) | STRING | No | - | | `model_version` | The version of the Tripo model to use for generation (default: v2.5-20250123) | COMBO | No | `v1.4`
`v2.0`
`v2.5-20250123`
`v3.0` | -| `style` | Style setting for the generated model (default: "None") | COMBO | No | `None`
`sculpture`
`low-poly`
`voxel`
`brick`
`clay`
`marble`
`origami`
`papercraft`
`pixel-art`
`tile`
`cartoon`
`fantasy`
`hand-drawn`
`illustration`
`isometric`
`pixel-art`
`sketch`
`stained-glass`
`steampunk`
`vector`
`watercolor` | +| `style` | Style setting for the generated model (default: "None") | COMBO | No | `None`
`sculpture`
`low-poly`
`voxel`
`brick`
`clay`
`marble`
`origami`
`papercraft`
`pixel-art`
`tile`
`cartoon`
`fantasy`
`hand-drawn`
`illustration`
`isometric`
`sketch`
`stained-glass`
`steampunk`
`vector`
`watercolor` | | `texture` | Whether to generate textures for the model (default: True) | BOOLEAN | No | - | | `pbr` | Whether to generate PBR (Physically Based Rendering) materials (default: True) | BOOLEAN | No | - | | `image_seed` | Random seed for image generation (default: 42) | INT | No | - | @@ -30,7 +31,7 @@ Generates 3D models synchronously based on a text prompt using Tripo's API. This ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The generated 3D model file (for backward compatibility only) | STRING | | `model task_id` | The unique task identifier for the model generation process | MODEL_TASK_ID | | `GLB` | The generated 3D model in GLB format | FILE3DGLB | @@ -38,4 +39,4 @@ Generates 3D models synchronously based on a text prompt using Tripo's API. This > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextToModelNode/en.md) --- -**Source fingerprint (SHA-256):** `6cd6fefff0fbda14729b68383209eded6eb2e779ccf39dd2e03c0ddf04859372` +**Source fingerprint (SHA-256):** `7fb03aedc1481d95c6dcbdc1be1cd8087fb5104473d58d29827eb85b397129b8` diff --git a/built-in-nodes/TripoTextureNode.mdx b/built-in-nodes/TripoTextureNode.mdx index 7c6673e5e..ab61d5eb2 100644 --- a/built-in-nodes/TripoTextureNode.mdx +++ b/built-in-nodes/TripoTextureNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "TripoTextureNode" icon: "circle" mode: wide --- + The TripoTextureNode generates textured 3D models using the Tripo API. It takes a model task ID and applies texture generation with various options including PBR materials, texture quality settings, and alignment methods. The node communicates with the Tripo API to process the texture generation request and returns the resulting model file and task ID. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model_task_id` | The task ID of the model to apply textures to | MODEL_TASK_ID | Yes | - | | `texture` | Whether to generate textures (default: True) | BOOLEAN | No | - | | `pbr` | Whether to generate PBR (Physically Based Rendering) materials (default: True) | BOOLEAN | No | - | @@ -23,7 +24,7 @@ The TripoTextureNode generates textured 3D models using the Tripo API. It takes ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `model_file` | The generated model file with applied textures (for backward compatibility only) | STRING | | `model task_id` | The task ID for tracking the texture generation process | MODEL_TASK_ID | | `GLB` | The generated 3D model in GLB format with applied textures | FILE3DGLB | @@ -31,4 +32,4 @@ The TripoTextureNode generates textured 3D models using the Tripo API. It takes > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextureNode/en.md) --- -**Source fingerprint (SHA-256):** `dca49933b1b892df38004adc34ab0d95cdcb32d3e38db0e66b260ab7a58dcea5` +**Source fingerprint (SHA-256):** `6dee13c5785486cc560a250e35234ebed9a544bcf6e30e6babbbb09c1314bbe1` diff --git a/built-in-nodes/TruncateText.mdx b/built-in-nodes/TruncateText.mdx index 5e18ae9ca..6d791b7c0 100644 --- a/built-in-nodes/TruncateText.mdx +++ b/built-in-nodes/TruncateText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TruncateText" icon: "circle" mode: wide --- + This node shortens text by cutting it off at a specified maximum length. It takes any input text and returns only the first part, up to the number of characters you set. It is a simple way to ensure text does not exceed a certain size. ## Inputs diff --git a/built-in-nodes/UNETLoader.mdx b/built-in-nodes/UNETLoader.mdx index 2e12d58e2..3ad4fa8ef 100644 --- a/built-in-nodes/UNETLoader.mdx +++ b/built-in-nodes/UNETLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNETLoader" icon: "circle" mode: wide --- + The UNETLoader node is designed for loading U-Net models by name, facilitating the use of pre-trained U-Net architectures within the system. This node will detect models located in the `ComfyUI/models/diffusion_models` folder. diff --git a/built-in-nodes/UNetCrossAttentionMultiply.mdx b/built-in-nodes/UNetCrossAttentionMultiply.mdx index e857a6717..dc5534693 100644 --- a/built-in-nodes/UNetCrossAttentionMultiply.mdx +++ b/built-in-nodes/UNetCrossAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetCrossAttentionMultiply" icon: "circle" mode: wide --- + The UNetCrossAttentionMultiply node applies multiplication factors to the cross-attention mechanism in a UNet model. It allows you to scale the query, key, value, and output components of the cross-attention layers to experiment with different attention behaviors and effects. ## Inputs diff --git a/built-in-nodes/UNetSelfAttentionMultiply.mdx b/built-in-nodes/UNetSelfAttentionMultiply.mdx index 0dc5fcd5e..5b5ac7083 100644 --- a/built-in-nodes/UNetSelfAttentionMultiply.mdx +++ b/built-in-nodes/UNetSelfAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetSelfAttentionMultiply" icon: "circle" mode: wide --- + The UNetSelfAttentionMultiply node applies multiplication factors to the query, key, value, and output components of the self-attention mechanism in a UNet model. It allows you to scale different parts of the attention computation to experiment with how attention weights affect the model's behavior. ## Inputs diff --git a/built-in-nodes/UNetTemporalAttentionMultiply.mdx b/built-in-nodes/UNetTemporalAttentionMultiply.mdx index 3e16aaba9..9ea953a88 100644 --- a/built-in-nodes/UNetTemporalAttentionMultiply.mdx +++ b/built-in-nodes/UNetTemporalAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetTemporalAttentionMultiply" icon: "circle" mode: wide --- + The UNetTemporalAttentionMultiply node applies multiplication factors to different types of attention mechanisms in a temporal UNet model. It modifies the model by adjusting the weights of self-attention and cross-attention layers, distinguishing between structural and temporal components. This allows fine-tuning of how much influence each attention type has on the model's output. ## Inputs diff --git a/built-in-nodes/USOStyleReference.mdx b/built-in-nodes/USOStyleReference.mdx index f699381f5..877c9408a 100644 --- a/built-in-nodes/USOStyleReference.mdx +++ b/built-in-nodes/USOStyleReference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "USOStyleReference" icon: "circle" mode: wide --- + The USOStyleReference node applies style reference patches to models using encoded image features from CLIP vision output. It creates a modified version of the input model by incorporating style information extracted from visual inputs, enabling style transfer or reference-based generation capabilities. ## Inputs diff --git a/built-in-nodes/UpscaleModelLoader.mdx b/built-in-nodes/UpscaleModelLoader.mdx index fa5ed5109..e8a92a0dd 100644 --- a/built-in-nodes/UpscaleModelLoader.mdx +++ b/built-in-nodes/UpscaleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UpscaleModelLoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/upscale_models` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. The UpscaleModelLoader node is designed for loading upscale models from a specified directory. It facilitates the retrieval and preparation of upscale models for image upscaling tasks, ensuring that the models are correctly loaded and configured for evaluation. diff --git a/built-in-nodes/VAEDecode.mdx b/built-in-nodes/VAEDecode.mdx index d8e641211..6767f2d39 100644 --- a/built-in-nodes/VAEDecode.mdx +++ b/built-in-nodes/VAEDecode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecode" icon: "circle" mode: wide --- + The VAEDecode node is designed for decoding latent representations into images using a specified Variational Autoencoder (VAE). It serves the purpose of generating images from compressed data representations, facilitating the reconstruction of images from their latent space encodings. ## Inputs diff --git a/built-in-nodes/VAEDecodeAudio.mdx b/built-in-nodes/VAEDecodeAudio.mdx index dc1b39a64..e80ccfccb 100644 --- a/built-in-nodes/VAEDecodeAudio.mdx +++ b/built-in-nodes/VAEDecodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeAudio" icon: "circle" mode: wide --- + The VAEDecodeAudio node converts latent representations back into audio waveforms using a Variational Autoencoder. It takes encoded audio samples and processes them through the VAE to reconstruct the original audio, applying normalization to ensure consistent output levels. The resulting audio is returned with a standard sample rate of 44100 Hz, or the sample rate from the input samples if provided. ## Inputs diff --git a/built-in-nodes/VAEDecodeAudioTiled.mdx b/built-in-nodes/VAEDecodeAudioTiled.mdx index 287840868..b207201cd 100644 --- a/built-in-nodes/VAEDecodeAudioTiled.mdx +++ b/built-in-nodes/VAEDecodeAudioTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeAudioTiled" icon: "circle" mode: wide --- + This node converts a compressed audio representation (latent samples) back into an audio waveform using a Variational Autoencoder (VAE). It processes the data in smaller, overlapping sections (tiles) to manage memory usage, making it suitable for handling longer audio sequences. ## Inputs diff --git a/built-in-nodes/VAEDecodeHunyuan3D.mdx b/built-in-nodes/VAEDecodeHunyuan3D.mdx index 16e473cff..50afe726c 100644 --- a/built-in-nodes/VAEDecodeHunyuan3D.mdx +++ b/built-in-nodes/VAEDecodeHunyuan3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeHunyuan3D" icon: "circle" mode: wide --- + The VAEDecodeHunyuan3D node converts latent representations into 3D voxel data using a VAE decoder. It processes the latent samples through the VAE model with configurable chunking and resolution settings to generate volumetric data suitable for 3D applications. ## Inputs diff --git a/built-in-nodes/VAEDecodeTiled.mdx b/built-in-nodes/VAEDecodeTiled.mdx index 431938ba2..a836cba9a 100644 --- a/built-in-nodes/VAEDecodeTiled.mdx +++ b/built-in-nodes/VAEDecodeTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeTiled" icon: "circle" mode: wide --- + The VAEDecodeTiled node decodes latent representations into images using a tiled approach to handle large images efficiently. It processes the input in smaller tiles to manage memory usage while maintaining image quality. The node also supports video VAEs by processing temporal frames in chunks with overlap for smooth transitions. ## Inputs diff --git a/built-in-nodes/VAEDecodeTripoSplat.mdx b/built-in-nodes/VAEDecodeTripoSplat.mdx index 81131ca4f..1bf432a2c 100644 --- a/built-in-nodes/VAEDecodeTripoSplat.mdx +++ b/built-in-nodes/VAEDecodeTripoSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VAEDecodeTripoSplat" icon: "circle" mode: wide --- -# VAEDecodeTripoSplat Decode a TripoSplat latent representation into a 3D gaussian splat. This node takes the sampled latent from a TripoSplat model and reconstructs it as a set of 3D gaussians, which can be adjusted in density by modifying the number of gaussians produced. diff --git a/built-in-nodes/VAEEncode.mdx b/built-in-nodes/VAEEncode.mdx index 00fc9114a..d06acd249 100644 --- a/built-in-nodes/VAEEncode.mdx +++ b/built-in-nodes/VAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncode" icon: "circle" mode: wide --- + This node is designed for encoding images into a latent space representation using a specified VAE model. It abstracts the complexity of the encoding process, providing a straightforward way to transform images into their latent representations. ## Inputs diff --git a/built-in-nodes/VAEEncodeAudio.mdx b/built-in-nodes/VAEEncodeAudio.mdx index 08308d267..75151f315 100644 --- a/built-in-nodes/VAEEncodeAudio.mdx +++ b/built-in-nodes/VAEEncodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeAudio" icon: "circle" mode: wide --- + The VAEEncodeAudio node converts audio data into a latent representation using a Variational Autoencoder (VAE). It takes audio input and processes it through the VAE to generate compressed latent samples that can be used for further audio generation or manipulation tasks. The node automatically resamples audio to match the VAE's expected sample rate if needed before encoding. ## Inputs diff --git a/built-in-nodes/VAEEncodeForInpaint.mdx b/built-in-nodes/VAEEncodeForInpaint.mdx index 3774f797c..3ae3246ab 100644 --- a/built-in-nodes/VAEEncodeForInpaint.mdx +++ b/built-in-nodes/VAEEncodeForInpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeForInpaint" icon: "circle" mode: wide --- + This node is designed for encoding images into a latent representation suitable for inpainting tasks, incorporating additional preprocessing steps to adjust the input image and mask for optimal encoding by the VAE model. ## Inputs diff --git a/built-in-nodes/VAEEncodeTiled.mdx b/built-in-nodes/VAEEncodeTiled.mdx index adbe2fa7f..164ea9cf6 100644 --- a/built-in-nodes/VAEEncodeTiled.mdx +++ b/built-in-nodes/VAEEncodeTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeTiled" icon: "circle" mode: wide --- + The VAEEncodeTiled node processes images by breaking them into smaller tiles and encoding them using a Variational Autoencoder. This tiled approach allows handling of large images that might otherwise exceed memory limitations. The node supports both image and video VAEs, with separate tiling controls for spatial and temporal dimensions. ## Inputs diff --git a/built-in-nodes/VAELoader.mdx b/built-in-nodes/VAELoader.mdx index 5bcd0b193..c7a252ad6 100644 --- a/built-in-nodes/VAELoader.mdx +++ b/built-in-nodes/VAELoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAELoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/vae` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. The VAELoader node is designed for loading Variational Autoencoder (VAE) models, specifically tailored to handle both standard and approximate VAEs. It supports loading VAEs by name, including specialized handling for 'taesd' and 'taesdxl' models, and dynamically adjusts based on the VAE's specific configuration. diff --git a/built-in-nodes/VAESave.mdx b/built-in-nodes/VAESave.mdx index 03bb22f58..ca414851e 100644 --- a/built-in-nodes/VAESave.mdx +++ b/built-in-nodes/VAESave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAESave" icon: "circle" mode: wide --- + The VAESave node is designed for saving VAE models along with their metadata, including prompts and additional PNG information, to a specified output directory. It encapsulates the functionality to serialize the model state and associated information into a file, facilitating the preservation and sharing of trained models. ## Inputs diff --git a/built-in-nodes/VOIDInpaintConditioning.mdx b/built-in-nodes/VOIDInpaintConditioning.mdx index 7c02e54cc..db817f763 100644 --- a/built-in-nodes/VOIDInpaintConditioning.mdx +++ b/built-in-nodes/VOIDInpaintConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDInpaintConditioning" icon: "circle" mode: wide --- + The VOIDInpaintConditioning node prepares the conditioning data needed for inpainting with CogVideoX models. It takes a source video and a preprocessed quadmask, encodes them through the VAE, and combines them into a 32-channel conditioning signal that the model uses to fill in the masked areas. ## Inputs diff --git a/built-in-nodes/VOIDQuadmaskPreprocess.mdx b/built-in-nodes/VOIDQuadmaskPreprocess.mdx index 7ab8c3f8a..079e55333 100644 --- a/built-in-nodes/VOIDQuadmaskPreprocess.mdx +++ b/built-in-nodes/VOIDQuadmaskPreprocess.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDQuadmaskPreprocess" icon: "circle" mode: wide --- + ## Overview The VOIDQuadmaskPreprocess node prepares a mask for VOID inpainting by converting it into a special four-level "quadmask." It takes an input mask, optionally dilates the primary region, then quantizes the mask values into four distinct levels representing different semantic regions (primary object, overlap, affected area, and background). Finally, it inverts and normalizes the mask so the output values are in the range [0, 1], where 1.0 indicates the area to remove and 0.0 indicates the area to keep. diff --git a/built-in-nodes/VOIDSampler.mdx b/built-in-nodes/VOIDSampler.mdx index 3146d7ffa..e078fe9bf 100644 --- a/built-in-nodes/VOIDSampler.mdx +++ b/built-in-nodes/VOIDSampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDSampler" icon: "circle" mode: wide --- + ## Overview The VOIDSampler node provides a specialized DDIM sampling method designed specifically for VOID inpainting models. It implements the same denoising process used during VOID model training, without the noise scaling that standard KSamplers apply. This node is intended for use with SamplerCustom or SamplerCustomAdvanced nodes, and should be paired with RandomNoise or VOIDWarpedNoiseSource. diff --git a/built-in-nodes/VOIDWarpedNoise.mdx b/built-in-nodes/VOIDWarpedNoise.mdx index 83c993fd8..8a1ad6e03 100644 --- a/built-in-nodes/VOIDWarpedNoise.mdx +++ b/built-in-nodes/VOIDWarpedNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDWarpedNoise" icon: "circle" mode: wide --- + ## Overview Generates temporally-correlated noise for the second pass of the VOID video refinement process. It takes the output video from Pass 1 and warps Gaussian noise along optical flow vectors, creating noise that moves consistently with the video content. This warped noise is used as the starting latent for Pass 2, which improves temporal consistency in the final output. diff --git a/built-in-nodes/VOIDWarpedNoiseSource.mdx b/built-in-nodes/VOIDWarpedNoiseSource.mdx index 9ef56cd87..182848674 100644 --- a/built-in-nodes/VOIDWarpedNoiseSource.mdx +++ b/built-in-nodes/VOIDWarpedNoiseSource.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDWarpedNoiseSource" icon: "circle" mode: wide --- + ## Overview This node converts a LATENT (such as the output from the VOIDWarpedNoise node) into a NOISE source. This allows you to use the warped noise with the SamplerCustomAdvanced node for more controlled image generation. diff --git a/built-in-nodes/VPScheduler.mdx b/built-in-nodes/VPScheduler.mdx index 0b00e454e..b156a8696 100644 --- a/built-in-nodes/VPScheduler.mdx +++ b/built-in-nodes/VPScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VPScheduler" icon: "circle" mode: wide --- + The VPScheduler node is designed to generate a sequence of noise levels (sigmas) based on the Variance Preserving (VP) scheduling method. This sequence is crucial for guiding the denoising process in diffusion models, allowing for controlled generation of images or other data types. ## Inputs diff --git a/built-in-nodes/Veo3FirstLastFrameNode.mdx b/built-in-nodes/Veo3FirstLastFrameNode.mdx index 96bdc6b7b..7ba323068 100644 --- a/built-in-nodes/Veo3FirstLastFrameNode.mdx +++ b/built-in-nodes/Veo3FirstLastFrameNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Veo3FirstLastFrameNode" icon: "circle" mode: wide --- + The Veo3FirstLastFrameNode uses Google's Veo 3 model to generate a video based on a text prompt, with a provided first and last frame that define the start and end of the video sequence. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text description of the video (default: empty string). | STRING | Yes | N/A | | `negative_prompt` | Negative text prompt to guide what to avoid in the video (default: empty string). | STRING | No | N/A | | `resolution` | The resolution of the output video. | COMBO | Yes | `"720p"`
`"1080p"`
`"4k"` | @@ -19,7 +20,7 @@ The Veo3FirstLastFrameNode uses Google's Veo 3 model to generate a video based o | `seed` | Seed for video generation (default: 0). | INT | No | 0 to 4294967295 | | `first_frame` | The start frame for the video. | IMAGE | Yes | N/A | | `last_frame` | The end frame for the video. | IMAGE | Yes | N/A | -| `model` | The specific Veo 3 model to use for generation (default: "veo-3.1-generate"). | COMBO | No | `"veo-3.1-generate"`
`"veo-3.1-fast-generate"`
`"veo-3.1-lite"` | +| `model` | The specific Veo model to use for generation (default: "veo-3.1-generate"). | COMBO | No | `"veo-3.1-generate"`
`"veo-3.1-fast-generate"`
`"veo-3.1-lite"` | | `generate_audio` | Generate audio for the video (default: True). | BOOLEAN | No | N/A | **Note:** The `veo-3.1-lite` model does not support 4K resolution. If you select `veo-3.1-lite` and `4k` resolution, an error will occur. @@ -27,10 +28,10 @@ The Veo3FirstLastFrameNode uses Google's Veo 3 model to generate a video based o ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3FirstLastFrameNode/en.md) --- -**Source fingerprint (SHA-256):** `63d2cf6b636bff6e8bc4efc8b795cb63f6cd775e040323e290986266029109b3` +**Source fingerprint (SHA-256):** `2fe55d2a1d018e58fd290c901c596708898acda835d2358adf36ed80103aeb6e` diff --git a/built-in-nodes/Veo3VideoGenerationNode.mdx b/built-in-nodes/Veo3VideoGenerationNode.mdx index 3b29700b6..f2e18de9b 100644 --- a/built-in-nodes/Veo3VideoGenerationNode.mdx +++ b/built-in-nodes/Veo3VideoGenerationNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Veo3VideoGenerationNode" icon: "circle" mode: wide --- + Generates videos from text prompts using Google's Veo 3 API. This node supports multiple Veo 3 models, including fast and lite variants, and allows you to specify video resolution, duration, and audio generation. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text description of the video (default: "") | STRING | Yes | - | | `aspect_ratio` | Aspect ratio of the output video (default: "16:9") | COMBO | Yes | "16:9"
"9:16" | | `resolution` | Output video resolution. 4K is not available for veo-3.1-lite and veo-3.0 models. (default: "720p") | COMBO | No | "720p"
"1080p"
"4k" | @@ -28,10 +29,10 @@ Generates videos from text prompts using Google's Veo 3 API. This node supports ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3VideoGenerationNode/en.md) --- -**Source fingerprint (SHA-256):** `d19071ba853a846c797bc88d4a803357563f144ea9071fc79fc4203ea40f1a81` +**Source fingerprint (SHA-256):** `8aa8c5050343867ce6c684d4d378d0f444bb88d1edc8830541bfc28e5e238eab` diff --git a/built-in-nodes/VeoVideoGenerationNode.mdx b/built-in-nodes/VeoVideoGenerationNode.mdx index b83640ec6..316a0eaad 100644 --- a/built-in-nodes/VeoVideoGenerationNode.mdx +++ b/built-in-nodes/VeoVideoGenerationNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "VeoVideoGenerationNode" icon: "circle" mode: wide --- + Generates videos from text prompts using Google's Veo API. This node can create videos from text descriptions and optional image inputs, with control over parameters like aspect ratio, duration, and more. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `prompt` | Text description of the video (default: empty) | STRING | Yes | - | | `aspect_ratio` | Aspect ratio of the output video (default: "16:9") | COMBO | Yes | "16:9"
"9:16" | | `negative_prompt` | Negative text prompt to guide what to avoid in the video (default: empty) | STRING | No | - | @@ -26,10 +27,10 @@ Generates videos from text prompts using Google's Veo API. This node can create ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VeoVideoGenerationNode/en.md) --- -**Source fingerprint (SHA-256):** `abb403ceddb16511988e4ac98ae126c7d6de3bf2f25789189fc05d72f475ca95` +**Source fingerprint (SHA-256):** `055569f26c7e8f074371239f12f307ca86ce2aa5fd17ca55dd951b34f71fa559` diff --git a/built-in-nodes/Video Slice.mdx b/built-in-nodes/Video Slice.mdx index 6e85f0c9e..eb0d6928f 100644 --- a/built-in-nodes/Video Slice.mdx +++ b/built-in-nodes/Video Slice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Video Slice" icon: "circle" mode: wide --- + The Video Slice node allows you to extract a specific segment from a video. You can define a start time and a duration to trim the video, or simply skip the beginning frames. If the requested duration is longer than the remaining video, the node can either return what's available or raise an error. ## Inputs diff --git a/built-in-nodes/VideoLinearCFGGuidance.mdx b/built-in-nodes/VideoLinearCFGGuidance.mdx index 6872c3b5d..0082dba6d 100644 --- a/built-in-nodes/VideoLinearCFGGuidance.mdx +++ b/built-in-nodes/VideoLinearCFGGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VideoLinearCFGGuidance" icon: "circle" mode: wide --- + The VideoLinearCFGGuidance node applies a linear conditioning guidance scale to a video model, adjusting the influence of conditioned and unconditioned components over a specified range. This enables dynamic control over the generation process, allowing for fine-tuning of the model's output based on the desired level of conditioning. ## Inputs diff --git a/built-in-nodes/VideoTriangleCFGGuidance.mdx b/built-in-nodes/VideoTriangleCFGGuidance.mdx index cbffa8115..7cabbaa26 100644 --- a/built-in-nodes/VideoTriangleCFGGuidance.mdx +++ b/built-in-nodes/VideoTriangleCFGGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VideoTriangleCFGGuidance" icon: "circle" mode: wide --- + The VideoTriangleCFGGuidance node applies a triangular classifier-free guidance scaling pattern to video models. It modifies the conditioning scale over time using a triangular wave function that oscillates between the minimum CFG value and the original conditioning scale. This creates a dynamic guidance pattern that can help improve video generation consistency and quality. ## Inputs diff --git a/built-in-nodes/Vidu2ImageToVideoNode.mdx b/built-in-nodes/Vidu2ImageToVideoNode.mdx index 0128627b9..b8312dc20 100644 --- a/built-in-nodes/Vidu2ImageToVideoNode.mdx +++ b/built-in-nodes/Vidu2ImageToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Vidu2ImageToVideoNode" icon: "circle" mode: wide --- + The Vidu2 Image-to-Video Generation node creates a video sequence starting from a single input image. It uses a specified Vidu2 model to animate the scene based on an optional text prompt, controlling the video's length, resolution, and the intensity of motion. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The Vidu2 model to use for video generation. Different models offer varying speed and quality trade-offs. | COMBO | Yes | `"viduq2-pro-fast"`
`"viduq2-pro"`
`"viduq2-turbo"` | | `image` | An image to be used as the start frame of the generated video. Only one image is allowed. | IMAGE | Yes | - | | `prompt` | An optional text prompt for video generation (max 2000 characters). Default is an empty string. | STRING | No | - | @@ -21,17 +22,17 @@ The Vidu2 Image-to-Video Generation node creates a video sequence starting from **Constraints:** -* The `image` input must contain exactly one image. -* The input image's aspect ratio must be between 1:4 and 4:1. -* The `prompt` text is limited to a maximum of 2000 characters. +- The `image` input must contain exactly one image. +- The input image's aspect ratio must be between 1:4 and 4:1. +- The `prompt` text is limited to a maximum of 2000 characters. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2ImageToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `5311b64380bf089b846d5ac0c32330e021b79754cf2f3cac41f71ca1da3ffdda` +**Source fingerprint (SHA-256):** `4cf56654286561f3d211ce50d0dce141880fe0e0a63aa45ab41ae0ff5ab6ccc3` diff --git a/built-in-nodes/Vidu2ReferenceVideoNode.mdx b/built-in-nodes/Vidu2ReferenceVideoNode.mdx index a21b835cf..692336c28 100644 --- a/built-in-nodes/Vidu2ReferenceVideoNode.mdx +++ b/built-in-nodes/Vidu2ReferenceVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Vidu2ReferenceVideoNode" icon: "circle" mode: wide --- + The Vidu2 Reference-to-Video Generation node creates a video from a text prompt and multiple reference images. You can define up to seven subjects, each with its own set of reference images, and reference them in the prompt using `@subject{subject_id}`. The node generates a video with configurable duration, aspect ratio, and movement. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The AI model to use for video generation. | COMBO | Yes | `"viduq2"` | | `subjects` | For each subject, provide up to 3 reference images (7 images total across all subjects). Reference them in prompts via `@subject{subject_id}`. | AUTOGROW | Yes | N/A | | `prompt` | The text description used to guide the video generation. When the `audio` parameter is enabled, the video will include generated speech and background music based on this prompt. | STRING | Yes | N/A | @@ -32,10 +33,10 @@ The Vidu2 Reference-to-Video Generation node creates a video from a text prompt ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2ReferenceVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `73366d1ae9d64428141a7f9de3f9632f12e41918f85771a9a41619564c88ed38` +**Source fingerprint (SHA-256):** `da4b0a24e186f24cff8031c786bb765299b00bbfa13cc4161d53d3a68e466744` diff --git a/built-in-nodes/Vidu2StartEndToVideoNode.mdx b/built-in-nodes/Vidu2StartEndToVideoNode.mdx index c9b8ef88c..665452afd 100644 --- a/built-in-nodes/Vidu2StartEndToVideoNode.mdx +++ b/built-in-nodes/Vidu2StartEndToVideoNode.mdx @@ -5,30 +5,31 @@ sidebarTitle: "Vidu2StartEndToVideoNode" icon: "circle" mode: wide --- + This node generates a video by interpolating between a provided start frame and an end frame, guided by a text prompt. It uses a specified Vidu model to create a smooth transition between the two images over a set duration. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The Vidu model to use for video generation. | COMBO | Yes | `"viduq2-pro-fast"`
`"viduq2-pro"`
`"viduq2-turbo"` | | `first_frame` | The starting image for the video sequence. Only a single image is allowed. | IMAGE | Yes | - | | `end_frame` | The ending image for the video sequence. Only a single image is allowed. | IMAGE | Yes | - | -| `prompt` | A text description guiding the video generation (maximum 2000 characters). | STRING | Yes | - | +| `prompt` | Prompt description (max 2000 characters). | STRING | Yes | - | | `duration` | The length of the generated video in seconds (default: 5). | INT | No | 2 to 8 | | `seed` | A number used to initialize the random generation for reproducible results (default: 1). | INT | No | 0 to 2147483647 | | `resolution` | The output resolution of the generated video. | COMBO | No | `"720p"`
`"1080p"` | | `movement_amplitude` | The movement amplitude of objects in the frame. | COMBO | No | `"auto"`
`"small"`
`"medium"`
`"large"` | -**Note:** The `first_frame` and `end_frame` images must have similar aspect ratios. The node will validate that their aspect ratios are within a relative range of 0.8 to 1.25. +**Note:** The `first_frame` and `end_frame` images must have similar aspect ratios. The node validates that their aspect ratios are within a relative range of 0.8 to 1.25. Only one image is allowed for each input. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2StartEndToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `4d4caf53387132c420fe0bb0eea581e6784bdc59243607c6440d6548f70f859b` +**Source fingerprint (SHA-256):** `01316d15f95f264cadfb33978565fc320a9f42917693faa87c1367c0f31ca400` diff --git a/built-in-nodes/Vidu2TextToVideoNode.mdx b/built-in-nodes/Vidu2TextToVideoNode.mdx index 67cd105ed..e4d80a9d2 100644 --- a/built-in-nodes/Vidu2TextToVideoNode.mdx +++ b/built-in-nodes/Vidu2TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2TextToVideoNode" icon: "circle" mode: wide --- + The Vidu2 Text-to-Video Generation node creates a video from a text description. It connects to an external API to generate video content based on your prompt, allowing you to control the video's length, visual style, and format. ## Inputs @@ -28,4 +29,4 @@ The Vidu2 Text-to-Video Generation node creates a video from a text description. > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2TextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `eec93de5d781474f919001a4d78525d80478852424506fae245f445d1ef3b0ee` +**Source fingerprint (SHA-256):** `27b7c05ae1b3b23d07e775f67474ecef1ffc0bd8240f4aa2219e15949d854f27` diff --git a/built-in-nodes/Vidu3ImageToVideoNode.mdx b/built-in-nodes/Vidu3ImageToVideoNode.mdx index 8e4d371b5..7c9f099bf 100644 --- a/built-in-nodes/Vidu3ImageToVideoNode.mdx +++ b/built-in-nodes/Vidu3ImageToVideoNode.mdx @@ -5,16 +5,17 @@ sidebarTitle: "Vidu3ImageToVideoNode" icon: "circle" mode: wide --- + The Vidu Q3 Image-to-Video Generation node creates a video sequence starting from an input image. It uses a Vidu Q3 model to animate the image, optionally guided by a text prompt, and outputs a video file. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model to use for video generation. | COMBO | Yes | `"viduq3-pro"`
`"viduq3-turbo"` | | `model.resolution` | Resolution of the output video. The available options depend on the selected model. | COMBO | Yes | `"720p"`
`"1080p"`
`"2K"` (viduq3-pro only) | | `model.duration` | Duration of the output video in seconds (default: 5). | INT | Yes | 1 to 16 | -| `model.audio` | When enabled, outputs video with sound (including dialogue and sound effects) (default: False). | BOOLEAN | Yes | `True` / `False` | +| `model.audio` | When enabled, outputs video with sound (including dialogue and sound effects) (default: False). | BOOLEAN | Yes | `True`
`False` | | `image` | An image to be used as the start frame of the generated video. | IMAGE | Yes | - | | `prompt` | An optional text prompt for video generation (max 2000 characters) (default: empty). | STRING | No | - | | `seed` | A seed value for controlling the randomness of the generation (default: 1). | INT | No | 0 to 2147483647 | @@ -24,10 +25,10 @@ The Vidu Q3 Image-to-Video Generation node creates a video sequence starting fro ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3ImageToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `5081dcbad3e9203c7a1b5ddc0d041d51e1961a2e0a0672c2e14cba2f839f562d` +**Source fingerprint (SHA-256):** `77500d1e19928128decc010540670e311cd8ec4fcad913412517f47f0e27e15f` diff --git a/built-in-nodes/Vidu3StartEndToVideoNode.mdx b/built-in-nodes/Vidu3StartEndToVideoNode.mdx index 85eafed3d..4d325485b 100644 --- a/built-in-nodes/Vidu3StartEndToVideoNode.mdx +++ b/built-in-nodes/Vidu3StartEndToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Vidu3StartEndToVideoNode" icon: "circle" mode: wide --- + This node generates a video by interpolating between a provided start frame and an end frame, guided by a text prompt. It uses the Vidu Q3 model to create a seamless transition between the two images, producing a video of a specified duration and resolution. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The model to use for video generation. Selecting an option reveals additional configuration parameters for `resolution`, `duration`, and `audio`. | COMBO | Yes | `"viduq3-pro"`
`"viduq3-turbo"` | | `model.resolution` | Resolution of the output video. This parameter is revealed after selecting a `model`. | COMBO | Yes | `"720p"`
`"1080p"` | | `model.duration` | Duration of the output video in seconds (default: 5). This parameter is revealed after selecting a `model`. | INT | Yes | 1 to 16 | @@ -25,10 +26,10 @@ This node generates a video by interpolating between a provided start frame and ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `video` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3StartEndToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `a3a1befd61a011ccc9912972d07506c2e851ca94cda3f83fcc1faa8a1dc3905c` +**Source fingerprint (SHA-256):** `c917867c5a7b68a1286f445025070f9a55d8d10091d9562960e0428cbedf25e4` diff --git a/built-in-nodes/Vidu3TextToVideoNode.mdx b/built-in-nodes/Vidu3TextToVideoNode.mdx index f01a50f12..ef28dd29a 100644 --- a/built-in-nodes/Vidu3TextToVideoNode.mdx +++ b/built-in-nodes/Vidu3TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3TextToVideoNode" icon: "circle" mode: wide --- + The Vidu Q3 Text-to-Video Generation node creates a video from a text description. It uses the Vidu Q3 Pro or Q3 Turbo model to generate video content based on your prompt, allowing you to control the video's length, resolution, aspect ratio, and whether it includes audio. ## Inputs @@ -30,4 +31,4 @@ The Vidu Q3 Text-to-Video Generation node creates a video from a text descriptio > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3TextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `d135d453159d113f9198b7510838c5ce5feefbf3cb7b318a55df95e6d26aa7a9` +**Source fingerprint (SHA-256):** `89c23454375a43cdfaf46c9e0e55a8a8166d02ada47ca2e237bd9f73fa4d78db` diff --git a/built-in-nodes/ViduExtendVideoNode.mdx b/built-in-nodes/ViduExtendVideoNode.mdx index fa5e1781d..556f112ff 100644 --- a/built-in-nodes/ViduExtendVideoNode.mdx +++ b/built-in-nodes/ViduExtendVideoNode.mdx @@ -5,17 +5,18 @@ sidebarTitle: "ViduExtendVideoNode" icon: "circle" mode: wide --- + The ViduExtendVideoNode generates additional frames to extend the length of an existing video. It uses a specified AI model to create a seamless continuation based on the source video and an optional text prompt. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `model` | The AI model to use for video extension. Selecting a model reveals its specific duration and resolution settings. | COMBO | Yes | `"viduq2-pro"`
`"viduq2-turbo"` | -| `model.duration` | The duration of the extended video in seconds (default: 4). This setting appears after selecting a model. | INT | Yes | 1 to 7 | -| `model.resolution` | The resolution of the output video. This setting appears after selecting a model. | COMBO | Yes | `"720p"`
`"1080p"` | +|-----------|-------------|-----------|----------|-------| +| `model` | Model to use for video extension. Selecting a model reveals its specific duration and resolution settings. | COMBO | Yes | `"viduq2-pro"`
`"viduq2-turbo"` | +| `model.duration` | Duration of the extended video in seconds (default: 4). This setting appears after selecting a model. | INT | Yes | 1 to 7 | +| `model.resolution` | Resolution of the output video. This setting appears after selecting a model. | COMBO | Yes | `"720p"`
`"1080p"` | | `video` | The source video to extend. | VIDEO | Yes | - | -| `prompt` | An optional text prompt to guide the content of the extended video (max 2000 characters, default: empty). | STRING | No | - | +| `prompt` | An optional text prompt for the extended video (max 2000 characters, default: empty). | STRING | No | - | | `seed` | A seed value for controlling the randomness of the generation (default: 1). | INT | No | 0 to 2147483647 | | `end_frame` | An optional image to use as the target end frame for the extension. If provided, its aspect ratio must be between 1:4 and 4:1, and its dimensions must be at least 128x128 pixels. | IMAGE | No | - | @@ -24,10 +25,10 @@ The ViduExtendVideoNode generates additional frames to extend the length of an e ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The newly generated video file containing the extended footage. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduExtendVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `067eda95bf7738fec1b68fb496b6309dab5f56c57ab4d7d92a3a5e50239c17c8` +**Source fingerprint (SHA-256):** `bfa79dd1aee8a3e56d95fe7a899454b5c5f93679e098f59fc3bf58d93d290819` diff --git a/built-in-nodes/ViduImageToVideoNode.mdx b/built-in-nodes/ViduImageToVideoNode.mdx index 2cb980005..868ba8f9b 100644 --- a/built-in-nodes/ViduImageToVideoNode.mdx +++ b/built-in-nodes/ViduImageToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ViduImageToVideoNode" icon: "circle" mode: wide --- + The Vidu Image To Video Generation node creates a short video from a starting image and an optional text description. It uses an AI model to generate video content that continues from the provided image frame, and returns the resulting video. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model name (default: viduq1) | COMBO | Yes | `viduq1` | | `image` | An image to be used as the start frame of the generated video | IMAGE | Yes | - | | `prompt` | A textual description for video generation (default: empty) | STRING | No | - | @@ -27,10 +28,10 @@ The Vidu Image To Video Generation node creates a short video from a starting im ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video output | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduImageToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `2364ee527cbc37905e973ae1870499040eea4ed94ab8ed789d3c85af857f5488` +**Source fingerprint (SHA-256):** `9e3b1ba325c44fcd03207f93030eba1a66507f9613d93135546ab7b6f37f7699` diff --git a/built-in-nodes/ViduMultiFrameVideoNode.mdx b/built-in-nodes/ViduMultiFrameVideoNode.mdx index d13723e82..efc4cee69 100644 --- a/built-in-nodes/ViduMultiFrameVideoNode.mdx +++ b/built-in-nodes/ViduMultiFrameVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ViduMultiFrameVideoNode" icon: "circle" mode: wide --- + This node generates a video by creating transitions between multiple keyframes. It starts from an initial image and animates through a sequence of user-defined end images and prompts, producing a single video file as output. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The Vidu model to use for video generation. | COMBO | Yes | `"viduq2-pro"`
`"viduq2-turbo"` | | `start_image` | The starting frame image. Aspect ratio must be between 1:4 and 4:1. | IMAGE | Yes | - | | `seed` | A seed value for random number generation to ensure reproducible results (default: 1). | INT | No | 0 to 2147483647 | @@ -18,6 +19,7 @@ This node generates a video by creating transitions between multiple keyframes. | `frames` | Number of keyframe transitions (2-9). Selecting a value dynamically reveals the required inputs for each frame. | DYNAMICCOMBO | Yes | `"2"`
`"3"`
`"4"`
`"5"`
`"6"`
`"7"`
`"8"`
`"9"` | **Frame Inputs (Dynamically Revealed):** + When you select a value for `frames` (e.g., "3"), the node will show a corresponding set of required inputs for each transition. For each frame `i` from 1 to the selected number, you must provide: * `end_image{i}` (IMAGE): The target image for this transition. Aspect ratio must be between 1:4 and 4:1. @@ -27,10 +29,10 @@ When you select a value for `frames` (e.g., "3"), the node will show a correspon ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file containing all the animated transitions. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduMultiFrameVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `06c3236589dd6067c5dd0a430e062686adb3e878542f8382e022a3fafe81507b` +**Source fingerprint (SHA-256):** `ad877532ba27444938b7b2e4634ac7f8a47db0f7fb53967d874ad38b44336dcf` diff --git a/built-in-nodes/ViduReferenceVideoNode.mdx b/built-in-nodes/ViduReferenceVideoNode.mdx index c598a4276..3982317f0 100644 --- a/built-in-nodes/ViduReferenceVideoNode.mdx +++ b/built-in-nodes/ViduReferenceVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ViduReferenceVideoNode" icon: "circle" mode: wide --- + The Vidu Reference Video Node generates videos from multiple reference images and a text prompt. It uses AI models to create consistent video content based on the provided images and description. The node supports various video settings including duration, aspect ratio, resolution, and movement control. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model name for video generation (default: "viduq1") | COMBO | Yes | `"viduq1"` | | `images` | Images to use as references to generate a video with consistent subjects (maximum 7 images) | IMAGE | Yes | - | | `prompt` | A textual description for video generation | STRING | Yes | - | @@ -31,10 +32,10 @@ The Vidu Reference Video Node generates videos from multiple reference images an ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video based on the reference images and prompt | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduReferenceVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `ac86287d93257105446a5af42efd7d7fc07738fb7fcd0b260b8049a98552f193` +**Source fingerprint (SHA-256):** `087ce07dbf0bdad9dcb1f1487dd95cf1b50d627cc8b1f8a17ff26d74016c2c3e` diff --git a/built-in-nodes/ViduStartEndToVideoNode.mdx b/built-in-nodes/ViduStartEndToVideoNode.mdx index e6787a685..e7029f691 100644 --- a/built-in-nodes/ViduStartEndToVideoNode.mdx +++ b/built-in-nodes/ViduStartEndToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ViduStartEndToVideoNode" icon: "circle" mode: wide --- + The Vidu Start End To Video Generation node creates a video by generating frames between a starting frame and an ending frame. It uses a text prompt to guide the video generation process and supports various video models with different resolution and movement settings. The node validates that the start and end frames have compatible aspect ratios before processing. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model name | COMBO | Yes | `"viduq1"` | | `first_frame` | Start frame | IMAGE | Yes | - | | `end_frame` | End frame | IMAGE | Yes | - | @@ -25,10 +26,10 @@ The Vidu Start End To Video Generation node creates a video by generating frames ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduStartEndToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `bffb4d3e90b1c6a1a3a7cc864a44ab96bac0be90411be791f9ffb15b9a50c6b6` +**Source fingerprint (SHA-256):** `5e8a566373fac84111e90d00c00a6932a23e827f9b4669950c223256c08dd96c` diff --git a/built-in-nodes/ViduTextToVideoNode.mdx b/built-in-nodes/ViduTextToVideoNode.mdx index a4bf6b124..d6942e7d9 100644 --- a/built-in-nodes/ViduTextToVideoNode.mdx +++ b/built-in-nodes/ViduTextToVideoNode.mdx @@ -5,12 +5,13 @@ sidebarTitle: "ViduTextToVideoNode" icon: "circle" mode: wide --- + The Vidu Text To Video Generation node creates videos from text descriptions. It uses the Vidu video generation model to transform your text prompts into video content with customizable settings for duration, aspect ratio, and visual style. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model name | COMBO | Yes | `viduq1` | | `prompt` | A textual description for video generation | STRING | Yes | - | | `duration` | Duration of the output video in seconds (default: 5) | INT | No | 5-5 | @@ -24,10 +25,10 @@ The Vidu Text To Video Generation node creates videos from text descriptions. It ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video based on the text prompt | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduTextToVideoNode/en.md) --- -**Source fingerprint (SHA-256):** `33ca2a60d7914e7b9ab65fbf166e1ba5388d53134cd56ef59acdcbfada5f999d` +**Source fingerprint (SHA-256):** `913efbb516c40e03ced1fef59905c7efa7737f0506368c9afcacb3b65aa4af66` diff --git a/built-in-nodes/VoxelToMesh.mdx b/built-in-nodes/VoxelToMesh.mdx index 6825aea3f..c0865d93a 100644 --- a/built-in-nodes/VoxelToMesh.mdx +++ b/built-in-nodes/VoxelToMesh.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VoxelToMesh" icon: "circle" mode: wide --- + The VoxelToMesh node converts 3D voxel data into a mesh geometry by extracting a surface at a specified threshold value. It offers two algorithms for surface extraction: a basic method that creates simple box-like faces, and a surface net method that produces smoother, more detailed meshes. The node processes each voxel grid in the input and generates vertices and faces that form a 3D mesh representation. ## Inputs diff --git a/built-in-nodes/VoxelToMeshBasic.mdx b/built-in-nodes/VoxelToMeshBasic.mdx index cfdecbdd6..8d1674e2f 100644 --- a/built-in-nodes/VoxelToMeshBasic.mdx +++ b/built-in-nodes/VoxelToMeshBasic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VoxelToMeshBasic" icon: "circle" mode: wide --- + The VoxelToMeshBasic node converts 3D voxel data into mesh geometry. It processes voxel volumes by applying a threshold value to determine which parts of the volume become solid surfaces in the resulting mesh. The node outputs a complete mesh structure with vertices and faces that can be used for 3D rendering and modeling. ## Inputs diff --git a/built-in-nodes/Wan22FunControlToVideo.mdx b/built-in-nodes/Wan22FunControlToVideo.mdx index 222b0f61f..293f0d271 100644 --- a/built-in-nodes/Wan22FunControlToVideo.mdx +++ b/built-in-nodes/Wan22FunControlToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan22FunControlToVideo" icon: "circle" mode: wide --- + The Wan22FunControlToVideo node prepares conditioning and latent representations for video generation using the Wan video model architecture. It processes positive and negative conditioning inputs along with optional reference images and control videos to create the necessary latent space representations for video synthesis. The node handles spatial scaling and temporal dimensions to generate appropriate conditioning data for video models. ## Inputs diff --git a/built-in-nodes/Wan22ImageToVideoLatent.mdx b/built-in-nodes/Wan22ImageToVideoLatent.mdx index f1ba69422..711838102 100644 --- a/built-in-nodes/Wan22ImageToVideoLatent.mdx +++ b/built-in-nodes/Wan22ImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan22ImageToVideoLatent" icon: "circle" mode: wide --- + The Wan22ImageToVideoLatent node creates video latent representations from images. It generates a blank video latent space with specified dimensions and can optionally encode a starting image sequence into the beginning frames. When a start image is provided, it encodes the image into the latent space and creates a corresponding noise mask for the inpainted regions. ## Inputs diff --git a/built-in-nodes/Wan2ImageToVideoApi.mdx b/built-in-nodes/Wan2ImageToVideoApi.mdx index 51c110136..3d5988a4c 100644 --- a/built-in-nodes/Wan2ImageToVideoApi.mdx +++ b/built-in-nodes/Wan2ImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2ImageToVideoApi" icon: "circle" mode: wide --- + The Wan 2.7 Image to Video node generates a video starting from a first-frame image. You can optionally provide a last-frame image to create a transition between the two, or provide an audio file to guide the video's motion and timing. The node uses an AI model to animate the scene based on your text description. ## Inputs @@ -34,4 +35,4 @@ The Wan 2.7 Image to Video node generates a video starting from a first-frame im > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan2ImageToVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `db5e4e26a407c71e2b79179d32cdad926db5af16461f2aa565eab544295df7ff` +**Source fingerprint (SHA-256):** `81b0dc9500ff00e1428422d3d9c8df8f790c1d9dec547dcba0d1aa239f8a8beb` diff --git a/built-in-nodes/Wan2ReferenceVideoApi.mdx b/built-in-nodes/Wan2ReferenceVideoApi.mdx index 80b8ca289..7bbc2d343 100644 --- a/built-in-nodes/Wan2ReferenceVideoApi.mdx +++ b/built-in-nodes/Wan2ReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2ReferenceVideoApi" icon: "circle" mode: wide --- + This node generates a video featuring a person or object based on provided reference materials. It uses the Wan 2.7 model to create videos from a text prompt, supporting single-character performances and multi-character interactions. You must provide at least one reference video or image for the generation to work. ## Inputs @@ -35,4 +36,4 @@ This node generates a video featuring a person or object based on provided refer > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan2ReferenceVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `83550e1193a13c3686506a279c0a8469be93be564dd27867e31b8b2724e7025d` +**Source fingerprint (SHA-256):** `52ac550522bf3fe8f57444ce8586fe83be470b893ff8c01292743553cfbd623d` diff --git a/built-in-nodes/Wan2TextToVideoApi.mdx b/built-in-nodes/Wan2TextToVideoApi.mdx index 2896cf0fb..078280c7a 100644 --- a/built-in-nodes/Wan2TextToVideoApi.mdx +++ b/built-in-nodes/Wan2TextToVideoApi.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Wan2TextToVideoApi" icon: "circle" mode: wide --- + This node generates a video from a text description using the Wan 2.7 model. It sends your request to an external API, which processes the prompt and returns a video file. You can optionally provide an audio clip to influence the video's motion and timing. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The specific model to use for video generation. | COMBO | Yes | `"wan2.7-t2v"` | | `model.prompt` | A description of the elements and visual features you want in the video. Supports English and Chinese. | STRING | Yes | - | | `model.negative_prompt` | A description of elements or features you want to avoid in the generated video. | STRING | No | - | @@ -27,10 +28,10 @@ This node generates a video from a text description using the Wan 2.7 model. It ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan2TextToVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `1eb775421209047ad06ffc210c6588c64fd39a8828a69d6fcc2b79360df311e3` +**Source fingerprint (SHA-256):** `2b35fb3e897f8c5fb9786576f4e314cb6709527a3cdc4f2eb9f0600d09076835` diff --git a/built-in-nodes/Wan2VideoContinuationApi.mdx b/built-in-nodes/Wan2VideoContinuationApi.mdx index 94711e7b9..bfb8ea62f 100644 --- a/built-in-nodes/Wan2VideoContinuationApi.mdx +++ b/built-in-nodes/Wan2VideoContinuationApi.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Wan2VideoContinuationApi" icon: "circle" mode: wide --- + The Wan 2.7 Video Continuation node generates a new video segment that continues seamlessly from the end of an input video clip. It uses the Wan 2.7 model to synthesize the continuation based on a text prompt and can optionally guide the ending towards a specific target frame. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The video generation model to use. | COMBO | Yes | `"wan2.7-i2v"` | | `model.prompt` | Prompt describing the elements and visual features. Supports English and Chinese. (default: empty string) | STRING | Yes | - | | `model.negative_prompt` | Negative prompt describing what to avoid. (default: empty string) | STRING | Yes | - | @@ -27,10 +28,10 @@ The Wan 2.7 Video Continuation node generates a new video segment that continues ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video continuation. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan2VideoContinuationApi/en.md) --- -**Source fingerprint (SHA-256):** `44f71824f1289351fe44ff0f830ee391d2387146444f50ba50309ecba2e54456` +**Source fingerprint (SHA-256):** `591e551676969bc1fedb5f820f6866512c132bb98ee8ef1766d1e0b389e2dc11` diff --git a/built-in-nodes/Wan2VideoEditApi.mdx b/built-in-nodes/Wan2VideoEditApi.mdx index 02a04fc95..28a21f132 100644 --- a/built-in-nodes/Wan2VideoEditApi.mdx +++ b/built-in-nodes/Wan2VideoEditApi.mdx @@ -5,12 +5,13 @@ sidebarTitle: "Wan2VideoEditApi" icon: "circle" mode: wide --- + The Wan2VideoEditApi node uses the Wan 2.7 model to edit a video based on text instructions, reference images, or style transfer. It processes the input video and generates a new video according to the specified parameters like resolution, duration, and aspect ratio. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The model to use for video editing. | COMBO | Yes | `"wan2.7-videoedit"` | | `model.prompt` | Editing instructions or style transfer requirements. (default: empty string) | STRING | Yes | - | | `model.resolution` | The resolution for the output video. | COMBO | Yes | `"720P"`
`"1080P"` | @@ -30,10 +31,10 @@ The Wan2VideoEditApi node uses the Wan 2.7 model to edit a video based on text i ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The edited video generated by the model. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan2VideoEditApi/en.md) --- -**Source fingerprint (SHA-256):** `1ea6cacbf8f5b6666e164c4806d931d21ddd44568e5c9f6d44f389288f5ce84f` +**Source fingerprint (SHA-256):** `27283273ee56c90903db103a3e9bc17dc4df0914676c9aedd2a115b07937dc10` diff --git a/built-in-nodes/WanAnimateToVideo.mdx b/built-in-nodes/WanAnimateToVideo.mdx index 793ed0b0a..69ef70eec 100644 --- a/built-in-nodes/WanAnimateToVideo.mdx +++ b/built-in-nodes/WanAnimateToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanAnimateToVideo" icon: "circle" mode: wide --- + The WanAnimateToVideo node generates video content by combining multiple conditioning inputs including pose references, facial expressions, and background elements. It processes various video inputs to create coherent animated sequences while maintaining temporal consistency across frames. The node handles latent space operations and can extend existing videos by continuing motion patterns. ## Inputs diff --git a/built-in-nodes/WanCameraEmbedding.mdx b/built-in-nodes/WanCameraEmbedding.mdx index c168b173f..ca38f521c 100644 --- a/built-in-nodes/WanCameraEmbedding.mdx +++ b/built-in-nodes/WanCameraEmbedding.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanCameraEmbedding" icon: "circle" mode: wide --- + The WanCameraEmbedding node generates camera trajectory embeddings using Plücker embeddings based on camera motion parameters. It creates a sequence of camera poses that simulate different camera movements and converts them into embedding tensors suitable for video generation pipelines. ## Inputs diff --git a/built-in-nodes/WanCameraImageToVideo.mdx b/built-in-nodes/WanCameraImageToVideo.mdx index f0333a78f..355170584 100644 --- a/built-in-nodes/WanCameraImageToVideo.mdx +++ b/built-in-nodes/WanCameraImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanCameraImageToVideo" icon: "circle" mode: wide --- + The WanCameraImageToVideo node prepares conditioning and latent data for video generation from images. It takes positive and negative conditioning prompts, along with optional starting images and camera controls, and outputs modified conditioning and an empty latent tensor ready for a video model to fill in. ## Inputs diff --git a/built-in-nodes/WanContextWindowsManual.mdx b/built-in-nodes/WanContextWindowsManual.mdx index 6dd83290f..db5f56d0f 100644 --- a/built-in-nodes/WanContextWindowsManual.mdx +++ b/built-in-nodes/WanContextWindowsManual.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanContextWindowsManual" icon: "circle" mode: wide --- + The WAN Context Windows (Manual) node allows you to manually configure context windows for WAN-like models with 2-dimensional processing. It applies custom context window settings during sampling by specifying the window length, overlap, scheduling method, and fusion technique. This gives you precise control over how the model processes information across different context regions. ## Inputs diff --git a/built-in-nodes/WanDancerEncodeAudio.mdx b/built-in-nodes/WanDancerEncodeAudio.mdx index 40f77378e..4ef4c64af 100644 --- a/built-in-nodes/WanDancerEncodeAudio.mdx +++ b/built-in-nodes/WanDancerEncodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerEncodeAudio" icon: "circle" mode: wide --- + ## Overview This node processes an audio input to extract features that can be used to guide a video generation model. It analyzes the audio to detect tempo, beats, and other musical characteristics, then packages this information into a format suitable for conditioning a video model, allowing the generated video to be synchronized with the audio. diff --git a/built-in-nodes/WanDancerPadKeyframes.mdx b/built-in-nodes/WanDancerPadKeyframes.mdx index cd09b29c1..2f3a4e247 100644 --- a/built-in-nodes/WanDancerPadKeyframes.mdx +++ b/built-in-nodes/WanDancerPadKeyframes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerPadKeyframes" icon: "circle" mode: wide --- + ## Overview This node prepares a sequence of keyframes for a specific segment of a longer video generation process. It takes a batch of input images and an audio track, calculates how many total frames the full video should have based on the audio duration, and then distributes the input images as keyframes across the chosen segment, padding the rest with blank frames. It also extracts the corresponding portion of the audio for that segment. diff --git a/built-in-nodes/WanDancerPadKeyframesList.mdx b/built-in-nodes/WanDancerPadKeyframesList.mdx index 851fcf60c..5f89d0c1a 100644 --- a/built-in-nodes/WanDancerPadKeyframesList.mdx +++ b/built-in-nodes/WanDancerPadKeyframesList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerPadKeyframesList" icon: "circle" mode: wide --- + ## Overview This node takes a sequence of images and an optional audio track, and splits them into a specified number of padded segments. It is designed to prepare keyframe sequences for video generation, where each segment is padded to a consistent length and a corresponding mask is created to indicate which frames are valid. diff --git a/built-in-nodes/WanDancerVideo.mdx b/built-in-nodes/WanDancerVideo.mdx index 54e00a8f0..b3c6f8f8d 100644 --- a/built-in-nodes/WanDancerVideo.mdx +++ b/built-in-nodes/WanDancerVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerVideo" icon: "circle" mode: wide --- + The WanDancerVideo node prepares conditioning data and an empty latent tensor for video generation with the WanDancer model. It combines positive and negative conditioning with optional inputs like a starting image, mask, CLIP vision embeddings, and audio features to control the generated video. ## Inputs diff --git a/built-in-nodes/WanFirstLastFrameToVideo.mdx b/built-in-nodes/WanFirstLastFrameToVideo.mdx index 9272fd0b0..389c5503f 100644 --- a/built-in-nodes/WanFirstLastFrameToVideo.mdx +++ b/built-in-nodes/WanFirstLastFrameToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFirstLastFrameToVideo" icon: "circle" mode: wide --- + The WanFirstLastFrameToVideo node creates video conditioning by combining start and end frames with text prompts. It generates a latent representation for video generation by encoding the first and last frames, applying masks to guide the generation process, and incorporating CLIP vision features when available. This node prepares both positive and negative conditioning for video models to generate coherent sequences between specified start and end points. ## Inputs diff --git a/built-in-nodes/WanFunControlToVideo.mdx b/built-in-nodes/WanFunControlToVideo.mdx index 6dc17b6a8..1a9a660a2 100644 --- a/built-in-nodes/WanFunControlToVideo.mdx +++ b/built-in-nodes/WanFunControlToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFunControlToVideo" icon: "circle" mode: wide --- + This node was added to support the Alibaba Wan Fun Control model for video generation, and was added after [this commit](https://github.com/comfyanonymous/ComfyUI/commit/3661c833bcc41b788a7c9f0e7bc48524f8ee5f82). - **Purpose:** Prepare the conditioning information needed for video generation, using the Wan 2.1 Fun Control model. diff --git a/built-in-nodes/WanFunInpaintToVideo.mdx b/built-in-nodes/WanFunInpaintToVideo.mdx index 8b5ba8aff..e38113075 100644 --- a/built-in-nodes/WanFunInpaintToVideo.mdx +++ b/built-in-nodes/WanFunInpaintToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFunInpaintToVideo" icon: "circle" mode: wide --- + The WanFunInpaintToVideo node creates video sequences by inpainting between start and end images. It takes positive and negative conditioning along with optional frame images to generate video latents. The node handles video generation with configurable dimensions and length parameters. ## Inputs diff --git a/built-in-nodes/WanHuMoImageToVideo.mdx b/built-in-nodes/WanHuMoImageToVideo.mdx index 38596ab43..b775ef51c 100644 --- a/built-in-nodes/WanHuMoImageToVideo.mdx +++ b/built-in-nodes/WanHuMoImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanHuMoImageToVideo" icon: "circle" mode: wide --- + The WanHuMoImageToVideo node converts images to video sequences by generating latent representations for video frames. It processes conditioning inputs and can incorporate reference images and audio embeddings to influence the video generation. The node outputs modified conditioning data and latent representations suitable for video synthesis. ## Inputs diff --git a/built-in-nodes/WanImageToImageApi.mdx b/built-in-nodes/WanImageToImageApi.mdx index de1dcb88a..2fa9a7b18 100644 --- a/built-in-nodes/WanImageToImageApi.mdx +++ b/built-in-nodes/WanImageToImageApi.mdx @@ -5,14 +5,15 @@ sidebarTitle: "WanImageToImageApi" icon: "circle" mode: wide --- + The Wan Image to Image node generates an image from one or two input images and a text prompt. It transforms your input images based on the description you provide, creating a new image that maintains the aspect ratio of your original input. The output image is fixed at 1.6 megapixels regardless of the input size. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model to use (default: "wan2.5-i2i-preview"). | COMBO | Yes | "wan2.5-i2i-preview" | -| `image` | Single-image editing or multi-image fusion, maximum 2 images. | IMAGE | Yes | - | +| `image` | Single-image editing or multi-image fusion. Maximum 2 images. | IMAGE | Yes | - | | `prompt` | Prompt describing the elements and visual features. Supports English and Chinese (default: empty). | STRING | Yes | - | | `negative_prompt` | Negative prompt describing what to avoid (default: empty). | STRING | No | - | | `seed` | Seed to use for generation (default: 0). | INT | No | 0 to 2147483647 | @@ -23,10 +24,10 @@ The Wan Image to Image node generates an image from one or two input images and ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The generated image based on the input images and text prompts. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToImageApi/en.md) --- -**Source fingerprint (SHA-256):** `c9afd38e3df8c080f489c4b569ea647eab5718fa78d95c65e294706344bb8067` +**Source fingerprint (SHA-256):** `e78e5fb43d92c839448d3449b89445fb5db081ee8c947e44edcc048b8740f45d` diff --git a/built-in-nodes/WanImageToVideo.mdx b/built-in-nodes/WanImageToVideo.mdx index 45c76b5b1..e44aea110 100644 --- a/built-in-nodes/WanImageToVideo.mdx +++ b/built-in-nodes/WanImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToVideo" icon: "circle" mode: wide --- + The WanImageToVideo node prepares conditioning and latent representations for video generation tasks. It creates an empty latent space for video generation and can optionally incorporate starting images and CLIP vision outputs to guide the video generation process. The node modifies both positive and negative conditioning inputs based on the provided image and vision data. ## Inputs diff --git a/built-in-nodes/WanImageToVideoApi.mdx b/built-in-nodes/WanImageToVideoApi.mdx index 02314d812..c4969fac2 100644 --- a/built-in-nodes/WanImageToVideoApi.mdx +++ b/built-in-nodes/WanImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToVideoApi" icon: "circle" mode: wide --- + The Wan Image to Video node generates a video from a single input image and a text prompt. It uses the provided image as the first frame and creates a video sequence based on the description, with options for resolution, duration, audio, and other advanced settings. ## Inputs @@ -40,4 +41,4 @@ The Wan Image to Video node generates a video from a single input image and a te > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `b8a75e324f7436e8a376e4a058b0a32556cafbe8e7975148cbc6302638f52058` +**Source fingerprint (SHA-256):** `dabcbfa3118669d9ff5b40b79ef643ffcf7ac5e510e61d6ad859d80360061673` diff --git a/built-in-nodes/WanInfiniteTalkToVideo.mdx b/built-in-nodes/WanInfiniteTalkToVideo.mdx index f20f67460..d054157fc 100644 --- a/built-in-nodes/WanInfiniteTalkToVideo.mdx +++ b/built-in-nodes/WanInfiniteTalkToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanInfiniteTalkToVideo" icon: "circle" mode: wide --- + The WanInfiniteTalkToVideo node generates video sequences from audio input. It uses a video diffusion model, conditioned on audio features extracted from one or two speakers, to produce a latent representation of a talking head video. The node can generate a new sequence or extend an existing one using previous frames for motion context. ## Inputs diff --git a/built-in-nodes/WanMoveConcatTrack.mdx b/built-in-nodes/WanMoveConcatTrack.mdx index 840db9112..ce48e886f 100644 --- a/built-in-nodes/WanMoveConcatTrack.mdx +++ b/built-in-nodes/WanMoveConcatTrack.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveConcatTrack" icon: "circle" mode: wide --- + The WanMoveConcatTrack node combines two sets of motion tracking data into a single, longer sequence. It works by joining the track paths and visibility masks from the input tracks along their respective dimensions. If only one track input is provided, it simply passes that data through unchanged. ## Inputs diff --git a/built-in-nodes/WanMoveTrackToVideo.mdx b/built-in-nodes/WanMoveTrackToVideo.mdx index 22ea5b8f4..e96ce9fe5 100644 --- a/built-in-nodes/WanMoveTrackToVideo.mdx +++ b/built-in-nodes/WanMoveTrackToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveTrackToVideo" icon: "circle" mode: wide --- + The WanMoveTrackToVideo node prepares conditioning and latent space data for video generation, incorporating optional motion tracking information. It encodes a starting image sequence into a latent representation and can blend in positional data from object tracks to guide the motion in the generated video. The node outputs modified positive and negative conditioning along with an empty latent tensor ready for a video model. ## Inputs diff --git a/built-in-nodes/WanMoveTracksFromCoords.mdx b/built-in-nodes/WanMoveTracksFromCoords.mdx index 5e6d3c792..7c29e6312 100644 --- a/built-in-nodes/WanMoveTracksFromCoords.mdx +++ b/built-in-nodes/WanMoveTracksFromCoords.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveTracksFromCoords" icon: "circle" mode: wide --- + The WanMoveTracksFromCoords node creates motion tracks from a JSON-formatted string of coordinates. It converts the coordinate data into a tensor format that can be used by other video processing nodes, and can optionally apply a mask to control the visibility of tracks over time. ## Inputs diff --git a/built-in-nodes/WanMoveVisualizeTracks.mdx b/built-in-nodes/WanMoveVisualizeTracks.mdx index 8e0ea8d04..08bcf9d21 100644 --- a/built-in-nodes/WanMoveVisualizeTracks.mdx +++ b/built-in-nodes/WanMoveVisualizeTracks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveVisualizeTracks" icon: "circle" mode: wide --- + The WanMoveVisualizeTracks node overlays motion tracking data onto a sequence of images or video frames. It draws visual representations of tracked points, including their movement paths and current positions, making the motion data visible and easier to analyze. ## Inputs diff --git a/built-in-nodes/WanPhantomSubjectToVideo.mdx b/built-in-nodes/WanPhantomSubjectToVideo.mdx index e31bd645d..b11d40021 100644 --- a/built-in-nodes/WanPhantomSubjectToVideo.mdx +++ b/built-in-nodes/WanPhantomSubjectToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanPhantomSubjectToVideo" icon: "circle" mode: wide --- + The WanPhantomSubjectToVideo node generates video content by processing conditioning inputs and optional reference images. It creates latent representations for video generation and can incorporate visual guidance from input images when provided. The node prepares conditioning data with time-dimensional concatenation for video models and outputs modified conditioning along with generated latent video data. ## Inputs diff --git a/built-in-nodes/WanReferenceVideoApi.mdx b/built-in-nodes/WanReferenceVideoApi.mdx index 77b2f192d..544684071 100644 --- a/built-in-nodes/WanReferenceVideoApi.mdx +++ b/built-in-nodes/WanReferenceVideoApi.mdx @@ -5,18 +5,19 @@ sidebarTitle: "WanReferenceVideoApi" icon: "circle" mode: wide --- + The Wan Reference to Video node uses the visual appearance and voice from one or more input reference videos, along with a text prompt, to generate a new video. It maintains consistency with the characters from the reference material while creating new content based on your description. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The specific AI model to use for video generation. | COMBO | Yes | `"wan2.6-r2v"` | | `prompt` | A description of the elements and visual features for the new video. Supports English and Chinese. Use identifiers like `character1` and `character2` to refer to the characters from the reference videos. | STRING | Yes | - | | `negative_prompt` | A description of elements or features to avoid in the generated video. | STRING | No | - | | `reference_videos` | A list of video inputs used as references for character appearance and voice. You must provide at least one video. Each video can be assigned a name like `character1`, `character2`, or `character3`. | AUTOGROW | Yes | - | | `size` | The resolution and aspect ratio for the output video. | COMBO | Yes | `"720p: 1:1 (960x960)"`
`"720p: 16:9 (1280x720)"`
`"720p: 9:16 (720x1280)"`
`"720p: 4:3 (1088x832)"`
`"720p: 3:4 (832x1088)"`
`"1080p: 1:1 (1440x1440)"`
`"1080p: 16:9 (1920x1080)"`
`"1080p: 9:16 (1080x1920)"`
`"1080p: 4:3 (1632x1248)"`
`"1080p: 3:4 (1248x1632)"` | -| `duration` | The length of the generated video in seconds. The value must be a multiple of 5 (default: 5). | INT | Yes | 5 to 10 | +| `duration` | The length of the generated video in seconds (default: 5). | INT | Yes | 5 to 10 | | `seed` | A random seed value for reproducible results. A value of 0 will generate a random seed. | INT | No | 0 to 2147483647 | | `shot_type` | Specifies whether the generated video is a single continuous shot or contains multiple shots with cuts. | COMBO | Yes | `"single"`
`"multi"` | | `watermark` | When enabled, an AI-generated watermark is added to the final video (default: False). | BOOLEAN | No | - | @@ -24,15 +25,15 @@ The Wan Reference to Video node uses the visual appearance and voice from one or **Constraints:** * Each video provided in `reference_videos` must be between 2 and 30 seconds in duration. -* The `duration` parameter is limited to specific values (5 or 10 seconds). +* The `duration` parameter is limited to values of 5 or 10 seconds. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The newly generated video file. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanReferenceVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `948976c64337299217616d60200ffed7e24cce32655960c525bb068c38cc6406` +**Source fingerprint (SHA-256):** `65ca81a7b5e83f8d8f4c00db41e24d5238ef438887362838351464e77a3af0c2` diff --git a/built-in-nodes/WanSCAILToVideo.mdx b/built-in-nodes/WanSCAILToVideo.mdx index 3a4131682..fc0869219 100644 --- a/built-in-nodes/WanSCAILToVideo.mdx +++ b/built-in-nodes/WanSCAILToVideo.mdx @@ -5,37 +5,45 @@ sidebarTitle: "WanSCAILToVideo" icon: "circle" mode: wide --- -The WanSCAILToVideo node prepares conditioning and an empty latent space for video generation. It processes optional inputs like reference images, pose videos, and CLIP vision outputs, embedding them into the positive and negative conditioning for a video model. The node outputs the modified conditioning and a blank latent tensor of the specified video dimensions. + +The WanSCAILToVideo node prepares conditioning and an empty latent space for video generation. It processes optional inputs like reference images, pose videos, CLIP vision outputs, and previous frame chunks, embedding them into the positive and negative conditioning for a video model. The node outputs the modified conditioning and a blank latent tensor of the specified video dimensions. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `positive` | The positive conditioning input. | CONDITIONING | Yes | - | | `negative` | The negative conditioning input. | CONDITIONING | Yes | - | | `vae` | The VAE model used for encoding images and video frames. | VAE | Yes | - | -| `width` | The width of the output video in pixels (default: 512). Must be divisible by 8. | INT | Yes | 32 to MAX_RESOLUTION | -| `height` | The height of the output video in pixels (default: 896). Must be divisible by 8. | INT | Yes | 32 to MAX_RESOLUTION | +| `width` | The width of the output video in pixels (default: 512). Must be divisible by 32. | INT | Yes | 32 to MAX_RESOLUTION | +| `height` | The height of the output video in pixels (default: 896). Must be divisible by 32. | INT | Yes | 32 to MAX_RESOLUTION | | `length` | The number of frames in the video (default: 81). Must be divisible by 4. | INT | Yes | 1 to MAX_RESOLUTION | | `batch_size` | The number of videos to generate in a batch (default: 1). | INT | Yes | 1 to 4096 | -| `clip_vision_output` | Optional CLIP vision output for conditioning. | CLIP_VISION_OUTPUT | No | - | -| `reference_image` | An optional reference image for conditioning. | IMAGE | No | - | | `pose_video` | Video used for pose conditioning. Will be downscaled to half the resolution of the main video. | IMAGE | No | - | +| `pose_video_mask` | SCAIL-2 only. Colored per-identity SAM3 mask video at the same resolution as pose_video. | IMAGE | No | - | +| `replacement_mode` | SCAIL-2 only. False = Animation Mode (pose_video_mask should have black background). True = Replacement Mode (pose_video_mask should have white background). Default: False. | BOOLEAN | No | - | | `pose_strength` | Strength of the pose latent (default: 1.0). | FLOAT | Yes | 0.0 to 10.0 | -| `pose_start` | Start step to use pose conditioning (default: 0.0). | FLOAT | Yes | 0.0 to 1.0 | -| `pose_end` | End step to use pose conditioning (default: 1.0). | FLOAT | Yes | 0.0 to 1.0 | +| `pose_start` | Start step of the pose conditioning (default: 0.0). | FLOAT | Yes | 0.0 to 1.0 | +| `pose_end` | End step of the pose conditioning (default: 1.0). | FLOAT | Yes | 0.0 to 1.0 | +| `reference_image` | Reference image, for multiple references composite all on single image. | IMAGE | No | - | +| `reference_image_mask` | SCAIL-2 only. Colored reference mask at the same resolution as reference_image. | IMAGE | No | - | +| `clip_vision_output` | CLIP vision features for conditioning. Model is trained with stretch resize to aspect ratio. | CLIP_VISION_OUTPUT | No | - | +| `video_frame_offset` | Cumulative output frame this chunk begins at. Wire from the previous chunk's video_frame_offset output (default: 0). | INT | Yes | 0 to MAX_RESOLUTION | +| `previous_frame_count` | Tail frames of previous_frames to anchor. SCAIL-2 trained at 5 (81-frame chunks, 76-frame step) (default: 5). | INT | Yes | 1 to MAX_RESOLUTION | +| `previous_frames` | SCAIL-2 only. Full decoded output of the previous chunk. Only the last previous_frame_count are used as the extension anchor. | IMAGE | No | - | -**Note:** The `pose_video` input is processed only for the first `length` frames. The `reference_image` is processed only for the first image in the batch. When `reference_image` is provided, a zero-filled latent of the same size is used for the negative conditioning. When `clip_vision_output` is provided, it is applied to both positive and negative conditioning. The `pose_video` is downscaled to half the resolution of the main video before encoding. +**Note:** The `pose_video` and `pose_video_mask` inputs are processed only for the first `length` frames. The `reference_image` is processed only for the first image in the batch. When `reference_image` is provided, it is encoded into a latent and embedded into both positive and negative conditioning. When `clip_vision_output` is provided, it is applied to both positive and negative conditioning. The `pose_video` is downscaled to half the resolution of the main video before encoding. When `previous_frames` is provided, only the last `previous_frame_count` frames are used as the extension anchor, and the `video_frame_offset` is adjusted accordingly. In Replacement Mode (`replacement_mode=True`), the reference image is composited on a black background using the reference image mask as an alpha matte. ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | -| `positive` | The modified positive conditioning, potentially containing embedded reference image latents, CLIP vision output, or pose video latents. | CONDITIONING | -| `negative` | The modified negative conditioning, potentially containing embedded reference image latents, CLIP vision output, or pose video latents. | CONDITIONING | -| `latent` | An empty latent tensor of shape `[batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8]`. | LATENT | +|-------------|-------------|-----------| +| `positive` | The modified positive conditioning, potentially containing embedded reference image latents, CLIP vision output, pose video latents, driving masks, reference masks, or previous frame latents. | CONDITIONING | +| `negative` | The modified negative conditioning, potentially containing embedded reference image latents, CLIP vision output, pose video latents, driving masks, reference masks, or previous frame latents. | CONDITIONING | +| `latent` | An empty latent tensor of shape `[batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8]`. When previous_frames is provided, the latent is partially filled with encoded previous frames and a noise mask is included. | LATENT | +| `video_frame_offset` | Adjusted offset + length. Wire into the next chunk for sequential video generation. | INT | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSCAILToVideo/en.md) --- -**Source fingerprint (SHA-256):** `01c0912474602c33fa0c3e277db90e0eb83edbcea307a860921bab486d267cc8` +**Source fingerprint (SHA-256):** `30e14959248c46e624e2ce2e3d079cd5aad94c12b66d74d4979ef70143b871e3` diff --git a/built-in-nodes/WanSoundImageToVideo.mdx b/built-in-nodes/WanSoundImageToVideo.mdx index 028f093c6..501e85f65 100644 --- a/built-in-nodes/WanSoundImageToVideo.mdx +++ b/built-in-nodes/WanSoundImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSoundImageToVideo" icon: "circle" mode: wide --- + The WanSoundImageToVideo node generates video content from images with optional audio conditioning. It takes positive and negative conditioning prompts along with a VAE model to create video latents, and can incorporate reference images, audio encoding, control videos, and motion references to guide the video generation process. ## Inputs diff --git a/built-in-nodes/WanSoundImageToVideoExtend.mdx b/built-in-nodes/WanSoundImageToVideoExtend.mdx index bf7e27829..0e1130dd5 100644 --- a/built-in-nodes/WanSoundImageToVideoExtend.mdx +++ b/built-in-nodes/WanSoundImageToVideoExtend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSoundImageToVideoExtend" icon: "circle" mode: wide --- + The WanSoundImageToVideoExtend node extends an existing video latent by generating additional frames, optionally guided by audio, a reference image, and a control video. It takes a starting video latent and produces a longer video sequence, using the provided conditioning and audio cues to influence the new content. ## Inputs diff --git a/built-in-nodes/WanTextToImageApi.mdx b/built-in-nodes/WanTextToImageApi.mdx index 47c6fab65..eb0524cfc 100644 --- a/built-in-nodes/WanTextToImageApi.mdx +++ b/built-in-nodes/WanTextToImageApi.mdx @@ -5,12 +5,13 @@ sidebarTitle: "WanTextToImageApi" icon: "circle" mode: wide --- + The Wan Text to Image node generates images based on text descriptions. It uses AI models to create visual content from written prompts, supporting both English and Chinese text input. The node provides various controls to adjust the output image size, quality, and style preferences. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model to use (default: "wan2.5-t2i-preview") | STRING | Yes | "wan2.5-t2i-preview" | | `prompt` | Prompt describing the elements and visual features. Supports English and Chinese (default: empty) | STRING | Yes | - | | `negative_prompt` | Negative prompt describing what to avoid (default: empty) | STRING | No | - | @@ -23,10 +24,10 @@ The Wan Text to Image node generates images based on text descriptions. It uses ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated image based on the text prompt | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTextToImageApi/en.md) --- -**Source fingerprint (SHA-256):** `4ab8fe7b1e6a0b781b006e03719203b65ed58aec75aaee780d479170ed6425ea` +**Source fingerprint (SHA-256):** `208b7c839da45316aeb1a14a3e9d176eeb09b2f931f764fb8a296da15ae3bd4e` diff --git a/built-in-nodes/WanTextToVideoApi.mdx b/built-in-nodes/WanTextToVideoApi.mdx index b935fe4e0..450b5e947 100644 --- a/built-in-nodes/WanTextToVideoApi.mdx +++ b/built-in-nodes/WanTextToVideoApi.mdx @@ -5,12 +5,13 @@ sidebarTitle: "WanTextToVideoApi" icon: "circle" mode: wide --- + The Wan Text to Video node generates video content based on text descriptions. It uses AI models to create videos from prompts and supports various video sizes, durations, and optional audio inputs. The node can automatically generate audio when needed and provides options for prompt enhancement and watermarking. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | Model to use (default: "wan2.6-t2v") | COMBO | Yes | "wan2.5-t2v-preview"
"wan2.6-t2v" | | `prompt` | Prompt describing the elements and visual features. Supports English and Chinese (default: "") | STRING | Yes | - | | `negative_prompt` | Negative prompt describing what to avoid (default: "") | STRING | No | - | @@ -28,10 +29,10 @@ The Wan Text to Video node generates video content based on text descriptions. I ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The generated video based on the input parameters | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTextToVideoApi/en.md) --- -**Source fingerprint (SHA-256):** `4fbdb2e06ff15849684de860ca3fdf4eb43e6af1803483b4baa7229e584f6e25` +**Source fingerprint (SHA-256):** `105ff4b575dc6cd319448b0f4c0e9cfab360df025480190ae6bccc324d351525` diff --git a/built-in-nodes/WanTrackToVideo.mdx b/built-in-nodes/WanTrackToVideo.mdx index 6ef3b186e..eb09cb964 100644 --- a/built-in-nodes/WanTrackToVideo.mdx +++ b/built-in-nodes/WanTrackToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTrackToVideo" icon: "circle" mode: wide --- + The WanTrackToVideo node converts motion tracking data into video sequences by processing track points and generating corresponding video frames. It takes tracking coordinates as input and produces video conditioning and latent representations that can be used for video generation. When no tracks are provided, it falls back to standard image-to-video conversion. ## Inputs diff --git a/built-in-nodes/WanVaceToVideo.mdx b/built-in-nodes/WanVaceToVideo.mdx index 9dac968a3..492552c00 100644 --- a/built-in-nodes/WanVaceToVideo.mdx +++ b/built-in-nodes/WanVaceToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanVaceToVideo" icon: "circle" mode: wide --- + The WanVaceToVideo node processes video conditioning data for video generation models. It takes positive and negative conditioning inputs along with video control data and prepares latent representations for video generation. The node handles video upscaling, masking, and VAE encoding to create the appropriate conditioning structure for video models. ## Inputs diff --git a/built-in-nodes/WavespeedFlashVSRNode.mdx b/built-in-nodes/WavespeedFlashVSRNode.mdx index b2fd25c47..b95d63ee8 100644 --- a/built-in-nodes/WavespeedFlashVSRNode.mdx +++ b/built-in-nodes/WavespeedFlashVSRNode.mdx @@ -5,27 +5,28 @@ sidebarTitle: "WavespeedFlashVSRNode" icon: "circle" mode: wide --- -The WavespeedFlashVSRNode is a fast, high-quality video upscaler that boosts the resolution and restores clarity for low-resolution or blurry footage. It processes a video input and outputs a new video at a user-selected higher resolution. + +The WavespeedFlashVSRNode is a fast, high-quality video upscaler that boosts resolution and restores clarity for low-resolution or blurry footage. It processes a video input and outputs a new video at a user-selected higher resolution. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `video` | The input video file to be upscaled. Must be in MP4 container format with a duration between 5 seconds and 10 minutes. | VIDEO | Yes | N/A | | `target_resolution` | The desired resolution for the upscaled output video. | STRING | Yes | `"720p"`
`"1080p"`
`"2K"`
`"4K"` | **Input Constraints:** -* The input `video` file must be in the MP4 container format. -* The duration of the input `video` must be between 5 seconds and 10 minutes (600 seconds). +- The input `video` file must be in the MP4 container format. +- The duration of the input `video` must be between 5 seconds and 10 minutes (600 seconds). ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `output` | The upscaled video file at the selected target resolution. | VIDEO | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WavespeedFlashVSRNode/en.md) --- -**Source fingerprint (SHA-256):** `61381d911521ccb8848ef3512749d5cb9e047cd0c1c2bdfc000c5d3ef3360918` +**Source fingerprint (SHA-256):** `d7885eeb2dacfc2bc398d1bc991620be479f45d8edbdca7eb046a21500581529` diff --git a/built-in-nodes/WavespeedImageUpscaleNode.mdx b/built-in-nodes/WavespeedImageUpscaleNode.mdx index 3698a3b05..db1887f68 100644 --- a/built-in-nodes/WavespeedImageUpscaleNode.mdx +++ b/built-in-nodes/WavespeedImageUpscaleNode.mdx @@ -5,14 +5,15 @@ sidebarTitle: "WavespeedImageUpscaleNode" icon: "circle" mode: wide --- + The WaveSpeed Image Upscale node uses an external AI service to increase the resolution and quality of an image. It takes a single input photo and upscales it to a higher target resolution, such as 2K, 4K, or 8K, producing a sharper and more detailed result. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | +|-----------|-------------|-----------|----------|-------| | `model` | The AI model to use for upscaling. "SeedVR2" and "Ultimate" offer different quality and pricing tiers. | STRING | Yes | `"SeedVR2"`
`"Ultimate"` | -| `image` | The input image to be upscaled. Exactly one image is required. | IMAGE | Yes | | +| `image` | The input image to be upscaled. Exactly one image is required. | IMAGE | Yes | | | `target_resolution` | The desired output resolution for the upscaled image. | STRING | Yes | `"2K"`
`"4K"`
`"8K"` | **Note:** This node requires exactly one input image. Providing a batch of images will result in an error. @@ -20,10 +21,10 @@ The WaveSpeed Image Upscale node uses an external AI service to increase the res ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `image` | The upscaled, high-resolution output image. | IMAGE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WavespeedImageUpscaleNode/en.md) --- -**Source fingerprint (SHA-256):** `9ed5a897cf067a9dbf8bee95f44cfc02c98349b1520e0f42d5f52c120d248014` +**Source fingerprint (SHA-256):** `1d715431efb690d30d9fc3b4769047a9d568b49c62eb318615e2748c780b8c20` diff --git a/built-in-nodes/WebcamCapture.mdx b/built-in-nodes/WebcamCapture.mdx index b9135f08f..bd57bf4d2 100644 --- a/built-in-nodes/WebcamCapture.mdx +++ b/built-in-nodes/WebcamCapture.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WebcamCapture" icon: "circle" mode: wide --- + The WebcamCapture node captures images from a webcam device and converts them into a format that can be used within ComfyUI workflows. It inherits from the LoadImage node and provides options to control the capture dimensions and timing. When enabled, the node can capture new images each time the workflow queue is processed. ## Inputs diff --git a/built-in-nodes/ZImageFunControlnet.mdx b/built-in-nodes/ZImageFunControlnet.mdx index 4f7bb88c9..21d887c10 100644 --- a/built-in-nodes/ZImageFunControlnet.mdx +++ b/built-in-nodes/ZImageFunControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ZImageFunControlnet" icon: "circle" mode: wide --- + The ZImageFunControlnet node applies a specialized control network to influence the image generation or editing process. It uses a base model, a model patch, and a VAE, allowing you to adjust the strength of the control effect. This node can work with a base image, an inpainting image, and a mask for more targeted edits. ## Inputs diff --git a/built-in-nodes/unCLIPCheckpointLoader.mdx b/built-in-nodes/unCLIPCheckpointLoader.mdx index 5f4707dd4..f70291780 100644 --- a/built-in-nodes/unCLIPCheckpointLoader.mdx +++ b/built-in-nodes/unCLIPCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "unCLIPCheckpointLoader" icon: "circle" mode: wide --- + This node will detect models located in the `ComfyUI/models/checkpoints` folder, and it will also read models from additional paths configured in the extra_model_paths.yaml file. Sometimes, you may need to **refresh the ComfyUI interface** to allow it to read the model files from the corresponding folder. The unCLIPCheckpointLoader node is designed for loading checkpoints specifically tailored for unCLIP models. It facilitates the retrieval and initialization of models, CLIP vision modules, and VAEs from a specified checkpoint, streamlining the setup process for further operations or analyses. diff --git a/built-in-nodes/unCLIPConditioning.mdx b/built-in-nodes/unCLIPConditioning.mdx index c93cae93a..dae2db94d 100644 --- a/built-in-nodes/unCLIPConditioning.mdx +++ b/built-in-nodes/unCLIPConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "unCLIPConditioning" icon: "circle" mode: wide --- + This node is designed to integrate CLIP vision outputs into the conditioning process, adjusting the influence of these outputs based on specified strength and noise augmentation parameters. It enriches the conditioning with visual context, enhancing the generation process. ## Inputs diff --git a/built-in-nodes/wanBlockSwap.mdx b/built-in-nodes/wanBlockSwap.mdx index f3301d6f8..7a2aa2e07 100644 --- a/built-in-nodes/wanBlockSwap.mdx +++ b/built-in-nodes/wanBlockSwap.mdx @@ -5,6 +5,7 @@ sidebarTitle: "wanBlockSwap" icon: "circle" mode: wide --- + This node is deprecated and serves no function. It accepts a model as input and returns the same model unchanged. The description "NOP" indicates it performs no operation. ## Inputs diff --git a/docs.json b/docs.json index bd95e8feb..119103574 100644 --- a/docs.json +++ b/docs.json @@ -575,12 +575,6 @@ "pages": [ "tutorials/partner-nodes/topaz/astra-2" ] - }, - { - "group": "Grok", - "pages": [ - "tutorials/partner-nodes/grok/grok-imagine-video-1-5" - ] } ] }, @@ -597,20 +591,6 @@ { "group": "3D", "pages": [ - { - "group": "Conditioning", - "pages": [ - "built-in-nodes/TripoSplatConditioning", - "built-in-nodes/TripoSplatPreprocessImage" - ] - }, - { - "group": "Latent", - "pages": [ - "built-in-nodes/TripoSplatSamplingPreview", - "built-in-nodes/VAEDecodeTripoSplat" - ] - }, { "group": "Splat", "pages": [ @@ -625,10 +605,13 @@ }, "built-in-nodes/CreateCameraInfo", "built-in-nodes/Load3D", + "built-in-nodes/Load3DAdvanced", "built-in-nodes/Load3DAnimation", "built-in-nodes/Preview3D", "built-in-nodes/Preview3DAdvanced", "built-in-nodes/Preview3DAnimation", + "built-in-nodes/PreviewGaussianSplat", + "built-in-nodes/PreviewPointCloud", "built-in-nodes/SaveGLB", "built-in-nodes/VoxelToMesh", "built-in-nodes/VoxelToMeshBasic" @@ -637,63 +620,12 @@ { "group": "Advanced", "pages": [ - { - "group": "Conditioning", - "pages": [ - { - "group": "Audio", - "pages": [ - "built-in-nodes/ReferenceTimbreAudio" - ] - }, - { - "group": "Edit Models", - "pages": [ - "built-in-nodes/ReferenceLatent" - ] - }, - { - "group": "Flux", - "pages": [ - "built-in-nodes/ClipTextEncodeFlux", - "built-in-nodes/FluxDisableGuidance", - "built-in-nodes/FluxGuidance", - "built-in-nodes/FluxKontextImageScale", - "built-in-nodes/FluxKontextMultiReferenceLatentMethod" - ] - }, - { - "group": "Kandinsky5", - "pages": [ - "built-in-nodes/CLIPTextEncodeKandinsky5" - ] - }, - "built-in-nodes/CLIPTextEncodeHiDream", - "built-in-nodes/ClipTextEncodeHunyuanDit", - "built-in-nodes/CLIPTextEncodePixArtAlpha", - "built-in-nodes/CLIPTextEncodeSD3", - "built-in-nodes/ClipTextEncodeSdxl", - "built-in-nodes/ClipTextEncodeSdxlRefiner", - "built-in-nodes/ConditioningSetTimestepRange", - "built-in-nodes/ConditioningZeroOut", - "built-in-nodes/PiDConditioning", - "built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo", - "built-in-nodes/TextEncodeQwenImageEdit", - "built-in-nodes/TextEncodeQwenImageEditPlus", - "built-in-nodes/TextEncodeZImageOmni" - ] - }, { "group": "Debug", "pages": [ - { - "group": "Model", - "pages": [ - "built-in-nodes/EasyCache", - "built-in-nodes/LazyCache", - "built-in-nodes/ModelComputeDtype" - ] - } + "built-in-nodes/EasyCache", + "built-in-nodes/LazyCache", + "built-in-nodes/ModelComputeDtype" ] }, { @@ -772,89 +704,14 @@ { "group": "Loaders", "pages": [ - { - "group": "Deprecated", - "pages": [ - "built-in-nodes/DiffusersLoader" - ] - }, - { - "group": "Qwen", - "pages": [ - "built-in-nodes/QwenImageDiffsynthControlnet" - ] - }, - { - "group": "Zimage", - "pages": [ - "built-in-nodes/ZImageFunControlnet" - ] - }, - "built-in-nodes/CheckpointLoader", - "built-in-nodes/ClipLoader", "built-in-nodes/DeprecatedCheckpointLoader", - "built-in-nodes/DeprecatedDiffusersLoader", - "built-in-nodes/DualCLIPLoader", - "built-in-nodes/LTXAVTextEncoderLoader", - "built-in-nodes/ModelPatchLoader", - "built-in-nodes/QuadrupleCLIPLoader", - "built-in-nodes/TripleCLIPLoader", - "built-in-nodes/UNETLoader" - ] - }, - { - "group": "Model", - "pages": [ - "built-in-nodes/HiDreamO1PatchSeamSmoothing", - "built-in-nodes/ModelNoiseScale", - "built-in-nodes/ModelSamplingAuraFlow", - "built-in-nodes/ModelSamplingContinuousEDM", - "built-in-nodes/ModelSamplingContinuousV", - "built-in-nodes/ModelSamplingDiscrete", - "built-in-nodes/ModelSamplingFlux", - "built-in-nodes/ModelSamplingLTXV", - "built-in-nodes/ModelSamplingSD3", - "built-in-nodes/ModelSamplingStableCascade", - "built-in-nodes/RenormCFG", - "built-in-nodes/RescaleCFG" + "built-in-nodes/DeprecatedDiffusersLoader" ] }, { "group": "Model Merging", "pages": [ - { - "group": "Model Specific", - "pages": [ - "built-in-nodes/ModelMergeAuraflow", - "built-in-nodes/ModelMergeCosmos14B", - "built-in-nodes/ModelMergeCosmos7B", - "built-in-nodes/ModelMergeCosmosPredict2_14B", - "built-in-nodes/ModelMergeCosmosPredict2_2B", - "built-in-nodes/ModelMergeFlux1", - "built-in-nodes/ModelMergeLTXV", - "built-in-nodes/ModelMergeMochiPreview", - "built-in-nodes/ModelMergeQwenImage", - "built-in-nodes/ModelMergeSD1", - "built-in-nodes/ModelMergeSD35_Large", - "built-in-nodes/ModelMergeSD3_2B", - "built-in-nodes/ModelMergeSDXL", - "built-in-nodes/ModelMergeWAN2_1" - ] - }, - "built-in-nodes/CheckpointSave", - "built-in-nodes/CLIPMergeAdd", - "built-in-nodes/ClipMergeSimple", - "built-in-nodes/CLIPMergeSubtract", - "built-in-nodes/ClipSave", - "built-in-nodes/ImageOnlyCheckpointSave", - "built-in-nodes/ModelMergeAdd", - "built-in-nodes/ModelMergeBlocks", - "built-in-nodes/ModelMergeSimple", - "built-in-nodes/ModelMergeSubtract", - "built-in-nodes/ModelSave", - "built-in-nodes/SaveLoRA", - "built-in-nodes/SaveLoRANode", - "built-in-nodes/VAESave" + "built-in-nodes/SaveLoRANode" ] }, { @@ -867,17 +724,23 @@ "built-in-nodes/SelectVAEDevice" ] }, - "built-in-nodes/GeminiNodeV2", + "built-in-nodes/IdeogramV1", + "built-in-nodes/IdeogramV2", "built-in-nodes/MoonvalleyImg2VideoNode", "built-in-nodes/MoonvalleyTxt2VideoNode", "built-in-nodes/MoonvalleyVideo2VideoNode", - "built-in-nodes/PreviewGaussianSplat", - "built-in-nodes/PreviewPointCloud", - "built-in-nodes/SaveAudioAdvanced", "built-in-nodes/SeedVR2Conditioning", "built-in-nodes/SeedVR2PostProcessing", "built-in-nodes/SeedVR2Preprocess", - "built-in-nodes/SeedVR2ProgressiveSampler" + "built-in-nodes/SeedVR2ProgressiveSampler", + "built-in-nodes/StabilityAudioInpaint", + "built-in-nodes/StabilityAudioToAudio", + "built-in-nodes/StabilityStableImageSD_3_5Node", + "built-in-nodes/StabilityStableImageUltraNode", + "built-in-nodes/StabilityTextToAudio", + "built-in-nodes/StabilityUpscaleConservativeNode", + "built-in-nodes/StabilityUpscaleCreativeNode", + "built-in-nodes/StabilityUpscaleFastNode" ] }, { @@ -1027,6 +890,7 @@ "built-in-nodes/PreviewAudio", "built-in-nodes/RecordAudio", "built-in-nodes/SaveAudio", + "built-in-nodes/SaveAudioAdvanced", "built-in-nodes/SaveAudioMP3", "built-in-nodes/SaveAudioOpus", "built-in-nodes/SplitAudioChannels", @@ -1056,38 +920,12 @@ { "group": "Attention Experiments", "pages": [ - "built-in-nodes/CLIPAttentionMultiply", + "built-in-nodes/ClipAttentionMultiply", "built-in-nodes/UNetCrossAttentionMultiply", "built-in-nodes/UNetSelfAttentionMultiply", "built-in-nodes/UNetTemporalAttentionMultiply" ] }, - { - "group": "Conditioning", - "pages": [ - "built-in-nodes/CLIPTextEncodeControlnet", - "built-in-nodes/T5TokenizerOptions" - ] - }, - { - "group": "Custom Sampling", - "pages": [ - { - "group": "Noise", - "pages": [ - "built-in-nodes/AddNoise" - ] - }, - "built-in-nodes/ManualSigmas" - ] - }, - { - "group": "Photomaker", - "pages": [ - "built-in-nodes/PhotoMakerEncode", - "built-in-nodes/PhotoMakerLoader" - ] - }, { "group": "Stable Cascade", "pages": [ @@ -1098,17 +936,13 @@ "built-in-nodes/FluxKVCache", "built-in-nodes/FreSca", "built-in-nodes/LatentBlend", - "built-in-nodes/LoadLatent", "built-in-nodes/LoraSave", "built-in-nodes/Mahiro", "built-in-nodes/PerpNeg", "built-in-nodes/PerpNegGuider", "built-in-nodes/SamplerEulerCFGpp", - "built-in-nodes/SaveLatent", "built-in-nodes/SelfAttentionGuidance", - "built-in-nodes/TorchCompileModel", - "built-in-nodes/VAEDecodeTiled", - "built-in-nodes/VAEEncodeTiled" + "built-in-nodes/TorchCompileModel" ] }, { @@ -1192,6 +1026,10 @@ { "group": "Geometry Estimation", "pages": [ + "built-in-nodes/DA3GeometryToMesh", + "built-in-nodes/DA3GeometryToPointCloud", + "built-in-nodes/DA3Inference", + "built-in-nodes/DA3Render", "built-in-nodes/MoGeInference", "built-in-nodes/MoGePanoramaInference", "built-in-nodes/MoGePointMapToMesh", @@ -1310,19 +1148,28 @@ "group": "Conditioning", "pages": [ { - "group": "3D Models", + "group": "Ace", "pages": [ - "built-in-nodes/Hunyuan3Dv2Conditioning", - "built-in-nodes/Hunyuan3Dv2ConditioningMultiView", - "built-in-nodes/StableZero123_Conditioning", - "built-in-nodes/StableZero123_Conditioning_Batched", - "built-in-nodes/SV3D_Conditioning" + "built-in-nodes/TextEncodeAceStepAudio", + "built-in-nodes/TextEncodeAceStepAudio1.5" ] }, { - "group": "Audio", + "group": "Autoregressive", "pages": [ - "built-in-nodes/LTXVReferenceAudio" + "built-in-nodes/ARVideoI2V" + ] + }, + { + "group": "Bernini", + "pages": [ + "built-in-nodes/BerniniConditioning" + ] + }, + { + "group": "Boogu", + "pages": [ + "built-in-nodes/TextEncodeBooguEdit" ] }, { @@ -1335,6 +1182,23 @@ "built-in-nodes/SetUnionControlNetType" ] }, + { + "group": "Cosmos", + "pages": [ + "built-in-nodes/CosmosImageToVideoLatent", + "built-in-nodes/CosmosPredict2ImageToVideoLatent" + ] + }, + { + "group": "Flux", + "pages": [ + "built-in-nodes/ClipTextEncodeFlux", + "built-in-nodes/FluxDisableGuidance", + "built-in-nodes/FluxGuidance", + "built-in-nodes/FluxKontextImageScale", + "built-in-nodes/FluxKontextMultiReferenceLatentMethod" + ] + }, { "group": "Gligen", "pages": [ @@ -1342,271 +1206,521 @@ ] }, { - "group": "Image", + "group": "Hidream", "pages": [ + "built-in-nodes/ClipTextEncodeHiDream", "built-in-nodes/HiDreamO1ReferenceImages" ] }, { - "group": "Inpaint", + "group": "Hunyuan 3D", "pages": [ - "built-in-nodes/CosmosImageToVideoLatent", - "built-in-nodes/CosmosPredict2ImageToVideoLatent", - "built-in-nodes/InpaintModelConditioning", - "built-in-nodes/Wan22ImageToVideoLatent" + "built-in-nodes/Hunyuan3Dv2Conditioning", + "built-in-nodes/Hunyuan3Dv2ConditioningMultiView" ] }, { - "group": "Instructpix2Pix", + "group": "Hunyuan Image", "pages": [ - "built-in-nodes/InstructPixToPixConditioning" + "built-in-nodes/ClipTextEncodeHunyuanDiT" ] }, { - "group": "Lotus", + "group": "Hunyuan Video", "pages": [ - "built-in-nodes/LotusConditioning" + "built-in-nodes/HunyuanImageToVideo", + "built-in-nodes/HunyuanRefinerLatent", + "built-in-nodes/HunyuanVideo15ImageToVideo", + "built-in-nodes/HunyuanVideo15SuperResolution", + "built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo" ] }, { - "group": "Stable Cascade", + "group": "Instructpix2Pix", "pages": [ - "built-in-nodes/StableCascade_StageB_Conditioning" + "built-in-nodes/InstructPixToPixConditioning" ] }, { - "group": "Style Model", + "group": "Kandinsky", "pages": [ - "built-in-nodes/StyleModelApply" + "built-in-nodes/ClipTextEncodeKandinsky5", + "built-in-nodes/Kandinsky5ImageToVideo" ] }, { - "group": "Upscale Diffusion", + "group": "Lotus", "pages": [ - "built-in-nodes/SD_4XUpscale_Conditioning" + "built-in-nodes/LotusConditioning" ] }, { - "group": "Video Models", + "group": "Ltxv", "pages": [ - "built-in-nodes/ARVideoI2V", - "built-in-nodes/GenerateTracks", "built-in-nodes/GetICLoRAParameters", - "built-in-nodes/HunyuanImageToVideo", - "built-in-nodes/HunyuanRefinerLatent", - "built-in-nodes/HunyuanVideo15ImageToVideo", - "built-in-nodes/HunyuanVideo15SuperResolution", - "built-in-nodes/Kandinsky5ImageToVideo", "built-in-nodes/LTXVAddGuide", "built-in-nodes/LTXVConditioning", "built-in-nodes/LTXVCropGuides", "built-in-nodes/LTXVImgToVideo", "built-in-nodes/LTXVImgToVideoInplace", - "built-in-nodes/NormalizeVideoLatentStart", - "built-in-nodes/VOIDInpaintConditioning", - "built-in-nodes/Wan22FunControlToVideo", - "built-in-nodes/WanAnimateToVideo", - "built-in-nodes/WanCameraEmbedding", - "built-in-nodes/WanCameraImageToVideo", - "built-in-nodes/WanDancerEncodeAudio", - "built-in-nodes/WanDancerVideo", - "built-in-nodes/WanFirstLastFrameToVideo", - "built-in-nodes/WanFunControlToVideo", - "built-in-nodes/WanFunInpaintToVideo", - "built-in-nodes/WanHuMoImageToVideo", - "built-in-nodes/WanImageToVideo", - "built-in-nodes/WanInfiniteTalkToVideo", - "built-in-nodes/WanMoveConcatTrack", - "built-in-nodes/WanMoveTracksFromCoords", - "built-in-nodes/WanMoveTrackToVideo", - "built-in-nodes/WanMoveVisualizeTracks", - "built-in-nodes/WanPhantomSubjectToVideo", - "built-in-nodes/WanSCAILToVideo", - "built-in-nodes/WanSoundImageToVideo", - "built-in-nodes/WanSoundImageToVideoExtend", - "built-in-nodes/WanTrackToVideo", - "built-in-nodes/WanVaceToVideo" + "built-in-nodes/LTXVReferenceAudio" ] }, - "built-in-nodes/AudioEncoderEncode", - "built-in-nodes/ClipSetLastLayer", - "built-in-nodes/ClipTextEncode", - "built-in-nodes/CLIPTextEncodeLumina2", - "built-in-nodes/ClipVisionEncode", - "built-in-nodes/ConditioningConcat", - "built-in-nodes/ConditioningSetArea", - "built-in-nodes/ConditioningSetAreaPercentage", - "built-in-nodes/ConditioningSetAreaPercentageVideo", - "built-in-nodes/ConditioningSetAreaStrength", - "built-in-nodes/ConditioningSetMask", - "built-in-nodes/ConditioningStableAudio", - "built-in-nodes/TextEncodeAceStepAudio", - "built-in-nodes/TextEncodeAceStepAudio1.5", - "built-in-nodes/unCLIPConditioning" - ] - }, - { - "group": "Latent", - "pages": [ { - "group": "3D", + "group": "Lumina", "pages": [ - "built-in-nodes/EmptyLatentHunyuan3Dv2", - "built-in-nodes/VAEDecodeHunyuan3D" + "built-in-nodes/ClipTextEncodeLumina2" ] }, { - "group": "Advanced", + "group": "Photomaker", "pages": [ - { - "group": "Operations", - "pages": [ - "built-in-nodes/LatentApplyOperation", - "built-in-nodes/LatentApplyOperationCFG", - "built-in-nodes/LatentOperationSharpen", - "built-in-nodes/LatentOperationTonemapReinhard" - ] - }, - "built-in-nodes/LatentAdd", - "built-in-nodes/LatentBatchSeedBehavior", - "built-in-nodes/LatentConcat", - "built-in-nodes/LatentCut", - "built-in-nodes/LatentCutToBatch", - "built-in-nodes/LatentInterpolate", - "built-in-nodes/LatentMultiply", - "built-in-nodes/LatentSubtract" + "built-in-nodes/PhotoMakerEncode" ] }, { - "group": "Audio", + "group": "Pixart", "pages": [ - "built-in-nodes/EmptyAceStep1.5LatentAudio", - "built-in-nodes/EmptyAceStepLatentAudio", - "built-in-nodes/EmptyLatentAudio", - "built-in-nodes/LTXVAudioVAEDecode", - "built-in-nodes/LTXVAudioVAEEncode", - "built-in-nodes/LTXVEmptyLatentAudio", - "built-in-nodes/VAEDecodeAudio", - "built-in-nodes/VAEDecodeAudioTiled", - "built-in-nodes/VAEEncodeAudio" + "built-in-nodes/ClipTextEncodePixArtAlpha" ] }, { - "group": "Batch", + "group": "Qwen Image", "pages": [ - "built-in-nodes/LatentBatch", - "built-in-nodes/LatentFromBatch", - "built-in-nodes/RebatchLatents", - "built-in-nodes/RepeatLatentBatch", - "built-in-nodes/ReplaceVideoLatentFrames" + "built-in-nodes/TextEncodeQwenImageEdit", + "built-in-nodes/TextEncodeQwenImageEditPlus" ] }, { - "group": "Chroma Radiance", + "group": "Stable Audio", "pages": [ - "built-in-nodes/EmptyChromaRadianceLatentImage" + "built-in-nodes/ConditioningStableAudio" ] }, { - "group": "Image", + "group": "Stable Cascade", "pages": [ - "built-in-nodes/EmptyHiDreamO1LatentImage" + "built-in-nodes/StableCascade_StageB_Conditioning" ] }, { - "group": "Inpaint", + "group": "Stable Diffusion", "pages": [ - "built-in-nodes/SetLatentNoiseMask", - "built-in-nodes/VAEEncodeForInpaint" + "built-in-nodes/ClipTextEncodeSD3", + "built-in-nodes/ClipTextEncodeSDXL", + "built-in-nodes/ClipTextEncodeSDXLRefiner" ] }, { - "group": "Qwen", + "group": "Stable Diffusion Upscaler", "pages": [ - "built-in-nodes/EmptyQwenImageLayeredLatentImage" + "built-in-nodes/SD_4XUpscale_Conditioning" ] }, { - "group": "Sd3", + "group": "Stable Video 3D", "pages": [ - "built-in-nodes/EmptySD3LatentImage" + "built-in-nodes/SV3D_Conditioning" ] }, { - "group": "Stable Cascade", + "group": "Stable Zero123", "pages": [ - "built-in-nodes/StableCascade_EmptyLatentImage", - "built-in-nodes/StableCascade_StageC_VAEEncode" + "built-in-nodes/StableZero123_Conditioning", + "built-in-nodes/StableZero123_Conditioning_Batched" ] }, { "group": "Transform", "pages": [ - "built-in-nodes/LatentCrop", - "built-in-nodes/LatentFlip", - "built-in-nodes/LatentRotate" + "built-in-nodes/ConditioningConcat", + "built-in-nodes/ConditioningMultiply", + "built-in-nodes/ConditioningSetArea", + "built-in-nodes/ConditioningSetAreaPercentage", + "built-in-nodes/ConditioningSetAreaPercentageVideo", + "built-in-nodes/ConditioningSetAreaStrength", + "built-in-nodes/ConditioningSetMask", + "built-in-nodes/ConditioningSetTimestepRange", + "built-in-nodes/ConditioningZeroOut" + ] + }, + { + "group": "Triposplat", + "pages": [ + "built-in-nodes/TripoSplatConditioning", + "built-in-nodes/TripoSplatPreprocessImage" + ] + }, + { + "group": "Void", + "pages": [ + "built-in-nodes/VOIDInpaintConditioning" ] }, { - "group": "Video", + "group": "Wan", "pages": [ { - "group": "Ltxv", + "group": "Animate", "pages": [ - "built-in-nodes/EmptyLTXVLatentVideo", - "built-in-nodes/LTXVConcatAVLatent", - "built-in-nodes/LTXVSeparateAVLatent" + "built-in-nodes/WanAnimateToVideo" ] }, - "built-in-nodes/EmptyARVideoLatent", - "built-in-nodes/EmptyCosmosLatentVideo", - "built-in-nodes/EmptyHunyuanLatentVideo", - "built-in-nodes/EmptyHunyuanVideo15Latent", - "built-in-nodes/EmptyMochiLatentVideo", - "built-in-nodes/LTXVLatentUpsampler", - "built-in-nodes/TrimVideoLatent", - "built-in-nodes/VOIDWarpedNoise" - ] - }, - "built-in-nodes/BatchLatentsNode", - "built-in-nodes/EmptyFlux2LatentImage", - "built-in-nodes/EmptyHunyuanImageLatent", - "built-in-nodes/EmptyLatentImage", - "built-in-nodes/HunyuanVideo15LatentUpscaleWithModel", - "built-in-nodes/LatentComposite", + { + "group": "Camera", + "pages": [ + "built-in-nodes/WanCameraEmbedding", + "built-in-nodes/WanCameraImageToVideo" + ] + }, + { + "group": "Dancer", + "pages": [ + "built-in-nodes/WanDancerEncodeAudio", + "built-in-nodes/WanDancerVideo" + ] + }, + { + "group": "Fun Control", + "pages": [ + "built-in-nodes/Wan22FunControlToVideo", + "built-in-nodes/WanFunControlToVideo" + ] + }, + { + "group": "Fun Inpaint", + "pages": [ + "built-in-nodes/WanFunInpaintToVideo" + ] + }, + { + "group": "Humo", + "pages": [ + "built-in-nodes/WanHuMoImageToVideo" + ] + }, + { + "group": "Infinite Talk", + "pages": [ + "built-in-nodes/WanInfiniteTalkToVideo" + ] + }, + { + "group": "Move", + "pages": [ + "built-in-nodes/GenerateTracks", + "built-in-nodes/WanMoveConcatTrack", + "built-in-nodes/WanMoveTracksFromCoords", + "built-in-nodes/WanMoveTrackToVideo", + "built-in-nodes/WanMoveVisualizeTracks", + "built-in-nodes/WanTrackToVideo" + ] + }, + { + "group": "Phantom Subject", + "pages": [ + "built-in-nodes/WanPhantomSubjectToVideo" + ] + }, + { + "group": "Scail", + "pages": [ + "built-in-nodes/SCAIL2ColoredMask", + "built-in-nodes/WanSCAILToVideo" + ] + }, + { + "group": "Sound", + "pages": [ + "built-in-nodes/WanSoundImageToVideo", + "built-in-nodes/WanSoundImageToVideoExtend" + ] + }, + { + "group": "Vace", + "pages": [ + "built-in-nodes/WanVaceToVideo" + ] + }, + "built-in-nodes/Wan22ImageToVideoLatent", + "built-in-nodes/WanFirstLastFrameToVideo", + "built-in-nodes/WanImageToVideo" + ] + }, + { + "group": "Z Image", + "pages": [ + "built-in-nodes/TextEncodeZImageOmni" + ] + }, + "built-in-nodes/AudioEncoderEncode", + "built-in-nodes/ClipSetLastLayer", + "built-in-nodes/ClipTextEncode", + "built-in-nodes/ClipTextEncodeControlnet", + "built-in-nodes/ClipVisionEncode", + "built-in-nodes/InpaintModelConditioning", + "built-in-nodes/NormalizeVideoLatentStart", + "built-in-nodes/PiDConditioning", + "built-in-nodes/ReferenceLatent", + "built-in-nodes/ReferenceTimbreAudio", + "built-in-nodes/StyleModelApply", + "built-in-nodes/T5TokenizerOptions", + "built-in-nodes/unCLIPConditioning" + ] + }, + { + "group": "Latent", + "pages": [ + { + "group": "Ace", + "pages": [ + "built-in-nodes/EmptyAceStep1.5LatentAudio", + "built-in-nodes/EmptyAceStepLatentAudio" + ] + }, + { + "group": "Advanced", + "pages": [ + { + "group": "Operations", + "pages": [ + "built-in-nodes/LatentApplyOperation", + "built-in-nodes/LatentApplyOperationCFG", + "built-in-nodes/LatentOperationSharpen", + "built-in-nodes/LatentOperationTonemapReinhard" + ] + }, + "built-in-nodes/LatentAdd", + "built-in-nodes/LatentBatchSeedBehavior", + "built-in-nodes/LatentConcat", + "built-in-nodes/LatentCut", + "built-in-nodes/LatentCutToBatch", + "built-in-nodes/LatentInterpolate", + "built-in-nodes/LatentMultiply", + "built-in-nodes/LatentSubtract" + ] + }, + { + "group": "Autoregressive", + "pages": [ + "built-in-nodes/EmptyARVideoLatent" + ] + }, + { + "group": "Batch", + "pages": [ + "built-in-nodes/BatchLatentsNode", + "built-in-nodes/LatentBatch", + "built-in-nodes/LatentFromBatch", + "built-in-nodes/RebatchLatents", + "built-in-nodes/RepeatLatentBatch", + "built-in-nodes/ReplaceVideoLatentFrames" + ] + }, + { + "group": "Chroma Radiance", + "pages": [ + "built-in-nodes/EmptyChromaRadianceLatentImage" + ] + }, + { + "group": "Cosmos", + "pages": [ + "built-in-nodes/EmptyCosmosLatentVideo" + ] + }, + { + "group": "Flux", + "pages": [ + "built-in-nodes/EmptyFlux2LatentImage" + ] + }, + { + "group": "Hidream", + "pages": [ + "built-in-nodes/EmptyHiDreamO1LatentImage" + ] + }, + { + "group": "Hunyhuan Video", + "pages": [ + "built-in-nodes/HunyuanVideo15LatentUpscaleWithModel" + ] + }, + { + "group": "Hunyuan 3D", + "pages": [ + "built-in-nodes/EmptyLatentHunyuan3Dv2", + "built-in-nodes/VAEDecodeHunyuan3D" + ] + }, + { + "group": "Hunyuan Image", + "pages": [ + "built-in-nodes/EmptyHunyuanImageLatent" + ] + }, + { + "group": "Hunyuan Video", + "pages": [ + "built-in-nodes/EmptyHunyuanLatentVideo", + "built-in-nodes/EmptyHunyuanVideo15Latent" + ] + }, + { + "group": "Ltxv", + "pages": [ + "built-in-nodes/EmptyLTXVLatentVideo", + "built-in-nodes/LTXVAudioVAEDecode", + "built-in-nodes/LTXVAudioVAEEncode", + "built-in-nodes/LTXVConcatAVLatent", + "built-in-nodes/LTXVEmptyLatentAudio", + "built-in-nodes/LTXVLatentUpsampler", + "built-in-nodes/LTXVSeparateAVLatent" + ] + }, + { + "group": "Mochi", + "pages": [ + "built-in-nodes/EmptyMochiLatentVideo" + ] + }, + { + "group": "Qwen", + "pages": [ + "built-in-nodes/EmptyQwenImageLayeredLatentImage" + ] + }, + { + "group": "Stable Cascade", + "pages": [ + "built-in-nodes/StableCascade_EmptyLatentImage", + "built-in-nodes/StableCascade_StageC_VAEEncode" + ] + }, + { + "group": "Stable Diffusion", + "pages": [ + "built-in-nodes/EmptySD3LatentImage" + ] + }, + { + "group": "Transform", + "pages": [ + "built-in-nodes/LatentCrop", + "built-in-nodes/LatentFlip", + "built-in-nodes/LatentRotate" + ] + }, + { + "group": "Triposplat", + "pages": [ + "built-in-nodes/TripoSplatSamplingPreview", + "built-in-nodes/VAEDecodeTripoSplat" + ] + }, + { + "group": "Void", + "pages": [ + "built-in-nodes/VOIDWarpedNoise", + "built-in-nodes/VOIDWarpedNoiseSource" + ] + }, + "built-in-nodes/EmptyLatentAudio", + "built-in-nodes/EmptyLatentImage", + "built-in-nodes/LatentComposite", "built-in-nodes/LatentCompositeMasked", "built-in-nodes/LatentUpscale", "built-in-nodes/LatentUpscaleBy", + "built-in-nodes/LoadLatent", + "built-in-nodes/SaveLatent", + "built-in-nodes/SetLatentNoiseMask", + "built-in-nodes/TrimVideoLatent", "built-in-nodes/VAEDecode", - "built-in-nodes/VAEEncode" + "built-in-nodes/VAEDecodeAudio", + "built-in-nodes/VAEDecodeAudioTiled", + "built-in-nodes/VAEDecodeTiled", + "built-in-nodes/VAEEncode", + "built-in-nodes/VAEEncodeAudio", + "built-in-nodes/VAEEncodeForInpaint", + "built-in-nodes/VAEEncodeTiled" ] }, { "group": "Loaders", "pages": [ "built-in-nodes/AudioEncoderLoader", + "built-in-nodes/CheckpointLoader", "built-in-nodes/CheckpointLoaderSimple", + "built-in-nodes/ClipLoader", "built-in-nodes/ClipVisionLoader", "built-in-nodes/DiffControlNetLoader", + "built-in-nodes/DiffusersLoader", + "built-in-nodes/DualCLIPLoader", "built-in-nodes/FrameInterpolationModelLoader", "built-in-nodes/GLIGENLoader", "built-in-nodes/HypernetworkLoader", "built-in-nodes/ImageOnlyCheckpointLoader", "built-in-nodes/LatentUpscaleModelLoader", "built-in-nodes/LoadBackgroundRemovalModel", + "built-in-nodes/LoadDA3Model", "built-in-nodes/LoadMediaPipeFaceLandmarker", "built-in-nodes/LoadMoGeModel", "built-in-nodes/LoraLoaderBypass", "built-in-nodes/LoraLoaderBypassModelOnly", "built-in-nodes/LoraModelLoader", + "built-in-nodes/LTXAVTextEncoderLoader", "built-in-nodes/LTXVAudioVAELoader", + "built-in-nodes/ModelPatchLoader", "built-in-nodes/OpticalFlowLoader", + "built-in-nodes/PhotoMakerLoader", + "built-in-nodes/QuadrupleCLIPLoader", "built-in-nodes/StyleModelLoader", + "built-in-nodes/TripleCLIPLoader", "built-in-nodes/unCLIPCheckpointLoader", + "built-in-nodes/UNETLoader", "built-in-nodes/UpscaleModelLoader", "built-in-nodes/VAELoader" ] }, + { + "group": "Merging", + "pages": [ + { + "group": "Model Specific", + "pages": [ + "built-in-nodes/ModelMergeAuraflow", + "built-in-nodes/ModelMergeCosmos14B", + "built-in-nodes/ModelMergeCosmos7B", + "built-in-nodes/ModelMergeCosmosPredict2_14B", + "built-in-nodes/ModelMergeCosmosPredict2_2B", + "built-in-nodes/ModelMergeFlux1", + "built-in-nodes/ModelMergeKrea2", + "built-in-nodes/ModelMergeLTXV", + "built-in-nodes/ModelMergeMochiPreview", + "built-in-nodes/ModelMergeQwenImage", + "built-in-nodes/ModelMergeSD1", + "built-in-nodes/ModelMergeSD35_Large", + "built-in-nodes/ModelMergeSD3_2B", + "built-in-nodes/ModelMergeSDXL", + "built-in-nodes/ModelMergeWAN2_1" + ] + }, + "built-in-nodes/CheckpointSave", + "built-in-nodes/ClipMergeAdd", + "built-in-nodes/ClipMergeSimple", + "built-in-nodes/ClipMergeSubtract", + "built-in-nodes/ClipSave", + "built-in-nodes/ImageOnlyCheckpointSave", + "built-in-nodes/ModelMergeAdd", + "built-in-nodes/ModelMergeBlocks", + "built-in-nodes/ModelMergeSimple", + "built-in-nodes/ModelMergeSubtract", + "built-in-nodes/ModelSave", + "built-in-nodes/SaveLoRA", + "built-in-nodes/VAESave" + ] + }, { "group": "Patch", "pages": [ @@ -1619,42 +1733,92 @@ { "group": "Flux", "pages": [ + "built-in-nodes/ModelSamplingFlux", "built-in-nodes/USOStyleReference" ] }, { - "group": "Supir", + "group": "Hidream", "pages": [ - "built-in-nodes/SUPIRApply" + "built-in-nodes/HiDreamO1PatchSeamSmoothing" ] }, { - "group": "Unet", + "group": "Ltxv", "pages": [ - "built-in-nodes/Epsilon Scaling", - "built-in-nodes/FreeU", - "built-in-nodes/FreeU_V2", - "built-in-nodes/HyperTile", - "built-in-nodes/PatchModelAddDownscale", - "built-in-nodes/PerturbedAttentionGuidance", - "built-in-nodes/TemporalScoreRescaling", - "built-in-nodes/TomePatchModel" + "built-in-nodes/ModelSamplingLTXV" ] }, - "built-in-nodes/ContextWindowsManual", - "built-in-nodes/ScaleROPE", - "built-in-nodes/WanContextWindowsManual" - ] - }, - { - "group": "Sampling", - "pages": [ { - "group": "Custom Sampling", + "group": "Qwen", "pages": [ - "built-in-nodes/APG", - "built-in-nodes/SamplerCustom", - "built-in-nodes/SamplerCustomAdvanced" + "built-in-nodes/QwenImageDiffsynthControlnet" + ] + }, + { + "group": "Stable Cascade", + "pages": [ + "built-in-nodes/ModelSamplingStableCascade" + ] + }, + { + "group": "Stable Diffusion", + "pages": [ + "built-in-nodes/ModelSamplingSD3" + ] + }, + { + "group": "Supir", + "pages": [ + "built-in-nodes/SUPIRApply" + ] + }, + { + "group": "Unet", + "pages": [ + "built-in-nodes/Epsilon Scaling", + "built-in-nodes/FreeU", + "built-in-nodes/FreeU_V2", + "built-in-nodes/HyperTile", + "built-in-nodes/PatchModelAddDownscale", + "built-in-nodes/PerturbedAttentionGuidance", + "built-in-nodes/TemporalScoreRescaling", + "built-in-nodes/TomePatchModel" + ] + }, + { + "group": "Wan", + "pages": [ + "built-in-nodes/WanContextWindowsManual" + ] + }, + { + "group": "Z Image", + "pages": [ + "built-in-nodes/ZImageFunControlnet" + ] + }, + "built-in-nodes/ContextWindowsManual", + "built-in-nodes/LTXVContextWindows", + "built-in-nodes/ModelNoiseScale", + "built-in-nodes/ModelSamplingAuraFlow", + "built-in-nodes/ModelSamplingContinuousEDM", + "built-in-nodes/ModelSamplingContinuousV", + "built-in-nodes/ModelSamplingDiscrete", + "built-in-nodes/RenormCFG", + "built-in-nodes/RescaleCFG", + "built-in-nodes/ScaleROPE" + ] + }, + { + "group": "Sampling", + "pages": [ + { + "group": "Custom", + "pages": [ + "built-in-nodes/APG", + "built-in-nodes/SamplerCustom", + "built-in-nodes/SamplerCustomAdvanced" ] }, { @@ -1662,6 +1826,7 @@ "pages": [ "built-in-nodes/BasicGuider", "built-in-nodes/CFGGuider", + "built-in-nodes/CFGOverride", "built-in-nodes/DualCFGGuider", "built-in-nodes/DualModelGuider", "built-in-nodes/VideoLinearCFGGuidance", @@ -1671,9 +1836,9 @@ { "group": "Noise", "pages": [ + "built-in-nodes/AddNoise", "built-in-nodes/DisableNoise", - "built-in-nodes/RandomNoise", - "built-in-nodes/VOIDWarpedNoiseSource" + "built-in-nodes/RandomNoise" ] }, { @@ -1706,6 +1871,7 @@ "built-in-nodes/ExponentialScheduler", "built-in-nodes/Flux2Scheduler", "built-in-nodes/GITSScheduler", + "built-in-nodes/Ideogram4Scheduler", "built-in-nodes/KarrasScheduler", "built-in-nodes/LaplaceScheduler", "built-in-nodes/LTXVScheduler", @@ -1720,6 +1886,7 @@ "pages": [ "built-in-nodes/ExtendIntermediateSigmas", "built-in-nodes/FlipSigmas", + "built-in-nodes/ManualSigmas", "built-in-nodes/SamplingPercentToSigma", "built-in-nodes/SetFirstSigma", "built-in-nodes/SplitSigmas", @@ -1789,6 +1956,7 @@ "pages": [ "built-in-nodes/TripoConversionNode", "built-in-nodes/TripoImageToModelNode", + "built-in-nodes/TripoImportModelNode", "built-in-nodes/TripoMultiviewToModelNode", "built-in-nodes/TripoP1ImageToModelNode", "built-in-nodes/TripoP1MultiviewToModelNode", @@ -1805,6 +1973,12 @@ { "group": "Audio", "pages": [ + { + "group": "Bytedance", + "pages": [ + "built-in-nodes/ByteDanceSeedAudio" + ] + }, { "group": "Elevenlabs", "pages": [ @@ -1824,14 +1998,6 @@ "built-in-nodes/SoniloTextToMusic", "built-in-nodes/SoniloVideoToMusic" ] - }, - { - "group": "Stability Ai", - "pages": [ - "built-in-nodes/StabilityAudioInpaint", - "built-in-nodes/StabilityAudioToAudio", - "built-in-nodes/StabilityTextToAudio" - ] } ] }, @@ -1897,8 +2063,6 @@ { "group": "Ideogram", "pages": [ - "built-in-nodes/IdeogramV1", - "built-in-nodes/IdeogramV2", "built-in-nodes/IdeogramV3", "built-in-nodes/IdeogramV4" ] @@ -1992,16 +2156,6 @@ "built-in-nodes/RunwayTextToImageNode" ] }, - { - "group": "Stability Ai", - "pages": [ - "built-in-nodes/StabilityStableImageSD_3_5Node", - "built-in-nodes/StabilityStableImageUltraNode", - "built-in-nodes/StabilityUpscaleConservativeNode", - "built-in-nodes/StabilityUpscaleCreativeNode", - "built-in-nodes/StabilityUpscaleFastNode" - ] - }, { "group": "Topaz", "pages": [ @@ -2042,7 +2196,8 @@ "group": "Gemini", "pages": [ "built-in-nodes/GeminiInputFiles", - "built-in-nodes/GeminiNode" + "built-in-nodes/GeminiNode", + "built-in-nodes/GeminiNodeV2" ] }, { @@ -2092,6 +2247,12 @@ "built-in-nodes/ByteDanceTextToVideoNode" ] }, + { + "group": "Gemini", + "pages": [ + "built-in-nodes/GeminiVideoOmni" + ] + }, { "group": "Grok", "pages": [ @@ -2146,6 +2307,13 @@ "pages": [ "built-in-nodes/LumaConceptsNode", "built-in-nodes/LumaImageToVideoNode", + "built-in-nodes/LumaRay32ExtendVideoNode", + "built-in-nodes/LumaRay32ImageToVideoNode", + "built-in-nodes/LumaRay32KeyframeNode", + "built-in-nodes/LumaRay32KeyframesToVideoNode", + "built-in-nodes/LumaRay32TextToVideoNode", + "built-in-nodes/LumaRay32VideoEditNode", + "built-in-nodes/LumaRay32VideoReframeNode", "built-in-nodes/LumaVideoNode" ] }, @@ -2170,6 +2338,9 @@ { "group": "Runway", "pages": [ + "built-in-nodes/RunwayAleph2KeyframeNode", + "built-in-nodes/RunwayAleph2PromptImageNode", + "built-in-nodes/RunwayAleph2VideoToVideoNode", "built-in-nodes/RunwayFirstLastFrameNode", "built-in-nodes/RunwayImageToVideoNodeGen3a", "built-in-nodes/RunwayImageToVideoNodeGen4" @@ -2253,14 +2424,7 @@ "built-in-nodes/SamplerDpmpp2mSde", "built-in-nodes/SamplerDpmppSde" ] - }, - { - "group": "Schedulers", - "pages": [ - "built-in-nodes/Ideogram4Scheduler" - ] - }, - "built-in-nodes/CFGOverride" + } ] } ] @@ -2270,7 +2434,10 @@ "pages": [ "built-in-nodes/AddTextPrefix", "built-in-nodes/AddTextSuffix", + "built-in-nodes/BuildJsonPromptIdeogram", "built-in-nodes/CaseConverter", + "built-in-nodes/ConvertArrayToString", + "built-in-nodes/ConvertDictionaryToString", "built-in-nodes/JsonExtractString", "built-in-nodes/MergeTextLists", "built-in-nodes/RegexExtract", @@ -2326,12 +2493,14 @@ "built-in-nodes/ColorToRGBInt", "built-in-nodes/ComfyMathExpression", "built-in-nodes/ComfyNumberConvert", + "built-in-nodes/CreateBoundingBoxes", "built-in-nodes/CreateList", "built-in-nodes/CurveEditor", "built-in-nodes/CustomCombo", "built-in-nodes/ImageHistogram", "built-in-nodes/PreviewAny", - "built-in-nodes/ResolutionSelector" + "built-in-nodes/ResolutionSelector", + "built-in-nodes/SeedNode" ] }, { @@ -2567,14 +2736,14 @@ "language": "zh", "tabs": [ { - "tab": "\u5f00\u59cb\u4f7f\u7528", + "tab": "开始使用", "pages": [ { - "group": "\u5f00\u59cb\u4f7f\u7528", + "group": "开始使用", "pages": [ "zh/index", { - "group": "\u672c\u5730 (\u81ea\u6258\u7ba1)", + "group": "本地 (自托管)", "icon": "download", "pages": [ "zh/installation/system_requirements", @@ -2583,7 +2752,7 @@ "pages": [ "zh/installation/desktop/overview", { - "group": "\u5b89\u88c5", + "group": "安装", "pages": [ "zh/installation/desktop/windows", "zh/installation/desktop/macos", @@ -2591,7 +2760,7 @@ ] }, { - "group": "\u4f7f\u7528\u6307\u5357", + "group": "使用指南", "pages": [ "zh/installation/desktop/usage/overview", "zh/installation/desktop/usage/instance-management", @@ -2611,7 +2780,7 @@ }, "zh/get_started/cloud", { - "group": "\u5b89\u88c5\u81ea\u5b9a\u4e49\u8282\u70b9", + "group": "安装自定义节点", "icon": "puzzle-piece", "pages": [ "zh/installation/install_custom_node", @@ -2621,7 +2790,7 @@ "zh/manager/overview", "zh/manager/install", { - "group": "\u81ea\u5b9a\u4e49\u8282\u70b9\u7ba1\u7406", + "group": "自定义节点管理", "pages": [ "zh/manager/pack-management", "zh/manager/legacy-ui" @@ -2647,7 +2816,7 @@ ] }, { - "group": "\u57fa\u7840\u6982\u5ff5", + "group": "基础概念", "pages": [ "zh/development/core-concepts/workflow", "zh/development/core-concepts/nodes", @@ -2659,7 +2828,7 @@ ] }, { - "group": "\u754c\u9762\u6307\u5357", + "group": "界面指南", "pages": [ "zh/interface/overview", "zh/interface/app-mode", @@ -2670,7 +2839,7 @@ "zh/interface/features/partial-execution", "zh/interface/features/node-docs", { - "group": "ComfyUI \u8bbe\u7f6e", + "group": "ComfyUI 设置", "icon": "gear", "pages": [ "zh/interface/settings/overview", @@ -2687,7 +2856,7 @@ ] }, { - "group": "Cloud \u4e13\u5c5e\u529f\u80fd", + "group": "Cloud 专属功能", "icon": "cloud", "pages": [ "zh/cloud/share-workflow", @@ -2697,11 +2866,11 @@ ] }, { - "group": "\u6559\u7a0b", + "group": "教程", "icon": "book", "pages": [ { - "group": "\u57fa\u7840\u793a\u4f8b", + "group": "基础示例", "pages": [ "zh/tutorials/basic/text-to-image", "zh/tutorials/basic/image-to-image", @@ -2723,7 +2892,7 @@ ] }, { - "group": "\u56fe\u50cf", + "group": "图像", "pages": [ { "group": "Flux", @@ -2837,7 +3006,7 @@ ] }, { - "group": "\u89c6\u9891", + "group": "视频", "pages": [ { "group": "LTX", @@ -2848,7 +3017,7 @@ ] }, { - "group": "Wan \u89c6\u9891", + "group": "Wan 视频", "pages": [ "zh/tutorials/video/wan/wan2_2", "zh/tutorials/video/wan/wan2-2-animate", @@ -2907,7 +3076,7 @@ ] }, { - "group": "\u97f3\u9891", + "group": "音频", "pages": [ { "group": "Stable Audio 1.0", @@ -2931,7 +3100,7 @@ ] }, { - "group": "\u5b9e\u7528\u5de5\u5177", + "group": "实用工具", "pages": [ "zh/tutorials/utility/preprocessors", "zh/tutorials/utility/frame-interpolation", @@ -2944,7 +3113,7 @@ "zh/tutorials/utility/moge", "zh/tutorials/utility/depth-anything-3", { - "group": "\u4eba\u8138\u68c0\u6d4b", + "group": "人脸检测", "pages": [ "zh/tutorials/utility/face-detection/mediapipe" ] @@ -2954,7 +3123,7 @@ ] }, { - "group": "\u5408\u4f5c\u4f19\u4f34\u8282\u70b9", + "group": "合作伙伴节点", "icon": "handshake", "pages": [ "zh/tutorials/partner-nodes/overview", @@ -3125,12 +3294,6 @@ "pages": [ "zh/tutorials/partner-nodes/topaz/astra-2" ] - }, - { - "group": "Grok", - "pages": [ - "zh/tutorials/partner-nodes/grok/grok-imagine-video-1-5" - ] } ] }, @@ -3138,29 +3301,15 @@ ] }, { - "tab": "\u5185\u7f6e\u8282\u70b9", + "tab": "内置节点", "pages": [ "zh/built-in-nodes/overview", { - "group": "\u8282\u70b9", + "group": "节点", "pages": [ { "group": "3D", "pages": [ - { - "group": "\u6761\u4ef6", - "pages": [ - "zh/built-in-nodes/TripoSplatConditioning", - "zh/built-in-nodes/TripoSplatPreprocessImage" - ] - }, - { - "group": "\u6f5c\u7a7a\u95f4", - "pages": [ - "zh/built-in-nodes/TripoSplatSamplingPreview", - "zh/built-in-nodes/VAEDecodeTripoSplat" - ] - }, { "group": "Splat", "pages": [ @@ -3175,747 +3324,372 @@ }, "zh/built-in-nodes/CreateCameraInfo", "zh/built-in-nodes/Load3D", + "zh/built-in-nodes/Load3DAdvanced", "zh/built-in-nodes/Load3DAnimation", "zh/built-in-nodes/Preview3D", "zh/built-in-nodes/Preview3DAdvanced", "zh/built-in-nodes/Preview3DAnimation", + "zh/built-in-nodes/PreviewGaussianSplat", + "zh/built-in-nodes/PreviewPointCloud", "zh/built-in-nodes/SaveGLB", "zh/built-in-nodes/VoxelToMesh", "zh/built-in-nodes/VoxelToMeshBasic" ] }, { - "group": "\u9ad8\u7ea7", + "group": "API Node", "pages": [ { - "group": "\u6761\u4ef6", + "group": "Image", "pages": [ { - "group": "\u97f3\u9891", - "pages": [ - "zh/built-in-nodes/ReferenceTimbreAudio" - ] - }, - { - "group": "\u7f16\u8f91\u6a21\u578b", - "pages": [ - "zh/built-in-nodes/ReferenceLatent" - ] - }, - { - "group": "Flux", + "group": "Bfl", "pages": [ - "zh/built-in-nodes/ClipTextEncodeFlux", - "zh/built-in-nodes/FluxDisableGuidance", - "zh/built-in-nodes/FluxGuidance", - "zh/built-in-nodes/FluxKontextImageScale", - "zh/built-in-nodes/FluxKontextMultiReferenceLatentMethod" + "zh/built-in-nodes/FluxProCannyNode", + "zh/built-in-nodes/FluxProDepthNode", + "zh/built-in-nodes/FluxProImageNode" ] }, { - "group": "Kandinsky5", + "group": "Bytedance", "pages": [ - "zh/built-in-nodes/CLIPTextEncodeKandinsky5" + "zh/built-in-nodes/ByteDanceImageEditNode" ] - }, - "zh/built-in-nodes/CLIPTextEncodeHiDream", - "zh/built-in-nodes/ClipTextEncodeHunyuanDit", - "zh/built-in-nodes/CLIPTextEncodePixArtAlpha", - "zh/built-in-nodes/CLIPTextEncodeSD3", - "zh/built-in-nodes/ClipTextEncodeSdxl", - "zh/built-in-nodes/ClipTextEncodeSdxlRefiner", - "zh/built-in-nodes/ConditioningSetTimestepRange", - "zh/built-in-nodes/ConditioningZeroOut", - "zh/built-in-nodes/PiDConditioning", - "zh/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo", - "zh/built-in-nodes/TextEncodeQwenImageEdit", - "zh/built-in-nodes/TextEncodeQwenImageEditPlus", - "zh/built-in-nodes/TextEncodeZImageOmni" + } ] }, { - "group": "\u8c03\u8bd5", + "group": "Video", "pages": [ { - "group": "\u6a21\u578b", + "group": "Pika", "pages": [ - "zh/built-in-nodes/EasyCache", - "zh/built-in-nodes/LazyCache", - "zh/built-in-nodes/ModelComputeDtype" + "zh/built-in-nodes/Pikadditions", + "zh/built-in-nodes/Pikaffects", + "zh/built-in-nodes/PikaImageToVideoNode2_2", + "zh/built-in-nodes/PikaScenesV2_2", + "zh/built-in-nodes/PikaStartEndFrameNode2_2", + "zh/built-in-nodes/Pikaswaps", + "zh/built-in-nodes/PikaTextToVideoNode2_2" ] } ] }, { - "group": "\u5f15\u5bfc", - "pages": [ - "zh/built-in-nodes/CFGNorm", - "zh/built-in-nodes/CFGZeroStar", - "zh/built-in-nodes/NAGuidance", - "zh/built-in-nodes/SkipLayerGuidanceDiT", - "zh/built-in-nodes/SkipLayerGuidanceDiTSimple", - "zh/built-in-nodes/SkipLayerGuidanceSD3", - "zh/built-in-nodes/TCFG" - ] - }, - { - "group": "\u94a9\u5b50", + "group": "图像", "pages": [ { - "group": "Clip", + "group": "BFL", "pages": [ - "zh/built-in-nodes/SetClipHooks" + "zh/built-in-nodes/partner-node/image/bfl/flux-1-1-pro-ultra-image" ] }, { - "group": "\u5408\u5e76", + "group": "Ideogram", "pages": [ - "zh/built-in-nodes/CombineHooks", - "zh/built-in-nodes/CombineHooksEight", - "zh/built-in-nodes/CombineHooksFour" + "zh/built-in-nodes/partner-node/image/ideogram/ideogram-v1", + "zh/built-in-nodes/partner-node/image/ideogram/ideogram-v2" ] }, { - "group": "\u6761\u4ef6\u5bf9", + "group": "Luma", "pages": [ - "zh/built-in-nodes/PairConditioningCombine", - "zh/built-in-nodes/PairConditioningSetDefaultAndCombine", - "zh/built-in-nodes/PairConditioningSetProperties", - "zh/built-in-nodes/PairConditioningSetPropertiesAndCombine" + "zh/built-in-nodes/partner-node/image/luma/luma-image-to-image", + "zh/built-in-nodes/partner-node/image/luma/luma-reference", + "zh/built-in-nodes/partner-node/image/luma/luma-text-to-image" ] }, { - "group": "\u6761\u4ef6\u5355", + "group": "OpenAI", "pages": [ - "zh/built-in-nodes/ConditioningSetDefaultAndCombine", - "zh/built-in-nodes/ConditioningSetProperties", - "zh/built-in-nodes/ConditioningSetPropertiesAndCombine" + "zh/built-in-nodes/partner-node/image/openai/openai-dalle2", + "zh/built-in-nodes/partner-node/image/openai/openai-dalle3", + "zh/built-in-nodes/partner-node/image/openai/openai-gpt-image1" ] }, { - "group": "\u521b\u5efa", + "group": "Recraft", "pages": [ - "zh/built-in-nodes/CreateHookLora", - "zh/built-in-nodes/CreateHookLoraModelOnly", - "zh/built-in-nodes/CreateHookModelAsLora", - "zh/built-in-nodes/CreateHookModelAsLoraModelOnly" + "zh/built-in-nodes/partner-node/image/recraft/recraft-color-rgb", + "zh/built-in-nodes/partner-node/image/recraft/recraft-controls", + "zh/built-in-nodes/partner-node/image/recraft/recraft-creative-upscale", + "zh/built-in-nodes/partner-node/image/recraft/recraft-crisp-upscale", + "zh/built-in-nodes/partner-node/image/recraft/recraft-image-inpainting", + "zh/built-in-nodes/partner-node/image/recraft/recraft-image-to-image", + "zh/built-in-nodes/partner-node/image/recraft/recraft-remove-background", + "zh/built-in-nodes/partner-node/image/recraft/recraft-replace-background", + "zh/built-in-nodes/partner-node/image/recraft/recraft-style-digital-illustration", + "zh/built-in-nodes/partner-node/image/recraft/recraft-style-logo-raster", + "zh/built-in-nodes/partner-node/image/recraft/recraft-style-realistic-image", + "zh/built-in-nodes/partner-node/image/recraft/recraft-text-to-image", + "zh/built-in-nodes/partner-node/image/recraft/recraft-text-to-vector", + "zh/built-in-nodes/partner-node/image/recraft/recraft-vectorize-image", + "zh/built-in-nodes/partner-node/image/recraft/save-svg" ] - }, + } + ] + }, + { + "group": "视频", + "pages": [ { - "group": "\u624b\u518c", + "group": "Google", "pages": [ - "zh/built-in-nodes/SetModelHooksOnCond" + "zh/built-in-nodes/partner-node/video/google/google-veo2-video" ] }, { - "group": "\u8c03\u5ea6", + "group": "Kling", "pages": [ - "zh/built-in-nodes/CreateHookKeyframe", - "zh/built-in-nodes/CreateHookKeyframesFromFloats", - "zh/built-in-nodes/CreateHookKeyframesInterpolated", - "zh/built-in-nodes/SetHookKeyframes" + "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-i2v", + "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-t2v", + "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-controls", + "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-image-to-video", + "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-start-end-frame-to-video", + "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-text-to-video" ] }, - "zh/built-in-nodes/ConditioningTimestepsRange" - ] - }, - { - "group": "\u52a0\u8f7d\u5668", - "pages": [ { - "group": "\u5df2\u5f03\u7528", + "group": "Luma", "pages": [ - "zh/built-in-nodes/DiffusersLoader" + "zh/built-in-nodes/partner-node/video/luma/luma-concepts", + "zh/built-in-nodes/partner-node/video/luma/luma-image-to-video", + "zh/built-in-nodes/partner-node/video/luma/luma-text-to-video" ] }, { - "group": "Qwen", + "group": "MiniMax", "pages": [ - "zh/built-in-nodes/QwenImageDiffsynthControlnet" + "zh/built-in-nodes/partner-node/video/minimax/minimax-image-to-video", + "zh/built-in-nodes/partner-node/video/minimax/minimax-text-to-video" ] }, { - "group": "Zimage", + "group": "Pika", "pages": [ - "zh/built-in-nodes/ZImageFunControlnet" + "zh/built-in-nodes/partner-node/video/pika/pika-image-to-video", + "zh/built-in-nodes/partner-node/video/pika/pika-scenes", + "zh/built-in-nodes/partner-node/video/pika/pika-text-to-video" ] }, - "zh/built-in-nodes/CheckpointLoader", - "zh/built-in-nodes/ClipLoader", - "zh/built-in-nodes/DeprecatedCheckpointLoader", - "zh/built-in-nodes/DeprecatedDiffusersLoader", - "zh/built-in-nodes/DualCLIPLoader", - "zh/built-in-nodes/LTXAVTextEncoderLoader", - "zh/built-in-nodes/ModelPatchLoader", - "zh/built-in-nodes/QuadrupleCLIPLoader", - "zh/built-in-nodes/TripleCLIPLoader", - "zh/built-in-nodes/UNETLoader" - ] - }, - { - "group": "\u6a21\u578b", - "pages": [ - "zh/built-in-nodes/HiDreamO1PatchSeamSmoothing", - "zh/built-in-nodes/ModelNoiseScale", - "zh/built-in-nodes/ModelSamplingAuraFlow", - "zh/built-in-nodes/ModelSamplingContinuousEDM", - "zh/built-in-nodes/ModelSamplingContinuousV", - "zh/built-in-nodes/ModelSamplingDiscrete", - "zh/built-in-nodes/ModelSamplingFlux", - "zh/built-in-nodes/ModelSamplingLTXV", - "zh/built-in-nodes/ModelSamplingSD3", - "zh/built-in-nodes/ModelSamplingStableCascade", - "zh/built-in-nodes/RenormCFG", - "zh/built-in-nodes/RescaleCFG" - ] - }, - { - "group": "\u6a21\u578b\u5408\u5e76", - "pages": [ { - "group": "\u6a21\u578b\u7279\u5b9a", + "group": "PixVerse", "pages": [ - "zh/built-in-nodes/ModelMergeAuraflow", - "zh/built-in-nodes/ModelMergeCosmos14B", - "zh/built-in-nodes/ModelMergeCosmos7B", - "zh/built-in-nodes/ModelMergeCosmosPredict2_14B", - "zh/built-in-nodes/ModelMergeCosmosPredict2_2B", - "zh/built-in-nodes/ModelMergeFlux1", - "zh/built-in-nodes/ModelMergeLTXV", - "zh/built-in-nodes/ModelMergeMochiPreview", - "zh/built-in-nodes/ModelMergeQwenImage", - "zh/built-in-nodes/ModelMergeSD1", - "zh/built-in-nodes/ModelMergeSD35_Large", - "zh/built-in-nodes/ModelMergeSD3_2B", - "zh/built-in-nodes/ModelMergeSDXL", - "zh/built-in-nodes/ModelMergeWAN2_1" + "zh/built-in-nodes/partner-node/video/pixverse/pixverse-image-to-video", + "zh/built-in-nodes/partner-node/video/pixverse/pixverse-template", + "zh/built-in-nodes/partner-node/video/pixverse/pixverse-text-to-video", + "zh/built-in-nodes/partner-node/video/pixverse/pixverse-transition-video" ] - }, - "zh/built-in-nodes/CheckpointSave", - "zh/built-in-nodes/CLIPMergeAdd", - "zh/built-in-nodes/ClipMergeSimple", - "zh/built-in-nodes/CLIPMergeSubtract", - "zh/built-in-nodes/ClipSave", - "zh/built-in-nodes/ImageOnlyCheckpointSave", - "zh/built-in-nodes/ModelMergeAdd", - "zh/built-in-nodes/ModelMergeBlocks", - "zh/built-in-nodes/ModelMergeSimple", - "zh/built-in-nodes/ModelMergeSubtract", - "zh/built-in-nodes/ModelSave", - "zh/built-in-nodes/SaveLoRA", - "zh/built-in-nodes/SaveLoRANode", - "zh/built-in-nodes/VAESave" + } + ] + } + ] + }, + { + "group": "Audio", + "pages": [ + "zh/built-in-nodes/AudioAdjustVolume", + "zh/built-in-nodes/AudioConcat", + "zh/built-in-nodes/AudioEqualizer3Band", + "zh/built-in-nodes/AudioMerge", + "zh/built-in-nodes/EmptyAudio", + "zh/built-in-nodes/JoinAudioChannels", + "zh/built-in-nodes/LoadAudio", + "zh/built-in-nodes/PreviewAudio", + "zh/built-in-nodes/RecordAudio", + "zh/built-in-nodes/SaveAudio", + "zh/built-in-nodes/SaveAudioAdvanced", + "zh/built-in-nodes/SaveAudioMP3", + "zh/built-in-nodes/SaveAudioOpus", + "zh/built-in-nodes/SplitAudioChannels", + "zh/built-in-nodes/TrimAudioDuration" + ] + }, + { + "group": "Experimental", + "pages": [ + { + "group": "Attention Experiments", + "pages": [ + "zh/built-in-nodes/ClipAttentionMultiply", + "zh/built-in-nodes/UNetCrossAttentionMultiply", + "zh/built-in-nodes/UNetSelfAttentionMultiply", + "zh/built-in-nodes/UNetTemporalAttentionMultiply" ] }, { - "group": "\u591aGPU", + "group": "Stable Cascade", "pages": [ - "zh/built-in-nodes/MultiGPU_Options", - "zh/built-in-nodes/MultiGPU_WorkUnits", - "zh/built-in-nodes/SelectCLIPDevice", - "zh/built-in-nodes/SelectModelDevice", - "zh/built-in-nodes/SelectVAEDevice" + "zh/built-in-nodes/StableCascade_SuperResolutionControlnet" ] }, - "zh/built-in-nodes/GeminiNodeV2", - "zh/built-in-nodes/MoonvalleyImg2VideoNode", - "zh/built-in-nodes/MoonvalleyTxt2VideoNode", - "zh/built-in-nodes/MoonvalleyVideo2VideoNode", - "zh/built-in-nodes/PreviewGaussianSplat", - "zh/built-in-nodes/PreviewPointCloud", - "zh/built-in-nodes/SaveAudioAdvanced", - "zh/built-in-nodes/SeedVR2Conditioning", - "zh/built-in-nodes/SeedVR2PostProcessing", - "zh/built-in-nodes/SeedVR2Preprocess", - "zh/built-in-nodes/SeedVR2ProgressiveSampler" + "zh/built-in-nodes/DifferentialDiffusion", + "zh/built-in-nodes/FluxKVCache", + "zh/built-in-nodes/FreSca", + "zh/built-in-nodes/LatentBlend", + "zh/built-in-nodes/LoraSave", + "zh/built-in-nodes/Mahiro", + "zh/built-in-nodes/PerpNeg", + "zh/built-in-nodes/PerpNegGuider", + "zh/built-in-nodes/SamplerEulerCFGpp", + "zh/built-in-nodes/SelfAttentionGuidance", + "zh/built-in-nodes/TorchCompileModel" ] }, { - "group": "API Node", + "group": "Model", "pages": [ { - "group": "\u56fe\u50cf", + "group": "Conditioning", "pages": [ { - "group": "BFL", + "group": "Ace", "pages": [ - "zh/built-in-nodes/partner-node/image/bfl/flux-1-1-pro-ultra-image" + "zh/built-in-nodes/TextEncodeAceStepAudio", + "zh/built-in-nodes/TextEncodeAceStepAudio1.5" ] }, { - "group": "Bfl", + "group": "Autoregressive", "pages": [ - "zh/built-in-nodes/FluxProCannyNode", - "zh/built-in-nodes/FluxProDepthNode", - "zh/built-in-nodes/FluxProImageNode" + "zh/built-in-nodes/ARVideoI2V" ] }, { - "group": "Bytedance", + "group": "Bernini", "pages": [ - "zh/built-in-nodes/ByteDanceImageEditNode" + "zh/built-in-nodes/BerniniConditioning" ] }, { - "group": "Ideogram", + "group": "Boogu", "pages": [ - "zh/built-in-nodes/partner-node/image/ideogram/ideogram-v1", - "zh/built-in-nodes/partner-node/image/ideogram/ideogram-v2" + "zh/built-in-nodes/TextEncodeBooguEdit" ] }, { - "group": "Luma", + "group": "Controlnet", "pages": [ - "zh/built-in-nodes/partner-node/image/luma/luma-image-to-image", - "zh/built-in-nodes/partner-node/image/luma/luma-reference", - "zh/built-in-nodes/partner-node/image/luma/luma-text-to-image" + "zh/built-in-nodes/ControlNetApply", + "zh/built-in-nodes/ControlNetApplyAdvanced", + "zh/built-in-nodes/ControlNetApplySD3", + "zh/built-in-nodes/ControlNetInpaintingAliMamaApply", + "zh/built-in-nodes/SetUnionControlNetType" ] }, { - "group": "OpenAI", + "group": "Cosmos", "pages": [ - "zh/built-in-nodes/partner-node/image/openai/openai-dalle2", - "zh/built-in-nodes/partner-node/image/openai/openai-dalle3", - "zh/built-in-nodes/partner-node/image/openai/openai-gpt-image1" + "zh/built-in-nodes/CosmosImageToVideoLatent", + "zh/built-in-nodes/CosmosPredict2ImageToVideoLatent" ] }, { - "group": "Recraft", + "group": "Flux", "pages": [ - "zh/built-in-nodes/partner-node/image/recraft/recraft-color-rgb", - "zh/built-in-nodes/partner-node/image/recraft/recraft-controls", - "zh/built-in-nodes/partner-node/image/recraft/recraft-creative-upscale", - "zh/built-in-nodes/partner-node/image/recraft/recraft-crisp-upscale", - "zh/built-in-nodes/partner-node/image/recraft/recraft-image-inpainting", - "zh/built-in-nodes/partner-node/image/recraft/recraft-image-to-image", - "zh/built-in-nodes/partner-node/image/recraft/recraft-remove-background", - "zh/built-in-nodes/partner-node/image/recraft/recraft-replace-background", - "zh/built-in-nodes/partner-node/image/recraft/recraft-style-digital-illustration", - "zh/built-in-nodes/partner-node/image/recraft/recraft-style-logo-raster", - "zh/built-in-nodes/partner-node/image/recraft/recraft-style-realistic-image", - "zh/built-in-nodes/partner-node/image/recraft/recraft-text-to-image", - "zh/built-in-nodes/partner-node/image/recraft/recraft-text-to-vector", - "zh/built-in-nodes/partner-node/image/recraft/recraft-vectorize-image", - "zh/built-in-nodes/partner-node/image/recraft/save-svg" + "zh/built-in-nodes/ClipTextEncodeFlux", + "zh/built-in-nodes/FluxDisableGuidance", + "zh/built-in-nodes/FluxGuidance", + "zh/built-in-nodes/FluxKontextImageScale", + "zh/built-in-nodes/FluxKontextMultiReferenceLatentMethod" ] - } - ] - }, - { - "group": "\u89c6\u9891", - "pages": [ + }, { - "group": "Google", + "group": "Gligen", "pages": [ - "zh/built-in-nodes/partner-node/video/google/google-veo2-video" + "zh/built-in-nodes/GLIGENTextBoxApply" ] }, { - "group": "Kling", + "group": "Hidream", "pages": [ - "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-i2v", - "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-t2v", - "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-controls", - "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-image-to-video", - "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-start-end-frame-to-video", - "zh/built-in-nodes/partner-node/video/kwai_vgi/kling-text-to-video" + "zh/built-in-nodes/ClipTextEncodeHiDream", + "zh/built-in-nodes/HiDreamO1ReferenceImages" ] }, { - "group": "Luma", + "group": "Hunyuan 3D", "pages": [ - "zh/built-in-nodes/partner-node/video/luma/luma-concepts", - "zh/built-in-nodes/partner-node/video/luma/luma-image-to-video", - "zh/built-in-nodes/partner-node/video/luma/luma-text-to-video" + "zh/built-in-nodes/Hunyuan3Dv2Conditioning", + "zh/built-in-nodes/Hunyuan3Dv2ConditioningMultiView" ] }, { - "group": "MiniMax", + "group": "Hunyuan Image", "pages": [ - "zh/built-in-nodes/partner-node/video/minimax/minimax-image-to-video", - "zh/built-in-nodes/partner-node/video/minimax/minimax-text-to-video" + "zh/built-in-nodes/ClipTextEncodeHunyuanDiT" ] }, { - "group": "Pika", + "group": "Hunyuan Video", "pages": [ - "zh/built-in-nodes/partner-node/video/pika/pika-image-to-video", - "zh/built-in-nodes/partner-node/video/pika/pika-scenes", - "zh/built-in-nodes/partner-node/video/pika/pika-text-to-video", - "zh/built-in-nodes/Pikadditions", - "zh/built-in-nodes/Pikaffects", - "zh/built-in-nodes/PikaImageToVideoNode2_2", - "zh/built-in-nodes/PikaScenesV2_2", - "zh/built-in-nodes/PikaStartEndFrameNode2_2", - "zh/built-in-nodes/Pikaswaps", - "zh/built-in-nodes/PikaTextToVideoNode2_2" + "zh/built-in-nodes/HunyuanImageToVideo", + "zh/built-in-nodes/HunyuanRefinerLatent", + "zh/built-in-nodes/HunyuanVideo15ImageToVideo", + "zh/built-in-nodes/HunyuanVideo15SuperResolution", + "zh/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo" ] }, { - "group": "PixVerse", + "group": "Instructpix2Pix", "pages": [ - "zh/built-in-nodes/partner-node/video/pixverse/pixverse-image-to-video", - "zh/built-in-nodes/partner-node/video/pixverse/pixverse-template", - "zh/built-in-nodes/partner-node/video/pixverse/pixverse-text-to-video", - "zh/built-in-nodes/partner-node/video/pixverse/pixverse-transition-video" + "zh/built-in-nodes/InstructPixToPixConditioning" ] - } - ] - } - ] - }, - { - "group": "\u97f3\u9891", - "pages": [ - "zh/built-in-nodes/AudioAdjustVolume", - "zh/built-in-nodes/AudioConcat", - "zh/built-in-nodes/AudioEqualizer3Band", - "zh/built-in-nodes/AudioMerge", - "zh/built-in-nodes/EmptyAudio", - "zh/built-in-nodes/JoinAudioChannels", - "zh/built-in-nodes/LoadAudio", - "zh/built-in-nodes/PreviewAudio", - "zh/built-in-nodes/RecordAudio", - "zh/built-in-nodes/SaveAudio", - "zh/built-in-nodes/SaveAudioMP3", - "zh/built-in-nodes/SaveAudioOpus", - "zh/built-in-nodes/SplitAudioChannels", - "zh/built-in-nodes/TrimAudioDuration" - ] - }, - { - "group": "\u6761\u4ef6", - "pages": [ - { - "group": "\u89c6\u9891\u6a21\u578b", - "pages": [ - "zh/built-in-nodes/conditioning/video-models/wan-vace-to-video", - "zh/built-in-nodes/Stablezero123Conditioning", - "zh/built-in-nodes/Stablezero123ConditioningBatched", - "zh/built-in-nodes/SVD_img2vid_Conditioning", - "zh/built-in-nodes/SvdImg2vidConditioning" - ] - }, - "zh/built-in-nodes/ConditioningAverage", - "zh/built-in-nodes/Sd4xupscaleConditioning" - ] - }, - { - "group": "\u5b9e\u9a8c\u6027", - "pages": [ - { - "group": "\u6ce8\u610f\u529b\u5b9e\u9a8c", - "pages": [ - "zh/built-in-nodes/CLIPAttentionMultiply", - "zh/built-in-nodes/UNetCrossAttentionMultiply", - "zh/built-in-nodes/UNetSelfAttentionMultiply", - "zh/built-in-nodes/UNetTemporalAttentionMultiply" - ] - }, - { - "group": "\u6761\u4ef6", - "pages": [ - "zh/built-in-nodes/CLIPTextEncodeControlnet", - "zh/built-in-nodes/T5TokenizerOptions" - ] - }, - { - "group": "\u81ea\u5b9a\u4e49\u91c7\u6837", - "pages": [ + }, { - "group": "\u566a\u58f0", + "group": "Kandinsky", "pages": [ - "zh/built-in-nodes/AddNoise" + "zh/built-in-nodes/ClipTextEncodeKandinsky5", + "zh/built-in-nodes/Kandinsky5ImageToVideo" ] }, - "zh/built-in-nodes/ManualSigmas" - ] - }, - { - "group": "Photomaker", - "pages": [ - "zh/built-in-nodes/PhotoMakerEncode", - "zh/built-in-nodes/PhotoMakerLoader" - ] - }, - { - "group": "Stable Cascade", - "pages": [ - "zh/built-in-nodes/StableCascade_SuperResolutionControlnet" - ] - }, - "zh/built-in-nodes/DifferentialDiffusion", - "zh/built-in-nodes/FluxKVCache", - "zh/built-in-nodes/FreSca", - "zh/built-in-nodes/LatentBlend", - "zh/built-in-nodes/LoadLatent", - "zh/built-in-nodes/LoraSave", - "zh/built-in-nodes/Mahiro", - "zh/built-in-nodes/PerpNeg", - "zh/built-in-nodes/PerpNegGuider", - "zh/built-in-nodes/SamplerEulerCFGpp", - "zh/built-in-nodes/SaveLatent", - "zh/built-in-nodes/SelfAttentionGuidance", - "zh/built-in-nodes/TorchCompileModel", - "zh/built-in-nodes/VAEDecodeTiled", - "zh/built-in-nodes/VAEEncodeTiled" - ] - }, - { - "group": "\u56fe\u50cf", - "pages": [ - { - "group": "\u8c03\u6574", - "pages": [ - "zh/built-in-nodes/AdjustBrightness", - "zh/built-in-nodes/AdjustContrast" - ] - }, - { - "group": "\u80cc\u666f\u53bb\u9664", - "pages": [ - "zh/built-in-nodes/RemoveBackground" - ] - }, - { - "group": "\u6279\u5904\u7406", - "pages": [ - "zh/built-in-nodes/ImageDeduplication", - "zh/built-in-nodes/ImageFromBatch", - "zh/built-in-nodes/ImageGrid", - "zh/built-in-nodes/ImageMergeTileList", - "zh/built-in-nodes/MergeImageLists", - "zh/built-in-nodes/RebatchImages", - "zh/built-in-nodes/RepeatImageBatch", - "zh/built-in-nodes/ShuffleDataset", - "zh/built-in-nodes/ShuffleImageTextDataset", - "zh/built-in-nodes/SplitImageToTileList" - ] - }, - { - "group": "\u989c\u8272", - "pages": [ - "zh/built-in-nodes/ImageRGBToYUV", - "zh/built-in-nodes/ImageYUVToRGB", - "zh/built-in-nodes/NormalizeImages" - ] - }, - { - "group": "\u5408\u6210", - "pages": [ - "zh/built-in-nodes/ImageCompositeMasked", - "zh/built-in-nodes/JoinImageWithAlpha", - "zh/built-in-nodes/PorterDuffImageComposite", - "zh/built-in-nodes/SplitImageWithAlpha" - ] - }, - { - "group": "\u68c0\u6d4b", - "pages": [ - "zh/built-in-nodes/DrawBBoxes", - "zh/built-in-nodes/MediaPipeFaceLandmarker", - "zh/built-in-nodes/MediaPipeFaceMask", - "zh/built-in-nodes/MediaPipeFaceMeshVisualize", - "zh/built-in-nodes/RTDETR_detect", - "zh/built-in-nodes/SAM3_Detect", - "zh/built-in-nodes/SAM3_TrackPreview", - "zh/built-in-nodes/SAM3_TrackToMask", - "zh/built-in-nodes/SAM3_VideoTrack", - "zh/built-in-nodes/SDPoseDrawKeypoints", - "zh/built-in-nodes/SDPoseFaceBBoxes", - "zh/built-in-nodes/SDPoseKeypointExtractor" - ] - }, - { - "group": "\u6ee4\u955c", - "pages": [ - "zh/built-in-nodes/Canny", - "zh/built-in-nodes/ColorTransfer", - "zh/built-in-nodes/ImageAddNoise", - "zh/built-in-nodes/ImageBlend", - "zh/built-in-nodes/ImageBlur", - "zh/built-in-nodes/ImageQuantize", - "zh/built-in-nodes/ImageSharpen", - "zh/built-in-nodes/Morphology" - ] - }, - { - "group": "\u51e0\u4f55\u4f30\u8ba1", - "pages": [ - "zh/built-in-nodes/MoGeInference", - "zh/built-in-nodes/MoGePanoramaInference", - "zh/built-in-nodes/MoGePointMapToMesh", - "zh/built-in-nodes/MoGeRender" - ] - }, - { - "group": "\u906e\u7f69", - "pages": [ - "zh/built-in-nodes/BatchMasksNode", - "zh/built-in-nodes/CropMask", - "zh/built-in-nodes/FeatherMask", - "zh/built-in-nodes/GrowMask", - "zh/built-in-nodes/ImageColorToMask", - "zh/built-in-nodes/ImageToMask", - "zh/built-in-nodes/InvertMask", - "zh/built-in-nodes/MaskComposite", - "zh/built-in-nodes/MaskPreview", - "zh/built-in-nodes/MaskToImage", - "zh/built-in-nodes/SolidMask", - "zh/built-in-nodes/ThresholdMask", - "zh/built-in-nodes/VOIDQuadmaskPreprocess" - ] - }, - { - "group": "\u7740\u8272\u5668", - "pages": [ - "zh/built-in-nodes/GLSLShader" - ] - }, - { - "group": "\u53d8\u6362", - "pages": [ - "zh/built-in-nodes/CenterCropImages", - "zh/built-in-nodes/CropByBBoxes", - "zh/built-in-nodes/ImageCrop", - "zh/built-in-nodes/ImageCropV2", - "zh/built-in-nodes/ImageFlip", - "zh/built-in-nodes/ImagePadForOutpaint", - "zh/built-in-nodes/ImageRotate", - "zh/built-in-nodes/ImageStitch", - "zh/built-in-nodes/RandomCropImages", - "zh/built-in-nodes/ResizeAndPadImage", - "zh/built-in-nodes/ResizeImagesByLongerEdge", - "zh/built-in-nodes/ResizeImagesByShorterEdge" - ] - }, - { - "group": "\u653e\u5927", - "pages": [ - "zh/built-in-nodes/ImageScale", - "zh/built-in-nodes/ImageScaleBy", - "zh/built-in-nodes/ImageScaleToMaxDimension", - "zh/built-in-nodes/ImageScaleToTotalPixels", - "zh/built-in-nodes/ImageUpscaleWithModel" - ] - }, - { - "group": "\u89c6\u9891", - "pages": [ - "zh/built-in-nodes/WanDancerPadKeyframes", - "zh/built-in-nodes/WanDancerPadKeyframesList" - ] - }, - "zh/built-in-nodes/BatchImagesNode", - "zh/built-in-nodes/ConditioningCombine", - "zh/built-in-nodes/EmptyImage", - "zh/built-in-nodes/GetImageSize", - "zh/built-in-nodes/ImageBatch", - "zh/built-in-nodes/ImageCompare", - "zh/built-in-nodes/ImageInvert", - "zh/built-in-nodes/LoadImage", - "zh/built-in-nodes/LoadImageDataSetFromFolder", - "zh/built-in-nodes/LoadImageMask", - "zh/built-in-nodes/LoadImageOutput", - "zh/built-in-nodes/LoadImageSetFromFolderNode", - "zh/built-in-nodes/LoadImageSetNode", - "zh/built-in-nodes/LoadImageTextDataSetFromFolder", - "zh/built-in-nodes/LoadImageTextSetFromFolderNode", - "zh/built-in-nodes/LoraLoader", - "zh/built-in-nodes/LoraLoaderModelOnly", - "zh/built-in-nodes/Painter", - "zh/built-in-nodes/PreviewImage", - "zh/built-in-nodes/ResizeImageMaskNode", - "zh/built-in-nodes/SaveAnimatedPNG", - "zh/built-in-nodes/SaveAnimatedWEBP", - "zh/built-in-nodes/SaveImage", - "zh/built-in-nodes/SaveImageAdvanced", - "zh/built-in-nodes/SaveImageDataSetToFolder", - "zh/built-in-nodes/SaveImageTextDataSetToFolder", - "zh/built-in-nodes/SaveSVGNode", - "zh/built-in-nodes/WebcamCapture" - ] - }, - { - "group": "\u6f5c\u7a7a\u95f4", - "pages": [ - { - "group": "\u89c6\u9891", - "pages": [ - "zh/built-in-nodes/latent/video/trim-video-latent" - ] - } - ] - }, - { - "group": "\u52a0\u8f7d\u5668", - "pages": [ - "zh/built-in-nodes/ControlNetLoader" - ] - }, - { - "group": "\u6a21\u578b", - "pages": [ - { - "group": "\u6761\u4ef6", - "pages": [ { - "group": "3D Models", + "group": "Lotus", "pages": [ - "zh/built-in-nodes/Hunyuan3Dv2Conditioning", - "zh/built-in-nodes/Hunyuan3Dv2ConditioningMultiView", - "zh/built-in-nodes/StableZero123_Conditioning", - "zh/built-in-nodes/StableZero123_Conditioning_Batched", - "zh/built-in-nodes/SV3D_Conditioning" + "zh/built-in-nodes/LotusConditioning" ] }, { - "group": "\u97f3\u9891", + "group": "Ltxv", "pages": [ + "zh/built-in-nodes/GetICLoRAParameters", + "zh/built-in-nodes/LTXVAddGuide", + "zh/built-in-nodes/LTXVConditioning", + "zh/built-in-nodes/LTXVCropGuides", + "zh/built-in-nodes/LTXVImgToVideo", + "zh/built-in-nodes/LTXVImgToVideoInplace", "zh/built-in-nodes/LTXVReferenceAudio" ] }, { - "group": "Controlnet", - "pages": [ - "zh/built-in-nodes/ControlNetApply", - "zh/built-in-nodes/ControlNetApplyAdvanced", - "zh/built-in-nodes/ControlNetApplySD3", - "zh/built-in-nodes/ControlNetInpaintingAliMamaApply", - "zh/built-in-nodes/SetUnionControlNetType" - ] - }, - { - "group": "Gligen", + "group": "Lumina", "pages": [ - "zh/built-in-nodes/GLIGENTextBoxApply" + "zh/built-in-nodes/ClipTextEncodeLumina2" ] }, { - "group": "\u56fe\u50cf", + "group": "Photomaker", "pages": [ - "zh/built-in-nodes/HiDreamO1ReferenceImages" + "zh/built-in-nodes/PhotoMakerEncode" ] }, { - "group": "\u4fee\u590d", + "group": "Pixart", "pages": [ - "zh/built-in-nodes/CosmosImageToVideoLatent", - "zh/built-in-nodes/CosmosPredict2ImageToVideoLatent", - "zh/built-in-nodes/InpaintModelConditioning", - "zh/built-in-nodes/Wan22ImageToVideoLatent" + "zh/built-in-nodes/ClipTextEncodePixArtAlpha" ] }, { - "group": "Instructpix2Pix", + "group": "Qwen Image", "pages": [ - "zh/built-in-nodes/InstructPixToPixConditioning" + "zh/built-in-nodes/TextEncodeQwenImageEdit", + "zh/built-in-nodes/TextEncodeQwenImageEditPlus" ] }, { - "group": "Lotus", + "group": "Stable Audio", "pages": [ - "zh/built-in-nodes/LotusConditioning" + "zh/built-in-nodes/ConditioningStableAudio" ] }, { @@ -3925,125 +3699,212 @@ ] }, { - "group": "\u98ce\u683c\u6a21\u578b", + "group": "Stable Diffusion", "pages": [ - "zh/built-in-nodes/StyleModelApply" + "zh/built-in-nodes/ClipTextEncodeSD3", + "zh/built-in-nodes/ClipTextEncodeSDXL", + "zh/built-in-nodes/ClipTextEncodeSDXLRefiner" ] }, { - "group": "Upscale Diffusion", + "group": "Stable Diffusion Upscaler", "pages": [ "zh/built-in-nodes/SD_4XUpscale_Conditioning" ] }, { - "group": "\u89c6\u9891\u6a21\u578b", + "group": "Stable Video 3D", "pages": [ - "zh/built-in-nodes/ARVideoI2V", - "zh/built-in-nodes/GenerateTracks", - "zh/built-in-nodes/GetICLoRAParameters", - "zh/built-in-nodes/HunyuanImageToVideo", - "zh/built-in-nodes/HunyuanRefinerLatent", - "zh/built-in-nodes/HunyuanVideo15ImageToVideo", - "zh/built-in-nodes/HunyuanVideo15SuperResolution", - "zh/built-in-nodes/Kandinsky5ImageToVideo", - "zh/built-in-nodes/LTXVAddGuide", - "zh/built-in-nodes/LTXVConditioning", - "zh/built-in-nodes/LTXVCropGuides", - "zh/built-in-nodes/LTXVImgToVideo", - "zh/built-in-nodes/LTXVImgToVideoInplace", - "zh/built-in-nodes/NormalizeVideoLatentStart", - "zh/built-in-nodes/VOIDInpaintConditioning", - "zh/built-in-nodes/Wan22FunControlToVideo", - "zh/built-in-nodes/WanAnimateToVideo", - "zh/built-in-nodes/WanCameraEmbedding", - "zh/built-in-nodes/WanCameraImageToVideo", - "zh/built-in-nodes/WanDancerEncodeAudio", - "zh/built-in-nodes/WanDancerVideo", - "zh/built-in-nodes/WanFirstLastFrameToVideo", - "zh/built-in-nodes/WanFunControlToVideo", - "zh/built-in-nodes/WanFunInpaintToVideo", - "zh/built-in-nodes/WanHuMoImageToVideo", - "zh/built-in-nodes/WanImageToVideo", - "zh/built-in-nodes/WanInfiniteTalkToVideo", - "zh/built-in-nodes/WanMoveConcatTrack", - "zh/built-in-nodes/WanMoveTracksFromCoords", - "zh/built-in-nodes/WanMoveTrackToVideo", - "zh/built-in-nodes/WanMoveVisualizeTracks", - "zh/built-in-nodes/WanPhantomSubjectToVideo", - "zh/built-in-nodes/WanSCAILToVideo", - "zh/built-in-nodes/WanSoundImageToVideo", - "zh/built-in-nodes/WanSoundImageToVideoExtend", - "zh/built-in-nodes/WanTrackToVideo", - "zh/built-in-nodes/WanVaceToVideo" + "zh/built-in-nodes/SV3D_Conditioning" ] }, - "zh/built-in-nodes/AudioEncoderEncode", - "zh/built-in-nodes/ClipSetLastLayer", - "zh/built-in-nodes/ClipTextEncode", - "zh/built-in-nodes/CLIPTextEncodeLumina2", - "zh/built-in-nodes/ClipVisionEncode", - "zh/built-in-nodes/ConditioningConcat", - "zh/built-in-nodes/ConditioningSetArea", - "zh/built-in-nodes/ConditioningSetAreaPercentage", - "zh/built-in-nodes/ConditioningSetAreaPercentageVideo", - "zh/built-in-nodes/ConditioningSetAreaStrength", - "zh/built-in-nodes/ConditioningSetMask", - "zh/built-in-nodes/ConditioningStableAudio", - "zh/built-in-nodes/TextEncodeAceStepAudio", - "zh/built-in-nodes/TextEncodeAceStepAudio1.5", - "zh/built-in-nodes/unCLIPConditioning" - ] - }, - { - "group": "\u6f5c\u7a7a\u95f4", - "pages": [ { - "group": "3D", + "group": "Stable Zero123", "pages": [ - "zh/built-in-nodes/EmptyLatentHunyuan3Dv2", - "zh/built-in-nodes/VAEDecodeHunyuan3D" + "zh/built-in-nodes/StableZero123_Conditioning", + "zh/built-in-nodes/StableZero123_Conditioning_Batched" ] }, { - "group": "\u9ad8\u7ea7", + "group": "Transform", "pages": [ - { - "group": "\u64cd\u4f5c", - "pages": [ - "zh/built-in-nodes/LatentApplyOperation", - "zh/built-in-nodes/LatentApplyOperationCFG", - "zh/built-in-nodes/LatentOperationSharpen", - "zh/built-in-nodes/LatentOperationTonemapReinhard" - ] - }, - "zh/built-in-nodes/LatentAdd", - "zh/built-in-nodes/LatentBatchSeedBehavior", - "zh/built-in-nodes/LatentConcat", - "zh/built-in-nodes/LatentCut", - "zh/built-in-nodes/LatentCutToBatch", - "zh/built-in-nodes/LatentInterpolate", - "zh/built-in-nodes/LatentMultiply", - "zh/built-in-nodes/LatentSubtract" + "zh/built-in-nodes/ConditioningConcat", + "zh/built-in-nodes/ConditioningMultiply", + "zh/built-in-nodes/ConditioningSetArea", + "zh/built-in-nodes/ConditioningSetAreaPercentage", + "zh/built-in-nodes/ConditioningSetAreaPercentageVideo", + "zh/built-in-nodes/ConditioningSetAreaStrength", + "zh/built-in-nodes/ConditioningSetMask", + "zh/built-in-nodes/ConditioningSetTimestepRange", + "zh/built-in-nodes/ConditioningZeroOut" ] }, { - "group": "\u97f3\u9891", + "group": "Triposplat", "pages": [ - "zh/built-in-nodes/EmptyAceStep1.5LatentAudio", - "zh/built-in-nodes/EmptyAceStepLatentAudio", - "zh/built-in-nodes/EmptyLatentAudio", - "zh/built-in-nodes/LTXVAudioVAEDecode", - "zh/built-in-nodes/LTXVAudioVAEEncode", - "zh/built-in-nodes/LTXVEmptyLatentAudio", - "zh/built-in-nodes/VAEDecodeAudio", - "zh/built-in-nodes/VAEDecodeAudioTiled", - "zh/built-in-nodes/VAEEncodeAudio" + "zh/built-in-nodes/TripoSplatConditioning", + "zh/built-in-nodes/TripoSplatPreprocessImage" ] }, { - "group": "\u6279\u5904\u7406", + "group": "Void", "pages": [ + "zh/built-in-nodes/VOIDInpaintConditioning" + ] + }, + { + "group": "Wan", + "pages": [ + { + "group": "Animate", + "pages": [ + "zh/built-in-nodes/WanAnimateToVideo" + ] + }, + { + "group": "Camera", + "pages": [ + "zh/built-in-nodes/WanCameraEmbedding", + "zh/built-in-nodes/WanCameraImageToVideo" + ] + }, + { + "group": "Dancer", + "pages": [ + "zh/built-in-nodes/WanDancerEncodeAudio", + "zh/built-in-nodes/WanDancerVideo" + ] + }, + { + "group": "Fun Control", + "pages": [ + "zh/built-in-nodes/Wan22FunControlToVideo", + "zh/built-in-nodes/WanFunControlToVideo" + ] + }, + { + "group": "Fun Inpaint", + "pages": [ + "zh/built-in-nodes/WanFunInpaintToVideo" + ] + }, + { + "group": "Humo", + "pages": [ + "zh/built-in-nodes/WanHuMoImageToVideo" + ] + }, + { + "group": "Infinite Talk", + "pages": [ + "zh/built-in-nodes/WanInfiniteTalkToVideo" + ] + }, + { + "group": "Move", + "pages": [ + "zh/built-in-nodes/GenerateTracks", + "zh/built-in-nodes/WanMoveConcatTrack", + "zh/built-in-nodes/WanMoveTracksFromCoords", + "zh/built-in-nodes/WanMoveTrackToVideo", + "zh/built-in-nodes/WanMoveVisualizeTracks", + "zh/built-in-nodes/WanTrackToVideo" + ] + }, + { + "group": "Phantom Subject", + "pages": [ + "zh/built-in-nodes/WanPhantomSubjectToVideo" + ] + }, + { + "group": "Scail", + "pages": [ + "zh/built-in-nodes/SCAIL2ColoredMask", + "zh/built-in-nodes/WanSCAILToVideo" + ] + }, + { + "group": "Sound", + "pages": [ + "zh/built-in-nodes/WanSoundImageToVideo", + "zh/built-in-nodes/WanSoundImageToVideoExtend" + ] + }, + { + "group": "Vace", + "pages": [ + "zh/built-in-nodes/WanVaceToVideo" + ] + }, + "zh/built-in-nodes/Wan22ImageToVideoLatent", + "zh/built-in-nodes/WanFirstLastFrameToVideo", + "zh/built-in-nodes/WanImageToVideo" + ] + }, + { + "group": "Z Image", + "pages": [ + "zh/built-in-nodes/TextEncodeZImageOmni" + ] + }, + "zh/built-in-nodes/AudioEncoderEncode", + "zh/built-in-nodes/ClipSetLastLayer", + "zh/built-in-nodes/ClipTextEncode", + "zh/built-in-nodes/ClipTextEncodeControlnet", + "zh/built-in-nodes/ClipVisionEncode", + "zh/built-in-nodes/InpaintModelConditioning", + "zh/built-in-nodes/NormalizeVideoLatentStart", + "zh/built-in-nodes/PiDConditioning", + "zh/built-in-nodes/ReferenceLatent", + "zh/built-in-nodes/ReferenceTimbreAudio", + "zh/built-in-nodes/StyleModelApply", + "zh/built-in-nodes/T5TokenizerOptions", + "zh/built-in-nodes/unCLIPConditioning" + ] + }, + { + "group": "Latent", + "pages": [ + { + "group": "Ace", + "pages": [ + "zh/built-in-nodes/EmptyAceStep1.5LatentAudio", + "zh/built-in-nodes/EmptyAceStepLatentAudio" + ] + }, + { + "group": "Advanced", + "pages": [ + { + "group": "Operations", + "pages": [ + "zh/built-in-nodes/LatentApplyOperation", + "zh/built-in-nodes/LatentApplyOperationCFG", + "zh/built-in-nodes/LatentOperationSharpen", + "zh/built-in-nodes/LatentOperationTonemapReinhard" + ] + }, + "zh/built-in-nodes/LatentAdd", + "zh/built-in-nodes/LatentBatchSeedBehavior", + "zh/built-in-nodes/LatentConcat", + "zh/built-in-nodes/LatentCut", + "zh/built-in-nodes/LatentCutToBatch", + "zh/built-in-nodes/LatentInterpolate", + "zh/built-in-nodes/LatentMultiply", + "zh/built-in-nodes/LatentSubtract" + ] + }, + { + "group": "Autoregressive", + "pages": [ + "zh/built-in-nodes/EmptyARVideoLatent" + ] + }, + { + "group": "Batch", + "pages": [ + "zh/built-in-nodes/BatchLatentsNode", "zh/built-in-nodes/LatentBatch", "zh/built-in-nodes/LatentFromBatch", "zh/built-in-nodes/RebatchLatents", @@ -4058,28 +3919,71 @@ ] }, { - "group": "\u56fe\u50cf", + "group": "Cosmos", + "pages": [ + "zh/built-in-nodes/EmptyCosmosLatentVideo" + ] + }, + { + "group": "Flux", + "pages": [ + "zh/built-in-nodes/EmptyFlux2LatentImage" + ] + }, + { + "group": "Hidream", "pages": [ "zh/built-in-nodes/EmptyHiDreamO1LatentImage" ] }, { - "group": "\u4fee\u590d", + "group": "Hunyhuan Video", "pages": [ - "zh/built-in-nodes/SetLatentNoiseMask", - "zh/built-in-nodes/VAEEncodeForInpaint" + "zh/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel" ] }, { - "group": "Qwen", + "group": "Hunyuan 3D", "pages": [ - "zh/built-in-nodes/EmptyQwenImageLayeredLatentImage" + "zh/built-in-nodes/EmptyLatentHunyuan3Dv2", + "zh/built-in-nodes/VAEDecodeHunyuan3D" ] }, { - "group": "Sd3", + "group": "Hunyuan Image", "pages": [ - "zh/built-in-nodes/EmptySD3LatentImage" + "zh/built-in-nodes/EmptyHunyuanImageLatent" + ] + }, + { + "group": "Hunyuan Video", + "pages": [ + "zh/built-in-nodes/EmptyHunyuanLatentVideo", + "zh/built-in-nodes/EmptyHunyuanVideo15Latent" + ] + }, + { + "group": "Ltxv", + "pages": [ + "zh/built-in-nodes/EmptyLTXVLatentVideo", + "zh/built-in-nodes/LTXVAudioVAEDecode", + "zh/built-in-nodes/LTXVAudioVAEEncode", + "zh/built-in-nodes/LTXVConcatAVLatent", + "zh/built-in-nodes/LTXVEmptyLatentAudio", + "zh/built-in-nodes/LTXVLatentUpsampler", + "zh/built-in-nodes/LTXVSeparateAVLatent" + ] + }, + { + "group": "Mochi", + "pages": [ + "zh/built-in-nodes/EmptyMochiLatentVideo" + ] + }, + { + "group": "Qwen", + "pages": [ + "zh/built-in-nodes/EmptyQwenImageLayeredLatentImage" ] }, { @@ -4090,7 +3994,13 @@ ] }, { - "group": "\u53d8\u6362", + "group": "Stable Diffusion", + "pages": [ + "zh/built-in-nodes/EmptySD3LatentImage" + ] + }, + { + "group": "Transform", "pages": [ "zh/built-in-nodes/LatentCrop", "zh/built-in-nodes/LatentFlip", @@ -4098,67 +4008,116 @@ ] }, { - "group": "\u89c6\u9891", + "group": "Triposplat", "pages": [ - { - "group": "Ltxv", - "pages": [ - "zh/built-in-nodes/EmptyLTXVLatentVideo", - "zh/built-in-nodes/LTXVConcatAVLatent", - "zh/built-in-nodes/LTXVSeparateAVLatent" - ] - }, - "zh/built-in-nodes/EmptyARVideoLatent", - "zh/built-in-nodes/EmptyCosmosLatentVideo", - "zh/built-in-nodes/EmptyHunyuanLatentVideo", - "zh/built-in-nodes/EmptyHunyuanVideo15Latent", - "zh/built-in-nodes/EmptyMochiLatentVideo", - "zh/built-in-nodes/LTXVLatentUpsampler", - "zh/built-in-nodes/TrimVideoLatent", - "zh/built-in-nodes/VOIDWarpedNoise" + "zh/built-in-nodes/TripoSplatSamplingPreview", + "zh/built-in-nodes/VAEDecodeTripoSplat" + ] + }, + { + "group": "Void", + "pages": [ + "zh/built-in-nodes/VOIDWarpedNoise", + "zh/built-in-nodes/VOIDWarpedNoiseSource" ] }, - "zh/built-in-nodes/BatchLatentsNode", - "zh/built-in-nodes/EmptyFlux2LatentImage", - "zh/built-in-nodes/EmptyHunyuanImageLatent", + "zh/built-in-nodes/EmptyLatentAudio", "zh/built-in-nodes/EmptyLatentImage", - "zh/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel", "zh/built-in-nodes/LatentComposite", "zh/built-in-nodes/LatentCompositeMasked", "zh/built-in-nodes/LatentUpscale", "zh/built-in-nodes/LatentUpscaleBy", + "zh/built-in-nodes/LoadLatent", + "zh/built-in-nodes/SaveLatent", + "zh/built-in-nodes/SetLatentNoiseMask", + "zh/built-in-nodes/TrimVideoLatent", "zh/built-in-nodes/VAEDecode", - "zh/built-in-nodes/VAEEncode" + "zh/built-in-nodes/VAEDecodeAudio", + "zh/built-in-nodes/VAEDecodeAudioTiled", + "zh/built-in-nodes/VAEDecodeTiled", + "zh/built-in-nodes/VAEEncode", + "zh/built-in-nodes/VAEEncodeAudio", + "zh/built-in-nodes/VAEEncodeForInpaint", + "zh/built-in-nodes/VAEEncodeTiled" ] }, { - "group": "\u52a0\u8f7d\u5668", + "group": "Loaders", "pages": [ "zh/built-in-nodes/AudioEncoderLoader", + "zh/built-in-nodes/CheckpointLoader", "zh/built-in-nodes/CheckpointLoaderSimple", + "zh/built-in-nodes/ClipLoader", "zh/built-in-nodes/ClipVisionLoader", "zh/built-in-nodes/DiffControlNetLoader", + "zh/built-in-nodes/DiffusersLoader", + "zh/built-in-nodes/DualCLIPLoader", "zh/built-in-nodes/FrameInterpolationModelLoader", "zh/built-in-nodes/GLIGENLoader", "zh/built-in-nodes/HypernetworkLoader", "zh/built-in-nodes/ImageOnlyCheckpointLoader", "zh/built-in-nodes/LatentUpscaleModelLoader", "zh/built-in-nodes/LoadBackgroundRemovalModel", + "zh/built-in-nodes/LoadDA3Model", "zh/built-in-nodes/LoadMediaPipeFaceLandmarker", "zh/built-in-nodes/LoadMoGeModel", "zh/built-in-nodes/LoraLoaderBypass", "zh/built-in-nodes/LoraLoaderBypassModelOnly", "zh/built-in-nodes/LoraModelLoader", + "zh/built-in-nodes/LTXAVTextEncoderLoader", "zh/built-in-nodes/LTXVAudioVAELoader", + "zh/built-in-nodes/ModelPatchLoader", "zh/built-in-nodes/OpticalFlowLoader", + "zh/built-in-nodes/PhotoMakerLoader", + "zh/built-in-nodes/QuadrupleCLIPLoader", "zh/built-in-nodes/StyleModelLoader", + "zh/built-in-nodes/TripleCLIPLoader", "zh/built-in-nodes/unCLIPCheckpointLoader", + "zh/built-in-nodes/UNETLoader", "zh/built-in-nodes/UpscaleModelLoader", "zh/built-in-nodes/VAELoader" ] }, { - "group": "\u8865\u4e01", + "group": "Merging", + "pages": [ + { + "group": "Model Specific", + "pages": [ + "zh/built-in-nodes/ModelMergeAuraflow", + "zh/built-in-nodes/ModelMergeCosmos14B", + "zh/built-in-nodes/ModelMergeCosmos7B", + "zh/built-in-nodes/ModelMergeCosmosPredict2_14B", + "zh/built-in-nodes/ModelMergeCosmosPredict2_2B", + "zh/built-in-nodes/ModelMergeFlux1", + "zh/built-in-nodes/ModelMergeKrea2", + "zh/built-in-nodes/ModelMergeLTXV", + "zh/built-in-nodes/ModelMergeMochiPreview", + "zh/built-in-nodes/ModelMergeQwenImage", + "zh/built-in-nodes/ModelMergeSD1", + "zh/built-in-nodes/ModelMergeSD35_Large", + "zh/built-in-nodes/ModelMergeSD3_2B", + "zh/built-in-nodes/ModelMergeSDXL", + "zh/built-in-nodes/ModelMergeWAN2_1" + ] + }, + "zh/built-in-nodes/CheckpointSave", + "zh/built-in-nodes/ClipMergeAdd", + "zh/built-in-nodes/ClipMergeSimple", + "zh/built-in-nodes/ClipMergeSubtract", + "zh/built-in-nodes/ClipSave", + "zh/built-in-nodes/ImageOnlyCheckpointSave", + "zh/built-in-nodes/ModelMergeAdd", + "zh/built-in-nodes/ModelMergeBlocks", + "zh/built-in-nodes/ModelMergeSimple", + "zh/built-in-nodes/ModelMergeSubtract", + "zh/built-in-nodes/ModelSave", + "zh/built-in-nodes/SaveLoRA", + "zh/built-in-nodes/VAESave" + ] + }, + { + "group": "Patch", "pages": [ { "group": "Chroma Radiance", @@ -4169,9 +4128,40 @@ { "group": "Flux", "pages": [ + "zh/built-in-nodes/ModelSamplingFlux", "zh/built-in-nodes/USOStyleReference" ] }, + { + "group": "Hidream", + "pages": [ + "zh/built-in-nodes/HiDreamO1PatchSeamSmoothing" + ] + }, + { + "group": "Ltxv", + "pages": [ + "zh/built-in-nodes/ModelSamplingLTXV" + ] + }, + { + "group": "Qwen", + "pages": [ + "zh/built-in-nodes/QwenImageDiffsynthControlnet" + ] + }, + { + "group": "Stable Cascade", + "pages": [ + "zh/built-in-nodes/ModelSamplingStableCascade" + ] + }, + { + "group": "Stable Diffusion", + "pages": [ + "zh/built-in-nodes/ModelSamplingSD3" + ] + }, { "group": "Supir", "pages": [ @@ -4191,16 +4181,35 @@ "zh/built-in-nodes/TomePatchModel" ] }, + { + "group": "Wan", + "pages": [ + "zh/built-in-nodes/WanContextWindowsManual" + ] + }, + { + "group": "Z Image", + "pages": [ + "zh/built-in-nodes/ZImageFunControlnet" + ] + }, "zh/built-in-nodes/ContextWindowsManual", - "zh/built-in-nodes/ScaleROPE", - "zh/built-in-nodes/WanContextWindowsManual" + "zh/built-in-nodes/LTXVContextWindows", + "zh/built-in-nodes/ModelNoiseScale", + "zh/built-in-nodes/ModelSamplingAuraFlow", + "zh/built-in-nodes/ModelSamplingContinuousEDM", + "zh/built-in-nodes/ModelSamplingContinuousV", + "zh/built-in-nodes/ModelSamplingDiscrete", + "zh/built-in-nodes/RenormCFG", + "zh/built-in-nodes/RescaleCFG", + "zh/built-in-nodes/ScaleROPE" ] }, { - "group": "\u91c7\u6837", + "group": "Sampling", "pages": [ { - "group": "\u81ea\u5b9a\u4e49\u91c7\u6837", + "group": "Custom", "pages": [ "zh/built-in-nodes/APG", "zh/built-in-nodes/SamplerCustom", @@ -4208,10 +4217,11 @@ ] }, { - "group": "\u5f15\u5bfc\u5668", + "group": "Guiders", "pages": [ "zh/built-in-nodes/BasicGuider", "zh/built-in-nodes/CFGGuider", + "zh/built-in-nodes/CFGOverride", "zh/built-in-nodes/DualCFGGuider", "zh/built-in-nodes/DualModelGuider", "zh/built-in-nodes/VideoLinearCFGGuidance", @@ -4219,15 +4229,15 @@ ] }, { - "group": "\u566a\u58f0", + "group": "Noise", "pages": [ + "zh/built-in-nodes/AddNoise", "zh/built-in-nodes/DisableNoise", - "zh/built-in-nodes/RandomNoise", - "zh/built-in-nodes/VOIDWarpedNoiseSource" + "zh/built-in-nodes/RandomNoise" ] }, { - "group": "\u91c7\u6837\u5668", + "group": "Samplers", "pages": [ "zh/built-in-nodes/KSamplerSelect", "zh/built-in-nodes/SamplerARVideo", @@ -4248,7 +4258,7 @@ ] }, { - "group": "\u8c03\u5ea6\u5668", + "group": "Schedulers", "pages": [ "zh/built-in-nodes/AlignYourStepsScheduler", "zh/built-in-nodes/BasicScheduler", @@ -4256,6 +4266,7 @@ "zh/built-in-nodes/ExponentialScheduler", "zh/built-in-nodes/Flux2Scheduler", "zh/built-in-nodes/GITSScheduler", + "zh/built-in-nodes/Ideogram4Scheduler", "zh/built-in-nodes/KarrasScheduler", "zh/built-in-nodes/LaplaceScheduler", "zh/built-in-nodes/LTXVScheduler", @@ -4270,6 +4281,7 @@ "pages": [ "zh/built-in-nodes/ExtendIntermediateSigmas", "zh/built-in-nodes/FlipSigmas", + "zh/built-in-nodes/ManualSigmas", "zh/built-in-nodes/SamplingPercentToSigma", "zh/built-in-nodes/SetFirstSigma", "zh/built-in-nodes/SplitSigmas", @@ -4281,7 +4293,7 @@ ] }, { - "group": "\u8bad\u7ec3", + "group": "Training", "pages": [ "zh/built-in-nodes/LoadTrainingDataset", "zh/built-in-nodes/LossGraphNode", @@ -4294,7 +4306,7 @@ ] }, { - "group": "\u5408\u4f5c\u4f19\u4f34", + "group": "Partner", "pages": [ { "group": "3D", @@ -4339,6 +4351,7 @@ "pages": [ "zh/built-in-nodes/TripoConversionNode", "zh/built-in-nodes/TripoImageToModelNode", + "zh/built-in-nodes/TripoImportModelNode", "zh/built-in-nodes/TripoMultiviewToModelNode", "zh/built-in-nodes/TripoP1ImageToModelNode", "zh/built-in-nodes/TripoP1MultiviewToModelNode", @@ -4353,13 +4366,19 @@ ] }, { - "group": "\u97f3\u9891", + "group": "Audio", "pages": [ { - "group": "Elevenlabs", + "group": "Bytedance", "pages": [ - "zh/built-in-nodes/ElevenLabsAudioIsolation", - "zh/built-in-nodes/ElevenLabsInstantVoiceClone", + "zh/built-in-nodes/ByteDanceSeedAudio" + ] + }, + { + "group": "Elevenlabs", + "pages": [ + "zh/built-in-nodes/ElevenLabsAudioIsolation", + "zh/built-in-nodes/ElevenLabsInstantVoiceClone", "zh/built-in-nodes/ElevenLabsSpeechToSpeech", "zh/built-in-nodes/ElevenLabsSpeechToText", "zh/built-in-nodes/ElevenLabsTextToDialogue", @@ -4374,19 +4393,11 @@ "zh/built-in-nodes/SoniloTextToMusic", "zh/built-in-nodes/SoniloVideoToMusic" ] - }, - { - "group": "Stability Ai", - "pages": [ - "zh/built-in-nodes/StabilityAudioInpaint", - "zh/built-in-nodes/StabilityAudioToAudio", - "zh/built-in-nodes/StabilityTextToAudio" - ] } ] }, { - "group": "\u56fe\u50cf", + "group": "Image", "pages": [ { "group": "Beeble", @@ -4447,8 +4458,6 @@ { "group": "Ideogram", "pages": [ - "zh/built-in-nodes/IdeogramV1", - "zh/built-in-nodes/IdeogramV2", "zh/built-in-nodes/IdeogramV3", "zh/built-in-nodes/IdeogramV4" ] @@ -4542,16 +4551,6 @@ "zh/built-in-nodes/RunwayTextToImageNode" ] }, - { - "group": "Stability Ai", - "pages": [ - "zh/built-in-nodes/StabilityStableImageSD_3_5Node", - "zh/built-in-nodes/StabilityStableImageUltraNode", - "zh/built-in-nodes/StabilityUpscaleConservativeNode", - "zh/built-in-nodes/StabilityUpscaleCreativeNode", - "zh/built-in-nodes/StabilityUpscaleFastNode" - ] - }, { "group": "Topaz", "pages": [ @@ -4574,7 +4573,7 @@ ] }, { - "group": "\u6587\u672c", + "group": "Text", "pages": [ { "group": "Anthropic", @@ -4592,7 +4591,8 @@ "group": "Gemini", "pages": [ "zh/built-in-nodes/GeminiInputFiles", - "zh/built-in-nodes/GeminiNode" + "zh/built-in-nodes/GeminiNode", + "zh/built-in-nodes/GeminiNodeV2" ] }, { @@ -4612,7 +4612,7 @@ ] }, { - "group": "\u89c6\u9891", + "group": "Video", "pages": [ { "group": "Beeble", @@ -4642,6 +4642,12 @@ "zh/built-in-nodes/ByteDanceTextToVideoNode" ] }, + { + "group": "Gemini", + "pages": [ + "zh/built-in-nodes/GeminiVideoOmni" + ] + }, { "group": "Grok", "pages": [ @@ -4696,6 +4702,13 @@ "pages": [ "zh/built-in-nodes/LumaConceptsNode", "zh/built-in-nodes/LumaImageToVideoNode", + "zh/built-in-nodes/LumaRay32ExtendVideoNode", + "zh/built-in-nodes/LumaRay32ImageToVideoNode", + "zh/built-in-nodes/LumaRay32KeyframeNode", + "zh/built-in-nodes/LumaRay32KeyframesToVideoNode", + "zh/built-in-nodes/LumaRay32TextToVideoNode", + "zh/built-in-nodes/LumaRay32VideoEditNode", + "zh/built-in-nodes/LumaRay32VideoReframeNode", "zh/built-in-nodes/LumaVideoNode" ] }, @@ -4720,6 +4733,9 @@ { "group": "Runway", "pages": [ + "zh/built-in-nodes/RunwayAleph2KeyframeNode", + "zh/built-in-nodes/RunwayAleph2PromptImageNode", + "zh/built-in-nodes/RunwayAleph2VideoToVideoNode", "zh/built-in-nodes/RunwayFirstLastFrameNode", "zh/built-in-nodes/RunwayImageToVideoNodeGen3a", "zh/built-in-nodes/RunwayImageToVideoNodeGen4" @@ -4792,35 +4808,14 @@ ] }, { - "group": "\u91c7\u6837", - "pages": [ - { - "group": "\u81ea\u5b9a\u4e49\u91c7\u6837", - "pages": [ - { - "group": "\u91c7\u6837\u5668", - "pages": [ - "zh/built-in-nodes/SamplerDpmpp2mSde", - "zh/built-in-nodes/SamplerDpmppSde" - ] - }, - { - "group": "\u8c03\u5ea6\u5668", - "pages": [ - "zh/built-in-nodes/Ideogram4Scheduler" - ] - }, - "zh/built-in-nodes/CFGOverride" - ] - } - ] - }, - { - "group": "\u6587\u672c", + "group": "Text", "pages": [ "zh/built-in-nodes/AddTextPrefix", "zh/built-in-nodes/AddTextSuffix", + "zh/built-in-nodes/BuildJsonPromptIdeogram", "zh/built-in-nodes/CaseConverter", + "zh/built-in-nodes/ConvertArrayToString", + "zh/built-in-nodes/ConvertDictionaryToString", "zh/built-in-nodes/JsonExtractString", "zh/built-in-nodes/MergeTextLists", "zh/built-in-nodes/RegexExtract", @@ -4844,10 +4839,10 @@ ] }, { - "group": "\u5b9e\u7528\u5de5\u5177", + "group": "Utilities", "pages": [ { - "group": "\u903b\u8f91", + "group": "Logic", "pages": [ "zh/built-in-nodes/AutogrowNamesTestNode", "zh/built-in-nodes/AutogrowPrefixTestNode", @@ -4863,7 +4858,7 @@ ] }, { - "group": "\u57fa\u5143", + "group": "Primitive", "pages": [ "zh/built-in-nodes/PrimitiveBoolean", "zh/built-in-nodes/PrimitiveBoundingBox", @@ -4876,30 +4871,21 @@ "zh/built-in-nodes/ColorToRGBInt", "zh/built-in-nodes/ComfyMathExpression", "zh/built-in-nodes/ComfyNumberConvert", + "zh/built-in-nodes/CreateBoundingBoxes", "zh/built-in-nodes/CreateList", "zh/built-in-nodes/CurveEditor", "zh/built-in-nodes/CustomCombo", "zh/built-in-nodes/ImageHistogram", "zh/built-in-nodes/PreviewAny", - "zh/built-in-nodes/ResolutionSelector" - ] - }, - { - "group": "\u5b9e\u7528\u5de5\u5177", - "pages": [ - "zh/built-in-nodes/BatchImagesMasksLatentsNode", - "zh/built-in-nodes/MarkdownNote", - "zh/built-in-nodes/Note", - "zh/built-in-nodes/Reroute", - "zh/built-in-nodes/TerminalLog", - "zh/built-in-nodes/wanBlockSwap" + "zh/built-in-nodes/ResolutionSelector", + "zh/built-in-nodes/SeedNode" ] }, { - "group": "\u89c6\u9891", + "group": "Video", "pages": [ { - "group": "\u9884\u5904\u7406\u5668", + "group": "Preprocessors", "pages": [ "zh/built-in-nodes/LTXVPreprocess" ] @@ -4912,1560 +4898,1538 @@ "zh/built-in-nodes/SaveWEBM", "zh/built-in-nodes/Video Slice" ] - } - ] - } - ] - }, - { - "tab": "\u5f00\u53d1", - "pages": [ - "zh/development/overview", - { - "group": "ComfyUI APIs", - "icon": "computer", - "pages": [ - "zh/development/api-development/overview", - { - "group": "Cloud API", - "icon": "cloud", - "pages": [ - "zh/development/cloud/overview", - "zh/development/cloud/api-reference", - "zh/development/cloud/openapi" - ] - }, - { - "group": "ComfyUI Server API", - "icon": "server", - "pages": [ - "zh/development/comfyui-server/comms_overview", - "zh/development/comfyui-server/startup-flags", - "zh/development/comfyui-server/comms_routes", - "zh/development/comfyui-server/api-examples", - "zh/development/comfyui-server/comms_messages", - "zh/development/comfyui-server/execution_model_inversion_guide" - ] - }, - "zh/development/comfyui-server/api-key-integration", - "zh/development/api-development/workflow-api-format", - "zh/development/api-development/getting-an-api-key" - ] - }, - { - "group": "CLI", - "pages": [ - "zh/comfy-cli/getting-started", - "zh/comfy-cli/reference", - "zh/comfy-cli/troubleshooting" - ] - }, - { - "group": "\u5f00\u53d1\u81ea\u5b9a\u4e49\u8282\u70b9", - "pages": [ - "zh/custom-nodes/overview", - "zh/custom-nodes/walkthrough", - { - "group": "\u540e\u7aef", - "icon": "python", - "pages": [ - "zh/custom-nodes/backend/server_overview", - "zh/custom-nodes/backend/lifecycle", - "zh/custom-nodes/backend/datatypes", - "zh/custom-nodes/backend/images_and_masks", - "zh/custom-nodes/backend/more_on_inputs", - "zh/custom-nodes/backend/lazy_evaluation", - "zh/custom-nodes/backend/expansion", - "zh/custom-nodes/backend/lists", - "zh/custom-nodes/backend/snippets", - "zh/custom-nodes/backend/tensors", - "zh/custom-nodes/backend/node-replacement" - ] - }, - { - "group": "UI", - "icon": "js", - "pages": [ - "zh/custom-nodes/js/javascript_overview", - "zh/custom-nodes/js/javascript_hooks", - "zh/custom-nodes/js/javascript_objects_and_hijacking", - "zh/custom-nodes/js/javascript_settings", - "zh/custom-nodes/js/javascript_dialog", - "zh/custom-nodes/js/javascript_toast", - "zh/custom-nodes/js/javascript_about_panel_badges", - "zh/custom-nodes/js/javascript_bottom_panel_tabs", - "zh/custom-nodes/js/javascript_sidebar_tabs", - "zh/custom-nodes/js/javascript_selection_toolbox", - "zh/custom-nodes/js/javascript_commands_keybindings", - "zh/custom-nodes/js/javascript_topbar_menu", - "zh/custom-nodes/js/context-menu-migration", - "zh/custom-nodes/js/subgraphs", - "zh/custom-nodes/js/javascript_examples", - "zh/custom-nodes/i18n" - ] - }, - "zh/custom-nodes/v3_migration", - "zh/custom-nodes/help_page", - "zh/custom-nodes/workflow_templates", - "zh/custom-nodes/subgraph_blueprints" - ] - }, - { - "group": "\u6ce8\u518c\u8868(Registry)", - "pages": [ - "zh/registry/overview", - "zh/registry/publishing", - "zh/registry/claim-my-node", - "zh/registry/standards", - "zh/registry/cicd", - "zh/registry/specifications", - "zh/registry/api-reference/overview" - ] - }, - { - "group": "\u89c4\u8303", - "pages": [ - { - "group": "Workflow JSON", - "pages": [ - "zh/specs/workflow_json", - "zh/specs/workflow_json_0.4" - ] }, { - "group": "\u8282\u70b9\u5b9a\u4e49", - "pages": [ - "zh/specs/nodedef_json", - "zh/specs/nodedef_json_1_0" - ] - } - ] - } - ] - }, - { - "tab": "\u652f\u6301", - "pages": [ - "zh/support/contact-support", - "zh/support/data-retention", - { - "group": "\u8d26\u6237\u7ba1\u7406", - "icon": "user", - "pages": [ - "zh/account/create-account", - "zh/account/login", - "zh/account/delete-account" - ] - }, - { - "group": "\u8d26\u5355\u652f\u6301", - "pages": [ - { - "group": "\u8ba2\u9605", + "group": "加载器", "pages": [ - "zh/support/subscription/subscribing", - "zh/support/subscription/managing", - "zh/support/subscription/changing-plan", - "zh/support/subscription/canceling" + "zh/built-in-nodes/ControlNetLoader" ] }, { - "group": "\u652f\u4ed8", - "pages": [ - "zh/support/payment/accepted-payment-methods", - "zh/support/payment/editing-payment-information", - "zh/support/payment/payment-history", - "zh/support/payment/unsuccessful-payments", - "zh/support/payment/payment-currency", - "zh/support/payment/invoice-information" - ] - } - ] - }, - { - "group": "\u6545\u969c\u6392\u9664", - "icon": "bug", - "pages": [ - "zh/troubleshooting/overview", - "zh/troubleshooting/model-issues", - "zh/troubleshooting/custom-node-issues" - ] - }, - { - "group": "\u793e\u533a", - "pages": [ - "zh/community/contributing", - "zh/community/links" - ] - } - ] - }, - { - "tab": "Registry API Reference", - "openapi": "https://api.comfy.org/openapi" - }, - { - "tab": "Cloud API \u53c2\u8003\u6587\u6863", - "openapi": { - "source": "openapi-cloud.yaml", - "directory": "zh/api-reference/cloud" - } - } - ] - }, - { - "language": "ja", - "tabs": [ - { - "tab": "\u306f\u3058\u3081\u306b", - "pages": [ - { - "group": "\u306f\u3058\u3081\u306b", - "pages": [ - "ja/index", - { - "group": "\u30ed\u30fc\u30ab\u30eb (\u30bb\u30eb\u30d5\u30db\u30b9\u30c6\u30c3\u30c9)", - "icon": "download", + "group": "图像", "pages": [ - "ja/installation/system_requirements", { - "group": "Comfy Desktop", + "group": "Adjustments", "pages": [ - "ja/installation/desktop/overview", - { - "group": "\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb", - "pages": [ - "ja/installation/desktop/windows", - "ja/installation/desktop/macos", - "ja/installation/desktop/linux" - ] - }, - { - "group": "\u4f7f\u3044\u65b9\u30ac\u30a4\u30c9", - "pages": [ - "ja/installation/desktop/usage/overview", - "ja/installation/desktop/usage/instance-management", - "ja/installation/desktop/usage/snapshots", - "ja/installation/desktop/usage/manage", - "ja/installation/desktop/usage/settings", - "ja/installation/desktop/usage/migrate" - ] - }, - "ja/installation/desktop/faq" + "zh/built-in-nodes/AdjustBrightness", + "zh/built-in-nodes/AdjustContrast" ] }, - "ja/installation/comfyui_portable_windows", - "ja/installation/manual_install", - "ja/installation/update_comfyui" - ] - }, - "ja/get_started/cloud", - { - "group": "\u30ab\u30b9\u30bf\u30e0\u30ce\u30fc\u30c9\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb", - "icon": "puzzle-piece", - "pages": [ - "ja/installation/install_custom_node", - { - "group": "ComfyUI-Manager", - "pages": [ - "ja/manager/overview", - "ja/manager/install", - { - "group": "\u30ab\u30b9\u30bf\u30e0\u30ce\u30fc\u30c9\u7ba1\u7406", - "pages": [ - "ja/manager/pack-management", - "ja/manager/legacy-ui" - ] - }, - "ja/manager/configuration", - "ja/manager/troubleshooting" - ] - } - ] - }, - "ja/get_started/first_generation" - ] - }, - { - "group": "Agent Tools / MCP", - "icon": "robot", - "pages": [ - "ja/agent-tools/index", - "ja/agent-tools/cloud", - "ja/agent-tools/partner-mcp", - "ja/agent-tools/comfy-cli" - ] - }, - { - "group": "\u57fa\u672c\u6982\u5ff5", - "pages": [ - "ja/development/core-concepts/workflow", - "ja/development/core-concepts/nodes", - "ja/development/core-concepts/custom-nodes", - "ja/development/core-concepts/properties", - "ja/development/core-concepts/links", - "ja/development/core-concepts/models", - "ja/development/core-concepts/dependencies" - ] - }, - { - "group": "\u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30fc\u30b9\u30ac\u30a4\u30c9", - "pages": [ - "ja/interface/overview", - "ja/interface/app-mode", - "ja/interface/nodes-2", - "ja/interface/maskeditor", - "ja/interface/features/template", - "ja/interface/features/subgraph", - "ja/interface/features/partial-execution", - "ja/interface/features/node-docs", - { - "group": "ComfyUI Settings", - "icon": "gear", - "pages": [ - "ja/interface/settings/overview", - "ja/interface/user", - "ja/interface/credits", - "ja/interface/settings/comfy", - "ja/interface/settings/lite-graph", - "ja/interface/appearance", - "ja/interface/settings/3d", - "ja/interface/settings/mask-editor", - "ja/interface/shortcuts", - "ja/interface/settings/extension", - "ja/interface/settings/about" - ] - }, - { - "group": "Cloud \u5c02\u7528\u6a5f\u80fd", - "icon": "cloud", - "pages": [ - "ja/cloud/share-workflow", - "ja/cloud/import-models" - ] - } - ] - }, - { - "group": "\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb", - "icon": "book", - "pages": [ - { - "group": "\u57fa\u672c\u4f8b", - "pages": [ - "ja/tutorials/basic/text-to-image", - "ja/tutorials/basic/image-to-image", - "ja/tutorials/basic/inpaint", - "ja/tutorials/basic/outpaint", - "ja/tutorials/basic/upscale", - "ja/tutorials/basic/lora", - "ja/tutorials/basic/multiple-loras" - ] - }, - { - "group": "ControlNet", - "pages": [ - "ja/tutorials/controlnet/controlnet", - "ja/tutorials/controlnet/pose-controlnet-2-pass", - "ja/tutorials/controlnet/depth-controlnet", - "ja/tutorials/controlnet/depth-t2i-adapter", - "ja/tutorials/controlnet/mixing-controlnets" - ] - }, - { - "group": "\u753b\u50cf", - "pages": [ { - "group": "Flux", + "group": "Background Removal", "pages": [ - "ja/tutorials/flux/flux-2-dev", - "ja/tutorials/flux/flux-2-klein", - "ja/tutorials/flux/flux1-krea-dev", - "ja/tutorials/flux/flux-1-kontext-dev", - "ja/tutorials/flux/flux-1-text-to-image", - "ja/tutorials/flux/flux-1-uso", - "ja/tutorials/flux/flux-1-fill-dev", - "ja/tutorials/flux/flux-1-controlnet" + "zh/built-in-nodes/RemoveBackground" ] }, { - "group": "Qwen", + "group": "Batch", "pages": [ - "ja/tutorials/image/qwen/qwen-image", - "ja/tutorials/image/qwen/qwen-image-2512", - "ja/tutorials/image/qwen/qwen-image-edit", - "ja/tutorials/image/qwen/qwen-image-edit-2511", - "ja/tutorials/image/qwen/qwen-image-layered" + "zh/built-in-nodes/ImageDeduplication", + "zh/built-in-nodes/ImageFromBatch", + "zh/built-in-nodes/ImageGrid", + "zh/built-in-nodes/ImageMergeTileList", + "zh/built-in-nodes/MergeImageLists", + "zh/built-in-nodes/RebatchImages", + "zh/built-in-nodes/RepeatImageBatch", + "zh/built-in-nodes/ShuffleDataset", + "zh/built-in-nodes/ShuffleImageTextDataset", + "zh/built-in-nodes/SplitImageToTileList" ] }, { - "group": "Z-Image", + "group": "Color", "pages": [ - "ja/tutorials/image/z-image/z-image", - "ja/tutorials/image/z-image/z-image-turbo" + "zh/built-in-nodes/ImageRGBToYUV", + "zh/built-in-nodes/ImageYUVToRGB", + "zh/built-in-nodes/NormalizeImages" ] }, { - "group": "Boogu", + "group": "Compositing", "pages": [ - "ja/tutorials/image/boogu/boogu-image-0.1" + "zh/built-in-nodes/ImageCompositeMasked", + "zh/built-in-nodes/JoinImageWithAlpha", + "zh/built-in-nodes/PorterDuffImageComposite", + "zh/built-in-nodes/SplitImageWithAlpha" ] }, { - "group": "HiDream", + "group": "Detection", "pages": [ - "ja/tutorials/image/hidream/hidream-i1", - "ja/tutorials/image/hidream/hidream-e1", - "ja/tutorials/image/hidream/hidream-o1" + "zh/built-in-nodes/DrawBBoxes", + "zh/built-in-nodes/MediaPipeFaceLandmarker", + "zh/built-in-nodes/MediaPipeFaceMask", + "zh/built-in-nodes/MediaPipeFaceMeshVisualize", + "zh/built-in-nodes/RTDETR_detect", + "zh/built-in-nodes/SAM3_Detect", + "zh/built-in-nodes/SAM3_TrackPreview", + "zh/built-in-nodes/SAM3_TrackToMask", + "zh/built-in-nodes/SAM3_VideoTrack", + "zh/built-in-nodes/SDPoseDrawKeypoints", + "zh/built-in-nodes/SDPoseFaceBBoxes", + "zh/built-in-nodes/SDPoseKeypointExtractor" ] }, { - "group": "Ovis", + "group": "Filters", "pages": [ - "ja/tutorials/image/ovis/ovis-image" + "zh/built-in-nodes/Canny", + "zh/built-in-nodes/ColorTransfer", + "zh/built-in-nodes/ImageAddNoise", + "zh/built-in-nodes/ImageBlend", + "zh/built-in-nodes/ImageBlur", + "zh/built-in-nodes/ImageQuantize", + "zh/built-in-nodes/ImageSharpen", + "zh/built-in-nodes/Morphology" ] }, { - "group": "NewBie-image", + "group": "Geometry Estimation", "pages": [ - "ja/tutorials/image/newbie-image/newbie-image-exp-0-1" + "zh/built-in-nodes/DA3GeometryToMesh", + "zh/built-in-nodes/DA3GeometryToPointCloud", + "zh/built-in-nodes/DA3Inference", + "zh/built-in-nodes/DA3Render", + "zh/built-in-nodes/MoGeInference", + "zh/built-in-nodes/MoGePanoramaInference", + "zh/built-in-nodes/MoGePointMapToMesh", + "zh/built-in-nodes/MoGeRender" ] }, { - "group": "ERNIE-Image", + "group": "Mask", "pages": [ - "ja/tutorials/image/ernie-image/ernie-image" + "zh/built-in-nodes/BatchMasksNode", + "zh/built-in-nodes/CropMask", + "zh/built-in-nodes/FeatherMask", + "zh/built-in-nodes/GrowMask", + "zh/built-in-nodes/ImageColorToMask", + "zh/built-in-nodes/ImageToMask", + "zh/built-in-nodes/InvertMask", + "zh/built-in-nodes/MaskComposite", + "zh/built-in-nodes/MaskPreview", + "zh/built-in-nodes/MaskToImage", + "zh/built-in-nodes/SolidMask", + "zh/built-in-nodes/ThresholdMask", + "zh/built-in-nodes/VOIDQuadmaskPreprocess" ] }, { - "group": "Anima", + "group": "Shader", "pages": [ - "ja/tutorials/image/anima/anima" + "zh/built-in-nodes/GLSLShader" ] }, { - "group": "\u30ec\u30f3\u30ba", + "group": "Transform", "pages": [ - "ja/tutorials/image/lens/lens" + "zh/built-in-nodes/CenterCropImages", + "zh/built-in-nodes/CropByBBoxes", + "zh/built-in-nodes/ImageCrop", + "zh/built-in-nodes/ImageCropV2", + "zh/built-in-nodes/ImageFlip", + "zh/built-in-nodes/ImagePadForOutpaint", + "zh/built-in-nodes/ImageRotate", + "zh/built-in-nodes/ImageStitch", + "zh/built-in-nodes/RandomCropImages", + "zh/built-in-nodes/ResizeAndPadImage", + "zh/built-in-nodes/ResizeImagesByLongerEdge", + "zh/built-in-nodes/ResizeImagesByShorterEdge" ] }, { - "group": "PixelDiT", + "group": "Upscaling", "pages": [ - "ja/tutorials/image/pixeldit/pixeldit" + "zh/built-in-nodes/ImageScale", + "zh/built-in-nodes/ImageScaleBy", + "zh/built-in-nodes/ImageScaleToMaxDimension", + "zh/built-in-nodes/ImageScaleToTotalPixels", + "zh/built-in-nodes/ImageUpscaleWithModel" ] }, { - "group": "Krea 2", + "group": "Video", "pages": [ - "ja/tutorials/image/krea/krea-2" + "zh/built-in-nodes/WanDancerPadKeyframes", + "zh/built-in-nodes/WanDancerPadKeyframesList" ] }, - { - "group": "Ideogram", - "pages": [ - "ja/tutorials/image/ideogram/ideogram-v4" - ] - }, - "ja/tutorials/image/cosmos/cosmos-predict2-t2i", - "ja/tutorials/image/omnigen/omnigen2" + "zh/built-in-nodes/BatchImagesNode", + "zh/built-in-nodes/ConditioningCombine", + "zh/built-in-nodes/EmptyImage", + "zh/built-in-nodes/GetImageSize", + "zh/built-in-nodes/ImageBatch", + "zh/built-in-nodes/ImageCompare", + "zh/built-in-nodes/ImageInvert", + "zh/built-in-nodes/LoadImage", + "zh/built-in-nodes/LoadImageDataSetFromFolder", + "zh/built-in-nodes/LoadImageMask", + "zh/built-in-nodes/LoadImageOutput", + "zh/built-in-nodes/LoadImageSetFromFolderNode", + "zh/built-in-nodes/LoadImageSetNode", + "zh/built-in-nodes/LoadImageTextDataSetFromFolder", + "zh/built-in-nodes/LoadImageTextSetFromFolderNode", + "zh/built-in-nodes/LoraLoader", + "zh/built-in-nodes/LoraLoaderModelOnly", + "zh/built-in-nodes/Painter", + "zh/built-in-nodes/PreviewImage", + "zh/built-in-nodes/ResizeImageMaskNode", + "zh/built-in-nodes/SaveAnimatedPNG", + "zh/built-in-nodes/SaveAnimatedWEBP", + "zh/built-in-nodes/SaveImage", + "zh/built-in-nodes/SaveImageAdvanced", + "zh/built-in-nodes/SaveImageDataSetToFolder", + "zh/built-in-nodes/SaveImageTextDataSetToFolder", + "zh/built-in-nodes/SaveSVGNode", + "zh/built-in-nodes/WebcamCapture" ] }, { - "group": "3D", + "group": "实用工具", "pages": [ - "ja/tutorials/3d/triposplat", - "ja/tutorials/3d/hunyuan3D-2" + "zh/built-in-nodes/BatchImagesMasksLatentsNode", + "zh/built-in-nodes/MarkdownNote", + "zh/built-in-nodes/Note", + "zh/built-in-nodes/Reroute", + "zh/built-in-nodes/TerminalLog", + "zh/built-in-nodes/wanBlockSwap" ] }, { - "group": "LLM", + "group": "条件", "pages": [ - "ja/tutorials/llm/gemma4/gemma4", - "ja/tutorials/llm/qwen/qwen3", - "ja/tutorials/llm/qwen/qwen3_5" + { + "group": "Video Models", + "pages": [ + "zh/built-in-nodes/conditioning/video-models/wan-vace-to-video", + "zh/built-in-nodes/Stablezero123Conditioning", + "zh/built-in-nodes/Stablezero123ConditioningBatched", + "zh/built-in-nodes/SVD_img2vid_Conditioning", + "zh/built-in-nodes/SvdImg2vidConditioning" + ] + }, + "zh/built-in-nodes/ConditioningAverage", + "zh/built-in-nodes/Sd4xupscaleConditioning" ] }, { - "group": "\u30d3\u30c7\u30aa", + "group": "潜变量", "pages": [ { - "group": "LTX", + "group": "Video", "pages": [ - "ja/tutorials/video/ltxv", - "ja/tutorials/video/ltx/ltx-2", - "ja/tutorials/video/ltx/ltx-2-3" + "zh/built-in-nodes/latent/video/trim-video-latent" ] - }, + } + ] + }, + { + "group": "采样", + "pages": [ { - "group": "Wan Video", + "group": "Custom Sampling", "pages": [ - "ja/tutorials/video/wan/wan2_2", - "ja/tutorials/video/wan/wan2-2-animate", - "ja/tutorials/video/wan/wan2-2-s2v", - "ja/tutorials/video/wan/wan2-2-fun-inp", - "ja/tutorials/video/wan/wan2-2-fun-control", - "ja/tutorials/video/wan/wan2-2-fun-camera", { - "group": "Wan2.1", + "group": "Samplers", "pages": [ - "ja/tutorials/video/wan/wan-video", - "ja/tutorials/video/wan/vace", - "ja/tutorials/video/wan/wan-move", - "ja/tutorials/video/wan/wan-alpha", - "ja/tutorials/video/wan/wan-ati", - "ja/tutorials/video/wan/fun-control", - "ja/tutorials/video/wan/fun-camera", - "ja/tutorials/video/wan/fun-inp", - "ja/tutorials/video/wan/wan-flf" + "zh/built-in-nodes/SamplerDpmpp2mSde", + "zh/built-in-nodes/SamplerDpmppSde" ] } ] - }, - { - "group": "ByteDance", - "pages": [ - "ja/tutorials/video/bytedance/bernini-r" - ] - }, + } + ] + }, + { + "group": "高级", + "pages": [ { - "group": "Hunyuan", + "group": "Debug", "pages": [ - "ja/tutorials/video/hunyuan/hunyuan-video", - "ja/tutorials/video/hunyuan/hunyuan-video-1-5" + "zh/built-in-nodes/EasyCache", + "zh/built-in-nodes/LazyCache", + "zh/built-in-nodes/ModelComputeDtype" ] }, { - "group": "Cosmos", + "group": "Guidance", "pages": [ - "ja/tutorials/video/cosmos/cosmos-predict2-video2world" + "zh/built-in-nodes/CFGNorm", + "zh/built-in-nodes/CFGZeroStar", + "zh/built-in-nodes/NAGuidance", + "zh/built-in-nodes/SkipLayerGuidanceDiT", + "zh/built-in-nodes/SkipLayerGuidanceDiTSimple", + "zh/built-in-nodes/SkipLayerGuidanceSD3", + "zh/built-in-nodes/TCFG" ] }, { - "group": "Kandinsky", + "group": "Hooks", "pages": [ - "ja/tutorials/video/kandinsky/kandinsky-5" + { + "group": "Clip", + "pages": [ + "zh/built-in-nodes/SetClipHooks" + ] + }, + { + "group": "Combine", + "pages": [ + "zh/built-in-nodes/CombineHooks", + "zh/built-in-nodes/CombineHooksEight", + "zh/built-in-nodes/CombineHooksFour" + ] + }, + { + "group": "Cond Pair", + "pages": [ + "zh/built-in-nodes/PairConditioningCombine", + "zh/built-in-nodes/PairConditioningSetDefaultAndCombine", + "zh/built-in-nodes/PairConditioningSetProperties", + "zh/built-in-nodes/PairConditioningSetPropertiesAndCombine" + ] + }, + { + "group": "Cond Single", + "pages": [ + "zh/built-in-nodes/ConditioningSetDefaultAndCombine", + "zh/built-in-nodes/ConditioningSetProperties", + "zh/built-in-nodes/ConditioningSetPropertiesAndCombine" + ] + }, + { + "group": "Create", + "pages": [ + "zh/built-in-nodes/CreateHookLora", + "zh/built-in-nodes/CreateHookLoraModelOnly", + "zh/built-in-nodes/CreateHookModelAsLora", + "zh/built-in-nodes/CreateHookModelAsLoraModelOnly" + ] + }, + { + "group": "Manual", + "pages": [ + "zh/built-in-nodes/SetModelHooksOnCond" + ] + }, + { + "group": "Scheduling", + "pages": [ + "zh/built-in-nodes/CreateHookKeyframe", + "zh/built-in-nodes/CreateHookKeyframesFromFloats", + "zh/built-in-nodes/CreateHookKeyframesInterpolated", + "zh/built-in-nodes/SetHookKeyframes" + ] + }, + "zh/built-in-nodes/ConditioningTimestepsRange" ] }, { - "group": "ZAI", + "group": "Loaders", "pages": [ - "ja/tutorials/video/zai/scail2" + "zh/built-in-nodes/DeprecatedCheckpointLoader", + "zh/built-in-nodes/DeprecatedDiffusersLoader" ] }, - "ja/tutorials/video/bytedance/bernini-r" - ] - }, - { - "group": "\u30aa\u30fc\u30c7\u30a3\u30aa", - "pages": [ { - "group": "Stable Audio 1.0", + "group": "Model Merging", "pages": [ - "ja/tutorials/audio/stable-audio/stable-audio-1" + "zh/built-in-nodes/SaveLoRANode" ] }, { - "group": "Stable Audio 3", + "group": "Multigpu", "pages": [ - "ja/tutorials/audio/stable-audio/stable-audio-3" + "zh/built-in-nodes/MultiGPU_Options", + "zh/built-in-nodes/MultiGPU_WorkUnits", + "zh/built-in-nodes/SelectCLIPDevice", + "zh/built-in-nodes/SelectModelDevice", + "zh/built-in-nodes/SelectVAEDevice" ] }, - { - "group": "ACE-Step", - "pages": [ - "ja/tutorials/audio/ace-step/ace-step-v1", - "ja/tutorials/audio/ace-step/ace-step-v1-5" - ] - } - ] - }, - { - "group": "\u30e6\u30fc\u30c6\u30a3\u30ea\u30c6\u30a3", - "pages": [ - "ja/tutorials/utility/preprocessors", - "ja/tutorials/utility/frame-interpolation", - "ja/tutorials/utility/image-upscale", - "ja/tutorials/utility/video-upscale", - "ja/tutorials/utility/void-video-inpainting", - "ja/tutorials/utility/video-segment-sam3", - "ja/tutorials/utility/remove-background-birefnet", - "ja/tutorials/utility/pose-detection-sdpose", - "ja/tutorials/utility/moge", - "ja/tutorials/utility/depth-anything-3", - { - "group": "\u9854\u691c\u51fa", - "pages": [ - "ja/tutorials/utility/face-detection/mediapipe" - ] - } + "zh/built-in-nodes/IdeogramV1", + "zh/built-in-nodes/IdeogramV2", + "zh/built-in-nodes/MoonvalleyImg2VideoNode", + "zh/built-in-nodes/MoonvalleyTxt2VideoNode", + "zh/built-in-nodes/MoonvalleyVideo2VideoNode", + "zh/built-in-nodes/SeedVR2Conditioning", + "zh/built-in-nodes/SeedVR2PostProcessing", + "zh/built-in-nodes/SeedVR2Preprocess", + "zh/built-in-nodes/SeedVR2ProgressiveSampler", + "zh/built-in-nodes/StabilityAudioInpaint", + "zh/built-in-nodes/StabilityAudioToAudio", + "zh/built-in-nodes/StabilityStableImageSD_3_5Node", + "zh/built-in-nodes/StabilityStableImageUltraNode", + "zh/built-in-nodes/StabilityTextToAudio", + "zh/built-in-nodes/StabilityUpscaleConservativeNode", + "zh/built-in-nodes/StabilityUpscaleCreativeNode", + "zh/built-in-nodes/StabilityUpscaleFastNode" ] } ] - }, + } + ] + }, + { + "tab": "开发", + "pages": [ + "zh/development/overview", { - "group": "\u30d1\u30fc\u30c8\u30ca\u30fc\u30ce\u30fc\u30c9", - "icon": "handshake", + "group": "ComfyUI APIs", + "icon": "computer", "pages": [ - "ja/tutorials/partner-nodes/overview", - "ja/tutorials/partner-nodes/faq", - "ja/tutorials/partner-nodes/pricing", - "ja/tutorials/partner-nodes/concurrency-limits", + "zh/development/api-development/overview", { - "group": "Black Forest Labs", + "group": "Cloud API", + "icon": "cloud", "pages": [ - "ja/tutorials/partner-nodes/black-forest-labs/flux-1-1-pro-ultra-image", - "ja/tutorials/partner-nodes/black-forest-labs/flux-1-kontext" + "zh/development/cloud/overview", + "zh/development/cloud/api-reference", + "zh/development/cloud/openapi" ] }, { - "group": "Beeble", + "group": "ComfyUI Server API", + "icon": "server", "pages": [ - "ja/tutorials/partner-nodes/beeble/beeble-switchx" - ] - }, - { - "group": "ByteDance", - "pages": [ - "ja/tutorials/partner-nodes/bytedance/seedance-2-0", - "ja/tutorials/partner-nodes/bytedance/seedance-2-0-real-human", - "ja/tutorials/partner-nodes/bytedance/seedream-5-lite" - ] - }, - { - "group": "Google", - "pages": [ - "ja/tutorials/partner-nodes/google/gemini", - "ja/tutorials/partner-nodes/google/gemini-omni-flash", - "ja/tutorials/partner-nodes/google/nano-banana-pro", - "ja/tutorials/partner-nodes/google/nano-banana-2", - "ja/tutorials/partner-nodes/google/nano-banana-2-lite" - ] - }, - { - "group": "Anthropic", - "pages": [ - "ja/tutorials/partner-nodes/anthropic/claude" - ] - }, - { - "group": "Ideogram", - "pages": [ - "ja/tutorials/partner-nodes/ideogram/ideogram-v4" + "zh/development/comfyui-server/comms_overview", + "zh/development/comfyui-server/startup-flags", + "zh/development/comfyui-server/comms_routes", + "zh/development/comfyui-server/api-examples", + "zh/development/comfyui-server/comms_messages", + "zh/development/comfyui-server/execution_model_inversion_guide" ] }, + "zh/development/comfyui-server/api-key-integration", + "zh/development/api-development/workflow-api-format", + "zh/development/api-development/getting-an-api-key" + ] + }, + { + "group": "CLI", + "pages": [ + "zh/comfy-cli/getting-started", + "zh/comfy-cli/reference", + "zh/comfy-cli/troubleshooting" + ] + }, + { + "group": "开发自定义节点", + "pages": [ + "zh/custom-nodes/overview", + "zh/custom-nodes/walkthrough", { - "group": "Luma", + "group": "后端", + "icon": "python", "pages": [ - "ja/tutorials/partner-nodes/luma/luma-uni-1", - "ja/tutorials/partner-nodes/luma/luma-text-to-image", - "ja/tutorials/partner-nodes/luma/luma-image-to-image", - "ja/tutorials/partner-nodes/luma/luma-text-to-video", - "ja/tutorials/partner-nodes/luma/luma-image-to-video" + "zh/custom-nodes/backend/server_overview", + "zh/custom-nodes/backend/lifecycle", + "zh/custom-nodes/backend/datatypes", + "zh/custom-nodes/backend/images_and_masks", + "zh/custom-nodes/backend/more_on_inputs", + "zh/custom-nodes/backend/lazy_evaluation", + "zh/custom-nodes/backend/expansion", + "zh/custom-nodes/backend/lists", + "zh/custom-nodes/backend/snippets", + "zh/custom-nodes/backend/tensors", + "zh/custom-nodes/backend/node-replacement" ] }, { - "group": "Moonvalley", + "group": "UI", + "icon": "js", "pages": [ - "ja/tutorials/partner-nodes/moonvalley/moonvalley-video-generation" + "zh/custom-nodes/js/javascript_overview", + "zh/custom-nodes/js/javascript_hooks", + "zh/custom-nodes/js/javascript_objects_and_hijacking", + "zh/custom-nodes/js/javascript_settings", + "zh/custom-nodes/js/javascript_dialog", + "zh/custom-nodes/js/javascript_toast", + "zh/custom-nodes/js/javascript_about_panel_badges", + "zh/custom-nodes/js/javascript_bottom_panel_tabs", + "zh/custom-nodes/js/javascript_sidebar_tabs", + "zh/custom-nodes/js/javascript_selection_toolbox", + "zh/custom-nodes/js/javascript_commands_keybindings", + "zh/custom-nodes/js/javascript_topbar_menu", + "zh/custom-nodes/js/context-menu-migration", + "zh/custom-nodes/js/subgraphs", + "zh/custom-nodes/js/javascript_examples", + "zh/custom-nodes/i18n" ] }, + "zh/custom-nodes/v3_migration", + "zh/custom-nodes/help_page", + "zh/custom-nodes/workflow_templates", + "zh/custom-nodes/subgraph_blueprints" + ] + }, + { + "group": "注册表(Registry)", + "pages": [ + "zh/registry/overview", + "zh/registry/publishing", + "zh/registry/claim-my-node", + "zh/registry/standards", + "zh/registry/cicd", + "zh/registry/specifications", + "zh/registry/api-reference/overview" + ] + }, + { + "group": "规范", + "pages": [ { - "group": "OpenAI", + "group": "Workflow JSON", "pages": [ - "ja/tutorials/partner-nodes/openai/gpt-image-2", - "ja/tutorials/partner-nodes/openai/gpt-image-1", - "ja/tutorials/partner-nodes/openai/dall-e-2", - "ja/tutorials/partner-nodes/openai/dall-e-3", - "ja/tutorials/partner-nodes/openai/chat" + "zh/specs/workflow_json", + "zh/specs/workflow_json_0.4" ] }, { - "group": "OpenRouter", + "group": "节点定义", "pages": [ - "ja/tutorials/partner-nodes/openrouter/llm" + "zh/specs/nodedef_json", + "zh/specs/nodedef_json_1_0" ] - }, + } + ] + } + ] + }, + { + "tab": "支持", + "pages": [ + "zh/support/contact-support", + "zh/support/data-retention", + { + "group": "账户管理", + "icon": "user", + "pages": [ + "zh/account/create-account", + "zh/account/login", + "zh/account/delete-account" + ] + }, + { + "group": "账单支持", + "pages": [ { - "group": "Recraft", + "group": "订阅", "pages": [ - "ja/tutorials/partner-nodes/recraft/recraft-v4", - "ja/tutorials/partner-nodes/recraft/recraft-text-to-image" + "zh/support/subscription/subscribing", + "zh/support/subscription/managing", + "zh/support/subscription/changing-plan", + "zh/support/subscription/canceling" ] }, { - "group": "Krea 2", + "group": "支付", "pages": [ - "ja/tutorials/partner-nodes/krea2/krea2-t2i" + "zh/support/payment/accepted-payment-methods", + "zh/support/payment/editing-payment-information", + "zh/support/payment/payment-history", + "zh/support/payment/unsuccessful-payments", + "zh/support/payment/payment-currency", + "zh/support/payment/invoice-information" ] - }, + } + ] + }, + { + "group": "故障排除", + "icon": "bug", + "pages": [ + "zh/troubleshooting/overview", + "zh/troubleshooting/model-issues", + "zh/troubleshooting/custom-node-issues" + ] + }, + { + "group": "社区", + "pages": [ + "zh/community/contributing", + "zh/community/links" + ] + } + ] + }, + { + "tab": "Registry API Reference", + "openapi": "https://api.comfy.org/openapi" + }, + { + "tab": "Cloud API 参考文档", + "openapi": { + "source": "openapi-cloud.yaml", + "directory": "zh/api-reference/cloud" + } + } + ] + }, + { + "language": "ja", + "tabs": [ + { + "tab": "はじめに", + "pages": [ + { + "group": "はじめに", + "pages": [ + "ja/index", { - "group": "Kling", + "group": "ローカル (セルフホステッド)", + "icon": "download", "pages": [ - "ja/tutorials/partner-nodes/kling/kling-3-0", - "ja/tutorials/partner-nodes/kling/kling-motion-control" + "ja/installation/system_requirements", + { + "group": "Comfy Desktop", + "pages": [ + "ja/installation/desktop/overview", + { + "group": "インストール", + "pages": [ + "ja/installation/desktop/windows", + "ja/installation/desktop/macos", + "ja/installation/desktop/linux" + ] + }, + { + "group": "使い方ガイド", + "pages": [ + "ja/installation/desktop/usage/overview", + "ja/installation/desktop/usage/instance-management", + "ja/installation/desktop/usage/snapshots", + "ja/installation/desktop/usage/manage", + "ja/installation/desktop/usage/settings", + "ja/installation/desktop/usage/migrate" + ] + }, + "ja/installation/desktop/faq" + ] + }, + "ja/installation/comfyui_portable_windows", + "ja/installation/manual_install", + "ja/installation/update_comfyui" ] }, + "ja/get_started/cloud", { - "group": "Runway", + "group": "カスタムノードのインストール", + "icon": "puzzle-piece", "pages": [ - "ja/tutorials/partner-nodes/runway/image-generation", - "ja/tutorials/partner-nodes/runway/video-generation" - ] - }, - { - "group": "Rodin", - "pages": [ - "ja/tutorials/partner-nodes/rodin/model-generation" - ] - }, - { - "group": "Tripo", - "pages": [ - "ja/tutorials/partner-nodes/tripo/model-generation", - "ja/tutorials/partner-nodes/tripo/tripo-3-1" - ] - }, - { - "group": "Hunyuan 3D", - "pages": [ - "ja/tutorials/partner-nodes/hunyuan3d/hunyuan3d-3-0" - ] - }, - { - "group": "Meshy", - "pages": [ - "ja/tutorials/partner-nodes/meshy/meshy-6" - ] - }, - { - "group": "Bria", - "pages": [ - "ja/tutorials/partner-nodes/bria/fibo", - "ja/tutorials/partner-nodes/bria/background-removal" - ] - }, - { - "group": "Reve", - "pages": [ - "ja/tutorials/partner-nodes/reve/reve-image" + "ja/installation/install_custom_node", + { + "group": "ComfyUI-Manager", + "pages": [ + "ja/manager/overview", + "ja/manager/install", + { + "group": "カスタムノード管理", + "pages": [ + "ja/manager/pack-management", + "ja/manager/legacy-ui" + ] + }, + "ja/manager/configuration", + "ja/manager/troubleshooting" + ] + } ] }, + "ja/get_started/first_generation" + ] + }, + { + "group": "Agent Tools / MCP", + "icon": "robot", + "pages": [ + "ja/agent-tools/index", + "ja/agent-tools/cloud", + "ja/agent-tools/partner-mcp", + "ja/agent-tools/comfy-cli" + ] + }, + { + "group": "基本概念", + "pages": [ + "ja/development/core-concepts/workflow", + "ja/development/core-concepts/nodes", + "ja/development/core-concepts/custom-nodes", + "ja/development/core-concepts/properties", + "ja/development/core-concepts/links", + "ja/development/core-concepts/models", + "ja/development/core-concepts/dependencies" + ] + }, + { + "group": "インターフェースガイド", + "pages": [ + "ja/interface/overview", + "ja/interface/app-mode", + "ja/interface/nodes-2", + "ja/interface/maskeditor", + "ja/interface/features/template", + "ja/interface/features/subgraph", + "ja/interface/features/partial-execution", + "ja/interface/features/node-docs", { - "group": "Wan", + "group": "ComfyUI Settings", + "icon": "gear", "pages": [ - "ja/tutorials/partner-nodes/wan/wan2-7" + "ja/interface/settings/overview", + "ja/interface/user", + "ja/interface/credits", + "ja/interface/settings/comfy", + "ja/interface/settings/lite-graph", + "ja/interface/appearance", + "ja/interface/settings/3d", + "ja/interface/settings/mask-editor", + "ja/interface/shortcuts", + "ja/interface/settings/extension", + "ja/interface/settings/about" ] }, { - "group": "HappyHorse", + "group": "Cloud 専用機能", + "icon": "cloud", "pages": [ - "ja/tutorials/partner-nodes/happyhorse/happyhorse1-1", - "ja/tutorials/partner-nodes/happyhorse/happyhorse1-0" + "ja/cloud/share-workflow", + "ja/cloud/import-models" ] - }, + } + ] + }, + { + "group": "チュートリアル", + "icon": "book", + "pages": [ { - "group": "Sonilo", + "group": "基本例", "pages": [ - "ja/tutorials/partner-nodes/sonilo/video-to-music" + "ja/tutorials/basic/text-to-image", + "ja/tutorials/basic/image-to-image", + "ja/tutorials/basic/inpaint", + "ja/tutorials/basic/outpaint", + "ja/tutorials/basic/upscale", + "ja/tutorials/basic/lora", + "ja/tutorials/basic/multiple-loras" ] }, { - "group": "Topaz", + "group": "ControlNet", "pages": [ - "ja/tutorials/partner-nodes/topaz/astra-2" + "ja/tutorials/controlnet/controlnet", + "ja/tutorials/controlnet/pose-controlnet-2-pass", + "ja/tutorials/controlnet/depth-controlnet", + "ja/tutorials/controlnet/depth-t2i-adapter", + "ja/tutorials/controlnet/mixing-controlnets" ] }, { - "group": "Grok", - "pages": [ - "ja/tutorials/partner-nodes/grok/grok-imagine-video-1-5" - ] - } - ] - }, - "ko/changelog/index" - ] - }, - { - "tab": "\u7d44\u307f\u8fbc\u307f\u30ce\u30fc\u30c9", - "pages": [ - "ja/built-in-nodes/overview", - { - "group": "\u30ce\u30fc\u30c9", - "pages": [ - { - "group": "3D", + "group": "画像", "pages": [ { - "group": "\u30b3\u30f3\u30c7\u30a3\u30b7\u30e7\u30cb\u30f3\u30b0", + "group": "Flux", "pages": [ - "ja/built-in-nodes/TripoSplatConditioning", - "ja/built-in-nodes/TripoSplatPreprocessImage" + "ja/tutorials/flux/flux-2-dev", + "ja/tutorials/flux/flux-2-klein", + "ja/tutorials/flux/flux1-krea-dev", + "ja/tutorials/flux/flux-1-kontext-dev", + "ja/tutorials/flux/flux-1-text-to-image", + "ja/tutorials/flux/flux-1-uso", + "ja/tutorials/flux/flux-1-fill-dev", + "ja/tutorials/flux/flux-1-controlnet" ] }, { - "group": "\u6f5c\u5728", + "group": "Qwen", "pages": [ - "ja/built-in-nodes/TripoSplatSamplingPreview", - "ja/built-in-nodes/VAEDecodeTripoSplat" + "ja/tutorials/image/qwen/qwen-image", + "ja/tutorials/image/qwen/qwen-image-2512", + "ja/tutorials/image/qwen/qwen-image-edit", + "ja/tutorials/image/qwen/qwen-image-edit-2511", + "ja/tutorials/image/qwen/qwen-image-layered" ] }, { - "group": "Splat", + "group": "Z-Image", "pages": [ - "ja/built-in-nodes/File3DToSplat", - "ja/built-in-nodes/GetSplatCount", - "ja/built-in-nodes/MergeSplat", - "ja/built-in-nodes/RenderSplat", - "ja/built-in-nodes/SplatToFile3D", - "ja/built-in-nodes/SplatToMesh", - "ja/built-in-nodes/TransformSplat" + "ja/tutorials/image/z-image/z-image", + "ja/tutorials/image/z-image/z-image-turbo" ] }, - "ja/built-in-nodes/CreateCameraInfo", - "ja/built-in-nodes/Load3D", - "ja/built-in-nodes/Load3DAnimation", - "ja/built-in-nodes/Preview3D", - "ja/built-in-nodes/Preview3DAdvanced", - "ja/built-in-nodes/Preview3DAnimation", - "ja/built-in-nodes/SaveGLB", - "ja/built-in-nodes/VoxelToMesh", - "ja/built-in-nodes/VoxelToMeshBasic" - ] - }, - { - "group": "\u8a73\u7d30", - "pages": [ { - "group": "\u30b3\u30f3\u30c7\u30a3\u30b7\u30e7\u30cb\u30f3\u30b0", + "group": "Boogu", "pages": [ - { - "group": "\u30aa\u30fc\u30c7\u30a3\u30aa", - "pages": [ - "ja/built-in-nodes/ReferenceTimbreAudio" - ] - }, - { - "group": "\u30e2\u30c7\u30eb\u7de8\u96c6", - "pages": [ - "ja/built-in-nodes/ReferenceLatent" - ] - }, - { - "group": "Flux", - "pages": [ - "ja/built-in-nodes/ClipTextEncodeFlux", - "ja/built-in-nodes/FluxDisableGuidance", - "ja/built-in-nodes/FluxGuidance", - "ja/built-in-nodes/FluxKontextImageScale", - "ja/built-in-nodes/FluxKontextMultiReferenceLatentMethod" - ] - }, - { - "group": "Kandinsky5", - "pages": [ - "ja/built-in-nodes/CLIPTextEncodeKandinsky5" - ] - }, - "ja/built-in-nodes/CLIPTextEncodeHiDream", - "ja/built-in-nodes/ClipTextEncodeHunyuanDit", - "ja/built-in-nodes/CLIPTextEncodePixArtAlpha", - "ja/built-in-nodes/CLIPTextEncodeSD3", - "ja/built-in-nodes/ClipTextEncodeSdxl", - "ja/built-in-nodes/ClipTextEncodeSdxlRefiner", - "ja/built-in-nodes/ConditioningSetTimestepRange", - "ja/built-in-nodes/ConditioningZeroOut", - "ja/built-in-nodes/PiDConditioning", - "ja/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo", - "ja/built-in-nodes/TextEncodeQwenImageEdit", - "ja/built-in-nodes/TextEncodeQwenImageEditPlus", - "ja/built-in-nodes/TextEncodeZImageOmni" + "ja/tutorials/image/boogu/boogu-image-0.1" ] }, { - "group": "\u30c7\u30d0\u30c3\u30b0", + "group": "HiDream", "pages": [ - { - "group": "\u30e2\u30c7\u30eb", - "pages": [ - "ja/built-in-nodes/EasyCache", - "ja/built-in-nodes/LazyCache", - "ja/built-in-nodes/ModelComputeDtype" - ] - } + "ja/tutorials/image/hidream/hidream-i1", + "ja/tutorials/image/hidream/hidream-e1", + "ja/tutorials/image/hidream/hidream-o1" ] }, { - "group": "\u30ac\u30a4\u30c0\u30f3\u30b9", + "group": "Ovis", "pages": [ - "ja/built-in-nodes/CFGNorm", - "ja/built-in-nodes/CFGZeroStar", - "ja/built-in-nodes/NAGuidance", - "ja/built-in-nodes/SkipLayerGuidanceDiT", - "ja/built-in-nodes/SkipLayerGuidanceDiTSimple", - "ja/built-in-nodes/SkipLayerGuidanceSD3", - "ja/built-in-nodes/TCFG" + "ja/tutorials/image/ovis/ovis-image" ] }, { - "group": "\u30d5\u30c3\u30af", + "group": "NewBie-image", "pages": [ - { - "group": "CLIP", - "pages": [ - "ja/built-in-nodes/SetClipHooks" - ] - }, - { - "group": "\u7d50\u5408", - "pages": [ - "ja/built-in-nodes/CombineHooks", - "ja/built-in-nodes/CombineHooksEight", - "ja/built-in-nodes/CombineHooksFour" - ] - }, - { - "group": "Cond Pair", - "pages": [ - "ja/built-in-nodes/PairConditioningCombine", - "ja/built-in-nodes/PairConditioningSetDefaultAndCombine", - "ja/built-in-nodes/PairConditioningSetProperties", - "ja/built-in-nodes/PairConditioningSetPropertiesAndCombine" - ] - }, - { - "group": "Cond Single", - "pages": [ - "ja/built-in-nodes/ConditioningSetDefaultAndCombine", - "ja/built-in-nodes/ConditioningSetProperties", - "ja/built-in-nodes/ConditioningSetPropertiesAndCombine" - ] - }, - { - "group": "\u4f5c\u6210", - "pages": [ - "ja/built-in-nodes/CreateHookLora", - "ja/built-in-nodes/CreateHookLoraModelOnly", - "ja/built-in-nodes/CreateHookModelAsLora", - "ja/built-in-nodes/CreateHookModelAsLoraModelOnly" - ] - }, - { - "group": "\u30de\u30cb\u30e5\u30a2\u30eb", - "pages": [ - "ja/built-in-nodes/SetModelHooksOnCond" - ] - }, - { - "group": "\u30b9\u30b1\u30b8\u30e5\u30fc\u30ea\u30f3\u30b0", - "pages": [ - "ja/built-in-nodes/CreateHookKeyframe", - "ja/built-in-nodes/CreateHookKeyframesFromFloats", - "ja/built-in-nodes/CreateHookKeyframesInterpolated", - "ja/built-in-nodes/SetHookKeyframes" - ] - }, - "ja/built-in-nodes/ConditioningTimestepsRange" + "ja/tutorials/image/newbie-image/newbie-image-exp-0-1" ] }, { - "group": "\u30ed\u30fc\u30c0\u30fc", + "group": "ERNIE-Image", "pages": [ - { - "group": "\u975e\u63a8\u5968", - "pages": [ - "ja/built-in-nodes/DiffusersLoader" - ] - }, - { - "group": "Qwen", - "pages": [ - "ja/built-in-nodes/QwenImageDiffsynthControlnet" - ] - }, - { - "group": "Zimage", - "pages": [ - "ja/built-in-nodes/ZImageFunControlnet" - ] - }, - "ja/built-in-nodes/CheckpointLoader", - "ja/built-in-nodes/ClipLoader", - "ja/built-in-nodes/DeprecatedCheckpointLoader", - "ja/built-in-nodes/DeprecatedDiffusersLoader", - "ja/built-in-nodes/DualCLIPLoader", - "ja/built-in-nodes/LTXAVTextEncoderLoader", - "ja/built-in-nodes/ModelPatchLoader", - "ja/built-in-nodes/QuadrupleCLIPLoader", - "ja/built-in-nodes/TripleCLIPLoader", - "ja/built-in-nodes/UNETLoader" + "ja/tutorials/image/ernie-image/ernie-image" ] }, { - "group": "\u30e2\u30c7\u30eb", + "group": "Anima", "pages": [ - "ja/built-in-nodes/HiDreamO1PatchSeamSmoothing", - "ja/built-in-nodes/ModelNoiseScale", - "ja/built-in-nodes/ModelSamplingAuraFlow", - "ja/built-in-nodes/ModelSamplingContinuousEDM", - "ja/built-in-nodes/ModelSamplingContinuousV", - "ja/built-in-nodes/ModelSamplingDiscrete", - "ja/built-in-nodes/ModelSamplingFlux", - "ja/built-in-nodes/ModelSamplingLTXV", - "ja/built-in-nodes/ModelSamplingSD3", - "ja/built-in-nodes/ModelSamplingStableCascade", - "ja/built-in-nodes/RenormCFG", - "ja/built-in-nodes/RescaleCFG" + "ja/tutorials/image/anima/anima" ] }, { - "group": "\u30e2\u30c7\u30eb\u30de\u30fc\u30b8", + "group": "レンズ", "pages": [ - { - "group": "\u30e2\u30c7\u30eb\u56fa\u6709", - "pages": [ - "ja/built-in-nodes/ModelMergeAuraflow", - "ja/built-in-nodes/ModelMergeCosmos14B", - "ja/built-in-nodes/ModelMergeCosmos7B", - "ja/built-in-nodes/ModelMergeCosmosPredict2_14B", - "ja/built-in-nodes/ModelMergeCosmosPredict2_2B", - "ja/built-in-nodes/ModelMergeFlux1", - "ja/built-in-nodes/ModelMergeLTXV", - "ja/built-in-nodes/ModelMergeMochiPreview", - "ja/built-in-nodes/ModelMergeQwenImage", - "ja/built-in-nodes/ModelMergeSD1", - "ja/built-in-nodes/ModelMergeSD35_Large", - "ja/built-in-nodes/ModelMergeSD3_2B", - "ja/built-in-nodes/ModelMergeSDXL", - "ja/built-in-nodes/ModelMergeWAN2_1" - ] - }, - "ja/built-in-nodes/CheckpointSave", - "ja/built-in-nodes/CLIPMergeAdd", - "ja/built-in-nodes/ClipMergeSimple", - "ja/built-in-nodes/CLIPMergeSubtract", - "ja/built-in-nodes/ClipSave", - "ja/built-in-nodes/ImageOnlyCheckpointSave", - "ja/built-in-nodes/ModelMergeAdd", - "ja/built-in-nodes/ModelMergeBlocks", - "ja/built-in-nodes/ModelMergeSimple", - "ja/built-in-nodes/ModelMergeSubtract", - "ja/built-in-nodes/ModelSave", - "ja/built-in-nodes/SaveLoRA", - "ja/built-in-nodes/SaveLoRANode", - "ja/built-in-nodes/VAESave" + "ja/tutorials/image/lens/lens" ] }, { - "group": "\u30de\u30eb\u30c1GPU", + "group": "PixelDiT", "pages": [ - "ja/built-in-nodes/MultiGPU_Options", - "ja/built-in-nodes/MultiGPU_WorkUnits", - "ja/built-in-nodes/SelectCLIPDevice", - "ja/built-in-nodes/SelectModelDevice", - "ja/built-in-nodes/SelectVAEDevice" + "ja/tutorials/image/pixeldit/pixeldit" ] }, - "ja/built-in-nodes/GeminiNodeV2", - "ja/built-in-nodes/MoonvalleyImg2VideoNode", - "ja/built-in-nodes/MoonvalleyTxt2VideoNode", - "ja/built-in-nodes/MoonvalleyVideo2VideoNode", - "ja/built-in-nodes/PreviewGaussianSplat", - "ja/built-in-nodes/PreviewPointCloud", - "ja/built-in-nodes/SaveAudioAdvanced", - "ja/built-in-nodes/SeedVR2Conditioning", - "ja/built-in-nodes/SeedVR2PostProcessing", - "ja/built-in-nodes/SeedVR2Preprocess", - "ja/built-in-nodes/SeedVR2ProgressiveSampler" - ] - }, - { - "group": "API Node", - "pages": [ { - "group": "\u753b\u50cf", + "group": "Krea 2", "pages": [ - { - "group": "BFL", - "pages": [ - "ja/built-in-nodes/partner-node/image/bfl/flux-1-1-pro-ultra-image" - ] - }, - { - "group": "Bfl", - "pages": [ - "ja/built-in-nodes/FluxProCannyNode", - "ja/built-in-nodes/FluxProDepthNode", - "ja/built-in-nodes/FluxProImageNode" - ] - }, - { - "group": "Bytedance", - "pages": [ - "ja/built-in-nodes/ByteDanceImageEditNode" - ] - }, - { - "group": "Ideogram", - "pages": [ - "ja/built-in-nodes/partner-node/image/ideogram/ideogram-v1", - "ja/built-in-nodes/partner-node/image/ideogram/ideogram-v2" - ] - }, - { - "group": "Luma", - "pages": [ - "ja/built-in-nodes/partner-node/image/luma/luma-image-to-image", - "ja/built-in-nodes/partner-node/image/luma/luma-reference", - "ja/built-in-nodes/partner-node/image/luma/luma-text-to-image" - ] - }, - { - "group": "OpenAI", - "pages": [ - "ja/built-in-nodes/partner-node/image/openai/openai-dalle2", - "ja/built-in-nodes/partner-node/image/openai/openai-dalle3", - "ja/built-in-nodes/partner-node/image/openai/openai-gpt-image1" - ] - }, - { - "group": "Recraft", - "pages": [ - "ja/built-in-nodes/partner-node/image/recraft/recraft-color-rgb", - "ja/built-in-nodes/partner-node/image/recraft/recraft-controls", - "ja/built-in-nodes/partner-node/image/recraft/recraft-creative-upscale", - "ja/built-in-nodes/partner-node/image/recraft/recraft-crisp-upscale", - "ja/built-in-nodes/partner-node/image/recraft/recraft-image-inpainting", - "ja/built-in-nodes/partner-node/image/recraft/recraft-image-to-image", - "ja/built-in-nodes/partner-node/image/recraft/recraft-remove-background", - "ja/built-in-nodes/partner-node/image/recraft/recraft-replace-background", - "ja/built-in-nodes/partner-node/image/recraft/recraft-style-digital-illustration", - "ja/built-in-nodes/partner-node/image/recraft/recraft-style-logo-raster", - "ja/built-in-nodes/partner-node/image/recraft/recraft-style-realistic-image", - "ja/built-in-nodes/partner-node/image/recraft/recraft-text-to-image", - "ja/built-in-nodes/partner-node/image/recraft/recraft-text-to-vector", - "ja/built-in-nodes/partner-node/image/recraft/recraft-vectorize-image", - "ja/built-in-nodes/partner-node/image/recraft/save-svg" - ] - } + "ja/tutorials/image/krea/krea-2" ] }, { - "group": "\u30d3\u30c7\u30aa", + "group": "Ideogram", "pages": [ - { - "group": "Google", - "pages": [ - "ja/built-in-nodes/partner-node/video/google/google-veo2-video" - ] - }, - { - "group": "Kling", - "pages": [ - "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-i2v", - "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-t2v", - "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-controls", - "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-image-to-video", - "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-start-end-frame-to-video", - "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-text-to-video" - ] - }, - { - "group": "Luma", - "pages": [ - "ja/built-in-nodes/partner-node/video/luma/luma-concepts", - "ja/built-in-nodes/partner-node/video/luma/luma-image-to-video", - "ja/built-in-nodes/partner-node/video/luma/luma-text-to-video" - ] - }, - { - "group": "MiniMax", - "pages": [ - "ja/built-in-nodes/partner-node/video/minimax/minimax-image-to-video", - "ja/built-in-nodes/partner-node/video/minimax/minimax-text-to-video" - ] - }, - { - "group": "Pika", - "pages": [ - "ja/built-in-nodes/partner-node/video/pika/pika-image-to-video", - "ja/built-in-nodes/partner-node/video/pika/pika-scenes", - "ja/built-in-nodes/partner-node/video/pika/pika-text-to-video", - "ja/built-in-nodes/Pikadditions", - "ja/built-in-nodes/Pikaffects", - "ja/built-in-nodes/PikaImageToVideoNode2_2", - "ja/built-in-nodes/PikaScenesV2_2", - "ja/built-in-nodes/PikaStartEndFrameNode2_2", - "ja/built-in-nodes/Pikaswaps", - "ja/built-in-nodes/PikaTextToVideoNode2_2" - ] - }, - { - "group": "PixVerse", - "pages": [ - "ja/built-in-nodes/partner-node/video/pixverse/pixverse-image-to-video", - "ja/built-in-nodes/partner-node/video/pixverse/pixverse-template", - "ja/built-in-nodes/partner-node/video/pixverse/pixverse-text-to-video", - "ja/built-in-nodes/partner-node/video/pixverse/pixverse-transition-video" - ] - } + "ja/tutorials/image/ideogram/ideogram-v4" ] - } + }, + "ja/tutorials/image/cosmos/cosmos-predict2-t2i", + "ja/tutorials/image/omnigen/omnigen2" ] }, { - "group": "\u30aa\u30fc\u30c7\u30a3\u30aa", + "group": "3D", "pages": [ - "ja/built-in-nodes/AudioAdjustVolume", - "ja/built-in-nodes/AudioConcat", - "ja/built-in-nodes/AudioEqualizer3Band", - "ja/built-in-nodes/AudioMerge", - "ja/built-in-nodes/EmptyAudio", - "ja/built-in-nodes/JoinAudioChannels", - "ja/built-in-nodes/LoadAudio", - "ja/built-in-nodes/PreviewAudio", - "ja/built-in-nodes/RecordAudio", - "ja/built-in-nodes/SaveAudio", - "ja/built-in-nodes/SaveAudioMP3", - "ja/built-in-nodes/SaveAudioOpus", - "ja/built-in-nodes/SplitAudioChannels", - "ja/built-in-nodes/TrimAudioDuration" + "ja/tutorials/3d/triposplat", + "ja/tutorials/3d/hunyuan3D-2" ] }, { - "group": "\u30b3\u30f3\u30c7\u30a3\u30b7\u30e7\u30cb\u30f3\u30b0", + "group": "LLM", "pages": [ - { - "group": "\u30d3\u30c7\u30aa\u30e2\u30c7\u30eb", - "pages": [ - "ja/built-in-nodes/conditioning/video-models/wan-vace-to-video", - "ja/built-in-nodes/Stablezero123Conditioning", - "ja/built-in-nodes/Stablezero123ConditioningBatched", - "ja/built-in-nodes/SVD_img2vid_Conditioning", - "ja/built-in-nodes/SvdImg2vidConditioning" - ] - }, - "ja/built-in-nodes/ConditioningAverage", - "ja/built-in-nodes/Sd4xupscaleConditioning" + "ja/tutorials/llm/gemma4/gemma4", + "ja/tutorials/llm/qwen/qwen3", + "ja/tutorials/llm/qwen/qwen3_5" ] }, { - "group": "\u5b9f\u9a13\u7684", + "group": "ビデオ", "pages": [ { - "group": "Attention \u5b9f\u9a13", + "group": "LTX", "pages": [ - "ja/built-in-nodes/CLIPAttentionMultiply", - "ja/built-in-nodes/UNetCrossAttentionMultiply", - "ja/built-in-nodes/UNetSelfAttentionMultiply", - "ja/built-in-nodes/UNetTemporalAttentionMultiply" + "ja/tutorials/video/ltxv", + "ja/tutorials/video/ltx/ltx-2", + "ja/tutorials/video/ltx/ltx-2-3" ] }, { - "group": "\u30b3\u30f3\u30c7\u30a3\u30b7\u30e7\u30cb\u30f3\u30b0", - "pages": [ - "ja/built-in-nodes/CLIPTextEncodeControlnet", - "ja/built-in-nodes/T5TokenizerOptions" - ] - }, - { - "group": "\u30ab\u30b9\u30bf\u30e0\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0", + "group": "Wan Video", "pages": [ + "ja/tutorials/video/wan/wan2_2", + "ja/tutorials/video/wan/wan2-2-animate", + "ja/tutorials/video/wan/wan2-2-s2v", + "ja/tutorials/video/wan/wan2-2-fun-inp", + "ja/tutorials/video/wan/wan2-2-fun-control", + "ja/tutorials/video/wan/wan2-2-fun-camera", { - "group": "\u30ce\u30a4\u30ba", + "group": "Wan2.1", "pages": [ - "ja/built-in-nodes/AddNoise" + "ja/tutorials/video/wan/wan-video", + "ja/tutorials/video/wan/vace", + "ja/tutorials/video/wan/wan-move", + "ja/tutorials/video/wan/wan-alpha", + "ja/tutorials/video/wan/wan-ati", + "ja/tutorials/video/wan/fun-control", + "ja/tutorials/video/wan/fun-camera", + "ja/tutorials/video/wan/fun-inp", + "ja/tutorials/video/wan/wan-flf" ] - }, - "ja/built-in-nodes/ManualSigmas" - ] - }, - { - "group": "PhotoMaker", - "pages": [ - "ja/built-in-nodes/PhotoMakerEncode", - "ja/built-in-nodes/PhotoMakerLoader" - ] - }, - { - "group": "Stable Cascade", - "pages": [ - "ja/built-in-nodes/StableCascade_SuperResolutionControlnet" - ] - }, - "ja/built-in-nodes/DifferentialDiffusion", - "ja/built-in-nodes/FluxKVCache", - "ja/built-in-nodes/FreSca", - "ja/built-in-nodes/LatentBlend", - "ja/built-in-nodes/LoadLatent", - "ja/built-in-nodes/LoraSave", - "ja/built-in-nodes/Mahiro", - "ja/built-in-nodes/PerpNeg", - "ja/built-in-nodes/PerpNegGuider", - "ja/built-in-nodes/SamplerEulerCFGpp", - "ja/built-in-nodes/SaveLatent", - "ja/built-in-nodes/SelfAttentionGuidance", - "ja/built-in-nodes/TorchCompileModel", - "ja/built-in-nodes/VAEDecodeTiled", - "ja/built-in-nodes/VAEEncodeTiled" - ] - }, - { - "group": "\u753b\u50cf", - "pages": [ - { - "group": "\u8abf\u6574", - "pages": [ - "ja/built-in-nodes/AdjustBrightness", - "ja/built-in-nodes/AdjustContrast" - ] - }, - { - "group": "\u80cc\u666f\u9664\u53bb", - "pages": [ - "ja/built-in-nodes/RemoveBackground" - ] - }, - { - "group": "\u30d0\u30c3\u30c1", - "pages": [ - "ja/built-in-nodes/ImageDeduplication", - "ja/built-in-nodes/ImageFromBatch", - "ja/built-in-nodes/ImageGrid", - "ja/built-in-nodes/ImageMergeTileList", - "ja/built-in-nodes/MergeImageLists", - "ja/built-in-nodes/RebatchImages", - "ja/built-in-nodes/RepeatImageBatch", - "ja/built-in-nodes/ShuffleDataset", - "ja/built-in-nodes/ShuffleImageTextDataset", - "ja/built-in-nodes/SplitImageToTileList" - ] - }, - { - "group": "\u30ab\u30e9\u30fc", - "pages": [ - "ja/built-in-nodes/ImageRGBToYUV", - "ja/built-in-nodes/ImageYUVToRGB", - "ja/built-in-nodes/NormalizeImages" - ] - }, - { - "group": "\u5408\u6210", - "pages": [ - "ja/built-in-nodes/ImageCompositeMasked", - "ja/built-in-nodes/JoinImageWithAlpha", - "ja/built-in-nodes/PorterDuffImageComposite", - "ja/built-in-nodes/SplitImageWithAlpha" + } ] }, { - "group": "\u691c\u51fa", + "group": "ByteDance", "pages": [ - "ja/built-in-nodes/DrawBBoxes", - "ja/built-in-nodes/MediaPipeFaceLandmarker", - "ja/built-in-nodes/MediaPipeFaceMask", - "ja/built-in-nodes/MediaPipeFaceMeshVisualize", - "ja/built-in-nodes/RTDETR_detect", - "ja/built-in-nodes/SAM3_Detect", - "ja/built-in-nodes/SAM3_TrackPreview", - "ja/built-in-nodes/SAM3_TrackToMask", - "ja/built-in-nodes/SAM3_VideoTrack", - "ja/built-in-nodes/SDPoseDrawKeypoints", - "ja/built-in-nodes/SDPoseFaceBBoxes", - "ja/built-in-nodes/SDPoseKeypointExtractor" + "ja/tutorials/video/bytedance/bernini-r" ] }, { - "group": "\u30d5\u30a3\u30eb\u30bf\u30fc", + "group": "Hunyuan", "pages": [ - "ja/built-in-nodes/Canny", - "ja/built-in-nodes/ColorTransfer", - "ja/built-in-nodes/ImageAddNoise", - "ja/built-in-nodes/ImageBlend", - "ja/built-in-nodes/ImageBlur", - "ja/built-in-nodes/ImageQuantize", - "ja/built-in-nodes/ImageSharpen", - "ja/built-in-nodes/Morphology" + "ja/tutorials/video/hunyuan/hunyuan-video", + "ja/tutorials/video/hunyuan/hunyuan-video-1-5" ] }, { - "group": "\u30b8\u30aa\u30e1\u30c8\u30ea\u63a8\u5b9a", + "group": "Cosmos", "pages": [ - "ja/built-in-nodes/MoGeInference", - "ja/built-in-nodes/MoGePanoramaInference", - "ja/built-in-nodes/MoGePointMapToMesh", - "ja/built-in-nodes/MoGeRender" + "ja/tutorials/video/cosmos/cosmos-predict2-video2world" ] }, { - "group": "\u30de\u30b9\u30af", + "group": "Kandinsky", "pages": [ - "ja/built-in-nodes/BatchMasksNode", - "ja/built-in-nodes/CropMask", - "ja/built-in-nodes/FeatherMask", - "ja/built-in-nodes/GrowMask", - "ja/built-in-nodes/ImageColorToMask", - "ja/built-in-nodes/ImageToMask", - "ja/built-in-nodes/InvertMask", - "ja/built-in-nodes/MaskComposite", - "ja/built-in-nodes/MaskPreview", - "ja/built-in-nodes/MaskToImage", - "ja/built-in-nodes/SolidMask", - "ja/built-in-nodes/ThresholdMask", - "ja/built-in-nodes/VOIDQuadmaskPreprocess" + "ja/tutorials/video/kandinsky/kandinsky-5" ] }, { - "group": "\u30b7\u30a7\u30fc\u30c0\u30fc", + "group": "ZAI", "pages": [ - "ja/built-in-nodes/GLSLShader" + "ja/tutorials/video/zai/scail2" ] }, + "ja/tutorials/video/bytedance/bernini-r" + ] + }, + { + "group": "オーディオ", + "pages": [ { - "group": "\u5909\u63db", + "group": "Stable Audio 1.0", "pages": [ - "ja/built-in-nodes/CenterCropImages", - "ja/built-in-nodes/CropByBBoxes", - "ja/built-in-nodes/ImageCrop", - "ja/built-in-nodes/ImageCropV2", - "ja/built-in-nodes/ImageFlip", - "ja/built-in-nodes/ImagePadForOutpaint", - "ja/built-in-nodes/ImageRotate", - "ja/built-in-nodes/ImageStitch", - "ja/built-in-nodes/RandomCropImages", - "ja/built-in-nodes/ResizeAndPadImage", - "ja/built-in-nodes/ResizeImagesByLongerEdge", - "ja/built-in-nodes/ResizeImagesByShorterEdge" + "ja/tutorials/audio/stable-audio/stable-audio-1" ] }, { - "group": "\u30a2\u30c3\u30d7\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0", + "group": "Stable Audio 3", "pages": [ - "ja/built-in-nodes/ImageScale", - "ja/built-in-nodes/ImageScaleBy", - "ja/built-in-nodes/ImageScaleToMaxDimension", - "ja/built-in-nodes/ImageScaleToTotalPixels", - "ja/built-in-nodes/ImageUpscaleWithModel" + "ja/tutorials/audio/stable-audio/stable-audio-3" ] }, { - "group": "\u30d3\u30c7\u30aa", + "group": "ACE-Step", "pages": [ - "ja/built-in-nodes/WanDancerPadKeyframes", - "ja/built-in-nodes/WanDancerPadKeyframesList" + "ja/tutorials/audio/ace-step/ace-step-v1", + "ja/tutorials/audio/ace-step/ace-step-v1-5" ] - }, - "ja/built-in-nodes/BatchImagesNode", - "ja/built-in-nodes/ConditioningCombine", - "ja/built-in-nodes/EmptyImage", - "ja/built-in-nodes/GetImageSize", - "ja/built-in-nodes/ImageBatch", - "ja/built-in-nodes/ImageCompare", - "ja/built-in-nodes/ImageInvert", - "ja/built-in-nodes/LoadImage", - "ja/built-in-nodes/LoadImageDataSetFromFolder", - "ja/built-in-nodes/LoadImageMask", - "ja/built-in-nodes/LoadImageOutput", - "ja/built-in-nodes/LoadImageSetFromFolderNode", - "ja/built-in-nodes/LoadImageSetNode", - "ja/built-in-nodes/LoadImageTextDataSetFromFolder", - "ja/built-in-nodes/LoadImageTextSetFromFolderNode", - "ja/built-in-nodes/LoraLoader", - "ja/built-in-nodes/LoraLoaderModelOnly", - "ja/built-in-nodes/Painter", - "ja/built-in-nodes/PreviewImage", - "ja/built-in-nodes/ResizeImageMaskNode", - "ja/built-in-nodes/SaveAnimatedPNG", - "ja/built-in-nodes/SaveAnimatedWEBP", - "ja/built-in-nodes/SaveImage", - "ja/built-in-nodes/SaveImageAdvanced", - "ja/built-in-nodes/SaveImageDataSetToFolder", - "ja/built-in-nodes/SaveImageTextDataSetToFolder", - "ja/built-in-nodes/SaveSVGNode", - "ja/built-in-nodes/WebcamCapture" + } ] }, { - "group": "\u6f5c\u5728", + "group": "ユーティリティ", "pages": [ + "ja/tutorials/utility/preprocessors", + "ja/tutorials/utility/frame-interpolation", + "ja/tutorials/utility/image-upscale", + "ja/tutorials/utility/video-upscale", + "ja/tutorials/utility/void-video-inpainting", + "ja/tutorials/utility/video-segment-sam3", + "ja/tutorials/utility/remove-background-birefnet", + "ja/tutorials/utility/pose-detection-sdpose", + "ja/tutorials/utility/moge", + "ja/tutorials/utility/depth-anything-3", { - "group": "\u30d3\u30c7\u30aa", + "group": "顔検出", "pages": [ - "ja/built-in-nodes/latent/video/trim-video-latent" + "ja/tutorials/utility/face-detection/mediapipe" ] } ] + } + ] + }, + { + "group": "パートナーノード", + "icon": "handshake", + "pages": [ + "ja/tutorials/partner-nodes/overview", + "ja/tutorials/partner-nodes/faq", + "ja/tutorials/partner-nodes/pricing", + "ja/tutorials/partner-nodes/concurrency-limits", + { + "group": "Black Forest Labs", + "pages": [ + "ja/tutorials/partner-nodes/black-forest-labs/flux-1-1-pro-ultra-image", + "ja/tutorials/partner-nodes/black-forest-labs/flux-1-kontext" + ] }, { - "group": "\u30ed\u30fc\u30c0\u30fc", + "group": "Beeble", "pages": [ - "ja/built-in-nodes/ControlNetLoader" + "ja/tutorials/partner-nodes/beeble/beeble-switchx" ] }, { - "group": "\u30e2\u30c7\u30eb", + "group": "ByteDance", "pages": [ - { - "group": "\u30b3\u30f3\u30c7\u30a3\u30b7\u30e7\u30cb\u30f3\u30b0", - "pages": [ - { - "group": "3D Models", - "pages": [ - "ja/built-in-nodes/Hunyuan3Dv2Conditioning", - "ja/built-in-nodes/Hunyuan3Dv2ConditioningMultiView", - "ja/built-in-nodes/StableZero123_Conditioning", - "ja/built-in-nodes/StableZero123_Conditioning_Batched", - "ja/built-in-nodes/SV3D_Conditioning" - ] - }, - { - "group": "\u30aa\u30fc\u30c7\u30a3\u30aa", - "pages": [ - "ja/built-in-nodes/LTXVReferenceAudio" - ] - }, - { - "group": "ControlNet", - "pages": [ - "ja/built-in-nodes/ControlNetApply", - "ja/built-in-nodes/ControlNetApplyAdvanced", - "ja/built-in-nodes/ControlNetApplySD3", - "ja/built-in-nodes/ControlNetInpaintingAliMamaApply", - "ja/built-in-nodes/SetUnionControlNetType" - ] - }, - { - "group": "GLIGEN", - "pages": [ - "ja/built-in-nodes/GLIGENTextBoxApply" - ] - }, - { - "group": "\u753b\u50cf", + "ja/tutorials/partner-nodes/bytedance/seedance-2-0", + "ja/tutorials/partner-nodes/bytedance/seedance-2-0-real-human", + "ja/tutorials/partner-nodes/bytedance/seedream-5-lite" + ] + }, + { + "group": "Google", + "pages": [ + "ja/tutorials/partner-nodes/google/gemini", + "ja/tutorials/partner-nodes/google/gemini-omni-flash", + "ja/tutorials/partner-nodes/google/nano-banana-pro", + "ja/tutorials/partner-nodes/google/nano-banana-2", + "ja/tutorials/partner-nodes/google/nano-banana-2-lite" + ] + }, + { + "group": "Anthropic", + "pages": [ + "ja/tutorials/partner-nodes/anthropic/claude" + ] + }, + { + "group": "Ideogram", + "pages": [ + "ja/tutorials/partner-nodes/ideogram/ideogram-v4" + ] + }, + { + "group": "Luma", + "pages": [ + "ja/tutorials/partner-nodes/luma/luma-uni-1", + "ja/tutorials/partner-nodes/luma/luma-text-to-image", + "ja/tutorials/partner-nodes/luma/luma-image-to-image", + "ja/tutorials/partner-nodes/luma/luma-text-to-video", + "ja/tutorials/partner-nodes/luma/luma-image-to-video" + ] + }, + { + "group": "Moonvalley", + "pages": [ + "ja/tutorials/partner-nodes/moonvalley/moonvalley-video-generation" + ] + }, + { + "group": "OpenAI", + "pages": [ + "ja/tutorials/partner-nodes/openai/gpt-image-2", + "ja/tutorials/partner-nodes/openai/gpt-image-1", + "ja/tutorials/partner-nodes/openai/dall-e-2", + "ja/tutorials/partner-nodes/openai/dall-e-3", + "ja/tutorials/partner-nodes/openai/chat" + ] + }, + { + "group": "OpenRouter", + "pages": [ + "ja/tutorials/partner-nodes/openrouter/llm" + ] + }, + { + "group": "Recraft", + "pages": [ + "ja/tutorials/partner-nodes/recraft/recraft-v4", + "ja/tutorials/partner-nodes/recraft/recraft-text-to-image" + ] + }, + { + "group": "Krea 2", + "pages": [ + "ja/tutorials/partner-nodes/krea2/krea2-t2i" + ] + }, + { + "group": "Kling", + "pages": [ + "ja/tutorials/partner-nodes/kling/kling-3-0", + "ja/tutorials/partner-nodes/kling/kling-motion-control" + ] + }, + { + "group": "Runway", + "pages": [ + "ja/tutorials/partner-nodes/runway/image-generation", + "ja/tutorials/partner-nodes/runway/video-generation" + ] + }, + { + "group": "Rodin", + "pages": [ + "ja/tutorials/partner-nodes/rodin/model-generation" + ] + }, + { + "group": "Tripo", + "pages": [ + "ja/tutorials/partner-nodes/tripo/model-generation", + "ja/tutorials/partner-nodes/tripo/tripo-3-1" + ] + }, + { + "group": "Hunyuan 3D", + "pages": [ + "ja/tutorials/partner-nodes/hunyuan3d/hunyuan3d-3-0" + ] + }, + { + "group": "Meshy", + "pages": [ + "ja/tutorials/partner-nodes/meshy/meshy-6" + ] + }, + { + "group": "Bria", + "pages": [ + "ja/tutorials/partner-nodes/bria/fibo", + "ja/tutorials/partner-nodes/bria/background-removal" + ] + }, + { + "group": "Reve", + "pages": [ + "ja/tutorials/partner-nodes/reve/reve-image" + ] + }, + { + "group": "Wan", + "pages": [ + "ja/tutorials/partner-nodes/wan/wan2-7" + ] + }, + { + "group": "HappyHorse", + "pages": [ + "ja/tutorials/partner-nodes/happyhorse/happyhorse1-1", + "ja/tutorials/partner-nodes/happyhorse/happyhorse1-0" + ] + }, + { + "group": "Sonilo", + "pages": [ + "ja/tutorials/partner-nodes/sonilo/video-to-music" + ] + }, + { + "group": "Topaz", + "pages": [ + "ja/tutorials/partner-nodes/topaz/astra-2" + ] + }, + { + "group": "Krea 2", + "pages": [ + "ko/tutorials/partner-nodes/krea2/krea2-t2i" + ] + } + ] + }, + "ko/changelog/index" + ] + }, + { + "tab": "組み込みノード", + "pages": [ + "ja/built-in-nodes/overview", + { + "group": "ノード", + "pages": [ + { + "group": "3D", + "pages": [ + { + "group": "Splat", + "pages": [ + "ja/built-in-nodes/File3DToSplat", + "ja/built-in-nodes/GetSplatCount", + "ja/built-in-nodes/MergeSplat", + "ja/built-in-nodes/RenderSplat", + "ja/built-in-nodes/SplatToFile3D", + "ja/built-in-nodes/SplatToMesh", + "ja/built-in-nodes/TransformSplat" + ] + }, + "ja/built-in-nodes/CreateCameraInfo", + "ja/built-in-nodes/Load3D", + "ja/built-in-nodes/Load3DAdvanced", + "ja/built-in-nodes/Load3DAnimation", + "ja/built-in-nodes/Preview3D", + "ja/built-in-nodes/Preview3DAdvanced", + "ja/built-in-nodes/Preview3DAnimation", + "ja/built-in-nodes/PreviewGaussianSplat", + "ja/built-in-nodes/PreviewPointCloud", + "ja/built-in-nodes/SaveGLB", + "ja/built-in-nodes/VoxelToMesh", + "ja/built-in-nodes/VoxelToMeshBasic" + ] + }, + { + "group": "API Node", + "pages": [ + { + "group": "Image", + "pages": [ + { + "group": "Bfl", + "pages": [ + "ja/built-in-nodes/FluxProCannyNode", + "ja/built-in-nodes/FluxProDepthNode", + "ja/built-in-nodes/FluxProImageNode" + ] + }, + { + "group": "Bytedance", + "pages": [ + "ja/built-in-nodes/ByteDanceImageEditNode" + ] + } + ] + }, + { + "group": "Video", + "pages": [ + { + "group": "Pika", + "pages": [ + "ja/built-in-nodes/Pikadditions", + "ja/built-in-nodes/Pikaffects", + "ja/built-in-nodes/PikaImageToVideoNode2_2", + "ja/built-in-nodes/PikaScenesV2_2", + "ja/built-in-nodes/PikaStartEndFrameNode2_2", + "ja/built-in-nodes/Pikaswaps", + "ja/built-in-nodes/PikaTextToVideoNode2_2" + ] + } + ] + }, + { + "group": "ビデオ", + "pages": [ + { + "group": "Google", + "pages": [ + "ja/built-in-nodes/partner-node/video/google/google-veo2-video" + ] + }, + { + "group": "Kling", + "pages": [ + "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-i2v", + "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-control-t2v", + "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-camera-controls", + "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-image-to-video", + "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-start-end-frame-to-video", + "ja/built-in-nodes/partner-node/video/kwai_vgi/kling-text-to-video" + ] + }, + { + "group": "Luma", + "pages": [ + "ja/built-in-nodes/partner-node/video/luma/luma-concepts", + "ja/built-in-nodes/partner-node/video/luma/luma-image-to-video", + "ja/built-in-nodes/partner-node/video/luma/luma-text-to-video" + ] + }, + { + "group": "MiniMax", + "pages": [ + "ja/built-in-nodes/partner-node/video/minimax/minimax-image-to-video", + "ja/built-in-nodes/partner-node/video/minimax/minimax-text-to-video" + ] + }, + { + "group": "Pika", + "pages": [ + "ja/built-in-nodes/partner-node/video/pika/pika-image-to-video", + "ja/built-in-nodes/partner-node/video/pika/pika-scenes", + "ja/built-in-nodes/partner-node/video/pika/pika-text-to-video" + ] + }, + { + "group": "PixVerse", + "pages": [ + "ja/built-in-nodes/partner-node/video/pixverse/pixverse-image-to-video", + "ja/built-in-nodes/partner-node/video/pixverse/pixverse-template", + "ja/built-in-nodes/partner-node/video/pixverse/pixverse-text-to-video", + "ja/built-in-nodes/partner-node/video/pixverse/pixverse-transition-video" + ] + } + ] + }, + { + "group": "画像", + "pages": [ + { + "group": "BFL", + "pages": [ + "ja/built-in-nodes/partner-node/image/bfl/flux-1-1-pro-ultra-image" + ] + }, + { + "group": "Ideogram", + "pages": [ + "ja/built-in-nodes/partner-node/image/ideogram/ideogram-v1", + "ja/built-in-nodes/partner-node/image/ideogram/ideogram-v2" + ] + }, + { + "group": "Luma", + "pages": [ + "ja/built-in-nodes/partner-node/image/luma/luma-image-to-image", + "ja/built-in-nodes/partner-node/image/luma/luma-reference", + "ja/built-in-nodes/partner-node/image/luma/luma-text-to-image" + ] + }, + { + "group": "OpenAI", + "pages": [ + "ja/built-in-nodes/partner-node/image/openai/openai-dalle2", + "ja/built-in-nodes/partner-node/image/openai/openai-dalle3", + "ja/built-in-nodes/partner-node/image/openai/openai-gpt-image1" + ] + }, + { + "group": "Recraft", + "pages": [ + "ja/built-in-nodes/partner-node/image/recraft/recraft-color-rgb", + "ja/built-in-nodes/partner-node/image/recraft/recraft-controls", + "ja/built-in-nodes/partner-node/image/recraft/recraft-creative-upscale", + "ja/built-in-nodes/partner-node/image/recraft/recraft-crisp-upscale", + "ja/built-in-nodes/partner-node/image/recraft/recraft-image-inpainting", + "ja/built-in-nodes/partner-node/image/recraft/recraft-image-to-image", + "ja/built-in-nodes/partner-node/image/recraft/recraft-remove-background", + "ja/built-in-nodes/partner-node/image/recraft/recraft-replace-background", + "ja/built-in-nodes/partner-node/image/recraft/recraft-style-digital-illustration", + "ja/built-in-nodes/partner-node/image/recraft/recraft-style-logo-raster", + "ja/built-in-nodes/partner-node/image/recraft/recraft-style-realistic-image", + "ja/built-in-nodes/partner-node/image/recraft/recraft-text-to-image", + "ja/built-in-nodes/partner-node/image/recraft/recraft-text-to-vector", + "ja/built-in-nodes/partner-node/image/recraft/recraft-vectorize-image", + "ja/built-in-nodes/partner-node/image/recraft/save-svg" + ] + } + ] + } + ] + }, + { + "group": "Audio", + "pages": [ + "ja/built-in-nodes/AudioAdjustVolume", + "ja/built-in-nodes/AudioConcat", + "ja/built-in-nodes/AudioEqualizer3Band", + "ja/built-in-nodes/AudioMerge", + "ja/built-in-nodes/EmptyAudio", + "ja/built-in-nodes/JoinAudioChannels", + "ja/built-in-nodes/LoadAudio", + "ja/built-in-nodes/PreviewAudio", + "ja/built-in-nodes/RecordAudio", + "ja/built-in-nodes/SaveAudio", + "ja/built-in-nodes/SaveAudioAdvanced", + "ja/built-in-nodes/SaveAudioMP3", + "ja/built-in-nodes/SaveAudioOpus", + "ja/built-in-nodes/SplitAudioChannels", + "ja/built-in-nodes/TrimAudioDuration" + ] + }, + { + "group": "Experimental", + "pages": [ + { + "group": "Attention Experiments", + "pages": [ + "ja/built-in-nodes/ClipAttentionMultiply", + "ja/built-in-nodes/UNetCrossAttentionMultiply", + "ja/built-in-nodes/UNetSelfAttentionMultiply", + "ja/built-in-nodes/UNetTemporalAttentionMultiply" + ] + }, + { + "group": "Stable Cascade", + "pages": [ + "ja/built-in-nodes/StableCascade_SuperResolutionControlnet" + ] + }, + "ja/built-in-nodes/DifferentialDiffusion", + "ja/built-in-nodes/FluxKVCache", + "ja/built-in-nodes/FreSca", + "ja/built-in-nodes/LatentBlend", + "ja/built-in-nodes/LoraSave", + "ja/built-in-nodes/Mahiro", + "ja/built-in-nodes/PerpNeg", + "ja/built-in-nodes/PerpNegGuider", + "ja/built-in-nodes/SamplerEulerCFGpp", + "ja/built-in-nodes/SelfAttentionGuidance", + "ja/built-in-nodes/TorchCompileModel" + ] + }, + { + "group": "Model", + "pages": [ + { + "group": "Conditioning", + "pages": [ + { + "group": "Ace", + "pages": [ + "ja/built-in-nodes/TextEncodeAceStepAudio", + "ja/built-in-nodes/TextEncodeAceStepAudio1.5" + ] + }, + { + "group": "Autoregressive", + "pages": [ + "ja/built-in-nodes/ARVideoI2V" + ] + }, + { + "group": "Bernini", + "pages": [ + "ja/built-in-nodes/BerniniConditioning" + ] + }, + { + "group": "Boogu", + "pages": [ + "ja/built-in-nodes/TextEncodeBooguEdit" + ] + }, + { + "group": "Controlnet", + "pages": [ + "ja/built-in-nodes/ControlNetApply", + "ja/built-in-nodes/ControlNetApplyAdvanced", + "ja/built-in-nodes/ControlNetApplySD3", + "ja/built-in-nodes/ControlNetInpaintingAliMamaApply", + "ja/built-in-nodes/SetUnionControlNetType" + ] + }, + { + "group": "Cosmos", + "pages": [ + "ja/built-in-nodes/CosmosImageToVideoLatent", + "ja/built-in-nodes/CosmosPredict2ImageToVideoLatent" + ] + }, + { + "group": "Flux", + "pages": [ + "ja/built-in-nodes/ClipTextEncodeFlux", + "ja/built-in-nodes/FluxDisableGuidance", + "ja/built-in-nodes/FluxGuidance", + "ja/built-in-nodes/FluxKontextImageScale", + "ja/built-in-nodes/FluxKontextMultiReferenceLatentMethod" + ] + }, + { + "group": "Gligen", + "pages": [ + "ja/built-in-nodes/GLIGENTextBoxApply" + ] + }, + { + "group": "Hidream", + "pages": [ + "ja/built-in-nodes/ClipTextEncodeHiDream", + "ja/built-in-nodes/HiDreamO1ReferenceImages" + ] + }, + { + "group": "Hunyuan 3D", + "pages": [ + "ja/built-in-nodes/Hunyuan3Dv2Conditioning", + "ja/built-in-nodes/Hunyuan3Dv2ConditioningMultiView" + ] + }, + { + "group": "Hunyuan Image", + "pages": [ + "ja/built-in-nodes/ClipTextEncodeHunyuanDiT" + ] + }, + { + "group": "Hunyuan Video", + "pages": [ + "ja/built-in-nodes/HunyuanImageToVideo", + "ja/built-in-nodes/HunyuanRefinerLatent", + "ja/built-in-nodes/HunyuanVideo15ImageToVideo", + "ja/built-in-nodes/HunyuanVideo15SuperResolution", + "ja/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo" + ] + }, + { + "group": "Instructpix2Pix", + "pages": [ + "ja/built-in-nodes/InstructPixToPixConditioning" + ] + }, + { + "group": "Kandinsky", "pages": [ - "ja/built-in-nodes/HiDreamO1ReferenceImages" + "ja/built-in-nodes/ClipTextEncodeKandinsky5", + "ja/built-in-nodes/Kandinsky5ImageToVideo" ] }, { - "group": "\u30a4\u30f3\u30da\u30a4\u30f3\u30c8", + "group": "Lotus", "pages": [ - "ja/built-in-nodes/CosmosImageToVideoLatent", - "ja/built-in-nodes/CosmosPredict2ImageToVideoLatent", - "ja/built-in-nodes/InpaintModelConditioning", - "ja/built-in-nodes/Wan22ImageToVideoLatent" + "ja/built-in-nodes/LotusConditioning" ] }, { - "group": "InstructPix2Pix", + "group": "Ltxv", "pages": [ - "ja/built-in-nodes/InstructPixToPixConditioning" + "ja/built-in-nodes/GetICLoRAParameters", + "ja/built-in-nodes/LTXVAddGuide", + "ja/built-in-nodes/LTXVConditioning", + "ja/built-in-nodes/LTXVCropGuides", + "ja/built-in-nodes/LTXVImgToVideo", + "ja/built-in-nodes/LTXVImgToVideoInplace", + "ja/built-in-nodes/LTXVReferenceAudio" ] }, { - "group": "Lotus", + "group": "Lumina", "pages": [ - "ja/built-in-nodes/LotusConditioning" + "ja/built-in-nodes/ClipTextEncodeLumina2" + ] + }, + { + "group": "Photomaker", + "pages": [ + "ja/built-in-nodes/PhotoMakerEncode" + ] + }, + { + "group": "Pixart", + "pages": [ + "ja/built-in-nodes/ClipTextEncodePixArtAlpha" + ] + }, + { + "group": "Qwen Image", + "pages": [ + "ja/built-in-nodes/TextEncodeQwenImageEdit", + "ja/built-in-nodes/TextEncodeQwenImageEditPlus" + ] + }, + { + "group": "Stable Audio", + "pages": [ + "ja/built-in-nodes/ConditioningStableAudio" ] }, { @@ -6475,91 +6439,185 @@ ] }, { - "group": "\u30b9\u30bf\u30a4\u30eb\u30e2\u30c7\u30eb", + "group": "Stable Diffusion", "pages": [ - "ja/built-in-nodes/StyleModelApply" + "ja/built-in-nodes/ClipTextEncodeSD3", + "ja/built-in-nodes/ClipTextEncodeSDXL", + "ja/built-in-nodes/ClipTextEncodeSDXLRefiner" ] }, { - "group": "Upscale Diffusion", + "group": "Stable Diffusion Upscaler", "pages": [ "ja/built-in-nodes/SD_4XUpscale_Conditioning" ] }, { - "group": "\u30d3\u30c7\u30aa\u30e2\u30c7\u30eb", + "group": "Stable Video 3D", "pages": [ - "ja/built-in-nodes/ARVideoI2V", - "ja/built-in-nodes/GenerateTracks", - "ja/built-in-nodes/GetICLoRAParameters", - "ja/built-in-nodes/HunyuanImageToVideo", - "ja/built-in-nodes/HunyuanRefinerLatent", - "ja/built-in-nodes/HunyuanVideo15ImageToVideo", - "ja/built-in-nodes/HunyuanVideo15SuperResolution", - "ja/built-in-nodes/Kandinsky5ImageToVideo", - "ja/built-in-nodes/LTXVAddGuide", - "ja/built-in-nodes/LTXVConditioning", - "ja/built-in-nodes/LTXVCropGuides", - "ja/built-in-nodes/LTXVImgToVideo", - "ja/built-in-nodes/LTXVImgToVideoInplace", - "ja/built-in-nodes/NormalizeVideoLatentStart", - "ja/built-in-nodes/VOIDInpaintConditioning", - "ja/built-in-nodes/Wan22FunControlToVideo", - "ja/built-in-nodes/WanAnimateToVideo", - "ja/built-in-nodes/WanCameraEmbedding", - "ja/built-in-nodes/WanCameraImageToVideo", - "ja/built-in-nodes/WanDancerEncodeAudio", - "ja/built-in-nodes/WanDancerVideo", + "ja/built-in-nodes/SV3D_Conditioning" + ] + }, + { + "group": "Stable Zero123", + "pages": [ + "ja/built-in-nodes/StableZero123_Conditioning", + "ja/built-in-nodes/StableZero123_Conditioning_Batched" + ] + }, + { + "group": "Transform", + "pages": [ + "ja/built-in-nodes/ConditioningConcat", + "ja/built-in-nodes/ConditioningMultiply", + "ja/built-in-nodes/ConditioningSetArea", + "ja/built-in-nodes/ConditioningSetAreaPercentage", + "ja/built-in-nodes/ConditioningSetAreaPercentageVideo", + "ja/built-in-nodes/ConditioningSetAreaStrength", + "ja/built-in-nodes/ConditioningSetMask", + "ja/built-in-nodes/ConditioningSetTimestepRange", + "ja/built-in-nodes/ConditioningZeroOut" + ] + }, + { + "group": "Triposplat", + "pages": [ + "ja/built-in-nodes/TripoSplatConditioning", + "ja/built-in-nodes/TripoSplatPreprocessImage" + ] + }, + { + "group": "Void", + "pages": [ + "ja/built-in-nodes/VOIDInpaintConditioning" + ] + }, + { + "group": "Wan", + "pages": [ + { + "group": "Animate", + "pages": [ + "ja/built-in-nodes/WanAnimateToVideo" + ] + }, + { + "group": "Camera", + "pages": [ + "ja/built-in-nodes/WanCameraEmbedding", + "ja/built-in-nodes/WanCameraImageToVideo" + ] + }, + { + "group": "Dancer", + "pages": [ + "ja/built-in-nodes/WanDancerEncodeAudio", + "ja/built-in-nodes/WanDancerVideo" + ] + }, + { + "group": "Fun Control", + "pages": [ + "ja/built-in-nodes/Wan22FunControlToVideo", + "ja/built-in-nodes/WanFunControlToVideo" + ] + }, + { + "group": "Fun Inpaint", + "pages": [ + "ja/built-in-nodes/WanFunInpaintToVideo" + ] + }, + { + "group": "Humo", + "pages": [ + "ja/built-in-nodes/WanHuMoImageToVideo" + ] + }, + { + "group": "Infinite Talk", + "pages": [ + "ja/built-in-nodes/WanInfiniteTalkToVideo" + ] + }, + { + "group": "Move", + "pages": [ + "ja/built-in-nodes/GenerateTracks", + "ja/built-in-nodes/WanMoveConcatTrack", + "ja/built-in-nodes/WanMoveTracksFromCoords", + "ja/built-in-nodes/WanMoveTrackToVideo", + "ja/built-in-nodes/WanMoveVisualizeTracks", + "ja/built-in-nodes/WanTrackToVideo" + ] + }, + { + "group": "Phantom Subject", + "pages": [ + "ja/built-in-nodes/WanPhantomSubjectToVideo" + ] + }, + { + "group": "Scail", + "pages": [ + "ja/built-in-nodes/SCAIL2ColoredMask", + "ja/built-in-nodes/WanSCAILToVideo" + ] + }, + { + "group": "Sound", + "pages": [ + "ja/built-in-nodes/WanSoundImageToVideo", + "ja/built-in-nodes/WanSoundImageToVideoExtend" + ] + }, + { + "group": "Vace", + "pages": [ + "ja/built-in-nodes/WanVaceToVideo" + ] + }, + "ja/built-in-nodes/Wan22ImageToVideoLatent", "ja/built-in-nodes/WanFirstLastFrameToVideo", - "ja/built-in-nodes/WanFunControlToVideo", - "ja/built-in-nodes/WanFunInpaintToVideo", - "ja/built-in-nodes/WanHuMoImageToVideo", - "ja/built-in-nodes/WanImageToVideo", - "ja/built-in-nodes/WanInfiniteTalkToVideo", - "ja/built-in-nodes/WanMoveConcatTrack", - "ja/built-in-nodes/WanMoveTracksFromCoords", - "ja/built-in-nodes/WanMoveTrackToVideo", - "ja/built-in-nodes/WanMoveVisualizeTracks", - "ja/built-in-nodes/WanPhantomSubjectToVideo", - "ja/built-in-nodes/WanSCAILToVideo", - "ja/built-in-nodes/WanSoundImageToVideo", - "ja/built-in-nodes/WanSoundImageToVideoExtend", - "ja/built-in-nodes/WanTrackToVideo", - "ja/built-in-nodes/WanVaceToVideo" + "ja/built-in-nodes/WanImageToVideo" + ] + }, + { + "group": "Z Image", + "pages": [ + "ja/built-in-nodes/TextEncodeZImageOmni" ] }, "ja/built-in-nodes/AudioEncoderEncode", "ja/built-in-nodes/ClipSetLastLayer", "ja/built-in-nodes/ClipTextEncode", - "ja/built-in-nodes/CLIPTextEncodeLumina2", + "ja/built-in-nodes/ClipTextEncodeControlnet", "ja/built-in-nodes/ClipVisionEncode", - "ja/built-in-nodes/ConditioningConcat", - "ja/built-in-nodes/ConditioningSetArea", - "ja/built-in-nodes/ConditioningSetAreaPercentage", - "ja/built-in-nodes/ConditioningSetAreaPercentageVideo", - "ja/built-in-nodes/ConditioningSetAreaStrength", - "ja/built-in-nodes/ConditioningSetMask", - "ja/built-in-nodes/ConditioningStableAudio", - "ja/built-in-nodes/TextEncodeAceStepAudio", - "ja/built-in-nodes/TextEncodeAceStepAudio1.5", + "ja/built-in-nodes/InpaintModelConditioning", + "ja/built-in-nodes/NormalizeVideoLatentStart", + "ja/built-in-nodes/PiDConditioning", + "ja/built-in-nodes/ReferenceLatent", + "ja/built-in-nodes/ReferenceTimbreAudio", + "ja/built-in-nodes/StyleModelApply", + "ja/built-in-nodes/T5TokenizerOptions", "ja/built-in-nodes/unCLIPConditioning" ] }, { - "group": "\u6f5c\u5728", + "group": "Latent", "pages": [ { - "group": "3D", + "group": "Ace", "pages": [ - "ja/built-in-nodes/EmptyLatentHunyuan3Dv2", - "ja/built-in-nodes/VAEDecodeHunyuan3D" + "ja/built-in-nodes/EmptyAceStep1.5LatentAudio", + "ja/built-in-nodes/EmptyAceStepLatentAudio" ] }, { - "group": "\u8a73\u7d30", + "group": "Advanced", "pages": [ { - "group": "\u64cd\u4f5c", + "group": "Operations", "pages": [ "ja/built-in-nodes/LatentApplyOperation", "ja/built-in-nodes/LatentApplyOperationCFG", @@ -6578,22 +6636,15 @@ ] }, { - "group": "\u30aa\u30fc\u30c7\u30a3\u30aa", + "group": "Autoregressive", "pages": [ - "ja/built-in-nodes/EmptyAceStep1.5LatentAudio", - "ja/built-in-nodes/EmptyAceStepLatentAudio", - "ja/built-in-nodes/EmptyLatentAudio", - "ja/built-in-nodes/LTXVAudioVAEDecode", - "ja/built-in-nodes/LTXVAudioVAEEncode", - "ja/built-in-nodes/LTXVEmptyLatentAudio", - "ja/built-in-nodes/VAEDecodeAudio", - "ja/built-in-nodes/VAEDecodeAudioTiled", - "ja/built-in-nodes/VAEEncodeAudio" + "ja/built-in-nodes/EmptyARVideoLatent" ] }, { - "group": "\u30d0\u30c3\u30c1", + "group": "Batch", "pages": [ + "ja/built-in-nodes/BatchLatentsNode", "ja/built-in-nodes/LatentBatch", "ja/built-in-nodes/LatentFromBatch", "ja/built-in-nodes/RebatchLatents", @@ -6608,28 +6659,71 @@ ] }, { - "group": "\u753b\u50cf", + "group": "Cosmos", + "pages": [ + "ja/built-in-nodes/EmptyCosmosLatentVideo" + ] + }, + { + "group": "Flux", + "pages": [ + "ja/built-in-nodes/EmptyFlux2LatentImage" + ] + }, + { + "group": "Hidream", "pages": [ "ja/built-in-nodes/EmptyHiDreamO1LatentImage" ] }, { - "group": "\u30a4\u30f3\u30da\u30a4\u30f3\u30c8", + "group": "Hunyhuan Video", "pages": [ - "ja/built-in-nodes/SetLatentNoiseMask", - "ja/built-in-nodes/VAEEncodeForInpaint" + "ja/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel" ] }, { - "group": "Qwen", + "group": "Hunyuan 3D", "pages": [ - "ja/built-in-nodes/EmptyQwenImageLayeredLatentImage" + "ja/built-in-nodes/EmptyLatentHunyuan3Dv2", + "ja/built-in-nodes/VAEDecodeHunyuan3D" ] }, { - "group": "SD3", + "group": "Hunyuan Image", "pages": [ - "ja/built-in-nodes/EmptySD3LatentImage" + "ja/built-in-nodes/EmptyHunyuanImageLatent" + ] + }, + { + "group": "Hunyuan Video", + "pages": [ + "ja/built-in-nodes/EmptyHunyuanLatentVideo", + "ja/built-in-nodes/EmptyHunyuanVideo15Latent" + ] + }, + { + "group": "Ltxv", + "pages": [ + "ja/built-in-nodes/EmptyLTXVLatentVideo", + "ja/built-in-nodes/LTXVAudioVAEDecode", + "ja/built-in-nodes/LTXVAudioVAEEncode", + "ja/built-in-nodes/LTXVConcatAVLatent", + "ja/built-in-nodes/LTXVEmptyLatentAudio", + "ja/built-in-nodes/LTXVLatentUpsampler", + "ja/built-in-nodes/LTXVSeparateAVLatent" + ] + }, + { + "group": "Mochi", + "pages": [ + "ja/built-in-nodes/EmptyMochiLatentVideo" + ] + }, + { + "group": "Qwen", + "pages": [ + "ja/built-in-nodes/EmptyQwenImageLayeredLatentImage" ] }, { @@ -6640,7 +6734,13 @@ ] }, { - "group": "\u5909\u63db", + "group": "Stable Diffusion", + "pages": [ + "ja/built-in-nodes/EmptySD3LatentImage" + ] + }, + { + "group": "Transform", "pages": [ "ja/built-in-nodes/LatentCrop", "ja/built-in-nodes/LatentFlip", @@ -6648,67 +6748,116 @@ ] }, { - "group": "\u30d3\u30c7\u30aa", + "group": "Triposplat", "pages": [ - { - "group": "LTXV", - "pages": [ - "ja/built-in-nodes/EmptyLTXVLatentVideo", - "ja/built-in-nodes/LTXVConcatAVLatent", - "ja/built-in-nodes/LTXVSeparateAVLatent" - ] - }, - "ja/built-in-nodes/EmptyARVideoLatent", - "ja/built-in-nodes/EmptyCosmosLatentVideo", - "ja/built-in-nodes/EmptyHunyuanLatentVideo", - "ja/built-in-nodes/EmptyHunyuanVideo15Latent", - "ja/built-in-nodes/EmptyMochiLatentVideo", - "ja/built-in-nodes/LTXVLatentUpsampler", - "ja/built-in-nodes/TrimVideoLatent", - "ja/built-in-nodes/VOIDWarpedNoise" + "ja/built-in-nodes/TripoSplatSamplingPreview", + "ja/built-in-nodes/VAEDecodeTripoSplat" + ] + }, + { + "group": "Void", + "pages": [ + "ja/built-in-nodes/VOIDWarpedNoise", + "ja/built-in-nodes/VOIDWarpedNoiseSource" ] }, - "ja/built-in-nodes/BatchLatentsNode", - "ja/built-in-nodes/EmptyFlux2LatentImage", - "ja/built-in-nodes/EmptyHunyuanImageLatent", + "ja/built-in-nodes/EmptyLatentAudio", "ja/built-in-nodes/EmptyLatentImage", - "ja/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel", "ja/built-in-nodes/LatentComposite", "ja/built-in-nodes/LatentCompositeMasked", "ja/built-in-nodes/LatentUpscale", "ja/built-in-nodes/LatentUpscaleBy", + "ja/built-in-nodes/LoadLatent", + "ja/built-in-nodes/SaveLatent", + "ja/built-in-nodes/SetLatentNoiseMask", + "ja/built-in-nodes/TrimVideoLatent", "ja/built-in-nodes/VAEDecode", - "ja/built-in-nodes/VAEEncode" + "ja/built-in-nodes/VAEDecodeAudio", + "ja/built-in-nodes/VAEDecodeAudioTiled", + "ja/built-in-nodes/VAEDecodeTiled", + "ja/built-in-nodes/VAEEncode", + "ja/built-in-nodes/VAEEncodeAudio", + "ja/built-in-nodes/VAEEncodeForInpaint", + "ja/built-in-nodes/VAEEncodeTiled" ] }, { - "group": "\u30ed\u30fc\u30c0\u30fc", + "group": "Loaders", "pages": [ "ja/built-in-nodes/AudioEncoderLoader", + "ja/built-in-nodes/CheckpointLoader", "ja/built-in-nodes/CheckpointLoaderSimple", + "ja/built-in-nodes/ClipLoader", "ja/built-in-nodes/ClipVisionLoader", "ja/built-in-nodes/DiffControlNetLoader", + "ja/built-in-nodes/DiffusersLoader", + "ja/built-in-nodes/DualCLIPLoader", "ja/built-in-nodes/FrameInterpolationModelLoader", "ja/built-in-nodes/GLIGENLoader", "ja/built-in-nodes/HypernetworkLoader", "ja/built-in-nodes/ImageOnlyCheckpointLoader", "ja/built-in-nodes/LatentUpscaleModelLoader", "ja/built-in-nodes/LoadBackgroundRemovalModel", + "ja/built-in-nodes/LoadDA3Model", "ja/built-in-nodes/LoadMediaPipeFaceLandmarker", "ja/built-in-nodes/LoadMoGeModel", "ja/built-in-nodes/LoraLoaderBypass", "ja/built-in-nodes/LoraLoaderBypassModelOnly", "ja/built-in-nodes/LoraModelLoader", + "ja/built-in-nodes/LTXAVTextEncoderLoader", "ja/built-in-nodes/LTXVAudioVAELoader", + "ja/built-in-nodes/ModelPatchLoader", "ja/built-in-nodes/OpticalFlowLoader", + "ja/built-in-nodes/PhotoMakerLoader", + "ja/built-in-nodes/QuadrupleCLIPLoader", "ja/built-in-nodes/StyleModelLoader", + "ja/built-in-nodes/TripleCLIPLoader", "ja/built-in-nodes/unCLIPCheckpointLoader", + "ja/built-in-nodes/UNETLoader", "ja/built-in-nodes/UpscaleModelLoader", "ja/built-in-nodes/VAELoader" ] }, { - "group": "\u30d1\u30c3\u30c1", + "group": "Merging", + "pages": [ + { + "group": "Model Specific", + "pages": [ + "ja/built-in-nodes/ModelMergeAuraflow", + "ja/built-in-nodes/ModelMergeCosmos14B", + "ja/built-in-nodes/ModelMergeCosmos7B", + "ja/built-in-nodes/ModelMergeCosmosPredict2_14B", + "ja/built-in-nodes/ModelMergeCosmosPredict2_2B", + "ja/built-in-nodes/ModelMergeFlux1", + "ja/built-in-nodes/ModelMergeKrea2", + "ja/built-in-nodes/ModelMergeLTXV", + "ja/built-in-nodes/ModelMergeMochiPreview", + "ja/built-in-nodes/ModelMergeQwenImage", + "ja/built-in-nodes/ModelMergeSD1", + "ja/built-in-nodes/ModelMergeSD35_Large", + "ja/built-in-nodes/ModelMergeSD3_2B", + "ja/built-in-nodes/ModelMergeSDXL", + "ja/built-in-nodes/ModelMergeWAN2_1" + ] + }, + "ja/built-in-nodes/CheckpointSave", + "ja/built-in-nodes/ClipMergeAdd", + "ja/built-in-nodes/ClipMergeSimple", + "ja/built-in-nodes/ClipMergeSubtract", + "ja/built-in-nodes/ClipSave", + "ja/built-in-nodes/ImageOnlyCheckpointSave", + "ja/built-in-nodes/ModelMergeAdd", + "ja/built-in-nodes/ModelMergeBlocks", + "ja/built-in-nodes/ModelMergeSimple", + "ja/built-in-nodes/ModelMergeSubtract", + "ja/built-in-nodes/ModelSave", + "ja/built-in-nodes/SaveLoRA", + "ja/built-in-nodes/VAESave" + ] + }, + { + "group": "Patch", "pages": [ { "group": "Chroma Radiance", @@ -6719,17 +6868,48 @@ { "group": "Flux", "pages": [ + "ja/built-in-nodes/ModelSamplingFlux", "ja/built-in-nodes/USOStyleReference" ] }, { - "group": "SUPIR", + "group": "Hidream", + "pages": [ + "ja/built-in-nodes/HiDreamO1PatchSeamSmoothing" + ] + }, + { + "group": "Ltxv", + "pages": [ + "ja/built-in-nodes/ModelSamplingLTXV" + ] + }, + { + "group": "Qwen", + "pages": [ + "ja/built-in-nodes/QwenImageDiffsynthControlnet" + ] + }, + { + "group": "Stable Cascade", + "pages": [ + "ja/built-in-nodes/ModelSamplingStableCascade" + ] + }, + { + "group": "Stable Diffusion", + "pages": [ + "ja/built-in-nodes/ModelSamplingSD3" + ] + }, + { + "group": "Supir", "pages": [ "ja/built-in-nodes/SUPIRApply" ] }, { - "group": "UNet", + "group": "Unet", "pages": [ "ja/built-in-nodes/Epsilon Scaling", "ja/built-in-nodes/FreeU", @@ -6741,16 +6921,35 @@ "ja/built-in-nodes/TomePatchModel" ] }, + { + "group": "Wan", + "pages": [ + "ja/built-in-nodes/WanContextWindowsManual" + ] + }, + { + "group": "Z Image", + "pages": [ + "ja/built-in-nodes/ZImageFunControlnet" + ] + }, "ja/built-in-nodes/ContextWindowsManual", - "ja/built-in-nodes/ScaleROPE", - "ja/built-in-nodes/WanContextWindowsManual" + "ja/built-in-nodes/LTXVContextWindows", + "ja/built-in-nodes/ModelNoiseScale", + "ja/built-in-nodes/ModelSamplingAuraFlow", + "ja/built-in-nodes/ModelSamplingContinuousEDM", + "ja/built-in-nodes/ModelSamplingContinuousV", + "ja/built-in-nodes/ModelSamplingDiscrete", + "ja/built-in-nodes/RenormCFG", + "ja/built-in-nodes/RescaleCFG", + "ja/built-in-nodes/ScaleROPE" ] }, { - "group": "\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0", + "group": "Sampling", "pages": [ { - "group": "\u30ab\u30b9\u30bf\u30e0\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0", + "group": "Custom", "pages": [ "ja/built-in-nodes/APG", "ja/built-in-nodes/SamplerCustom", @@ -6762,6 +6961,7 @@ "pages": [ "ja/built-in-nodes/BasicGuider", "ja/built-in-nodes/CFGGuider", + "ja/built-in-nodes/CFGOverride", "ja/built-in-nodes/DualCFGGuider", "ja/built-in-nodes/DualModelGuider", "ja/built-in-nodes/VideoLinearCFGGuidance", @@ -6769,15 +6969,15 @@ ] }, { - "group": "\u30ce\u30a4\u30ba", + "group": "Noise", "pages": [ + "ja/built-in-nodes/AddNoise", "ja/built-in-nodes/DisableNoise", - "ja/built-in-nodes/RandomNoise", - "ja/built-in-nodes/VOIDWarpedNoiseSource" + "ja/built-in-nodes/RandomNoise" ] }, { - "group": "\u30b5\u30f3\u30d7\u30e9\u30fc", + "group": "Samplers", "pages": [ "ja/built-in-nodes/KSamplerSelect", "ja/built-in-nodes/SamplerARVideo", @@ -6798,7 +6998,7 @@ ] }, { - "group": "\u30b9\u30b1\u30b8\u30e5\u30fc\u30e9\u30fc", + "group": "Schedulers", "pages": [ "ja/built-in-nodes/AlignYourStepsScheduler", "ja/built-in-nodes/BasicScheduler", @@ -6806,6 +7006,7 @@ "ja/built-in-nodes/ExponentialScheduler", "ja/built-in-nodes/Flux2Scheduler", "ja/built-in-nodes/GITSScheduler", + "ja/built-in-nodes/Ideogram4Scheduler", "ja/built-in-nodes/KarrasScheduler", "ja/built-in-nodes/LaplaceScheduler", "ja/built-in-nodes/LTXVScheduler", @@ -6816,10 +7017,11 @@ ] }, { - "group": "\u30b7\u30b0\u30de", + "group": "Sigmas", "pages": [ "ja/built-in-nodes/ExtendIntermediateSigmas", "ja/built-in-nodes/FlipSigmas", + "ja/built-in-nodes/ManualSigmas", "ja/built-in-nodes/SamplingPercentToSigma", "ja/built-in-nodes/SetFirstSigma", "ja/built-in-nodes/SplitSigmas", @@ -6831,7 +7033,7 @@ ] }, { - "group": "\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0", + "group": "Training", "pages": [ "ja/built-in-nodes/LoadTrainingDataset", "ja/built-in-nodes/LossGraphNode", @@ -6844,7 +7046,7 @@ ] }, { - "group": "\u30d1\u30fc\u30c8\u30ca\u30fc", + "group": "Partner", "pages": [ { "group": "3D", @@ -6889,6 +7091,7 @@ "pages": [ "ja/built-in-nodes/TripoConversionNode", "ja/built-in-nodes/TripoImageToModelNode", + "ja/built-in-nodes/TripoImportModelNode", "ja/built-in-nodes/TripoMultiviewToModelNode", "ja/built-in-nodes/TripoP1ImageToModelNode", "ja/built-in-nodes/TripoP1MultiviewToModelNode", @@ -6903,8 +7106,14 @@ ] }, { - "group": "\u30aa\u30fc\u30c7\u30a3\u30aa", + "group": "Audio", "pages": [ + { + "group": "Bytedance", + "pages": [ + "ja/built-in-nodes/ByteDanceSeedAudio" + ] + }, { "group": "Elevenlabs", "pages": [ @@ -6924,19 +7133,11 @@ "ja/built-in-nodes/SoniloTextToMusic", "ja/built-in-nodes/SoniloVideoToMusic" ] - }, - { - "group": "Stability AI", - "pages": [ - "ja/built-in-nodes/StabilityAudioInpaint", - "ja/built-in-nodes/StabilityAudioToAudio", - "ja/built-in-nodes/StabilityTextToAudio" - ] } ] }, { - "group": "\u753b\u50cf", + "group": "Image", "pages": [ { "group": "Beeble", @@ -6989,7 +7190,7 @@ ] }, { - "group": "HitPaw", + "group": "Hitpaw", "pages": [ "ja/built-in-nodes/HitPawGeneralImageEnhance" ] @@ -6997,8 +7198,6 @@ { "group": "Ideogram", "pages": [ - "ja/built-in-nodes/IdeogramV1", - "ja/built-in-nodes/IdeogramV2", "ja/built-in-nodes/IdeogramV3", "ja/built-in-nodes/IdeogramV4" ] @@ -7039,7 +7238,7 @@ ] }, { - "group": "OpenAI", + "group": "Openai", "pages": [ "ja/built-in-nodes/OpenAIDalle2", "ja/built-in-nodes/OpenAIDalle3", @@ -7092,16 +7291,6 @@ "ja/built-in-nodes/RunwayTextToImageNode" ] }, - { - "group": "Stability AI", - "pages": [ - "ja/built-in-nodes/StabilityStableImageSD_3_5Node", - "ja/built-in-nodes/StabilityStableImageUltraNode", - "ja/built-in-nodes/StabilityUpscaleConservativeNode", - "ja/built-in-nodes/StabilityUpscaleCreativeNode", - "ja/built-in-nodes/StabilityUpscaleFastNode" - ] - }, { "group": "Topaz", "pages": [ @@ -7124,7 +7313,7 @@ ] }, { - "group": "\u30c6\u30ad\u30b9\u30c8", + "group": "Text", "pages": [ { "group": "Anthropic", @@ -7142,11 +7331,12 @@ "group": "Gemini", "pages": [ "ja/built-in-nodes/GeminiInputFiles", - "ja/built-in-nodes/GeminiNode" + "ja/built-in-nodes/GeminiNode", + "ja/built-in-nodes/GeminiNodeV2" ] }, { - "group": "OpenAI", + "group": "Openai", "pages": [ "ja/built-in-nodes/OpenAIChatConfig", "ja/built-in-nodes/OpenAIChatNode", @@ -7154,7 +7344,7 @@ ] }, { - "group": "OpenRouter", + "group": "Openrouter", "pages": [ "ja/built-in-nodes/OpenRouterLLMNode" ] @@ -7162,7 +7352,7 @@ ] }, { - "group": "\u30d3\u30c7\u30aa", + "group": "Video", "pages": [ { "group": "Beeble", @@ -7192,6 +7382,12 @@ "ja/built-in-nodes/ByteDanceTextToVideoNode" ] }, + { + "group": "Gemini", + "pages": [ + "ja/built-in-nodes/GeminiVideoOmni" + ] + }, { "group": "Grok", "pages": [ @@ -7202,7 +7398,7 @@ ] }, { - "group": "HitPaw", + "group": "Hitpaw", "pages": [ "ja/built-in-nodes/HitPawVideoEnhance" ] @@ -7235,7 +7431,7 @@ ] }, { - "group": "LTXV", + "group": "Ltxv", "pages": [ "ja/built-in-nodes/LtxvApiImageToVideo", "ja/built-in-nodes/LtxvApiTextToVideo" @@ -7246,6 +7442,13 @@ "pages": [ "ja/built-in-nodes/LumaConceptsNode", "ja/built-in-nodes/LumaImageToVideoNode", + "ja/built-in-nodes/LumaRay32ExtendVideoNode", + "ja/built-in-nodes/LumaRay32ImageToVideoNode", + "ja/built-in-nodes/LumaRay32KeyframeNode", + "ja/built-in-nodes/LumaRay32KeyframesToVideoNode", + "ja/built-in-nodes/LumaRay32TextToVideoNode", + "ja/built-in-nodes/LumaRay32VideoEditNode", + "ja/built-in-nodes/LumaRay32VideoReframeNode", "ja/built-in-nodes/LumaVideoNode" ] }, @@ -7259,7 +7462,7 @@ ] }, { - "group": "PixVerse", + "group": "Pixverse", "pages": [ "ja/built-in-nodes/PixverseImageToVideoNode", "ja/built-in-nodes/PixverseTemplateNode", @@ -7270,6 +7473,9 @@ { "group": "Runway", "pages": [ + "ja/built-in-nodes/RunwayAleph2KeyframeNode", + "ja/built-in-nodes/RunwayAleph2PromptImageNode", + "ja/built-in-nodes/RunwayAleph2VideoToVideoNode", "ja/built-in-nodes/RunwayFirstLastFrameNode", "ja/built-in-nodes/RunwayImageToVideoNodeGen3a", "ja/built-in-nodes/RunwayImageToVideoNodeGen4" @@ -7338,129 +7544,466 @@ ] } ] - } + } + ] + }, + { + "group": "Text", + "pages": [ + "ja/built-in-nodes/AddTextPrefix", + "ja/built-in-nodes/AddTextSuffix", + "ja/built-in-nodes/BuildJsonPromptIdeogram", + "ja/built-in-nodes/CaseConverter", + "ja/built-in-nodes/ConvertArrayToString", + "ja/built-in-nodes/ConvertDictionaryToString", + "ja/built-in-nodes/JsonExtractString", + "ja/built-in-nodes/MergeTextLists", + "ja/built-in-nodes/RegexExtract", + "ja/built-in-nodes/RegexMatch", + "ja/built-in-nodes/RegexReplace", + "ja/built-in-nodes/ReplaceText", + "ja/built-in-nodes/StringCompare", + "ja/built-in-nodes/StringConcatenate", + "ja/built-in-nodes/StringContains", + "ja/built-in-nodes/StringFormat", + "ja/built-in-nodes/StringLength", + "ja/built-in-nodes/StringReplace", + "ja/built-in-nodes/StringSubstring", + "ja/built-in-nodes/StringTrim", + "ja/built-in-nodes/StripWhitespace", + "ja/built-in-nodes/TextGenerate", + "ja/built-in-nodes/TextGenerateLTX2Prompt", + "ja/built-in-nodes/TextToLowercase", + "ja/built-in-nodes/TextToUppercase", + "ja/built-in-nodes/TruncateText" + ] + }, + { + "group": "Utilities", + "pages": [ + { + "group": "Logic", + "pages": [ + "ja/built-in-nodes/AutogrowNamesTestNode", + "ja/built-in-nodes/AutogrowPrefixTestNode", + "ja/built-in-nodes/ComboOptionTestNode", + "ja/built-in-nodes/ComfyAndNode", + "ja/built-in-nodes/ComfyNotNode", + "ja/built-in-nodes/ComfyOrNode", + "ja/built-in-nodes/ComfySoftSwitchNode", + "ja/built-in-nodes/ComfySwitchNode", + "ja/built-in-nodes/ConvertStringToComboNode", + "ja/built-in-nodes/DCTestNode", + "ja/built-in-nodes/InvertBooleanNode" + ] + }, + { + "group": "Primitive", + "pages": [ + "ja/built-in-nodes/PrimitiveBoolean", + "ja/built-in-nodes/PrimitiveBoundingBox", + "ja/built-in-nodes/PrimitiveFloat", + "ja/built-in-nodes/PrimitiveInt", + "ja/built-in-nodes/PrimitiveString", + "ja/built-in-nodes/PrimitiveStringMultiline" + ] + }, + "ja/built-in-nodes/ColorToRGBInt", + "ja/built-in-nodes/ComfyMathExpression", + "ja/built-in-nodes/ComfyNumberConvert", + "ja/built-in-nodes/CreateBoundingBoxes", + "ja/built-in-nodes/CreateList", + "ja/built-in-nodes/CurveEditor", + "ja/built-in-nodes/CustomCombo", + "ja/built-in-nodes/ImageHistogram", + "ja/built-in-nodes/PreviewAny", + "ja/built-in-nodes/ResolutionSelector", + "ja/built-in-nodes/SeedNode" + ] + }, + { + "group": "Video", + "pages": [ + { + "group": "Preprocessors", + "pages": [ + "ja/built-in-nodes/LTXVPreprocess" + ] + }, + "ja/built-in-nodes/CreateVideo", + "ja/built-in-nodes/FrameInterpolate", + "ja/built-in-nodes/GetVideoComponents", + "ja/built-in-nodes/LoadVideo", + "ja/built-in-nodes/SaveVideo", + "ja/built-in-nodes/SaveWEBM", + "ja/built-in-nodes/Video Slice" + ] + }, + { + "group": "サンプリング", + "pages": [ + { + "group": "Custom Sampling", + "pages": [ + { + "group": "Samplers", + "pages": [ + "ja/built-in-nodes/SamplerDpmpp2mSde", + "ja/built-in-nodes/SamplerDpmppSde" + ] + } + ] + } + ] + }, + { + "group": "ユーティリティ", + "pages": [ + "ja/built-in-nodes/BatchImagesMasksLatentsNode", + "ja/built-in-nodes/MarkdownNote", + "ja/built-in-nodes/Note", + "ja/built-in-nodes/Reroute", + "ja/built-in-nodes/TerminalLog", + "ja/built-in-nodes/wanBlockSwap" + ] + }, + { + "group": "ローダー", + "pages": [ + "ja/built-in-nodes/ControlNetLoader" + ] + }, + { + "group": "上級", + "pages": [ + { + "group": "Debug", + "pages": [ + "ja/built-in-nodes/EasyCache", + "ja/built-in-nodes/LazyCache", + "ja/built-in-nodes/ModelComputeDtype" + ] + }, + { + "group": "Guidance", + "pages": [ + "ja/built-in-nodes/CFGNorm", + "ja/built-in-nodes/CFGZeroStar", + "ja/built-in-nodes/NAGuidance", + "ja/built-in-nodes/SkipLayerGuidanceDiT", + "ja/built-in-nodes/SkipLayerGuidanceDiTSimple", + "ja/built-in-nodes/SkipLayerGuidanceSD3", + "ja/built-in-nodes/TCFG" + ] + }, + { + "group": "Hooks", + "pages": [ + { + "group": "Clip", + "pages": [ + "ja/built-in-nodes/SetClipHooks" + ] + }, + { + "group": "Combine", + "pages": [ + "ja/built-in-nodes/CombineHooks", + "ja/built-in-nodes/CombineHooksEight", + "ja/built-in-nodes/CombineHooksFour" + ] + }, + { + "group": "Cond Pair", + "pages": [ + "ja/built-in-nodes/PairConditioningCombine", + "ja/built-in-nodes/PairConditioningSetDefaultAndCombine", + "ja/built-in-nodes/PairConditioningSetProperties", + "ja/built-in-nodes/PairConditioningSetPropertiesAndCombine" + ] + }, + { + "group": "Cond Single", + "pages": [ + "ja/built-in-nodes/ConditioningSetDefaultAndCombine", + "ja/built-in-nodes/ConditioningSetProperties", + "ja/built-in-nodes/ConditioningSetPropertiesAndCombine" + ] + }, + { + "group": "Create", + "pages": [ + "ja/built-in-nodes/CreateHookLora", + "ja/built-in-nodes/CreateHookLoraModelOnly", + "ja/built-in-nodes/CreateHookModelAsLora", + "ja/built-in-nodes/CreateHookModelAsLoraModelOnly" + ] + }, + { + "group": "Manual", + "pages": [ + "ja/built-in-nodes/SetModelHooksOnCond" + ] + }, + { + "group": "Scheduling", + "pages": [ + "ja/built-in-nodes/CreateHookKeyframe", + "ja/built-in-nodes/CreateHookKeyframesFromFloats", + "ja/built-in-nodes/CreateHookKeyframesInterpolated", + "ja/built-in-nodes/SetHookKeyframes" + ] + }, + "ja/built-in-nodes/ConditioningTimestepsRange" + ] + }, + { + "group": "Loaders", + "pages": [ + "ja/built-in-nodes/DeprecatedCheckpointLoader", + "ja/built-in-nodes/DeprecatedDiffusersLoader" + ] + }, + { + "group": "Model Merging", + "pages": [ + "ja/built-in-nodes/SaveLoRANode" + ] + }, + { + "group": "Multigpu", + "pages": [ + "ja/built-in-nodes/MultiGPU_Options", + "ja/built-in-nodes/MultiGPU_WorkUnits", + "ja/built-in-nodes/SelectCLIPDevice", + "ja/built-in-nodes/SelectModelDevice", + "ja/built-in-nodes/SelectVAEDevice" + ] + }, + "ja/built-in-nodes/IdeogramV1", + "ja/built-in-nodes/IdeogramV2", + "ja/built-in-nodes/MoonvalleyImg2VideoNode", + "ja/built-in-nodes/MoonvalleyTxt2VideoNode", + "ja/built-in-nodes/MoonvalleyVideo2VideoNode", + "ja/built-in-nodes/SeedVR2Conditioning", + "ja/built-in-nodes/SeedVR2PostProcessing", + "ja/built-in-nodes/SeedVR2Preprocess", + "ja/built-in-nodes/SeedVR2ProgressiveSampler", + "ja/built-in-nodes/StabilityAudioInpaint", + "ja/built-in-nodes/StabilityAudioToAudio", + "ja/built-in-nodes/StabilityStableImageSD_3_5Node", + "ja/built-in-nodes/StabilityStableImageUltraNode", + "ja/built-in-nodes/StabilityTextToAudio", + "ja/built-in-nodes/StabilityUpscaleConservativeNode", + "ja/built-in-nodes/StabilityUpscaleCreativeNode", + "ja/built-in-nodes/StabilityUpscaleFastNode" ] }, { - "group": "\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0", + "group": "条件付け", "pages": [ { - "group": "\u30ab\u30b9\u30bf\u30e0\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0", + "group": "Video Models", "pages": [ - { - "group": "\u30b5\u30f3\u30d7\u30e9\u30fc", - "pages": [ - "ja/built-in-nodes/SamplerDpmpp2mSde", - "ja/built-in-nodes/SamplerDpmppSde" - ] - }, - { - "group": "\u30b9\u30b1\u30b8\u30e5\u30fc\u30e9\u30fc", - "pages": [ - "ja/built-in-nodes/Ideogram4Scheduler" - ] - }, - "ja/built-in-nodes/CFGOverride" + "ja/built-in-nodes/conditioning/video-models/wan-vace-to-video", + "ja/built-in-nodes/Stablezero123Conditioning", + "ja/built-in-nodes/Stablezero123ConditioningBatched", + "ja/built-in-nodes/SVD_img2vid_Conditioning", + "ja/built-in-nodes/SvdImg2vidConditioning" ] - } + }, + "ja/built-in-nodes/ConditioningAverage", + "ja/built-in-nodes/Sd4xupscaleConditioning" ] }, { - "group": "\u30c6\u30ad\u30b9\u30c8", + "group": "潜在変数", "pages": [ - "ja/built-in-nodes/AddTextPrefix", - "ja/built-in-nodes/AddTextSuffix", - "ja/built-in-nodes/CaseConverter", - "ja/built-in-nodes/JsonExtractString", - "ja/built-in-nodes/MergeTextLists", - "ja/built-in-nodes/RegexExtract", - "ja/built-in-nodes/RegexMatch", - "ja/built-in-nodes/RegexReplace", - "ja/built-in-nodes/ReplaceText", - "ja/built-in-nodes/StringCompare", - "ja/built-in-nodes/StringConcatenate", - "ja/built-in-nodes/StringContains", - "ja/built-in-nodes/StringFormat", - "ja/built-in-nodes/StringLength", - "ja/built-in-nodes/StringReplace", - "ja/built-in-nodes/StringSubstring", - "ja/built-in-nodes/StringTrim", - "ja/built-in-nodes/StripWhitespace", - "ja/built-in-nodes/TextGenerate", - "ja/built-in-nodes/TextGenerateLTX2Prompt", - "ja/built-in-nodes/TextToLowercase", - "ja/built-in-nodes/TextToUppercase", - "ja/built-in-nodes/TruncateText" + { + "group": "Video", + "pages": [ + "ja/built-in-nodes/latent/video/trim-video-latent" + ] + } ] }, { - "group": "\u30e6\u30fc\u30c6\u30a3\u30ea\u30c6\u30a3", + "group": "画像", "pages": [ { - "group": "\u30ed\u30b8\u30c3\u30af", + "group": "Adjustments", "pages": [ - "ja/built-in-nodes/AutogrowNamesTestNode", - "ja/built-in-nodes/AutogrowPrefixTestNode", - "ja/built-in-nodes/ComboOptionTestNode", - "ja/built-in-nodes/ComfyAndNode", - "ja/built-in-nodes/ComfyNotNode", - "ja/built-in-nodes/ComfyOrNode", - "ja/built-in-nodes/ComfySoftSwitchNode", - "ja/built-in-nodes/ComfySwitchNode", - "ja/built-in-nodes/ConvertStringToComboNode", - "ja/built-in-nodes/DCTestNode", - "ja/built-in-nodes/InvertBooleanNode" + "ja/built-in-nodes/AdjustBrightness", + "ja/built-in-nodes/AdjustContrast" ] }, { - "group": "\u30d7\u30ea\u30df\u30c6\u30a3\u30d6", + "group": "Background Removal", "pages": [ - "ja/built-in-nodes/PrimitiveBoolean", - "ja/built-in-nodes/PrimitiveBoundingBox", - "ja/built-in-nodes/PrimitiveFloat", - "ja/built-in-nodes/PrimitiveInt", - "ja/built-in-nodes/PrimitiveString", - "ja/built-in-nodes/PrimitiveStringMultiline" + "ja/built-in-nodes/RemoveBackground" ] }, - "ja/built-in-nodes/ColorToRGBInt", - "ja/built-in-nodes/ComfyMathExpression", - "ja/built-in-nodes/ComfyNumberConvert", - "ja/built-in-nodes/CreateList", - "ja/built-in-nodes/CurveEditor", - "ja/built-in-nodes/CustomCombo", - "ja/built-in-nodes/ImageHistogram", - "ja/built-in-nodes/PreviewAny", - "ja/built-in-nodes/ResolutionSelector" - ] - }, - { - "group": "\u30e6\u30fc\u30c6\u30a3\u30ea\u30c6\u30a3", - "pages": [ - "ja/built-in-nodes/BatchImagesMasksLatentsNode", - "ja/built-in-nodes/MarkdownNote", - "ja/built-in-nodes/Note", - "ja/built-in-nodes/Reroute", - "ja/built-in-nodes/TerminalLog", - "ja/built-in-nodes/wanBlockSwap" - ] - }, - { - "group": "\u30d3\u30c7\u30aa", - "pages": [ { - "group": "\u30d7\u30ea\u30d7\u30ed\u30bb\u30c3\u30b5", + "group": "Batch", "pages": [ - "ja/built-in-nodes/LTXVPreprocess" + "ja/built-in-nodes/ImageDeduplication", + "ja/built-in-nodes/ImageFromBatch", + "ja/built-in-nodes/ImageGrid", + "ja/built-in-nodes/ImageMergeTileList", + "ja/built-in-nodes/MergeImageLists", + "ja/built-in-nodes/RebatchImages", + "ja/built-in-nodes/RepeatImageBatch", + "ja/built-in-nodes/ShuffleDataset", + "ja/built-in-nodes/ShuffleImageTextDataset", + "ja/built-in-nodes/SplitImageToTileList" ] }, - "ja/built-in-nodes/CreateVideo", - "ja/built-in-nodes/FrameInterpolate", - "ja/built-in-nodes/GetVideoComponents", - "ja/built-in-nodes/LoadVideo", - "ja/built-in-nodes/SaveVideo", - "ja/built-in-nodes/SaveWEBM", - "ja/built-in-nodes/Video Slice" + { + "group": "Color", + "pages": [ + "ja/built-in-nodes/ImageRGBToYUV", + "ja/built-in-nodes/ImageYUVToRGB", + "ja/built-in-nodes/NormalizeImages" + ] + }, + { + "group": "Compositing", + "pages": [ + "ja/built-in-nodes/ImageCompositeMasked", + "ja/built-in-nodes/JoinImageWithAlpha", + "ja/built-in-nodes/PorterDuffImageComposite", + "ja/built-in-nodes/SplitImageWithAlpha" + ] + }, + { + "group": "Detection", + "pages": [ + "ja/built-in-nodes/DrawBBoxes", + "ja/built-in-nodes/MediaPipeFaceLandmarker", + "ja/built-in-nodes/MediaPipeFaceMask", + "ja/built-in-nodes/MediaPipeFaceMeshVisualize", + "ja/built-in-nodes/RTDETR_detect", + "ja/built-in-nodes/SAM3_Detect", + "ja/built-in-nodes/SAM3_TrackPreview", + "ja/built-in-nodes/SAM3_TrackToMask", + "ja/built-in-nodes/SAM3_VideoTrack", + "ja/built-in-nodes/SDPoseDrawKeypoints", + "ja/built-in-nodes/SDPoseFaceBBoxes", + "ja/built-in-nodes/SDPoseKeypointExtractor" + ] + }, + { + "group": "Filters", + "pages": [ + "ja/built-in-nodes/Canny", + "ja/built-in-nodes/ColorTransfer", + "ja/built-in-nodes/ImageAddNoise", + "ja/built-in-nodes/ImageBlend", + "ja/built-in-nodes/ImageBlur", + "ja/built-in-nodes/ImageQuantize", + "ja/built-in-nodes/ImageSharpen", + "ja/built-in-nodes/Morphology" + ] + }, + { + "group": "Geometry Estimation", + "pages": [ + "ja/built-in-nodes/DA3GeometryToMesh", + "ja/built-in-nodes/DA3GeometryToPointCloud", + "ja/built-in-nodes/DA3Inference", + "ja/built-in-nodes/DA3Render", + "ja/built-in-nodes/MoGeInference", + "ja/built-in-nodes/MoGePanoramaInference", + "ja/built-in-nodes/MoGePointMapToMesh", + "ja/built-in-nodes/MoGeRender" + ] + }, + { + "group": "Mask", + "pages": [ + "ja/built-in-nodes/BatchMasksNode", + "ja/built-in-nodes/CropMask", + "ja/built-in-nodes/FeatherMask", + "ja/built-in-nodes/GrowMask", + "ja/built-in-nodes/ImageColorToMask", + "ja/built-in-nodes/ImageToMask", + "ja/built-in-nodes/InvertMask", + "ja/built-in-nodes/MaskComposite", + "ja/built-in-nodes/MaskPreview", + "ja/built-in-nodes/MaskToImage", + "ja/built-in-nodes/SolidMask", + "ja/built-in-nodes/ThresholdMask", + "ja/built-in-nodes/VOIDQuadmaskPreprocess" + ] + }, + { + "group": "Shader", + "pages": [ + "ja/built-in-nodes/GLSLShader" + ] + }, + { + "group": "Transform", + "pages": [ + "ja/built-in-nodes/CenterCropImages", + "ja/built-in-nodes/CropByBBoxes", + "ja/built-in-nodes/ImageCrop", + "ja/built-in-nodes/ImageCropV2", + "ja/built-in-nodes/ImageFlip", + "ja/built-in-nodes/ImagePadForOutpaint", + "ja/built-in-nodes/ImageRotate", + "ja/built-in-nodes/ImageStitch", + "ja/built-in-nodes/RandomCropImages", + "ja/built-in-nodes/ResizeAndPadImage", + "ja/built-in-nodes/ResizeImagesByLongerEdge", + "ja/built-in-nodes/ResizeImagesByShorterEdge" + ] + }, + { + "group": "Upscaling", + "pages": [ + "ja/built-in-nodes/ImageScale", + "ja/built-in-nodes/ImageScaleBy", + "ja/built-in-nodes/ImageScaleToMaxDimension", + "ja/built-in-nodes/ImageScaleToTotalPixels", + "ja/built-in-nodes/ImageUpscaleWithModel" + ] + }, + { + "group": "Video", + "pages": [ + "ja/built-in-nodes/WanDancerPadKeyframes", + "ja/built-in-nodes/WanDancerPadKeyframesList" + ] + }, + "ja/built-in-nodes/BatchImagesNode", + "ja/built-in-nodes/ConditioningCombine", + "ja/built-in-nodes/EmptyImage", + "ja/built-in-nodes/GetImageSize", + "ja/built-in-nodes/ImageBatch", + "ja/built-in-nodes/ImageCompare", + "ja/built-in-nodes/ImageInvert", + "ja/built-in-nodes/LoadImage", + "ja/built-in-nodes/LoadImageDataSetFromFolder", + "ja/built-in-nodes/LoadImageMask", + "ja/built-in-nodes/LoadImageOutput", + "ja/built-in-nodes/LoadImageSetFromFolderNode", + "ja/built-in-nodes/LoadImageSetNode", + "ja/built-in-nodes/LoadImageTextDataSetFromFolder", + "ja/built-in-nodes/LoadImageTextSetFromFolderNode", + "ja/built-in-nodes/LoraLoader", + "ja/built-in-nodes/LoraLoaderModelOnly", + "ja/built-in-nodes/Painter", + "ja/built-in-nodes/PreviewImage", + "ja/built-in-nodes/ResizeImageMaskNode", + "ja/built-in-nodes/SaveAnimatedPNG", + "ja/built-in-nodes/SaveAnimatedWEBP", + "ja/built-in-nodes/SaveImage", + "ja/built-in-nodes/SaveImageAdvanced", + "ja/built-in-nodes/SaveImageDataSetToFolder", + "ja/built-in-nodes/SaveImageTextDataSetToFolder", + "ja/built-in-nodes/SaveSVGNode", + "ja/built-in-nodes/WebcamCapture" ] } ] @@ -7468,7 +8011,7 @@ ] }, { - "tab": "\u958b\u767a", + "tab": "開発", "pages": [ "ja/development/overview", { @@ -7511,12 +8054,12 @@ ] }, { - "group": "\u30ab\u30b9\u30bf\u30e0\u30ce\u30fc\u30c9\u958b\u767a", + "group": "カスタムノード開発", "pages": [ "ja/custom-nodes/overview", "ja/custom-nodes/walkthrough", { - "group": "\u30d0\u30c3\u30af\u30a8\u30f3\u30c9", + "group": "バックエンド", "icon": "python", "pages": [ "ja/custom-nodes/backend/server_overview", @@ -7561,7 +8104,7 @@ ] }, { - "group": "\u30ec\u30b8\u30b9\u30c8\u30ea\uff08Registry\uff09", + "group": "レジストリ（Registry）", "pages": [ "ja/registry/overview", "ja/registry/publishing", @@ -7573,7 +8116,7 @@ ] }, { - "group": "\u4ed5\u69d8", + "group": "仕様", "pages": [ { "group": "Workflow JSON", @@ -7583,7 +8126,7 @@ ] }, { - "group": "\u30ce\u30fc\u30c9\u5b9a\u7fa9", + "group": "ノード定義", "pages": [ "ja/specs/nodedef_json", "ja/specs/nodedef_json_1_0" @@ -7594,12 +8137,12 @@ ] }, { - "tab": "\u30b5\u30dd\u30fc\u30c8", + "tab": "サポート", "pages": [ "ja/support/contact-support", "ja/support/data-retention", { - "group": "\u30a2\u30ab\u30a6\u30f3\u30c8\u7ba1\u7406", + "group": "アカウント管理", "icon": "user", "pages": [ "ja/account/create-account", @@ -7608,10 +8151,10 @@ ] }, { - "group": "\u8acb\u6c42\u30b5\u30dd\u30fc\u30c8", + "group": "請求サポート", "pages": [ { - "group": "\u30b5\u30d6\u30b9\u30af\u30ea\u30d7\u30b7\u30e7\u30f3", + "group": "サブスクリプション", "pages": [ "ja/support/subscription/subscribing", "ja/support/subscription/managing", @@ -7620,7 +8163,7 @@ ] }, { - "group": "\u304a\u652f\u6255\u3044", + "group": "お支払い", "pages": [ "ja/support/payment/accepted-payment-methods", "ja/support/payment/editing-payment-information", @@ -7633,7 +8176,7 @@ ] }, { - "group": "\u30c8\u30e9\u30d6\u30eb\u30b7\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0", + "group": "トラブルシューティング", "icon": "bug", "pages": [ "ja/troubleshooting/overview", @@ -7642,7 +8185,7 @@ ] }, { - "group": "\u30b3\u30df\u30e5\u30cb\u30c6\u30a3", + "group": "コミュニティ", "pages": [ "ja/community/contributing", "ja/community/links" @@ -7651,11 +8194,11 @@ ] }, { - "tab": "Registry API\u30ea\u30d5\u30a1\u30ec\u30f3\u30b9", + "tab": "Registry APIリファレンス", "openapi": "https://api.comfy.org/openapi" }, { - "tab": "Cloud API\u30ea\u30d5\u30a1\u30ec\u30f3\u30b9", + "tab": "Cloud APIリファレンス", "openapi": { "source": "openapi-cloud.yaml", "directory": "ja/api-reference/cloud" @@ -7671,56 +8214,56 @@ }, "links": [ { - "header": "\u30ea\u30bd\u30fc\u30b9", + "header": "リソース", "items": [ { - "label": "\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb", + "label": "インストール", "href": "https://docs.comfy.org/ja/installation/system_requirements" }, { - "label": "\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb", + "label": "チュートリアル", "href": "https://docs.comfy.org/ja/tutorials/basic/text-to-image" }, { - "label": "\u958b\u767a", + "label": "開発", "href": "https://docs.comfy.org/ja/development/overview" } ] }, { - "header": "\u30d7\u30ed\u30c0\u30af\u30c8", + "header": "プロダクト", "items": [ { - "label": "\u6a5f\u80fd", + "label": "機能", "href": "https://www.comfy.org/?utm_source=docs#features-1" }, { - "label": "\u30ae\u30e3\u30e9\u30ea\u30fc", + "label": "ギャラリー", "href": "https://www.comfy.org/gallery?utm_source=docs" }, { - "label": "\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9", + "label": "ダウンロード", "href": "https://www.comfy.org/download?utm_source=docs" } ] }, { - "header": "\u4f1a\u793e\u60c5\u5831", + "header": "会社情報", "items": [ { - "label": "\u6982\u8981", + "label": "概要", "href": "https://www.comfy.org/about?utm_source=docs" }, { - "label": "\u63a1\u7528\u60c5\u5831", + "label": "採用情報", "href": "https://www.comfy.org/careers?utm_source=docs" }, { - "label": "\u5229\u7528\u898f\u7d04", + "label": "利用規約", "href": "https://www.comfy.org/terms-of-service?utm_source=docs" }, { - "label": "\u30d7\u30e9\u30a4\u30d0\u30b7\u30fc\u30dd\u30ea\u30b7\u30fc", + "label": "プライバシーポリシー", "href": "https://www.comfy.org/privacy-policy?utm_source=docs" } ] @@ -7730,7 +8273,7 @@ "navbar": { "links": [ { - "label": "\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9", + "label": "ダウンロード", "href": "https://comfy.org/download?utm_source=docs" } ], @@ -7745,14 +8288,14 @@ "language": "ko", "tabs": [ { - "tab": "\uc2dc\uc791\ud558\uae30", + "tab": "시작하기", "pages": [ { - "group": "\uc2dc\uc791\ud558\uae30", + "group": "시작하기", "pages": [ "ko/index", { - "group": "\ub85c\uceec (\uc790\uccb4 \ud638\uc2a4\ud305)", + "group": "로컬 (자체 호스팅)", "icon": "download", "pages": [ "ko/installation/system_requirements", @@ -7761,7 +8304,7 @@ "pages": [ "ko/installation/desktop/overview", { - "group": "\uc124\uce58", + "group": "설치", "pages": [ "ko/installation/desktop/windows", "ko/installation/desktop/macos", @@ -7769,7 +8312,7 @@ ] }, { - "group": "\uc0ac\uc6a9 \uac00\uc774\ub4dc", + "group": "사용 가이드", "pages": [ "ko/installation/desktop/usage/overview", "ko/installation/desktop/usage/instance-management", @@ -7789,17 +8332,17 @@ }, "ko/get_started/cloud", { - "group": "\ucee4\uc2a4\ud140 \ub178\ub4dc \uc124\uce58", + "group": "커스텀 노드 설치", "icon": "puzzle-piece", "pages": [ "ko/installation/install_custom_node", { - "group": "ComfyUI \ub9e4\ub2c8\uc800", + "group": "ComfyUI 매니저", "pages": [ "ko/manager/overview", "ko/manager/install", { - "group": "\ub178\ub4dc \uad00\ub9ac", + "group": "노드 관리", "pages": [ "ko/manager/pack-management", "ko/manager/legacy-ui" @@ -7825,7 +8368,7 @@ ] }, { - "group": "\uae30\ubcf8 \uac1c\ub150", + "group": "기본 개념", "pages": [ "ko/development/core-concepts/workflow", "ko/development/core-concepts/nodes", @@ -7837,7 +8380,7 @@ ] }, { - "group": "\uc778\ud130\ud398\uc774\uc2a4 \uac00\uc774\ub4dc", + "group": "인터페이스 가이드", "pages": [ "ko/interface/overview", "ko/interface/app-mode", @@ -7848,7 +8391,7 @@ "ko/interface/features/partial-execution", "ko/interface/features/node-docs", { - "group": "ComfyUI \uc124\uc815", + "group": "ComfyUI 설정", "icon": "gear", "pages": [ "ko/interface/settings/overview", @@ -7865,7 +8408,7 @@ ] }, { - "group": "Cloud \uc804\uc6a9 \uae30\ub2a5", + "group": "Cloud 전용 기능", "icon": "cloud", "pages": [ "ko/cloud/share-workflow", @@ -7875,11 +8418,11 @@ ] }, { - "group": "\ud29c\ud1a0\ub9ac\uc5bc", + "group": "튜토리얼", "icon": "book", "pages": [ { - "group": "\uae30\ubcf8 \uc608\uc81c", + "group": "기본 예제", "pages": [ "ko/tutorials/basic/text-to-image", "ko/tutorials/basic/image-to-image", @@ -7901,7 +8444,7 @@ ] }, { - "group": "\uc774\ubbf8\uc9c0", + "group": "이미지", "pages": [ { "group": "Flux", @@ -7972,7 +8515,7 @@ ] }, { - "group": "\ub80c\uc988", + "group": "렌즈", "pages": [ "ko/tutorials/image/lens/lens" ] @@ -8015,7 +8558,7 @@ ] }, { - "group": "\ube44\ub514\uc624", + "group": "비디오", "pages": [ { "group": "LTX", @@ -8085,7 +8628,7 @@ ] }, { - "group": "\uc624\ub514\uc624", + "group": "오디오", "pages": [ { "group": "Stable Audio 1.0", @@ -8109,7 +8652,7 @@ ] }, { - "group": "\uc720\ud2f8\ub9ac\ud2f0", + "group": "유틸리티", "pages": [ "ko/tutorials/utility/preprocessors", "ko/tutorials/utility/frame-interpolation", @@ -8122,7 +8665,7 @@ "ko/tutorials/utility/moge", "ko/tutorials/utility/depth-anything-3", { - "group": "\uc5bc\uad74 \uac10\uc9c0", + "group": "얼굴 감지", "pages": [ "ko/tutorials/utility/face-detection/mediapipe" ] @@ -8132,7 +8675,7 @@ ] }, { - "group": "\ud30c\ud2b8\ub108 \ub178\ub4dc", + "group": "파트너 노드", "icon": "handshake", "pages": [ "ko/tutorials/partner-nodes/overview", @@ -8297,12 +8840,6 @@ "pages": [ "ko/tutorials/partner-nodes/topaz/astra-2" ] - }, - { - "group": "Grok", - "pages": [ - "ko/tutorials/partner-nodes/grok/grok-imagine-video-1-5" - ] } ] }, @@ -8310,31 +8847,17 @@ ] }, { - "tab": "\ub0b4\uc7a5 \ub178\ub4dc (Built-in Nodes)", + "tab": "내장 노드 (Built-in Nodes)", "pages": [ "ko/built-in-nodes/overview", { - "group": "\ub178\ub4dc", + "group": "노드", "pages": [ { "group": "3D", "pages": [ { - "group": "\ucee8\ub514\uc154\ub2dd", - "pages": [ - "ko/built-in-nodes/TripoSplatConditioning", - "ko/built-in-nodes/TripoSplatPreprocessImage" - ] - }, - { - "group": "\uc7a0\uc7ac", - "pages": [ - "ko/built-in-nodes/TripoSplatSamplingPreview", - "ko/built-in-nodes/VAEDecodeTripoSplat" - ] - }, - { - "group": "\uc2a4\ud50c\ub7ab", + "group": "Splat", "pages": [ "ko/built-in-nodes/File3DToSplat", "ko/built-in-nodes/GetSplatCount", @@ -8347,266 +8870,23 @@ }, "ko/built-in-nodes/CreateCameraInfo", "ko/built-in-nodes/Load3D", + "ko/built-in-nodes/Load3DAdvanced", "ko/built-in-nodes/Load3DAnimation", "ko/built-in-nodes/Preview3D", "ko/built-in-nodes/Preview3DAdvanced", "ko/built-in-nodes/Preview3DAnimation", + "ko/built-in-nodes/PreviewGaussianSplat", + "ko/built-in-nodes/PreviewPointCloud", "ko/built-in-nodes/SaveGLB", "ko/built-in-nodes/VoxelToMesh", "ko/built-in-nodes/VoxelToMeshBasic" ] }, - { - "group": "\uace0\uae09", - "pages": [ - { - "group": "\ucee8\ub514\uc154\ub2dd", - "pages": [ - { - "group": "\uc624\ub514\uc624", - "pages": [ - "ko/built-in-nodes/ReferenceTimbreAudio" - ] - }, - { - "group": "\ubaa8\ub378 \ud3b8\uc9d1", - "pages": [ - "ko/built-in-nodes/ReferenceLatent" - ] - }, - { - "group": "Flux", - "pages": [ - "ko/built-in-nodes/ClipTextEncodeFlux", - "ko/built-in-nodes/FluxDisableGuidance", - "ko/built-in-nodes/FluxGuidance", - "ko/built-in-nodes/FluxKontextImageScale", - "ko/built-in-nodes/FluxKontextMultiReferenceLatentMethod" - ] - }, - { - "group": "Kandinsky5", - "pages": [ - "ko/built-in-nodes/ClipTextEncodeKandinsky5" - ] - }, - "ko/built-in-nodes/ClipTextEncodeHiDream", - "ko/built-in-nodes/ClipTextEncodeHunyuanDiT", - "ko/built-in-nodes/ClipTextEncodePixArtAlpha", - "ko/built-in-nodes/ClipTextEncodeSD3", - "ko/built-in-nodes/ClipTextEncodeSDXL", - "ko/built-in-nodes/ClipTextEncodeSDXLRefiner", - "ko/built-in-nodes/ConditioningSetTimestepRange", - "ko/built-in-nodes/ConditioningZeroOut", - "ko/built-in-nodes/PiDConditioning", - "ko/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo", - "ko/built-in-nodes/TextEncodeQwenImageEdit", - "ko/built-in-nodes/TextEncodeQwenImageEditPlus", - "ko/built-in-nodes/TextEncodeZImageOmni" - ] - }, - { - "group": "\ub514\ubc84\uadf8", - "pages": [ - { - "group": "\ubaa8\ub378", - "pages": [ - "ko/built-in-nodes/EasyCache", - "ko/built-in-nodes/LazyCache", - "ko/built-in-nodes/ModelComputeDtype" - ] - } - ] - }, - { - "group": "\uac00\uc774\ub358\uc2a4", - "pages": [ - "ko/built-in-nodes/CFGNorm", - "ko/built-in-nodes/CFGZeroStar", - "ko/built-in-nodes/NAGuidance", - "ko/built-in-nodes/SkipLayerGuidanceDiT", - "ko/built-in-nodes/SkipLayerGuidanceDiTSimple", - "ko/built-in-nodes/SkipLayerGuidanceSD3", - "ko/built-in-nodes/TCFG" - ] - }, - { - "group": "\ud6c5", - "pages": [ - { - "group": "Clip", - "pages": [ - "ko/built-in-nodes/SetClipHooks" - ] - }, - { - "group": "\uacb0\ud569", - "pages": [ - "ko/built-in-nodes/CombineHooks", - "ko/built-in-nodes/CombineHooksEight", - "ko/built-in-nodes/CombineHooksFour" - ] - }, - { - "group": "\ucee8\ub514\uc154\ub2dd \uc30d", - "pages": [ - "ko/built-in-nodes/PairConditioningCombine", - "ko/built-in-nodes/PairConditioningSetDefaultAndCombine", - "ko/built-in-nodes/PairConditioningSetProperties", - "ko/built-in-nodes/PairConditioningSetPropertiesAndCombine" - ] - }, - { - "group": "\ucee8\ub514\uc154\ub2dd \ub2e8\uc77c", - "pages": [ - "ko/built-in-nodes/ConditioningSetDefaultAndCombine", - "ko/built-in-nodes/ConditioningSetProperties", - "ko/built-in-nodes/ConditioningSetPropertiesAndCombine" - ] - }, - { - "group": "\uc0dd\uc131", - "pages": [ - "ko/built-in-nodes/CreateHookLora", - "ko/built-in-nodes/CreateHookLoraModelOnly", - "ko/built-in-nodes/CreateHookModelAsLora", - "ko/built-in-nodes/CreateHookModelAsLoraModelOnly" - ] - }, - { - "group": "\ub9e4\ub274\uc5bc", - "pages": [ - "ko/built-in-nodes/SetModelHooksOnCond" - ] - }, - { - "group": "\uc2a4\ucf00\uc904\ub9c1", - "pages": [ - "ko/built-in-nodes/CreateHookKeyframe", - "ko/built-in-nodes/CreateHookKeyframesFromFloats", - "ko/built-in-nodes/CreateHookKeyframesInterpolated", - "ko/built-in-nodes/SetHookKeyframes" - ] - }, - "ko/built-in-nodes/ConditioningTimestepsRange" - ] - }, - { - "group": "\ub85c\ub354", - "pages": [ - { - "group": "\uc9c0\uc6d0 \uc911\ub2e8", - "pages": [ - "ko/built-in-nodes/DiffusersLoader" - ] - }, - { - "group": "Qwen", - "pages": [ - "ko/built-in-nodes/QwenImageDiffsynthControlnet" - ] - }, - { - "group": "Zimage", - "pages": [ - "ko/built-in-nodes/ZImageFunControlnet" - ] - }, - "ko/built-in-nodes/CheckpointLoader", - "ko/built-in-nodes/ClipLoader", - "ko/built-in-nodes/DeprecatedCheckpointLoader", - "ko/built-in-nodes/DeprecatedDiffusersLoader", - "ko/built-in-nodes/DualCLIPLoader", - "ko/built-in-nodes/LTXAVTextEncoderLoader", - "ko/built-in-nodes/ModelPatchLoader", - "ko/built-in-nodes/QuadrupleCLIPLoader", - "ko/built-in-nodes/TripleCLIPLoader", - "ko/built-in-nodes/UNETLoader" - ] - }, - { - "group": "\ubaa8\ub378", - "pages": [ - "ko/built-in-nodes/HiDreamO1PatchSeamSmoothing", - "ko/built-in-nodes/ModelNoiseScale", - "ko/built-in-nodes/ModelSamplingAuraFlow", - "ko/built-in-nodes/ModelSamplingContinuousEDM", - "ko/built-in-nodes/ModelSamplingContinuousV", - "ko/built-in-nodes/ModelSamplingDiscrete", - "ko/built-in-nodes/ModelSamplingFlux", - "ko/built-in-nodes/ModelSamplingLTXV", - "ko/built-in-nodes/ModelSamplingSD3", - "ko/built-in-nodes/ModelSamplingStableCascade", - "ko/built-in-nodes/RenormCFG", - "ko/built-in-nodes/RescaleCFG" - ] - }, - { - "group": "\ubaa8\ub378 \ubcd1\ud569", - "pages": [ - { - "group": "\ubaa8\ub378\ubcc4", - "pages": [ - "ko/built-in-nodes/ModelMergeAuraflow", - "ko/built-in-nodes/ModelMergeCosmos14B", - "ko/built-in-nodes/ModelMergeCosmos7B", - "ko/built-in-nodes/ModelMergeCosmosPredict2_14B", - "ko/built-in-nodes/ModelMergeCosmosPredict2_2B", - "ko/built-in-nodes/ModelMergeFlux1", - "ko/built-in-nodes/ModelMergeLTXV", - "ko/built-in-nodes/ModelMergeMochiPreview", - "ko/built-in-nodes/ModelMergeQwenImage", - "ko/built-in-nodes/ModelMergeSD1", - "ko/built-in-nodes/ModelMergeSD35_Large", - "ko/built-in-nodes/ModelMergeSD3_2B", - "ko/built-in-nodes/ModelMergeSDXL", - "ko/built-in-nodes/ModelMergeWAN2_1" - ] - }, - "ko/built-in-nodes/CheckpointSave", - "ko/built-in-nodes/ClipMergeAdd", - "ko/built-in-nodes/ClipMergeSimple", - "ko/built-in-nodes/ClipMergeSubtract", - "ko/built-in-nodes/ClipSave", - "ko/built-in-nodes/ImageOnlyCheckpointSave", - "ko/built-in-nodes/ModelMergeAdd", - "ko/built-in-nodes/ModelMergeBlocks", - "ko/built-in-nodes/ModelMergeSimple", - "ko/built-in-nodes/ModelMergeSubtract", - "ko/built-in-nodes/ModelSave", - "ko/built-in-nodes/SaveLoRA", - "ko/built-in-nodes/SaveLoRANode", - "ko/built-in-nodes/VAESave" - ] - }, - { - "group": "\uba40\ud2f0 GPU", - "pages": [ - "ko/built-in-nodes/MultiGPU_Options", - "ko/built-in-nodes/MultiGPU_WorkUnits", - "ko/built-in-nodes/SelectCLIPDevice", - "ko/built-in-nodes/SelectModelDevice", - "ko/built-in-nodes/SelectVAEDevice" - ] - }, - "ko/built-in-nodes/GeminiNodeV2", - "ko/built-in-nodes/MoonvalleyImg2VideoNode", - "ko/built-in-nodes/MoonvalleyTxt2VideoNode", - "ko/built-in-nodes/MoonvalleyVideo2VideoNode", - "ko/built-in-nodes/PreviewGaussianSplat", - "ko/built-in-nodes/PreviewPointCloud", - "ko/built-in-nodes/SaveAudioAdvanced", - "ko/built-in-nodes/SeedVR2Conditioning", - "ko/built-in-nodes/SeedVR2PostProcessing", - "ko/built-in-nodes/SeedVR2Preprocess", - "ko/built-in-nodes/SeedVR2ProgressiveSampler" - ] - }, { "group": "API Node", "pages": [ { - "group": "\uc774\ubbf8\uc9c0", + "group": "Image", "pages": [ { "group": "Bfl", @@ -8625,7 +8905,7 @@ ] }, { - "group": "\ube44\ub514\uc624", + "group": "Video", "pages": [ { "group": "Pika", @@ -8644,7 +8924,7 @@ ] }, { - "group": "\uc624\ub514\uc624", + "group": "Audio", "pages": [ "ko/built-in-nodes/AudioAdjustVolume", "ko/built-in-nodes/AudioConcat", @@ -8654,35 +8934,20 @@ "ko/built-in-nodes/JoinAudioChannels", "ko/built-in-nodes/LoadAudio", "ko/built-in-nodes/PreviewAudio", - "ko/built-in-nodes/RecordAudio", - "ko/built-in-nodes/SaveAudio", - "ko/built-in-nodes/SaveAudioMP3", - "ko/built-in-nodes/SaveAudioOpus", - "ko/built-in-nodes/SplitAudioChannels", - "ko/built-in-nodes/TrimAudioDuration" - ] - }, - { - "group": "\ucee8\ub514\uc154\ub2dd", - "pages": [ - { - "group": "\ube44\ub514\uc624 \ubaa8\ub378", - "pages": [ - "ko/built-in-nodes/Stablezero123Conditioning", - "ko/built-in-nodes/Stablezero123ConditioningBatched", - "ko/built-in-nodes/SVD_img2vid_Conditioning", - "ko/built-in-nodes/SvdImg2vidConditioning" - ] - }, - "ko/built-in-nodes/ConditioningAverage", - "ko/built-in-nodes/Sd4xupscaleConditioning" + "ko/built-in-nodes/RecordAudio", + "ko/built-in-nodes/SaveAudio", + "ko/built-in-nodes/SaveAudioAdvanced", + "ko/built-in-nodes/SaveAudioMP3", + "ko/built-in-nodes/SaveAudioOpus", + "ko/built-in-nodes/SplitAudioChannels", + "ko/built-in-nodes/TrimAudioDuration" ] }, { - "group": "\uc2e4\ud5d8\uc801", + "group": "Experimental", "pages": [ { - "group": "\uc5b4\ud150\uc158 \uc2e4\ud5d8", + "group": "Attention Experiments", "pages": [ "ko/built-in-nodes/ClipAttentionMultiply", "ko/built-in-nodes/UNetCrossAttentionMultiply", @@ -8690,32 +8955,6 @@ "ko/built-in-nodes/UNetTemporalAttentionMultiply" ] }, - { - "group": "\ucee8\ub514\uc154\ub2dd", - "pages": [ - "ko/built-in-nodes/ClipTextEncodeControlnet", - "ko/built-in-nodes/T5TokenizerOptions" - ] - }, - { - "group": "\ucee4\uc2a4\ud140 \uc0d8\ud50c\ub9c1", - "pages": [ - { - "group": "\ub178\uc774\uc988", - "pages": [ - "ko/built-in-nodes/AddNoise" - ] - }, - "ko/built-in-nodes/ManualSigmas" - ] - }, - { - "group": "Photomaker", - "pages": [ - "ko/built-in-nodes/PhotoMakerEncode", - "ko/built-in-nodes/PhotoMakerLoader" - ] - }, { "group": "Stable Cascade", "pages": [ @@ -8726,263 +8965,169 @@ "ko/built-in-nodes/FluxKVCache", "ko/built-in-nodes/FreSca", "ko/built-in-nodes/LatentBlend", - "ko/built-in-nodes/LoadLatent", "ko/built-in-nodes/LoraSave", "ko/built-in-nodes/Mahiro", "ko/built-in-nodes/PerpNeg", "ko/built-in-nodes/PerpNegGuider", "ko/built-in-nodes/SamplerEulerCFGpp", - "ko/built-in-nodes/SaveLatent", "ko/built-in-nodes/SelfAttentionGuidance", - "ko/built-in-nodes/TorchCompileModel", - "ko/built-in-nodes/VAEDecodeTiled", - "ko/built-in-nodes/VAEEncodeTiled" - ] - }, - { - "group": "\uc774\ubbf8\uc9c0", - "pages": [ - { - "group": "\uc870\uc815", - "pages": [ - "ko/built-in-nodes/AdjustBrightness", - "ko/built-in-nodes/AdjustContrast" - ] - }, - { - "group": "\ubc30\uacbd \uc81c\uac70", - "pages": [ - "ko/built-in-nodes/RemoveBackground" - ] - }, - { - "group": "\ubc30\uce58", - "pages": [ - "ko/built-in-nodes/ImageDeduplication", - "ko/built-in-nodes/ImageFromBatch", - "ko/built-in-nodes/ImageGrid", - "ko/built-in-nodes/ImageMergeTileList", - "ko/built-in-nodes/MergeImageLists", - "ko/built-in-nodes/RebatchImages", - "ko/built-in-nodes/RepeatImageBatch", - "ko/built-in-nodes/ShuffleDataset", - "ko/built-in-nodes/ShuffleImageTextDataset", - "ko/built-in-nodes/SplitImageToTileList" - ] - }, - { - "group": "\uc0c9\uc0c1", - "pages": [ - "ko/built-in-nodes/ImageRGBToYUV", - "ko/built-in-nodes/ImageYUVToRGB", - "ko/built-in-nodes/NormalizeImages" - ] - }, - { - "group": "\ud569\uc131", - "pages": [ - "ko/built-in-nodes/ImageCompositeMasked", - "ko/built-in-nodes/JoinImageWithAlpha", - "ko/built-in-nodes/PorterDuffImageComposite", - "ko/built-in-nodes/SplitImageWithAlpha" - ] - }, - { - "group": "\uac10\uc9c0", - "pages": [ - "ko/built-in-nodes/DrawBBoxes", - "ko/built-in-nodes/MediaPipeFaceLandmarker", - "ko/built-in-nodes/MediaPipeFaceMask", - "ko/built-in-nodes/MediaPipeFaceMeshVisualize", - "ko/built-in-nodes/RTDETR_detect", - "ko/built-in-nodes/SAM3_Detect", - "ko/built-in-nodes/SAM3_TrackPreview", - "ko/built-in-nodes/SAM3_TrackToMask", - "ko/built-in-nodes/SAM3_VideoTrack", - "ko/built-in-nodes/SDPoseDrawKeypoints", - "ko/built-in-nodes/SDPoseFaceBBoxes", - "ko/built-in-nodes/SDPoseKeypointExtractor" - ] - }, - { - "group": "\ud544\ud130", - "pages": [ - "ko/built-in-nodes/Canny", - "ko/built-in-nodes/ColorTransfer", - "ko/built-in-nodes/ImageAddNoise", - "ko/built-in-nodes/ImageBlend", - "ko/built-in-nodes/ImageBlur", - "ko/built-in-nodes/ImageQuantize", - "ko/built-in-nodes/ImageSharpen", - "ko/built-in-nodes/Morphology" - ] - }, - { - "group": "\uc9c0\uc624\uba54\ud2b8\ub9ac \ucd94\uc815", - "pages": [ - "ko/built-in-nodes/MoGeInference", - "ko/built-in-nodes/MoGePanoramaInference", - "ko/built-in-nodes/MoGePointMapToMesh", - "ko/built-in-nodes/MoGeRender" - ] - }, - { - "group": "\ub9c8\uc2a4\ud06c", - "pages": [ - "ko/built-in-nodes/BatchMasksNode", - "ko/built-in-nodes/CropMask", - "ko/built-in-nodes/FeatherMask", - "ko/built-in-nodes/GrowMask", - "ko/built-in-nodes/ImageColorToMask", - "ko/built-in-nodes/ImageToMask", - "ko/built-in-nodes/InvertMask", - "ko/built-in-nodes/MaskComposite", - "ko/built-in-nodes/MaskPreview", - "ko/built-in-nodes/MaskToImage", - "ko/built-in-nodes/SolidMask", - "ko/built-in-nodes/ThresholdMask", - "ko/built-in-nodes/VOIDQuadmaskPreprocess" - ] - }, - { - "group": "\uc170\uc774\ub354", - "pages": [ - "ko/built-in-nodes/GLSLShader" - ] - }, - { - "group": "\ubcc0\ud658", - "pages": [ - "ko/built-in-nodes/CenterCropImages", - "ko/built-in-nodes/CropByBBoxes", - "ko/built-in-nodes/ImageCrop", - "ko/built-in-nodes/ImageCropV2", - "ko/built-in-nodes/ImageFlip", - "ko/built-in-nodes/ImagePadForOutpaint", - "ko/built-in-nodes/ImageRotate", - "ko/built-in-nodes/ImageStitch", - "ko/built-in-nodes/RandomCropImages", - "ko/built-in-nodes/ResizeAndPadImage", - "ko/built-in-nodes/ResizeImagesByLongerEdge", - "ko/built-in-nodes/ResizeImagesByShorterEdge" - ] - }, - { - "group": "\uc5c5\uc2a4\ucf00\uc77c\ub9c1", - "pages": [ - "ko/built-in-nodes/ImageScale", - "ko/built-in-nodes/ImageScaleBy", - "ko/built-in-nodes/ImageScaleToMaxDimension", - "ko/built-in-nodes/ImageScaleToTotalPixels", - "ko/built-in-nodes/ImageUpscaleWithModel" - ] - }, - { - "group": "\ube44\ub514\uc624", - "pages": [ - "ko/built-in-nodes/WanDancerPadKeyframes", - "ko/built-in-nodes/WanDancerPadKeyframesList" - ] - }, - "ko/built-in-nodes/BatchImagesNode", - "ko/built-in-nodes/ConditioningCombine", - "ko/built-in-nodes/EmptyImage", - "ko/built-in-nodes/GetImageSize", - "ko/built-in-nodes/ImageBatch", - "ko/built-in-nodes/ImageCompare", - "ko/built-in-nodes/ImageInvert", - "ko/built-in-nodes/LoadImage", - "ko/built-in-nodes/LoadImageDataSetFromFolder", - "ko/built-in-nodes/LoadImageMask", - "ko/built-in-nodes/LoadImageOutput", - "ko/built-in-nodes/LoadImageSetFromFolderNode", - "ko/built-in-nodes/LoadImageSetNode", - "ko/built-in-nodes/LoadImageTextDataSetFromFolder", - "ko/built-in-nodes/LoadImageTextSetFromFolderNode", - "ko/built-in-nodes/LoraLoader", - "ko/built-in-nodes/LoraLoaderModelOnly", - "ko/built-in-nodes/Painter", - "ko/built-in-nodes/PreviewImage", - "ko/built-in-nodes/ResizeImageMaskNode", - "ko/built-in-nodes/SaveAnimatedPNG", - "ko/built-in-nodes/SaveAnimatedWEBP", - "ko/built-in-nodes/SaveImage", - "ko/built-in-nodes/SaveImageAdvanced", - "ko/built-in-nodes/SaveImageDataSetToFolder", - "ko/built-in-nodes/SaveImageTextDataSetToFolder", - "ko/built-in-nodes/SaveSVGNode", - "ko/built-in-nodes/WebcamCapture" - ] - }, - { - "group": "\ub85c\ub354", - "pages": [ - "ko/built-in-nodes/ControlNetLoader" + "ko/built-in-nodes/TorchCompileModel" ] }, { - "group": "\ubaa8\ub378", + "group": "Model", "pages": [ { - "group": "\ucee8\ub514\uc154\ub2dd", + "group": "Conditioning", "pages": [ { - "group": "3D Models", + "group": "Ace", + "pages": [ + "ko/built-in-nodes/TextEncodeAceStepAudio", + "ko/built-in-nodes/TextEncodeAceStepAudio1.5" + ] + }, + { + "group": "Autoregressive", + "pages": [ + "ko/built-in-nodes/ARVideoI2V" + ] + }, + { + "group": "Bernini", + "pages": [ + "ko/built-in-nodes/BerniniConditioning" + ] + }, + { + "group": "Boogu", + "pages": [ + "ko/built-in-nodes/TextEncodeBooguEdit" + ] + }, + { + "group": "Controlnet", + "pages": [ + "ko/built-in-nodes/ControlNetApply", + "ko/built-in-nodes/ControlNetApplyAdvanced", + "ko/built-in-nodes/ControlNetApplySD3", + "ko/built-in-nodes/ControlNetInpaintingAliMamaApply", + "ko/built-in-nodes/SetUnionControlNetType" + ] + }, + { + "group": "Cosmos", + "pages": [ + "ko/built-in-nodes/CosmosImageToVideoLatent", + "ko/built-in-nodes/CosmosPredict2ImageToVideoLatent" + ] + }, + { + "group": "Flux", + "pages": [ + "ko/built-in-nodes/ClipTextEncodeFlux", + "ko/built-in-nodes/FluxDisableGuidance", + "ko/built-in-nodes/FluxGuidance", + "ko/built-in-nodes/FluxKontextImageScale", + "ko/built-in-nodes/FluxKontextMultiReferenceLatentMethod" + ] + }, + { + "group": "Gligen", + "pages": [ + "ko/built-in-nodes/GLIGENTextBoxApply" + ] + }, + { + "group": "Hidream", + "pages": [ + "ko/built-in-nodes/ClipTextEncodeHiDream", + "ko/built-in-nodes/HiDreamO1ReferenceImages" + ] + }, + { + "group": "Hunyuan 3D", + "pages": [ + "ko/built-in-nodes/Hunyuan3Dv2Conditioning", + "ko/built-in-nodes/Hunyuan3Dv2ConditioningMultiView" + ] + }, + { + "group": "Hunyuan Image", + "pages": [ + "ko/built-in-nodes/ClipTextEncodeHunyuanDiT" + ] + }, + { + "group": "Hunyuan Video", + "pages": [ + "ko/built-in-nodes/HunyuanImageToVideo", + "ko/built-in-nodes/HunyuanRefinerLatent", + "ko/built-in-nodes/HunyuanVideo15ImageToVideo", + "ko/built-in-nodes/HunyuanVideo15SuperResolution", + "ko/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo" + ] + }, + { + "group": "Instructpix2Pix", "pages": [ - "ko/built-in-nodes/Hunyuan3Dv2Conditioning", - "ko/built-in-nodes/Hunyuan3Dv2ConditioningMultiView", - "ko/built-in-nodes/StableZero123_Conditioning", - "ko/built-in-nodes/StableZero123_Conditioning_Batched", - "ko/built-in-nodes/SV3D_Conditioning" + "ko/built-in-nodes/InstructPixToPixConditioning" ] }, { - "group": "\uc624\ub514\uc624", + "group": "Kandinsky", "pages": [ - "ko/built-in-nodes/LTXVReferenceAudio" + "ko/built-in-nodes/ClipTextEncodeKandinsky5", + "ko/built-in-nodes/Kandinsky5ImageToVideo" ] }, { - "group": "Controlnet", + "group": "Lotus", "pages": [ - "ko/built-in-nodes/ControlNetApply", - "ko/built-in-nodes/ControlNetApplyAdvanced", - "ko/built-in-nodes/ControlNetApplySD3", - "ko/built-in-nodes/ControlNetInpaintingAliMamaApply", - "ko/built-in-nodes/SetUnionControlNetType" + "ko/built-in-nodes/LotusConditioning" ] }, { - "group": "Gligen", + "group": "Ltxv", "pages": [ - "ko/built-in-nodes/GLIGENTextBoxApply" + "ko/built-in-nodes/GetICLoRAParameters", + "ko/built-in-nodes/LTXVAddGuide", + "ko/built-in-nodes/LTXVConditioning", + "ko/built-in-nodes/LTXVCropGuides", + "ko/built-in-nodes/LTXVImgToVideo", + "ko/built-in-nodes/LTXVImgToVideoInplace", + "ko/built-in-nodes/LTXVReferenceAudio" ] }, { - "group": "\uc774\ubbf8\uc9c0", + "group": "Lumina", "pages": [ - "ko/built-in-nodes/HiDreamO1ReferenceImages" + "ko/built-in-nodes/ClipTextEncodeLumina2" ] }, { - "group": "\uc778\ud398\uc778\ud305", + "group": "Photomaker", "pages": [ - "ko/built-in-nodes/CosmosImageToVideoLatent", - "ko/built-in-nodes/CosmosPredict2ImageToVideoLatent", - "ko/built-in-nodes/InpaintModelConditioning", - "ko/built-in-nodes/Wan22ImageToVideoLatent" + "ko/built-in-nodes/PhotoMakerEncode" ] }, { - "group": "Instructpix2Pix", + "group": "Pixart", "pages": [ - "ko/built-in-nodes/InstructPixToPixConditioning" + "ko/built-in-nodes/ClipTextEncodePixArtAlpha" ] }, { - "group": "Lotus", + "group": "Qwen Image", "pages": [ - "ko/built-in-nodes/LotusConditioning" + "ko/built-in-nodes/TextEncodeQwenImageEdit", + "ko/built-in-nodes/TextEncodeQwenImageEditPlus" + ] + }, + { + "group": "Stable Audio", + "pages": [ + "ko/built-in-nodes/ConditioningStableAudio" ] }, { @@ -8992,91 +9137,185 @@ ] }, { - "group": "\uc2a4\ud0c0\uc77c \ubaa8\ub378", + "group": "Stable Diffusion", "pages": [ - "ko/built-in-nodes/StyleModelApply" + "ko/built-in-nodes/ClipTextEncodeSD3", + "ko/built-in-nodes/ClipTextEncodeSDXL", + "ko/built-in-nodes/ClipTextEncodeSDXLRefiner" ] }, { - "group": "\uc5c5\uc2a4\ucf00\uc77c \ub514\ud4e8\uc804", + "group": "Stable Diffusion Upscaler", "pages": [ "ko/built-in-nodes/SD_4XUpscale_Conditioning" ] }, { - "group": "\ube44\ub514\uc624 \ubaa8\ub378", + "group": "Stable Video 3D", "pages": [ - "ko/built-in-nodes/ARVideoI2V", - "ko/built-in-nodes/GenerateTracks", - "ko/built-in-nodes/GetICLoRAParameters", - "ko/built-in-nodes/HunyuanImageToVideo", - "ko/built-in-nodes/HunyuanRefinerLatent", - "ko/built-in-nodes/HunyuanVideo15ImageToVideo", - "ko/built-in-nodes/HunyuanVideo15SuperResolution", - "ko/built-in-nodes/Kandinsky5ImageToVideo", - "ko/built-in-nodes/LTXVAddGuide", - "ko/built-in-nodes/LTXVConditioning", - "ko/built-in-nodes/LTXVCropGuides", - "ko/built-in-nodes/LTXVImgToVideo", - "ko/built-in-nodes/LTXVImgToVideoInplace", - "ko/built-in-nodes/NormalizeVideoLatentStart", - "ko/built-in-nodes/VOIDInpaintConditioning", - "ko/built-in-nodes/Wan22FunControlToVideo", - "ko/built-in-nodes/WanAnimateToVideo", - "ko/built-in-nodes/WanCameraEmbedding", - "ko/built-in-nodes/WanCameraImageToVideo", - "ko/built-in-nodes/WanDancerEncodeAudio", - "ko/built-in-nodes/WanDancerVideo", + "ko/built-in-nodes/SV3D_Conditioning" + ] + }, + { + "group": "Stable Zero123", + "pages": [ + "ko/built-in-nodes/StableZero123_Conditioning", + "ko/built-in-nodes/StableZero123_Conditioning_Batched" + ] + }, + { + "group": "Transform", + "pages": [ + "ko/built-in-nodes/ConditioningConcat", + "ko/built-in-nodes/ConditioningMultiply", + "ko/built-in-nodes/ConditioningSetArea", + "ko/built-in-nodes/ConditioningSetAreaPercentage", + "ko/built-in-nodes/ConditioningSetAreaPercentageVideo", + "ko/built-in-nodes/ConditioningSetAreaStrength", + "ko/built-in-nodes/ConditioningSetMask", + "ko/built-in-nodes/ConditioningSetTimestepRange", + "ko/built-in-nodes/ConditioningZeroOut" + ] + }, + { + "group": "Triposplat", + "pages": [ + "ko/built-in-nodes/TripoSplatConditioning", + "ko/built-in-nodes/TripoSplatPreprocessImage" + ] + }, + { + "group": "Void", + "pages": [ + "ko/built-in-nodes/VOIDInpaintConditioning" + ] + }, + { + "group": "Wan", + "pages": [ + { + "group": "Animate", + "pages": [ + "ko/built-in-nodes/WanAnimateToVideo" + ] + }, + { + "group": "Camera", + "pages": [ + "ko/built-in-nodes/WanCameraEmbedding", + "ko/built-in-nodes/WanCameraImageToVideo" + ] + }, + { + "group": "Dancer", + "pages": [ + "ko/built-in-nodes/WanDancerEncodeAudio", + "ko/built-in-nodes/WanDancerVideo" + ] + }, + { + "group": "Fun Control", + "pages": [ + "ko/built-in-nodes/Wan22FunControlToVideo", + "ko/built-in-nodes/WanFunControlToVideo" + ] + }, + { + "group": "Fun Inpaint", + "pages": [ + "ko/built-in-nodes/WanFunInpaintToVideo" + ] + }, + { + "group": "Humo", + "pages": [ + "ko/built-in-nodes/WanHuMoImageToVideo" + ] + }, + { + "group": "Infinite Talk", + "pages": [ + "ko/built-in-nodes/WanInfiniteTalkToVideo" + ] + }, + { + "group": "Move", + "pages": [ + "ko/built-in-nodes/GenerateTracks", + "ko/built-in-nodes/WanMoveConcatTrack", + "ko/built-in-nodes/WanMoveTracksFromCoords", + "ko/built-in-nodes/WanMoveTrackToVideo", + "ko/built-in-nodes/WanMoveVisualizeTracks", + "ko/built-in-nodes/WanTrackToVideo" + ] + }, + { + "group": "Phantom Subject", + "pages": [ + "ko/built-in-nodes/WanPhantomSubjectToVideo" + ] + }, + { + "group": "Scail", + "pages": [ + "ko/built-in-nodes/SCAIL2ColoredMask", + "ko/built-in-nodes/WanSCAILToVideo" + ] + }, + { + "group": "Sound", + "pages": [ + "ko/built-in-nodes/WanSoundImageToVideo", + "ko/built-in-nodes/WanSoundImageToVideoExtend" + ] + }, + { + "group": "Vace", + "pages": [ + "ko/built-in-nodes/WanVaceToVideo" + ] + }, + "ko/built-in-nodes/Wan22ImageToVideoLatent", "ko/built-in-nodes/WanFirstLastFrameToVideo", - "ko/built-in-nodes/WanFunControlToVideo", - "ko/built-in-nodes/WanFunInpaintToVideo", - "ko/built-in-nodes/WanHuMoImageToVideo", - "ko/built-in-nodes/WanImageToVideo", - "ko/built-in-nodes/WanInfiniteTalkToVideo", - "ko/built-in-nodes/WanMoveConcatTrack", - "ko/built-in-nodes/WanMoveTracksFromCoords", - "ko/built-in-nodes/WanMoveTrackToVideo", - "ko/built-in-nodes/WanMoveVisualizeTracks", - "ko/built-in-nodes/WanPhantomSubjectToVideo", - "ko/built-in-nodes/WanSCAILToVideo", - "ko/built-in-nodes/WanSoundImageToVideo", - "ko/built-in-nodes/WanSoundImageToVideoExtend", - "ko/built-in-nodes/WanTrackToVideo", - "ko/built-in-nodes/WanVaceToVideo" + "ko/built-in-nodes/WanImageToVideo" + ] + }, + { + "group": "Z Image", + "pages": [ + "ko/built-in-nodes/TextEncodeZImageOmni" ] }, "ko/built-in-nodes/AudioEncoderEncode", "ko/built-in-nodes/ClipSetLastLayer", "ko/built-in-nodes/ClipTextEncode", - "ko/built-in-nodes/ClipTextEncodeLumina2", + "ko/built-in-nodes/ClipTextEncodeControlnet", "ko/built-in-nodes/ClipVisionEncode", - "ko/built-in-nodes/ConditioningConcat", - "ko/built-in-nodes/ConditioningSetArea", - "ko/built-in-nodes/ConditioningSetAreaPercentage", - "ko/built-in-nodes/ConditioningSetAreaPercentageVideo", - "ko/built-in-nodes/ConditioningSetAreaStrength", - "ko/built-in-nodes/ConditioningSetMask", - "ko/built-in-nodes/ConditioningStableAudio", - "ko/built-in-nodes/TextEncodeAceStepAudio", - "ko/built-in-nodes/TextEncodeAceStepAudio1.5", + "ko/built-in-nodes/InpaintModelConditioning", + "ko/built-in-nodes/NormalizeVideoLatentStart", + "ko/built-in-nodes/PiDConditioning", + "ko/built-in-nodes/ReferenceLatent", + "ko/built-in-nodes/ReferenceTimbreAudio", + "ko/built-in-nodes/StyleModelApply", + "ko/built-in-nodes/T5TokenizerOptions", "ko/built-in-nodes/unCLIPConditioning" ] }, { - "group": "\uc7a0\uc7ac", + "group": "Latent", "pages": [ { - "group": "3D", + "group": "Ace", "pages": [ - "ko/built-in-nodes/EmptyLatentHunyuan3Dv2", - "ko/built-in-nodes/VAEDecodeHunyuan3D" + "ko/built-in-nodes/EmptyAceStep1.5LatentAudio", + "ko/built-in-nodes/EmptyAceStepLatentAudio" ] }, { - "group": "\uace0\uae09", + "group": "Advanced", "pages": [ { - "group": "\uc5f0\uc0b0", + "group": "Operations", "pages": [ "ko/built-in-nodes/LatentApplyOperation", "ko/built-in-nodes/LatentApplyOperationCFG", @@ -9095,22 +9334,15 @@ ] }, { - "group": "\uc624\ub514\uc624", + "group": "Autoregressive", "pages": [ - "ko/built-in-nodes/EmptyAceStep1.5LatentAudio", - "ko/built-in-nodes/EmptyAceStepLatentAudio", - "ko/built-in-nodes/EmptyLatentAudio", - "ko/built-in-nodes/LTXVAudioVAEDecode", - "ko/built-in-nodes/LTXVAudioVAEEncode", - "ko/built-in-nodes/LTXVEmptyLatentAudio", - "ko/built-in-nodes/VAEDecodeAudio", - "ko/built-in-nodes/VAEDecodeAudioTiled", - "ko/built-in-nodes/VAEEncodeAudio" + "ko/built-in-nodes/EmptyARVideoLatent" ] }, { - "group": "\ubc30\uce58", + "group": "Batch", "pages": [ + "ko/built-in-nodes/BatchLatentsNode", "ko/built-in-nodes/LatentBatch", "ko/built-in-nodes/LatentFromBatch", "ko/built-in-nodes/RebatchLatents", @@ -9125,28 +9357,71 @@ ] }, { - "group": "\uc774\ubbf8\uc9c0", + "group": "Cosmos", + "pages": [ + "ko/built-in-nodes/EmptyCosmosLatentVideo" + ] + }, + { + "group": "Flux", + "pages": [ + "ko/built-in-nodes/EmptyFlux2LatentImage" + ] + }, + { + "group": "Hidream", "pages": [ "ko/built-in-nodes/EmptyHiDreamO1LatentImage" ] }, { - "group": "\uc778\ud398\uc778\ud305", + "group": "Hunyhuan Video", "pages": [ - "ko/built-in-nodes/SetLatentNoiseMask", - "ko/built-in-nodes/VAEEncodeForInpaint" + "ko/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel" ] }, { - "group": "Qwen", + "group": "Hunyuan 3D", "pages": [ - "ko/built-in-nodes/EmptyQwenImageLayeredLatentImage" + "ko/built-in-nodes/EmptyLatentHunyuan3Dv2", + "ko/built-in-nodes/VAEDecodeHunyuan3D" ] }, { - "group": "Sd3", + "group": "Hunyuan Image", "pages": [ - "ko/built-in-nodes/EmptySD3LatentImage" + "ko/built-in-nodes/EmptyHunyuanImageLatent" + ] + }, + { + "group": "Hunyuan Video", + "pages": [ + "ko/built-in-nodes/EmptyHunyuanLatentVideo", + "ko/built-in-nodes/EmptyHunyuanVideo15Latent" + ] + }, + { + "group": "Ltxv", + "pages": [ + "ko/built-in-nodes/EmptyLTXVLatentVideo", + "ko/built-in-nodes/LTXVAudioVAEDecode", + "ko/built-in-nodes/LTXVAudioVAEEncode", + "ko/built-in-nodes/LTXVConcatAVLatent", + "ko/built-in-nodes/LTXVEmptyLatentAudio", + "ko/built-in-nodes/LTXVLatentUpsampler", + "ko/built-in-nodes/LTXVSeparateAVLatent" + ] + }, + { + "group": "Mochi", + "pages": [ + "ko/built-in-nodes/EmptyMochiLatentVideo" + ] + }, + { + "group": "Qwen", + "pages": [ + "ko/built-in-nodes/EmptyQwenImageLayeredLatentImage" ] }, { @@ -9157,7 +9432,13 @@ ] }, { - "group": "\ubcc0\ud658", + "group": "Stable Diffusion", + "pages": [ + "ko/built-in-nodes/EmptySD3LatentImage" + ] + }, + { + "group": "Transform", "pages": [ "ko/built-in-nodes/LatentCrop", "ko/built-in-nodes/LatentFlip", @@ -9165,78 +9446,158 @@ ] }, { - "group": "\ube44\ub514\uc624", + "group": "Triposplat", "pages": [ - { - "group": "Ltxv", - "pages": [ - "ko/built-in-nodes/EmptyLTXVLatentVideo", - "ko/built-in-nodes/LTXVConcatAVLatent", - "ko/built-in-nodes/LTXVSeparateAVLatent" - ] - }, - "ko/built-in-nodes/EmptyARVideoLatent", - "ko/built-in-nodes/EmptyCosmosLatentVideo", - "ko/built-in-nodes/EmptyHunyuanLatentVideo", - "ko/built-in-nodes/EmptyHunyuanVideo15Latent", - "ko/built-in-nodes/EmptyMochiLatentVideo", - "ko/built-in-nodes/LTXVLatentUpsampler", - "ko/built-in-nodes/TrimVideoLatent", - "ko/built-in-nodes/VOIDWarpedNoise" + "ko/built-in-nodes/TripoSplatSamplingPreview", + "ko/built-in-nodes/VAEDecodeTripoSplat" + ] + }, + { + "group": "Void", + "pages": [ + "ko/built-in-nodes/VOIDWarpedNoise", + "ko/built-in-nodes/VOIDWarpedNoiseSource" ] }, - "ko/built-in-nodes/BatchLatentsNode", - "ko/built-in-nodes/EmptyFlux2LatentImage", - "ko/built-in-nodes/EmptyHunyuanImageLatent", + "ko/built-in-nodes/EmptyLatentAudio", "ko/built-in-nodes/EmptyLatentImage", - "ko/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel", "ko/built-in-nodes/LatentComposite", "ko/built-in-nodes/LatentCompositeMasked", "ko/built-in-nodes/LatentUpscale", "ko/built-in-nodes/LatentUpscaleBy", + "ko/built-in-nodes/LoadLatent", + "ko/built-in-nodes/SaveLatent", + "ko/built-in-nodes/SetLatentNoiseMask", + "ko/built-in-nodes/TrimVideoLatent", "ko/built-in-nodes/VAEDecode", - "ko/built-in-nodes/VAEEncode" + "ko/built-in-nodes/VAEDecodeAudio", + "ko/built-in-nodes/VAEDecodeAudioTiled", + "ko/built-in-nodes/VAEDecodeTiled", + "ko/built-in-nodes/VAEEncode", + "ko/built-in-nodes/VAEEncodeAudio", + "ko/built-in-nodes/VAEEncodeForInpaint", + "ko/built-in-nodes/VAEEncodeTiled" ] }, { - "group": "\ub85c\ub354", + "group": "Loaders", "pages": [ "ko/built-in-nodes/AudioEncoderLoader", + "ko/built-in-nodes/CheckpointLoader", "ko/built-in-nodes/CheckpointLoaderSimple", + "ko/built-in-nodes/ClipLoader", "ko/built-in-nodes/ClipVisionLoader", "ko/built-in-nodes/DiffControlNetLoader", + "ko/built-in-nodes/DiffusersLoader", + "ko/built-in-nodes/DualCLIPLoader", "ko/built-in-nodes/FrameInterpolationModelLoader", "ko/built-in-nodes/GLIGENLoader", "ko/built-in-nodes/HypernetworkLoader", "ko/built-in-nodes/ImageOnlyCheckpointLoader", "ko/built-in-nodes/LatentUpscaleModelLoader", "ko/built-in-nodes/LoadBackgroundRemovalModel", + "ko/built-in-nodes/LoadDA3Model", "ko/built-in-nodes/LoadMediaPipeFaceLandmarker", "ko/built-in-nodes/LoadMoGeModel", "ko/built-in-nodes/LoraLoaderBypass", "ko/built-in-nodes/LoraLoaderBypassModelOnly", "ko/built-in-nodes/LoraModelLoader", + "ko/built-in-nodes/LTXAVTextEncoderLoader", "ko/built-in-nodes/LTXVAudioVAELoader", + "ko/built-in-nodes/ModelPatchLoader", "ko/built-in-nodes/OpticalFlowLoader", + "ko/built-in-nodes/PhotoMakerLoader", + "ko/built-in-nodes/QuadrupleCLIPLoader", "ko/built-in-nodes/StyleModelLoader", + "ko/built-in-nodes/TripleCLIPLoader", "ko/built-in-nodes/unCLIPCheckpointLoader", + "ko/built-in-nodes/UNETLoader", "ko/built-in-nodes/UpscaleModelLoader", "ko/built-in-nodes/VAELoader" ] }, { - "group": "\ud328\uce58", + "group": "Merging", + "pages": [ + { + "group": "Model Specific", + "pages": [ + "ko/built-in-nodes/ModelMergeAuraflow", + "ko/built-in-nodes/ModelMergeCosmos14B", + "ko/built-in-nodes/ModelMergeCosmos7B", + "ko/built-in-nodes/ModelMergeCosmosPredict2_14B", + "ko/built-in-nodes/ModelMergeCosmosPredict2_2B", + "ko/built-in-nodes/ModelMergeFlux1", + "ko/built-in-nodes/ModelMergeKrea2", + "ko/built-in-nodes/ModelMergeLTXV", + "ko/built-in-nodes/ModelMergeMochiPreview", + "ko/built-in-nodes/ModelMergeQwenImage", + "ko/built-in-nodes/ModelMergeSD1", + "ko/built-in-nodes/ModelMergeSD35_Large", + "ko/built-in-nodes/ModelMergeSD3_2B", + "ko/built-in-nodes/ModelMergeSDXL", + "ko/built-in-nodes/ModelMergeWAN2_1" + ] + }, + "ko/built-in-nodes/CheckpointSave", + "ko/built-in-nodes/ClipMergeAdd", + "ko/built-in-nodes/ClipMergeSimple", + "ko/built-in-nodes/ClipMergeSubtract", + "ko/built-in-nodes/ClipSave", + "ko/built-in-nodes/ImageOnlyCheckpointSave", + "ko/built-in-nodes/ModelMergeAdd", + "ko/built-in-nodes/ModelMergeBlocks", + "ko/built-in-nodes/ModelMergeSimple", + "ko/built-in-nodes/ModelMergeSubtract", + "ko/built-in-nodes/ModelSave", + "ko/built-in-nodes/SaveLoRA", + "ko/built-in-nodes/VAESave" + ] + }, + { + "group": "Patch", "pages": [ { - "group": "Chroma Radiance", + "group": "Chroma Radiance", + "pages": [ + "ko/built-in-nodes/ChromaRadianceOptions" + ] + }, + { + "group": "Flux", + "pages": [ + "ko/built-in-nodes/ModelSamplingFlux", + "ko/built-in-nodes/USOStyleReference" + ] + }, + { + "group": "Hidream", + "pages": [ + "ko/built-in-nodes/HiDreamO1PatchSeamSmoothing" + ] + }, + { + "group": "Ltxv", "pages": [ - "ko/built-in-nodes/ChromaRadianceOptions" + "ko/built-in-nodes/ModelSamplingLTXV" ] }, { - "group": "Flux", + "group": "Qwen", "pages": [ - "ko/built-in-nodes/USOStyleReference" + "ko/built-in-nodes/QwenImageDiffsynthControlnet" + ] + }, + { + "group": "Stable Cascade", + "pages": [ + "ko/built-in-nodes/ModelSamplingStableCascade" + ] + }, + { + "group": "Stable Diffusion", + "pages": [ + "ko/built-in-nodes/ModelSamplingSD3" ] }, { @@ -9258,16 +9619,35 @@ "ko/built-in-nodes/TomePatchModel" ] }, + { + "group": "Wan", + "pages": [ + "ko/built-in-nodes/WanContextWindowsManual" + ] + }, + { + "group": "Z Image", + "pages": [ + "ko/built-in-nodes/ZImageFunControlnet" + ] + }, "ko/built-in-nodes/ContextWindowsManual", - "ko/built-in-nodes/ScaleROPE", - "ko/built-in-nodes/WanContextWindowsManual" + "ko/built-in-nodes/LTXVContextWindows", + "ko/built-in-nodes/ModelNoiseScale", + "ko/built-in-nodes/ModelSamplingAuraFlow", + "ko/built-in-nodes/ModelSamplingContinuousEDM", + "ko/built-in-nodes/ModelSamplingContinuousV", + "ko/built-in-nodes/ModelSamplingDiscrete", + "ko/built-in-nodes/RenormCFG", + "ko/built-in-nodes/RescaleCFG", + "ko/built-in-nodes/ScaleROPE" ] }, { - "group": "\uc0d8\ud50c\ub9c1", + "group": "Sampling", "pages": [ { - "group": "\ucee4\uc2a4\ud140 \uc0d8\ud50c\ub9c1", + "group": "Custom", "pages": [ "ko/built-in-nodes/APG", "ko/built-in-nodes/SamplerCustom", @@ -9275,10 +9655,11 @@ ] }, { - "group": "\uac00\uc774\ub354", + "group": "Guiders", "pages": [ "ko/built-in-nodes/BasicGuider", "ko/built-in-nodes/CFGGuider", + "ko/built-in-nodes/CFGOverride", "ko/built-in-nodes/DualCFGGuider", "ko/built-in-nodes/DualModelGuider", "ko/built-in-nodes/VideoLinearCFGGuidance", @@ -9286,15 +9667,15 @@ ] }, { - "group": "\ub178\uc774\uc988", + "group": "Noise", "pages": [ + "ko/built-in-nodes/AddNoise", "ko/built-in-nodes/DisableNoise", - "ko/built-in-nodes/RandomNoise", - "ko/built-in-nodes/VOIDWarpedNoiseSource" + "ko/built-in-nodes/RandomNoise" ] }, { - "group": "\uc0d8\ud50c\ub7ec", + "group": "Samplers", "pages": [ "ko/built-in-nodes/KSamplerSelect", "ko/built-in-nodes/SamplerARVideo", @@ -9315,7 +9696,7 @@ ] }, { - "group": "\uc2a4\ucf00\uc904\ub7ec", + "group": "Schedulers", "pages": [ "ko/built-in-nodes/AlignYourStepsScheduler", "ko/built-in-nodes/BasicScheduler", @@ -9323,6 +9704,7 @@ "ko/built-in-nodes/ExponentialScheduler", "ko/built-in-nodes/Flux2Scheduler", "ko/built-in-nodes/GITSScheduler", + "ko/built-in-nodes/Ideogram4Scheduler", "ko/built-in-nodes/KarrasScheduler", "ko/built-in-nodes/LaplaceScheduler", "ko/built-in-nodes/LTXVScheduler", @@ -9333,10 +9715,11 @@ ] }, { - "group": "\uc2dc\uadf8\ub9c8", + "group": "Sigmas", "pages": [ "ko/built-in-nodes/ExtendIntermediateSigmas", "ko/built-in-nodes/FlipSigmas", + "ko/built-in-nodes/ManualSigmas", "ko/built-in-nodes/SamplingPercentToSigma", "ko/built-in-nodes/SetFirstSigma", "ko/built-in-nodes/SplitSigmas", @@ -9348,7 +9731,7 @@ ] }, { - "group": "\ud559\uc2b5", + "group": "Training", "pages": [ "ko/built-in-nodes/LoadTrainingDataset", "ko/built-in-nodes/LossGraphNode", @@ -9361,7 +9744,7 @@ ] }, { - "group": "\ud30c\ud2b8\ub108", + "group": "Partner", "pages": [ { "group": "3D", @@ -9406,6 +9789,7 @@ "pages": [ "ko/built-in-nodes/TripoConversionNode", "ko/built-in-nodes/TripoImageToModelNode", + "ko/built-in-nodes/TripoImportModelNode", "ko/built-in-nodes/TripoMultiviewToModelNode", "ko/built-in-nodes/TripoP1ImageToModelNode", "ko/built-in-nodes/TripoP1MultiviewToModelNode", @@ -9420,8 +9804,14 @@ ] }, { - "group": "\uc624\ub514\uc624", + "group": "Audio", "pages": [ + { + "group": "Bytedance", + "pages": [ + "ko/built-in-nodes/ByteDanceSeedAudio" + ] + }, { "group": "Elevenlabs", "pages": [ @@ -9441,19 +9831,11 @@ "ko/built-in-nodes/SoniloTextToMusic", "ko/built-in-nodes/SoniloVideoToMusic" ] - }, - { - "group": "Stability Ai", - "pages": [ - "ko/built-in-nodes/StabilityAudioInpaint", - "ko/built-in-nodes/StabilityAudioToAudio", - "ko/built-in-nodes/StabilityTextToAudio" - ] } ] }, { - "group": "\uc774\ubbf8\uc9c0", + "group": "Image", "pages": [ { "group": "Beeble", @@ -9514,8 +9896,6 @@ { "group": "Ideogram", "pages": [ - "ko/built-in-nodes/IdeogramV1", - "ko/built-in-nodes/IdeogramV2", "ko/built-in-nodes/IdeogramV3", "ko/built-in-nodes/IdeogramV4" ] @@ -9609,16 +9989,6 @@ "ko/built-in-nodes/RunwayTextToImageNode" ] }, - { - "group": "Stability Ai", - "pages": [ - "ko/built-in-nodes/StabilityStableImageSD_3_5Node", - "ko/built-in-nodes/StabilityStableImageUltraNode", - "ko/built-in-nodes/StabilityUpscaleConservativeNode", - "ko/built-in-nodes/StabilityUpscaleCreativeNode", - "ko/built-in-nodes/StabilityUpscaleFastNode" - ] - }, { "group": "Topaz", "pages": [ @@ -9641,7 +10011,7 @@ ] }, { - "group": "\ud14d\uc2a4\ud2b8", + "group": "Text", "pages": [ { "group": "Anthropic", @@ -9659,7 +10029,8 @@ "group": "Gemini", "pages": [ "ko/built-in-nodes/GeminiInputFiles", - "ko/built-in-nodes/GeminiNode" + "ko/built-in-nodes/GeminiNode", + "ko/built-in-nodes/GeminiNodeV2" ] }, { @@ -9679,7 +10050,7 @@ ] }, { - "group": "\ube44\ub514\uc624", + "group": "Video", "pages": [ { "group": "Beeble", @@ -9709,6 +10080,12 @@ "ko/built-in-nodes/ByteDanceTextToVideoNode" ] }, + { + "group": "Gemini", + "pages": [ + "ko/built-in-nodes/GeminiVideoOmni" + ] + }, { "group": "Grok", "pages": [ @@ -9763,6 +10140,13 @@ "pages": [ "ko/built-in-nodes/LumaConceptsNode", "ko/built-in-nodes/LumaImageToVideoNode", + "ko/built-in-nodes/LumaRay32ExtendVideoNode", + "ko/built-in-nodes/LumaRay32ImageToVideoNode", + "ko/built-in-nodes/LumaRay32KeyframeNode", + "ko/built-in-nodes/LumaRay32KeyframesToVideoNode", + "ko/built-in-nodes/LumaRay32TextToVideoNode", + "ko/built-in-nodes/LumaRay32VideoEditNode", + "ko/built-in-nodes/LumaRay32VideoReframeNode", "ko/built-in-nodes/LumaVideoNode" ] }, @@ -9787,6 +10171,9 @@ { "group": "Runway", "pages": [ + "ko/built-in-nodes/RunwayAleph2KeyframeNode", + "ko/built-in-nodes/RunwayAleph2PromptImageNode", + "ko/built-in-nodes/RunwayAleph2VideoToVideoNode", "ko/built-in-nodes/RunwayFirstLastFrameNode", "ko/built-in-nodes/RunwayImageToVideoNodeGen3a", "ko/built-in-nodes/RunwayImageToVideoNodeGen4" @@ -9859,125 +10246,450 @@ ] }, { - "group": "\uc0d8\ud50c\ub9c1", + "group": "Text", + "pages": [ + "ko/built-in-nodes/AddTextPrefix", + "ko/built-in-nodes/AddTextSuffix", + "ko/built-in-nodes/BuildJsonPromptIdeogram", + "ko/built-in-nodes/CaseConverter", + "ko/built-in-nodes/ConvertArrayToString", + "ko/built-in-nodes/ConvertDictionaryToString", + "ko/built-in-nodes/JsonExtractString", + "ko/built-in-nodes/MergeTextLists", + "ko/built-in-nodes/RegexExtract", + "ko/built-in-nodes/RegexMatch", + "ko/built-in-nodes/RegexReplace", + "ko/built-in-nodes/ReplaceText", + "ko/built-in-nodes/StringCompare", + "ko/built-in-nodes/StringConcatenate", + "ko/built-in-nodes/StringContains", + "ko/built-in-nodes/StringFormat", + "ko/built-in-nodes/StringLength", + "ko/built-in-nodes/StringReplace", + "ko/built-in-nodes/StringSubstring", + "ko/built-in-nodes/StringTrim", + "ko/built-in-nodes/StripWhitespace", + "ko/built-in-nodes/TextGenerate", + "ko/built-in-nodes/TextGenerateLTX2Prompt", + "ko/built-in-nodes/TextToLowercase", + "ko/built-in-nodes/TextToUppercase", + "ko/built-in-nodes/TruncateText" + ] + }, + { + "group": "Utilities", + "pages": [ + { + "group": "Logic", + "pages": [ + "ko/built-in-nodes/AutogrowNamesTestNode", + "ko/built-in-nodes/AutogrowPrefixTestNode", + "ko/built-in-nodes/ComboOptionTestNode", + "ko/built-in-nodes/ComfyAndNode", + "ko/built-in-nodes/ComfyNotNode", + "ko/built-in-nodes/ComfyOrNode", + "ko/built-in-nodes/ComfySoftSwitchNode", + "ko/built-in-nodes/ComfySwitchNode", + "ko/built-in-nodes/ConvertStringToComboNode", + "ko/built-in-nodes/DCTestNode", + "ko/built-in-nodes/InvertBooleanNode" + ] + }, + { + "group": "Primitive", + "pages": [ + "ko/built-in-nodes/PrimitiveBoolean", + "ko/built-in-nodes/PrimitiveBoundingBox", + "ko/built-in-nodes/PrimitiveFloat", + "ko/built-in-nodes/PrimitiveInt", + "ko/built-in-nodes/PrimitiveString", + "ko/built-in-nodes/PrimitiveStringMultiline" + ] + }, + "ko/built-in-nodes/ColorToRGBInt", + "ko/built-in-nodes/ComfyMathExpression", + "ko/built-in-nodes/ComfyNumberConvert", + "ko/built-in-nodes/CreateBoundingBoxes", + "ko/built-in-nodes/CreateList", + "ko/built-in-nodes/CurveEditor", + "ko/built-in-nodes/CustomCombo", + "ko/built-in-nodes/ImageHistogram", + "ko/built-in-nodes/PreviewAny", + "ko/built-in-nodes/ResolutionSelector", + "ko/built-in-nodes/SeedNode" + ] + }, + { + "group": "Video", + "pages": [ + { + "group": "Preprocessors", + "pages": [ + "ko/built-in-nodes/LTXVPreprocess" + ] + }, + "ko/built-in-nodes/CreateVideo", + "ko/built-in-nodes/FrameInterpolate", + "ko/built-in-nodes/GetVideoComponents", + "ko/built-in-nodes/LoadVideo", + "ko/built-in-nodes/SaveVideo", + "ko/built-in-nodes/SaveWEBM", + "ko/built-in-nodes/Video Slice" + ] + }, + { + "group": "고급", + "pages": [ + { + "group": "Debug", + "pages": [ + "ko/built-in-nodes/EasyCache", + "ko/built-in-nodes/LazyCache", + "ko/built-in-nodes/ModelComputeDtype" + ] + }, + { + "group": "Guidance", + "pages": [ + "ko/built-in-nodes/CFGNorm", + "ko/built-in-nodes/CFGZeroStar", + "ko/built-in-nodes/NAGuidance", + "ko/built-in-nodes/SkipLayerGuidanceDiT", + "ko/built-in-nodes/SkipLayerGuidanceDiTSimple", + "ko/built-in-nodes/SkipLayerGuidanceSD3", + "ko/built-in-nodes/TCFG" + ] + }, + { + "group": "Hooks", + "pages": [ + { + "group": "Clip", + "pages": [ + "ko/built-in-nodes/SetClipHooks" + ] + }, + { + "group": "Combine", + "pages": [ + "ko/built-in-nodes/CombineHooks", + "ko/built-in-nodes/CombineHooksEight", + "ko/built-in-nodes/CombineHooksFour" + ] + }, + { + "group": "Cond Pair", + "pages": [ + "ko/built-in-nodes/PairConditioningCombine", + "ko/built-in-nodes/PairConditioningSetDefaultAndCombine", + "ko/built-in-nodes/PairConditioningSetProperties", + "ko/built-in-nodes/PairConditioningSetPropertiesAndCombine" + ] + }, + { + "group": "Cond Single", + "pages": [ + "ko/built-in-nodes/ConditioningSetDefaultAndCombine", + "ko/built-in-nodes/ConditioningSetProperties", + "ko/built-in-nodes/ConditioningSetPropertiesAndCombine" + ] + }, + { + "group": "Create", + "pages": [ + "ko/built-in-nodes/CreateHookLora", + "ko/built-in-nodes/CreateHookLoraModelOnly", + "ko/built-in-nodes/CreateHookModelAsLora", + "ko/built-in-nodes/CreateHookModelAsLoraModelOnly" + ] + }, + { + "group": "Manual", + "pages": [ + "ko/built-in-nodes/SetModelHooksOnCond" + ] + }, + { + "group": "Scheduling", + "pages": [ + "ko/built-in-nodes/CreateHookKeyframe", + "ko/built-in-nodes/CreateHookKeyframesFromFloats", + "ko/built-in-nodes/CreateHookKeyframesInterpolated", + "ko/built-in-nodes/SetHookKeyframes" + ] + }, + "ko/built-in-nodes/ConditioningTimestepsRange" + ] + }, + { + "group": "Loaders", + "pages": [ + "ko/built-in-nodes/DeprecatedCheckpointLoader", + "ko/built-in-nodes/DeprecatedDiffusersLoader" + ] + }, + { + "group": "Model Merging", + "pages": [ + "ko/built-in-nodes/SaveLoRANode" + ] + }, + { + "group": "Multigpu", + "pages": [ + "ko/built-in-nodes/MultiGPU_Options", + "ko/built-in-nodes/MultiGPU_WorkUnits", + "ko/built-in-nodes/SelectCLIPDevice", + "ko/built-in-nodes/SelectModelDevice", + "ko/built-in-nodes/SelectVAEDevice" + ] + }, + "ko/built-in-nodes/IdeogramV1", + "ko/built-in-nodes/IdeogramV2", + "ko/built-in-nodes/MoonvalleyImg2VideoNode", + "ko/built-in-nodes/MoonvalleyTxt2VideoNode", + "ko/built-in-nodes/MoonvalleyVideo2VideoNode", + "ko/built-in-nodes/SeedVR2Conditioning", + "ko/built-in-nodes/SeedVR2PostProcessing", + "ko/built-in-nodes/SeedVR2Preprocess", + "ko/built-in-nodes/SeedVR2ProgressiveSampler", + "ko/built-in-nodes/StabilityAudioInpaint", + "ko/built-in-nodes/StabilityAudioToAudio", + "ko/built-in-nodes/StabilityStableImageSD_3_5Node", + "ko/built-in-nodes/StabilityStableImageUltraNode", + "ko/built-in-nodes/StabilityTextToAudio", + "ko/built-in-nodes/StabilityUpscaleConservativeNode", + "ko/built-in-nodes/StabilityUpscaleCreativeNode", + "ko/built-in-nodes/StabilityUpscaleFastNode" + ] + }, + { + "group": "로더", + "pages": [ + "ko/built-in-nodes/ControlNetLoader" + ] + }, + { + "group": "샘플링", "pages": [ { - "group": "\ucee4\uc2a4\ud140 \uc0d8\ud50c\ub9c1", + "group": "Custom Sampling", "pages": [ { - "group": "\uc0d8\ud50c\ub7ec", + "group": "Samplers", "pages": [ "ko/built-in-nodes/SamplerDpmpp2mSde", "ko/built-in-nodes/SamplerDpmppSde" ] - }, - { - "group": "\uc2a4\ucf00\uc904\ub7ec", - "pages": [ - "ko/built-in-nodes/Ideogram4Scheduler" - ] - }, - "ko/built-in-nodes/CFGOverride" + } ] } ] }, { - "group": "\ud14d\uc2a4\ud2b8", + "group": "유틸리티", "pages": [ - "ko/built-in-nodes/AddTextPrefix", - "ko/built-in-nodes/AddTextSuffix", - "ko/built-in-nodes/CaseConverter", - "ko/built-in-nodes/JsonExtractString", - "ko/built-in-nodes/MergeTextLists", - "ko/built-in-nodes/RegexExtract", - "ko/built-in-nodes/RegexMatch", - "ko/built-in-nodes/RegexReplace", - "ko/built-in-nodes/ReplaceText", - "ko/built-in-nodes/StringCompare", - "ko/built-in-nodes/StringConcatenate", - "ko/built-in-nodes/StringContains", - "ko/built-in-nodes/StringFormat", - "ko/built-in-nodes/StringLength", - "ko/built-in-nodes/StringReplace", - "ko/built-in-nodes/StringSubstring", - "ko/built-in-nodes/StringTrim", - "ko/built-in-nodes/StripWhitespace", - "ko/built-in-nodes/TextGenerate", - "ko/built-in-nodes/TextGenerateLTX2Prompt", - "ko/built-in-nodes/TextToLowercase", - "ko/built-in-nodes/TextToUppercase", - "ko/built-in-nodes/TruncateText" + "ko/built-in-nodes/BatchImagesMasksLatentsNode", + "ko/built-in-nodes/MarkdownNote", + "ko/built-in-nodes/Note", + "ko/built-in-nodes/Reroute", + "ko/built-in-nodes/TerminalLog", + "ko/built-in-nodes/wanBlockSwap" ] }, { - "group": "\uc720\ud2f8\ub9ac\ud2f0", + "group": "이미지", "pages": [ { - "group": "\ub85c\uc9c1", + "group": "Adjustments", "pages": [ - "ko/built-in-nodes/AutogrowNamesTestNode", - "ko/built-in-nodes/AutogrowPrefixTestNode", - "ko/built-in-nodes/ComboOptionTestNode", - "ko/built-in-nodes/ComfyAndNode", - "ko/built-in-nodes/ComfyNotNode", - "ko/built-in-nodes/ComfyOrNode", - "ko/built-in-nodes/ComfySoftSwitchNode", - "ko/built-in-nodes/ComfySwitchNode", - "ko/built-in-nodes/ConvertStringToComboNode", - "ko/built-in-nodes/DCTestNode", - "ko/built-in-nodes/InvertBooleanNode" + "ko/built-in-nodes/AdjustBrightness", + "ko/built-in-nodes/AdjustContrast" ] }, { - "group": "\ud504\ub9ac\ubbf8\ud2f0\ube0c", + "group": "Background Removal", "pages": [ - "ko/built-in-nodes/PrimitiveBoolean", - "ko/built-in-nodes/PrimitiveBoundingBox", - "ko/built-in-nodes/PrimitiveFloat", - "ko/built-in-nodes/PrimitiveInt", - "ko/built-in-nodes/PrimitiveString", - "ko/built-in-nodes/PrimitiveStringMultiline" + "ko/built-in-nodes/RemoveBackground" ] }, - "ko/built-in-nodes/ColorToRGBInt", - "ko/built-in-nodes/ComfyMathExpression", - "ko/built-in-nodes/ComfyNumberConvert", - "ko/built-in-nodes/CreateList", - "ko/built-in-nodes/CurveEditor", - "ko/built-in-nodes/CustomCombo", - "ko/built-in-nodes/ImageHistogram", - "ko/built-in-nodes/PreviewAny", - "ko/built-in-nodes/ResolutionSelector" - ] - }, - { - "group": "\uc720\ud2f8\ub9ac\ud2f0", - "pages": [ - "ko/built-in-nodes/BatchImagesMasksLatentsNode", - "ko/built-in-nodes/MarkdownNote", - "ko/built-in-nodes/Note", - "ko/built-in-nodes/Reroute", - "ko/built-in-nodes/TerminalLog", - "ko/built-in-nodes/wanBlockSwap" + { + "group": "Batch", + "pages": [ + "ko/built-in-nodes/ImageDeduplication", + "ko/built-in-nodes/ImageFromBatch", + "ko/built-in-nodes/ImageGrid", + "ko/built-in-nodes/ImageMergeTileList", + "ko/built-in-nodes/MergeImageLists", + "ko/built-in-nodes/RebatchImages", + "ko/built-in-nodes/RepeatImageBatch", + "ko/built-in-nodes/ShuffleDataset", + "ko/built-in-nodes/ShuffleImageTextDataset", + "ko/built-in-nodes/SplitImageToTileList" + ] + }, + { + "group": "Color", + "pages": [ + "ko/built-in-nodes/ImageRGBToYUV", + "ko/built-in-nodes/ImageYUVToRGB", + "ko/built-in-nodes/NormalizeImages" + ] + }, + { + "group": "Compositing", + "pages": [ + "ko/built-in-nodes/ImageCompositeMasked", + "ko/built-in-nodes/JoinImageWithAlpha", + "ko/built-in-nodes/PorterDuffImageComposite", + "ko/built-in-nodes/SplitImageWithAlpha" + ] + }, + { + "group": "Detection", + "pages": [ + "ko/built-in-nodes/DrawBBoxes", + "ko/built-in-nodes/MediaPipeFaceLandmarker", + "ko/built-in-nodes/MediaPipeFaceMask", + "ko/built-in-nodes/MediaPipeFaceMeshVisualize", + "ko/built-in-nodes/RTDETR_detect", + "ko/built-in-nodes/SAM3_Detect", + "ko/built-in-nodes/SAM3_TrackPreview", + "ko/built-in-nodes/SAM3_TrackToMask", + "ko/built-in-nodes/SAM3_VideoTrack", + "ko/built-in-nodes/SDPoseDrawKeypoints", + "ko/built-in-nodes/SDPoseFaceBBoxes", + "ko/built-in-nodes/SDPoseKeypointExtractor" + ] + }, + { + "group": "Filters", + "pages": [ + "ko/built-in-nodes/Canny", + "ko/built-in-nodes/ColorTransfer", + "ko/built-in-nodes/ImageAddNoise", + "ko/built-in-nodes/ImageBlend", + "ko/built-in-nodes/ImageBlur", + "ko/built-in-nodes/ImageQuantize", + "ko/built-in-nodes/ImageSharpen", + "ko/built-in-nodes/Morphology" + ] + }, + { + "group": "Geometry Estimation", + "pages": [ + "ko/built-in-nodes/DA3GeometryToMesh", + "ko/built-in-nodes/DA3GeometryToPointCloud", + "ko/built-in-nodes/DA3Inference", + "ko/built-in-nodes/DA3Render", + "ko/built-in-nodes/MoGeInference", + "ko/built-in-nodes/MoGePanoramaInference", + "ko/built-in-nodes/MoGePointMapToMesh", + "ko/built-in-nodes/MoGeRender" + ] + }, + { + "group": "Mask", + "pages": [ + "ko/built-in-nodes/BatchMasksNode", + "ko/built-in-nodes/CropMask", + "ko/built-in-nodes/FeatherMask", + "ko/built-in-nodes/GrowMask", + "ko/built-in-nodes/ImageColorToMask", + "ko/built-in-nodes/ImageToMask", + "ko/built-in-nodes/InvertMask", + "ko/built-in-nodes/MaskComposite", + "ko/built-in-nodes/MaskPreview", + "ko/built-in-nodes/MaskToImage", + "ko/built-in-nodes/SolidMask", + "ko/built-in-nodes/ThresholdMask", + "ko/built-in-nodes/VOIDQuadmaskPreprocess" + ] + }, + { + "group": "Shader", + "pages": [ + "ko/built-in-nodes/GLSLShader" + ] + }, + { + "group": "Transform", + "pages": [ + "ko/built-in-nodes/CenterCropImages", + "ko/built-in-nodes/CropByBBoxes", + "ko/built-in-nodes/ImageCrop", + "ko/built-in-nodes/ImageCropV2", + "ko/built-in-nodes/ImageFlip", + "ko/built-in-nodes/ImagePadForOutpaint", + "ko/built-in-nodes/ImageRotate", + "ko/built-in-nodes/ImageStitch", + "ko/built-in-nodes/RandomCropImages", + "ko/built-in-nodes/ResizeAndPadImage", + "ko/built-in-nodes/ResizeImagesByLongerEdge", + "ko/built-in-nodes/ResizeImagesByShorterEdge" + ] + }, + { + "group": "Upscaling", + "pages": [ + "ko/built-in-nodes/ImageScale", + "ko/built-in-nodes/ImageScaleBy", + "ko/built-in-nodes/ImageScaleToMaxDimension", + "ko/built-in-nodes/ImageScaleToTotalPixels", + "ko/built-in-nodes/ImageUpscaleWithModel" + ] + }, + { + "group": "Video", + "pages": [ + "ko/built-in-nodes/WanDancerPadKeyframes", + "ko/built-in-nodes/WanDancerPadKeyframesList" + ] + }, + "ko/built-in-nodes/BatchImagesNode", + "ko/built-in-nodes/ConditioningCombine", + "ko/built-in-nodes/EmptyImage", + "ko/built-in-nodes/GetImageSize", + "ko/built-in-nodes/ImageBatch", + "ko/built-in-nodes/ImageCompare", + "ko/built-in-nodes/ImageInvert", + "ko/built-in-nodes/LoadImage", + "ko/built-in-nodes/LoadImageDataSetFromFolder", + "ko/built-in-nodes/LoadImageMask", + "ko/built-in-nodes/LoadImageOutput", + "ko/built-in-nodes/LoadImageSetFromFolderNode", + "ko/built-in-nodes/LoadImageSetNode", + "ko/built-in-nodes/LoadImageTextDataSetFromFolder", + "ko/built-in-nodes/LoadImageTextSetFromFolderNode", + "ko/built-in-nodes/LoraLoader", + "ko/built-in-nodes/LoraLoaderModelOnly", + "ko/built-in-nodes/Painter", + "ko/built-in-nodes/PreviewImage", + "ko/built-in-nodes/ResizeImageMaskNode", + "ko/built-in-nodes/SaveAnimatedPNG", + "ko/built-in-nodes/SaveAnimatedWEBP", + "ko/built-in-nodes/SaveImage", + "ko/built-in-nodes/SaveImageAdvanced", + "ko/built-in-nodes/SaveImageDataSetToFolder", + "ko/built-in-nodes/SaveImageTextDataSetToFolder", + "ko/built-in-nodes/SaveSVGNode", + "ko/built-in-nodes/WebcamCapture" ] }, { - "group": "\ube44\ub514\uc624", + "group": "컨디셔닝", "pages": [ { - "group": "\uc804\ucc98\ub9ac\uae30", + "group": "Video Models", "pages": [ - "ko/built-in-nodes/LTXVPreprocess" + "ko/built-in-nodes/Stablezero123Conditioning", + "ko/built-in-nodes/Stablezero123ConditioningBatched", + "ko/built-in-nodes/SVD_img2vid_Conditioning", + "ko/built-in-nodes/SvdImg2vidConditioning" ] }, - "ko/built-in-nodes/CreateVideo", - "ko/built-in-nodes/FrameInterpolate", - "ko/built-in-nodes/GetVideoComponents", - "ko/built-in-nodes/LoadVideo", - "ko/built-in-nodes/SaveVideo", - "ko/built-in-nodes/SaveWEBM", - "ko/built-in-nodes/Video Slice" + "ko/built-in-nodes/ConditioningAverage", + "ko/built-in-nodes/Sd4xupscaleConditioning" ] } ] @@ -9985,7 +10697,7 @@ ] }, { - "tab": "\uac1c\ubc1c", + "tab": "개발", "pages": [ "ko/development/overview", { @@ -10003,7 +10715,7 @@ ] }, { - "group": "ComfyUI \uc11c\ubc84 API", + "group": "ComfyUI 서버 API", "icon": "server", "pages": [ "ko/development/comfyui-server/comms_overview", @@ -10028,12 +10740,12 @@ ] }, { - "group": "\ucee4\uc2a4\ud140 \ub178\ub4dc \uac1c\ubc1c", + "group": "커스텀 노드 개발", "pages": [ "ko/custom-nodes/overview", "ko/custom-nodes/walkthrough", { - "group": "\ubc31\uc5d4\ub4dc", + "group": "백엔드", "icon": "python", "pages": [ "ko/custom-nodes/backend/server_overview", @@ -10078,7 +10790,7 @@ ] }, { - "group": "\ub808\uc9c0\uc2a4\ud2b8\ub9ac", + "group": "레지스트리", "pages": [ "ko/registry/overview", "ko/registry/publishing", @@ -10090,7 +10802,7 @@ ] }, { - "group": "\uc2a4\ud399", + "group": "스펙", "pages": [ { "group": "Workflow JSON", @@ -10100,7 +10812,7 @@ ] }, { - "group": "\ub178\ub4dc \uc815\uc758", + "group": "노드 정의", "pages": [ "ko/specs/nodedef_json", "ko/specs/nodedef_json_1_0" @@ -10111,12 +10823,12 @@ ] }, { - "tab": "\uc9c0\uc6d0", + "tab": "지원", "pages": [ "ko/support/contact-support", "ko/support/data-retention", { - "group": "\uacc4\uc815 \uad00\ub9ac", + "group": "계정 관리", "icon": "user", "pages": [ "ko/account/create-account", @@ -10125,10 +10837,10 @@ ] }, { - "group": "\uacb0\uc81c \uc9c0\uc6d0", + "group": "결제 지원", "pages": [ { - "group": "\uad6c\ub3c5", + "group": "구독", "pages": [ "ko/support/subscription/subscribing", "ko/support/subscription/managing", @@ -10137,7 +10849,7 @@ ] }, { - "group": "\uacb0\uc81c", + "group": "결제", "pages": [ "ko/support/payment/accepted-payment-methods", "ko/support/payment/editing-payment-information", @@ -10150,7 +10862,7 @@ ] }, { - "group": "\ubb38\uc81c \ud574\uacb0", + "group": "문제 해결", "icon": "bug", "pages": [ "ko/troubleshooting/overview", @@ -10159,7 +10871,7 @@ ] }, { - "group": "\ucee4\ubba4\ub2c8\ud2f0", + "group": "커뮤니티", "pages": [ "ko/community/contributing", "ko/community/links" @@ -10168,11 +10880,11 @@ ] }, { - "tab": "Registry API \ucc38\uc870", + "tab": "Registry API 참조", "openapi": "https://api.comfy.org/openapi" }, { - "tab": "Cloud API \ucc38\uc870", + "tab": "Cloud API 참조", "openapi": { "source": "openapi-cloud.yaml", "directory": "ko/api-reference/cloud" @@ -10188,56 +10900,56 @@ }, "links": [ { - "header": "\ub9ac\uc18c\uc2a4", + "header": "리소스", "items": [ { - "label": "\uc124\uce58", + "label": "설치", "href": "https://docs.comfy.org/ko/installation/system_requirements" }, { - "label": "\ud29c\ud1a0\ub9ac\uc5bc", + "label": "튜토리얼", "href": "https://docs.comfy.org/ko/tutorials/basic/text-to-image" }, { - "label": "\uac1c\ubc1c", + "label": "개발", "href": "https://docs.comfy.org/ko/development/overview" } ] }, { - "header": "\uc81c\ud488", + "header": "제품", "items": [ { - "label": "\uae30\ub2a5", + "label": "기능", "href": "https://www.comfy.org/?utm_source=docs#features-1" }, { - "label": "\uac24\ub7ec\ub9ac", + "label": "갤러리", "href": "https://www.comfy.org/gallery?utm_source=docs" }, { - "label": "\ub2e4\uc6b4\ub85c\ub4dc", + "label": "다운로드", "href": "https://www.comfy.org/download?utm_source=docs" } ] }, { - "header": "\ud68c\uc0ac \uc815\ubcf4", + "header": "회사 정보", "items": [ { - "label": "\uc18c\uac1c", + "label": "소개", "href": "https://www.comfy.org/about?utm_source=docs" }, { - "label": "\ucc44\uc6a9", + "label": "채용", "href": "https://www.comfy.org/careers?utm_source=docs" }, { - "label": "\uc774\uc6a9\uc57d\uad00", + "label": "이용약관", "href": "https://www.comfy.org/terms-of-service?utm_source=docs" }, { - "label": "\uac1c\uc778\uc815\ubcf4 \ucc98\ub9ac\ubc29\uce68", + "label": "개인정보 처리방침", "href": "https://www.comfy.org/privacy-policy?utm_source=docs" } ] @@ -10247,7 +10959,7 @@ "navbar": { "links": [ { - "label": "\ub2e4\uc6b4\ub85c\ub4dc", + "label": "다운로드", "href": "https://comfy.org/download?utm_source=docs" } ], diff --git a/ja/built-in-nodes/APG.mdx b/ja/built-in-nodes/APG.mdx index b676c62e1..982b6d337 100644 --- a/ja/built-in-nodes/APG.mdx +++ b/ja/built-in-nodes/APG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "APG" icon: "circle" mode: wide --- + 以下が翻訳結果です。 APG（適応型投影ガイダンス）ノードは、拡散プロセス中のガイダンスの適用方法を調整することで、サンプリングプロセスを変更します。このノードは、条件付き出力に対するガイダンスベクトルを平行成分と直交成分に分離し、より制御された画像生成を可能にします。ガイダンスのスケーリング、その大きさの正規化、および拡散ステップ間のスムーズな遷移のためのモメンタム適用のためのパラメータを提供します。 diff --git a/ja/built-in-nodes/ARVideoI2V.mdx b/ja/built-in-nodes/ARVideoI2V.mdx index 295225bf9..e87a9c2a6 100644 --- a/ja/built-in-nodes/ARVideoI2V.mdx +++ b/ja/built-in-nodes/ARVideoI2V.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ARVideoI2V" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/AddNoise.mdx b/ja/built-in-nodes/AddNoise.mdx index a987c962b..c0d84fb17 100644 --- a/ja/built-in-nodes/AddNoise.mdx +++ b/ja/built-in-nodes/AddNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddNoise" icon: "circle" mode: wide --- + このノードは、指定されたノイズ生成器とシグマ値を使用して、潜在画像に制御されたノイズを追加します。モデルのサンプリングシステムを通じて入力を処理し、指定されたシグマ範囲に適したノイズスケーリングを適用して、ノイズが適用された新しい潜在表現を返します。 ## 入力 diff --git a/ja/built-in-nodes/AddTextPrefix.mdx b/ja/built-in-nodes/AddTextPrefix.mdx index 180f5f394..83e999b8e 100644 --- a/ja/built-in-nodes/AddTextPrefix.mdx +++ b/ja/built-in-nodes/AddTextPrefix.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddTextPrefix" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- @@ -22,7 +23,7 @@ Add Text Prefix ノードは、各入力テキストの先頭に指定された | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `text` | 先頭にプレフィックスが追加された結果のテキストです。 | STRING | +| `テキスト` | 先頭にプレフィックスが追加された結果のテキストです。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextPrefix/ja.md) diff --git a/ja/built-in-nodes/AddTextSuffix.mdx b/ja/built-in-nodes/AddTextSuffix.mdx index 6d962406b..436754516 100644 --- a/ja/built-in-nodes/AddTextSuffix.mdx +++ b/ja/built-in-nodes/AddTextSuffix.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddTextSuffix" icon: "circle" mode: wide --- + このノードは、入力されたテキスト文字列の末尾に指定されたサフィックス（接尾語）を追加します。元のテキストとサフィックスを入力として受け取り、結合された結果を返します。 ## 入力 @@ -18,7 +19,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `text` | サフィックスが追加された結果のテキストです。 | STRING | +| `テキスト` | サフィックスが追加された結果のテキストです。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextSuffix/ja.md) diff --git a/ja/built-in-nodes/AdjustBrightness.mdx b/ja/built-in-nodes/AdjustBrightness.mdx index 8f04b6c33..01a4fdfb2 100644 --- a/ja/built-in-nodes/AdjustBrightness.mdx +++ b/ja/built-in-nodes/AdjustBrightness.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AdjustBrightness" icon: "circle" mode: wide --- + ## 概要 明るさ調整ノードは、入力画像の明るさを変更します。各ピクセルの値に指定された係数を乗算し、結果の値を有効範囲内に収めることで動作します。係数1.0は画像を変更せず、1.0未満の値は暗く、1.0を超える値は明るくします。 @@ -20,7 +21,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `image` | 明るさが調整された出力画像です。 | IMAGE | +| `画像` | 明るさが調整された出力画像です。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustBrightness/ja.md) diff --git a/ja/built-in-nodes/AdjustContrast.mdx b/ja/built-in-nodes/AdjustContrast.mdx index b787f8b06..58a993f2c 100644 --- a/ja/built-in-nodes/AdjustContrast.mdx +++ b/ja/built-in-nodes/AdjustContrast.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AdjustContrast" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -21,7 +22,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `image` | コントラストが調整された結果の画像です。 | IMAGE | +| `画像` | コントラストが調整された結果の画像です。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustContrast/ja.md) diff --git a/ja/built-in-nodes/AlignYourStepsScheduler.mdx b/ja/built-in-nodes/AlignYourStepsScheduler.mdx index f901b4e7f..5afcb65b7 100644 --- a/ja/built-in-nodes/AlignYourStepsScheduler.mdx +++ b/ja/built-in-nodes/AlignYourStepsScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AlignYourStepsScheduler" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/AudioAdjustVolume.mdx b/ja/built-in-nodes/AudioAdjustVolume.mdx index 34ed954f3..fe4bebd43 100644 --- a/ja/built-in-nodes/AudioAdjustVolume.mdx +++ b/ja/built-in-nodes/AudioAdjustVolume.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioAdjustVolume" icon: "circle" mode: wide --- + AudioAdjustVolumeノードは、デシベル（dB）単位で音量調整を適用することで、オーディオのラウドネスを変更します。オーディオ入力を受け取り、指定された音量レベルに基づいてゲイン係数を適用します。正の値は音量を増加させ、負の値は音量を減少させます。このノードは、元のオーディオと同じサンプルレートで変更されたオーディオを返します。 ## 入力 diff --git a/ja/built-in-nodes/AudioConcat.mdx b/ja/built-in-nodes/AudioConcat.mdx index 0941a65a3..893efb023 100644 --- a/ja/built-in-nodes/AudioConcat.mdx +++ b/ja/built-in-nodes/AudioConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioConcat" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 AudioConcatノードは、2つのオーディオ入力を結合して連結します。2つのオーディオ入力を受け取り、指定した順序で接続します。2つ目のオーディオを1つ目のオーディオの前または後に配置できます。このノードは、モノラルオーディオをステレオに変換し、2つの入力間でサンプルレートを一致させることで、異なるオーディオ形式を自動的に処理します。 diff --git a/ja/built-in-nodes/AudioEncoderEncode.mdx b/ja/built-in-nodes/AudioEncoderEncode.mdx index 1e5a2373d..8d6eee9ab 100644 --- a/ja/built-in-nodes/AudioEncoderEncode.mdx +++ b/ja/built-in-nodes/AudioEncoderEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEncoderEncode" icon: "circle" mode: wide --- + 以下は、ご依頼いただいた英語ドキュメントを日本語に翻訳したものです。 AudioEncoderEncode ノードは、オーディオエンコーダーモデルを使用してオーディオデータをエンコード処理します。オーディオ入力を受け取り、それをエンコードされた表現に変換し、条件付けパイプラインでのさらなる処理に使用できるようにします。このノードは、生のオーディオ波形を、オーディオベースの機械学習アプリケーションに適した形式に変換します。 diff --git a/ja/built-in-nodes/AudioEncoderLoader.mdx b/ja/built-in-nodes/AudioEncoderLoader.mdx index 95a696ed2..12a99c715 100644 --- a/ja/built-in-nodes/AudioEncoderLoader.mdx +++ b/ja/built-in-nodes/AudioEncoderLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEncoderLoader" icon: "circle" mode: wide --- + AudioEncoderLoader ノードは、オーディオエンコーダーフォルダ内のファイルからオーディオエンコーダーモデルを読み込みます。このノードは、オーディオエンコーダーモデルのファイル名を入力として受け取り、読み込まれたモデルを返します。このモデルは、ワークフロー内のオーディオ処理タスクに使用できます。 ## 入力 diff --git a/ja/built-in-nodes/AudioEqualizer3Band.mdx b/ja/built-in-nodes/AudioEqualizer3Band.mdx index b9e42c1aa..b5ed18efd 100644 --- a/ja/built-in-nodes/AudioEqualizer3Band.mdx +++ b/ja/built-in-nodes/AudioEqualizer3Band.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEqualizer3Band" icon: "circle" mode: wide --- + 以下が翻訳結果です。 オーディオイコライザー（3バンド）ノードを使用すると、オーディオ波形の低音、中音、高音の周波数を調整できます。このノードは、低音用のローシェルフ、中音用のピーキングフィルター、高音用のハイシェルフの3つの独立したフィルターを適用します。各バンドは、ゲイン、周波数、帯域幅の設定で個別に制御できます。 diff --git a/ja/built-in-nodes/AudioMerge.mdx b/ja/built-in-nodes/AudioMerge.mdx index d7355f511..eba2397b3 100644 --- a/ja/built-in-nodes/AudioMerge.mdx +++ b/ja/built-in-nodes/AudioMerge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioMerge" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioMerge/en.md) AudioMergeノードは、2つのオーディオトラックの波形を重ね合わせて結合します。両方のオーディオ入力のサンプルレートを自動的に一致させ、マージ前に長さを等しく調整します。このノードは、オーディオ信号を結合するためのいくつかの数学的手法を提供し、出力が許容可能な音量レベル内に収まるようにします。 diff --git a/ja/built-in-nodes/AutogrowNamesTestNode.mdx b/ja/built-in-nodes/AutogrowNamesTestNode.mdx index 6d9763806..d67a697dd 100644 --- a/ja/built-in-nodes/AutogrowNamesTestNode.mdx +++ b/ja/built-in-nodes/AutogrowNamesTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AutogrowNamesTestNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！ このノードは、Autogrow入力機能のテスト用です。動的な数のfloat入力を受け取り、それぞれに特定の名前をラベルとして付け、それらの値をカンマ区切りの単一の文字列に結合します。 diff --git a/ja/built-in-nodes/AutogrowPrefixTestNode.mdx b/ja/built-in-nodes/AutogrowPrefixTestNode.mdx index f5832b422..81dc1f433 100644 --- a/ja/built-in-nodes/AutogrowPrefixTestNode.mdx +++ b/ja/built-in-nodes/AutogrowPrefixTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AutogrowPrefixTestNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AutogrowPrefixTestNode/en.md) AutogrowPrefixTestNodeは、入力自動拡張機能をテストするために設計されたロジックノードです。動的な数のfloat入力を受け取り、それらの値をカンマ区切りの文字列に結合して出力します。 diff --git a/ja/built-in-nodes/BasicGuider.mdx b/ja/built-in-nodes/BasicGuider.mdx index 16652c53d..f75c7b84e 100644 --- a/ja/built-in-nodes/BasicGuider.mdx +++ b/ja/built-in-nodes/BasicGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BasicGuider" icon: "circle" mode: wide --- + BasicGuiderノードは、サンプリングプロセス用のシンプルなガイダンス機構を作成します。モデルと条件付けデータを入力として受け取り、サンプリング中の生成プロセスをガイドするために使用できるガイダーオブジェクトを生成します。このノードは、制御された生成に必要な基本的なガイダンス機能を提供します。 ## 入力 diff --git a/ja/built-in-nodes/BasicScheduler.mdx b/ja/built-in-nodes/BasicScheduler.mdx index bcf153f44..0cc1f042d 100755 --- a/ja/built-in-nodes/BasicScheduler.mdx +++ b/ja/built-in-nodes/BasicScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BasicScheduler" icon: "circle" mode: wide --- + `BasicScheduler`ノードは、指定されたスケジューラー、モデル、およびノイズ除去パラメーターに基づいて、拡散モデルのシグマ値のシーケンスを計算するように設計されています。ノイズ除去係数に基づいて総ステップ数を動的に調整し、拡散プロセスを微調整します。これにより、高度なサンプリングプロセス（マルチステージサンプリングなど）において、細かい制御が必要な各段階に正確な「レシピ」を提供します。 ## 入力 diff --git a/ja/built-in-nodes/BatchImagesMasksLatentsNode.mdx b/ja/built-in-nodes/BatchImagesMasksLatentsNode.mdx index 8bc02ce8e..e52852949 100644 --- a/ja/built-in-nodes/BatchImagesMasksLatentsNode.mdx +++ b/ja/built-in-nodes/BatchImagesMasksLatentsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchImagesMasksLatentsNode" icon: "circle" mode: wide --- + ## 概要 **バッチ画像/マスク/潜在表現**ノードは、同じタイプの複数の入力を1つのバッチに結合します。入力が画像、マスク、または潜在表現のいずれであるかを自動的に検出し、適切なバッチ処理方法を使用します。これは、バッチ入力を受け付けるノードで処理するために、複数のアイテムを準備する際に便利です。 diff --git a/ja/built-in-nodes/BatchImagesNode.mdx b/ja/built-in-nodes/BatchImagesNode.mdx index 5f3511f6c..c60459237 100644 --- a/ja/built-in-nodes/BatchImagesNode.mdx +++ b/ja/built-in-nodes/BatchImagesNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchImagesNode" icon: "circle" mode: wide --- + このドキュメントはAIが生成しました。誤りや改善の提案がありましたら、ぜひご貢献ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BatchImagesNode/en.md) バッチイメージノードは、複数の個別画像を1つのバッチに結合します。可変数の画像入力を受け取り、それらを1つのバッチ化された画像テンソルとして出力し、後続のノードでまとめて処理できるようにします。 diff --git a/ja/built-in-nodes/BatchLatentsNode.mdx b/ja/built-in-nodes/BatchLatentsNode.mdx index 9fa5b228e..d2e6c8019 100644 --- a/ja/built-in-nodes/BatchLatentsNode.mdx +++ b/ja/built-in-nodes/BatchLatentsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchLatentsNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！ Batch Latentsノードは、複数の潜在入力（latent inputs）を1つのバッチに結合します。可変数の潜在サンプルを受け取り、それらをバッチ次元に沿ってマージすることで、後続のノードでまとめて処理できるようにします。これは、複数の画像を1回の操作で生成または処理する際に便利です。 diff --git a/ja/built-in-nodes/BatchMasksNode.mdx b/ja/built-in-nodes/BatchMasksNode.mdx index 4d09de5e0..7b6f46f71 100644 --- a/ja/built-in-nodes/BatchMasksNode.mdx +++ b/ja/built-in-nodes/BatchMasksNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchMasksNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/BeebleSwitchXImageEdit.mdx b/ja/built-in-nodes/BeebleSwitchXImageEdit.mdx index ac792273e..79aeb663d 100644 --- a/ja/built-in-nodes/BeebleSwitchXImageEdit.mdx +++ b/ja/built-in-nodes/BeebleSwitchXImageEdit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BeebleSwitchXImageEdit" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、お気軽にご貢献ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BeebleSwitchXImageEdit/en.md) ## 概要 @@ -28,8 +29,8 @@ Beeble SwitchXを使用して、1枚の画像を編集します。このノー | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `アルファ` | シーン要素が切り替えられた編集済み画像です。 | IMAGE | -| `alpha` | Beebleによって使用されたアルファマットです。"fill"モードの場合は空で、個別のマットはありません。 | MASK | +| `画像` | シーン要素が切り替えられた編集済み画像です。 | IMAGE | +| `アルファ` | Beebleによって使用されたアルファマットです。"fill"モードの場合は空で、個別のマットはありません。 | MASK | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BeebleSwitchXImageEdit/ja.md) diff --git a/ja/built-in-nodes/BeebleSwitchXVideoEdit.mdx b/ja/built-in-nodes/BeebleSwitchXVideoEdit.mdx index cbab54631..02e4285c2 100644 --- a/ja/built-in-nodes/BeebleSwitchXVideoEdit.mdx +++ b/ja/built-in-nodes/BeebleSwitchXVideoEdit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BeebleSwitchXVideoEdit" icon: "circle" mode: wide --- + あなたは ComfyUI ノードドキュメントを英語から日本語に翻訳する技術翻訳の専門家です。 ## 翻訳ルール @@ -62,8 +63,8 @@ Beeble SwitchX を使用してビデオを編集します。このノードは | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `アルファ` | シーンの変更が適用された編集済みビデオ。 | VIDEO | -| `alpha` | Beeble によって使用されたアルファマット。"fill"モードの場合は空で、個別のマットはありません。 | VIDEO | +| `動画` | シーンの変更が適用された編集済みビデオ。 | VIDEO | +| `アルファ` | Beeble によって使用されたアルファマット。"fill"モードの場合は空で、個別のマットはありません。 | VIDEO | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BeebleSwitchXVideoEdit/ja.md) diff --git a/ja/built-in-nodes/BerniniConditioning.mdx b/ja/built-in-nodes/BerniniConditioning.mdx new file mode 100644 index 000000000..8b1e69d50 --- /dev/null +++ b/ja/built-in-nodes/BerniniConditioning.mdx @@ -0,0 +1,45 @@ +--- +title: "BerniniConditioning - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the BerniniConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "BerniniConditioning" +icon: "circle" +mode: wide +--- + +BerniniConditioningノードは、Wan2.2-A14Bモデル用の動画および画像の条件付けデータを準備します。提供されたVAEを使用してソース動画、参照動画、参照画像をエンコードし、それらを条件付けデータに付加して、インコンテキスト生成タスクを実行します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `positive` | ポジティブ条件付けデータ | CONDITIONING | はい | - | +| `negative` | ネガティブ条件付けデータ | CONDITIONING | はい | - | +| `vae` | 動画および画像入力をエンコードするために使用するVAEモデル | VAE | はい | - | +| `幅` | 出力潜在変数の幅（デフォルト: 832） | INT | はい | 16～8192（ステップ: 16） | +| `高さ` | 出力潜在変数の高さ（デフォルト: 480） | INT | はい | 16～8192（ステップ: 16） | +| `長さ` | 出力潜在変数のフレーム数（デフォルト: 81） | INT | はい | 1～8192（ステップ: 4） | +| `バッチサイズ` | 1バッチで生成する動画の数（デフォルト: 1） | INT | はい | 1～4096 | +| `ソース動画` | 編集またはリスタイルするソース動画（v2v、rv2v）。幅/高さにリサイズされ、長さにトリミングされます。 | IMAGE | いいえ | - | +| `リファレンス動画` | ソース動画に挿入する動画（ads2v）。 | IMAGE | いいえ | - | +| `リファレンス画像` | インコンテキストトークンとして注入される参照画像（r2v、rv2v）。最大8枚の画像を指定できます。 | IMAGE | いいえ | 0～8枚の画像 | +| `ref_max_size` | reference_videoおよびreference_imagesの長辺の最大サイズ。アスペクト比を維持してリサイズされ、16pxにスナップされます（デフォルト: 848）。 | INT | いいえ | 16～8192（ステップ: 16） | + +**注記:** タスクは、どの入力が接続されているかから推論されます： +- 入力が接続されていない場合 → テキストから動画へ（t2v） +- `source_video`のみの場合 → 動画から動画へ（v2v） +- `source_video` + `reference_images`の場合 → 参照ガイド付き動画編集（rv2v） +- `reference_images`のみの場合 → 参照から動画へ（r2v） +- `source_video` + `reference_video`の場合 → 画像/動画を動画に挿入（ads2v） + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `positive` | コンテキスト潜在変数が付加されたポジティブ条件付けデータ | CONDITIONING | +| `negative` | コンテキスト潜在変数が付加されたネガティブ条件付けデータ | CONDITIONING | +| `latent` | 指定された幅、高さ、長さ、バッチサイズに一致する次元を持つ空の潜在テンソル | LATENT | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BerniniConditioning/ja.md) + +--- +**Source fingerprint (SHA-256):** `3535bbe9a1ae007dc579242b44787ab315479a820eb0da680eab9b870ab60699` diff --git a/ja/built-in-nodes/BetaSamplingScheduler.mdx b/ja/built-in-nodes/BetaSamplingScheduler.mdx index dfe411f06..a03386caf 100644 --- a/ja/built-in-nodes/BetaSamplingScheduler.mdx +++ b/ja/built-in-nodes/BetaSamplingScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BetaSamplingScheduler" icon: "circle" mode: wide --- + BetaSamplingScheduler ノードは、ベータスケジューリングアルゴリズムを使用して、サンプリングプロセス用のノイズレベル（シグマ）のシーケンスを生成します。モデルと設定パラメータを受け取り、画像生成中のノイズ除去プロセスを制御するカスタマイズされたノイズスケジュールを作成します。このスケジューラーは、アルファパラメータとベータパラメータを通じてノイズ低減の軌跡を微調整することができます。 ## 入力 diff --git a/ja/built-in-nodes/BriaImageEditNode.mdx b/ja/built-in-nodes/BriaImageEditNode.mdx index 69013830c..29daa45b7 100644 --- a/ja/built-in-nodes/BriaImageEditNode.mdx +++ b/ja/built-in-nodes/BriaImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BriaImageEditNode" icon: "circle" mode: wide --- + Bria FIBO 画像編集ノードを使用すると、テキスト指示に基づいて既存の画像を変更できます。このノードは画像とプロンプトを Bria API に送信し、Bria API が FIBO モデルを使用して、リクエストに基づいた新しい編集済み画像を生成します。マスクを指定して、編集範囲を特定の領域に限定することもできます。 ## 入力 diff --git a/ja/built-in-nodes/BriaRemoveImageBackground.mdx b/ja/built-in-nodes/BriaRemoveImageBackground.mdx index 9f069a680..714af04cf 100644 --- a/ja/built-in-nodes/BriaRemoveImageBackground.mdx +++ b/ja/built-in-nodes/BriaRemoveImageBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BriaRemoveImageBackground" icon: "circle" mode: wide --- + このノードは、Bria RMBG 2.0サービスを使用して画像から背景を除去します。画像を外部APIに送信して処理し、背景が除去された結果を返します。 ## 入力 diff --git a/ja/built-in-nodes/BriaRemoveVideoBackground.mdx b/ja/built-in-nodes/BriaRemoveVideoBackground.mdx index 40ed1ad14..a27a2346f 100644 --- a/ja/built-in-nodes/BriaRemoveVideoBackground.mdx +++ b/ja/built-in-nodes/BriaRemoveVideoBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BriaRemoveVideoBackground" icon: "circle" mode: wide --- + このノードは、Bria AIサービスを使用して動画から背景を除去します。入力された動画を処理し、元の背景をお好みの単色に置き換えます。この処理は外部APIを介して実行され、結果は新しい動画ファイルとして返されます。 ## 入力 diff --git a/ja/built-in-nodes/BriaTransparentVideoBackground.mdx b/ja/built-in-nodes/BriaTransparentVideoBackground.mdx index 1810f0e7a..af1995398 100644 --- a/ja/built-in-nodes/BriaTransparentVideoBackground.mdx +++ b/ja/built-in-nodes/BriaTransparentVideoBackground.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaTransparentVideoBackground" icon: "circle" mode: wide --- -# Bria 動画背景削除（透明） このノードは、Bria の AI サービスを使用して動画から背景を削除し、切り抜かれたフレームとアルファマスクを出力します。両方の出力をコンポジットノードに接続するか、Save WEBM ノードに渡して透明動画を書き出します。 @@ -20,8 +19,8 @@ mode: wide | 出力名 | 説明 | データ型 | |--------|------|---------| -| `マスク` | 背景が除去された動画フレーム | IMAGE | -| `mask` | 動画フレームのアルファマスク | MASK | +| `画像` | 背景が除去された動画フレーム | IMAGE | +| `マスク` | 動画フレームのアルファマスク | MASK | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaTransparentVideoBackground/ja.md) diff --git a/ja/built-in-nodes/BriaVideoGreenScreen.mdx b/ja/built-in-nodes/BriaVideoGreenScreen.mdx index 28c8e9b72..3a23a4c41 100644 --- a/ja/built-in-nodes/BriaVideoGreenScreen.mdx +++ b/ja/built-in-nodes/BriaVideoGreenScreen.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaVideoGreenScreen" icon: "circle" mode: wide --- -# Bria ビデオグリーンスクリーン このノードは、Bria APIを使用してビデオの背景を単一色のクロマキー画面に置き換えます。入力ビデオを処理し、元の背景が除去されて均一なグリーンまたはブルースクリーンの色に置き換えられた新しいビデオを返します。 diff --git a/ja/built-in-nodes/BriaVideoReplaceBackground.mdx b/ja/built-in-nodes/BriaVideoReplaceBackground.mdx index fe47b9613..08c0db885 100644 --- a/ja/built-in-nodes/BriaVideoReplaceBackground.mdx +++ b/ja/built-in-nodes/BriaVideoReplaceBackground.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaVideoReplaceBackground" icon: "circle" mode: wide --- -# Bria ビデオ背景置換 このノードは、Bria の API を使用して、ビデオの背景を指定された画像またはビデオに置き換えます。出力は前景ビデオの解像度とフレームレートを維持します。アスペクト比が異なる背景は引き伸ばされて適合するため、アスペクト比を一致させると歪みのない結果が得られます。 @@ -13,10 +12,10 @@ mode: wide | パラメータ | 説明 | データ型 | 必須 | 範囲 | |-----------|-------------|-----------|----------|-------| -| `video` | 背景を置き換える前景ビデオ。 | VIDEO | はい | - | -| `background_image` | 前景の背後に合成する背景画像。背景画像または背景ビデオのいずれか一方を指定してください。両方は指定できません。 | IMAGE | いいえ | - | -| `background_video` | 前景の背後に合成する背景ビデオ。背景画像または背景ビデオのいずれか一方を指定してください。両方は指定できません。 | VIDEO | いいえ | - | -| `seed` | シードはノードを再実行するかどうかを制御します。シードに関係なく結果は非決定的です。（デフォルト：0） | INT | はい | 0 ～ 2147483647 | +| `ビデオ` | 背景を置き換える前景ビデオ。 | VIDEO | はい | - | +| `背景画像` | 前景の背後に合成する背景画像。背景画像または背景ビデオのいずれか一方を指定してください。両方は指定できません。 | IMAGE | いいえ | - | +| `背景ビデオ` | 前景の背後に合成する背景ビデオ。背景画像または背景ビデオのいずれか一方を指定してください。両方は指定できません。 | VIDEO | いいえ | - | +| `シード` | シードはノードを再実行するかどうかを制御します。シードに関係なく結果は非決定的です。（デフォルト：0） | INT | はい | 0 ～ 2147483647 | **注記：** `background_image` または `background_video` のいずれか一方のみを正確に指定する必要があります。両方の指定や、どちらも指定しないことはできません。前景ビデオは 60 秒以下である必要があります。 @@ -24,7 +23,7 @@ mode: wide | 出力名 | 説明 | データ型 | |-------------|-------------|-----------| -| `video` | 背景が置き換えられた結果のビデオ。 | VIDEO | +| `ビデオ` | 背景が置き換えられた結果のビデオ。 | VIDEO | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaVideoReplaceBackground/ja.md) diff --git a/ja/built-in-nodes/BuildJsonPromptIdeogram.mdx b/ja/built-in-nodes/BuildJsonPromptIdeogram.mdx new file mode 100644 index 000000000..ff6474230 --- /dev/null +++ b/ja/built-in-nodes/BuildJsonPromptIdeogram.mdx @@ -0,0 +1,37 @@ +--- +title: "BuildJsonPromptIdeogram - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the BuildJsonPromptIdeogram node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "BuildJsonPromptIdeogram" +icon: "circle" +mode: wide +--- + +このノードは、Ideogram 4 画像生成モデル用に特別にフォーマットされた構造化 JSON プロンプトを構築します。テキストによる指示、スタイル設定、カラーパレットを、モデルが期待する必要な JSON 構造に整理します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `要素` | 「Create Bounding Boxes」ノードからのプロンプト要素です。 | ARRAY | はい | - | +| `概要説明` | 画像のオプションの説明を1～2文で指定します。強く推奨されます。（デフォルト：空） | STRING | いいえ | - | +| `背景` | 画像の背景または環境の必須説明です。（デフォルト：空） | STRING | はい | - | +| `スタイル` | 生成画像のビジュアルスタイルカテゴリです。（デフォルト："none"） | COMBO | はい | `"none"`
`"photo"`
`"art_style"` | +| `photo` | 写真出力用のカメラまたはレンズの詳細（例：35mm、f/1.4、ボケ）。スタイルが"photo"に設定されている場合のみ使用可能です。（デフォルト：空） | STRING | いいえ | - | +| `art_style` | アートスタイルの説明（例：フラットベクターイラスト、太い輪郭線）。スタイルが"art_style"に設定されている場合のみ使用可能です。（デフォルト：空） | STRING | いいえ | - | +| `美的要素` | 必須の美的キーワード（例：ムーディー、シネマティック、彩度低め）。（デフォルト：空） | STRING | はい | - | +| `ライティング` | 必須の照明の説明（例：ゴールデンアワー、リムライト、劇的な影）。（デフォルト：空） | STRING | はい | - | +| `媒体` | 必須のメディアタイプ（例：photograph、illustration、3d_render、painting、graphic_design）。スタイルがphotoの場合、photographに設定してください。（デフォルト：空） | STRING | はい | - | +| `カラーパレット` | 画像の主要な色を誘導する16進数カラーコードです。最大16エントリまで指定できます。 | COLORS | いいえ | - | + +**注記：** `style` パラメータが "photo" に設定されている場合、`photo` 入力が使用可能になり、`medium` パラメータを "photograph" に設定する必要があります。`style` が "art_style" に設定されている場合、`art_style` 入力が使用可能になります。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `プロンプト` | 高レベルの説明、スタイルの説明（該当する場合）、および背景と要素を含む構成的な分解を格納した、構造化されたJSON辞書です。 | DICT | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BuildJsonPromptIdeogram/ja.md) + +--- +**Source fingerprint (SHA-256):** `56a045e0c7c19531e6443696c0bdf3946df066d03eea7d2d217b7d92f052592f` diff --git a/ja/built-in-nodes/ByteDance2FirstLastFrameNode.mdx b/ja/built-in-nodes/ByteDance2FirstLastFrameNode.mdx index 0072b090b..4bcf85a73 100644 --- a/ja/built-in-nodes/ByteDance2FirstLastFrameNode.mdx +++ b/ja/built-in-nodes/ByteDance2FirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2FirstLastFrameNode" icon: "circle" mode: wide --- + このノードは、ByteDance の Seedance 2.0 モデルを使用して動画を生成します。テキストプロンプトと必須の最初のフレーム画像に基づいて動画を作成します。オプションで最後のフレーム画像を指定すると、動画シーケンスの終了をガイドできます。 ## 入力 diff --git a/ja/built-in-nodes/ByteDance2ReferenceNode.mdx b/ja/built-in-nodes/ByteDance2ReferenceNode.mdx index 1a73c4601..e2ab6d704 100644 --- a/ja/built-in-nodes/ByteDance2ReferenceNode.mdx +++ b/ja/built-in-nodes/ByteDance2ReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2ReferenceNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 概要 diff --git a/ja/built-in-nodes/ByteDance2TextToVideoNode.mdx b/ja/built-in-nodes/ByteDance2TextToVideoNode.mdx index 7b7856154..55c3df491 100644 --- a/ja/built-in-nodes/ByteDance2TextToVideoNode.mdx +++ b/ja/built-in-nodes/ByteDance2TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2TextToVideoNode" icon: "circle" mode: wide --- + このノードは、ByteDanceのSeedance 2.0 APIを使用して、テキスト記述から動画を生成します。プロンプトを選択したモデルに送信し、動画が処理されるのを待って、最終結果を返します。 ## 入力 diff --git a/ja/built-in-nodes/ByteDanceCreateImageAsset.mdx b/ja/built-in-nodes/ByteDanceCreateImageAsset.mdx index 03a094698..629c3a2fe 100644 --- a/ja/built-in-nodes/ByteDanceCreateImageAsset.mdx +++ b/ja/built-in-nodes/ByteDanceCreateImageAsset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceCreateImageAsset" icon: "circle" mode: wide --- + このノードは、ByteDance の Seedance 2.0 サービス用に個人画像アセットを作成します。入力画像をアップロードし、指定されたアセットグループに登録します。グループ ID が指定されていない場合は、ブラウザで実在人物認証プロセスを開始し、新しいグループを作成してからアセットを追加します。 ## 入力 @@ -23,7 +24,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `group_id` | 新しく作成された画像アセットの一意の識別子です。 | STRING | +| `asset_id` | 新しく作成された画像アセットの一意の識別子です。 | STRING | | `group_id` | アセットグループの識別子です。指定された `group_id` または新しく作成された ID になります。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateImageAsset/ja.md) diff --git a/ja/built-in-nodes/ByteDanceCreateVideoAsset.mdx b/ja/built-in-nodes/ByteDanceCreateVideoAsset.mdx index dfaeccb50..308fb7da1 100644 --- a/ja/built-in-nodes/ByteDanceCreateVideoAsset.mdx +++ b/ja/built-in-nodes/ByteDanceCreateVideoAsset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceCreateVideoAsset" icon: "circle" mode: wide --- + このノードは、Seedance 2.0 用の個人用ビデオアセットを作成します。入力ビデオをアップロードし、指定されたアセットグループに登録します。グループ ID を指定しない場合は、ブラウザで実在確認プロセスを案内し、最初に新しいグループを作成します。 ## 入力 @@ -25,7 +26,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `group_id` | 新しく作成されたビデオアセットの一意の識別子。 | STRING | +| `asset_id` | 新しく作成されたビデオアセットの一意の識別子。 | STRING | | `group_id` | 新しいビデオを含むアセットグループの識別子。これは、指定された `group_id` または新しく作成されたものになります。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateVideoAsset/ja.md) diff --git a/ja/built-in-nodes/ByteDanceFirstLastFrameNode.mdx b/ja/built-in-nodes/ByteDanceFirstLastFrameNode.mdx index 0fc9c2d4e..9a5e449fe 100644 --- a/ja/built-in-nodes/ByteDanceFirstLastFrameNode.mdx +++ b/ja/built-in-nodes/ByteDanceFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceFirstLastFrameNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 このノードは、テキストプロンプトと最初と最後のフレーム画像を使用して動画を生成します。あなたの説明と2つのキーフレームを基に、それらの間を遷移する完全な動画シーケンスを作成します。このノードは、動画の解像度、アスペクト比、長さ、およびその他の生成パラメータを制御するためのさまざまなオプションを提供します。 diff --git a/ja/built-in-nodes/ByteDanceImageEditNode.mdx b/ja/built-in-nodes/ByteDanceImageEditNode.mdx index 694dfe0df..ccd168327 100644 --- a/ja/built-in-nodes/ByteDanceImageEditNode.mdx +++ b/ja/built-in-nodes/ByteDanceImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageEditNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご貢献ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageEditNode/en.md) ByteDance Image Editノードを使用すると、APIを通じてByteDanceのAIモデルを利用して画像を編集できます。入力画像と目的の変更内容を記述したテキストプロンプトを提供すると、ノードが指示に従って画像を処理します。このノードはAPI通信を自動的に処理し、編集済みの画像を返します。 diff --git a/ja/built-in-nodes/ByteDanceImageNode.mdx b/ja/built-in-nodes/ByteDanceImageNode.mdx index 04d5f2548..19e83ff08 100644 --- a/ja/built-in-nodes/ByteDanceImageNode.mdx +++ b/ja/built-in-nodes/ByteDanceImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ByteDanceImageReferenceNode.mdx b/ja/built-in-nodes/ByteDanceImageReferenceNode.mdx index 8a3cbedda..b7d74d4e5 100644 --- a/ja/built-in-nodes/ByteDanceImageReferenceNode.mdx +++ b/ja/built-in-nodes/ByteDanceImageReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageReferenceNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ByteDanceImageToVideoNode.mdx b/ja/built-in-nodes/ByteDanceImageToVideoNode.mdx index 296eb3bdb..c82cdc361 100644 --- a/ja/built-in-nodes/ByteDanceImageToVideoNode.mdx +++ b/ja/built-in-nodes/ByteDanceImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ByteDance Image to Video ノードは、入力画像とテキストプロンプトに基づいて、API を通じて ByteDance モデルを使用し動画を生成します。開始フレームとなる画像を受け取り、指定された説明に従った動画シーケンスを作成します。このノードは、動画の解像度、アスペクト比、長さ、およびその他の生成パラメータに関するさまざまなカスタマイズオプションを提供します。 diff --git a/ja/built-in-nodes/ByteDanceSeedAudio.mdx b/ja/built-in-nodes/ByteDanceSeedAudio.mdx new file mode 100644 index 000000000..0a4330b64 --- /dev/null +++ b/ja/built-in-nodes/ByteDanceSeedAudio.mdx @@ -0,0 +1,77 @@ +--- +title: "ByteDanceSeedAudio - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ByteDanceSeedAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ByteDanceSeedAudio" +icon: "circle" +mode: wide +--- + +あなたは ComfyUI ノードドキュメントを英語から日本語に翻訳する技術翻訳の専門家です。 + +## 翻訳ルール + +1. **翻訳してはいけない内容：** + - バッククォートで囲まれたパラメータ名：`image`、`seed`、`model` + - 大文字のデータ型：IMAGE、STRING、INT、FLOAT、MODEL、CONDITIONING など + - Range列の値：数値、"auto"、オプション名 + - コード、ファイルパス + +2. **翻訳する内容：** + - セクション見出し：## 概要、## 入力、## 出力 + - すべての説明文 + - パラメータの説明 + +3. **翻訳品質：** + - 丁寧語（です・ます体）を使用 + - 専門的でありながらわかりやすい表現 + - 技術的な正確性を保つ + - 標準的な日本語技術用語を使用 + +4. **フォーマット：** + - すべての Markdown フォーマットを保持 + - 表の構造を維持 + - 免責事項は追加しないでください（システムが文書末尾に自動追加します） + +以下の英語ドキュメントを日本語に翻訳してください（免責事項は含めないでください）： + +ByteDance Seed Audio 1.0 を使用して、単一のプロンプトから音声、音楽、効果音、マルチスピーカーの対話を生成します。プロンプト内で、声、感情、雰囲気、背景音楽、効果音を記述し、発話する台詞を含めてください。オプションで、内蔵のプリセット音声を選択したり、最大3つの参照クリップ（プロンプト内で @Audio1-3 とタグ付け）から声をクローンしたり、キャラクター画像から声を導出したりできます。1回の実行で最大2分間の音声を生成できます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `text_prompt` | 声、感情、話す速さ、雰囲気、背景音楽、効果音を記述し、発話する台詞を含めてください（対話の場合はキャラクター名をインラインで指定します）。「音声参照」モードでは、接続されたクリップを @Audio1、@Audio2、@Audio3 の順序で参照します。最大3000文字です。 | STRING | はい | 1～3000文字 | +| `reference_mode` | 声を条件付ける方法：「text only」（すべてをプロンプトで記述）、「audio reference」（最大3つの声をクローンし、@Audio1-3 とタグ付け）、「image reference」（1つのキャラクター画像から声を導出）、または「preset voice」（プロンプトを読み上げる内蔵の名前付き音声を選択）から選択します。 | COMBO | はい | `"text only"`
`"audio reference"`
`"image reference"`
`"preset voice"` | +| `reference_audio_1` | 音声クローン用の参照クリップ。プロンプト内で @Audio1 とタグ付けされます。最大30秒です。`reference_mode` が "audio reference" の場合のみ使用可能です。 | AUDIO | いいえ | 最大30秒 | +| `reference_audio_2` | プロンプト内で @Audio2 とタグ付けされる参照クリップ。最大30秒です。`reference_mode` が "audio reference" の場合のみ使用可能です。 | AUDIO | いいえ | 最大30秒 | +| `reference_audio_3` | プロンプト内で @Audio3 とタグ付けされる参照クリップ。最大30秒です。`reference_mode` が "audio reference" の場合のみ使用可能です。 | AUDIO | いいえ | 最大30秒 | +| `reference_image` | 単一のキャラクター画像。モデルはこれから声を導出します。参照音声と組み合わせることはできません。`reference_mode` が "image reference" の場合のみ使用可能です。 | IMAGE | いいえ | - | +| `preset_voice` | プロンプトを読み上げる内蔵の TTS 2.0 音声です。参照クリップは不要で、このモードでは @AudioN タグは使用されません。`reference_mode` が "preset voice" の場合のみ使用可能です。 | COMBO | いいえ | 複数のオプションが利用可能（説明を参照） | +| `sample_rate` | 出力サンプルレート（Hz）です。（デフォルト："24000"） | COMBO | はい | `"8000"`
`"16000"`
`"24000"`
`"32000"`
`"44100"`
`"48000"` | +| `speech_rate` | 話す速度です。0 = 通常、100 = 2.0倍、-50 = 0.5倍です。（デフォルト：0） | INT | はい | -50～100 | +| `loudness_rate` | 音量です。0 = 通常、100 = 2.0倍、-50 = 0.5倍です。（デフォルト：0） | INT | はい | -50～100 | +| `pitch_rate` | ピッチシフト（半音単位、-12～12）です。（デフォルト：0） | INT | はい | -12～12 | +| `seed` | シードはノードが再実行されるかどうかを制御します。結果はシードに関わらず非決定的です。（デフォルト：42） | INT | はい | 0～2147483647 | + +### パラメータの制約 + +- **参照モードの依存関係**: `reference_mode` パラメータによって、どの他の入力が必要かが決まります。 + - **"text only"**: 追加の入力は必要ありません。プロンプトに @AudioN タグを含めてはいけません。 + - **"audio reference"**: `reference_audio_1`、`reference_audio_2`、`reference_audio_3` のうち少なくとも1つが接続されている必要があります。参照クリップは順序通りに、かつ欠落なく接続する必要があります（例：_1、次に _2、次に _3）。各クリップの最大長は30秒です。プロンプトは、接続されたクリップを @Audio1、@Audio2、@Audio3 タグを使用して参照する必要があります。 + - **"image reference"**: `reference_image` が接続されている必要があります。プロンプトに @AudioN タグを含めてはいけません。 + - **"preset voice"**: `preset_voice` が選択されている必要があります。プロンプトに @AudioN タグを含めてはいけません（プロンプト全体が選択された音声で読み上げられます）。 + +- **音声参照の順序**: "audio reference" モードを使用する場合、参照音声入力は `reference_audio_1` から順に、欠落なく接続する必要があります。例えば、_1 と _2 を接続することはできますが、_2 なしで _1 と _3 を接続することはできません。 + +- **最大音声タグ数**: "audio reference" モードでは、プロンプトは最大3つの音声クリップ（@Audio1、@Audio2、@Audio3）を参照できます。最も大きい番号のタグは、接続されている参照音声入力の数を超えてはいけません。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `AUDIO` | ByteDance Seed Audio 1.0 によって生成された音声出力です。プロンプトで記述された通り、音声、音楽、効果音、またはマルチスピーカーの対話が含まれます。 | AUDIO | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedAudio/ja.md) + +--- +**Source fingerprint (SHA-256):** `cefd5fca496b02c35022d25be3d99d3911c1304b6e3a751751b58841d5895ef7` diff --git a/ja/built-in-nodes/ByteDanceSeedNode.mdx b/ja/built-in-nodes/ByteDanceSeedNode.mdx index cb8184a8c..46943026c 100644 --- a/ja/built-in-nodes/ByteDanceSeedNode.mdx +++ b/ja/built-in-nodes/ByteDanceSeedNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceSeedNode" icon: "circle" mode: wide --- + ## 概要 ByteDanceのSeed 2.0モデルを使用してテキスト応答を生成します。テキストプロンプトを入力し、オプションで画像や動画を含めることでマルチモーダルなコンテキストを提供できます。 diff --git a/ja/built-in-nodes/ByteDanceSeedreamNode.mdx b/ja/built-in-nodes/ByteDanceSeedreamNode.mdx index c9cf06005..33bab061b 100644 --- a/ja/built-in-nodes/ByteDanceSeedreamNode.mdx +++ b/ja/built-in-nodes/ByteDanceSeedreamNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceSeedreamNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedreamNode/en.md) ByteDance Seedream 4.5 & 5.0 ノードは、最大4K解像度での統合テキスト-to-画像生成と、高精度な単一文編集機能を提供します。テキストプロンプトから新しい画像を作成したり、テキスト指示を使用して既存の画像を編集したりできます。このノードは、単一画像の生成と、複数の関連画像の連続生成の両方をサポートしています。 diff --git a/ja/built-in-nodes/ByteDanceSeedreamNodeV2.mdx b/ja/built-in-nodes/ByteDanceSeedreamNodeV2.mdx index 99cf66567..747e56ade 100644 --- a/ja/built-in-nodes/ByteDanceSeedreamNodeV2.mdx +++ b/ja/built-in-nodes/ByteDanceSeedreamNodeV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceSeedreamNodeV2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ByteDanceTextToVideoNode.mdx b/ja/built-in-nodes/ByteDanceTextToVideoNode.mdx index 9501c8ea6..6cf17541e 100644 --- a/ja/built-in-nodes/ByteDanceTextToVideoNode.mdx +++ b/ja/built-in-nodes/ByteDanceTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceTextToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 このドキュメントは AI によって生成されました。誤りや改善のための提案があれば、ぜひコントリビュートしてください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceTextToVideoNode/en.md) diff --git a/ja/built-in-nodes/CFGGuider.mdx b/ja/built-in-nodes/CFGGuider.mdx index 6e00a8158..08157e222 100644 --- a/ja/built-in-nodes/CFGGuider.mdx +++ b/ja/built-in-nodes/CFGGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGGuider" icon: "circle" mode: wide --- + 以下は、提供された英語ドキュメントを日本語に翻訳したものです。 ## 概要 diff --git a/ja/built-in-nodes/CFGNorm.mdx b/ja/built-in-nodes/CFGNorm.mdx index 8de2dd9f1..969621939 100644 --- a/ja/built-in-nodes/CFGNorm.mdx +++ b/ja/built-in-nodes/CFGNorm.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGNorm" icon: "circle" mode: wide --- + CFGNormノードは、拡散モデルにおける分類器フリーガイダンス（CFG）プロセスに正規化手法を適用します。条件付き出力と無条件出力のノルムを比較することで、ノイズ除去予測のスケールを調整し、強度倍率を適用して効果を制御します。これにより、ガイダンススケーリングにおける極端な値を防ぎ、生成プロセスを安定化します。 ## 入力 @@ -18,7 +19,7 @@ CFGNormノードは、拡散モデルにおける分類器フリーガイダン | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `patched_model` | サンプリングプロセスにCFG正規化が適用された修正済みモデルを返します | MODEL | +| `修正済みモデル` | サンプリングプロセスにCFG正規化が適用された修正済みモデルを返します | MODEL | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGNorm/ja.md) diff --git a/ja/built-in-nodes/CFGOverride.mdx b/ja/built-in-nodes/CFGOverride.mdx index 0b5e007b6..6d1bb9ea3 100644 --- a/ja/built-in-nodes/CFGOverride.mdx +++ b/ja/built-in-nodes/CFGOverride.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CFGOverride" icon: "circle" mode: wide --- -# CFG オーバーライド CFG オーバーライドノードを使用すると、サンプリングプロセスの特定の範囲（全体のステップ数に対するパーセンテージで定義）に対して、固定のCFG（Classifier-Free Guidance）スケール値を設定できます。複数のCFGオーバーライドノードが接続されている場合、チェーン内でサンプラーに最も近いノードが、重複する範囲に対して優先されます。 diff --git a/ja/built-in-nodes/CFGZeroStar.mdx b/ja/built-in-nodes/CFGZeroStar.mdx index a49b16e83..e557df305 100644 --- a/ja/built-in-nodes/CFGZeroStar.mdx +++ b/ja/built-in-nodes/CFGZeroStar.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGZeroStar" icon: "circle" mode: wide --- + 以下が翻訳結果です。 CFGZeroStarノードは、拡散モデルに特殊なガイダンススケーリング技術を適用します。条件付き予測と無条件予測の差分に基づいて最適化されたスケール係数を計算することで、分類器フリーガイダンスプロセスを変更します。このアプローチにより、モデルの安定性を維持しながら、生成プロセスに対する高度な制御を実現する最終出力が調整されます。 @@ -19,7 +20,7 @@ CFGZeroStarノードは、拡散モデルに特殊なガイダンススケーリ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `patched_model` | CFGZeroStarガイダンススケーリングが適用された変更済みモデル | MODEL | +| `パッチ済みモデル` | CFGZeroStarガイダンススケーリングが適用された変更済みモデル | MODEL | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGZeroStar/ja.md) diff --git a/ja/built-in-nodes/CLIPAttentionMultiply.mdx b/ja/built-in-nodes/CLIPAttentionMultiply.mdx index 3fb22ff48..6ba18653f 100644 --- a/ja/built-in-nodes/CLIPAttentionMultiply.mdx +++ b/ja/built-in-nodes/CLIPAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPAttentionMultiply" icon: "circle" mode: wide --- + CLIPAttentionMultiply ノードを使用すると、自己注意層の異なるコンポーネントに乗算係数を適用することで、CLIP モデルの注意機構を調整できます。このノードは、CLIP モデルの注意機構におけるクエリ、キー、バリュー、および出力投影の重みとバイアスを変更することで機能します。この実験的なノードは、指定されたスケーリング係数を適用した、入力 CLIP モデルの修正コピーを作成します。 ## 入力 diff --git a/ja/built-in-nodes/CLIPMergeAdd.mdx b/ja/built-in-nodes/CLIPMergeAdd.mdx index 64cc5191b..10b515577 100644 --- a/ja/built-in-nodes/CLIPMergeAdd.mdx +++ b/ja/built-in-nodes/CLIPMergeAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeAdd" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 CLIPMergeAdd ノードは、2つのCLIPモデルを結合し、2番目のモデルから1番目のモデルにパッチを追加します。このノードは、1番目のCLIPモデルのコピーを作成し、位置IDやロジットスケールパラメータを除外して、2番目のモデルから重要なキーパッチを選択的に取り込みます。これにより、ベースモデルの構造を維持しながら、CLIPモデルのコンポーネントをマージできます。 diff --git a/ja/built-in-nodes/CLIPMergeSubtract.mdx b/ja/built-in-nodes/CLIPMergeSubtract.mdx index e3a65fb70..720622200 100644 --- a/ja/built-in-nodes/CLIPMergeSubtract.mdx +++ b/ja/built-in-nodes/CLIPMergeSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeSubtract" icon: "circle" mode: wide --- + CLIPMergeSubtract ノードは、一方のCLIPモデルの重みからもう一方のCLIPモデルの重みを減算することで、モデルのマージを実行します。最初のモデルを複製し、2番目のモデルのキーパッチを減算することで新しいCLIPモデルを作成し、調整可能な乗数で減算の強度を制御します。これにより、ベースモデルから特定の特性を除去することで、微調整されたモデルのブレンドが可能になります。 ## 入力 diff --git a/ja/built-in-nodes/CLIPTextEncodeControlnet.mdx b/ja/built-in-nodes/CLIPTextEncodeControlnet.mdx index ad5433e0c..5fc281cb5 100644 --- a/ja/built-in-nodes/CLIPTextEncodeControlnet.mdx +++ b/ja/built-in-nodes/CLIPTextEncodeControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeControlnet" icon: "circle" mode: wide --- + 以下が翻訳結果です。 CLIPTextEncodeControlnet ノードは、CLIP モデルを使用してテキスト入力を処理し、既存のコンディショニングデータと組み合わせることで、ControlNet アプリケーション向けの拡張コンディショニング出力を生成します。このノードは入力テキストをトークン化し、CLIP モデルを通じてエンコードし、得られた埋め込みをクロスアテンション ControlNet パラメータとして提供されたコンディショニングデータに追加します。 diff --git a/ja/built-in-nodes/CLIPTextEncodeHiDream.mdx b/ja/built-in-nodes/CLIPTextEncodeHiDream.mdx index 06a9b3bb6..f75c89fbd 100644 --- a/ja/built-in-nodes/CLIPTextEncodeHiDream.mdx +++ b/ja/built-in-nodes/CLIPTextEncodeHiDream.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeHiDream" icon: "circle" mode: wide --- + CLIPTextEncodeHiDream ノードは、異なる言語モデル（CLIP-L、CLIP-G、T5-XXL、LLaMA）を使用して4つの個別のテキスト入力を処理し、それらを1つのコンディショニング出力に結合します。各テキスト入力を対応するモデルでトークン化し、スケジュールされたエンコーディング手法を使用して一緒にエンコードすることで、複数の言語モデルを同時に活用した、より高度なテキストコンディショニングを実現します。 ## 入力 diff --git a/ja/built-in-nodes/CLIPTextEncodeKandinsky5.mdx b/ja/built-in-nodes/CLIPTextEncodeKandinsky5.mdx index a24cfc815..9cbb76c9f 100644 --- a/ja/built-in-nodes/CLIPTextEncodeKandinsky5.mdx +++ b/ja/built-in-nodes/CLIPTextEncodeKandinsky5.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeKandinsky5" icon: "circle" mode: wide --- + 以下が翻訳結果です。 CLIPTextEncodeKandinsky5 ノードは、Kandinsky 5 モデルで使用するテキストプロンプトを準備します。このノードは、2 つの個別のテキスト入力を受け取り、提供された CLIP モデルを使用してトークン化し、それらを 1 つの conditioning 出力に結合します。この出力は、画像生成プロセスをガイドするために使用されます。 diff --git a/ja/built-in-nodes/CLIPTextEncodeLumina2.mdx b/ja/built-in-nodes/CLIPTextEncodeLumina2.mdx index c44279710..9211d1a58 100644 --- a/ja/built-in-nodes/CLIPTextEncodeLumina2.mdx +++ b/ja/built-in-nodes/CLIPTextEncodeLumina2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeLumina2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx b/ja/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx index 368a424fb..025557e80 100644 --- a/ja/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx +++ b/ja/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodePixArtAlpha" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善のご提案がございましたら、ぜひご協力ください。[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPTextEncodePixArtAlpha/en.md) PixArt Alpha用にテキストをエンコードし、解像度の条件付けを設定します。このノードはテキスト入力を処理し、幅と高さの情報を追加して、PixArt Alphaモデル専用の条件付けデータを作成します。PixArt Sigmaモデルには適用されません。 diff --git a/ja/built-in-nodes/CLIPTextEncodeSD3.mdx b/ja/built-in-nodes/CLIPTextEncodeSD3.mdx index 77af06b40..c2eb3f5c7 100644 --- a/ja/built-in-nodes/CLIPTextEncodeSD3.mdx +++ b/ja/built-in-nodes/CLIPTextEncodeSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSD3" icon: "circle" mode: wide --- + CLIPTextEncodeSD3 ノードは、複数のテキストプロンプトを異なるCLIPモデルを使用してエンコードすることで、Stable Diffusion 3モデル向けのテキスト入力を処理します。このノードは3つの個別のテキスト入力（`clip_g`、`clip_l`、`t5xxl`）を処理し、空のテキストパディングを管理するためのオプションを提供します。ノードは異なるテキスト入力間で適切なトークン位置合わせを保証し、SD3生成パイプラインに適した条件付けデータを返します。 ## 入力 diff --git a/ja/built-in-nodes/Canny.mdx b/ja/built-in-nodes/Canny.mdx index 26fead014..b2f7776c7 100755 --- a/ja/built-in-nodes/Canny.mdx +++ b/ja/built-in-nodes/Canny.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Canny" icon: "circle" mode: wide --- + 写真からすべてのエッジラインを抽出します。まるで写真をペンでなぞるように、オブジェクトの輪郭や詳細の境界線を描き出します。 ## 動作原理 diff --git a/ja/built-in-nodes/CaseConverter.mdx b/ja/built-in-nodes/CaseConverter.mdx index 0079de76b..7cac696aa 100644 --- a/ja/built-in-nodes/CaseConverter.mdx +++ b/ja/built-in-nodes/CaseConverter.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CaseConverter" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CaseConverter/en.md) Case Converterノードは、テキスト文字列を異なる文字ケース形式に変換します。入力文字列を受け取り、選択されたモードに基づいて変換し、指定されたケース形式が適用された出力文字列を生成します。このノードは、テキストの大文字小文字を変更するための4つの異なるケース変換オプションをサポートしています。 diff --git a/ja/built-in-nodes/CenterCropImages.mdx b/ja/built-in-nodes/CenterCropImages.mdx index 51b06a392..a286ed414 100644 --- a/ja/built-in-nodes/CenterCropImages.mdx +++ b/ja/built-in-nodes/CenterCropImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CenterCropImages" icon: "circle" mode: wide --- + 以下は、ご指定の翻訳ルールに従って日本語に翻訳したドキュメントです。 --- @@ -23,7 +24,7 @@ Center Crop Images ノードは、画像の中心から指定された幅と高 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `image` | センタークロップ処理後の結果画像です。 | IMAGE | +| `画像` | センタークロップ処理後の結果画像です。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CenterCropImages/ja.md) diff --git a/ja/built-in-nodes/CheckpointLoader.mdx b/ja/built-in-nodes/CheckpointLoader.mdx index 4aa027c4c..5e308af03 100644 --- a/ja/built-in-nodes/CheckpointLoader.mdx +++ b/ja/built-in-nodes/CheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointLoader" icon: "circle" mode: wide --- + 以下は、指定された翻訳ルールに従って日本語に翻訳したドキュメントです。 --- diff --git a/ja/built-in-nodes/CheckpointLoaderSimple.mdx b/ja/built-in-nodes/CheckpointLoaderSimple.mdx index 63ba582a7..755c5edd8 100755 --- a/ja/built-in-nodes/CheckpointLoaderSimple.mdx +++ b/ja/built-in-nodes/CheckpointLoaderSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointLoaderSimple" icon: "circle" mode: wide --- + ## 概要 拡散モデルのチェックポイントファイルを読み込み、ノイズ除去用の潜在変数を処理するメインモデル、CLIPテキストエンコーダー、VAE画像エンコーダー/デコーダーの3つのコアコンポーネントに分解します。このノードは、`ComfyUI/models/checkpoints`フォルダ内のすべてのモデルファイルと、`extra_model_paths.yaml`ファイルで設定された追加パスを自動的に検出します。 diff --git a/ja/built-in-nodes/CheckpointSave.mdx b/ja/built-in-nodes/CheckpointSave.mdx index 3196c5974..79c8eeca0 100755 --- a/ja/built-in-nodes/CheckpointSave.mdx +++ b/ja/built-in-nodes/CheckpointSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointSave" icon: "circle" mode: wide --- + `Save Checkpoint`ノードは、完全なStable Diffusionモデル（UNet、CLIP、VAEコンポーネントを含む）を **.safetensors** 形式のチェックポイントファイルとして保存するために設計されています。 Save Checkpointは主にモデルマージワークフローで使用されます。`ModelMergeSimple`、`ModelMergeBlocks`などのノードを通じて新しいマージモデルを作成した後、このノードを使用して結果を再利用可能なチェックポイントファイルとして保存できます。 diff --git a/ja/built-in-nodes/ChromaRadianceOptions.mdx b/ja/built-in-nodes/ChromaRadianceOptions.mdx index fd41bd92b..2c68ca7eb 100644 --- a/ja/built-in-nodes/ChromaRadianceOptions.mdx +++ b/ja/built-in-nodes/ChromaRadianceOptions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ChromaRadianceOptions" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/ClaudeNode.mdx b/ja/built-in-nodes/ClaudeNode.mdx index f342b6fc8..2c581dfa3 100644 --- a/ja/built-in-nodes/ClaudeNode.mdx +++ b/ja/built-in-nodes/ClaudeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ClaudeNode" icon: "circle" mode: wide --- + ## 概要 Anthropic Claude モデルからテキスト応答を生成します。このノードはテキストプロンプトとオプションの画像をClaudeモデルに送信し、生成されたテキスト応答を返します。 diff --git a/ja/built-in-nodes/ClipLoader.mdx b/ja/built-in-nodes/ClipLoader.mdx index 83e0967a9..49385fa43 100755 --- a/ja/built-in-nodes/ClipLoader.mdx +++ b/ja/built-in-nodes/ClipLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPLoader" icon: "circle" mode: wide --- + 以下が翻訳結果です。 CLIPLoader ノードは、テキストエンコーダモデル（CLIP、T5、または類似のもの）をファイルから読み込み、テキストプロンプトを数値表現に変換する必要がある他のノードで使用できるようにします。このノードは多種多様なモデルアーキテクチャをサポートしており、それぞれに特定のエンコーダタイプが必要です。 diff --git a/ja/built-in-nodes/ClipMergeSimple.mdx b/ja/built-in-nodes/ClipMergeSimple.mdx index 074b2b64b..b7eec62d9 100755 --- a/ja/built-in-nodes/ClipMergeSimple.mdx +++ b/ja/built-in-nodes/ClipMergeSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeSimple" icon: "circle" mode: wide --- + 以下が翻訳です。 `CLIPMergeSimple` は、指定された比率に基づいて2つのCLIPテキストエンコーダモデルを結合する、高度なモデルマージノードです。 diff --git a/ja/built-in-nodes/ClipSave.mdx b/ja/built-in-nodes/ClipSave.mdx index 4dfe1e5c4..be0b6f6bb 100755 --- a/ja/built-in-nodes/ClipSave.mdx +++ b/ja/built-in-nodes/ClipSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPSave" icon: "circle" mode: wide --- + `CLIPSave`ノードは、CLIPテキストエンコーダーモデルをSafeTensors形式でディスクに保存します。高度なモデルマージワークフロー向けに設計されており、モデルの内部構造に基づいてCLIPモデルを構成要素（CLIP-L、CLIP-G、T5XXLなど）に自動的に分割し、各コンポーネントを個別のファイルとして保存します。 ## 入力 diff --git a/ja/built-in-nodes/ClipSetLastLayer.mdx b/ja/built-in-nodes/ClipSetLastLayer.mdx index 933cd8762..1f1cab3b7 100755 --- a/ja/built-in-nodes/ClipSetLastLayer.mdx +++ b/ja/built-in-nodes/ClipSetLastLayer.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPSetLastLayer" icon: "circle" mode: wide --- + `CLIP Set Last Layer` は、CLIPモデルの処理深度を制御するためのComfyUIのコアノードです。ユーザーはCLIPテキストエンコーダーの処理を停止する位置を正確に指定でき、テキスト理解の深さと生成画像のスタイルの両方に影響を与えます。 CLIPモデルを24層からなるインテリジェントな脳として想像してみてください。 diff --git a/ja/built-in-nodes/ClipTextEncode.mdx b/ja/built-in-nodes/ClipTextEncode.mdx index 265f9fb4f..347427995 100755 --- a/ja/built-in-nodes/ClipTextEncode.mdx +++ b/ja/built-in-nodes/ClipTextEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncode" icon: "circle" mode: wide --- + `CLIP Text Encode (CLIPTextEncode)` は翻訳者の役割を果たし、テキストによる説明をAIが理解できる形式に変換します。これにより、AIがあなたの入力を解釈し、希望する画像を生成できるようになります。 これは、異なる言語を話すアーティストとコミュニケーションをとるようなものだと考えてください。膨大な画像とテキストのペアで学習されたCLIPモデルが、あなたの説明をAIモデルが従うことのできる「指示」に変換することで、このギャップを埋めます。 diff --git a/ja/built-in-nodes/ClipTextEncodeFlux.mdx b/ja/built-in-nodes/ClipTextEncodeFlux.mdx index 79e2e7ae5..efbcad158 100644 --- a/ja/built-in-nodes/ClipTextEncodeFlux.mdx +++ b/ja/built-in-nodes/ClipTextEncodeFlux.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeFlux" icon: "circle" mode: wide --- + `CLIPTextEncodeFlux` は、Flux アーキテクチャ向けに設計された高度なテキストエンコードノードです。CLIP-L と T5XXL という異なるエンコーダーを通じて、2 つの個別のテキスト入力を処理し、それらをガイダンススケールと組み合わせて、画像生成のための統一された条件付け出力を生成します。 ## 入力 diff --git a/ja/built-in-nodes/ClipTextEncodeHunyuanDit.mdx b/ja/built-in-nodes/ClipTextEncodeHunyuanDit.mdx index bea866f7f..d993f73ea 100644 --- a/ja/built-in-nodes/ClipTextEncodeHunyuanDit.mdx +++ b/ja/built-in-nodes/ClipTextEncodeHunyuanDit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeHunyuanDiT" icon: "circle" mode: wide --- + `CLIPTextEncodeHunyuanDiT` ノードは、テキストによる説明を HunyuanDiT モデルが理解できる形式に変換します。これは、HunyuanDiT のデュアルテキストエンコーダーアーキテクチャ向けに設計された高度なコンディショニングノードであり、異なるトークナイザーを通じて2つの別々のテキスト入力を処理します。 ## 入力 diff --git a/ja/built-in-nodes/ClipTextEncodeSdxl.mdx b/ja/built-in-nodes/ClipTextEncodeSdxl.mdx index 8f34ba57b..ee57d846d 100755 --- a/ja/built-in-nodes/ClipTextEncodeSdxl.mdx +++ b/ja/built-in-nodes/ClipTextEncodeSdxl.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSDXL" icon: "circle" mode: wide --- + このノードは、SDXLアーキテクチャ用に特別にカスタマイズされたCLIPモデルを使用して、テキスト入力をエンコードするように設計されています。デュアルエンコーダーシステム（CLIP-LおよびCLIP-G）を使用してテキスト記述を処理し、より正確な画像生成を実現します。 ## 入力 diff --git a/ja/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx b/ja/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx index b266f499c..39669640a 100755 --- a/ja/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx +++ b/ja/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSDXLRefiner" icon: "circle" mode: wide --- + このノードは、SDXL Refinerモデル用に特別に設計されており、美的スコアと次元情報を組み込むことで、テキストプロンプトをコンディショニング情報に変換し、生成タスクの条件を強化して、最終的なリファイン効果を向上させます。これはプロのアートディレクターのように機能し、あなたの創造的な意図を伝えるだけでなく、作品に正確な美的基準と仕様要件を注入します。 ## SDXL Refinerについて diff --git a/ja/built-in-nodes/ClipVisionEncode.mdx b/ja/built-in-nodes/ClipVisionEncode.mdx index 5224ebd5b..cb79324ef 100755 --- a/ja/built-in-nodes/ClipVisionEncode.mdx +++ b/ja/built-in-nodes/ClipVisionEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPVisionEncode" icon: "circle" mode: wide --- + `CLIP Vision Encode` ノードは、ComfyUI における画像エンコードノードであり、CLIP Vision モデルを通じて入力画像を視覚特徴ベクトルに変換します。このノードは、画像とテキストの理解を結びつける重要なブリッジであり、様々なAI画像生成・処理ワークフローで広く使用されています。 **ノード機能** diff --git a/ja/built-in-nodes/ClipVisionLoader.mdx b/ja/built-in-nodes/ClipVisionLoader.mdx index 96dca1b81..ed6d4c7fa 100755 --- a/ja/built-in-nodes/ClipVisionLoader.mdx +++ b/ja/built-in-nodes/ClipVisionLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPVisionLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/clip_vision` フォルダ内に配置されたモデルと、`extra_model_paths.yaml` ファイルで設定された追加のモデルパスを自動的に検出します。ComfyUI 起動後にモデルを追加した場合は、**ComfyUI インターフェースを更新**して、最新のモデルファイルが一覧表示されるようにしてください。 ## 入力 diff --git a/ja/built-in-nodes/ColorToRGBInt.mdx b/ja/built-in-nodes/ColorToRGBInt.mdx index afa31622c..dc513c818 100644 --- a/ja/built-in-nodes/ColorToRGBInt.mdx +++ b/ja/built-in-nodes/ColorToRGBInt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ColorToRGBInt" icon: "circle" mode: wide --- + ColorToRGBIntノードは、16進数形式で指定された色を単一の整数値に変換します。`#FF5733`のようなカラー文字列を受け取り、赤、緑、青の各成分を組み合わせて対応するRGB整数を計算します。 ## 入力 @@ -19,7 +20,7 @@ ColorToRGBIntノードは、16進数形式で指定された色を単一の整 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `rgb_int` | 計算されたRGB整数値。次の式から導出されます：`(赤 * 65536) + (緑 * 256) + 青` | INT | +| `rgb整数値` | 計算されたRGB整数値。次の式から導出されます：`(赤 * 65536) + (緑 * 256) + 青` | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ColorToRGBInt/ja.md) diff --git a/ja/built-in-nodes/ColorTransfer.mdx b/ja/built-in-nodes/ColorTransfer.mdx index b0393149f..ad0b4f87c 100644 --- a/ja/built-in-nodes/ColorTransfer.mdx +++ b/ja/built-in-nodes/ColorTransfer.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ColorTransfer" icon: "circle" mode: wide --- + ## 概要 ColorTransferノードは、ターゲット画像のカラーパレットを調整し、参照画像の色に合わせます。輝度、コントラスト、色相分布などの色特性を、参照画像からターゲット画像へ分析・転送するために、異なる数学的アルゴリズムを使用します。これは、複数の画像間で視覚的な一貫性を生み出したり、特定のカラーグレードを適用する際に有用です。 diff --git a/ja/built-in-nodes/CombineHooks.mdx b/ja/built-in-nodes/CombineHooks.mdx index abe458e53..341879150 100644 --- a/ja/built-in-nodes/CombineHooks.mdx +++ b/ja/built-in-nodes/CombineHooks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooks" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- diff --git a/ja/built-in-nodes/CombineHooksEight.mdx b/ja/built-in-nodes/CombineHooksEight.mdx index 65845d366..7167beeef 100644 --- a/ja/built-in-nodes/CombineHooksEight.mdx +++ b/ja/built-in-nodes/CombineHooksEight.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooksEight" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Combine Hooks [8] ノードは、最大8つの異なるフックグループを1つの結合されたフックグループに統合します。複数のフック入力を受け取り、ComfyUIのフック結合機能を使用してそれらを組み合わせます。これにより、複数のフック設定を統合し、高度なワークフローで処理を効率化できます。 diff --git a/ja/built-in-nodes/CombineHooksFour.mdx b/ja/built-in-nodes/CombineHooksFour.mdx index abee75415..2677c045f 100644 --- a/ja/built-in-nodes/CombineHooksFour.mdx +++ b/ja/built-in-nodes/CombineHooksFour.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooksFour" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CombineHooksFour/en.md) **Combine Hooks [4]** ノードは、最大4つの個別のフックグループを1つの結合されたフックグループに統合します。4つの利用可能なフック入力の任意の組み合わせを受け取り、ComfyUIのフック結合システムを使用してそれらを結合します。これにより、高度なワークフローにおいて、複数のフック設定を統合して処理を効率化できます。 diff --git a/ja/built-in-nodes/ComboOptionTestNode.mdx b/ja/built-in-nodes/ComboOptionTestNode.mdx index 5fc383bc7..dd65c9ad4 100644 --- a/ja/built-in-nodes/ComboOptionTestNode.mdx +++ b/ja/built-in-nodes/ComboOptionTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComboOptionTestNode" icon: "circle" mode: wide --- + 以下は、指定された翻訳ルールに従って日本語に翻訳したドキュメントです。 --- diff --git a/ja/built-in-nodes/ComfyAndNode.mdx b/ja/built-in-nodes/ComfyAndNode.mdx index 9b4ac1cd2..fae9a8e6a 100644 --- a/ja/built-in-nodes/ComfyAndNode.mdx +++ b/ja/built-in-nodes/ComfyAndNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyAndNode" icon: "circle" mode: wide --- + ## 概要 Andノードは、一連の入力値に対して論理AND演算を実行します。提供されたすべての値がPythonの真偽値ルールに従って真とみなされる場合にのみ、`true`を返します。このノードは、複数の条件がすべて満たされていることを確認してから処理を進める場合に便利です。 diff --git a/ja/built-in-nodes/ComfyMathExpression.mdx b/ja/built-in-nodes/ComfyMathExpression.mdx index 1813ead26..f87ed79b8 100644 --- a/ja/built-in-nodes/ComfyMathExpression.mdx +++ b/ja/built-in-nodes/ComfyMathExpression.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyMathExpression" icon: "circle" mode: wide --- + ComfyMathExpression ノードは、一連の入力値を使用して数式を評価します。`a`、`b`、`c` のような変数名を使用して式を記述すると、ノードが結果を計算します。計算に必要な数だけ入力値を動的に追加することができます。 ## 入力 diff --git a/ja/built-in-nodes/ComfyNotNode.mdx b/ja/built-in-nodes/ComfyNotNode.mdx index 8ca5e6459..65ce751a1 100644 --- a/ja/built-in-nodes/ComfyNotNode.mdx +++ b/ja/built-in-nodes/ComfyNotNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyNotNode" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 ## 概要 diff --git a/ja/built-in-nodes/ComfyNumberConvert.mdx b/ja/built-in-nodes/ComfyNumberConvert.mdx index a9bd504f2..3d63f73d1 100644 --- a/ja/built-in-nodes/ComfyNumberConvert.mdx +++ b/ja/built-in-nodes/ComfyNumberConvert.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyNumberConvert" icon: "circle" mode: wide --- + 以下は、ご依頼いただいたComfyUIノードドキュメントの日本語翻訳です。 --- diff --git a/ja/built-in-nodes/ComfyOrNode.mdx b/ja/built-in-nodes/ComfyOrNode.mdx index bb983d3cf..ef3f66274 100644 --- a/ja/built-in-nodes/ComfyOrNode.mdx +++ b/ja/built-in-nodes/ComfyOrNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ComfyOrNode" icon: "circle" mode: wide --- -# ComfyOrNode ComfyOrNodeは、一連の入力値に対して論理OR演算を実行します。提供された値のいずれかが、Pythonの標準的な真偽値ルールに従って真とみなされる場合、`true`を返します。 diff --git a/ja/built-in-nodes/ComfySoftSwitchNode.mdx b/ja/built-in-nodes/ComfySoftSwitchNode.mdx index 9f6e3bc05..3d306e2ce 100644 --- a/ja/built-in-nodes/ComfySoftSwitchNode.mdx +++ b/ja/built-in-nodes/ComfySoftSwitchNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfySoftSwitchNode" icon: "circle" mode: wide --- + ## 概要 Soft Switch ノードは、ブール条件に基づいて2つの入力値のいずれかを選択します。`switch` が true の場合は `on_true` 入力の値を出力し、`switch` が false の場合は `on_false` 入力の値を出力します。このノードは遅延評価方式で設計されており、スイッチの状態に応じて必要な入力のみを評価します。 diff --git a/ja/built-in-nodes/ComfySwitchNode.mdx b/ja/built-in-nodes/ComfySwitchNode.mdx index 2cb5b392b..cbb95fdfa 100644 --- a/ja/built-in-nodes/ComfySwitchNode.mdx +++ b/ja/built-in-nodes/ComfySwitchNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfySwitchNode" icon: "circle" mode: wide --- + Switchノードは、ブール条件に基づいて2つの入力のうち1つを選択します。`switch`が有効（true）の場合は`on_true`入力を出力し、`switch`が無効（false）の場合は`on_false`入力を出力します。これにより、ワークフロー内で条件付きロジックを作成し、異なるデータパスを選択することができます。 ## 入力 @@ -21,7 +22,7 @@ Switchノードは、ブール条件に基づいて2つの入力のうち1つを | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `output` | 選択されたデータです。`スイッチ`がtrueの場合は`真の場合`入力の値、`スイッチ`がfalseの場合は`偽の場合`入力の値になります。 | MATCH_TYPE | +| `出力` | 選択されたデータです。`スイッチ`がtrueの場合は`真の場合`入力の値、`スイッチ`がfalseの場合は`偽の場合`入力の値になります。 | MATCH_TYPE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfySwitchNode/ja.md) diff --git a/ja/built-in-nodes/ConditioningAverage.mdx b/ja/built-in-nodes/ConditioningAverage.mdx index 659b412a3..695ad741e 100644 --- a/ja/built-in-nodes/ConditioningAverage.mdx +++ b/ja/built-in-nodes/ConditioningAverage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningAverage" icon: "circle" mode: wide --- + `ConditioningAverage`ノードは、指定された重みに従って2つの異なる条件付け（テキストプロンプトなど）をブレンドし、その中間に位置する新しい条件付けベクトルを生成するために使用されます。`conditioning_to_strength`パラメータを調整することで、最終結果に対する各条件付けの影響を柔軟に制御できます。これは、プロンプトの補間やスタイルの融合など、高度なユースケースに特に適しています。 下図に示すように、`conditioning_to`の強度を調整することで、2つの条件付けの中間の結果を出力できます。 diff --git a/ja/built-in-nodes/ConditioningCombine.mdx b/ja/built-in-nodes/ConditioningCombine.mdx index 5e181a742..b59761c26 100644 --- a/ja/built-in-nodes/ConditioningCombine.mdx +++ b/ja/built-in-nodes/ConditioningCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningCombine" icon: "circle" mode: wide --- + このノードは、2つの条件付け入力を1つの出力に結合し、それらの情報を効果的にマージします。2つの条件は、リストの連結を使用して結合されます。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningConcat.mdx b/ja/built-in-nodes/ConditioningConcat.mdx index ea891b9a2..950176347 100644 --- a/ja/built-in-nodes/ConditioningConcat.mdx +++ b/ja/built-in-nodes/ConditioningConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningConcat" icon: "circle" mode: wide --- + ConditioningConcat ノードは、コンディショニングベクトルを連結するために設計されており、具体的には `conditioning_from` ベクトルを `conditioning_to` ベクトルにマージします。この操作は、2つのソースからのコンディショニング情報を1つの統合された表現に結合する必要があるシナリオにおいて基本となる処理です。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningMultiply.mdx b/ja/built-in-nodes/ConditioningMultiply.mdx new file mode 100644 index 000000000..12c6ff876 --- /dev/null +++ b/ja/built-in-nodes/ConditioningMultiply.mdx @@ -0,0 +1,27 @@ +--- +title: "ConditioningMultiply - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConditioningMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConditioningMultiply" +icon: "circle" +mode: wide +--- + +このノードは、条件付けの値を指定された係数で乗算し、生成プロセスにおける条件付けの影響を拡大・縮小できるようにします。メインの条件付けテンソルとプールされた出力値の両方に乗数を適用することで機能します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `conditioning` | 拡大・縮小する条件付けデータ | CONDITIONING | はい | - | +| `multiplier` | 条件付けの値を乗算する係数（デフォルト: 1.0） | FLOAT | はい | -100.0 ～ 100.0（ステップ: 0.01） | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `CONDITIONING` | 値が乗算された拡大・縮小済み条件付けデータ | CONDITIONING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningMultiply/ja.md) + +--- +**Source fingerprint (SHA-256):** `8d241e3d5d91e513c24ade5b4bece4bf879fe093a4be6d53dab11a5a0bf55616` diff --git a/ja/built-in-nodes/ConditioningSetArea.mdx b/ja/built-in-nodes/ConditioningSetArea.mdx index 228cce7e3..29b978b70 100644 --- a/ja/built-in-nodes/ConditioningSetArea.mdx +++ b/ja/built-in-nodes/ConditioningSetArea.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetArea" icon: "circle" mode: wide --- + このノードは、コンディショニングコンテキスト内に特定の領域を設定することで、コンディショニング情報を変更するように設計されています。これにより、コンディショニング要素の正確な空間的操作が可能になり、指定された寸法と強度に基づいて、対象を絞った調整と拡張を実現します。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningSetAreaPercentage.mdx b/ja/built-in-nodes/ConditioningSetAreaPercentage.mdx index 5d8290bad..bdd7275e6 100644 --- a/ja/built-in-nodes/ConditioningSetAreaPercentage.mdx +++ b/ja/built-in-nodes/ConditioningSetAreaPercentage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaPercentage" icon: "circle" mode: wide --- + ConditioningSetAreaPercentageノードは、条件付け要素の影響範囲をパーセンテージ値に基づいて調整することに特化しています。このノードでは、領域の寸法と位置を画像全体のサイズに対するパーセンテージとして指定できるほか、条件付け効果の強度を調整するための強度パラメータも提供します。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx b/ja/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx index 1aa76a29e..2d65ca516 100644 --- a/ja/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx +++ b/ja/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaPercentageVideo" icon: "circle" mode: wide --- + ConditioningSetAreaPercentageVideo ノードは、ビデオ生成用の特定の領域と時間範囲を定義することで、条件付けデータを変更します。このノードを使用すると、全体の寸法に対するパーセンテージ値を使用して、条件付けが適用される領域の位置、サイズ、および持続時間を設定できます。これは、ビデオシーケンスの特定の部分に生成を集中させる場合に便利です。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningSetAreaStrength.mdx b/ja/built-in-nodes/ConditioningSetAreaStrength.mdx index 2231abe5f..ffbab65e4 100644 --- a/ja/built-in-nodes/ConditioningSetAreaStrength.mdx +++ b/ja/built-in-nodes/ConditioningSetAreaStrength.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaStrength" icon: "circle" mode: wide --- + このノードは、指定された条件付けセットの強度属性を変更するために設計されており、生成プロセスにおける条件付けの影響や強度を調整することができます。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningSetDefaultAndCombine.mdx b/ja/built-in-nodes/ConditioningSetDefaultAndCombine.mdx index a32107e5a..16a24d303 100644 --- a/ja/built-in-nodes/ConditioningSetDefaultAndCombine.mdx +++ b/ja/built-in-nodes/ConditioningSetDefaultAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetDefaultAndCombine" icon: "circle" mode: wide --- + このノードは、フックベースのシステムを使用して、プライマリ条件付け入力とデフォルト条件付け入力を結合します。2つの条件付けソースを単一の出力にマージし、プライマリ条件付けが不完全な場合に、デフォルト条件付けがフォールバックまたはベースとして機能することを可能にします。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningSetMask.mdx b/ja/built-in-nodes/ConditioningSetMask.mdx index 113cf95d2..747bda83c 100644 --- a/ja/built-in-nodes/ConditioningSetMask.mdx +++ b/ja/built-in-nodes/ConditioningSetMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetMask" icon: "circle" mode: wide --- + このノードは、指定された強度でマスクを特定の領域に適用することにより、生成モデルの条件付け（conditioning）を変更するように設計されています。条件付け内で対象を絞った調整を可能にし、生成プロセスをより精密に制御できるようにします。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningSetProperties.mdx b/ja/built-in-nodes/ConditioningSetProperties.mdx index 519f9e2de..14fce8b8d 100644 --- a/ja/built-in-nodes/ConditioningSetProperties.mdx +++ b/ja/built-in-nodes/ConditioningSetProperties.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetProperties" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ConditioningSetProperties ノードは、強度、領域設定の調整、およびオプションのマスク、フック、タイムステップ範囲の適用により、条件付けデータのプロパティを変更します。このノードを使用すると、画像生成中に条件付けデータの適用に影響を与える特定のパラメータを設定することで、条件付けが生成プロセスに与える影響を制御できます。 diff --git a/ja/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx b/ja/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx index 98eee6fb7..3d1dff0ca 100644 --- a/ja/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx +++ b/ja/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetPropertiesAndCombine" icon: "circle" mode: wide --- + ConditioningSetPropertiesAndCombine ノードは、既存の条件付け入力に新しい条件付け入力のプロパティを適用することで、条件付けデータを変更します。このノードは、新しい条件付けの強度を制御し、条件付け領域の適用方法を指定しながら、2つの条件付けセットを結合します。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningSetTimestepRange.mdx b/ja/built-in-nodes/ConditioningSetTimestepRange.mdx index b2aabb17d..6f11fbdab 100644 --- a/ja/built-in-nodes/ConditioningSetTimestepRange.mdx +++ b/ja/built-in-nodes/ConditioningSetTimestepRange.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetTimestepRange" icon: "circle" mode: wide --- + このノードは、特定のタイムステップ範囲を設定することで、コンディショニングの時間的側面を調整するために設計されています。これにより、コンディショニングプロセスの開始点と終了点を正確に制御でき、よりターゲットを絞った効率的な生成が可能になります。 ## 入力 diff --git a/ja/built-in-nodes/ConditioningStableAudio.mdx b/ja/built-in-nodes/ConditioningStableAudio.mdx index bb1782178..01f957c2b 100644 --- a/ja/built-in-nodes/ConditioningStableAudio.mdx +++ b/ja/built-in-nodes/ConditioningStableAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningStableAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ConditioningStableAudio ノードは、音声生成用のポジティブおよびネガティブの両方の条件付け入力にタイミング情報を追加します。このノードは、音声コンテンツをいつ、どのくらいの長さで生成するかを制御する開始時間と総再生時間のパラメーターを設定します。既存の条件付けデータに、音声固有のタイミングメタデータを追加して変更します。 @@ -22,7 +23,7 @@ ConditioningStableAudio ノードは、音声生成用のポジティブおよ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 音声タイミング情報が適用された、変更後のポジティブ条件付け | CONDITIONING | +| `ポジティブ` | 音声タイミング情報が適用された、変更後のポジティブ条件付け | CONDITIONING | | `ネガティブ` | 音声タイミング情報が適用された、変更後のネガティブ条件付け | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningStableAudio/ja.md) diff --git a/ja/built-in-nodes/ConditioningTimestepsRange.mdx b/ja/built-in-nodes/ConditioningTimestepsRange.mdx index 1f8962534..52283253e 100644 --- a/ja/built-in-nodes/ConditioningTimestepsRange.mdx +++ b/ja/built-in-nodes/ConditioningTimestepsRange.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningTimestepsRange" icon: "circle" mode: wide --- + ConditioningTimestepsRange ノードは、生成プロセス中にコンディショニング効果を適用するタイミングを制御するための、3つの異なるタイムステップ範囲を作成します。開始パーセント値と終了パーセント値を受け取り、タイムステップ全体の範囲（0.0 から 1.0）を次の3つのセグメントに分割します：指定されたパーセンテージ間のメイン範囲、開始パーセンテージより前の範囲、および終了パーセンテージより後の範囲です。 ## 入力 @@ -19,8 +20,8 @@ ConditioningTimestepsRange ノードは、生成プロセス中にコンディ | 出力名 | 説明 | データ型 | | --- | --- | --- | | `範囲前` | start_percent と end_percent によって定義されるメインのタイムステップ範囲 | TIMESTEPS_RANGE | -| `範囲後` | 0.0 から start_percent までのタイムステップ範囲 | TIMESTEPS_RANGE | -| `AFTER_RANGE` | end_percent から 1.0 までのタイムステップ範囲 | TIMESTEPS_RANGE | +| `範囲前` | 0.0 から start_percent までのタイムステップ範囲 | TIMESTEPS_RANGE | +| `範囲後` | end_percent から 1.0 までのタイムステップ範囲 | TIMESTEPS_RANGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningTimestepsRange/ja.md) diff --git a/ja/built-in-nodes/ConditioningZeroOut.mdx b/ja/built-in-nodes/ConditioningZeroOut.mdx index 7bd088fb5..61a7c2ec6 100644 --- a/ja/built-in-nodes/ConditioningZeroOut.mdx +++ b/ja/built-in-nodes/ConditioningZeroOut.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningZeroOut" icon: "circle" mode: wide --- + このノードは、条件付けデータ構造内の特定の要素をゼロに設定し、後続の処理ステップにおけるそれらの影響を実質的に無効化します。条件付けの内部表現を直接操作する必要がある高度な条件付け操作向けに設計されています。 ## 入力 diff --git a/ja/built-in-nodes/ContextWindowsManual.mdx b/ja/built-in-nodes/ContextWindowsManual.mdx index 0e2378865..99ea5fca6 100644 --- a/ja/built-in-nodes/ContextWindowsManual.mdx +++ b/ja/built-in-nodes/ContextWindowsManual.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ContextWindowsManual" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ControlNetApply.mdx b/ja/built-in-nodes/ControlNetApply.mdx index b39111feb..9b4daca43 100644 --- a/ja/built-in-nodes/ControlNetApply.mdx +++ b/ja/built-in-nodes/ControlNetApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApply" icon: "circle" mode: wide --- + ControlNetを使用するには、入力画像の前処理が必要です。ComfyUIの初期ノードにはプリプロセッサーやControlNetモデルが付属していないため、まずControlNetプリプロセッサーをインストールし（[こちらからプリプロセッサーをダウンロード](https://github.com/Fannovel16/comfy_controlnet_preprocessors)）、対応するControlNetモデルもインストールしてください。 ## 入力 diff --git a/ja/built-in-nodes/ControlNetApplyAdvanced.mdx b/ja/built-in-nodes/ControlNetApplyAdvanced.mdx index f4dc6ec39..f9511fbe2 100644 --- a/ja/built-in-nodes/ControlNetApplyAdvanced.mdx +++ b/ja/built-in-nodes/ControlNetApplyAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApplyAdvanced" icon: "circle" mode: wide --- + このノードは、画像とコントロールネットモデルに基づいて、条件付けデータに高度なコントロールネット変換を適用します。これにより、生成コンテンツに対するコントロールネットの影響を微調整し、条件付けに対してより精密で多様な変更を加えることが可能になります。 ## 入力 @@ -23,7 +24,7 @@ mode: wide | パラメータ | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | コントロールネット変換の適用後、入力パラメータに基づいて行われた強化を反映した、変更後のポジティブ条件付けデータです。 | `CONDITIONING` | +| `ポジティブ` | コントロールネット変換の適用後、入力パラメータに基づいて行われた強化を反映した、変更後のポジティブ条件付けデータです。 | `CONDITIONING` | | `ネガティブ` | コントロールネット変換の適用後、入力パラメータに基づく特定の特徴の抑制または除去を反映した、変更後のネガティブ条件付けデータです。 | `CONDITIONING` | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetApplyAdvanced/ja.md) diff --git a/ja/built-in-nodes/ControlNetApplySD3.mdx b/ja/built-in-nodes/ControlNetApplySD3.mdx index fa0cb4acc..41505adb2 100644 --- a/ja/built-in-nodes/ControlNetApplySD3.mdx +++ b/ja/built-in-nodes/ControlNetApplySD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApplySD3" icon: "circle" mode: wide --- + このノードは、ControlNetガイダンスをStable Diffusion 3の条件付けに適用します。ポジティブおよびネガティブの条件付け入力と、ControlNetモデルおよび画像を受け取り、調整可能な強度とタイミングパラメータで制御ガイダンスを適用し、生成プロセスに影響を与えます。 **注意：** このノードは非推奨としてマークされており、将来のバージョンで削除される可能性があります。 @@ -26,7 +27,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | ControlNetガイダンスが適用された変更後のポジティブ条件付け | CONDITIONING | +| `ポジティブ` | ControlNetガイダンスが適用された変更後のポジティブ条件付け | CONDITIONING | | `ネガティブ` | ControlNetガイダンスが適用された変更後のネガティブ条件付け | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetApplySD3/ja.md) diff --git a/ja/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx b/ja/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx index 3b895d843..66729457f 100644 --- a/ja/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx +++ b/ja/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetInpaintingAliMamaApply" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ControlNetInpaintingAliMamaApply ノードは、ポジティブおよびネガティブな条件付けとコントロール画像およびマスクを組み合わせることで、インペインティングタスク用の ControlNet 条件付けを適用します。入力画像とマスクを処理して、生成プロセスをガイドする修正済み条件付けを作成し、画像のどの領域をインペイントするかを正確に制御できます。このノードは、生成プロセスのさまざまな段階で ControlNet の影響を微調整するための強度調整機能とタイミング制御機能をサポートしています。 @@ -29,7 +30,7 @@ ControlNetInpaintingAliMamaApply ノードは、ポジティブおよびネガ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | インペインティング用に ControlNet が適用された修正済みポジティブ条件付け | CONDITIONING | +| `ポジティブ` | インペインティング用に ControlNet が適用された修正済みポジティブ条件付け | CONDITIONING | | `ネガティブ` | インペインティング用に ControlNet が適用された修正済みネガティブ条件付け | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetInpaintingAliMamaApply/ja.md) diff --git a/ja/built-in-nodes/ControlNetLoader.mdx b/ja/built-in-nodes/ControlNetLoader.mdx index b2ab8ec2d..f977cf475 100644 --- a/ja/built-in-nodes/ControlNetLoader.mdx +++ b/ja/built-in-nodes/ControlNetLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/controlnet` フォルダ内にあるモデルを検出し、さらに `extra_model_paths.yaml` ファイルで設定された追加パスからもモデルを読み込みます。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、対応するフォルダからモデルファイルを読み込ませる必要があります。 ControlNetLoader ノードは、指定されたパスから ControlNet モデルを読み込むように設計されています。このノードは、生成コンテンツに制御メカニズムを適用したり、制御信号に基づいて既存のコンテンツを変更したりするために不可欠な、ControlNet モデルの初期化において重要な役割を果たします。 diff --git a/ja/built-in-nodes/ConvertArrayToString.mdx b/ja/built-in-nodes/ConvertArrayToString.mdx new file mode 100644 index 000000000..5e0b7c515 --- /dev/null +++ b/ja/built-in-nodes/ConvertArrayToString.mdx @@ -0,0 +1,27 @@ +--- +title: "ConvertArrayToString - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConvertArrayToString node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConvertArrayToString" +icon: "circle" +mode: wide +--- + +Convert Array to String ノードは、アイテムの配列（リスト）を受け取り、それを整形されたJSON文字列に変換します。これは、配列データを表示、ログ記録、または文字列入力を想定した他のシステムに渡すためにシリアライズする必要がある場合に便利です。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `配列` | JSON文字列に変換する配列 | ARRAY | はい | - | +| `インデント` | インデントレベルごとのスペース数。0を指定するとコンパクトな1行の文字列になります（デフォルト：2） | INT | いいえ | 0～8 | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `STRING` | JSON形式の文字列に変換された配列 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertArrayToString/ja.md) + +--- +**Source fingerprint (SHA-256):** `ac8397fed0336f546403ee3e1f17d7e8f5973190b102e74943f098bf6905f726` diff --git a/ja/built-in-nodes/ConvertDictionaryToString.mdx b/ja/built-in-nodes/ConvertDictionaryToString.mdx new file mode 100644 index 000000000..03cc1357f --- /dev/null +++ b/ja/built-in-nodes/ConvertDictionaryToString.mdx @@ -0,0 +1,27 @@ +--- +title: "ConvertDictionaryToString - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConvertDictionaryToString node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConvertDictionaryToString" +icon: "circle" +mode: wide +--- + +このノードは、辞書（キーと値のペアの集合）をテキスト文字列、通常はJSON形式に変換します。インデントのレベルを調整することで、出力を読みやすくしたり、コンパクトにしたりできます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `辞書` | 文字列に変換する辞書 | DICT | はい | - | +| `インデント` | インデントレベルあたりのスペース数。0を指定するとコンパクトな1行の文字列になります（デフォルト：2） | INT | いいえ | 0～8 | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `STRING` | JSON形式の文字列に変換された辞書 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertDictionaryToString/ja.md) + +--- +**Source fingerprint (SHA-256):** `ae4e9889d5347acfc69166bac66f2ba63f5cd37dafab25a9e0aff6bfe7381219` diff --git a/ja/built-in-nodes/ConvertStringToComboNode.mdx b/ja/built-in-nodes/ConvertStringToComboNode.mdx index 1199ac3bf..87a3db5ed 100644 --- a/ja/built-in-nodes/ConvertStringToComboNode.mdx +++ b/ja/built-in-nodes/ConvertStringToComboNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConvertStringToComboNode" icon: "circle" mode: wide --- + このドキュメントは AI が生成したものです。誤りや改善の提案があれば、ぜひご協力ください！[GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertStringToComboNode/en.md) Convert String to Combo ノードは、テキスト文字列を入力として受け取り、それを Combo データ型に変換します。これにより、テキスト値を、Combo 入力が必要な他のノードの選択肢として使用できるようになります。このノードは、文字列の値を変更せずにそのまま渡しますが、データ型を変更します。 diff --git a/ja/built-in-nodes/CosmosImageToVideoLatent.mdx b/ja/built-in-nodes/CosmosImageToVideoLatent.mdx index f873391ba..e67ecbca0 100644 --- a/ja/built-in-nodes/CosmosImageToVideoLatent.mdx +++ b/ja/built-in-nodes/CosmosImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CosmosImageToVideoLatent" icon: "circle" mode: wide --- + CosmosImageToVideoLatent ノードは、入力画像からビデオの潜在表現を生成します。空のビデオ潜在表現を作成し、オプションで開始画像や終了画像をビデオシーケンスの先頭フレームや末尾フレームにエンコードします。画像が提供された場合、生成中に潜在表現のどの部分を保持すべきかを示す、対応するノイズマスクも作成します。 ## 入力 diff --git a/ja/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx b/ja/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx index cd14bfd72..6845aaee4 100644 --- a/ja/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx +++ b/ja/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CosmosPredict2ImageToVideoLatent" icon: "circle" mode: wide --- + CosmosPredict2ImageToVideoLatent ノードは、動画生成のために画像からビデオ潜在表現を作成します。空白のビデオ潜在表現を生成したり、開始画像と終了画像を組み込んで、指定された寸法と長さの動画シーケンスを作成することができます。このノードは、画像を動画処理に適した潜在空間フォーマットにエンコードします。 ## 入力 diff --git a/ja/built-in-nodes/CreateBoundingBoxes.mdx b/ja/built-in-nodes/CreateBoundingBoxes.mdx new file mode 100644 index 000000000..39a7eb171 --- /dev/null +++ b/ja/built-in-nodes/CreateBoundingBoxes.mdx @@ -0,0 +1,31 @@ +--- +title: "CreateBoundingBoxes - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the CreateBoundingBoxes node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "CreateBoundingBoxes" +icon: "circle" +mode: wide +--- + +このノードは、画像内のオブジェクトやテキスト領域の周囲にバウンディングボックスを描画するためのキャンバスインターフェースを提供します。ピクセル空間でのバウンディングボックス座標、Ideogramのプロンプトフォーマットと互換性のある構造化要素データ、およびラベルとカラーパレットが表示された描画済みボックスを含むプレビュー画像を出力します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `背景画像` | キャンバスとプレビューの背景として使用されるオプションの画像です。 | IMAGE | いいえ | - | +| `幅` | キャンバスとバウンディングボックス用ピクセルグリッドの幅です（デフォルト：1024）。 | INT | はい | 64～16384（ステップ：16） | +| `高さ` | キャンバスとバウンディングボックス用ピクセルグリッドの高さです（デフォルト：1024）。 | INT | はい | 64～16384（ステップ：16） | +| `エディタ状態` | バウンディングボックスを描画し、各ボックスのタイプ、テキスト、説明、カラーパレットを設定します。最初に背景要素、最後に前景要素を配置してください。 | BOUNDING_BOXES | はい | - | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `プレビュー` | すべてのバウンディングボックスがレンダリングされたキャンバスを示すRGB画像です。ラベル、カラーパレットの見本、説明テキストが含まれます。 | IMAGE | +| `バウンディングボックス` | ピクセル座標でのバウンディングボックスのリストです。各ボックスにはx、y、幅、高さの値が含まれます。 | BOUNDING_BOX | +| `要素` | 要素オブジェクトの構造化配列です。各要素にはタイプ、バウンディングボックス座標（0～1000に正規化）、テキスト（テキストタイプの場合）、説明、カラーパレットが含まれます。 | ARRAY | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateBoundingBoxes/ja.md) + +--- +**Source fingerprint (SHA-256):** `a63939f13edc6c6507590a390dcd6d0a3321febb5831baab1655d9952228612c` diff --git a/ja/built-in-nodes/CreateCameraInfo.mdx b/ja/built-in-nodes/CreateCameraInfo.mdx index 0ddf68176..caf72146b 100644 --- a/ja/built-in-nodes/CreateCameraInfo.mdx +++ b/ja/built-in-nodes/CreateCameraInfo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateCameraInfo" icon: "circle" mode: wide --- -# カメラ情報の作成 Create Camera Infoノードは、3Dレンダリング用のカメラ情報構造体を構築します。カメラの定義には、オービット（ターゲット周りのヨー/ピッチ/距離）、look_at（明示的なワールド位置）、クォータニオン（位置＋回転）の3つのモードをサポートしています。座標系は右手系で、Y軸が上方向となります。 diff --git a/ja/built-in-nodes/CreateHookKeyframe.mdx b/ja/built-in-nodes/CreateHookKeyframe.mdx index c433a9fef..71c72f5b5 100644 --- a/ja/built-in-nodes/CreateHookKeyframe.mdx +++ b/ja/built-in-nodes/CreateHookKeyframe.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframe" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Create Hook Keyframe ノードを使用すると、生成プロセス内でフックの動作が変化する特定のポイントを定義できます。このノードは、生成進行の特定のパーセンテージ時点でフックの強度を変更するキーフレームを作成し、これらのキーフレームを連鎖させることで複雑なスケジューリングパターンを実現できます。 @@ -21,7 +22,7 @@ Create Hook Keyframe ノードを使用すると、生成プロセス内でフ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `HOOK_KF` | 新しく作成されたキーフレームを含むフックキーフレームのグループ | HOOK_KEYFRAMES | +| `フックKF` | 新しく作成されたキーフレームを含むフックキーフレームのグループ | HOOK_KEYFRAMES | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframe/ja.md) diff --git a/ja/built-in-nodes/CreateHookKeyframesFromFloats.mdx b/ja/built-in-nodes/CreateHookKeyframesFromFloats.mdx index 7d0814737..add970119 100644 --- a/ja/built-in-nodes/CreateHookKeyframesFromFloats.mdx +++ b/ja/built-in-nodes/CreateHookKeyframesFromFloats.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframesFromFloats" icon: "circle" mode: wide --- + このノードは、浮動小数点数の強度値のリストからフックキーフレームを作成し、指定された開始パーセンテージと終了パーセンテージの間で均等に分散します。各強度値がアニメーションタイムライン上の特定のパーセンテージ位置に割り当てられたキーフレームのシーケンスを生成します。このノードは、新しいキーフレームグループを作成するか、既存のグループに追加することができ、デバッグ目的で生成されたキーフレームを出力するオプションもあります。 ## 入力 @@ -23,7 +24,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `HOOK_KF` | 新しく作成されたキーフレームを含むフックキーフレームグループ。新しいグループとして、または入力キーフレームグループに追加された状態で提供されます | HOOK_KEYFRAMES | +| `フックKF` | 新しく作成されたキーフレームを含むフックキーフレームグループ。新しいグループとして、または入力キーフレームグループに追加された状態で提供されます | HOOK_KEYFRAMES | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesFromFloats/ja.md) diff --git a/ja/built-in-nodes/CreateHookKeyframesInterpolated.mdx b/ja/built-in-nodes/CreateHookKeyframesInterpolated.mdx index fbbab2f1b..1b31c4f06 100644 --- a/ja/built-in-nodes/CreateHookKeyframesInterpolated.mdx +++ b/ja/built-in-nodes/CreateHookKeyframesInterpolated.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframesInterpolated" icon: "circle" mode: wide --- + ## 概要 開始点と終了点の間で強度値を補間したフックキーフレームのシーケンスを作成します。このノードは、生成プロセスの指定されたパーセンテージ範囲にわたって強度パラメータを滑らかに遷移させる複数のキーフレームを生成し、さまざまな補間方式を使用して遷移曲線を制御します。 @@ -26,7 +27,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `HOOK_KF` | 補間シーケンスを含む、生成されたフックキーフレームグループ | HOOK_KEYFRAMES | +| `フックKF` | 補間シーケンスを含む、生成されたフックキーフレームグループ | HOOK_KEYFRAMES | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesInterpolated/ja.md) diff --git a/ja/built-in-nodes/CreateHookLora.mdx b/ja/built-in-nodes/CreateHookLora.mdx index a491d30e9..c28078b80 100644 --- a/ja/built-in-nodes/CreateHookLora.mdx +++ b/ja/built-in-nodes/CreateHookLora.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookLora" icon: "circle" mode: wide --- + このドキュメントは AI によって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひコントリビュートしてください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookLora/en.md) Create Hook LoRA ノードは、モデルに LoRA（低ランク適応）変更を適用するためのフックオブジェクトを生成します。指定された LoRA ファイルを読み込み、モデルと CLIP の強度を調整できるフックを作成し、これらのフックを既存のフックと結合します。このノードは、以前に読み込んだ LoRA ファイルをキャッシュすることで冗長な処理を回避し、LoRA の読み込みを効率的に管理します。 diff --git a/ja/built-in-nodes/CreateHookLoraModelOnly.mdx b/ja/built-in-nodes/CreateHookLoraModelOnly.mdx index 876a17ed4..325f349fe 100644 --- a/ja/built-in-nodes/CreateHookLoraModelOnly.mdx +++ b/ja/built-in-nodes/CreateHookLoraModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookLoraModelOnly" icon: "circle" mode: wide --- + このドキュメントは AI が生成しました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookLoraModelOnly/en.md) このノードは、モデルコンポーネントにのみ適用される LoRA（低ランク適応）フックを作成し、CLIP コンポーネントは完全に変更しません。LoRA ファイルを読み込み、指定された強度でモデルに適用する一方、CLIP の強度はゼロに設定します。このノードは、以前のフックと連鎖させて、複雑な修正パイプラインを構築することができます。 diff --git a/ja/built-in-nodes/CreateHookModelAsLora.mdx b/ja/built-in-nodes/CreateHookModelAsLora.mdx index 4a7ecb992..46e2fb352 100644 --- a/ja/built-in-nodes/CreateHookModelAsLora.mdx +++ b/ja/built-in-nodes/CreateHookModelAsLora.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookModelAsLora" icon: "circle" mode: wide --- + 以下が翻訳結果です。 このノードは、チェックポイントの重みを読み込み、モデルとCLIPコンポーネントの両方に強度調整を適用することで、フックモデルをLoRA（低ランク適応）として作成します。フックベースのアプローチを通じて既存のモデルにLoRAスタイルの変更を適用できるため、モデルを恒久的に変更することなく微調整や適応が可能です。このノードは、以前のフックと組み合わせたり、読み込んだ重みをキャッシュして効率化することができます。 diff --git a/ja/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx b/ja/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx index 352f6eca2..cbe453b5b 100644 --- a/ja/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx +++ b/ja/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookModelAsLoraModelOnly" icon: "circle" mode: wide --- + このノードは、ニューラルネットワークのモデルコンポーネントのみを変更するためにLoRA（低ランク適応）モデルを適用するフックを作成します。チェックポイントファイルを読み込み、指定された強度でモデルに適用し、CLIPコンポーネントは変更しません。これは、基本となるCreateHookModelAsLoraクラスの機能を拡張した実験的なノードです。 ## 入力 diff --git a/ja/built-in-nodes/CreateList.mdx b/ja/built-in-nodes/CreateList.mdx index fd737c59d..be9b3e5a8 100644 --- a/ja/built-in-nodes/CreateList.mdx +++ b/ja/built-in-nodes/CreateList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateList" icon: "circle" mode: wide --- + 以下は、ご依頼いただいたComfyUIノードドキュメントの日本語翻訳です。 ## 概要 @@ -23,7 +24,7 @@ Create Listノードは、複数の入力を1つのシーケンシャルなリ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `list` | 接続された入力からのすべてのアイテムを、提供された順序で連結した単一のリストです。出力データ型は入力データ型と一致します。 | 可変 | +| `リスト` | 接続された入力からのすべてのアイテムを、提供された順序で連結した単一のリストです。出力データ型は入力データ型と一致します。 | 可変 | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateList/ja.md) diff --git a/ja/built-in-nodes/CreateVideo.mdx b/ja/built-in-nodes/CreateVideo.mdx index f450eaf09..a012a3509 100644 --- a/ja/built-in-nodes/CreateVideo.mdx +++ b/ja/built-in-nodes/CreateVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateVideo" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Create Video ノードは、画像のシーケンスから動画ファイルを生成します。フレームレート（1秒あたりのフレーム数）を使用して再生速度を指定し、必要に応じて動画に音声を追加することもできます。このノードは、指定されたフレームレートで再生可能な動画形式に画像を結合します。 diff --git a/ja/built-in-nodes/CropByBBoxes.mdx b/ja/built-in-nodes/CropByBBoxes.mdx index dd8f57f9f..caddf2483 100644 --- a/ja/built-in-nodes/CropByBBoxes.mdx +++ b/ja/built-in-nodes/CropByBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CropByBBoxes" icon: "circle" mode: wide --- + CropByBBoxes ノードは、入力画像バッチから特定の矩形領域を抽出し、リサイズします。提供されたバウンディングボックスの座標を使用して、各画像から切り取る領域を定義します。切り取られた領域は、指定された出力サイズにリサイズされ、切り抜きを引き伸ばすか、元のアスペクト比を維持するためにパディングするかを選択できます。 ## 入力 diff --git a/ja/built-in-nodes/CropMask.mdx b/ja/built-in-nodes/CropMask.mdx index 110a43f22..dc7904561 100644 --- a/ja/built-in-nodes/CropMask.mdx +++ b/ja/built-in-nodes/CropMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CropMask" icon: "circle" mode: wide --- + CropMaskノードは、指定されたマスクから特定の領域を切り抜くために設計されています。ユーザーは座標と寸法を指定して関心領域を定義し、マスクの一部を抽出してさらなる処理や分析に使用できます。 ## 入力 diff --git a/ja/built-in-nodes/CurveEditor.mdx b/ja/built-in-nodes/CurveEditor.mdx index 78a8a1eda..5b71e0590 100644 --- a/ja/built-in-nodes/CurveEditor.mdx +++ b/ja/built-in-nodes/CurveEditor.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CurveEditor" icon: "circle" mode: wide --- + Curve Editorノードは、カーブの調整と微調整を行うためのビジュアルインターフェースを提供します。入力されたカーブの形状を変更したり、オプションでヒストグラムを表示して分布を可視化したりすることができます。このノードは、ワークフローの他の部分で使用するために、修正されたカーブを出力します。 ## 入力 diff --git a/ja/built-in-nodes/CustomCombo.mdx b/ja/built-in-nodes/CustomCombo.mdx index 005a7baad..007502589 100644 --- a/ja/built-in-nodes/CustomCombo.mdx +++ b/ja/built-in-nodes/CustomCombo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CustomCombo" icon: "circle" mode: wide --- + 以下が翻訳です。 ## 概要 @@ -25,7 +26,7 @@ Custom Combo ノードを使用すると、独自のテキストオプション | 出力名 | 説明 | データ型 | | --- | --- | --- | | `インデックス` | カスタムコンボボックスから選択されたオプションのテキスト文字列。 | STRING | -| `INDEX` | ドロップダウンリスト内で選択されたオプションのインデックス位置。 | INT | +| `インデックス` | ドロップダウンリスト内で選択されたオプションのインデックス位置。 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CustomCombo/ja.md) diff --git a/ja/built-in-nodes/DA3GeometryToMesh.mdx b/ja/built-in-nodes/DA3GeometryToMesh.mdx new file mode 100644 index 000000000..9eeb23d51 --- /dev/null +++ b/ja/built-in-nodes/DA3GeometryToMesh.mdx @@ -0,0 +1,32 @@ +--- +title: "DA3GeometryToMesh - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3GeometryToMesh node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3GeometryToMesh" +icon: "circle" +mode: wide +--- + +このノードは、深度マップをアンプロジェクションし、結果の点群を三角形分割することで、DA3_GEOMETRY パケットを3Dメッシュに変換します。バッチから1枚の画像を処理し、テクスチャ付きまたはテクスチャなしの3Dレンダリングに適したメッシュを生成します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 深度マップ、オプションの信頼度マップ、オプションの空マップ、およびソース画像を含む DA3_GEOMETRY パケット | DA3_GEOMETRY | はい | - | +| `batch_index` | 変換するバッチ内の画像を指定します。画像ごとに頂点数が異なるため、バッチを積み重ねることはできません（デフォルト：0） | INT | はい | 0 ～ 4096 | +| `decimation` | 頂点ストライド。1 = フル解像度、2 = 半分、など（デフォルト：1） | INT | はい | 1 ～ 8 | +| `discontinuity_threshold` | 3x3の深度範囲がこの割合を超える三角形を削除します。0 = オフ（デフォルト：0.04） | FLOAT | はい | 0.0 ～ 1.0 | +| `confidence_threshold` | 画像ごとの正規化された信頼度がこの値未満のピクセルを除外します。0 = すべて保持、1 = 最も信頼度の高い1ピクセルのみ保持。ジオメトリに信頼度マップがある場合（Small/Baseモデル）に使用されます（デフォルト：0.1） | FLOAT | はい | 0.0 ～ 1.0 | +| `use_sky_mask` | 空の確率が高いピクセル（空 >= 0.5）をメッシュから除外します。ジオメトリに空マップがある場合（Mono/Metricモデル）に使用されます（デフォルト：True） | BOOLEAN | はい | True または False | +| `texture` | ソース画像をベースカラーテクスチャとして使用します（デフォルト：True） | BOOLEAN | はい | True または False | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `MESH` | 頂点、面、UV座標、およびオプションのテクスチャを持つ三角形分割された3Dメッシュ | MESH | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToMesh/ja.md) + +--- +**Source fingerprint (SHA-256):** `1d311223a8d131030bcd4930d21852a21ac9dd5758e7f8b8d20b1cf68698893b` diff --git a/ja/built-in-nodes/DA3GeometryToPointCloud.mdx b/ja/built-in-nodes/DA3GeometryToPointCloud.mdx new file mode 100644 index 000000000..7e26dfc17 --- /dev/null +++ b/ja/built-in-nodes/DA3GeometryToPointCloud.mdx @@ -0,0 +1,30 @@ +--- +title: "DA3GeometryToPointCloud - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3GeometryToPointCloud node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3GeometryToPointCloud" +icon: "circle" +mode: wide +--- + +このノードは、DA3_GEOMETRY オブジェクトから深度マップを3Dポイントクラウドに変換します。信頼度マスクと空マスクに基づいてフィルタリングを適用し、マルチビューシーンに適した共通のワールド座標系にポイントを変換します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 深度データとオプションの画像、信頼度、空マップを含む DA3_GEOMETRY オブジェクト | DA3_GEOMETRY | はい | - | +| `batch_index` | バッチ内のどの画像を変換するか（デフォルト：0） | INT | はい | 0 から 4096 | +| `confidence_threshold` | 画像ごとの正規化された信頼度がこの値を下回るピクセルを除外します（0 = すべて保持）。ジオメトリに信頼度マップがある場合（Small/Baseモデル）に使用されます。（デフォルト：0.1） | FLOAT | はい | 0.0 から 1.0 | +| `use_sky_mask` | 空の確率が高いピクセル（空 >= 0.5）を除外します。ジオメトリに空マップがある場合（Mono/Metricモデル）に使用されます。（デフォルト：True） | BOOLEAN | はい | True または False | +| `downsample` | Nピクセルごとに1ピクセルを取得します（1 = フル解像度）。値が大きいほどポイント数が減り、処理が高速化します。（デフォルト：1） | INT | はい | 1 から 16 | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `point_cloud` | フィルタリングされた3Dポイント、オプションの色、およびオプションの信頼度値を含むポイントクラウドオブジェクト | DA3_POINT_CLOUD | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToPointCloud/ja.md) + +--- +**Source fingerprint (SHA-256):** `3cf5bdbb8afdfcfc02f9832a8cbc5a3df49da755dea6df01792aa6ef9e5d7287` diff --git a/ja/built-in-nodes/DA3Inference.mdx b/ja/built-in-nodes/DA3Inference.mdx new file mode 100644 index 000000000..7ab6101e6 --- /dev/null +++ b/ja/built-in-nodes/DA3Inference.mdx @@ -0,0 +1,38 @@ +--- +title: "DA3Inference - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3Inference node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3Inference" +icon: "circle" +mode: wide +--- + +このノードは、Depth Anything 3 モデルを画像に適用し、深度と幾何学情報を推定します。マルチビューモードでは、複数の画像を同一シーンの別々のビューとしてまとめて処理し、幾何学的に一貫した深度マップとカメラポーズを生成します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `da3_model` | 推論に使用する Depth Anything 3 モデル | DA3_MODEL | はい | - | +| `image` | 処理する入力画像（複数可） | IMAGE | はい | - | +| `resolution` | モデルが動作する解像度（最長辺、14の倍数）。値が小さいほど高速でVRAM使用量が少なくなります。値が大きいほど詳細な結果が得られます。出力は元のサイズにアップサンプリングされます（デフォルト：504） | INT | はい | 140～2520（ステップ：14） | +| `resize_method` | upper_bound_resize：最長辺が解像度と一致するようにスケーリング（メモリを抑える、デフォルト）。lower_bound_resize：最短辺が解像度と一致するようにスケーリング（縦長/横長の画像で詳細を保持、メモリ使用量増加） | COMBO | はい | `"upper_bound_resize"`
`"lower_bound_resize"` | +| `mode` | mono：単一ビュー画像処理（すべてのモデルバリアントで動作）。multiview：すべての画像をまとめて処理し、幾何学的一貫性とカメラポーズ推定を実現（SmallおよびBaseモデルのみ） | COMBO | はい | `"mono"`
`"multiview"` | +| `ref_view_strategy` | マルチビューモードで幾何学的アンカーとなるビュー。saddle_balanced：他のすべてのビューに対して最も平均的なビュー（一般的に最適）。saddle_sim_range：他のビューと最も視覚的に異なるビュー。first / middle：固定位置による選択 | COMBO | いいえ（条件付き） | `"saddle_balanced"`
`"saddle_sim_range"`
`"first"`
`"middle"` | +| `pose_method` | カメラの視野角の推定方法（SmallおよびBaseモデルのみ）。cam_dec：画像特徴から学習。ray_pose：モデルの3Dレイ出力から幾何学的に導出。3D出力の遠近感の正確さに影響します | COMBO | いいえ（条件付き） | `"cam_dec"`
`"ray_pose"` | + +**パラメータ制約に関する注意事項：** +- `ref_view_strategy` および `pose_method` パラメータは、`mode` が `"multiview"` に設定されている場合のみ使用可能です +- マルチビューモードには Small または Base モデルバリアントが必要です。他のヘッドタイプ（Metric や Mono など）のモデルは、クロスビューアテンションやカメラポーズ推定をサポートしていません +- `pose_method` が `"cam_dec"` に設定されている場合、モデルにカメラデコーダが必要です。`"ray_pose"` に設定されている場合、モデルに DualDPT ヘッドが必要です +- 選択した `pose_method` が読み込まれたモデルと互換性がない場合、エラーが発生します + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `da3_geometry` | 非正規化テンソルの辞書。常に depth、image、mode のキーを含みます。オプションのキーには、sky（Mono/Metricモデル用）、confidence（Small/Baseモデル用）、extrinsics および intrinsics（マルチビューモード用）があります | DA3_GEOMETRY | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3Inference/ja.md) + +--- +**Source fingerprint (SHA-256):** `e91dd47e6a01719cdd6b6ce8a9bcc45933cac72c5e147ac42906d2f83ab7c250` diff --git a/ja/built-in-nodes/DA3Render.mdx b/ja/built-in-nodes/DA3Render.mdx new file mode 100644 index 000000000..eb028edfc --- /dev/null +++ b/ja/built-in-nodes/DA3Render.mdx @@ -0,0 +1,54 @@ +--- +title: "DA3Render - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3Render node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3Render" +icon: "circle" +mode: wide +--- + +このノードは、Depth Anything 3 のジオメトリデータから可視化画像をレンダリングします。選択した出力モードに応じて、深度マップ、信頼度マップ、または空マスクを出力できます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 深度、オプションで空および信頼度テンソルを含む Depth Anything 3 ジオメトリデータパケット | DA3_GEOMETRY | はい | - | +| `output` | レンダリングする可視化の種類。オプションには depth、depth_colored、sky_mask、confidence があります。各オプションには独自のサブパラメータセットがあります。 | COMBO | はい | `"depth"`
`"depth_colored"`
`"sky_mask"`
`"confidence"` | + +### `output` オプションのサブパラメータ + +`output` が `"depth"` または `"depth_colored"` に設定されている場合： + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `normalization` | 深度の正規化方法。v2_style は平均/標準偏差による正規化を使用し、知覚的にバランスの取れた結果を得ます（デフォルト）。min_max は深度範囲全体を [0, 1] に引き伸ばし、最大コントラストを実現します。raw は Metric モデルでメートル単位をスケーリングせずに保持します。 | COMBO | はい | `"v2_style"`
`"min_max"`
`"raw"` | +| `apply_sky_clip` | 正規化前に空領域の深度を前景深度の99パーセンタイルにクリップします。da3_geometry 入力に sky キーが必要です（Mono/Metric モデルのみ）。デフォルト：False | BOOLEAN | はい | True
False | + +`output` が `"sky_mask"` に設定されている場合： + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `colored` | 空マスクに Turbo カラーマップを適用します。デフォルト：False | BOOLEAN | はい | True
False | + +`output` が `"confidence"` に設定されている場合： + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `colored` | 信頼度マップに Turbo カラーマップを適用します。デフォルト：False | BOOLEAN | はい | True
False | + +### パラメータ制約 + +- `apply_sky_clip` が True に設定されている場合、`da3_geometry` 入力に sky テンソルが含まれている必要があります。これは Mono または Metric モデルを使用する場合のみ利用可能です。sky テンソルがない場合、ノードはエラーを発生させます。 +- `sky_mask` 出力オプションには、`da3_geometry` 入力に sky テンソルが必要です。これは Mono または Metric モデルでのみ利用可能です。 +- `confidence` 出力オプションには、`da3_geometry` 入力に信頼度テンソルが必要です。これは Small または Base モデルでのみ利用可能です。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `IMAGE` | レンダリングされた可視化画像テンソル。深度出力の場合は、グレースケールまたはカラーの深度マップを返します。sky_mask および confidence の場合は、colored パラメータに応じてグレースケールまたはカラーの可視化画像を返します。 | IMAGE | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3Render/ja.md) + +--- +**Source fingerprint (SHA-256):** `54d4cde95a916cac26c8a2e19c5623e794d46c0d7652f1c8204f9f2a0deabe0c` diff --git a/ja/built-in-nodes/DCTestNode.mdx b/ja/built-in-nodes/DCTestNode.mdx index 35d9f4608..e59df2115 100644 --- a/ja/built-in-nodes/DCTestNode.mdx +++ b/ja/built-in-nodes/DCTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DCTestNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 DCTestNodeは、動的コンボボックスでのユーザーの選択に基づいて異なるタイプのデータを返すロジックノードです。これは条件付きルーターとして機能し、選択されたオプションによって、どの入力フィールドがアクティブになり、ノードがどのタイプの値を出力するかが決まります。 diff --git a/ja/built-in-nodes/DeprecatedCheckpointLoader.mdx b/ja/built-in-nodes/DeprecatedCheckpointLoader.mdx index 5dfeb00db..075473491 100644 --- a/ja/built-in-nodes/DeprecatedCheckpointLoader.mdx +++ b/ja/built-in-nodes/DeprecatedCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DeprecatedCheckpointLoader" icon: "circle" mode: wide --- + CheckpointLoaderノードは、高度な読み込み操作、具体的にはモデルチェックポイントとその設定を読み込むために設計されています。このノードは、指定されたディレクトリから設定やチェックポイントを含む、生成モデルの初期化と実行に必要なモデルコンポーネントの取得を容易にします。 ## 入力 diff --git a/ja/built-in-nodes/DeprecatedDiffusersLoader.mdx b/ja/built-in-nodes/DeprecatedDiffusersLoader.mdx index 718b2116e..92df777f2 100644 --- a/ja/built-in-nodes/DeprecatedDiffusersLoader.mdx +++ b/ja/built-in-nodes/DeprecatedDiffusersLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DeprecatedDiffusersLoader" icon: "circle" mode: wide --- + DiffusersLoaderノードは、diffusersライブラリからモデルを読み込むために設計されており、指定されたモデルパスに基づいてUNet、CLIP、VAEモデルの読み込みを処理します。このノードは、これらのモデルをComfyUIフレームワークに統合し、テキストから画像への生成、画像操作などの高度な機能を実現します。 ## 入力 diff --git a/ja/built-in-nodes/DiffControlNetLoader.mdx b/ja/built-in-nodes/DiffControlNetLoader.mdx index 6586731c9..e8fea270d 100644 --- a/ja/built-in-nodes/DiffControlNetLoader.mdx +++ b/ja/built-in-nodes/DiffControlNetLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DiffControlNetLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/controlnet` フォルダ内のモデルを検出し、さらに `extra_model_paths.yaml` ファイルで設定された追加パスからもモデルを読み取ります。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、対応するフォルダからモデルファイルを読み取らせる必要があります。 DiffControlNetLoader ノードは、差分制御ネットワークを読み込むために設計されています。これは、制御ネットの仕様に基づいて別のモデルの動作を変更できる特殊なモデルです。このノードを使用すると、差分制御ネットを適用することでモデルの動作を動的に調整し、カスタマイズされたモデル出力の作成を容易にします。 diff --git a/ja/built-in-nodes/DifferentialDiffusion.mdx b/ja/built-in-nodes/DifferentialDiffusion.mdx index d7aeb43d0..5c76530af 100644 --- a/ja/built-in-nodes/DifferentialDiffusion.mdx +++ b/ja/built-in-nodes/DifferentialDiffusion.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DifferentialDiffusion" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がございましたら、ぜひご協力ください。[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DifferentialDiffusion/en.md) Differential Diffusionノードは、タイムステップのしきい値に基づいてバイナリマスクを適用することで、ノイズ除去プロセスを変更します。このノードは、元のノイズ除去マスクとしきい値ベースのバイナリマスクをブレンドするマスクを作成し、拡散プロセスの強度を制御調整できるようにします。 diff --git a/ja/built-in-nodes/DiffusersLoader.mdx b/ja/built-in-nodes/DiffusersLoader.mdx index 6e8914649..e80a8e524 100644 --- a/ja/built-in-nodes/DiffusersLoader.mdx +++ b/ja/built-in-nodes/DiffusersLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DiffusersLoader" icon: "circle" mode: wide --- + DiffusersLoaderノードは、diffusers形式の事前学習済みモデルを読み込みます。`model_index.json`ファイルを含む有効なdiffusersモデルディレクトリを検索し、パイプラインで使用するためにMODEL、CLIP、VAEコンポーネントとして読み込みます。このノードは非推奨のローダーカテゴリに属し、Hugging Face diffusersモデルとの互換性を提供します。 ## 入力 diff --git a/ja/built-in-nodes/DisableNoise.mdx b/ja/built-in-nodes/DisableNoise.mdx index 760fec969..024365f4e 100644 --- a/ja/built-in-nodes/DisableNoise.mdx +++ b/ja/built-in-nodes/DisableNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DisableNoise" icon: "circle" mode: wide --- + DisableNoise ノードは、サンプリング処理におけるノイズ生成を無効化するための空のノイズ設定を提供します。このノードはノイズデータを含まない特殊なノイズオブジェクトを返すため、この出力に接続された他のノードはノイズ関連の処理をスキップできるようになります。 ## 入力 diff --git a/ja/built-in-nodes/DrawBBoxes.mdx b/ja/built-in-nodes/DrawBBoxes.mdx index 7aa7124b7..d818c26fe 100644 --- a/ja/built-in-nodes/DrawBBoxes.mdx +++ b/ja/built-in-nodes/DrawBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DrawBBoxes" icon: "circle" mode: wide --- + DrawBBoxes ノードは、画像上にバウンディングボックス、ラベル、信頼度スコアを描画することで、物体検出結果を可視化します。入力画像が提供されない場合は、描画するすべてのボックスを収容できる十分な大きさの空白キャンバスを作成します。バッチ処理に対応しており、複数の画像に対して異なる検出結果を描画したり、バッチ全体で同じ検出結果を繰り返し描画することができます。 ## 入力 diff --git a/ja/built-in-nodes/DualCFGGuider.mdx b/ja/built-in-nodes/DualCFGGuider.mdx index 4b0cf11a1..293ecec6f 100644 --- a/ja/built-in-nodes/DualCFGGuider.mdx +++ b/ja/built-in-nodes/DualCFGGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DualCFGGuider" icon: "circle" mode: wide --- + {DualCFGGuider}ノードは、デュアル分類器不要ガイダンス（Dual Classifier-Free Guidance）サンプリングのためのガイダンスシステムを作成します。2つのポジティブ条件付け入力と1つのネガティブ条件付け入力を組み合わせ、各条件付けペアに異なるガイダンススケールを適用することで、生成出力に対する各プロンプトの影響を制御します。 ## 入力 diff --git a/ja/built-in-nodes/DualCLIPLoader.mdx b/ja/built-in-nodes/DualCLIPLoader.mdx index 03e8fa86d..c74334e41 100644 --- a/ja/built-in-nodes/DualCLIPLoader.mdx +++ b/ja/built-in-nodes/DualCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DualCLIPLoader" icon: "circle" mode: wide --- + DualCLIPLoader ノードは、2つのCLIPモデルを同時に読み込むために設計されており、両方のモデルからの特徴量の統合や比較を必要とする操作を容易にします。 このノードは、`ComfyUI/models/text_encoders` フォルダ内にあるモデルを検出します。 diff --git a/ja/built-in-nodes/DualModelGuider.mdx b/ja/built-in-nodes/DualModelGuider.mdx index dd5d89d13..292f8a1f9 100644 --- a/ja/built-in-nodes/DualModelGuider.mdx +++ b/ja/built-in-nodes/DualModelGuider.mdx @@ -5,7 +5,6 @@ sidebarTitle: "DualModelGuider" icon: "circle" mode: wide --- -# デュアルモデルCFGガイダー このノードを使用すると、ガイド付きCFGサンプリングプロセス中に2つの異なるモデルを使用できます。ポジティブ（条件付き）パスには1つのモデル、ネガティブ（無条件）パスには別のモデルを使用します。ネガティブモデルが指定されていない場合は、単一モデルを使用する標準のCFGガイダーとして動作します。 diff --git a/ja/built-in-nodes/EasyCache.mdx b/ja/built-in-nodes/EasyCache.mdx index ecbb3bf48..428194f5c 100644 --- a/ja/built-in-nodes/EasyCache.mdx +++ b/ja/built-in-nodes/EasyCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EasyCache" icon: "circle" mode: wide --- + EasyCache ノードは、モデル用のネイティブキャッシュシステムを実装し、サンプリングプロセス中に以前計算したステップを再利用することでパフォーマンスを向上させます。サンプリングのタイムラインにおいて、キャッシュの使用を開始および停止するタイミングを設定可能な閾値とともに、モデルに EasyCache 機能を追加します。 ## 入力 diff --git a/ja/built-in-nodes/ElevenLabsAudioIsolation.mdx b/ja/built-in-nodes/ElevenLabsAudioIsolation.mdx index a70795b50..e52939f65 100644 --- a/ja/built-in-nodes/ElevenLabsAudioIsolation.mdx +++ b/ja/built-in-nodes/ElevenLabsAudioIsolation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsAudioIsolation" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ElevenLabs Voice Isolationノードは、オーディオファイルから背景ノイズを除去し、ボーカルや音声を分離します。このノードはオーディオをElevenLabs APIに送信して処理し、クリーンなオーディオを返します。 diff --git a/ja/built-in-nodes/ElevenLabsInstantVoiceClone.mdx b/ja/built-in-nodes/ElevenLabsInstantVoiceClone.mdx index 36adc53df..1caf1c7a3 100644 --- a/ja/built-in-nodes/ElevenLabsInstantVoiceClone.mdx +++ b/ja/built-in-nodes/ElevenLabsInstantVoiceClone.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsInstantVoiceClone" icon: "circle" mode: wide --- + 以下が翻訳結果です。 このドキュメントは AI によって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsInstantVoiceClone/en.md) @@ -24,7 +25,7 @@ ElevenLabs Instant Voice Clone ノードは、1 ～ 8 件の音声録音を分 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `voice` | 新しく作成されたクローン音声モデルの一意の識別子です。この出力は、他の ElevenLabs テキスト読み上げノードに接続できます。 | ELEVENLABS_VOICE | +| `ボイス` | 新しく作成されたクローン音声モデルの一意の識別子です。この出力は、他の ElevenLabs テキスト読み上げノードに接続できます。 | ELEVENLABS_VOICE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsInstantVoiceClone/ja.md) diff --git a/ja/built-in-nodes/ElevenLabsSpeechToSpeech.mdx b/ja/built-in-nodes/ElevenLabsSpeechToSpeech.mdx index 0deb828c0..3f14bf97b 100644 --- a/ja/built-in-nodes/ElevenLabsSpeechToSpeech.mdx +++ b/ja/built-in-nodes/ElevenLabsSpeechToSpeech.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsSpeechToSpeech" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ElevenLabs Speech to Speech ノードは、入力された音声ファイルを別の声に変換します。ElevenLabs API を使用して音声を変換し、元の音声の内容と感情的なトーンを保持します。 diff --git a/ja/built-in-nodes/ElevenLabsSpeechToText.mdx b/ja/built-in-nodes/ElevenLabsSpeechToText.mdx index 79e869ea4..d4c159e49 100644 --- a/ja/built-in-nodes/ElevenLabsSpeechToText.mdx +++ b/ja/built-in-nodes/ElevenLabsSpeechToText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsSpeechToText" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ElevenLabs Speech to Text ノードは、オーディオファイルをテキストに文字起こしします。ElevenLabs の API を使用して、音声を書き起こしテキストに変換します。自動言語検出、話者の識別、音楽や笑い声などの非音声サウンドのタグ付けなどの機能をサポートしています。 @@ -30,9 +31,9 @@ ElevenLabs Speech to Text ノードは、オーディオファイルをテキス | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `言語コード` | オーディオから文字起こしされたテキスト。 | STRING | -| `単語JSON` | 検出されたオーディオの言語コード。 | STRING | -| `words_json` | タイムスタンプや、有効な場合は話者ラベルを含む、詳細な単語レベルの情報を含む JSON 形式の文字列。 | STRING | +| `テキスト` | オーディオから文字起こしされたテキスト。 | STRING | +| `言語コード` | 検出されたオーディオの言語コード。 | STRING | +| `単語JSON` | タイムスタンプや、有効な場合は話者ラベルを含む、詳細な単語レベルの情報を含む JSON 形式の文字列。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToText/ja.md) diff --git a/ja/built-in-nodes/ElevenLabsTextToDialogue.mdx b/ja/built-in-nodes/ElevenLabsTextToDialogue.mdx index 5368f5f92..8877be75f 100644 --- a/ja/built-in-nodes/ElevenLabsTextToDialogue.mdx +++ b/ja/built-in-nodes/ElevenLabsTextToDialogue.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsTextToDialogue" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ElevenLabs Text to Dialogue ノードは、テキストから複数の話者による音声ダイアログを生成します。異なるテキスト行と各参加者に個別の声を指定することで、会話を作成できます。このノードは、ダイアログリクエストを ElevenLabs API に送信し、生成された音声を返します。 diff --git a/ja/built-in-nodes/ElevenLabsTextToSoundEffects.mdx b/ja/built-in-nodes/ElevenLabsTextToSoundEffects.mdx index db93e172a..9545b4667 100644 --- a/ja/built-in-nodes/ElevenLabsTextToSoundEffects.mdx +++ b/ja/built-in-nodes/ElevenLabsTextToSoundEffects.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsTextToSoundEffects" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- diff --git a/ja/built-in-nodes/ElevenLabsTextToSpeech.mdx b/ja/built-in-nodes/ElevenLabsTextToSpeech.mdx index 9601b300d..5387990ce 100644 --- a/ja/built-in-nodes/ElevenLabsTextToSpeech.mdx +++ b/ja/built-in-nodes/ElevenLabsTextToSpeech.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsTextToSpeech" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ElevenLabs Text to Speech ノードは、ElevenLabs API を使用して、書き込まれたテキストを音声に変換します。特定の音声を選択し、安定性、速度、スタイルなどのさまざまな音声特性を微調整して、カスタマイズされた音声出力を生成できます。 diff --git a/ja/built-in-nodes/ElevenLabsVoiceSelector.mdx b/ja/built-in-nodes/ElevenLabsVoiceSelector.mdx index e5972b83f..9b1493b8f 100644 --- a/ja/built-in-nodes/ElevenLabsVoiceSelector.mdx +++ b/ja/built-in-nodes/ElevenLabsVoiceSelector.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsVoiceSelector" icon: "circle" mode: wide --- + ElevenLabs Voice Selector ノードを使用すると、ElevenLabs テキスト読み上げ用の定義済み音声リストから特定の音声を選択できます。このノードは音声名を入力として受け取り、音声生成に必要な対応する音声識別子を出力します。このノードにより、他の ElevenLabs オーディオノードと互換性のある音声を簡単に選択できるようになります。 ## 入力 diff --git a/ja/built-in-nodes/EmptyARVideoLatent.mdx b/ja/built-in-nodes/EmptyARVideoLatent.mdx index c23eba69d..e4fcfc712 100644 --- a/ja/built-in-nodes/EmptyARVideoLatent.mdx +++ b/ja/built-in-nodes/EmptyARVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyARVideoLatent" icon: "circle" mode: wide --- + ## 概要 EmptyARVideoLatent ノードは、動画生成用の空の潜在表現を作成します。指定された寸法、アスペクト比、長さを持つゼロテンソルを提供することで、動画生成プロセスを初期化するために使用されます。 diff --git a/ja/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx b/ja/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx index 589b550ae..5317d118b 100644 --- a/ja/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx +++ b/ja/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAceStep1.5LatentAudio" icon: "circle" mode: wide --- + ## 概要Empty Ace Step 1.5 Latent Audio ノードは、オーディオ処理用に設計された空の潜在テンソルを作成します。指定された長さとバッチサイズの無音オーディオ潜在表現を生成し、ComfyUI でのオーディオ生成ワークフローの開始点として使用できます。このノードは、入力された秒数と固定サンプルレートに基づいて潜在長を計算します。 ## 入力 diff --git a/ja/built-in-nodes/EmptyAceStepLatentAudio.mdx b/ja/built-in-nodes/EmptyAceStepLatentAudio.mdx index 50dba408d..291693a44 100644 --- a/ja/built-in-nodes/EmptyAceStepLatentAudio.mdx +++ b/ja/built-in-nodes/EmptyAceStepLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAceStepLatentAudio" icon: "circle" mode: wide --- + EmptyAceStepLatentAudioノードは、指定された長さの空の潜在音声サンプルを作成します。ゼロで埋められた無音の音声潜在表現のバッチを生成し、その長さは入力された秒数と音声処理パラメータに基づいて計算されます。このノードは、潜在表現を必要とする音声処理ワークフローの初期化に役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/EmptyAudio.mdx b/ja/built-in-nodes/EmptyAudio.mdx index 5b721aecc..03586a251 100644 --- a/ja/built-in-nodes/EmptyAudio.mdx +++ b/ja/built-in-nodes/EmptyAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/EmptyChromaRadianceLatentImage.mdx b/ja/built-in-nodes/EmptyChromaRadianceLatentImage.mdx index 737b4d943..efed76b66 100644 --- a/ja/built-in-nodes/EmptyChromaRadianceLatentImage.mdx +++ b/ja/built-in-nodes/EmptyChromaRadianceLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyChromaRadianceLatentImage" icon: "circle" mode: wide --- + EmptyChromaRadianceLatentImageノードは、クロマラディアンスワークフローで使用するための、指定された寸法の空白の潜在画像を作成します。このノードは、潜在空間操作の開始点として機能するゼロで満たされたテンソルを生成します。ノードでは、空白の潜在画像の幅、高さ、およびバッチサイズを定義できます。 ## 入力 diff --git a/ja/built-in-nodes/EmptyCosmosLatentVideo.mdx b/ja/built-in-nodes/EmptyCosmosLatentVideo.mdx index 23ee190be..87641b14a 100644 --- a/ja/built-in-nodes/EmptyCosmosLatentVideo.mdx +++ b/ja/built-in-nodes/EmptyCosmosLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyCosmosLatentVideo" icon: "circle" mode: wide --- + EmptyCosmosLatentVideo ノードは、指定された寸法で空の潜在ビデオテンソルを作成します。ゼロで埋められた潜在表現を生成し、ビデオ生成ワークフローの開始点として使用できます。幅、高さ、フレーム数、バッチサイズのパラメータを設定可能です。 ## 入力 diff --git a/ja/built-in-nodes/EmptyFlux2LatentImage.mdx b/ja/built-in-nodes/EmptyFlux2LatentImage.mdx index 8a999c14b..8b2945baa 100644 --- a/ja/built-in-nodes/EmptyFlux2LatentImage.mdx +++ b/ja/built-in-nodes/EmptyFlux2LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyFlux2LatentImage" icon: "circle" mode: wide --- + EmptyFlux2LatentImageノードは、空の潜在表現を作成します。ゼロで満たされたテンソルを生成し、Fluxモデルのノイズ除去プロセスの開始点として機能します。潜在表現の次元は、入力された幅と高さに基づき、16分の1にスケールダウンされます。 ## 入力 diff --git a/ja/built-in-nodes/EmptyHiDreamO1LatentImage.mdx b/ja/built-in-nodes/EmptyHiDreamO1LatentImage.mdx index c99161f1d..db78aeba2 100644 --- a/ja/built-in-nodes/EmptyHiDreamO1LatentImage.mdx +++ b/ja/built-in-nodes/EmptyHiDreamO1LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHiDreamO1LatentImage" icon: "circle" mode: wide --- + 以下は、指定された翻訳ルールに従って日本語に翻訳したドキュメントです。 ## 概要 diff --git a/ja/built-in-nodes/EmptyHunyuanImageLatent.mdx b/ja/built-in-nodes/EmptyHunyuanImageLatent.mdx index 0ac548d3f..9e9e9c080 100644 --- a/ja/built-in-nodes/EmptyHunyuanImageLatent.mdx +++ b/ja/built-in-nodes/EmptyHunyuanImageLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanImageLatent" icon: "circle" mode: wide --- + 以下が翻訳結果です。 EmptyHunyuanImageLatent ノードは、Hunyuan 画像生成モデルで使用するための特定の寸法を持つ空の潜在テンソルを作成します。ワークフロー内の後続ノードで処理可能な空白の開始点を生成し、潜在空間の幅、高さ、およびバッチサイズを指定できます。 diff --git a/ja/built-in-nodes/EmptyHunyuanLatentVideo.mdx b/ja/built-in-nodes/EmptyHunyuanLatentVideo.mdx index 6e125daf9..002d717db 100644 --- a/ja/built-in-nodes/EmptyHunyuanLatentVideo.mdx +++ b/ja/built-in-nodes/EmptyHunyuanLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanLatentVideo" icon: "circle" mode: wide --- + `EmptyHunyuanLatentVideo` ノードは、`EmptyLatentImage` ノードと類似しています。これは、動画生成のための空白のキャンバスと考えることができ、幅、高さ、長さがキャンバスのプロパティを定義し、バッチサイズが作成するキャンバスの数を決定します。このノードは、後続の動画生成タスクに備えて、空のキャンバスを作成します。 ## 入力 diff --git a/ja/built-in-nodes/EmptyHunyuanVideo15Latent.mdx b/ja/built-in-nodes/EmptyHunyuanVideo15Latent.mdx index a85fbc7fe..b0acc8281 100644 --- a/ja/built-in-nodes/EmptyHunyuanVideo15Latent.mdx +++ b/ja/built-in-nodes/EmptyHunyuanVideo15Latent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanVideo15Latent" icon: "circle" mode: wide --- + このノードは、HunyuanVideo 1.5モデルで使用するために特別にフォーマットされた空の潜在テンソルを作成します。モデルの潜在空間に適したチャンネル数と空間次元を持つゼロのテンソルを割り当てることで、動画生成のための空白の開始点を生成します。 ## 入力 diff --git a/ja/built-in-nodes/EmptyImage.mdx b/ja/built-in-nodes/EmptyImage.mdx index 80709c403..113aa1bdc 100644 --- a/ja/built-in-nodes/EmptyImage.mdx +++ b/ja/built-in-nodes/EmptyImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyImage" icon: "circle" mode: wide --- + ## 機能説明 EmptyImageノードは、指定された寸法と色で空白の画像を作成するために使用されます。単色の背景画像を生成でき、画像処理ワークフローの開始点や背景画像としてよく使用されます。 diff --git a/ja/built-in-nodes/EmptyLTXVLatentVideo.mdx b/ja/built-in-nodes/EmptyLTXVLatentVideo.mdx index cf19095ba..745d1dafb 100644 --- a/ja/built-in-nodes/EmptyLTXVLatentVideo.mdx +++ b/ja/built-in-nodes/EmptyLTXVLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLTXVLatentVideo" icon: "circle" mode: wide --- + EmptyLTXVLatentVideo ノードは、動画処理用の空の潜在テンソルを作成します。指定された寸法を持つ空の開始点を生成し、動画生成ワークフローの入力として使用できます。このノードは、設定された幅、高さ、長さ、バッチサイズでゼロ埋めされた潜在表現を生成します。 ## 入力 diff --git a/ja/built-in-nodes/EmptyLatentAudio.mdx b/ja/built-in-nodes/EmptyLatentAudio.mdx index 2ace8adb9..8d90307a8 100644 --- a/ja/built-in-nodes/EmptyLatentAudio.mdx +++ b/ja/built-in-nodes/EmptyLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx b/ja/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx index 90f70b8b9..f7316631b 100644 --- a/ja/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx +++ b/ja/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentHunyuan3Dv2" icon: "circle" mode: wide --- + このドキュメントは AI が生成したものです。誤りや改善の提案がありましたら、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyLatentHunyuan3Dv2/en.md) EmptyLatentHunyuan3Dv2 ノードは、Hunyuan3Dv2 3D 生成モデル用に特別にフォーマットされた空の潜在テンソルを作成します。このノードは、Hunyuan3Dv2 アーキテクチャに必要な正しい次元と構造を持つ空の潜在空間を生成し、ゼロから 3D 生成ワークフローを開始できるようにします。出力は、後続の 3D 生成プロセスの基盤となる、ゼロで満たされた潜在テンソルです。 diff --git a/ja/built-in-nodes/EmptyLatentImage.mdx b/ja/built-in-nodes/EmptyLatentImage.mdx index 84d06e442..3b3c9fc29 100644 --- a/ja/built-in-nodes/EmptyLatentImage.mdx +++ b/ja/built-in-nodes/EmptyLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentImage" icon: "circle" mode: wide --- + `EmptyLatentImage`ノードは、指定された寸法とバッチサイズで空白の潜在空間表現を生成するために設計されています。このノードは、潜在空間での画像生成や操作における基礎的なステップとして機能し、その後の画像合成や修正プロセスの開始点を提供します。 ## 入力 diff --git a/ja/built-in-nodes/EmptyMochiLatentVideo.mdx b/ja/built-in-nodes/EmptyMochiLatentVideo.mdx index 65f7a80c3..bfdc396d9 100644 --- a/ja/built-in-nodes/EmptyMochiLatentVideo.mdx +++ b/ja/built-in-nodes/EmptyMochiLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyMochiLatentVideo" icon: "circle" mode: wide --- + EmptyMochiLatentVideoノードは、指定された寸法で空の潜在ビデオテンソルを作成します。ゼロで埋められた潜在表現を生成し、ビデオ生成ワークフローの開始点として使用できます。このノードでは、潜在ビデオテンソルの幅、高さ、長さ、およびバッチサイズを定義できます。 ## 入力 diff --git a/ja/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx b/ja/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx index e41df7cff..f26485ba2 100644 --- a/ja/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx +++ b/ja/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyQwenImageLayeredLatentImage" icon: "circle" mode: wide --- + ## 概要 Empty Qwen Image Layered Latentノードは、Qwen画像モデルで使用するための空の多層潜在表現を作成します。指定されたレイヤー数、バッチサイズ、および空間次元で構成された、ゼロで満たされたテンソルを生成します。この空の潜在表現は、その後の画像生成や操作ワークフローの開始点として機能します。 ## 入力 diff --git a/ja/built-in-nodes/EmptySD3LatentImage.mdx b/ja/built-in-nodes/EmptySD3LatentImage.mdx index fd74809de..9ab390e07 100644 --- a/ja/built-in-nodes/EmptySD3LatentImage.mdx +++ b/ja/built-in-nodes/EmptySD3LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptySD3LatentImage" icon: "circle" mode: wide --- + EmptySD3LatentImage ノードは、Stable Diffusion 3 モデル用に特別にフォーマットされた空の潜在画像テンソルを作成します。ゼロで満たされたテンソルを生成し、SD3 パイプラインで期待される正しい次元と構造を持ちます。これは、画像生成ワークフローの開始点として一般的に使用されます。 ## 入力 diff --git a/ja/built-in-nodes/Epsilon Scaling.mdx b/ja/built-in-nodes/Epsilon Scaling.mdx index 2feaa128a..cafddc246 100644 --- a/ja/built-in-nodes/Epsilon Scaling.mdx +++ b/ja/built-in-nodes/Epsilon Scaling.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Epsilon Scaling" icon: "circle" mode: wide --- + このノードは、研究論文「Elucidating the Exposure Bias in Diffusion Models」（arxiv.org/abs/2308.15321v6）で提案されたEpsilon Scaling法を実装しています。サンプリングプロセス中に予測ノイズをスケーリングすることで、露出バイアスを低減し、生成画像の品質向上を実現します。本実装では、論文で実用性と効果のバランスが推奨されている「均一スケジュール」を採用しています。 ## 入力 diff --git a/ja/built-in-nodes/ExponentialScheduler.mdx b/ja/built-in-nodes/ExponentialScheduler.mdx index 65ba202eb..4a0a61500 100644 --- a/ja/built-in-nodes/ExponentialScheduler.mdx +++ b/ja/built-in-nodes/ExponentialScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ExponentialScheduler" icon: "circle" mode: wide --- + `ExponentialScheduler` ノードは、拡散サンプリングプロセスにおいて指数関数的なスケジュールに従ったシグマ値のシーケンスを生成するために設計されています。このノードは、拡散プロセスの各ステップで適用されるノイズレベルをカスタマイズ可能な方法で制御し、サンプリング動作の微調整を可能にします。 ## 入力 diff --git a/ja/built-in-nodes/ExtendIntermediateSigmas.mdx b/ja/built-in-nodes/ExtendIntermediateSigmas.mdx index 8b54a73cd..da226519e 100644 --- a/ja/built-in-nodes/ExtendIntermediateSigmas.mdx +++ b/ja/built-in-nodes/ExtendIntermediateSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ExtendIntermediateSigmas" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/FeatherMask.mdx b/ja/built-in-nodes/FeatherMask.mdx index f35b820fa..110b221b5 100644 --- a/ja/built-in-nodes/FeatherMask.mdx +++ b/ja/built-in-nodes/FeatherMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FeatherMask" icon: "circle" mode: wide --- + `FeatherMask`ノードは、指定されたマスクのエッジにフェザリング効果を適用し、各エッジからの指定距離に基づいてマスクのエッジの不透明度を滑らかに遷移させます。これにより、よりソフトでブレンドされたエッジ効果が生まれます。 ## 入力 diff --git a/ja/built-in-nodes/File3DToSplat.mdx b/ja/built-in-nodes/File3DToSplat.mdx index 921e1d081..2cf11e1ba 100644 --- a/ja/built-in-nodes/File3DToSplat.mdx +++ b/ja/built-in-nodes/File3DToSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "File3DToSplat" icon: "circle" mode: wide --- -# File3DToSplat このノードは、ガウシアンスプラットデータを含む3Dファイルを、ノードグラフで使用可能なガウシアンスプラット形式に変換します。PLY、SPLAT、KSPLAT、SPZのファイル形式に対応しており、ファイル形式はファイルの内容から自動的に検出されます。 diff --git a/ja/built-in-nodes/FlipSigmas.mdx b/ja/built-in-nodes/FlipSigmas.mdx index 52deefcb4..3d8dcf1eb 100644 --- a/ja/built-in-nodes/FlipSigmas.mdx +++ b/ja/built-in-nodes/FlipSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FlipSigmas" icon: "circle" mode: wide --- + `FlipSigmas`ノードは、拡散モデルで使用されるシグマ値のシーケンスを反転させ、元の最初の値がゼロの場合に非ゼロになるように調整することで操作するように設計されています。この操作は、ノイズレベルを逆順に適応させ、データからノイズを徐々に低減することで動作するモデルにおける生成プロセスを容易にするために重要です。 ## 入力 diff --git a/ja/built-in-nodes/Flux2ImageNode.mdx b/ja/built-in-nodes/Flux2ImageNode.mdx index d3b0de114..0924aaa79 100644 --- a/ja/built-in-nodes/Flux2ImageNode.mdx +++ b/ja/built-in-nodes/Flux2ImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Flux2ImageNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/Flux2Scheduler.mdx b/ja/built-in-nodes/Flux2Scheduler.mdx index 9ff227ee5..88c2b5b6e 100644 --- a/ja/built-in-nodes/Flux2Scheduler.mdx +++ b/ja/built-in-nodes/Flux2Scheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Flux2Scheduler" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Flux2Schedulerノードは、Fluxモデル専用に調整された、ノイズ除去プロセス用のノイズレベル（シグマ）のシーケンスを生成します。このノードは、ノイズ除去ステップ数とターゲット画像の寸法に基づいてスケジュールを計算し、画像生成中のノイズ除去の進行に影響を与えます。 diff --git a/ja/built-in-nodes/FluxDisableGuidance.mdx b/ja/built-in-nodes/FluxDisableGuidance.mdx index a17934616..8b76eb336 100644 --- a/ja/built-in-nodes/FluxDisableGuidance.mdx +++ b/ja/built-in-nodes/FluxDisableGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxDisableGuidance" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひご貢献ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxDisableGuidance/en.md) このノードは、Fluxおよび類似モデルにおけるガイダンス埋め込み機能を完全に無効化します。条件付けデータを入力として受け取り、ガイダンスコンポーネントをNoneに設定することで削除し、生成プロセスにおけるガイダンスベースの条件付けを実質的にオフにします。 diff --git a/ja/built-in-nodes/FluxEraseNode.mdx b/ja/built-in-nodes/FluxEraseNode.mdx index cbb4fd910..e20b55088 100644 --- a/ja/built-in-nodes/FluxEraseNode.mdx +++ b/ja/built-in-nodes/FluxEraseNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxEraseNode" icon: "circle" mode: wide --- -# Flux Erase ノード 画像からマスクされたオブジェクトを除去し、背景を再構築します。消去したい部分にマスクを描画すると、ノードがその領域を妥当な背景コンテンツで補完します。 diff --git a/ja/built-in-nodes/FluxGuidance.mdx b/ja/built-in-nodes/FluxGuidance.mdx index 4061fd778..bcaf803b7 100644 --- a/ja/built-in-nodes/FluxGuidance.mdx +++ b/ja/built-in-nodes/FluxGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxGuidance" icon: "circle" mode: wide --- + ## 入力 | パラメータ | 説明 | データ型 | diff --git a/ja/built-in-nodes/FluxKVCache.mdx b/ja/built-in-nodes/FluxKVCache.mdx index 03533d22e..0d99643bb 100644 --- a/ja/built-in-nodes/FluxKVCache.mdx +++ b/ja/built-in-nodes/FluxKVCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKVCache" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxKVCache/en.md) Flux KV Cacheノードは、Fluxファミリーモデルに対してKey-Value（KV）キャッシュ最適化を有効にします。この最適化は、参照画像を使用する際に特定の計算をキャッシュすることでパフォーマンスを向上させ、生成プロセスを高速化できます。 diff --git a/ja/built-in-nodes/FluxKontextImageScale.mdx b/ja/built-in-nodes/FluxKontextImageScale.mdx index 815c18129..ba9a85e68 100644 --- a/ja/built-in-nodes/FluxKontextImageScale.mdx +++ b/ja/built-in-nodes/FluxKontextImageScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKontextImageScale" icon: "circle" mode: wide --- + このノードは、入力画像のアスペクト比に基づいて、Lanczosアルゴリズムを使用してFlux Kontextモデルのトレーニング時に使用される最適なサイズに画像をスケーリングします。このノードは、大きなサイズの画像を入力する際に特に便利です。過剰に大きな入力は、モデルの出力品質の低下や、出力に複数の被写体が現れるなどの問題を引き起こす可能性があるためです。 ## 入力 diff --git a/ja/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx b/ja/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx index b8e70c437..74e2e094a 100644 --- a/ja/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx +++ b/ja/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKontextMultiReferenceLatentMethod" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxKontextMultiReferenceLatentMethod/en.md) FluxKontextMultiReferenceLatentMethod ノードは、特定の参照潜在変数メソッドを設定することで条件付けデータを変更します。選択されたメソッドを条件付け入力に追加し、その後の生成ステップで参照潜在変数がどのように処理されるかに影響を与えます。このノードは実験的機能としてマークされており、Flux 条件付けシステムの一部です。 diff --git a/ja/built-in-nodes/FluxProCannyNode.mdx b/ja/built-in-nodes/FluxProCannyNode.mdx index 38f00d288..ad229a7e4 100644 --- a/ja/built-in-nodes/FluxProCannyNode.mdx +++ b/ja/built-in-nodes/FluxProCannyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProCannyNode" icon: "circle" mode: wide --- + あなたは ComfyUI ノードドキュメントを英語から日本語に翻訳する技術翻訳の専門家です。 ## 翻訳ルール diff --git a/ja/built-in-nodes/FluxProDepthNode.mdx b/ja/built-in-nodes/FluxProDepthNode.mdx index 496702bdc..ea43e821e 100644 --- a/ja/built-in-nodes/FluxProDepthNode.mdx +++ b/ja/built-in-nodes/FluxProDepthNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProDepthNode" icon: "circle" mode: wide --- + このノードは、深度制御画像をガイドとして使用して画像を生成します。制御画像とテキストプロンプトを受け取り、制御画像の深度情報とプロンプトの説明の両方に従った新しい画像を作成します。このノードは外部APIに接続して画像生成処理を実行します。 ## 入力 diff --git a/ja/built-in-nodes/FluxProExpandNode.mdx b/ja/built-in-nodes/FluxProExpandNode.mdx index 3219cf6a5..d6974c9c7 100644 --- a/ja/built-in-nodes/FluxProExpandNode.mdx +++ b/ja/built-in-nodes/FluxProExpandNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProExpandNode" icon: "circle" mode: wide --- + このドキュメントは AI が生成したものです。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProExpandNode/en.md) プロンプトに基づいて画像を外側に拡張します。このノードは、画像の上、下、左、右にピクセルを追加し、指定されたテキスト説明に合致する新しいコンテンツを生成することで画像を拡張します。 diff --git a/ja/built-in-nodes/FluxProFillNode.mdx b/ja/built-in-nodes/FluxProFillNode.mdx index 6d5553e3c..12077201f 100644 --- a/ja/built-in-nodes/FluxProFillNode.mdx +++ b/ja/built-in-nodes/FluxProFillNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProFillNode" icon: "circle" mode: wide --- + 以下が翻訳です。 マスクとプロンプトに基づいて画像をインペイントします。このノードはFlux.1モデルを使用して、指定されたテキスト説明に従って画像のマスク領域を塗りつぶし、周囲の画像にマッチする新しいコンテンツを生成します。 diff --git a/ja/built-in-nodes/FluxProImageNode.mdx b/ja/built-in-nodes/FluxProImageNode.mdx index a81d66042..32ca4c46b 100644 --- a/ja/built-in-nodes/FluxProImageNode.mdx +++ b/ja/built-in-nodes/FluxProImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProImageNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 プロンプトと解像度に基づいて同期的に画像を生成します。このノードは、Flux 1.1 Pro モデルを使用し、API エンドポイントにリクエストを送信して、完全なレスポンスが返ってくるのを待ってから生成画像を出力します。 diff --git a/ja/built-in-nodes/FluxProUltraImageNode.mdx b/ja/built-in-nodes/FluxProUltraImageNode.mdx index 2bf9daeae..b47fdcc77 100644 --- a/ja/built-in-nodes/FluxProUltraImageNode.mdx +++ b/ja/built-in-nodes/FluxProUltraImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProUltraImageNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 プロンプトと解像度に基づいて、API経由でFlux Pro 1.1 Ultraを使用して画像を生成します。このノードは外部サービスに接続し、テキストによる説明と指定された寸法に従って画像を作成します。 diff --git a/ja/built-in-nodes/FluxVTONode.mdx b/ja/built-in-nodes/FluxVTONode.mdx index 37263a00a..6c451453f 100644 --- a/ja/built-in-nodes/FluxVTONode.mdx +++ b/ja/built-in-nodes/FluxVTONode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxVTONode" icon: "circle" mode: wide --- -# Flux バーチャル試着 このノードは、提供された衣服画像を人物に着せてバーチャル試着を実行します。BFL Flux VTO API を使用して、指定された衣服を着用した人物のリアルな画像を生成します。 diff --git a/ja/built-in-nodes/FrameInterpolate.mdx b/ja/built-in-nodes/FrameInterpolate.mdx index e5a689284..1e9f0af5a 100644 --- a/ja/built-in-nodes/FrameInterpolate.mdx +++ b/ja/built-in-nodes/FrameInterpolate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FrameInterpolate" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/FrameInterpolationModelLoader.mdx b/ja/built-in-nodes/FrameInterpolationModelLoader.mdx index 8a564f6f8..f1fd48320 100644 --- a/ja/built-in-nodes/FrameInterpolationModelLoader.mdx +++ b/ja/built-in-nodes/FrameInterpolationModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FrameInterpolationModelLoader" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/FreSca.mdx b/ja/built-in-nodes/FreSca.mdx index 1dfbb9b52..b176f15e8 100644 --- a/ja/built-in-nodes/FreSca.mdx +++ b/ja/built-in-nodes/FreSca.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreSca" icon: "circle" mode: wide --- + FreSca ノードは、サンプリングプロセス中にガイダンスに対して周波数依存のスケーリングを適用します。フーリエフィルタリングを使用してガイダンス信号を低周波成分と高周波成分に分離し、各周波数範囲に異なるスケーリング係数を適用した後、再結合します。これにより、生成出力のさまざまな側面に対するガイダンスの影響をより細かく制御できます。 ## 入力 diff --git a/ja/built-in-nodes/FreeU.mdx b/ja/built-in-nodes/FreeU.mdx index 53e7baedb..20fb8f3aa 100644 --- a/ja/built-in-nodes/FreeU.mdx +++ b/ja/built-in-nodes/FreeU.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreeU" icon: "circle" mode: wide --- + FreeUノードは、モデルの出力ブロックに周波数領域の変更を適用し、画像生成品質を向上させます。異なるチャンネルグループをスケーリングし、特定の特徴マップにフーリエフィルタリングを適用することで、生成プロセス中のモデルの動作を細かく制御できるようにします。 ## 入力 diff --git a/ja/built-in-nodes/FreeU_V2.mdx b/ja/built-in-nodes/FreeU_V2.mdx index be7049487..2657dc9e0 100644 --- a/ja/built-in-nodes/FreeU_V2.mdx +++ b/ja/built-in-nodes/FreeU_V2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreeU_V2" icon: "circle" mode: wide --- + FreeU_V2 ノードは、拡散モデルのU-Netアーキテクチャに周波数ベースの変更を適用することで、画像生成品質を向上させます。設定可能なスケーリング係数を使用して、異なるブロックの特徴チャンネルを調整し、追加のトレーニングを必要とせずに出力を改善します。 ## 入力 diff --git a/ja/built-in-nodes/GITSScheduler.mdx b/ja/built-in-nodes/GITSScheduler.mdx index c59c7f02e..714a1c828 100644 --- a/ja/built-in-nodes/GITSScheduler.mdx +++ b/ja/built-in-nodes/GITSScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GITSScheduler" icon: "circle" mode: wide --- + GITSSchedulerノードは、GITS（Generative Iterative Time Steps）サンプリング手法のためのノイズスケジュールシグマを生成します。係数パラメータとステップ数に基づいてシグマ値を計算し、オプションのノイズ除去係数によって使用する総ステップ数を減らすことができます。このノードは、事前定義されたノイズレベルと補間を使用して、最終的なシグマスケジュールを作成します。 ## 入力 diff --git a/ja/built-in-nodes/GLIGENLoader.mdx b/ja/built-in-nodes/GLIGENLoader.mdx index 01027e425..91ffdf160 100644 --- a/ja/built-in-nodes/GLIGENLoader.mdx +++ b/ja/built-in-nodes/GLIGENLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLIGENLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/gligen` フォルダ内にあるモデルを検出し、さらに `extra_model_paths.yaml` ファイルで設定された追加パスからもモデルを読み込みます。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、対応するフォルダからモデルファイルを読み込めるようにする必要があります。 `GLIGENLoader` ノードは、特殊な生成モデルである GLIGEN モデルを読み込むために設計されています。このノードは、指定されたパスからこれらのモデルを取得して初期化するプロセスを容易にし、後続の生成タスクに備えさせます。 diff --git a/ja/built-in-nodes/GLIGENTextBoxApply.mdx b/ja/built-in-nodes/GLIGENTextBoxApply.mdx index 181ac7980..aa2a8ac78 100644 --- a/ja/built-in-nodes/GLIGENTextBoxApply.mdx +++ b/ja/built-in-nodes/GLIGENTextBoxApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLIGENTextBoxApply" icon: "circle" mode: wide --- + `GLIGENTextBoxApply` ノードは、テキストベースの条件付けを生成モデルの入力に統合するために設計されています。具体的には、テキストボックスのパラメータを適用し、CLIPモデルを使用してそれらをエンコードします。このプロセスにより、空間情報とテキスト情報が条件付けに追加され、より正確でコンテキストを考慮した生成が可能になります。 ## 入力 diff --git a/ja/built-in-nodes/GLSLShader.mdx b/ja/built-in-nodes/GLSLShader.mdx index db14054fd..3406906f7 100644 --- a/ja/built-in-nodes/GLSLShader.mdx +++ b/ja/built-in-nodes/GLSLShader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLSLShader" icon: "circle" mode: wide --- + The **GLSL Shader** node lets you write custom fragment shaders in **GLSL ES 3.00** (WebGL 2.0 compatible) to process images directly on the GPU. You can create image effects like blurs, color grading, film grain, glow, and much more - all running at GPU speed. diff --git a/ja/built-in-nodes/GeminiImage2Node.mdx b/ja/built-in-nodes/GeminiImage2Node.mdx index 83fca4020..ea84c053f 100644 --- a/ja/built-in-nodes/GeminiImage2Node.mdx +++ b/ja/built-in-nodes/GeminiImage2Node.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiImage2Node" icon: "circle" mode: wide --- + 以下が翻訳結果です。 GeminiImage2Node は、Google の Vertex AI Gemini モデルを使用して画像を生成または編集します。テキストプロンプトと、オプションの参照画像やファイルを API に送信し、生成された画像やテキストによる説明を返します。 diff --git a/ja/built-in-nodes/GeminiImageNode.mdx b/ja/built-in-nodes/GeminiImageNode.mdx index 3dbfba248..017f2007b 100644 --- a/ja/built-in-nodes/GeminiImageNode.mdx +++ b/ja/built-in-nodes/GeminiImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiImageNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！ [GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImage/en.md) GeminiImageノードは、GoogleのGemini AIモデルからテキストと画像の応答を生成します。テキストプロンプト、画像、ファイルを含むマルチモーダル入力を提供することで、一貫性のあるテキストと画像の出力を作成できます。このノードは、最新のGeminiモデルとのすべてのAPI通信と応答解析を処理します。 diff --git a/ja/built-in-nodes/GeminiInputFiles.mdx b/ja/built-in-nodes/GeminiInputFiles.mdx index 7d241fb9a..067787a00 100644 --- a/ja/built-in-nodes/GeminiInputFiles.mdx +++ b/ja/built-in-nodes/GeminiInputFiles.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiInputFiles" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Gemini API で使用する入力ファイルを読み込み、フォーマットします。このノードを使用すると、テキスト（.txt）ファイルと PDF（.pdf）ファイルを Gemini モデルの入力コンテキストとして含めることができます。ファイルは API が必要とする適切な形式に変換され、複数のファイルを連結して 1 つのリクエストに含めることができます。 diff --git a/ja/built-in-nodes/GeminiNanoBanana2.mdx b/ja/built-in-nodes/GeminiNanoBanana2.mdx index 5b26de513..7ca4c6d59 100644 --- a/ja/built-in-nodes/GeminiNanoBanana2.mdx +++ b/ja/built-in-nodes/GeminiNanoBanana2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiNanoBanana2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 GeminiNanoBanana2 ノードは、Google の Vertex AI Gemini モデルを使用して画像を生成または編集します。テキストプロンプトと、必要に応じて参照画像やファイルを API に送信し、生成された画像とそれに付随するテキストを返します。 diff --git a/ja/built-in-nodes/GeminiNanoBanana2V2.mdx b/ja/built-in-nodes/GeminiNanoBanana2V2.mdx index 31bfeec02..451904daf 100644 --- a/ja/built-in-nodes/GeminiNanoBanana2V2.mdx +++ b/ja/built-in-nodes/GeminiNanoBanana2V2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiNanoBanana2V2" icon: "circle" mode: wide --- + このドキュメントは AI によって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiNanoBanana2V2/en.md) ## 概要 @@ -31,7 +32,7 @@ mode: wide | --- | --- | --- | | `IMAGE` | 生成または編集された画像です。 | IMAGE | | `思考画像` | モデルによって生成されたテキスト説明またはキャプションです。 | STRING | -| `thought_image` | モデルの思考プロセスからの最初の画像です。thinking_level が HIGH で、かつ IMAGE+TEXT モダリティの場合にのみ利用可能です。 | IMAGE | +| `思考画像` | モデルの思考プロセスからの最初の画像です。thinking_level が HIGH で、かつ IMAGE+TEXT モダリティの場合にのみ利用可能です。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiNanoBanana2V2/ja.md) diff --git a/ja/built-in-nodes/GeminiNode.mdx b/ja/built-in-nodes/GeminiNode.mdx index 0407602e0..64dda98fb 100644 --- a/ja/built-in-nodes/GeminiNode.mdx +++ b/ja/built-in-nodes/GeminiNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiNode" icon: "circle" mode: wide --- + このノードを使用すると、GoogleのGemini AIモデルと対話し、テキスト応答を生成できます。モデルにより関連性が高く意味のある応答を生成させるためのコンテキストとして、テキスト、画像、音声、動画、ファイルなど、複数の種類の入力を提供できます。このノードは、すべてのAPI通信と応答の解析を自動的に処理します。 ## 入力 diff --git a/ja/built-in-nodes/GeminiNodeV2.mdx b/ja/built-in-nodes/GeminiNodeV2.mdx index f283227fd..cda419c9f 100644 --- a/ja/built-in-nodes/GeminiNodeV2.mdx +++ b/ja/built-in-nodes/GeminiNodeV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GeminiNodeV2" icon: "circle" mode: wide --- -# Google Gemini Google の Gemini モデルを使用してテキスト応答を生成します。テキストプロンプトに加えて、オプションで1つ以上の画像、音声クリップ、動画、またはファイルをマルチモーダルコンテキストとして提供できます。 diff --git a/ja/built-in-nodes/GeminiVideoOmni.mdx b/ja/built-in-nodes/GeminiVideoOmni.mdx new file mode 100644 index 000000000..0d610c9a3 --- /dev/null +++ b/ja/built-in-nodes/GeminiVideoOmni.mdx @@ -0,0 +1,35 @@ +--- +title: "GeminiVideoOmni - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the GeminiVideoOmni node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "GeminiVideoOmni" +icon: "circle" +mode: wide +--- + +以下は、ご依頼いただいたComfyUIノードドキュメントの日本語訳です。 + +GoogleのGemini Omni Flashモデルを使用して、テキストプロンプトから音声付きの動画を生成します。オプションで参照画像や動画を提供し、結果をガイドまたは編集することもできます。希望する長さ（3～10秒）とアスペクト比（16：9または9：16）をプロンプトに直接記述してください。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `model` | 動画生成に使用するGemini動画モデルです。 | MODEL | はい | "Omni Flash" | +| `seed` | シードはノードを再実行するかどうかを制御します。シードに関わらず結果は非決定的です（デフォルト：42）。 | INT | はい | 0 ～ 2147483647 | +| `prompt` | 生成する動画を説明するテキストプロンプトです。 | STRING | はい | 空白除去後、最低1文字 | +| `images` | 動画生成をガイドするためのオプションの参照画像です。合計で最大14枚まで指定できます。 | IMAGE | いいえ | 複数画像可（最大14枚） | +| `videos` | 動画生成をガイドまたは編集するためのオプションの参照動画です。各動画は最大10秒で、最大3本まで指定できます。 | VIDEO | いいえ | 複数動画可（最大3本、各最大10秒） | +| `temperature` | 生成におけるランダム性を制御します（デフォルト：1.0）。 | FLOAT | いいえ | 0.0 ～ 2.0 | +| `top_p` | 核サンプリングのパラメータです（デフォルト：0.95）。 | FLOAT | いいえ | 0.0 ～ 1.0 | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `VIDEO` | Geminiモデルから生成された音声付き動画です。 | VIDEO | +| `STRING` | 推論や説明など、モデルからのテキスト応答です。 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiVideoOmni/ja.md) + +--- +**Source fingerprint (SHA-256):** `046842b7ec736283bba355aaa038b02fcf2416020f5f7aee7b0150d2a05bcbe6` diff --git a/ja/built-in-nodes/GenerateTracks.mdx b/ja/built-in-nodes/GenerateTracks.mdx index 6b45a4560..8e2099159 100644 --- a/ja/built-in-nodes/GenerateTracks.mdx +++ b/ja/built-in-nodes/GenerateTracks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GenerateTracks" icon: "circle" mode: wide --- + `GenerateTracks` ノードは、動画生成のための複数の並行モーションパスを作成します。開始点から終了点までの主要パスを定義し、そのパスに平行で等間隔に配置された一連のトラックを生成します。パスの形状（直線またはベジェ曲線）、パスに沿った移動速度、およびトラックを表示するフレームを制御できます。 ## 入力 @@ -33,7 +34,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | | `トラック長` | 生成されたパス座標と、すべてのフレームにわたるすべてのトラックの可視性情報を含むトラックオブジェクト。 | TRACKS | -| `track_length` | トラックが生成されたフレーム数。入力の `フレーム数` と一致します。 | INT | +| `トラック長` | トラックが生成されたフレーム数。入力の `フレーム数` と一致します。 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GenerateTracks/ja.md) diff --git a/ja/built-in-nodes/GetICLoRAParameters.mdx b/ja/built-in-nodes/GetICLoRAParameters.mdx index ed34a39b3..be303b04f 100644 --- a/ja/built-in-nodes/GetICLoRAParameters.mdx +++ b/ja/built-in-nodes/GetICLoRAParameters.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetICLoRAParameters" icon: "circle" mode: wide --- + ## 概要 このノードは、LoRAが読み込まれたモデルのメタデータからIC-LoRAパラメータを抽出します。safetensorsのメタデータを読み取り、参照ダウンスケール係数などの値を取得し、構造化されたパラメータオブジェクトとして出力します。この出力は、特別なガイド処理のためにLTXVAddGuideノードに接続することができます。 diff --git a/ja/built-in-nodes/GetImageSize.mdx b/ja/built-in-nodes/GetImageSize.mdx index 76dda59ec..1e7bba9b7 100644 --- a/ja/built-in-nodes/GetImageSize.mdx +++ b/ja/built-in-nodes/GetImageSize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetImageSize" icon: "circle" mode: wide --- + GetImageSize ノードは、入力画像から寸法とバッチ情報を抽出します。画像の幅、高さ、およびバッチサイズを返すとともに、この情報をノードインターフェース上に進捗テキストとして表示します。元の画像データは変更されずにそのまま通過します。 ## 入力 @@ -17,8 +18,8 @@ GetImageSize ノードは、入力画像から寸法とバッチ情報を抽出 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `height` | 入力画像の幅（ピクセル単位） | INT | -| `batch_size` | 入力画像の高さ（ピクセル単位） | INT | +| `width` | 入力画像の幅（ピクセル単位） | INT | +| `height` | 入力画像の高さ（ピクセル単位） | INT | | `batch_size` | バッチ内の画像数 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetImageSize/ja.md) diff --git a/ja/built-in-nodes/GetSplatCount.mdx b/ja/built-in-nodes/GetSplatCount.mdx index 9b6220181..cb0983bd7 100644 --- a/ja/built-in-nodes/GetSplatCount.mdx +++ b/ja/built-in-nodes/GetSplatCount.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GetSplatCount" icon: "circle" mode: wide --- -# スプラット数を取得 Get Splat Count ノードは、スプラットバッチ内のスプラット（ガウス点）の総数を返し、バッチ内のすべてのアイテムを合計します。元のスプラットデータは変更せずにそのまま渡し、含まれる個々のスプラットの数をカウントします。 @@ -19,8 +18,8 @@ Get Splat Count ノードは、スプラットバッチ内のスプラット（ | 出力名 | 説明 | データ型 | |-------------|-------------|-----------| -| `カウント` | 変更されずにそのまま渡される元のスプラットデータ | SPLAT | -| `count` | バッチ全体で合計されたスプラットの総数 | INT | +| `splat` | 変更されずにそのまま渡される元のスプラットデータ | SPLAT | +| `カウント` | バッチ全体で合計されたスプラットの総数 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetSplatCount/ja.md) diff --git a/ja/built-in-nodes/GetVideoComponents.mdx b/ja/built-in-nodes/GetVideoComponents.mdx index 9db7c277f..7925fa528 100644 --- a/ja/built-in-nodes/GetVideoComponents.mdx +++ b/ja/built-in-nodes/GetVideoComponents.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetVideoComponents" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetVideoComponents/en.md) Get Video Components ノードは、動画ファイルからすべての主要な要素を抽出します。動画を個別のフレームに分割し、オーディオトラックを抽出し、動画のフレームレート情報を提供します。これにより、各コンポーネントを独立して使用し、さらなる処理や分析を行うことができます。 @@ -19,8 +20,8 @@ Get Video Components ノードは、動画ファイルからすべての主要 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `オーディオ` | 動画から抽出された個別のフレームを、別々の画像として出力します。 | IMAGE | -| `fps` | 動画から抽出されたオーディオトラックです。 | AUDIO | +| `画像` | 動画から抽出された個別のフレームを、別々の画像として出力します。 | IMAGE | +| `オーディオ` | 動画から抽出されたオーディオトラックです。 | AUDIO | | `fps` | 動画のフレームレート（1秒あたりのフレーム数）です。 | FLOAT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetVideoComponents/ja.md) diff --git a/ja/built-in-nodes/GrokImageEditNode.mdx b/ja/built-in-nodes/GrokImageEditNode.mdx index 8613b0c97..c55c36216 100644 --- a/ja/built-in-nodes/GrokImageEditNode.mdx +++ b/ja/built-in-nodes/GrokImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokImageEditNode" icon: "circle" mode: wide --- + 以下が翻訳です。 Grok Image Edit ノードは、テキストプロンプトに基づいて既存の画像を修正します。Grok API を使用して、入力画像のバリエーションとなる1つ以上の新しい画像を、あなたの説明に従って生成します。 diff --git a/ja/built-in-nodes/GrokImageEditNodeV2.mdx b/ja/built-in-nodes/GrokImageEditNodeV2.mdx index c608e49c3..331b5643e 100644 --- a/ja/built-in-nodes/GrokImageEditNodeV2.mdx +++ b/ja/built-in-nodes/GrokImageEditNodeV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokImageEditNodeV2" icon: "circle" mode: wide --- + ## 概要 テキストプロンプトに基づいて既存の画像を編集します。このノードは画像とテキスト説明をGrok APIに送信し、指示に従って画像を編集した結果を返します。 diff --git a/ja/built-in-nodes/GrokImageNode.mdx b/ja/built-in-nodes/GrokImageNode.mdx index d5fb99b7b..541686fa8 100644 --- a/ja/built-in-nodes/GrokImageNode.mdx +++ b/ja/built-in-nodes/GrokImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokImageNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Grok Image ノードは、Grok AI モデルを使用して、テキスト説明に基づき1つ以上の画像を生成します。プロンプトを外部サービスに送信し、生成された画像をワークフローで使用可能なテンソルとして返します。 diff --git a/ja/built-in-nodes/GrokVideoEditNode.mdx b/ja/built-in-nodes/GrokVideoEditNode.mdx index 9c36615cd..6740f0fe1 100644 --- a/ja/built-in-nodes/GrokVideoEditNode.mdx +++ b/ja/built-in-nodes/GrokVideoEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoEditNode" icon: "circle" mode: wide --- + このノードは、Grok API を使用して、テキストプロンプトに基づいて既存の動画を編集します。動画をアップロードし、AI モデルにリクエストを送信して説明に従って動画を変更し、新しく生成された動画を返します。 ## 入力 diff --git a/ja/built-in-nodes/GrokVideoExtendNode.mdx b/ja/built-in-nodes/GrokVideoExtendNode.mdx index ff52db645..00ccbffd4 100644 --- a/ja/built-in-nodes/GrokVideoExtendNode.mdx +++ b/ja/built-in-nodes/GrokVideoExtendNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoExtendNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Grok Video Extend ノードは、AI モデルを使用して既存のビデオのシームレスな続きを生成します。短いビデオと、次に何が起こるべきかを説明するテキストプロンプトを入力すると、ノードは元のビデオに続く新しいビデオクリップを生成します。 diff --git a/ja/built-in-nodes/GrokVideoNode.mdx b/ja/built-in-nodes/GrokVideoNode.mdx index 6a588bd6d..596bf0367 100644 --- a/ja/built-in-nodes/GrokVideoNode.mdx +++ b/ja/built-in-nodes/GrokVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoNode" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- diff --git a/ja/built-in-nodes/GrokVideoReferenceNode.mdx b/ja/built-in-nodes/GrokVideoReferenceNode.mdx index 5748b9e99..bb07ef553 100644 --- a/ja/built-in-nodes/GrokVideoReferenceNode.mdx +++ b/ja/built-in-nodes/GrokVideoReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoReferenceNode" icon: "circle" mode: wide --- + 以下は、提供された英語ドキュメントを日本語に翻訳したものです。 このドキュメントは AI によって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoReferenceNode/en.md) diff --git a/ja/built-in-nodes/GrowMask.mdx b/ja/built-in-nodes/GrowMask.mdx index ecd642ecd..929d36cf1 100644 --- a/ja/built-in-nodes/GrowMask.mdx +++ b/ja/built-in-nodes/GrowMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrowMask" icon: "circle" mode: wide --- + `GrowMask` ノードは、指定されたマスクのサイズを拡大または縮小し、必要に応じて角にテーパー効果を適用するように設計されています。この機能は、画像処理タスクにおいてマスクの境界を動的に調整し、関心領域をより柔軟かつ精密に制御するために重要です。 ## 入力 diff --git a/ja/built-in-nodes/HappyHorseImageToVideoApi.mdx b/ja/built-in-nodes/HappyHorseImageToVideoApi.mdx index 2f9695574..418d8d5bc 100644 --- a/ja/built-in-nodes/HappyHorseImageToVideoApi.mdx +++ b/ja/built-in-nodes/HappyHorseImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseImageToVideoApi" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- diff --git a/ja/built-in-nodes/HappyHorseReferenceVideoApi.mdx b/ja/built-in-nodes/HappyHorseReferenceVideoApi.mdx index 02568a0de..4de5900dc 100644 --- a/ja/built-in-nodes/HappyHorseReferenceVideoApi.mdx +++ b/ja/built-in-nodes/HappyHorseReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseReferenceVideoApi" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/HappyHorseTextToVideoApi.mdx b/ja/built-in-nodes/HappyHorseTextToVideoApi.mdx index bfde9f8a8..34e9d180b 100644 --- a/ja/built-in-nodes/HappyHorseTextToVideoApi.mdx +++ b/ja/built-in-nodes/HappyHorseTextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseTextToVideoApi" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/HappyHorseVideoEditApi.mdx b/ja/built-in-nodes/HappyHorseVideoEditApi.mdx index 92a0c51b7..49918aeaf 100644 --- a/ja/built-in-nodes/HappyHorseVideoEditApi.mdx +++ b/ja/built-in-nodes/HappyHorseVideoEditApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseVideoEditApi" icon: "circle" mode: wide --- + 以下は、指定された英語ドキュメントを日本語に翻訳したものです。 ## 概要 diff --git a/ja/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx b/ja/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx index 7fe5c9086..18787e4b4 100644 --- a/ja/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx +++ b/ja/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HiDreamO1PatchSeamSmoothing" icon: "circle" mode: wide --- + ## 概要 このノードは、サンプリングプロセスの後半において、複数のシフトされたパッチグリッド位置でモデルの出力を平均化することで、HiDream-O1モデルが生成した画像の目に見える継ぎ目を低減します。画像の位置合わせをわずかに変えてモデルを複数回実行し、結果をブレンドすることで、パッチ境界に現れるグリッド状のアーティファクトを打ち消す仕組みです。 diff --git a/ja/built-in-nodes/HiDreamO1ReferenceImages.mdx b/ja/built-in-nodes/HiDreamO1ReferenceImages.mdx index 559389c19..1120f08ae 100644 --- a/ja/built-in-nodes/HiDreamO1ReferenceImages.mdx +++ b/ja/built-in-nodes/HiDreamO1ReferenceImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HiDreamO1ReferenceImages" icon: "circle" mode: wide --- + ## 概要 ポジティブおよびネガティブの両方のコンディショニングに参照画像を添付します。このノードを使用すると、1つ以上の参照画像を提供して画像生成プロセスをガイドできます。指示に基づく編集や、被写体駆動型のパーソナライゼーションに使用されます。 @@ -23,7 +24,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 参照画像が添付されたポジティブコンディショニングです。 | CONDITIONING | +| `ポジティブ` | 参照画像が添付されたポジティブコンディショニングです。 | CONDITIONING | | `ネガティブ` | 参照画像が添付されたネガティブコンディショニングです。 | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HiDreamO1ReferenceImages/ja.md) diff --git a/ja/built-in-nodes/HitPawGeneralImageEnhance.mdx b/ja/built-in-nodes/HitPawGeneralImageEnhance.mdx index 6bf0b8263..c26620661 100644 --- a/ja/built-in-nodes/HitPawGeneralImageEnhance.mdx +++ b/ja/built-in-nodes/HitPawGeneralImageEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HitPawGeneralImageEnhance" icon: "circle" mode: wide --- + このノードは、低解像度の画像を超解像にアップスケールし、アーティファクトやノイズを除去することで画質を向上させます。外部APIを使用して画像を処理し、処理制限内に収まるように入力サイズを自動調整できます。最大出力サイズは4メガピクセルです。 ## 入力 diff --git a/ja/built-in-nodes/HitPawVideoEnhance.mdx b/ja/built-in-nodes/HitPawVideoEnhance.mdx index 18933da1c..e2de85f1c 100644 --- a/ja/built-in-nodes/HitPawVideoEnhance.mdx +++ b/ja/built-in-nodes/HitPawVideoEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HitPawVideoEnhance" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/Hunyuan3Dv2Conditioning.mdx b/ja/built-in-nodes/Hunyuan3Dv2Conditioning.mdx index 72f112dbe..e1fad7eb7 100644 --- a/ja/built-in-nodes/Hunyuan3Dv2Conditioning.mdx +++ b/ja/built-in-nodes/Hunyuan3Dv2Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Hunyuan3Dv2Conditioning" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Hunyuan3Dv2Conditioning ノードは、CLIP ビジョン出力を処理して 3D モデル用の条件付けデータを生成します。ビジョン出力から最後の隠れ状態の埋め込みを抽出し、ポジティブ条件付けとネガティブ条件付けのペアを作成します。ポジティブ条件付けは実際の埋め込みを使用し、ネガティブ条件付けは同じ形状のゼロ値埋め込みを使用します。 @@ -19,7 +20,7 @@ Hunyuan3Dv2Conditioning ノードは、CLIP ビジョン出力を処理して 3D | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `negative` | CLIP ビジョン埋め込みを含むポジティブ条件付けデータ | CONDITIONING | +| `positive` | CLIP ビジョン埋め込みを含むポジティブ条件付けデータ | CONDITIONING | | `negative` | ポジティブ条件付けの形状に一致するゼロ値埋め込みを含むネガティブ条件付けデータ | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2Conditioning/ja.md) diff --git a/ja/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx b/ja/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx index 02741ef8c..baccb35e3 100644 --- a/ja/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx +++ b/ja/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Hunyuan3Dv2ConditioningMultiView" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善のご提案がございましたら、ぜひご協力ください！ [GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2ConditioningMultiView/en.md) Hunyuan3Dv2ConditioningMultiView ノードは、3D動画生成のためのマルチビューCLIPビジョン埋め込みを処理します。オプションで正面、左、背面、右の各ビュー埋め込みを受け取り、それらを位置エンコーディングと組み合わせて、動画モデル用の条件付けデータを作成します。このノードは、結合された埋め込みからのポジティブ条件付けと、ゼロ値によるネガティブ条件付けの両方を出力します。 @@ -24,7 +25,7 @@ Hunyuan3Dv2ConditioningMultiView ノードは、3D動画生成のためのマル | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `negative` | 位置エンコーディングを含む結合されたマルチビュー埋め込みによるポジティブ条件付け | CONDITIONING | +| `positive` | 位置エンコーディングを含む結合されたマルチビュー埋め込みによるポジティブ条件付け | CONDITIONING | | `negative` | 対照学習のためのゼロ値によるネガティブ条件付け | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2ConditioningMultiView/ja.md) diff --git a/ja/built-in-nodes/HunyuanImageToVideo.mdx b/ja/built-in-nodes/HunyuanImageToVideo.mdx index ed778dd07..a895ad768 100644 --- a/ja/built-in-nodes/HunyuanImageToVideo.mdx +++ b/ja/built-in-nodes/HunyuanImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanImageToVideo" icon: "circle" mode: wide --- + このドキュメントは AI が生成しました。誤りや改善の提案がありましたら、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanImageToVideo/en.md) HunyuanImageToVideo ノードは、Hunyuan ビデオモデルを使用して画像をビデオの潜在表現に変換します。このノードは、条件付け入力とオプションの開始画像を受け取り、ビデオ生成モデルでさらに処理できるビデオ潜在表現を生成します。開始画像がビデオ生成プロセスに与える影響を制御するために、異なるガイダンスタイプをサポートしています。 @@ -32,8 +33,8 @@ HunyuanImageToVideo ノードは、Hunyuan ビデオモデルを使用して画 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `潜在` | `開始画像` が指定された場合に画像ガイダンスが適用された、変更されたポジティブ条件付け | CONDITIONING | -| `latent` | ビデオ生成モデルによるさらなる処理の準備ができたビデオ潜在表現 | LATENT | +| `ポジティブ` | `開始画像` が指定された場合に画像ガイダンスが適用された、変更されたポジティブ条件付け | CONDITIONING | +| `潜在` | ビデオ生成モデルによるさらなる処理の準備ができたビデオ潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanImageToVideo/ja.md) diff --git a/ja/built-in-nodes/HunyuanRefinerLatent.mdx b/ja/built-in-nodes/HunyuanRefinerLatent.mdx index 19c12fb45..defc40c97 100644 --- a/ja/built-in-nodes/HunyuanRefinerLatent.mdx +++ b/ja/built-in-nodes/HunyuanRefinerLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanRefinerLatent" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- @@ -24,8 +25,8 @@ HunyuanRefinerLatent ノードは、リファインメント処理のために c | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | ノイズ拡張と潜在画像の結合が適用された、処理済みのポジティブ conditioning | CONDITIONING | -| `潜在表現` | ノイズ拡張と潜在画像の結合が適用された、処理済みのネガティブ conditioning | CONDITIONING | +| `ポジティブ` | ノイズ拡張と潜在画像の結合が適用された、処理済みのポジティブ conditioning | CONDITIONING | +| `ネガティブ` | ノイズ拡張と潜在画像の結合が適用された、処理済みのネガティブ conditioning | CONDITIONING | | `潜在表現` | 次元 [batch_size, 32, height, width, channels] を持つ新しい潜在変数出力 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanRefinerLatent/ja.md) diff --git a/ja/built-in-nodes/HunyuanVideo15ImageToVideo.mdx b/ja/built-in-nodes/HunyuanVideo15ImageToVideo.mdx index d42fc56c2..86122a3e5 100644 --- a/ja/built-in-nodes/HunyuanVideo15ImageToVideo.mdx +++ b/ja/built-in-nodes/HunyuanVideo15ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15ImageToVideo" icon: "circle" mode: wide --- + 以下が翻訳結果です。 HunyuanVideo15ImageToVideo ノードは、HunyuanVideo 1.5 モデルに基づいて動画生成のための条件付け（conditioning）および潜在空間データを準備します。このノードは動画シーケンスの初期潜在表現を作成し、オプションで開始画像や CLIP ビジョン出力を統合して生成プロセスをガイドします。 @@ -29,8 +30,8 @@ HunyuanVideo15ImageToVideo ノードは、HunyuanVideo 1.5 モデルに基づい | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 変更されたポジティブ条件付けです。エンコードされた開始画像や CLIP ビジョン出力が含まれる場合があります。 | CONDITIONING | -| `latent` | 変更されたネガティブ条件付けです。エンコードされた開始画像や CLIP ビジョン出力が含まれる場合があります。 | CONDITIONING | +| `ポジティブ` | 変更されたポジティブ条件付けです。エンコードされた開始画像や CLIP ビジョン出力が含まれる場合があります。 | CONDITIONING | +| `ネガティブ` | 変更されたネガティブ条件付けです。エンコードされた開始画像や CLIP ビジョン出力が含まれる場合があります。 | CONDITIONING | | `latent` | 指定されたバッチサイズ、動画長、幅、高さに合わせて次元が設定された空の潜在テンソルです。 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15ImageToVideo/ja.md) diff --git a/ja/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx b/ja/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx index 0e8f998c0..63ee68301 100644 --- a/ja/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx +++ b/ja/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15LatentUpscaleWithModel" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善のご提案がございましたら、ぜひご貢献ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15LatentUpscaleWithModel/en.md) Hunyuan Video 15 Latent Upscale With Model ノードは、潜在画像表現の解像度を向上させます。まず、選択した補間方式を使用して潜在サンプルを指定サイズにアップスケールし、その後、専用の Hunyuan Video 1.5 アップスケールモデルを使用してアップスケール結果を精緻化し、品質を改善します。 diff --git a/ja/built-in-nodes/HunyuanVideo15SuperResolution.mdx b/ja/built-in-nodes/HunyuanVideo15SuperResolution.mdx index 88962905f..4d4420f78 100644 --- a/ja/built-in-nodes/HunyuanVideo15SuperResolution.mdx +++ b/ja/built-in-nodes/HunyuanVideo15SuperResolution.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15SuperResolution" icon: "circle" mode: wide --- + 以下が翻訳結果です。 HunyuanVideo15SuperResolution ノードは、ビデオの超解像処理のための conditioning データを準備します。このノードは、ビデオの潜在表現と、オプションで開始画像を受け取り、それらをノイズ拡張データおよび CLIP ビジョンデータとともにパッケージ化し、モデルが高解像度出力を生成するために使用できる形式に変換します。 @@ -27,8 +28,8 @@ HunyuanVideo15SuperResolution ノードは、ビデオの超解像処理のた | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 変更されたポジティブ conditioning です。連結された潜在データ、ノイズ拡張、およびオプションの CLIP ビジョンデータが含まれます。 | CONDITIONING | -| `潜在` | 変更されたネガティブ conditioning です。連結された潜在データ、ノイズ拡張、およびオプションの CLIP ビジョンデータが含まれます。 | CONDITIONING | +| `ポジティブ` | 変更されたポジティブ conditioning です。連結された潜在データ、ノイズ拡張、およびオプションの CLIP ビジョンデータが含まれます。 | CONDITIONING | +| `ネガティブ` | 変更されたネガティブ conditioning です。連結された潜在データ、ノイズ拡張、およびオプションの CLIP ビジョンデータが含まれます。 | CONDITIONING | | `潜在` | 入力された潜在データがそのまま出力されます。 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15SuperResolution/ja.md) diff --git a/ja/built-in-nodes/HyperTile.mdx b/ja/built-in-nodes/HyperTile.mdx index b915a203f..a0bfaea95 100644 --- a/ja/built-in-nodes/HyperTile.mdx +++ b/ja/built-in-nodes/HyperTile.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HyperTile" icon: "circle" mode: wide --- + 以下が翻訳結果です。 HyperTile ノードは、拡散モデルのアテンション機構にタイル分割手法を適用し、画像生成時のメモリ使用量を最適化します。潜在空間をより小さなタイルに分割して個別に処理し、その後結果を再結合します。これにより、メモリ不足を起こさずに、より大きな画像サイズでの作業が可能になります。 diff --git a/ja/built-in-nodes/HypernetworkLoader.mdx b/ja/built-in-nodes/HypernetworkLoader.mdx index bd59f9937..3c44fad39 100644 --- a/ja/built-in-nodes/HypernetworkLoader.mdx +++ b/ja/built-in-nodes/HypernetworkLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HypernetworkLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/hypernetworks` フォルダ内のモデルを検出し、さらに `extra_model_paths.yaml` ファイルで設定された追加パスからもモデルを読み込みます。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、対応するフォルダからモデルファイルを読み込ませる必要があります。 HypernetworkLoader ノードは、ハイパーネットワークを適用することで、指定されたモデルの機能を強化または変更するように設計されています。指定されたハイパーネットワークを読み込み、それをモデルに適用し、強度パラメータに基づいてモデルの動作やパフォーマンスを変更する可能性があります。このプロセスにより、モデルのアーキテクチャやパラメータを動的に調整でき、より柔軟で適応性の高い AI システムを実現します。 diff --git a/ja/built-in-nodes/Ideogram4Scheduler.mdx b/ja/built-in-nodes/Ideogram4Scheduler.mdx index 442edc55f..8bccf4acd 100644 --- a/ja/built-in-nodes/Ideogram4Scheduler.mdx +++ b/ja/built-in-nodes/Ideogram4Scheduler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Ideogram4Scheduler" icon: "circle" mode: wide --- -# Ideogram 4 スケジューラー Ideogram 4 スケジューラーノードは、Ideogram 4 リファレンススケジュールに基づいて、拡散サンプリングプロセス用のシグマ値（ノイズレベル）のシーケンスを生成します。画像の寸法に適応し、統計パラメータを通じて微調整が可能なカスタムノイズスケジュールを作成します。 diff --git a/ja/built-in-nodes/IdeogramV1.mdx b/ja/built-in-nodes/IdeogramV1.mdx index 9bd15ab01..1bde6cc88 100644 --- a/ja/built-in-nodes/IdeogramV1.mdx +++ b/ja/built-in-nodes/IdeogramV1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "IdeogramV1" icon: "circle" mode: wide --- + ## 概要 IdeogramV1 ノードは、API を通じて Ideogram V1 モデルを使用して画像を生成します。テキストプロンプトと各種生成設定を受け取り、入力に基づいて1つ以上の画像を作成します。このノードは、異なるアスペクト比や生成モードをサポートしており、出力をカスタマイズできます。 diff --git a/ja/built-in-nodes/IdeogramV2.mdx b/ja/built-in-nodes/IdeogramV2.mdx index e1b0105d5..8c33a76f9 100644 --- a/ja/built-in-nodes/IdeogramV2.mdx +++ b/ja/built-in-nodes/IdeogramV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "IdeogramV2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/IdeogramV3.mdx b/ja/built-in-nodes/IdeogramV3.mdx index c52fd14be..fbfdad68f 100644 --- a/ja/built-in-nodes/IdeogramV3.mdx +++ b/ja/built-in-nodes/IdeogramV3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "IdeogramV3" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Ideogram V3 ノードは、Ideogram V3 モデルを使用して画像を生成します。テキストプロンプトからの通常の画像生成と、画像とマスクの両方が提供された場合の画像編集の両方をサポートしています。このノードは、アスペクト比、解像度、生成速度、およびオプションのキャラクター参照画像に関するさまざまな制御機能を提供します。 diff --git a/ja/built-in-nodes/IdeogramV4.mdx b/ja/built-in-nodes/IdeogramV4.mdx index aa9f884f9..39e1a4d68 100644 --- a/ja/built-in-nodes/IdeogramV4.mdx +++ b/ja/built-in-nodes/IdeogramV4.mdx @@ -5,7 +5,6 @@ sidebarTitle: "IdeogramV4" icon: "circle" mode: wide --- -# Ideogram V4 テキストプロンプトからIdeogram 4.0モデルを使用して画像を生成します。このノードは、テキストによる説明をIdeogram APIに送信し、生成された画像を出力テンソルとして返します。 diff --git a/ja/built-in-nodes/ImageAddNoise.mdx b/ja/built-in-nodes/ImageAddNoise.mdx index 16c9110da..bf9db7098 100644 --- a/ja/built-in-nodes/ImageAddNoise.mdx +++ b/ja/built-in-nodes/ImageAddNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageAddNoise" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ImageAddNoise ノードは、入力画像にランダムノイズを追加します。指定されたランダムシードを使用して一貫性のあるノイズパターンを生成し、ノイズ効果の強度を制御できます。出力画像は入力と同じ寸法を維持しますが、視覚的なテクスチャが追加されます。 diff --git a/ja/built-in-nodes/ImageBatch.mdx b/ja/built-in-nodes/ImageBatch.mdx index 512b5aaa9..0b37c4f99 100644 --- a/ja/built-in-nodes/ImageBatch.mdx +++ b/ja/built-in-nodes/ImageBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBatch" icon: "circle" mode: wide --- + `ImageBatch`ノードは、2つの画像を1つのバッチに結合するために設計されています。画像の寸法が一致しない場合、結合前に2番目の画像を自動的に1番目の画像の寸法に合わせて再スケーリングします。 ## 入力 diff --git a/ja/built-in-nodes/ImageBlend.mdx b/ja/built-in-nodes/ImageBlend.mdx index 4113dabb6..cd7fd61ef 100644 --- a/ja/built-in-nodes/ImageBlend.mdx +++ b/ja/built-in-nodes/ImageBlend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBlend" icon: "circle" mode: wide --- + `ImageBlend`ノードは、指定されたブレンドモードとブレンド係数に基づいて2つの画像をブレンドするように設計されています。ノーマル、乗算、スクリーン、オーバーレイ、ソフトライト、差分など、さまざまなブレンドモードをサポートしており、多彩な画像操作と合成技法を可能にします。このノードは、2つの画像レイヤー間の視覚的な相互作用を調整して合成画像を作成するために不可欠です。 ## 入力 diff --git a/ja/built-in-nodes/ImageBlur.mdx b/ja/built-in-nodes/ImageBlur.mdx index 6095069bd..e025de850 100644 --- a/ja/built-in-nodes/ImageBlur.mdx +++ b/ja/built-in-nodes/ImageBlur.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBlur" icon: "circle" mode: wide --- + `ImageBlur`ノードは、画像にガウシアンブラーを適用し、エッジを滑らかにしてディテールやノイズを低減します。パラメータを通じてブラーの強度と広がりを制御できます。 ## 入力 diff --git a/ja/built-in-nodes/ImageColorToMask.mdx b/ja/built-in-nodes/ImageColorToMask.mdx index 60d9f5c3d..6ee591af2 100644 --- a/ja/built-in-nodes/ImageColorToMask.mdx +++ b/ja/built-in-nodes/ImageColorToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageColorToMask" icon: "circle" mode: wide --- + `ImageColorToMask` ノードは、画像内の指定された色をマスクに変換するために設計されています。このノードは画像と対象の色を処理し、指定された色が強調表示されたマスクを生成することで、色ベースのセグメンテーションやオブジェクトの分離といった操作を容易にします。 ## 入力 diff --git a/ja/built-in-nodes/ImageCompare.mdx b/ja/built-in-nodes/ImageCompare.mdx index 88cf43a39..fd061cf50 100644 --- a/ja/built-in-nodes/ImageCompare.mdx +++ b/ja/built-in-nodes/ImageCompare.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCompare" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご貢献ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageCompare/en.md) Image Compareノードは、ドラッグ可能なスライダーを使用して2つの画像を並べて比較するためのビジュアルインターフェースを提供します。これは出力ノードとして設計されており、他のノードにデータを渡すのではなく、ユーザーインターフェースに直接画像を表示して検査できるようにします。 diff --git a/ja/built-in-nodes/ImageCompositeMasked.mdx b/ja/built-in-nodes/ImageCompositeMasked.mdx index 6ca44b51d..10d155416 100644 --- a/ja/built-in-nodes/ImageCompositeMasked.mdx +++ b/ja/built-in-nodes/ImageCompositeMasked.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCompositeMasked" icon: "circle" mode: wide --- + `ImageCompositeMasked` ノードは、画像を合成するためのもので、ソース画像を指定された座標でデスティネーション画像に重ね合わせることができます。オプションでリサイズやマスク処理も可能です。 ## 入力 diff --git a/ja/built-in-nodes/ImageCrop.mdx b/ja/built-in-nodes/ImageCrop.mdx index dd992896c..ec4639e9a 100644 --- a/ja/built-in-nodes/ImageCrop.mdx +++ b/ja/built-in-nodes/ImageCrop.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCrop" icon: "circle" mode: wide --- + `ImageCrop` ノードは、指定された x 座標と y 座標を起点として、画像を指定された幅と高さに切り抜く（クロップする）ために設計されています。この機能は、画像の特定の領域に焦点を当てたり、画像サイズを特定の要件に合わせて調整したりするために不可欠です。 ## 入力 diff --git a/ja/built-in-nodes/ImageCropV2.mdx b/ja/built-in-nodes/ImageCropV2.mdx index 38e812429..cfda0b155 100644 --- a/ja/built-in-nodes/ImageCropV2.mdx +++ b/ja/built-in-nodes/ImageCropV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCropV2" icon: "circle" mode: wide --- + このドキュメントは AI が生成しました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageCropV2/en.md) 画像クロップノードは、入力画像から長方形の領域を抽出します。保持する領域を、その左上隅の座標と幅および高さを指定して定義します。ノードは、元の画像のクロップされた部分を返します。 diff --git a/ja/built-in-nodes/ImageDeduplication.mdx b/ja/built-in-nodes/ImageDeduplication.mdx index 68f0f2774..d60dec64d 100644 --- a/ja/built-in-nodes/ImageDeduplication.mdx +++ b/ja/built-in-nodes/ImageDeduplication.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageDeduplication" icon: "circle" mode: wide --- + このノードは、バッチ内の重複または非常に類似した画像を削除します。各画像の視覚的な内容に基づいた単純な数値フィンガープリントである知覚ハッシュを作成し、それらを比較することで機能します。設定された閾値よりもハッシュが類似している画像は重複とみなされ、フィルタリングで除外されます。 ## 入力 diff --git a/ja/built-in-nodes/ImageFlip.mdx b/ja/built-in-nodes/ImageFlip.mdx index e8d6235d5..e89652872 100644 --- a/ja/built-in-nodes/ImageFlip.mdx +++ b/ja/built-in-nodes/ImageFlip.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageFlip" icon: "circle" mode: wide --- + ImageFlipノードは、画像を異なる軸に沿って反転させます。x軸に沿った垂直方向の反転、またはy軸に沿った水平方向の反転が可能です。このノードは、選択された方法に基づいて反転処理を行うために、torch.flip操作を使用します。 ## 入力 diff --git a/ja/built-in-nodes/ImageFromBatch.mdx b/ja/built-in-nodes/ImageFromBatch.mdx index 34bc2583a..97e03292a 100644 --- a/ja/built-in-nodes/ImageFromBatch.mdx +++ b/ja/built-in-nodes/ImageFromBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageFromBatch" icon: "circle" mode: wide --- + `ImageFromBatch` ノードは、指定されたインデックスと長さに基づいて、バッチから特定の画像セグメントを抽出するために設計されています。これにより、バッチ処理された画像をより細かく制御し、大きなバッチ内の個別またはサブセットの画像に対して操作を実行できます。 ## 入力 diff --git a/ja/built-in-nodes/ImageGrid.mdx b/ja/built-in-nodes/ImageGrid.mdx index 96755bcac..fca8ec732 100644 --- a/ja/built-in-nodes/ImageGrid.mdx +++ b/ja/built-in-nodes/ImageGrid.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageGrid" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageGrid/en.md) 画像グリッドノードは、複数の画像を1つの整理されたグリッドまたはコラージュに結合します。画像のリストを受け取り、指定された列数に配置し、各画像を定義されたセルサイズに合わせてリサイズし、必要に応じて画像間にパディングを追加します。結果として、すべての入力画像がグリッドレイアウトで配置された1つの新しい画像が生成されます。 @@ -23,7 +24,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `image` | すべての入力画像がグリッド状に配置された、単一の出力画像。 | IMAGE | +| `画像` | すべての入力画像がグリッド状に配置された、単一の出力画像。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageGrid/ja.md) diff --git a/ja/built-in-nodes/ImageHistogram.mdx b/ja/built-in-nodes/ImageHistogram.mdx index be4bfb9ab..0eb3f7984 100644 --- a/ja/built-in-nodes/ImageHistogram.mdx +++ b/ja/built-in-nodes/ImageHistogram.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageHistogram" icon: "circle" mode: wide --- + ImageHistogram ノードは、入力画像の色分布を分析します。各ピクセルの強度値ごとに、画像内にいくつのピクセルが存在するかを示すグラフ（ヒストグラム）を計算し、複数のヒストグラムを出力します。赤、緑、青の各色チャンネルごとのヒストグラム、RGB合成ヒストグラム、および標準的な輝度計算式に基づく輝度ヒストグラムを生成します。 ## 入力 @@ -17,11 +18,11 @@ ImageHistogram ノードは、入力画像の色分布を分析します。各 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `輝度` | 赤、緑、青の各チャンネルにおける平均ピクセル強度を表す合成ヒストグラムです。 | HISTOGRAM | -| `赤` | ITU-R BT.709標準輝度計算式を用いて計算された、画像の知覚的な明るさのヒストグラムです。 | HISTOGRAM | -| `緑` | 赤色チャンネルにおけるピクセル強度の分布を示すヒストグラムです。 | HISTOGRAM | -| `青` | 緑色チャンネルにおけるピクセル強度の分布を示すヒストグラムです。 | HISTOGRAM | -| `blue` | 青色チャンネルにおけるピクセル強度の分布を示すヒストグラムです。 | HISTOGRAM | +| `RGB` | 赤、緑、青の各チャンネルにおける平均ピクセル強度を表す合成ヒストグラムです。 | HISTOGRAM | +| `輝度` | ITU-R BT.709標準輝度計算式を用いて計算された、画像の知覚的な明るさのヒストグラムです。 | HISTOGRAM | +| `赤` | 赤色チャンネルにおけるピクセル強度の分布を示すヒストグラムです。 | HISTOGRAM | +| `緑` | 緑色チャンネルにおけるピクセル強度の分布を示すヒストグラムです。 | HISTOGRAM | +| `青` | 青色チャンネルにおけるピクセル強度の分布を示すヒストグラムです。 | HISTOGRAM | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageHistogram/ja.md) diff --git a/ja/built-in-nodes/ImageInvert.mdx b/ja/built-in-nodes/ImageInvert.mdx index 0771f9232..8e8e693ac 100644 --- a/ja/built-in-nodes/ImageInvert.mdx +++ b/ja/built-in-nodes/ImageInvert.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageInvert" icon: "circle" mode: wide --- + `ImageInvert`ノードは、画像の色を反転させるように設計されています。これにより、各ピクセルの色値がカラーホイール上の補色に変換されます。この操作は、ネガ画像の作成や、色反転を必要とする視覚効果に役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/ImageMergeTileList.mdx b/ja/built-in-nodes/ImageMergeTileList.mdx index 33499744b..267c97a3a 100644 --- a/ja/built-in-nodes/ImageMergeTileList.mdx +++ b/ja/built-in-nodes/ImageMergeTileList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageMergeTileList" icon: "circle" mode: wide --- + このノードは、画像タイルのリストを受け取り、それらを1つの大きな画像に結合します。以前にグリッド状の重なり合うタイルに分割された画像を、重み付きブレンディング技術を使用してシームレスな最終結果に再構築するように設計されています。 ## 入力 diff --git a/ja/built-in-nodes/ImageOnlyCheckpointLoader.mdx b/ja/built-in-nodes/ImageOnlyCheckpointLoader.mdx index 90ba21922..4e888bea3 100644 --- a/ja/built-in-nodes/ImageOnlyCheckpointLoader.mdx +++ b/ja/built-in-nodes/ImageOnlyCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageOnlyCheckpointLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/checkpoints` フォルダ内のモデルを検出し、さらに extra_model_paths.yaml ファイルで設定された追加パスからもモデルを読み込みます。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、対応するフォルダからモデルファイルを読み込ませる必要があります。 このノードは、動画生成ワークフロー内で画像ベースのモデル専用のチェックポイントを読み込むことに特化しています。指定されたチェックポイントから必要なコンポーネントを効率的に取得・設定し、モデルの画像関連の側面に焦点を当てます。 diff --git a/ja/built-in-nodes/ImageOnlyCheckpointSave.mdx b/ja/built-in-nodes/ImageOnlyCheckpointSave.mdx index 89efd1307..7cbaf9fd3 100644 --- a/ja/built-in-nodes/ImageOnlyCheckpointSave.mdx +++ b/ja/built-in-nodes/ImageOnlyCheckpointSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageOnlyCheckpointSave" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ImagePadForOutpaint.mdx b/ja/built-in-nodes/ImagePadForOutpaint.mdx index 74dd02830..3ab302072 100644 --- a/ja/built-in-nodes/ImagePadForOutpaint.mdx +++ b/ja/built-in-nodes/ImagePadForOutpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImagePadForOutpaint" icon: "circle" mode: wide --- + このノードは、画像の周囲にパディングを追加して、アウトペインティング処理用に画像を準備するために設計されています。画像の寸法を調整してアウトペインティングアルゴリズムとの互換性を確保し、元の境界を超えた拡張画像領域の生成を容易にします。 ## 入力 diff --git a/ja/built-in-nodes/ImageQuantize.mdx b/ja/built-in-nodes/ImageQuantize.mdx index 3269ea153..ae723952d 100644 --- a/ja/built-in-nodes/ImageQuantize.mdx +++ b/ja/built-in-nodes/ImageQuantize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageQuantize" icon: "circle" mode: wide --- + ## 概要 ImageQuantizeノードは、画像内の色数を指定された数に減らし、必要に応じてディザリング技術を適用して視覚的な品質を維持するために設計されています。この処理は、パレットベースの画像を作成したり、特定のアプリケーション向けに色の複雑さを軽減する際に役立ちます。 diff --git a/ja/built-in-nodes/ImageRGBToYUV.mdx b/ja/built-in-nodes/ImageRGBToYUV.mdx index 15c95bf5f..709b34e58 100644 --- a/ja/built-in-nodes/ImageRGBToYUV.mdx +++ b/ja/built-in-nodes/ImageRGBToYUV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageRGBToYUV" icon: "circle" mode: wide --- + ImageRGBToYUV ノードは、RGB カラー画像を YUV 色空間に変換します。入力として RGB 画像を受け取り、それを Y（輝度）、U（青色投影）、V（赤色投影）の3つの個別のチャンネルに分離します。各出力チャンネルは、対応する YUV コンポーネントを表す個別のグレースケール画像として返されます。 ## 入力 @@ -17,8 +18,8 @@ ImageRGBToYUV ノードは、RGB カラー画像を YUV 色空間に変換しま | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `U` | YUV 色空間の輝度（明るさ）コンポーネント | IMAGE | -| `V` | YUV 色空間の青色投影コンポーネント | IMAGE | +| `Y` | YUV 色空間の輝度（明るさ）コンポーネント | IMAGE | +| `U` | YUV 色空間の青色投影コンポーネント | IMAGE | | `V` | YUV 色空間の赤色投影コンポーネント | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageRGBToYUV/ja.md) diff --git a/ja/built-in-nodes/ImageRotate.mdx b/ja/built-in-nodes/ImageRotate.mdx index 289e7e678..7b6a58b46 100644 --- a/ja/built-in-nodes/ImageRotate.mdx +++ b/ja/built-in-nodes/ImageRotate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageRotate" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ImageRotate ノードは、入力画像を指定された角度に回転させます。回転オプションは4つあり、回転なし、時計回りに90度、180度、時計回りに270度に対応しています。回転処理は効率的なテンソル演算によって実行され、画像データの整合性が維持されます。 diff --git a/ja/built-in-nodes/ImageScale.mdx b/ja/built-in-nodes/ImageScale.mdx index 6441b2dd1..c853202ea 100644 --- a/ja/built-in-nodes/ImageScale.mdx +++ b/ja/built-in-nodes/ImageScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScale" icon: "circle" mode: wide --- + ImageScaleノードは、画像を特定の寸法にリサイズするために設計されており、アップスケール方法の選択肢とリサイズ後の画像をクロップする機能を提供します。このノードは画像のアップスケーリングとクロッピングの複雑さを抽象化し、ユーザーが定義したパラメータに従って画像の寸法を変更するための直感的なインターフェースを提供します。 ## 入力 diff --git a/ja/built-in-nodes/ImageScaleBy.mdx b/ja/built-in-nodes/ImageScaleBy.mdx index 62dc0fac1..0624a5232 100644 --- a/ja/built-in-nodes/ImageScaleBy.mdx +++ b/ja/built-in-nodes/ImageScaleBy.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleBy" icon: "circle" mode: wide --- + ImageScaleBy ノードは、指定された倍率で様々な補間方式を使用して画像をアップスケーリングするために設計されています。柔軟な方法で画像サイズを調整し、さまざまなアップスケーリングのニーズに対応します。 ## 入力 diff --git a/ja/built-in-nodes/ImageScaleToMaxDimension.mdx b/ja/built-in-nodes/ImageScaleToMaxDimension.mdx index 2ab17ef82..b1616bfd5 100644 --- a/ja/built-in-nodes/ImageScaleToMaxDimension.mdx +++ b/ja/built-in-nodes/ImageScaleToMaxDimension.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleToMaxDimension" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がございましたら、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageScaleToMaxDimension/en.md) ImageScaleToMaxDimensionノードは、画像を指定された最大寸法に収まるようにリサイズし、元のアスペクト比を維持します。画像が縦向きか横向きかを判定し、大きい方の寸法をターゲットサイズに合わせて拡大・縮小し、小さい方の寸法も比例して調整します。このノードは、品質とパフォーマンスの要件に応じて複数のアップスケーリング方法をサポートしています。 diff --git a/ja/built-in-nodes/ImageScaleToTotalPixels.mdx b/ja/built-in-nodes/ImageScaleToTotalPixels.mdx index 4ef91f89c..62a221e65 100644 --- a/ja/built-in-nodes/ImageScaleToTotalPixels.mdx +++ b/ja/built-in-nodes/ImageScaleToTotalPixels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleToTotalPixels" icon: "circle" mode: wide --- + ImageScaleToTotalPixels ノードは、アスペクト比を維持しながら画像を指定された総ピクセル数にリサイズするために設計されています。目的のピクセル数を達成するために、画像をアップスケーリングするためのさまざまな方法を提供します。 ## 入力 diff --git a/ja/built-in-nodes/ImageSharpen.mdx b/ja/built-in-nodes/ImageSharpen.mdx index f306685ef..56b5c81dd 100644 --- a/ja/built-in-nodes/ImageSharpen.mdx +++ b/ja/built-in-nodes/ImageSharpen.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageSharpen" icon: "circle" mode: wide --- + ImageSharpenノードは、画像のエッジやディテールを強調することで、画像の明瞭さを向上させます。画像にシャープネスフィルターを適用し、その強度と半径を調整することで、画像をより鮮明でくっきりとした印象にします。 ## 入力 diff --git a/ja/built-in-nodes/ImageStitch.mdx b/ja/built-in-nodes/ImageStitch.mdx index 95bcf66c0..78ef7c781 100644 --- a/ja/built-in-nodes/ImageStitch.mdx +++ b/ja/built-in-nodes/ImageStitch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageStitch" icon: "circle" mode: wide --- + このノードは、指定された方向（上、下、左、右）に2つの画像を結合し、サイズの一致や画像間のスペース設定をサポートします。 ## 入力 diff --git a/ja/built-in-nodes/ImageToMask.mdx b/ja/built-in-nodes/ImageToMask.mdx index 4a57c0f95..5a1f16c1a 100644 --- a/ja/built-in-nodes/ImageToMask.mdx +++ b/ja/built-in-nodes/ImageToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageToMask" icon: "circle" mode: wide --- + ImageToMask ノードは、指定されたカラーチャンネルに基づいて画像をマスクに変換するために設計されています。画像の赤、緑、青、またはアルファチャンネルに対応するマスクレイヤーを抽出し、チャンネル固有のマスキングや処理を必要とする操作を容易にします。 ## 入力 diff --git a/ja/built-in-nodes/ImageUpscaleWithModel.mdx b/ja/built-in-nodes/ImageUpscaleWithModel.mdx index ef384b7fa..e5b6a772c 100644 --- a/ja/built-in-nodes/ImageUpscaleWithModel.mdx +++ b/ja/built-in-nodes/ImageUpscaleWithModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageUpscaleWithModel" icon: "circle" mode: wide --- + このノードは、指定されたアップスケールモデルを使用して画像をアップスケールするために設計されています。画像を適切なデバイスに調整し、メモリ使用量を最適化し、メモリ不足エラーを防ぐためにアップスケールモデルをタイル状に適用することで、アップスケール処理を効率的に管理します。 ## 入力 diff --git a/ja/built-in-nodes/ImageYUVToRGB.mdx b/ja/built-in-nodes/ImageYUVToRGB.mdx index 2202e57a0..8c1f7c972 100644 --- a/ja/built-in-nodes/ImageYUVToRGB.mdx +++ b/ja/built-in-nodes/ImageYUVToRGB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageYUVToRGB" icon: "circle" mode: wide --- + ImageYUVToRGB ノードは、YUV色空間の画像をRGB色空間に変換します。このノードは、Y（輝度）、U（青色投影）、V（赤色投影）の3つのチャンネルを表す個別の入力画像を受け取り、色空間変換を用いてこれらを1つのRGB画像に結合します。 ## 入力 diff --git a/ja/built-in-nodes/InpaintModelConditioning.mdx b/ja/built-in-nodes/InpaintModelConditioning.mdx index 93ba6d512..85465d8f7 100644 --- a/ja/built-in-nodes/InpaintModelConditioning.mdx +++ b/ja/built-in-nodes/InpaintModelConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InpaintModelConditioning" icon: "circle" mode: wide --- + InpaintModelConditioning ノードは、インペイントモデルの条件付けプロセスを容易にするために設計されており、様々な条件付け入力を統合・操作してインペイント出力を調整することを可能にします。特定のモデルチェックポイントの読み込み、スタイルやコントロールネットモデルの適用から、条件付け要素のエンコードや結合に至るまで、幅広い機能を網羅しており、インペインタスクをカスタマイズするための包括的なツールとして機能します。 ## 入力 @@ -21,8 +22,8 @@ InpaintModelConditioning ノードは、インペイントモデルの条件付 | パラメータ | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 処理後の変更されたポジティブな条件付け情報で、インペイントモデルに適用できる状態です。この出力は、指定されたポジティブな条件に従ってインペイントプロセスを導くために不可欠です。 | `CONDITIONING` | -| `潜在` | 処理後の変更されたネガティブな条件付け情報で、インペイントモデルに適用できる状態です。この出力は、指定されたネガティブな条件に従ってインペイントプロセスを導くために不可欠です。 | `CONDITIONING` | -| `latent` | 条件付けプロセスから導出された潜在表現です。この出力は、インペイントされている画像の基礎となる特徴や特性を理解するために重要です。 | `LATENT` | +| `ポジティブ` | 処理後の変更されたポジティブな条件付け情報で、インペイントモデルに適用できる状態です。この出力は、指定されたポジティブな条件に従ってインペイントプロセスを導くために不可欠です。 | `CONDITIONING` | +| `ネガティブ` | 処理後の変更されたネガティブな条件付け情報で、インペイントモデルに適用できる状態です。この出力は、指定されたネガティブな条件に従ってインペイントプロセスを導くために不可欠です。 | `CONDITIONING` | +| `潜在` | 条件付けプロセスから導出された潜在表現です。この出力は、インペイントされている画像の基礎となる特徴や特性を理解するために重要です。 | `LATENT` | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InpaintModelConditioning/ja.md) diff --git a/ja/built-in-nodes/InstructPixToPixConditioning.mdx b/ja/built-in-nodes/InstructPixToPixConditioning.mdx index 1f2e533b5..b49c47c59 100644 --- a/ja/built-in-nodes/InstructPixToPixConditioning.mdx +++ b/ja/built-in-nodes/InstructPixToPixConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InstructPixToPixConditioning" icon: "circle" mode: wide --- + あなたは ComfyUI ノードドキュメントを英語から日本語に翻訳する技術翻訳の専門家です。 ## 翻訳ルール @@ -50,9 +51,9 @@ InstructPixToPixConditioning ノードは、ポジティブおよびネガティ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 潜在画像表現が付加されたポジティブ条件付けデータ | CONDITIONING | -| `潜在` | 潜在画像表現が付加されたネガティブ条件付けデータ | CONDITIONING | -| `latent` | エンコードされた画像と同じ寸法を持つ空の潜在テンソル | LATENT | +| `ポジティブ` | 潜在画像表現が付加されたポジティブ条件付けデータ | CONDITIONING | +| `ネガティブ` | 潜在画像表現が付加されたネガティブ条件付けデータ | CONDITIONING | +| `潜在` | エンコードされた画像と同じ寸法を持つ空の潜在テンソル | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InstructPixToPixConditioning/ja.md) diff --git a/ja/built-in-nodes/InvertBooleanNode.mdx b/ja/built-in-nodes/InvertBooleanNode.mdx index f278b5590..12dcb8412 100644 --- a/ja/built-in-nodes/InvertBooleanNode.mdx +++ b/ja/built-in-nodes/InvertBooleanNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InvertBooleanNode" icon: "circle" mode: wide --- + このノードは、単一のブール値（true/false）を入力として受け取り、その反対の値を出力します。論理否定（NOT）演算を実行し、`true` を `false` に、`false` を `true` に変換します。 ## 入力 diff --git a/ja/built-in-nodes/InvertMask.mdx b/ja/built-in-nodes/InvertMask.mdx index c312467d2..6870847ff 100644 --- a/ja/built-in-nodes/InvertMask.mdx +++ b/ja/built-in-nodes/InvertMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InvertMask" icon: "circle" mode: wide --- + InvertMaskノードは、指定されたマスクの値を反転させ、マスク領域と非マスク領域を効果的に入れ替えるように設計されています。この操作は、関心領域を前景と背景の間で切り替える必要がある画像処理タスクにおいて基本的な機能です。 ## 入力 diff --git a/ja/built-in-nodes/JoinAudioChannels.mdx b/ja/built-in-nodes/JoinAudioChannels.mdx index 29962cef1..0cbcb5e8e 100644 --- a/ja/built-in-nodes/JoinAudioChannels.mdx +++ b/ja/built-in-nodes/JoinAudioChannels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JoinAudioChannels" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/JoinImageWithAlpha.mdx b/ja/built-in-nodes/JoinImageWithAlpha.mdx index aa04d6e1c..56fe2e8d8 100644 --- a/ja/built-in-nodes/JoinImageWithAlpha.mdx +++ b/ja/built-in-nodes/JoinImageWithAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JoinImageWithAlpha" icon: "circle" mode: wide --- + このノードはコンポジット処理用に設計されており、具体的には画像と対応するアルファマスクを結合して単一の出力画像を生成します。視覚コンテンツと透明度情報を効果的に組み合わせることで、特定の領域が透明または半透明になる画像を作成できます。 ## 入力 diff --git a/ja/built-in-nodes/JsonExtractString.mdx b/ja/built-in-nodes/JsonExtractString.mdx index e581e4d9e..818ef0bb1 100644 --- a/ja/built-in-nodes/JsonExtractString.mdx +++ b/ja/built-in-nodes/JsonExtractString.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JsonExtractString" icon: "circle" mode: wide --- + JsonExtractString ノードは、JSON データを含むテキスト文字列を読み取り、特定のキーに関連付けられた値を抽出します。抽出された値を文字列に変換します。JSON が無効な場合、キーが見つからない場合、または値が null の場合、ノードは空の文字列を返します。 ## 入力 diff --git a/ja/built-in-nodes/KSampler.mdx b/ja/built-in-nodes/KSampler.mdx index 7b5f86a35..b737ec714 100644 --- a/ja/built-in-nodes/KSampler.mdx +++ b/ja/built-in-nodes/KSampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSampler" icon: "circle" mode: wide --- + KSamplerは次のように動作します。特定のモデルとポジティブ・ネガティブ両方の条件に基づいて、提供された元の潜在画像情報を変更します。 まず、設定された **seed** と **denoise strength** に従って元の画像データにノイズを追加し、その後、事前設定された **Model** に **ポジティブ** および **ネガティブ** なガイダンス条件を組み合わせて画像を生成します。 diff --git a/ja/built-in-nodes/KSamplerAdvanced.mdx b/ja/built-in-nodes/KSamplerAdvanced.mdx index 42a6233cd..c0685b7e2 100644 --- a/ja/built-in-nodes/KSamplerAdvanced.mdx +++ b/ja/built-in-nodes/KSamplerAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSamplerAdvanced" icon: "circle" mode: wide --- + 以下が翻訳結果です。 KSamplerAdvanced ノードは、高度な設定と技術を提供することでサンプリングプロセスを強化するために設計されています。基本の KSampler 機能を改善し、モデルからサンプルを生成するためのより洗練されたオプションを提供することを目的としています。 diff --git a/ja/built-in-nodes/KSamplerSelect.mdx b/ja/built-in-nodes/KSamplerSelect.mdx index d4ff2a9a7..07372a5e5 100644 --- a/ja/built-in-nodes/KSamplerSelect.mdx +++ b/ja/built-in-nodes/KSamplerSelect.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSamplerSelect" icon: "circle" mode: wide --- + KSamplerSelectノードは、指定されたサンプラー名に基づいて特定のサンプラーを選択するために設計されています。サンプラー選択の複雑さを抽象化し、ユーザーがタスクに応じて異なるサンプリング戦略を簡単に切り替えられるようにします。 ## 入力 diff --git a/ja/built-in-nodes/Kandinsky5ImageToVideo.mdx b/ja/built-in-nodes/Kandinsky5ImageToVideo.mdx index 5ffc72dee..29db0c45f 100644 --- a/ja/built-in-nodes/Kandinsky5ImageToVideo.mdx +++ b/ja/built-in-nodes/Kandinsky5ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Kandinsky5ImageToVideo" icon: "circle" mode: wide --- + 以下は、指定された英語ドキュメントを日本語に翻訳したものです。 --- @@ -30,9 +31,9 @@ Kandinsky5ImageToVideo ノードは、Kandinsky モデルを使用した動画 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 変更されたポジティブ条件付けです。エンコードされた開始画像データで更新される可能性があります。 | CONDITIONING | -| `latent` | 変更されたネガティブ条件付けです。エンコードされた開始画像データで更新される可能性があります。 | CONDITIONING | -| `cond_latent` | 指定された次元に合わせて形状が設定された、ゼロで満たされた空の動画潜在テンソルです。 | LATENT | +| `ポジティブ` | 変更されたポジティブ条件付けです。エンコードされた開始画像データで更新される可能性があります。 | CONDITIONING | +| `ネガティブ` | 変更されたネガティブ条件付けです。エンコードされた開始画像データで更新される可能性があります。 | CONDITIONING | +| `latent` | 指定された次元に合わせて形状が設定された、ゼロで満たされた空の動画潜在テンソルです。 | LATENT | | `cond_latent` | 提供された開始画像の、クリーンでエンコードされた潜在表現です。これは内部で使用され、生成された動画潜在のノイズの多い開始部分を置き換えます。 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Kandinsky5ImageToVideo/ja.md) diff --git a/ja/built-in-nodes/KarrasScheduler.mdx b/ja/built-in-nodes/KarrasScheduler.mdx index 0a0d2233e..2242cbb96 100644 --- a/ja/built-in-nodes/KarrasScheduler.mdx +++ b/ja/built-in-nodes/KarrasScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KarrasScheduler" icon: "circle" mode: wide --- + KarrasSchedulerノードは、Karras et al. (2022) のノイズスケジュールに基づいて、ノイズレベル（シグマ）のシーケンスを生成するために設計されています。このスケジューラーは、生成モデルにおける拡散プロセスを制御するのに役立ち、生成プロセスの各ステップで適用されるノイズレベルを微調整することができます。 ## 入力 diff --git a/ja/built-in-nodes/KlingAvatarNode.mdx b/ja/built-in-nodes/KlingAvatarNode.mdx index d49c7903b..ca7ffb1a7 100644 --- a/ja/built-in-nodes/KlingAvatarNode.mdx +++ b/ja/built-in-nodes/KlingAvatarNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingAvatarNode" icon: "circle" mode: wide --- + 以下は、ご指定の翻訳ルールに従って英語ドキュメントを日本語に翻訳したものです。 --- diff --git a/ja/built-in-nodes/KlingCameraControlI2VNode.mdx b/ja/built-in-nodes/KlingCameraControlI2VNode.mdx index 489f160a6..bb7c8c8ed 100644 --- a/ja/built-in-nodes/KlingCameraControlI2VNode.mdx +++ b/ja/built-in-nodes/KlingCameraControlI2VNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingCameraControlI2VNode" icon: "circle" mode: wide --- + 以下は、ご依頼いただいたComfyUIノードドキュメントの日本語翻訳です。 ## 概要 @@ -26,7 +27,7 @@ Kling Image to Video Camera Control Nodeは、静止画像をプロフェッシ | 出力名 | 説明 | データ型 | | --- | --- | --- | | `video_id` | 生成された動画出力 | VIDEO | -| `duration` | 生成された動画の一意の識別子 | STRING | +| `video_id` | 生成された動画の一意の識別子 | STRING | | `duration` | 生成された動画の長さ | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlI2VNode/ja.md) diff --git a/ja/built-in-nodes/KlingCameraControlT2VNode.mdx b/ja/built-in-nodes/KlingCameraControlT2VNode.mdx index 7ee1e96f7..be74af641 100644 --- a/ja/built-in-nodes/KlingCameraControlT2VNode.mdx +++ b/ja/built-in-nodes/KlingCameraControlT2VNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingCameraControlT2VNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -25,7 +26,7 @@ Kling Text to Video Camera Control Nodeは、テキストから映画のよう | 出力名 | 説明 | データ型 | | --- | --- | --- | | `video_id` | カメラ制御エフェクトが適用された生成動画 | VIDEO | -| `duration` | 生成された動画の一意識別子 | STRING | +| `video_id` | 生成された動画の一意識別子 | STRING | | `duration` | 生成された動画の長さ | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlT2VNode/ja.md) diff --git a/ja/built-in-nodes/KlingCameraControls.mdx b/ja/built-in-nodes/KlingCameraControls.mdx index 799148aa9..13cfb9055 100644 --- a/ja/built-in-nodes/KlingCameraControls.mdx +++ b/ja/built-in-nodes/KlingCameraControls.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingCameraControls" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Kling Camera Controls ノードは、動画生成におけるモーションコントロール効果を作成するために、さまざまなカメラの移動および回転パラメーターを設定できます。このノードは、カメラの位置、回転、ズームを制御して、さまざまなカメラワークをシミュレートします。 diff --git a/ja/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx b/ja/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx index 1d717c928..a1f28a7c2 100644 --- a/ja/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx +++ b/ja/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingDualCharacterVideoEffectNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingDualCharacterVideoEffectNode/en.md) Kling Dual Character Video Effect ノードは、選択されたシーンに基づいて特殊効果を適用した動画を生成します。2つの画像を入力として受け取り、合成動画の左側に1つ目の画像、右側に2つ目の画像を配置します。選択されたエフェクトシーンに応じて、異なる視覚効果が適用されます。 diff --git a/ja/built-in-nodes/KlingFirstLastFrameNode.mdx b/ja/built-in-nodes/KlingFirstLastFrameNode.mdx index b7866c289..d3646cd00 100644 --- a/ja/built-in-nodes/KlingFirstLastFrameNode.mdx +++ b/ja/built-in-nodes/KlingFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingFirstLastFrameNode" icon: "circle" mode: wide --- + このノードは、Kling 3.0モデルを使用して動画を生成します。テキストプロンプト、指定された長さ、および開始フレームと終了フレームの2つの画像に基づいて動画を作成します。また、動画に合わせた音声を生成することもできます。 ## 入力 diff --git a/ja/built-in-nodes/KlingImage2VideoNode.mdx b/ja/built-in-nodes/KlingImage2VideoNode.mdx index 39ac56127..6c2b09d06 100644 --- a/ja/built-in-nodes/KlingImage2VideoNode.mdx +++ b/ja/built-in-nodes/KlingImage2VideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingImage2VideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -29,7 +30,7 @@ Kling Image to Video ノードは、テキストプロンプトを使用して | 出力名 | 説明 | データ型 | | --- | --- | --- | | `video_id` | 生成された動画の出力です。 | VIDEO | -| `duration` | 生成された動画の一意の識別子です。 | STRING | +| `video_id` | 生成された動画の一意の識別子です。 | STRING | | `duration` | 生成された動画の長さ情報です。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImage2VideoNode/ja.md) diff --git a/ja/built-in-nodes/KlingImageGenerationNode.mdx b/ja/built-in-nodes/KlingImageGenerationNode.mdx index ef2cdcbd5..ab58d2ec4 100644 --- a/ja/built-in-nodes/KlingImageGenerationNode.mdx +++ b/ja/built-in-nodes/KlingImageGenerationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingImageGenerationNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Kling Image Generation ノードは、テキストプロンプトから画像を生成します。必要に応じて参照画像を使用して生成をガイドすることもできます。テキストによる説明と参照設定に基づいて1枚以上の画像を作成し、生成された画像を出力として返します。 diff --git a/ja/built-in-nodes/KlingImageToVideoWithAudio.mdx b/ja/built-in-nodes/KlingImageToVideoWithAudio.mdx index 27d936b85..aef5abbd7 100644 --- a/ja/built-in-nodes/KlingImageToVideoWithAudio.mdx +++ b/ja/built-in-nodes/KlingImageToVideoWithAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingImageToVideoWithAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要Kling Image（最初のフレーム）から音声付きビデオを生成するノードは、Kling AIモデルを使用して、1枚の開始画像とテキストプロンプトから短いビデオを生成します。提供された画像で始まるビデオシーケンスを作成し、オプションでAI生成の音声を映像に追加することもできます。 diff --git a/ja/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx b/ja/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx index 64bfa77e5..e8e403799 100644 --- a/ja/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx +++ b/ja/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingLipSyncAudioToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -32,8 +33,8 @@ Kling リップシンク音声動画ノードは、動画ファイル内の口 | 出力名 | 説明 | データ型 | | --- | --- | --- | | `動画ID` | 口の動きがリップシンクされた処理済み動画 | VIDEO | -| `再生時間` | 処理済み動画の一意識別子 | STRING | -| `duration` | 処理済み動画の長さ | STRING | +| `動画ID` | 処理済み動画の一意識別子 | STRING | +| `再生時間` | 処理済み動画の長さ | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncAudioToVideoNode/ja.md) diff --git a/ja/built-in-nodes/KlingLipSyncTextToVideoNode.mdx b/ja/built-in-nodes/KlingLipSyncTextToVideoNode.mdx index beca220b0..86c5fb0ff 100644 --- a/ja/built-in-nodes/KlingLipSyncTextToVideoNode.mdx +++ b/ja/built-in-nodes/KlingLipSyncTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingLipSyncTextToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- @@ -31,8 +32,8 @@ Kling Lip Sync Text to Video Node は、動画ファイル内の口の動きを | 出力名 | 説明 | データ型 | | --- | --- | --- | | `動画ID` | リップシンクされた音声付きの生成動画 | VIDEO | -| `再生時間` | 生成された動画の一意識別子 | STRING | -| `duration` | 生成された動画の長さ情報 | STRING | +| `動画ID` | 生成された動画の一意識別子 | STRING | +| `再生時間` | 生成された動画の長さ情報 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncTextToVideoNode/ja.md) diff --git a/ja/built-in-nodes/KlingMotionControl.mdx b/ja/built-in-nodes/KlingMotionControl.mdx index f34a432c9..52923f9aa 100644 --- a/ja/built-in-nodes/KlingMotionControl.mdx +++ b/ja/built-in-nodes/KlingMotionControl.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingMotionControl" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Kling Motion Control ノードは、参照画像とテキストプロンプトで定義されたキャラクターに対して、参照動画のモーション、表情、カメラワークを適用し、動画を生成します。このノードでは、キャラクターの最終的な向きを参照動画と参照画像のどちらから取得するかを制御できます。 diff --git a/ja/built-in-nodes/KlingOmniProEditVideoNode.mdx b/ja/built-in-nodes/KlingOmniProEditVideoNode.mdx index 0be57ebd4..1d2a435c8 100644 --- a/ja/built-in-nodes/KlingOmniProEditVideoNode.mdx +++ b/ja/built-in-nodes/KlingOmniProEditVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProEditVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx b/ja/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx index c50dcf818..04acf74ee 100644 --- a/ja/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx +++ b/ja/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProFirstLastFrameNode" icon: "circle" mode: wide --- + このノードは、最新のKling AIモデルを使用して、開始フレーム、オプションの終了フレーム、または参照画像から動画を生成します。単一の動画、または各セグメントに個別のプロンプトと長さを設定したマルチショットストーリーボードを作成できます。このノードはこれらの入力を処理し、指定された長さと解像度の動画を生成します。オプションで音声生成も可能です。 ## 入力 diff --git a/ja/built-in-nodes/KlingOmniProImageNode.mdx b/ja/built-in-nodes/KlingOmniProImageNode.mdx index d9c4abc7f..5a2a9e3a8 100644 --- a/ja/built-in-nodes/KlingOmniProImageNode.mdx +++ b/ja/built-in-nodes/KlingOmniProImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProImageNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/KlingOmniProImageToVideoNode.mdx b/ja/built-in-nodes/KlingOmniProImageToVideoNode.mdx index 991462ce2..ef9b7dcf4 100644 --- a/ja/built-in-nodes/KlingOmniProImageToVideoNode.mdx +++ b/ja/built-in-nodes/KlingOmniProImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProImageToVideoNode" icon: "circle" mode: wide --- + このノードは、Kling AIモデルを使用して、テキストプロンプトと最大7枚の参照画像に基づいて動画を生成します。動画のアスペクト比、長さ、解像度を制御でき、オプションでストーリーボードの使用や音声の生成も可能です。このノードは外部APIにリクエストを送信し、生成された動画を返します。 ## 入力 diff --git a/ja/built-in-nodes/KlingOmniProTextToVideoNode.mdx b/ja/built-in-nodes/KlingOmniProTextToVideoNode.mdx index 6d0933af3..75097438e 100644 --- a/ja/built-in-nodes/KlingOmniProTextToVideoNode.mdx +++ b/ja/built-in-nodes/KlingOmniProTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProTextToVideoNode" icon: "circle" mode: wide --- + このノードは、最新のKling AIモデルを使用して、テキスト説明から動画を生成します。プロンプトをリモートAPIに送信し、生成された動画を返します。このノードでは、動画の長さ、形状、品質を制御でき、マルチショットのストーリーボードを作成することも可能です。 ## 入力 diff --git a/ja/built-in-nodes/KlingOmniProVideoToVideoNode.mdx b/ja/built-in-nodes/KlingOmniProVideoToVideoNode.mdx index e20bc30e3..dd84e76a8 100644 --- a/ja/built-in-nodes/KlingOmniProVideoToVideoNode.mdx +++ b/ja/built-in-nodes/KlingOmniProVideoToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProVideoToVideoNode" icon: "circle" mode: wide --- + このノードは、Kling AIモデルを使用して、入力動画とオプションの参照画像に基づいて新しい動画を生成します。目的のコンテンツを説明するテキストプロンプトを指定すると、ノードが参照動画をそれに応じて変換します。また、最大4枚の追加参照画像を取り込んで、出力のスタイルとコンテンツをガイドすることもできます。 ## 入力 diff --git a/ja/built-in-nodes/KlingSingleImageVideoEffectNode.mdx b/ja/built-in-nodes/KlingSingleImageVideoEffectNode.mdx index 48b58251a..90cb31776 100644 --- a/ja/built-in-nodes/KlingSingleImageVideoEffectNode.mdx +++ b/ja/built-in-nodes/KlingSingleImageVideoEffectNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingSingleImageVideoEffectNode" icon: "circle" mode: wide --- + 以下は、ご依頼いただいたComfyUIノードドキュメントの日本語翻訳です。 --- @@ -27,7 +28,7 @@ Kling 単一画像ビデオエフェクトノードは、1枚の参照画像に | 出力名 | 説明 | データ型 | | --- | --- | --- | | `video_id` | エフェクトが適用された生成済み動画 | VIDEO | -| `duration` | 生成された動画の一意識別子 | STRING | +| `video_id` | 生成された動画の一意識別子 | STRING | | `duration` | 生成された動画の長さ | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingSingleImageVideoEffectNode/ja.md) diff --git a/ja/built-in-nodes/KlingStartEndFrameNode.mdx b/ja/built-in-nodes/KlingStartEndFrameNode.mdx index e8d3be060..7fe481448 100644 --- a/ja/built-in-nodes/KlingStartEndFrameNode.mdx +++ b/ja/built-in-nodes/KlingStartEndFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingStartEndFrameNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Kling 開始・終了フレーム動画ノードは、指定された開始画像と終了画像の間を遷移する動画シーケンスを生成します。最初のフレームから最後のフレームへの滑らかな変形を実現するため、中間の全フレームを生成します。このノードは画像から動画へのAPIを呼び出しますが、`image_tail` リクエストフィールドで動作する入力オプションのみをサポートします。 @@ -33,7 +34,7 @@ Kling 開始・終了フレーム動画ノードは、指定された開始画 | 出力名 | 説明 | データ型 | | --- | --- | --- | | `video_id` | 生成された動画シーケンス | VIDEO | -| `duration` | 生成された動画の一意識別子 | STRING | +| `video_id` | 生成された動画の一意識別子 | STRING | | `duration` | 生成された動画の持続時間 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingStartEndFrameNode/ja.md) diff --git a/ja/built-in-nodes/KlingTextToVideoNode.mdx b/ja/built-in-nodes/KlingTextToVideoNode.mdx index 9d9dfc778..598d7c8ec 100644 --- a/ja/built-in-nodes/KlingTextToVideoNode.mdx +++ b/ja/built-in-nodes/KlingTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingTextToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- @@ -26,8 +27,8 @@ Kling Text to Video ノードは、テキストによる説明を動画コンテ | 出力名 | 説明 | データ型 | | --- | --- | --- | | `video_id` | 生成された動画出力 | VIDEO | -| `継続時間` | 生成された動画の一意識別子 | STRING | -| `duration` | 生成された動画の長さ情報 | STRING | +| `video_id` | 生成された動画の一意識別子 | STRING | +| `継続時間` | 生成された動画の長さ情報 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoNode/ja.md) diff --git a/ja/built-in-nodes/KlingTextToVideoWithAudio.mdx b/ja/built-in-nodes/KlingTextToVideoWithAudio.mdx index b36c609fe..78b37218c 100644 --- a/ja/built-in-nodes/KlingTextToVideoWithAudio.mdx +++ b/ja/built-in-nodes/KlingTextToVideoWithAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingTextToVideoWithAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/KlingVideoExtendNode.mdx b/ja/built-in-nodes/KlingVideoExtendNode.mdx index 2b960bcaf..857e6eaf9 100644 --- a/ja/built-in-nodes/KlingVideoExtendNode.mdx +++ b/ja/built-in-nodes/KlingVideoExtendNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingVideoExtendNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -27,7 +28,7 @@ Kling Video Extend ノードは、他の Kling ノードで作成された動画 | 出力名 | 説明 | データ型 | | --- | --- | --- | | `video_id` | Kling API によって生成された延長動画 | VIDEO | -| `duration` | 延長動画の一意の識別子 | STRING | +| `video_id` | 延長動画の一意の識別子 | STRING | | `duration` | 延長動画の再生時間 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoExtendNode/ja.md) diff --git a/ja/built-in-nodes/KlingVideoNode.mdx b/ja/built-in-nodes/KlingVideoNode.mdx index d696b018a..fa5137b81 100644 --- a/ja/built-in-nodes/KlingVideoNode.mdx +++ b/ja/built-in-nodes/KlingVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingVideoNode" icon: "circle" mode: wide --- + このノードは、Kling V3モデルを使用して動画を生成します。テキスト説明から動画を作成するテキスト読み取り動画モードと、既存の画像を動かす画像読み取り動画モードの2つの主要モードをサポートしています。また、各パートに異なるプロンプトを使用したマルチセグメント動画（ストーリーボード）の作成や、オプションでオーディオを生成する高度な機能も提供します。 ## 入力 diff --git a/ja/built-in-nodes/KlingVirtualTryOnNode.mdx b/ja/built-in-nodes/KlingVirtualTryOnNode.mdx index d44729658..1f14b5d7b 100644 --- a/ja/built-in-nodes/KlingVirtualTryOnNode.mdx +++ b/ja/built-in-nodes/KlingVirtualTryOnNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingVirtualTryOnNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/Krea2ImageNode.mdx b/ja/built-in-nodes/Krea2ImageNode.mdx index 91243659b..86f4e91df 100644 --- a/ja/built-in-nodes/Krea2ImageNode.mdx +++ b/ja/built-in-nodes/Krea2ImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Krea2ImageNode" icon: "circle" mode: wide --- + 以下が日本語翻訳です。 ## 概要 diff --git a/ja/built-in-nodes/Krea2StyleReferenceNode.mdx b/ja/built-in-nodes/Krea2StyleReferenceNode.mdx index 17497fa86..271b5710a 100644 --- a/ja/built-in-nodes/Krea2StyleReferenceNode.mdx +++ b/ja/built-in-nodes/Krea2StyleReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Krea2StyleReferenceNode" icon: "circle" mode: wide --- + ## 概要 Krea 2 スタイル参照ノードを使用すると、参照画像を追加して Krea 2 の画像生成のスタイルに影響を与えることができます。複数のスタイル参照をチェーン接続（最大10個まで）し、結合した結果を Krea 2 画像ノードに入力できます。提供された各画像は ComfyAPI ストレージにアップロードされ、URL として渡されます。 diff --git a/ja/built-in-nodes/LTXAVTextEncoderLoader.mdx b/ja/built-in-nodes/LTXAVTextEncoderLoader.mdx index 1e31d6964..6474b5ec7 100644 --- a/ja/built-in-nodes/LTXAVTextEncoderLoader.mdx +++ b/ja/built-in-nodes/LTXAVTextEncoderLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXAVTextEncoderLoader" icon: "circle" mode: wide --- + このノードは、LTXVオーディオモデル用の特殊なテキストエンコーダを読み込みます。特定のテキストエンコーダファイルとチェックポイントファイルを組み合わせて、オーディオ関連のテキスト条件付けタスクに使用できるCLIPモデルを作成します。 ## 入力 diff --git a/ja/built-in-nodes/LTXVAddGuide.mdx b/ja/built-in-nodes/LTXVAddGuide.mdx index 1ce89b081..9e8a26d4b 100644 --- a/ja/built-in-nodes/LTXVAddGuide.mdx +++ b/ja/built-in-nodes/LTXVAddGuide.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAddGuide" icon: "circle" mode: wide --- + 以下は、提供された英語ドキュメントを日本語に翻訳したものです。 LTXVAddGuide ノードは、入力画像または動画をエンコードし、それらをキーフレームとして条件付けデータに組み込むことで、潜在シーケンスに動画条件付けガイダンスを追加します。このノードは、VAEエンコーダーを通じて入力を処理し、結果の潜在表現を指定されたフレーム位置に戦略的に配置するとともに、キーフレーム情報でポジティブ条件付けとネガティブ条件付けの両方を更新します。また、フレーム位置合わせの制約を処理し、条件付けの影響の強さを制御できます。 @@ -27,8 +28,8 @@ LTXVAddGuide ノードは、入力画像または動画をエンコードし、 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | キーフレームガイダンス情報で更新されたポジティブ条件付け | CONDITIONING | -| `潜在` | キーフレームガイダンス情報で更新されたネガティブ条件付け | CONDITIONING | +| `ポジティブ` | キーフレームガイダンス情報で更新されたポジティブ条件付け | CONDITIONING | +| `ネガティブ` | キーフレームガイダンス情報で更新されたネガティブ条件付け | CONDITIONING | | `潜在` | 条件付けフレームと更新されたノイズマスクが組み込まれた潜在シーケンス | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAddGuide/ja.md) diff --git a/ja/built-in-nodes/LTXVAudioVAEDecode.mdx b/ja/built-in-nodes/LTXVAudioVAEDecode.mdx index 35b2c0fc4..01d017fc9 100644 --- a/ja/built-in-nodes/LTXVAudioVAEDecode.mdx +++ b/ja/built-in-nodes/LTXVAudioVAEDecode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAEDecode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご貢献ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAEDecode/en.md) LTXV Audio VAE Decodeノードは、音声の潜在表現をオーディオ波形に戻す処理を行います。専用のAudio VAEモデルを使用してこのデコード処理を実行し、特定のサンプルレートを持つオーディオ出力を生成します。 diff --git a/ja/built-in-nodes/LTXVAudioVAEEncode.mdx b/ja/built-in-nodes/LTXVAudioVAEEncode.mdx index f5756d670..75c8715cb 100644 --- a/ja/built-in-nodes/LTXVAudioVAEEncode.mdx +++ b/ja/built-in-nodes/LTXVAudioVAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAEEncode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LTXV Audio VAE Encode ノードは、オーディオ入力を受け取り、指定された Audio VAE モデルを使用して、より小さな潜在表現に圧縮します。この処理は、潜在空間ワークフロー内でオーディオを生成または操作するために不可欠であり、生のオーディオデータをパイプライン内の他のノードが理解・処理できる形式に変換します。 diff --git a/ja/built-in-nodes/LTXVAudioVAELoader.mdx b/ja/built-in-nodes/LTXVAudioVAELoader.mdx index d1d2d11fa..ddc5dd6ac 100644 --- a/ja/built-in-nodes/LTXVAudioVAELoader.mdx +++ b/ja/built-in-nodes/LTXVAudioVAELoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAELoader" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/LTXVConcatAVLatent.mdx b/ja/built-in-nodes/LTXVConcatAVLatent.mdx index 2123a3d26..fd8e5a82e 100644 --- a/ja/built-in-nodes/LTXVConcatAVLatent.mdx +++ b/ja/built-in-nodes/LTXVConcatAVLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVConcatAVLatent" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LTXVConcatAVLatentノードは、ビデオ潜在表現とオーディオ潜在表現を結合し、単一の連結された潜在出力を生成します。両方の入力からの`samples`テンソルをマージし、存在する場合はそれらの`noise_mask`テンソルも同様にマージして、ビデオ生成パイプラインでのさらなる処理に備えます。 diff --git a/ja/built-in-nodes/LTXVConditioning.mdx b/ja/built-in-nodes/LTXVConditioning.mdx index 321bd2586..1b2dd62b5 100644 --- a/ja/built-in-nodes/LTXVConditioning.mdx +++ b/ja/built-in-nodes/LTXVConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVConditioning" icon: "circle" mode: wide --- + 以下は、ご指定の翻訳ルールに従った日本語訳です。 LTXVConditioning ノードは、動画生成モデル向けに、ポジティブおよびネガティブの両方の conditioning 入力にフレームレート情報を追加します。既存の conditioning データを受け取り、指定されたフレームレート値を両方の conditioning セットに適用することで、動画モデルの処理に適した状態にします。 @@ -21,7 +22,7 @@ LTXVConditioning ノードは、動画生成モデル向けに、ポジティブ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | フレームレート情報が適用されたポジティブ conditioning | CONDITIONING | +| `ポジティブ` | フレームレート情報が適用されたポジティブ conditioning | CONDITIONING | | `ネガティブ` | フレームレート情報が適用されたネガティブ conditioning | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVConditioning/ja.md) diff --git a/ja/built-in-nodes/LTXVContextWindows.mdx b/ja/built-in-nodes/LTXVContextWindows.mdx new file mode 100644 index 000000000..6666613f4 --- /dev/null +++ b/ja/built-in-nodes/LTXVContextWindows.mdx @@ -0,0 +1,37 @@ +--- +title: "LTXVContextWindows - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LTXVContextWindows node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LTXVContextWindows" +icon: "circle" +mode: wide +--- + +このノードは、サンプリング中にLTXVライクなモデルにコンテキストウィンドウを設定します。動画生成プロセスを重複するウィンドウに分割することで、メモリ使用量を管理し、時間的な一貫性を向上させます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `model` | サンプリング中にコンテキストウィンドウを適用するモデル。 | MODEL | はい | - | +| `context_length` | 実フレーム単位でのコンテキストウィンドウの長さ。8*n + 1 である必要があります。（デフォルト：145） | INT | はい | 最小：1
最大：nodes.MAX_RESOLUTION
ステップ：8 | +| `context_overlap` | 実フレーム単位でのコンテキストウィンドウの重複。（デフォルト：40） | INT | はい | 最小：0
ステップ：8 | +| `context_schedule` | コンテキストウィンドウのステップ依存スケジューリングアルゴリズム。（デフォルト：UNIFORM_STANDARD） | COMBO | はい | `STATIC_STANDARD`
`UNIFORM_STANDARD`
`UNIFORM_LOOPED`
`BATCHED` | +| `context_stride` | コンテキストウィンドウのストライド。均一スケジュールにのみ適用可能。（デフォルト：1） | INT | いいえ | 最小：1 | +| `closed_loop` | コンテキストウィンドウのループを閉じるかどうか。ループスケジュールにのみ適用可能。（デフォルト：False） | BOOLEAN | いいえ | True
False | +| `fuse_method` | コンテキストウィンドウを融合するために使用する方法。（デフォルト：PYRAMID） | COMBO | はい | comfy.context_windows.ContextFuseMethods.LIST_STATIC のオプション | +| `freenoise` | FreeNoiseノイズシャッフリングを適用するかどうか。ウィンドウのブレンドを改善します。（デフォルト：True） | BOOLEAN | いいえ | True
False | +| `retain_first_frame` | すべてのコンテキストウィンドウで最初の潜在フレームを保持します（初期参照の保持に役立つ場合があります）。（デフォルト：False） | BOOLEAN | いいえ | True
False | +| `split_conds_to_windows` | ConditionCombineで作成された複数のコンディショニングを、リージョンインデックスに基づいて各ウィンドウに分割するかどうか。（デフォルト：False） | BOOLEAN | いいえ | True
False | + +**注記：** `context_length` パラメータは、8*n + 1（nは正の整数）という式に従う必要があります。ノードは、実フレームを潜在フレームに変換することで、この要件を満たすように値を自動的に調整します。`context_overlap` も実フレームから潜在フレームに変換されます（8で除算されます）。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `MODEL` | サンプリング用にコンテキストウィンドウが適用されたモデル。 | MODEL | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVContextWindows/ja.md) + +--- +**Source fingerprint (SHA-256):** `ad0b8c54acaab1853f6fe98dbad675478f033caf867df954b40b7db5208f5ae4` diff --git a/ja/built-in-nodes/LTXVCropGuides.mdx b/ja/built-in-nodes/LTXVCropGuides.mdx index 54315854b..c5b4dd92b 100644 --- a/ja/built-in-nodes/LTXVCropGuides.mdx +++ b/ja/built-in-nodes/LTXVCropGuides.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVCropGuides" icon: "circle" mode: wide --- + LTXVCropGuides ノードは、キーフレーム情報を除去し、潜在空間の次元を調整することで、動画生成のための条件付け入力と潜在入力を処理します。潜在画像とノイズマスクをクロップしてキーフレーム部分を除外し、ポジティブ条件付けとネガティブ条件付けの両方からキーフレームインデックスをクリアします。これにより、キーフレームガイダンスを必要としない動画生成ワークフロー向けにデータを準備します。 ## 入力 @@ -19,8 +20,8 @@ LTXVCropGuides ノードは、キーフレーム情報を除去し、潜在空 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | キーフレームインデックスとガイドアテンションエントリがクリアされた、処理済みのポジティブ条件付け | CONDITIONING | -| `潜在` | キーフレームインデックスとガイドアテンションエントリがクリアされた、処理済みのネガティブ条件付け | CONDITIONING | +| `ポジティブ` | キーフレームインデックスとガイドアテンションエントリがクリアされた、処理済みのポジティブ条件付け | CONDITIONING | +| `ネガティブ` | キーフレームインデックスとガイドアテンションエントリがクリアされた、処理済みのネガティブ条件付け | CONDITIONING | | `潜在` | キーフレーム部分が除去され、サンプルとノイズマスクが調整された、クロップ済みの潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVCropGuides/ja.md) diff --git a/ja/built-in-nodes/LTXVEmptyLatentAudio.mdx b/ja/built-in-nodes/LTXVEmptyLatentAudio.mdx index 33dcdf695..4001c144f 100644 --- a/ja/built-in-nodes/LTXVEmptyLatentAudio.mdx +++ b/ja/built-in-nodes/LTXVEmptyLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVEmptyLatentAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/LTXVImgToVideo.mdx b/ja/built-in-nodes/LTXVImgToVideo.mdx index aaba55b6d..0e8fbfbb7 100644 --- a/ja/built-in-nodes/LTXVImgToVideo.mdx +++ b/ja/built-in-nodes/LTXVImgToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVImgToVideo" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LTXVImgToVideo ノードは、入力画像を動画生成モデル用の動画潜在表現に変換します。単一の画像を受け取り、VAE エンコーダを使用して一連のフレームに拡張し、強度制御による条件付けを適用して、動画生成中に元の画像コンテンツがどの程度保持されるか、または変更されるかを決定します。 @@ -27,9 +28,9 @@ LTXVImgToVideo ノードは、入力画像を動画生成モデル用の動画 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 動画フレームマスキングが適用された処理済みポジティブ条件付け | CONDITIONING | -| `潜在` | 動画フレームマスキングが適用された処理済みネガティブ条件付け | CONDITIONING | -| `latent` | エンコードされたフレームと動画生成用のノイズマスクを含む動画潜在表現 | LATENT | +| `ポジティブ` | 動画フレームマスキングが適用された処理済みポジティブ条件付け | CONDITIONING | +| `ネガティブ` | 動画フレームマスキングが適用された処理済みネガティブ条件付け | CONDITIONING | +| `潜在` | エンコードされたフレームと動画生成用のノイズマスクを含む動画潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVImgToVideo/ja.md) diff --git a/ja/built-in-nodes/LTXVImgToVideoInplace.mdx b/ja/built-in-nodes/LTXVImgToVideoInplace.mdx index 4af736495..99f0cd1c6 100644 --- a/ja/built-in-nodes/LTXVImgToVideoInplace.mdx +++ b/ja/built-in-nodes/LTXVImgToVideoInplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVImgToVideoInplace" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LTXVImgToVideoInplace ノードは、入力画像を初期フレームにエンコードすることで、ビデオ潜在表現を条件付けします。このノードは、VAE を使用して画像を潜在空間にエンコードし、指定された強度に基づいて既存の潜在サンプルとブレンドすることで機能します。これにより、画像をビデオ生成の開始点または条件付け信号として使用できます。 diff --git a/ja/built-in-nodes/LTXVLatentUpsampler.mdx b/ja/built-in-nodes/LTXVLatentUpsampler.mdx index 79df036bc..e3b9dcfb8 100644 --- a/ja/built-in-nodes/LTXVLatentUpsampler.mdx +++ b/ja/built-in-nodes/LTXVLatentUpsampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVLatentUpsampler" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LTXVLatentUpsampler ノードは、ビデオの潜在表現の空間解像度を2倍に拡大します。専用のアップスケールモデルを使用して潜在データを処理し、まず非正規化を行った後、指定されたVAEのチャンネル統計情報を用いて再正規化を実行します。このノードは、潜在空間内でのビデオワークフロー向けに設計されています。 diff --git a/ja/built-in-nodes/LTXVPreprocess.mdx b/ja/built-in-nodes/LTXVPreprocess.mdx index d68dbdd25..2a93ea060 100644 --- a/ja/built-in-nodes/LTXVPreprocess.mdx +++ b/ja/built-in-nodes/LTXVPreprocess.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVPreprocess" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LTXVPreprocess ノードは、画像に圧縮前処理を適用します。入力画像を受け取り、指定された圧縮レベルで処理を行い、適用された圧縮設定とともに処理済み画像を出力します。 @@ -20,7 +21,7 @@ LTXVPreprocess ノードは、画像に圧縮前処理を適用します。入 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `output_image` | 圧縮が適用された処理済みの出力画像 | IMAGE | +| `出力画像` | 圧縮が適用された処理済みの出力画像 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVPreprocess/ja.md) diff --git a/ja/built-in-nodes/LTXVReferenceAudio.mdx b/ja/built-in-nodes/LTXVReferenceAudio.mdx index ede109b7f..358811f76 100644 --- a/ja/built-in-nodes/LTXVReferenceAudio.mdx +++ b/ja/built-in-nodes/LTXVReferenceAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVReferenceAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LTXV リファレンスオーディオノードは、音声生成における話者同一性の転送に使用されます。リファレンスとなるオーディオクリップをモデルの条件付け（コンディショニング）にエンコードし、生成される音声がその話者の声の特徴を採用できるようにします。また、同一性ガイダンスを適用することも可能で、これにより追加の処理ステップを実行して話者同一性の効果を増幅します。 @@ -27,7 +28,7 @@ LTXV リファレンスオーディオノードは、音声生成における話 | 出力名 | 説明 | データ型 | | --- | --- | --- | | `positive` | 同一性ガイダンス機能でパッチ適用されたモデル。 | MODEL | -| `negative` | エンコードされたリファレンスオーディオデータを含む、ポジティブな条件付け。 | CONDITIONING | +| `positive` | エンコードされたリファレンスオーディオデータを含む、ポジティブな条件付け。 | CONDITIONING | | `negative` | エンコードされたリファレンスオーディオデータを含む、ネガティブな条件付け。 | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVReferenceAudio/ja.md) diff --git a/ja/built-in-nodes/LTXVScheduler.mdx b/ja/built-in-nodes/LTXVScheduler.mdx index 6cc7acbcb..3f1952f92 100644 --- a/ja/built-in-nodes/LTXVScheduler.mdx +++ b/ja/built-in-nodes/LTXVScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVScheduler" icon: "circle" mode: wide --- + LTXVScheduler ノードは、カスタムサンプリングプロセス用のシグマ値を生成します。入力潜在変数内のトークン数に基づいてノイズスケジュールパラメータを計算し、シグモイド変換を適用してサンプリングスケジュールを作成します。このノードは、必要に応じて結果のシグマを指定された終端値に一致するように引き伸ばすこともできます。 ## 入力 diff --git a/ja/built-in-nodes/LTXVSeparateAVLatent.mdx b/ja/built-in-nodes/LTXVSeparateAVLatent.mdx index 7cdd35137..f612a442f 100644 --- a/ja/built-in-nodes/LTXVSeparateAVLatent.mdx +++ b/ja/built-in-nodes/LTXVSeparateAVLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVSeparateAVLatent" icon: "circle" mode: wide --- + LTXVSeparateAVLatent ノードは、結合された音声・映像の潜在表現を受け取り、それを映像用と音声用の2つの個別の部分に分割します。入力された潜在表現からサンプルを分離し、ノイズマスクが存在する場合も同様に分割して、2つの新しい潜在オブジェクトを作成します。 ## 入力 @@ -19,8 +20,8 @@ LTXVSeparateAVLatent ノードは、結合された音声・映像の潜在表 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `オーディオlatent` | 分割された映像データを含む潜在表現です。 | LATENT | -| `audio_latent` | 分割された音声データを含む潜在表現です。 | LATENT | +| `ビデオlatent` | 分割された映像データを含む潜在表現です。 | LATENT | +| `オーディオlatent` | 分割された音声データを含む潜在表現です。 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVSeparateAVLatent/ja.md) diff --git a/ja/built-in-nodes/LaplaceScheduler.mdx b/ja/built-in-nodes/LaplaceScheduler.mdx index 9098fc0de..49ff5580c 100644 --- a/ja/built-in-nodes/LaplaceScheduler.mdx +++ b/ja/built-in-nodes/LaplaceScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LaplaceScheduler" icon: "circle" mode: wide --- + LaplaceSchedulerノードは、拡散サンプリングで使用するラプラス分布に従ったシグマ値のシーケンスを生成します。このノードは、ラプラス分布のパラメータを使用して進行を制御しながら、最大値から最小値へと徐々に減少するノイズレベルのスケジュールを作成します。このスケジューラーは、カスタムサンプリングワークフローにおいて拡散モデルのノイズスケジュールを定義するために一般的に使用されます。 ## 入力 diff --git a/ja/built-in-nodes/LatentAdd.mdx b/ja/built-in-nodes/LatentAdd.mdx index 927613737..1749a5dfb 100644 --- a/ja/built-in-nodes/LatentAdd.mdx +++ b/ja/built-in-nodes/LatentAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentAdd" icon: "circle" mode: wide --- + LatentAddノードは、2つの潜在表現を加算するために設計されています。これらの表現にエンコードされた特徴や特性を、要素ごとの加算によって組み合わせる機能を提供します。 ## 入力 diff --git a/ja/built-in-nodes/LatentApplyOperation.mdx b/ja/built-in-nodes/LatentApplyOperation.mdx index 8ffe20360..87b44706b 100644 --- a/ja/built-in-nodes/LatentApplyOperation.mdx +++ b/ja/built-in-nodes/LatentApplyOperation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentApplyOperation" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LatentApplyOperation ノードは、指定された操作を潜在サンプルに適用します。このノードは、潜在データと操作を入力として受け取り、提供された操作を使用して潜在サンプルを処理し、変更された潜在データを返します。このノードを使用すると、ワークフロー内で潜在表現を変換または操作できます。 diff --git a/ja/built-in-nodes/LatentApplyOperationCFG.mdx b/ja/built-in-nodes/LatentApplyOperationCFG.mdx index 8a9bce171..9114f77d0 100644 --- a/ja/built-in-nodes/LatentApplyOperationCFG.mdx +++ b/ja/built-in-nodes/LatentApplyOperationCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentApplyOperationCFG" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LatentApplyOperationCFG ノードは、潜在操作を適用してモデル内の条件付けガイダンスプロセスを変更します。このノードは、分類器フリーガイダンス（CFG）サンプリングプロセス中に条件付け出力をインターセプトし、生成に使用される前に潜在表現に指定された操作を適用することで機能します。 diff --git a/ja/built-in-nodes/LatentBatch.mdx b/ja/built-in-nodes/LatentBatch.mdx index 15134893c..58d44eae0 100644 --- a/ja/built-in-nodes/LatentBatch.mdx +++ b/ja/built-in-nodes/LatentBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBatch" icon: "circle" mode: wide --- + LatentBatchノードは、2つの潜在サンプルセットを1つのバッチに統合し、必要に応じて一方のセットのサイズをもう一方に合わせてリサイズした上で連結します。この操作により、異なる潜在表現を組み合わせて、さらなる処理や生成タスクに利用できるようになります。 ## 入力 diff --git a/ja/built-in-nodes/LatentBatchSeedBehavior.mdx b/ja/built-in-nodes/LatentBatchSeedBehavior.mdx index 6cf3b2b1c..861f9d583 100644 --- a/ja/built-in-nodes/LatentBatchSeedBehavior.mdx +++ b/ja/built-in-nodes/LatentBatchSeedBehavior.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBatchSeedBehavior" icon: "circle" mode: wide --- + LatentBatchSeedBehavior ノードは、潜在サンプルのバッチにおけるシード動作を変更するために設計されています。このノードにより、バッチ全体でシードをランダム化または固定化することができ、生成プロセスにばらつきをもたらすか、一貫性を維持するかを選択できます。 ## 入力 diff --git a/ja/built-in-nodes/LatentBlend.mdx b/ja/built-in-nodes/LatentBlend.mdx index 3b90e7225..5d73358cd 100644 --- a/ja/built-in-nodes/LatentBlend.mdx +++ b/ja/built-in-nodes/LatentBlend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBlend" icon: "circle" mode: wide --- + 以下は、ご指定の翻訳ルールに従って英語ドキュメントを日本語に翻訳したものです。 LatentBlend ノードは、指定されたブレンド係数を使用して2つの潜在サンプルを結合します。2つの潜在入力を受け取り、最初のサンプルがブレンド係数で重み付けされ、2番目のサンプルがその逆数で重み付けされた新しい出力を作成します。入力サンプルの形状が異なる場合、2番目のサンプルは自動的に最初のサンプルの寸法に合わせてリサイズされます。 diff --git a/ja/built-in-nodes/LatentComposite.mdx b/ja/built-in-nodes/LatentComposite.mdx index 0882f508c..dafbae033 100644 --- a/ja/built-in-nodes/LatentComposite.mdx +++ b/ja/built-in-nodes/LatentComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentComposite" icon: "circle" mode: wide --- + LatentCompositeノードは、2つの潜在表現を1つの出力にブレンドまたはマージするために設計されています。この処理は、入力された潜在表現の特性を制御された方法で組み合わせることで、合成画像や特徴を作成するために不可欠です。 ## 入力 diff --git a/ja/built-in-nodes/LatentCompositeMasked.mdx b/ja/built-in-nodes/LatentCompositeMasked.mdx index a7618fb0a..9bd3ade9d 100644 --- a/ja/built-in-nodes/LatentCompositeMasked.mdx +++ b/ja/built-in-nodes/LatentCompositeMasked.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCompositeMasked" icon: "circle" mode: wide --- + 以下は、ご依頼いただいたComfyUIノードドキュメントの日本語訳です。 --- diff --git a/ja/built-in-nodes/LatentConcat.mdx b/ja/built-in-nodes/LatentConcat.mdx index 234a83508..cf2a7263d 100644 --- a/ja/built-in-nodes/LatentConcat.mdx +++ b/ja/built-in-nodes/LatentConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentConcat" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LatentConcat ノードは、2つの潜在サンプルを選択した次元に沿って結合します。2つの潜在入力を x、y、または t 軸に沿って連結し、どちらのサンプルを先に配置するかを制御するオプションを備えています。このノードは、連結を実行する前に、2番目の入力のバッチサイズを最初の入力に自動的に合わせます。 diff --git a/ja/built-in-nodes/LatentCrop.mdx b/ja/built-in-nodes/LatentCrop.mdx index 05f43286d..abc470b4f 100644 --- a/ja/built-in-nodes/LatentCrop.mdx +++ b/ja/built-in-nodes/LatentCrop.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCrop" icon: "circle" mode: wide --- + LatentCropノードは、画像の潜在表現に対してクロッピング（切り抜き）操作を実行するために設計されています。クロップの寸法と位置を指定することで、潜在空間に対する対象を絞った変更を可能にします。 ## 入力 diff --git a/ja/built-in-nodes/LatentCut.mdx b/ja/built-in-nodes/LatentCut.mdx index 8c8006520..768fe9193 100644 --- a/ja/built-in-nodes/LatentCut.mdx +++ b/ja/built-in-nodes/LatentCut.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCut" icon: "circle" mode: wide --- + 以下は、ご指定の翻訳ルールに従って日本語に翻訳した ComfyUI ノードドキュメントです。 --- diff --git a/ja/built-in-nodes/LatentCutToBatch.mdx b/ja/built-in-nodes/LatentCutToBatch.mdx index 096fcfc17..9b627d790 100644 --- a/ja/built-in-nodes/LatentCutToBatch.mdx +++ b/ja/built-in-nodes/LatentCutToBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCutToBatch" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentCutToBatch/en.md) LatentCutToBatchノードは、潜在表現を選択した次元に沿って複数のスライスに分割し、それらを新しいバッチにスタックします。これにより、潜在サンプルの異なる部分を独立して処理できるようになります。 diff --git a/ja/built-in-nodes/LatentFlip.mdx b/ja/built-in-nodes/LatentFlip.mdx index da097ae9e..d7644c809 100644 --- a/ja/built-in-nodes/LatentFlip.mdx +++ b/ja/built-in-nodes/LatentFlip.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentFlip" icon: "circle" mode: wide --- + 以下は、提供された英語ドキュメントを日本語に翻訳したものです。 --- diff --git a/ja/built-in-nodes/LatentFromBatch.mdx b/ja/built-in-nodes/LatentFromBatch.mdx index 6aa219bc6..2f96e8566 100644 --- a/ja/built-in-nodes/LatentFromBatch.mdx +++ b/ja/built-in-nodes/LatentFromBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentFromBatch" icon: "circle" mode: wide --- + このノードは、指定されたバッチインデックスと長さに基づいて、特定の潜在サンプルのサブセットをバッチから抽出するように設計されています。潜在サンプルの選択的な処理を可能にし、効率化やターゲットを絞った操作のためにバッチの小さなセグメントに対する操作を容易にします。 ## 入力 diff --git a/ja/built-in-nodes/LatentInterpolate.mdx b/ja/built-in-nodes/LatentInterpolate.mdx index 1eb8bc1a0..a07c3a45c 100644 --- a/ja/built-in-nodes/LatentInterpolate.mdx +++ b/ja/built-in-nodes/LatentInterpolate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentInterpolate" icon: "circle" mode: wide --- + 以下が翻訳です。 LatentInterpolateノードは、指定された比率に基づいて2つの潜在サンプルセット間の補間を実行し、両方のセットの特性をブレンドして、新しい中間的な潜在サンプルセットを生成するように設計されています。 diff --git a/ja/built-in-nodes/LatentMultiply.mdx b/ja/built-in-nodes/LatentMultiply.mdx index 6d25bb110..cfa6d1f22 100644 --- a/ja/built-in-nodes/LatentMultiply.mdx +++ b/ja/built-in-nodes/LatentMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentMultiply" icon: "circle" mode: wide --- + ### LatentMultiply ノード LatentMultiplyノードは、サンプルの潜在表現を指定された倍率でスケーリングするように設計されています。この操作により、潜在空間内の特徴の強度や大きさを調整することができ、生成コンテンツの微調整や、特定の潜在方向におけるバリエーションの探索が可能になります。 diff --git a/ja/built-in-nodes/LatentOperationSharpen.mdx b/ja/built-in-nodes/LatentOperationSharpen.mdx index 4a103a365..19521c7b0 100644 --- a/ja/built-in-nodes/LatentOperationSharpen.mdx +++ b/ja/built-in-nodes/LatentOperationSharpen.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentOperationSharpen" icon: "circle" mode: wide --- + ## 概要 LatentOperationSharpen ノードは、ガウシアンカーネルを使用して潜在表現にシャープネス効果を適用します。潜在データを正規化し、カスタムシャープニングカーネルで畳み込みを適用した後、元の輝度を復元することで動作します。これにより、潜在空間表現のディテールとエッジが強調されます。 ## 入力 diff --git a/ja/built-in-nodes/LatentOperationTonemapReinhard.mdx b/ja/built-in-nodes/LatentOperationTonemapReinhard.mdx index dbf0b8826..a3786c91f 100644 --- a/ja/built-in-nodes/LatentOperationTonemapReinhard.mdx +++ b/ja/built-in-nodes/LatentOperationTonemapReinhard.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentOperationTonemapReinhard" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LatentOperationTonemapReinhard ノードは、潜在ベクトルに Reinhard トーンマッピングを適用します。この手法は、平均と標準偏差に基づく統計的アプローチを使用して潜在ベクトルを正規化し、その大きさを調整します。強度は乗数パラメータによって制御されます。 diff --git a/ja/built-in-nodes/LatentRotate.mdx b/ja/built-in-nodes/LatentRotate.mdx index 66d13417e..408c4996e 100644 --- a/ja/built-in-nodes/LatentRotate.mdx +++ b/ja/built-in-nodes/LatentRotate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentRotate" icon: "circle" mode: wide --- + LatentRotate ノードは、指定された角度に応じて画像の潜在表現を回転させるために設計されています。潜在空間を操作して回転効果を実現する複雑さを抽象化し、ユーザーが生成モデルの潜在空間内で画像を簡単に変換できるようにします。 ## 入力 diff --git a/ja/built-in-nodes/LatentSubtract.mdx b/ja/built-in-nodes/LatentSubtract.mdx index 8b43dda2e..2dab6ae22 100644 --- a/ja/built-in-nodes/LatentSubtract.mdx +++ b/ja/built-in-nodes/LatentSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentSubtract" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LatentSubtractノードは、ある潜在表現から別の潜在表現を減算するために設計されています。この操作は、一方の潜在空間に表現された特徴や属性を効果的に除去することで、生成モデルの出力特性を操作または変更するために使用できます。 diff --git a/ja/built-in-nodes/LatentUpscale.mdx b/ja/built-in-nodes/LatentUpscale.mdx index 8cbe67438..a20da91d3 100644 --- a/ja/built-in-nodes/LatentUpscale.mdx +++ b/ja/built-in-nodes/LatentUpscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscale" icon: "circle" mode: wide --- + LatentUpscale ノードは、画像の潜在表現をアップスケールするために設計されています。出力画像の寸法やアップスケール方法を調整でき、潜在画像の解像度を柔軟に向上させることができます。 ## 入力 diff --git a/ja/built-in-nodes/LatentUpscaleBy.mdx b/ja/built-in-nodes/LatentUpscaleBy.mdx index f714def34..d601e2b12 100644 --- a/ja/built-in-nodes/LatentUpscaleBy.mdx +++ b/ja/built-in-nodes/LatentUpscaleBy.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscaleBy" icon: "circle" mode: wide --- + LatentUpscaleBy ノードは、画像の潜在表現をアップスケーリングするために設計されています。スケール係数やアップスケーリング方法の調整が可能で、潜在サンプルの解像度を柔軟に向上させることができます。 ## 入力 diff --git a/ja/built-in-nodes/LatentUpscaleModelLoader.mdx b/ja/built-in-nodes/LatentUpscaleModelLoader.mdx index a4bf05858..9efee011e 100644 --- a/ja/built-in-nodes/LatentUpscaleModelLoader.mdx +++ b/ja/built-in-nodes/LatentUpscaleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscaleModelLoader" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要概要 diff --git a/ja/built-in-nodes/LazyCache.mdx b/ja/built-in-nodes/LazyCache.mdx index d9504f6b9..17ffc44ad 100644 --- a/ja/built-in-nodes/LazyCache.mdx +++ b/ja/built-in-nodes/LazyCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LazyCache" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LazyCache は、EasyCache の自家製バージョンであり、さらに簡単な実装を提供します。ComfyUI の任意のモデルで動作し、キャッシュ機能を追加してサンプリング中の計算を削減します。一般的には EasyCache よりも性能が劣りますが、まれに効果が高い場合があり、ユニバーサルな互換性を備えています。 diff --git a/ja/built-in-nodes/Load3D.mdx b/ja/built-in-nodes/Load3D.mdx index 241f2c334..67166095f 100644 --- a/ja/built-in-nodes/Load3D.mdx +++ b/ja/built-in-nodes/Load3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Load3D" icon: "circle" mode: wide --- + Load3Dノードは、3Dモデルファイルを読み込み、処理するためのコアノードです。ノードを読み込むと、`ComfyUI/input/3d/`から利用可能な3Dリソースを自動的に取得します。また、アップロード機能を使用して、対応する3Dファイルをアップロードし、プレビューすることもできます。 **対応フォーマット** diff --git a/ja/built-in-nodes/Load3DAdvanced.mdx b/ja/built-in-nodes/Load3DAdvanced.mdx new file mode 100644 index 000000000..b641bebb7 --- /dev/null +++ b/ja/built-in-nodes/Load3DAdvanced.mdx @@ -0,0 +1,38 @@ +--- +title: "Load3DAdvanced - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the Load3DAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "Load3DAdvanced" +icon: "circle" +mode: wide +--- + +このノードは、ComfyUIの入力ディレクトリから3Dモデルファイルを読み込み、カメラおよびビューポート情報とともにモデルデータを提供します。一般的な3Dファイル形式をサポートしており、レンダリング用の出力画像サイズを指定できます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `model_file` | 読み込む3Dモデルファイル。モデルの読み込みをスキップするには"none"を選択します。 | STRING | はい | `"none"`
input/3dディレクトリ内の利用可能な3Dファイルのリスト | +| `viewport_state` | 3Dビューアからのカメラとモデル情報を含む現在のビューポート状態。 | LOAD3D | はい | - | +| `width` | 出力画像の幅（ピクセル単位、デフォルト：1024） | INT | はい | 最小：1
最大：4096
ステップ：1 | +| `height` | 出力画像の高さ（ピクセル単位、デフォルト：1024） | INT | はい | 最小：1
最大：4096
ステップ：1 | + +**パラメータに関する注意事項：** +- `model_file`パラメータは、次の拡張子を持つファイルのみを表示します：.gltf、.glb、.obj、.fbx、.stl +- ファイルはComfyUIインストール先の`input/3d`ディレクトリに配置する必要があります +- `model_file`が"none"に設定されている場合、3Dモデルデータは読み込まれません（出力`model_3d`は空になります） + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `model_3d` | 読み込まれた3Dモデルデータ。モデルファイルが選択されていない場合は空。 | FILE3DANY | +| `model_3d_info` | ビューポート状態から取得した、読み込まれた3Dモデルに関する情報。 | LOAD3DMODELINFO | +| `camera_info` | ビューポート状態から取得したカメラ情報。 | LOAD3DCAMERA | +| `width` | 指定された出力画像の幅。 | INT | +| `height` | 指定された出力画像の高さ。 | INT | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Load3DAdvanced/ja.md) + +--- +**Source fingerprint (SHA-256):** `fdacea8abf627621150e1196743e36f61534333837c33cc9a7416a6d11700c4d` diff --git a/ja/built-in-nodes/Load3DAnimation.mdx b/ja/built-in-nodes/Load3DAnimation.mdx index 93856f0dd..455569410 100644 --- a/ja/built-in-nodes/Load3DAnimation.mdx +++ b/ja/built-in-nodes/Load3DAnimation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Load3DAnimation" icon: "circle" mode: wide --- + 以下は、ご依頼いただいた英語ドキュメントを日本語に翻訳したものです。 --- diff --git a/ja/built-in-nodes/LoadAudio.mdx b/ja/built-in-nodes/LoadAudio.mdx index e10a98d33..dfe71e3e7 100644 --- a/ja/built-in-nodes/LoadAudio.mdx +++ b/ja/built-in-nodes/LoadAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要：概要 diff --git a/ja/built-in-nodes/LoadBackgroundRemovalModel.mdx b/ja/built-in-nodes/LoadBackgroundRemovalModel.mdx index de6bddcde..70c9be718 100644 --- a/ja/built-in-nodes/LoadBackgroundRemovalModel.mdx +++ b/ja/built-in-nodes/LoadBackgroundRemovalModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadBackgroundRemovalModel" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/LoadDA3Model.mdx b/ja/built-in-nodes/LoadDA3Model.mdx new file mode 100644 index 000000000..259518dbb --- /dev/null +++ b/ja/built-in-nodes/LoadDA3Model.mdx @@ -0,0 +1,27 @@ +--- +title: "LoadDA3Model - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LoadDA3Model node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LoadDA3Model" +icon: "circle" +mode: wide +--- + +このノードは、Depth Anything 3 モデルをファイルから読み込み、深度推定タスクで使用できるように準備します。モデルファイルを選択し、必要に応じてモデルの重みの数値精度（データ型）を指定できます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `model_name` | 読み込む Depth Anything 3 モデルファイルの名前です。 | STRING | はい | `geometry_estimation` フォルダ内の利用可能なモデルファイルのリスト | +| `weight_dtype` | モデルの重みの数値精度（データ型）です。"default" オプションはモデルの元の精度を使用します。（デフォルト: "default"） | STRING | いいえ | `"default"`
`"fp16"`
`"bf16"`
`"fp32"` | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `DA3_MODEL` | 読み込まれた Depth Anything 3 モデルです。深度推定ワークフローで使用する準備が整っています。 | DA3_MODEL | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadDA3Model/ja.md) + +--- +**Source fingerprint (SHA-256):** `b1b3f4075cd9172bc1f274848b9300bca20d3cbd53b23d3c4a9f0986b36e409e` diff --git a/ja/built-in-nodes/LoadImage.mdx b/ja/built-in-nodes/LoadImage.mdx index 7fa7ef23d..cecdfa176 100644 --- a/ja/built-in-nodes/LoadImage.mdx +++ b/ja/built-in-nodes/LoadImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImage" icon: "circle" mode: wide --- + LoadImageノードは、指定されたパスから画像を読み込み、前処理するために設計されています。複数フレームを持つ画像形式を処理し、EXIFデータに基づく回転などの必要な変換を適用し、ピクセル値を正規化し、オプションでアルファチャンネルを持つ画像のマスクを生成します。このノードは、パイプライン内でのさらなる処理や分析に備えて画像を準備するために不可欠です。 ## 入力 diff --git a/ja/built-in-nodes/LoadImageDataSetFromFolder.mdx b/ja/built-in-nodes/LoadImageDataSetFromFolder.mdx index b3d10879d..3996ff82a 100644 --- a/ja/built-in-nodes/LoadImageDataSetFromFolder.mdx +++ b/ja/built-in-nodes/LoadImageDataSetFromFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageDataSetFromFolder" icon: "circle" mode: wide --- + このノードは、ComfyUIの入力ディレクトリ内の指定されたサブフォルダから複数の画像を読み込みます。選択されたフォルダ内の一般的な画像ファイル形式をスキャンし、それらをリストとして返します。バッチ処理やデータセットの準備に便利です。 ## 入力 @@ -17,7 +18,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `images` | 読み込まれた画像のリストです。このノードは、選択されたフォルダ内にあるすべての有効な画像ファイル（PNG、JPG、JPEG、WEBP）を読み込みます。 | IMAGE | +| `画像` | 読み込まれた画像のリストです。このノードは、選択されたフォルダ内にあるすべての有効な画像ファイル（PNG、JPG、JPEG、WEBP）を読み込みます。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageDataSetFromFolder/ja.md) diff --git a/ja/built-in-nodes/LoadImageMask.mdx b/ja/built-in-nodes/LoadImageMask.mdx index 1fbd3afc8..e0ffe6060 100644 --- a/ja/built-in-nodes/LoadImageMask.mdx +++ b/ja/built-in-nodes/LoadImageMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageMask" icon: "circle" mode: wide --- + LoadImageMask ノードは、指定されたパスから画像とそれに関連するマスクを読み込み、さらなる画像操作や分析タスクとの互換性を確保するために処理を行います。このノードは、マスク用のアルファチャンネルの有無など、さまざまな画像形式や条件を処理し、画像とマスクを標準化された形式に変換して後続の処理に備えます。 ## 入力 diff --git a/ja/built-in-nodes/LoadImageOutput.mdx b/ja/built-in-nodes/LoadImageOutput.mdx index ce7c1ff56..300898289 100644 --- a/ja/built-in-nodes/LoadImageOutput.mdx +++ b/ja/built-in-nodes/LoadImageOutput.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageOutput" icon: "circle" mode: wide --- + ## 概要 LoadImageOutputノードは、出力フォルダから画像を読み込みます。更新ボタンをクリックすると、利用可能な画像のリストが更新され、最初の画像が自動的に選択されるため、生成した画像を簡単に繰り返し確認できます。 diff --git a/ja/built-in-nodes/LoadImageSetFromFolderNode.mdx b/ja/built-in-nodes/LoadImageSetFromFolderNode.mdx index f9a68001a..ba4606bd6 100644 --- a/ja/built-in-nodes/LoadImageSetFromFolderNode.mdx +++ b/ja/built-in-nodes/LoadImageSetFromFolderNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageSetFromFolderNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/LoadImageSetNode.mdx b/ja/built-in-nodes/LoadImageSetNode.mdx index 58360f5e0..cb422c71f 100644 --- a/ja/built-in-nodes/LoadImageSetNode.mdx +++ b/ja/built-in-nodes/LoadImageSetNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageSetNode" icon: "circle" mode: wide --- + ## 概要 LoadImageSetNode は、バッチ処理やトレーニング目的のために、入力ディレクトリから複数の画像を読み込みます。さまざまな画像形式に対応しており、必要に応じて異なる方法で画像をリサイズすることも可能です。このノードは、選択されたすべての画像をバッチとして処理し、単一のテンソルとして返します。 diff --git a/ja/built-in-nodes/LoadImageTextDataSetFromFolder.mdx b/ja/built-in-nodes/LoadImageTextDataSetFromFolder.mdx index c47b6677b..972ef5ce2 100644 --- a/ja/built-in-nodes/LoadImageTextDataSetFromFolder.mdx +++ b/ja/built-in-nodes/LoadImageTextDataSetFromFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageTextDataSetFromFolder" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご貢献ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextDataSetFromFolder/en.md) このノードは、指定されたフォルダから画像とそれに対応するテキストキャプションのデータセットを読み込みます。画像ファイルを検索し、同じベース名を持つ一致する`.txt`ファイルを自動的に探してキャプションとして使用します。また、サブフォルダ名に数字のプレフィックス（例：`10_folder_name`）を付けることで、そのフォルダ内の画像を出力時に指定回数繰り返す特別なフォルダ構造にも対応しています。 @@ -21,8 +22,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `テキスト` | 読み込まれた画像テンソルのリストです。 | IMAGE | -| `texts` | 各読み込まれた画像に対応するテキストキャプションのリストです。 | STRING | +| `画像` | 読み込まれた画像テンソルのリストです。 | IMAGE | +| `テキスト` | 各読み込まれた画像に対応するテキストキャプションのリストです。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextDataSetFromFolder/ja.md) diff --git a/ja/built-in-nodes/LoadImageTextSetFromFolderNode.mdx b/ja/built-in-nodes/LoadImageTextSetFromFolderNode.mdx index 3d04f2ba6..f79701cd0 100644 --- a/ja/built-in-nodes/LoadImageTextSetFromFolderNode.mdx +++ b/ja/built-in-nodes/LoadImageTextSetFromFolderNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageTextSetFromFolderNode" icon: "circle" mode: wide --- + あなたは ComfyUI ノードドキュメントを英語から日本語に翻訳する技術翻訳の専門家です。 ## 翻訳ルール diff --git a/ja/built-in-nodes/LoadLatent.mdx b/ja/built-in-nodes/LoadLatent.mdx index ee9c9dfa1..d6ffe5d9c 100644 --- a/ja/built-in-nodes/LoadLatent.mdx +++ b/ja/built-in-nodes/LoadLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadLatent" icon: "circle" mode: wide --- + LoadLatentノードは、入力ディレクトリ内の.latentファイルから、以前に保存された潜在表現を読み込みます。ファイルから潜在テンソルデータを読み取り、必要なスケーリング調整を適用した後、他のノードで使用できるように潜在データを返します。 ## 入力 diff --git a/ja/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx b/ja/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx index 8ad8142c8..19a7f7458 100644 --- a/ja/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx +++ b/ja/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadMediaPipeFaceLandmarker" icon: "circle" mode: wide --- + 以下は、指定された翻訳ルールに従って日本語に翻訳したドキュメントです。 --- diff --git a/ja/built-in-nodes/LoadMoGeModel.mdx b/ja/built-in-nodes/LoadMoGeModel.mdx index 085521e16..7d786589a 100644 --- a/ja/built-in-nodes/LoadMoGeModel.mdx +++ b/ja/built-in-nodes/LoadMoGeModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadMoGeModel" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/LoadTrainingDataset.mdx b/ja/built-in-nodes/LoadTrainingDataset.mdx index ac9cf0068..6aa7965bc 100644 --- a/ja/built-in-nodes/LoadTrainingDataset.mdx +++ b/ja/built-in-nodes/LoadTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadTrainingDataset" icon: "circle" mode: wide --- + 以下が翻訳結果です。 このドキュメントは AI によって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadTrainingDataset/en.md) @@ -21,7 +22,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `conditioning` | 潜在辞書のリスト。各辞書にはテンソルを含む `"samples"` キーが含まれます。 | LATENT | +| `latents` | 潜在辞書のリスト。各辞書にはテンソルを含む `"samples"` キーが含まれます。 | LATENT | | `conditioning` | コンディショニングリストのリスト。各内部リストには、対応するサンプルのコンディショニングデータが含まれます。 | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadTrainingDataset/ja.md) diff --git a/ja/built-in-nodes/LoadVideo.mdx b/ja/built-in-nodes/LoadVideo.mdx index d2ce2dc66..b189a8140 100644 --- a/ja/built-in-nodes/LoadVideo.mdx +++ b/ja/built-in-nodes/LoadVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadVideo" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- diff --git a/ja/built-in-nodes/LoraLoader.mdx b/ja/built-in-nodes/LoraLoader.mdx index a997904cd..c9af35ddd 100644 --- a/ja/built-in-nodes/LoraLoader.mdx +++ b/ja/built-in-nodes/LoraLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoader" icon: "circle" mode: wide --- + このノードは、LoRAフォルダ（サブフォルダを含む）内にあるモデルを自動的に検出します。対応するモデルパスは `ComfyUI\models\loras` です。詳細については、「LoRAモデルのインストール」を参照してください。 LoRAローダーノードは、主にLoRAモデルを読み込むために使用します。LoRAモデルは、画像に特定のスタイル、コンテンツ、詳細を与えることができるフィルターのようなものと考えてください。 diff --git a/ja/built-in-nodes/LoraLoaderBypass.mdx b/ja/built-in-nodes/LoraLoaderBypass.mdx index 1e2019f68..6f6093cc8 100644 --- a/ja/built-in-nodes/LoraLoaderBypass.mdx +++ b/ja/built-in-nodes/LoraLoaderBypass.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderBypass" icon: "circle" mode: wide --- + 以下が翻訳結果です。 LoraLoaderBypass ノードは、特別な「バイパス」モードで拡散モデルと CLIP モデルに LoRA（低ランク適応）を適用します。標準の LoRA ローダーとは異なり、この方法はベースモデルの重みを恒久的に変更しません。代わりに、モデルの通常のフォワードパスに LoRA の効果を加算して出力を計算します。これは、トレーニング時や重みがオフロードされたモデルを扱う場合に便利です。 diff --git a/ja/built-in-nodes/LoraLoaderBypassModelOnly.mdx b/ja/built-in-nodes/LoraLoaderBypassModelOnly.mdx index 0732c6c12..59870101a 100644 --- a/ja/built-in-nodes/LoraLoaderBypassModelOnly.mdx +++ b/ja/built-in-nodes/LoraLoaderBypassModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderBypassModelOnly" icon: "circle" mode: wide --- + このノードは、LoRA（Low-Rank Adaptation）をモデルに適用してその動作を変更しますが、モデルコンポーネント自体のみに影響を与えます。指定されたLoRAファイルを読み込み、指定された強度でモデルの重みを調整し、CLIPテキストエンコーダーなどの他のコンポーネントは変更しません。 ## 入力 diff --git a/ja/built-in-nodes/LoraLoaderModelOnly.mdx b/ja/built-in-nodes/LoraLoaderModelOnly.mdx index ebea7eac0..422119064 100644 --- a/ja/built-in-nodes/LoraLoaderModelOnly.mdx +++ b/ja/built-in-nodes/LoraLoaderModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderModelOnly" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/loras` フォルダ内にあるモデルを検出し、さらに extra_model_paths.yaml ファイルで設定された追加パスからもモデルを読み取ります。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、対応するフォルダからモデルファイルを読み取らせる必要があります。 このノードは、CLIP モデルを必要とせずに LoRA モデルを読み込むことに特化しており、LoRA パラメータに基づいて特定のモデルを強化または変更することに重点を置いています。LoRA パラメータを通じてモデルの強度を動的に調整できるため、モデルの動作を細かく制御できます。 diff --git a/ja/built-in-nodes/LoraModelLoader.mdx b/ja/built-in-nodes/LoraModelLoader.mdx index ed2da4da6..2c01d294a 100644 --- a/ja/built-in-nodes/LoraModelLoader.mdx +++ b/ja/built-in-nodes/LoraModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraModelLoader" icon: "circle" mode: wide --- + LoraModelLoaderノードは、学習済みのLoRA（Low-Rank Adaptation）重みを拡散モデルに適用します。学習済みLoRAモデルから重みを読み込み、その影響度を調整することで、ベースモデルを変更します。これにより、ゼロから再学習することなく、拡散モデルの動作をカスタマイズできます。 ## 入力 @@ -22,7 +23,7 @@ LoraModelLoaderノードは、学習済みのLoRA（Low-Rank Adaptation）重み | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデル` | LoRA重みが適用された変更後の拡散モデルです。 | MODEL | +| `model` | LoRA重みが適用された変更後の拡散モデルです。 | MODEL | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraModelLoader/ja.md) diff --git a/ja/built-in-nodes/LoraSave.mdx b/ja/built-in-nodes/LoraSave.mdx index 3b4e0466b..dc65a85d4 100644 --- a/ja/built-in-nodes/LoraSave.mdx +++ b/ja/built-in-nodes/LoraSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraSave" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraSave/en.md) LoraSaveノードは、モデルの差分からLoRA（Low-Rank Adaptation）ファイルを抽出して保存します。拡散モデルの差分、テキストエンコーダの差分、またはその両方を処理し、指定されたランクとタイプでLoRA形式に変換します。生成されたLoRAファイルは、後で使用するために出力ディレクトリに保存されます。 diff --git a/ja/built-in-nodes/LossGraphNode.mdx b/ja/built-in-nodes/LossGraphNode.mdx index 3c2c53843..5c366de0a 100644 --- a/ja/built-in-nodes/LossGraphNode.mdx +++ b/ja/built-in-nodes/LossGraphNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LossGraphNode" icon: "circle" mode: wide --- + このLossGraphNodeは、トレーニング損失値の経時変化を視覚的なグラフとして作成し、プレビュー画像として表示します。トレーニングプロセスからの損失データを受け取り、トレーニングステップ全体での損失の変化を示す折れ線グラフを生成します。生成されたグラフには、軸ラベルと最小/最大損失値が含まれます。 ## 入力 diff --git a/ja/built-in-nodes/LotusConditioning.mdx b/ja/built-in-nodes/LotusConditioning.mdx index 6d1e08cbe..7c8b4f516 100644 --- a/ja/built-in-nodes/LotusConditioning.mdx +++ b/ja/built-in-nodes/LotusConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LotusConditioning" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LotusConditioning/en.md) LotusConditioningノードは、Lotusモデル用に事前計算された条件付け埋め込みを提供します。このノードは、ヌル条件付けを備えた凍結エンコーダーを使用し、推論や大規模なテンソルファイルの読み込みを必要とせずに、ハードコードされたプロンプト埋め込みを返すことで、リファレンス実装との同等性を実現します。このノードは、生成パイプラインで直接使用可能な固定条件付けテンソルを出力します。 @@ -19,7 +20,7 @@ LotusConditioningノードは、Lotusモデル用に事前計算された条件 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `conditioning` | Lotusモデル用の事前計算された条件付け埋め込み。固定プロンプト埋め込みと空の辞書を含みます。 | CONDITIONING | +| `コンディショニング` | Lotusモデル用の事前計算された条件付け埋め込み。固定プロンプト埋め込みと空の辞書を含みます。 | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LotusConditioning/ja.md) diff --git a/ja/built-in-nodes/LtxvApiImageToVideo.mdx b/ja/built-in-nodes/LtxvApiImageToVideo.mdx index 3182422b4..e9c5fe11a 100644 --- a/ja/built-in-nodes/LtxvApiImageToVideo.mdx +++ b/ja/built-in-nodes/LtxvApiImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LtxvApiImageToVideo" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください。[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LtxvApiImageToVideo/en.md) LTXV Image To Video ノードは、1枚の開始画像からプロフェッショナル品質の動画を生成します。外部APIを使用して、テキストプロンプトに基づいた動画シーケンスを作成し、長さ、解像度、フレームレートをカスタマイズすることができます。 diff --git a/ja/built-in-nodes/LtxvApiTextToVideo.mdx b/ja/built-in-nodes/LtxvApiTextToVideo.mdx index aaeacc02d..47686c311 100644 --- a/ja/built-in-nodes/LtxvApiTextToVideo.mdx +++ b/ja/built-in-nodes/LtxvApiTextToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LtxvApiTextToVideo" icon: "circle" mode: wide --- + 以下が日本語翻訳です。 LTXV Text To Video ノードは、テキストによる説明からプロフェッショナル品質の動画を生成します。外部APIに接続して、長さ、解像度、フレームレートをカスタマイズ可能な動画を作成します。AIが生成したオーディオを動画に追加することも選択できます。 diff --git a/ja/built-in-nodes/LumaConceptsNode.mdx b/ja/built-in-nodes/LumaConceptsNode.mdx index f12adbc45..948fde010 100644 --- a/ja/built-in-nodes/LumaConceptsNode.mdx +++ b/ja/built-in-nodes/LumaConceptsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaConceptsNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaConceptsNode/en.md) Luma Text to Video および Luma Image to Video ノードで使用するための、1つ以上のカメラコンセプトを保持します。このノードでは、最大4つのカメラコンセプトを選択し、必要に応じて既存のコンセプトチェーンと組み合わせることができます。 diff --git a/ja/built-in-nodes/LumaImageEditNode2.mdx b/ja/built-in-nodes/LumaImageEditNode2.mdx index 084a7075a..dd91078d5 100644 --- a/ja/built-in-nodes/LumaImageEditNode2.mdx +++ b/ja/built-in-nodes/LumaImageEditNode2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageEditNode2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/LumaImageModifyNode.mdx b/ja/built-in-nodes/LumaImageModifyNode.mdx index 3f9f32a36..625182a53 100644 --- a/ja/built-in-nodes/LumaImageModifyNode.mdx +++ b/ja/built-in-nodes/LumaImageModifyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageModifyNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください。[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageModifyNode/en.md) テキストプロンプトと元画像のアスペクト比に基づいて、画像を同期的に修正します。このノードは入力画像を受け取り、指定されたプロンプトに従って変換を行います。設定可能な画像重みを使用して、元画像がどの程度変更されるかを制御します。 diff --git a/ja/built-in-nodes/LumaImageNode.mdx b/ja/built-in-nodes/LumaImageNode.mdx index 1d2f7dcc2..8f5a35fef 100644 --- a/ja/built-in-nodes/LumaImageNode.mdx +++ b/ja/built-in-nodes/LumaImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 テキストプロンプトとアスペクト比に基づいて画像を同期的に生成します。このノードはテキスト記述を使用して画像を作成し、キャラクター画像やスタイル画像などのさまざまな参照入力を通じて、画像の寸法やスタイルを制御できます。 diff --git a/ja/built-in-nodes/LumaImageNode2.mdx b/ja/built-in-nodes/LumaImageNode2.mdx index dd69d2718..cfa9b6ed4 100644 --- a/ja/built-in-nodes/LumaImageNode2.mdx +++ b/ja/built-in-nodes/LumaImageNode2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageNode2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/LumaImageToVideoNode.mdx b/ja/built-in-nodes/LumaImageToVideoNode.mdx index d06c52538..63cbcf893 100644 --- a/ja/built-in-nodes/LumaImageToVideoNode.mdx +++ b/ja/built-in-nodes/LumaImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageToVideoNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください。[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageToVideoNode/en.md) テキストプロンプトとオプションの開始画像/終了画像に基づいて、同期的に動画を生成します。このノードはLuma APIを使用して動画を作成し、プロンプトを通じて動画のコンテンツを定義し、オプションで最初と最後のフレームを指定して動画の構造を制御できます。 diff --git a/ja/built-in-nodes/LumaRay32ExtendVideoNode.mdx b/ja/built-in-nodes/LumaRay32ExtendVideoNode.mdx new file mode 100644 index 000000000..439045480 --- /dev/null +++ b/ja/built-in-nodes/LumaRay32ExtendVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32ExtendVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32ExtendVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32ExtendVideoNode" +icon: "circle" +mode: wide +--- + +このノードは、以前のLuma Ray 3.2動画生成を拡張し、その後に新しいコンテンツを追加（前方拡張）するか、またはその前に追加（後方拡張）します。以前のLuma Ray 3.2ノードの生成ID出力を接続して、シームレスな5秒の動画拡張を作成します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `source_generation_id` | 拡張対象となる以前のRay 3.2動画の生成ID。別のLuma Ray 3.2ノードのgeneration_id出力を接続します。 | STRING | はい | - | +| `direction` | 「Forward」は以前のクリップの後に続き、「Backward」はその前に追加されます。「Forward（後に続ける）」を選択すると、オプションでループモードを有効にできます。 | COMBO | はい | "Forward (continue after)"
"Backward (lead-in before)" | +| `loop` | 拡張された動画をシームレスにループします（前方拡張のみ）。 | BOOLEAN | いいえ | True
False | +| `prompt` | 生成する新しいコンテンツを説明するテキストプロンプト。 | STRING | はい | - | +| `resolution` | 拡張された動画セグメントの出力解像度。 | COMBO | はい | "540p"
"720p"
"1080p" | +| `seed` | 再現可能な生成結果のためのランダムシード。 | INT | はい | - | + +**注記:** `loop`パラメータは、`direction`が「Forward (continue after)」に設定されている場合のみ使用可能です。「Backward (lead-in before)」を使用する場合、ループオプションは利用できません。`prompt`は1文字以上6000文字以下である必要があります。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `generation_id` | 生成された5秒の拡張動画セグメント。 | VIDEO | +| `generation_id` | この生成の一意の識別子。別のLuma Ray 3.2 Extend Videoノードに接続して、さらに拡張することができます。 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32ExtendVideoNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `a67ca53d4bcb9f3fd82bc0482b579f5f7fe4bf866f8d83cb922e1082ad320057` diff --git a/ja/built-in-nodes/LumaRay32ImageToVideoNode.mdx b/ja/built-in-nodes/LumaRay32ImageToVideoNode.mdx new file mode 100644 index 000000000..a77a01dd8 --- /dev/null +++ b/ja/built-in-nodes/LumaRay32ImageToVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32ImageToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32ImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32ImageToVideoNode" +icon: "circle" +mode: wide +--- + +LumaのRay 3.2モデルを使用して、開始フレームおよび/または終了フレームから動画を生成します。画像を起点とした生成は、常に5秒間の長さになります。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `prompt` | 動画生成のためのテキストプロンプト。 | STRING | はい | 1～6000文字 | +| `resolution` | 生成される動画の出力解像度（デフォルト："720p"）。 | COMBO | はい | "360p"
"540p"
"720p"
"1080p" | +| `ループ` | 動画をシームレスにループさせます。`end_frame`が設定されている場合は利用できません。 | BOOLEAN | はい | True
False | +| `seed` | 再現可能な生成のためのシード値。 | INT | はい | 0～2147483647 | +| `start_frame` | 生成される動画の最初のフレーム。 | IMAGE | いいえ | - | +| `end_frame` | 生成される動画の最後のフレーム。 | IMAGE | いいえ | - | + +**注記：** `start_frame`または`end_frame`のうち、少なくとも1つを指定する必要があります。両方を指定した場合、生成される動画は開始フレームから終了フレームへと遷移します。`end_frame`が設定されている場合、`loop`オプションは有効にできません。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `generation_id` | 生成された動画出力。 | VIDEO | +| `generation_id` | 生成リクエストの一意の識別子。 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32ImageToVideoNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `ff479c196f10153ffa09af6acfb4e286d1934aa28a5e9b413613097a2cfb5f2a` diff --git a/ja/built-in-nodes/LumaRay32KeyframeNode.mdx b/ja/built-in-nodes/LumaRay32KeyframeNode.mdx new file mode 100644 index 000000000..b7290b4df --- /dev/null +++ b/ja/built-in-nodes/LumaRay32KeyframeNode.mdx @@ -0,0 +1,32 @@ +--- +title: "LumaRay32KeyframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32KeyframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32KeyframeNode" +icon: "circle" +mode: wide +--- + +このノードは、ガイド画像をLuma Ray 3.2出力ビデオのタイムライン上の特定の位置に固定します。このノードをLuma Ray 3.2 Keyframes to Videoノードの「keyframes」入力に接続し、オプションの「keyframes」入力をチェーンすることで、複数のキーフレームを連鎖させることができます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `image` | 出力ビデオの選択した瞬間に配置するガイド画像です。 | IMAGE | はい | - | +| `position` | 出力ビデオのタイムライン上でこの画像を配置する方法です。 | COMBO | はい | "Fraction of duration (0.0-1.0)"
"Absolute time (seconds)" | +| `keyframes` | このキーフレームと連鎖させる、オプションの先行キーフレームです。 | LUMA_RAY32_KEYFRAME | いいえ | - | + +`position`パラメータに「Fraction of duration (0.0-1.0)」が選択された場合、`fraction`値（デフォルト：0.0、範囲：0.0～1.0、ステップ：0.01）を指定できます。この値は、出力ビデオ内でこの画像が適用される位置を決定します（0.0 = 開始、1.0 = 終了）。 + +`position`パラメータに「Absolute time (seconds)」が選択された場合、`seconds`値（デフォルト：0.0、範囲：0.0～10.0、ステップ：0.1）を指定できます。この値は、出力ビデオの開始からこの画像が適用されるまでの時間を秒単位で決定します。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `keyframes` | 新しいキーフレームと、オプションの先行キーフレームを組み合わせたキーフレームチェーンです。 | LUMA_RAY32_KEYFRAME | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32KeyframeNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `b49d879888e6e83d6937068e799ea583ed5c90284e829ac496821eea330fe9c7` diff --git a/ja/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx b/ja/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx new file mode 100644 index 000000000..befa8f22a --- /dev/null +++ b/ja/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32KeyframesToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32KeyframesToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32KeyframesToVideoNode" +icon: "circle" +mode: wide +--- + +このノードは、Luma Ray 3.2 を使用して、タイムライン上の特定の位置に固定された一連のガイド画像を補間するビデオを生成します。Luma Ray 3.2 キーフレームノードを使用してキーフレームシーケンスを構築し、アニメーションを定義するために少なくとも 2 つのキーフレームを接続してください。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `プロンプト` | ビデオ生成のためのテキストプロンプト。 | STRING | はい | 1～6000 文字 | +| `解像度` | 生成されるビデオの出力解像度（デフォルト："720p"）。 | COMBO | はい | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `長さ` | 生成されるビデオの長さ（デフォルト："5s"）。 | COMBO | はい | `"5s"`
`"10s"` | +| `シード` | 再現性を制御するための乱数生成のシード。 | INT | はい | 0～4294967295 | +| `キーフレーム` | Luma Ray 3.2 キーフレームノードからのキーフレームシーケンス（最低 2 つ）。 | LUMA_RAY32_KEYFRAME | はい | 2～64 キーフレーム | + +**注記：** キーフレームシーケンスには、最低 2 つ、最大 64 つのキーフレームが含まれている必要があります。各キーフレームはタイムライン上で異なる位置を持たなければなりません。キーフレームの位置は、選択された長さ（5秒の場合は120フレーム、10秒の場合は240フレーム）に基づいて出力フレームインデックスに解決されます。秒単位のキーフレーム位置は、ビデオの合計時間を超えてはなりません。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `generation_id` | 生成されたビデオ出力。 | VIDEO | +| `generation_id` | 生成リクエストの一意識別子。 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32KeyframesToVideoNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `28099e5990942860a20e23cfd5c71a36b23a6264b44097ca617f8bdd06e7857a` diff --git a/ja/built-in-nodes/LumaRay32TextToVideoNode.mdx b/ja/built-in-nodes/LumaRay32TextToVideoNode.mdx new file mode 100644 index 000000000..6ef40c472 --- /dev/null +++ b/ja/built-in-nodes/LumaRay32TextToVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32TextToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32TextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32TextToVideoNode" +icon: "circle" +mode: wide +--- + +このノードは、Luma の Ray 3.2 モデルを使用してテキストプロンプトから動画を生成します。プロンプトと動画設定を Luma API に送信し、生成された動画と生成 ID を返します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `プロンプト` | 動画生成のためのテキストプロンプト。 | STRING | はい | 1～6000文字 | +| `アスペクト比` | 生成される動画のアスペクト比。 | STRING | はい | `"16:9"`
`"9:16"`
`"1:1"`
`"4:3"`
`"3:4"`
`"21:9"` | +| `解像度` | 動画の出力解像度（デフォルト："720p"）。 | STRING | はい | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `長さ` | 生成される動画の長さ。 | STRING | はい | `"5s"`
`"10s"` | +| `ループ` | 動画をシームレスにループさせます。5秒の長さでのみ利用可能です。 | BOOLEAN | いいえ | True/False（デフォルト：False） | +| `シード` | 再現可能な生成のためのシード値。 | INT | いいえ | 0～2147483647 | + +**注記:** `loop` パラメータは、`duration` が "5s" に設定されている場合のみ有効にできます。"10s" の長さを選択してループを有効にすると、ノードはエラーを返します。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `generation_id` | 生成された動画ファイル。 | VIDEO | +| `generation_id` | 動画生成リクエストの一意の識別子。 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32TextToVideoNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `04358a872530e5a2622bf0f148a694f2c707ce8535586d8f860bdf9911e1fa6a` diff --git a/ja/built-in-nodes/LumaRay32VideoEditNode.mdx b/ja/built-in-nodes/LumaRay32VideoEditNode.mdx new file mode 100644 index 000000000..1a9214e50 --- /dev/null +++ b/ja/built-in-nodes/LumaRay32VideoEditNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32VideoEditNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32VideoEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32VideoEditNode" +icon: "circle" +mode: wide +--- + +このノードは、Luma Ray 3.2 を使用して既存の動画を新しいプロンプトで再レンダリングし、元の動きを保持しながらスタイルの変更、照明の調整、要素の追加または削除を可能にします。ソース動画は最大18秒まで対応し、編集後の動画はソースの元の長さを維持します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `ビデオ` | 編集するソース動画。最大18秒。 | VIDEO | はい | - | +| `プロンプト` | 希望する編集内容を記述します。 | STRING | はい | - | +| `解像度` | 編集後の動画の出力解像度。 | COMBO | はい | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `強度` | ソースを保持するか再解釈するかの強度。"auto" は Ray 3.2 が自動選択します。adhere_* は最も保持し、flex_* はバランスが取れており、reimagine_* は最も変化します。（デフォルト: "auto"） | COMBO | はい | `"auto"`
`"adhere_1"`
`"adhere_2"`
`"adhere_3"`
`"flex_1"`
`"flex_2"`
`"flex_3"`
`"reimagine_1"`
`"reimagine_2"`
`"reimagine_3"` | +| `シード` | 再現性のためのシード値。 | INT | はい | - | + +**注記:** `prompt` は1文字以上6000文字以下である必要があります。ソース動画の長さは18秒を超えてはいけません。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `generation_id` | 編集後の動画出力。 | VIDEO | +| `generation_id` | 生成リクエストの一意識別子。 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32VideoEditNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `936d9d7da3fdee9b0b468781fd470751db01f772f3c5c20582da7fb1ff85e6e6` diff --git a/ja/built-in-nodes/LumaRay32VideoReframeNode.mdx b/ja/built-in-nodes/LumaRay32VideoReframeNode.mdx new file mode 100644 index 000000000..c191ee586 --- /dev/null +++ b/ja/built-in-nodes/LumaRay32VideoReframeNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32VideoReframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32VideoReframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32VideoReframeNode" +icon: "circle" +mode: wide +--- + +このノードは、Luma Ray 3.2 を使用して既存の動画のアスペクト比を変更し、新たに露出したキャンバス領域を生成コンテンツで埋めます。ソース動画は最大30秒まで対応しており、料金は出力1秒あたりで課金されます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `video` | リフレーミングするソース動画。最大30秒。 | VIDEO | はい | - | +| `prompt` | 新たに露出したキャンバス領域をどのように埋めるかを説明します。 | STRING | はい | - | +| `aspect_ratio` | リフレーミング後の動画のターゲットアスペクト比（デフォルト："16:9"）。 | STRING | はい | "16:9"
"9:16"
"1:1"
"4:3"
"3:4"
"21:9" | +| `resolution` | リフレーミング後の動画の出力解像度（デフォルト："720p"）。 | STRING | はい | "360p"
"540p"
"720p"
"1080p" | +| `seed` | 再現可能な生成のためのシード値。 | INT | はい | - | + +**注記:** リフレーミング時、縦長のアスペクト比（`9:16` および `3:4`）では `1080p` 解像度は利用できません。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `generation_id` | 新しいアスペクト比と埋められたキャンバス領域を持つリフレーミング済み動画。 | VIDEO | +| `generation_id` | 生成リクエストの一意識別子。 | STRING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32VideoReframeNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `d35ff5b63a850e4e44a40857188918ab5cde00b9159e3720a189a81807cfa7cb` diff --git a/ja/built-in-nodes/LumaReferenceNode.mdx b/ja/built-in-nodes/LumaReferenceNode.mdx index e6343e603..fdce12f0f 100644 --- a/ja/built-in-nodes/LumaReferenceNode.mdx +++ b/ja/built-in-nodes/LumaReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaReferenceNode" icon: "circle" mode: wide --- + このノードは、Luma Generate Imageノードで使用するための画像と重みの値を保持します。参照チェーンを作成し、他のLumaノードに渡して画像生成に影響を与えることができます。このノードは、新しい参照チェーンを開始するか、既存のチェーンに追加することができます。 ## 入力 diff --git a/ja/built-in-nodes/LumaVideoNode.mdx b/ja/built-in-nodes/LumaVideoNode.mdx index 74d6ab0d1..9f7d09975 100644 --- a/ja/built-in-nodes/LumaVideoNode.mdx +++ b/ja/built-in-nodes/LumaVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaVideoNode" icon: "circle" mode: wide --- + このドキュメントは AI によって生成されました。誤りを見つけた場合や改善のための提案がある場合は、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaVideoNode/en.md) テキストプロンプトと出力設定に基づいて、同期的に動画を生成します。このノードは、テキストによる説明と様々な生成パラメータを使用して動画コンテンツを作成し、生成プロセスが完了すると最終的な動画を出力します。 diff --git a/ja/built-in-nodes/MagnificImageRelightNode.mdx b/ja/built-in-nodes/MagnificImageRelightNode.mdx index 61eebf024..e4ec09711 100644 --- a/ja/built-in-nodes/MagnificImageRelightNode.mdx +++ b/ja/built-in-nodes/MagnificImageRelightNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageRelightNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Magnific Image Relight ノードは、入力画像の照明を調整します。テキストプロンプトに基づいたスタイル照明の適用や、オプションの参照画像からの照明特性の転送が可能です。このノードは、最終出力の明るさ、コントラスト、全体的な雰囲気を微調整するためのさまざまなコントロールを提供します。 diff --git a/ja/built-in-nodes/MagnificImageSkinEnhancerNode.mdx b/ja/built-in-nodes/MagnificImageSkinEnhancerNode.mdx index 44cf2ff0c..99b89651f 100644 --- a/ja/built-in-nodes/MagnificImageSkinEnhancerNode.mdx +++ b/ja/built-in-nodes/MagnificImageSkinEnhancerNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageSkinEnhancerNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/MagnificImageStyleTransferNode.mdx b/ja/built-in-nodes/MagnificImageStyleTransferNode.mdx index 0e1846049..cefac5054 100644 --- a/ja/built-in-nodes/MagnificImageStyleTransferNode.mdx +++ b/ja/built-in-nodes/MagnificImageStyleTransferNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageStyleTransferNode" icon: "circle" mode: wide --- + このノードは、参照画像から視覚的なスタイルを抽出し、入力画像に適用します。外部のAIサービスを使用して画像を処理し、スタイル変換の強度や元画像の構造保持度合いを制御できます。 ## 入力 diff --git a/ja/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx b/ja/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx index 69d5c740a..9a187575f 100644 --- a/ja/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx +++ b/ja/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageUpscalerCreativeNode" icon: "circle" mode: wide --- + このノードは、Magnific AIサービスを使用して画像をアップスケールし、創造的に強化します。テキストプロンプトで強化をガイドしたり、最適化する特定のスタイルを選択したり、ディテール、元画像との類似性、スタイライゼーションの強さなど、創造的プロセスのさまざまな側面を制御できます。このノードは、選択した倍率（2倍、4倍、8倍、16倍）でアップスケールされた画像を出力し、最大出力サイズは25.3メガピクセルです。 ## 入力 diff --git a/ja/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx b/ja/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx index 0a61114f7..c33fa5b6c 100644 --- a/ja/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx +++ b/ja/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageUpscalerPreciseV2Node" icon: "circle" mode: wide --- + 以下が翻訳結果です。 **Magnific Image Upscale (Precise V2)** ノードは、シャープネス、グレイン、ディテール強調を精密に制御しながら、高忠実度の画像アップスケーリングを実行します。外部APIを通じて画像を処理し、最大出力解像度10060×10060ピクセルまで対応します。このノードは異なる処理スタイルを提供し、要求された出力が最大許容サイズを超える場合、入力画像を自動的にダウンスケールすることも可能です。 diff --git a/ja/built-in-nodes/Mahiro.mdx b/ja/built-in-nodes/Mahiro.mdx index eb25ac266..4f01248ce 100644 --- a/ja/built-in-nodes/Mahiro.mdx +++ b/ja/built-in-nodes/Mahiro.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Mahiro" icon: "circle" mode: wide --- + 以下が日本語翻訳です。 Mahiroノードは、ガイダンス関数を変更し、ポジティブプロンプトとネガティブプロンプトの差分ではなく、ポジティブプロンプトの方向に重点を置くようにします。このノードは、正規化された条件付きおよび無条件のノイズ除去出力間のコサイン類似度を使用して、カスタムガイダンススケーリングアプローチを適用するパッチ適用済みモデルを作成します。この実験的なノードは、生成をポジティブプロンプトの意図された方向により強く導くのに役立ちます。 @@ -19,7 +20,7 @@ Mahiroノードは、ガイダンス関数を変更し、ポジティブプロ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `patched_model` | Mahiroガイダンス関数が適用された変更済みモデル | MODEL | +| `パッチ適用モデル` | Mahiroガイダンス関数が適用された変更済みモデル | MODEL | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Mahiro/ja.md) diff --git a/ja/built-in-nodes/MakeTrainingDataset.mdx b/ja/built-in-nodes/MakeTrainingDataset.mdx index 4a6b8102e..0f1d3183e 100644 --- a/ja/built-in-nodes/MakeTrainingDataset.mdx +++ b/ja/built-in-nodes/MakeTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MakeTrainingDataset" icon: "circle" mode: wide --- + このノードは、画像とテキストをエンコードすることでトレーニング用のデータを準備します。画像のリストとそれに対応するテキストキャプションのリストを受け取り、VAEモデルを使用して画像を潜在表現に変換し、CLIPモデルを使用してテキストをコンディショニングデータに変換します。結果として得られるペアリングされた潜在表現とコンディショニングはリストとして出力され、トレーニングワークフローで使用できる状態になります。 ## 入力 @@ -24,8 +25,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `コンディショニング` | 潜在表現の辞書のリスト。 | LATENT | -| `conditioning` | コンディショニングリストのリスト。 | CONDITIONING | +| `latentリスト` | 潜在表現の辞書のリスト。 | LATENT | +| `コンディショニング` | コンディショニングリストのリスト。 | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MakeTrainingDataset/ja.md) diff --git a/ja/built-in-nodes/ManualSigmas.mdx b/ja/built-in-nodes/ManualSigmas.mdx index 4355ef85a..13ef2b7d7 100644 --- a/ja/built-in-nodes/ManualSigmas.mdx +++ b/ja/built-in-nodes/ManualSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ManualSigmas" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ManualSigmasノードを使用すると、サンプリングプロセスで使用するノイズレベル（シグマ）のカスタムシーケンスを手動で定義できます。数値のリストを文字列として入力すると、ノードがそれらをテンソルに変換し、他のサンプリングノードで使用できるようにします。これは、テストや特定のノイズスケジュールを作成する際に便利です。 diff --git a/ja/built-in-nodes/MarkdownNote.mdx b/ja/built-in-nodes/MarkdownNote.mdx index b2b550b8d..9ff940f2d 100644 --- a/ja/built-in-nodes/MarkdownNote.mdx +++ b/ja/built-in-nodes/MarkdownNote.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MarkdownNote" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語ドキュメントです。 ワークフローに注釈を追加するノードです。Markdown構文を使用したテキストの書式設定をサポートしています。 diff --git a/ja/built-in-nodes/MaskComposite.mdx b/ja/built-in-nodes/MaskComposite.mdx index 4ca82de68..f27663215 100644 --- a/ja/built-in-nodes/MaskComposite.mdx +++ b/ja/built-in-nodes/MaskComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskComposite" icon: "circle" mode: wide --- + このノードは、加算、減算、論理演算などの様々な操作を通じて2つのマスク入力を組み合わせ、新しく変更されたマスクを生成することに特化しています。マスクデータの操作を抽象的に処理し、複雑なマスキング効果を実現することで、マスクベースの画像編集および処理ワークフローにおいて重要なコンポーネントとして機能します。 ## 入力 diff --git a/ja/built-in-nodes/MaskPreview.mdx b/ja/built-in-nodes/MaskPreview.mdx index a69af4799..9fa829d3a 100644 --- a/ja/built-in-nodes/MaskPreview.mdx +++ b/ja/built-in-nodes/MaskPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskPreview" icon: "circle" mode: wide --- + 以下は、指定された英語ドキュメントを日本語に翻訳したものです。 --- diff --git a/ja/built-in-nodes/MaskToImage.mdx b/ja/built-in-nodes/MaskToImage.mdx index 7bbf69dcf..8bd812e7b 100644 --- a/ja/built-in-nodes/MaskToImage.mdx +++ b/ja/built-in-nodes/MaskToImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskToImage" icon: "circle" mode: wide --- + `MaskToImage` ノードは、マスクを画像形式に変換するために設計されています。この変換により、マスクを画像として可視化し、さらに処理することが可能になり、マスクベースの操作と画像ベースのアプリケーションの橋渡しを容易にします。 ## 入力 diff --git a/ja/built-in-nodes/MediaPipeFaceLandmarker.mdx b/ja/built-in-nodes/MediaPipeFaceLandmarker.mdx index bc9aa9e72..4ab720151 100644 --- a/ja/built-in-nodes/MediaPipeFaceLandmarker.mdx +++ b/ja/built-in-nodes/MediaPipeFaceLandmarker.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceLandmarker" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -26,7 +27,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `bboxes` | フレームごとの顔検出結果を含む構造化出力です。468個の顔のランドマーク、ARKit-52ブレンドシェイプ係数、変換行列、メッシュ可視化用の接続セットが含まれます。 | FACE_LANDMARKS | +| `face_landmarks` | フレームごとの顔検出結果を含む構造化出力です。468個の顔のランドマーク、ARKit-52ブレンドシェイプ係数、変換行列、メッシュ可視化用の接続セットが含まれます。 | FACE_LANDMARKS | | `bboxes` | 検出された各顔のバウンディングボックスのリストです。座標（x, y, 幅, 高さ）、ラベル「face」、信頼度スコアが含まれます。入力フレームごとに1つのリストが出力されます。 | BOUNDING_BOX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MediaPipeFaceLandmarker/ja.md) diff --git a/ja/built-in-nodes/MediaPipeFaceMask.mdx b/ja/built-in-nodes/MediaPipeFaceMask.mdx index 77c6af617..0ef73b201 100644 --- a/ja/built-in-nodes/MediaPipeFaceMask.mdx +++ b/ja/built-in-nodes/MediaPipeFaceMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceMask" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/MediaPipeFaceMeshVisualize.mdx b/ja/built-in-nodes/MediaPipeFaceMeshVisualize.mdx index 707cbb475..ba706fc08 100644 --- a/ja/built-in-nodes/MediaPipeFaceMeshVisualize.mdx +++ b/ja/built-in-nodes/MediaPipeFaceMeshVisualize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceMeshVisualize" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/MergeImageLists.mdx b/ja/built-in-nodes/MergeImageLists.mdx index 09e0eeb0f..a66493731 100644 --- a/ja/built-in-nodes/MergeImageLists.mdx +++ b/ja/built-in-nodes/MergeImageLists.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MergeImageLists" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/MergeSplat.mdx b/ja/built-in-nodes/MergeSplat.mdx index b95937316..a8cf71dd0 100644 --- a/ja/built-in-nodes/MergeSplat.mdx +++ b/ja/built-in-nodes/MergeSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MergeSplat" icon: "circle" mode: wide --- -# スプラットの結合 Merge Splatsノードは、複数のガウシアンスプラットモデルをデータ連結により1つのスプラットに結合します。これは、異なるシードで生成された同じ潜在変数の複数のデコード結果をマージする場合に有用であり、表面を高密度化し、3Dメッシュ作成時の品質を向上させることができます。 diff --git a/ja/built-in-nodes/MergeTextLists.mdx b/ja/built-in-nodes/MergeTextLists.mdx index 4be1adab8..6faabb568 100644 --- a/ja/built-in-nodes/MergeTextLists.mdx +++ b/ja/built-in-nodes/MergeTextLists.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MergeTextLists" icon: "circle" mode: wide --- + このノードは、複数のテキストリストを1つの結合されたリストに統合します。テキスト入力をリストとして受け取り、それらを連結するように設計されています。このノードは、統合されたリスト内のテキストの総数をログに記録します。 ## 入力 diff --git a/ja/built-in-nodes/MeshyAnimateModelNode.mdx b/ja/built-in-nodes/MeshyAnimateModelNode.mdx index e9fef7695..f0da825c2 100644 --- a/ja/built-in-nodes/MeshyAnimateModelNode.mdx +++ b/ja/built-in-nodes/MeshyAnimateModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyAnimateModelNode" icon: "circle" mode: wide --- + このノードは、Meshyサービスを使用してすでにリギングされた3Dキャラクターモデルに、特定のアニメーションを適用します。以前のリギング操作のタスクIDと、ライブラリから目的のアニメーションを選択するためのアクションIDを受け取ります。その後、ノードはリクエストを処理し、アニメーション化されたモデルをGLBおよびFBXの両方のファイル形式で返します。 ## 入力 @@ -18,8 +19,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `GLB` | アニメーション化されたモデルの文字列識別子です。この出力は後方互換性のためにのみ提供されています。 | STRING | -| `FBX` | GLB形式のアニメーション化された3Dモデルファイルです。 | FILE3DGLB | +| `model_file` | アニメーション化されたモデルの文字列識別子です。この出力は後方互換性のためにのみ提供されています。 | STRING | +| `GLB` | GLB形式のアニメーション化された3Dモデルファイルです。 | FILE3DGLB | | `FBX` | FBX形式のアニメーション化された3Dモデルファイルです。 | FILE3DFBX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyAnimateModelNode/ja.md) diff --git a/ja/built-in-nodes/MeshyImageToModelNode.mdx b/ja/built-in-nodes/MeshyImageToModelNode.mdx index 657eee37b..56c83dc2b 100644 --- a/ja/built-in-nodes/MeshyImageToModelNode.mdx +++ b/ja/built-in-nodes/MeshyImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyImageToModelNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Meshy: Image to Model ノードは、Meshy API を使用して、1枚の入力画像から3Dモデルを生成します。画像をアップロードし、処理タスクを送信し、生成された3Dモデルファイル（GLBおよびFBX）と参照用のタスクIDを返します。 @@ -36,9 +37,9 @@ Meshy: Image to Model ノードは、Meshy API を使用して、1枚の入力 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `meshy_task_id` | 生成されたGLBモデルのファイル名です（後方互換性のために維持されています）。 | STRING | -| `GLB` | Meshy APIタスクの一意の識別子であり、参照やトラブルシューティングに使用できます。 | MESHY_TASK_ID | -| `FBX` | GLBファイル形式で生成された3Dモデルです。 | FILE3DGLB | +| `model_file` | 生成されたGLBモデルのファイル名です（後方互換性のために維持されています）。 | STRING | +| `meshy_task_id` | Meshy APIタスクの一意の識別子であり、参照やトラブルシューティングに使用できます。 | MESHY_TASK_ID | +| `GLB` | GLBファイル形式で生成された3Dモデルです。 | FILE3DGLB | | `FBX` | FBXファイル形式で生成された3Dモデルです。 | FILE3DFBX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyImageToModelNode/ja.md) diff --git a/ja/built-in-nodes/MeshyMultiImageToModelNode.mdx b/ja/built-in-nodes/MeshyMultiImageToModelNode.mdx index 29846fb98..088b270fe 100644 --- a/ja/built-in-nodes/MeshyMultiImageToModelNode.mdx +++ b/ja/built-in-nodes/MeshyMultiImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyMultiImageToModelNode" icon: "circle" mode: wide --- + このノードは、Meshy APIを使用して複数の入力画像から3Dモデルを生成します。提供された画像をアップロードし、処理タスクを送信し、結果として得られる3Dモデルファイル（GLBおよびFBX）と、参照用のタスクIDを返します。 ## 入力 @@ -35,9 +36,9 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `meshy_task_id` | 生成されたGLBモデルのファイル名です。この出力は後方互換性のために提供されています。 | STRING | -| `GLB` | Meshy APIタスクの一意の識別子です。 | MESHY_TASK_ID | -| `FBX` | GLB形式で生成された3Dモデルです。 | FILE3DGLB | +| `model_file` | 生成されたGLBモデルのファイル名です。この出力は後方互換性のために提供されています。 | STRING | +| `meshy_task_id` | Meshy APIタスクの一意の識別子です。 | MESHY_TASK_ID | +| `GLB` | GLB形式で生成された3Dモデルです。 | FILE3DGLB | | `FBX` | FBX形式で生成された3Dモデルです。 | FILE3DFBX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyMultiImageToModelNode/ja.md) diff --git a/ja/built-in-nodes/MeshyRefineNode.mdx b/ja/built-in-nodes/MeshyRefineNode.mdx index baa6daf3a..283c0d1dc 100644 --- a/ja/built-in-nodes/MeshyRefineNode.mdx +++ b/ja/built-in-nodes/MeshyRefineNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyRefineNode" icon: "circle" mode: wide --- + 以下は、指定された翻訳ルールに従って日本語に翻訳したドキュメントです。 Meshy: 下書きモデル精細化ノードは、以前に生成された3D下書きモデルを受け取り、その品質を向上させ、オプションでテクスチャを追加します。Meshy APIに精細化タスクを送信し、処理が完了すると最終的な3Dモデルファイルを返します。 @@ -25,9 +26,9 @@ Meshy: 下書きモデル精細化ノードは、以前に生成された3D下 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `meshy_task_id` | 生成されたGLBモデルのファイル名です。（後方互換性のため） | STRING | -| `GLB` | 送信された精細化ジョブの一意のタスクIDです。 | MESHY_TASK_ID | -| `FBX` | GLB形式の最終的な精細化された3Dモデルです。 | FILE3DGLB | +| `model_file` | 生成されたGLBモデルのファイル名です。（後方互換性のため） | STRING | +| `meshy_task_id` | 送信された精細化ジョブの一意のタスクIDです。 | MESHY_TASK_ID | +| `GLB` | GLB形式の最終的な精細化された3Dモデルです。 | FILE3DGLB | | `FBX` | FBX形式の最終的な精細化された3Dモデルです。 | FILE3DFBX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRefineNode/ja.md) diff --git a/ja/built-in-nodes/MeshyRigModelNode.mdx b/ja/built-in-nodes/MeshyRigModelNode.mdx index 14f299552..324765f06 100644 --- a/ja/built-in-nodes/MeshyRigModelNode.mdx +++ b/ja/built-in-nodes/MeshyRigModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyRigModelNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -25,9 +26,9 @@ Meshy: Rig Modelノードは、以前のMeshyタスクから3Dモデルを取得 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `rig_task_id` | 下位互換性のためのレガシー出力です。GLBモデルのファイル名を含みます。 | STRING | -| `GLB` | このリギング操作の一意のタスクIDです。結果を参照するために使用できます。 | STRING | -| `FBX` | GLBファイル形式で保存された、リギング済み3Dキャラクターモデルです。 | FILE3DGLB | +| `model_file` | 下位互換性のためのレガシー出力です。GLBモデルのファイル名を含みます。 | STRING | +| `rig_task_id` | このリギング操作の一意のタスクIDです。結果を参照するために使用できます。 | STRING | +| `GLB` | GLBファイル形式で保存された、リギング済み3Dキャラクターモデルです。 | FILE3DGLB | | `FBX` | FBXファイル形式で保存された、リギング済み3Dキャラクターモデルです。 | FILE3DFBX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRigModelNode/ja.md) diff --git a/ja/built-in-nodes/MeshyTextToModelNode.mdx b/ja/built-in-nodes/MeshyTextToModelNode.mdx index 434ce8992..3749d2184 100644 --- a/ja/built-in-nodes/MeshyTextToModelNode.mdx +++ b/ja/built-in-nodes/MeshyTextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyTextToModelNode" icon: "circle" mode: wide --- + 以下は、ご指定の翻訳ルールに従って日本語に翻訳したドキュメントです。 --- @@ -31,9 +32,9 @@ Meshy: Text to Model ノードは、Meshy API を使用してテキスト記述 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `meshy_task_id` | 生成された GLB モデルのファイル名です。この出力は後方互換性のために提供されています。 | STRING | -| `GLB` | Meshy API タスクの一意の識別子です。 | MESHY_TASK_ID | -| `FBX` | GLB 形式で生成された 3D モデルファイルです。 | FILE3DGLB | +| `モデルファイル` | 生成された GLB モデルのファイル名です。この出力は後方互換性のために提供されています。 | STRING | +| `meshy_task_id` | Meshy API タスクの一意の識別子です。 | MESHY_TASK_ID | +| `GLB` | GLB 形式で生成された 3D モデルファイルです。 | FILE3DGLB | | `FBX` | FBX 形式で生成された 3D モデルファイルです。 | FILE3DFBX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextToModelNode/ja.md) diff --git a/ja/built-in-nodes/MeshyTextureNode.mdx b/ja/built-in-nodes/MeshyTextureNode.mdx index 6ae3beab5..afb964f38 100644 --- a/ja/built-in-nodes/MeshyTextureNode.mdx +++ b/ja/built-in-nodes/MeshyTextureNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyTextureNode" icon: "circle" mode: wide --- + 以下が翻訳です。 **Meshy: テクスチャノード**は、AIが生成したテクスチャを3Dモデルに適用します。このノードは、以前のMeshy 3D生成または変換ノードからのタスクIDを受け取り、テキストによる説明または参照画像を使用して、モデルに新しいテクスチャを作成します。ノードは、テクスチャが適用されたモデルをGLBおよびFBXファイル形式で出力します。 @@ -29,9 +30,9 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `meshy_task_id` | 生成されたGLBモデルのファイル名。この出力は後方互換性のために提供されています。 | STRING | -| `GLB` | このテクスチャリングジョブの一意のタスク識別子。結果を参照するために使用できます。 | MODEL_TASK_ID | -| `FBX` | GLBファイル形式で保存された、テクスチャが適用された3Dモデル。 | FILE3DGLB | +| `モデルファイル` | 生成されたGLBモデルのファイル名。この出力は後方互換性のために提供されています。 | STRING | +| `meshy_task_id` | このテクスチャリングジョブの一意のタスク識別子。結果を参照するために使用できます。 | MODEL_TASK_ID | +| `GLB` | GLBファイル形式で保存された、テクスチャが適用された3Dモデル。 | FILE3DGLB | | `FBX` | FBXファイル形式で保存された、テクスチャが適用された3Dモデル。 | FILE3DFBX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextureNode/ja.md) diff --git a/ja/built-in-nodes/MinimaxHailuoVideoNode.mdx b/ja/built-in-nodes/MinimaxHailuoVideoNode.mdx index 9d0b394c4..bd223b502 100644 --- a/ja/built-in-nodes/MinimaxHailuoVideoNode.mdx +++ b/ja/built-in-nodes/MinimaxHailuoVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxHailuoVideoNode" icon: "circle" mode: wide --- + 以下は、ご依頼いただいた英語ドキュメントを日本語に翻訳したものです。 --- diff --git a/ja/built-in-nodes/MinimaxImageToVideoNode.mdx b/ja/built-in-nodes/MinimaxImageToVideoNode.mdx index 50e1a0188..5330ba111 100644 --- a/ja/built-in-nodes/MinimaxImageToVideoNode.mdx +++ b/ja/built-in-nodes/MinimaxImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxImageToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/MinimaxSubjectToVideoNode.mdx b/ja/built-in-nodes/MinimaxSubjectToVideoNode.mdx index eea135412..dce0947e7 100644 --- a/ja/built-in-nodes/MinimaxSubjectToVideoNode.mdx +++ b/ja/built-in-nodes/MinimaxSubjectToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxSubjectToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/MinimaxTextToVideoNode.mdx b/ja/built-in-nodes/MinimaxTextToVideoNode.mdx index ef2c34d5e..01917e05d 100644 --- a/ja/built-in-nodes/MinimaxTextToVideoNode.mdx +++ b/ja/built-in-nodes/MinimaxTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxTextToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/MoGeInference.mdx b/ja/built-in-nodes/MoGeInference.mdx index 7bd55cf3e..f6051fc53 100644 --- a/ja/built-in-nodes/MoGeInference.mdx +++ b/ja/built-in-nodes/MoGeInference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGeInference" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/MoGePanoramaInference.mdx b/ja/built-in-nodes/MoGePanoramaInference.mdx index 5a99bf037..20076b1b9 100644 --- a/ja/built-in-nodes/MoGePanoramaInference.mdx +++ b/ja/built-in-nodes/MoGePanoramaInference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGePanoramaInference" icon: "circle" mode: wide --- + ## 概要 このノードは、正距円筒図法のパノラマ画像に対して深度推定を実行します。パノラマを12の透視図に分割し、各ビューに対してMoGe深度推定モデルを実行した後、結果を元のパノラマの単一かつ完全な深度マップに統合することで動作します。 diff --git a/ja/built-in-nodes/MoGePointMapToMesh.mdx b/ja/built-in-nodes/MoGePointMapToMesh.mdx index 7d40430be..42e14ec44 100644 --- a/ja/built-in-nodes/MoGePointMapToMesh.mdx +++ b/ja/built-in-nodes/MoGePointMapToMesh.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGePointMapToMesh" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/MoGeRender.mdx b/ja/built-in-nodes/MoGeRender.mdx index 96a428699..a12f53ff6 100644 --- a/ja/built-in-nodes/MoGeRender.mdx +++ b/ja/built-in-nodes/MoGeRender.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGeRender" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ModelComputeDtype.mdx b/ja/built-in-nodes/ModelComputeDtype.mdx index 027c320f3..61713b880 100644 --- a/ja/built-in-nodes/ModelComputeDtype.mdx +++ b/ja/built-in-nodes/ModelComputeDtype.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelComputeDtype" icon: "circle" mode: wide --- + ModelComputeDtypeノードは、モデルの処理中に使用される計算データ型（精度）を変更します。入力モデルのコピーを作成し、選択された精度設定を適用します。これにより、ハードウェアに応じてメモリ使用量とパフォーマンスを最適化できます。異なる精度設定のデバッグやテストに役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeAdd.mdx b/ja/built-in-nodes/ModelMergeAdd.mdx index b4c62ce61..d25d39e5d 100644 --- a/ja/built-in-nodes/ModelMergeAdd.mdx +++ b/ja/built-in-nodes/ModelMergeAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeAdd" icon: "circle" mode: wide --- + ModelMergeAddノードは、一方のモデルからキーパッチを他方のモデルに追加することで、2つのモデルをマージするために設計されています。このプロセスでは、最初のモデルをクローンし、次に2番目のモデルからパッチを適用することで、両方のモデルの特徴や動作を組み合わせることができます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeAuraflow.mdx b/ja/built-in-nodes/ModelMergeAuraflow.mdx index 1c3cc64c4..d6aa11ddb 100644 --- a/ja/built-in-nodes/ModelMergeAuraflow.mdx +++ b/ja/built-in-nodes/ModelMergeAuraflow.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeAuraflow" icon: "circle" mode: wide --- + ModelMergeAuraflow ノードを使用すると、2つの異なるモデルを、様々なモデルコンポーネントに対する特定のブレンドウェイトを調整してブレンドできます。このノードは、初期層から最終出力に至るまで、モデルの異なる部分をどのようにマージするかを細かく制御できます。特に、マージプロセスを精密に制御しながら、カスタムモデルの組み合わせを作成する場合に役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeBlocks.mdx b/ja/built-in-nodes/ModelMergeBlocks.mdx index 432a9ff86..977d864c9 100644 --- a/ja/built-in-nodes/ModelMergeBlocks.mdx +++ b/ja/built-in-nodes/ModelMergeBlocks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeBlocks" icon: "circle" mode: wide --- + ModelMergeBlocksは高度なモデルマージ操作のために設計されており、2つのモデルを統合し、モデルの各部分に対してカスタマイズ可能なブレンド比率を設定できます。このノードは、指定されたパラメータに基づいて2つのソースモデルからコンポーネントを選択的にマージすることで、ハイブリッドモデルの作成を容易にします。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeCosmos14B.mdx b/ja/built-in-nodes/ModelMergeCosmos14B.mdx index 8ef805562..60dc98425 100644 --- a/ja/built-in-nodes/ModelMergeCosmos14B.mdx +++ b/ja/built-in-nodes/ModelMergeCosmos14B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmos14B" icon: "circle" mode: wide --- + **ModelMergeCosmos14B** ノードは、Cosmos 14B モデルアーキテクチャ専用に設計されたブロックベースのアプローチを使用して、2つのAIモデルをマージします。各モデルブロックと埋め込みレイヤーの重み値を0.0から1.0の間で調整することで、モデルの異なるコンポーネントをブレンドできます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeCosmos7B.mdx b/ja/built-in-nodes/ModelMergeCosmos7B.mdx index 461565a44..a51e0924b 100644 --- a/ja/built-in-nodes/ModelMergeCosmos7B.mdx +++ b/ja/built-in-nodes/ModelMergeCosmos7B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmos7B" icon: "circle" mode: wide --- + ModelMergeCosmos7B ノードは、特定のコンポーネントに重み付けブレンドを適用して、2つのAIモデルをマージします。位置埋め込み、トランスフォーマーブロック、最終層の個別の重みを調整することで、モデルの異なる部分をどのように組み合わせるかを細かく制御できます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx b/ja/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx index 9f411a7e6..3a44ad8a9 100644 --- a/ja/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx +++ b/ja/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmosPredict2_14B" icon: "circle" mode: wide --- + ModelMergeCosmosPredict2_14B ノードは、2つのAIモデルの内部コンポーネントをブレンドしてマージします。特定のレイヤーとコンポーネントに対して調整可能な重み値を使用することで、2番目のモデルの各部分が最終的なマージ結果に与える影響の度合いを精密に制御できます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx b/ja/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx index 512ae3936..6a4af2bd1 100644 --- a/ja/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx +++ b/ja/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmosPredict2_2B" icon: "circle" mode: wide --- + ModelMergeCosmosPredict2_2B ノードは、ブロックベースのアプローチを使用して2つの拡散モデルをマージし、異なるモデルコンポーネントを細かく制御します。位置埋め込み、時間埋め込み、トランスフォーマーブロック、最終層の補間重みを調整することで、2つのモデルの特定の部分をブレンドできます。これにより、各モデルの異なるアーキテクチャコンポーネントが最終的なマージ結果にどのように寄与するかを正確に制御できます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeFlux1.mdx b/ja/built-in-nodes/ModelMergeFlux1.mdx index 2ed6be653..f408991ff 100644 --- a/ja/built-in-nodes/ModelMergeFlux1.mdx +++ b/ja/built-in-nodes/ModelMergeFlux1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeFlux1" icon: "circle" mode: wide --- + ModelMergeFlux1 ノードは、重み付け補間を使用してコンポーネントをブレンドすることで、2つの拡散モデルをマージします。これにより、画像処理ブロック、時間埋め込みレイヤー、ガイダンスメカニズム、ベクトル入力、テキストエンコーダー、およびさまざまなトランスフォーマーブロックなど、モデルの異なる部分をどのように組み合わせるかを細かく制御できます。これにより、2つのソースモデルからカスタマイズされた特性を持つハイブリッドモデルを作成できます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeKrea2.mdx b/ja/built-in-nodes/ModelMergeKrea2.mdx new file mode 100644 index 000000000..6754e7b4d --- /dev/null +++ b/ja/built-in-nodes/ModelMergeKrea2.mdx @@ -0,0 +1,40 @@ +--- +title: "ModelMergeKrea2 - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ModelMergeKrea2 node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ModelMergeKrea2" +icon: "circle" +mode: wide +--- + +このノードは、2つのモデルの内部コンポーネントを細かいレベルでブレンドすることでマージを行い、各モデルの特定の部分が最終結果に与える影響の度合いを制御できるようにします。2つの入力モデルを受け取り、それらのアーキテクチャの異なるセクションに個別のブレンド比率を適用することで動作します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `model1` | マージする最初のモデル | MODEL | はい | - | +| `model2` | マージする2番目のモデル | MODEL | はい | - | +| `first.` | 最初のレイヤーブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `tmlp.` | 時間MLPブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `txtmlp.` | テキストMLPブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `tproj.` | 時間射影ブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `txtfusion.layerwise_blocks.0.` | 最初のテキストフュージョンレイヤーワイズブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `txtfusion.layerwise_blocks.1.` | 2番目のテキストフュージョンレイヤーワイズブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `txtfusion.projector.` | テキストフュージョン射影ブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `txtfusion.refiner_blocks.0.` | 最初のテキストフュージョンリファイナーブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `txtfusion.refiner_blocks.1.` | 2番目のテキストフュージョンリファイナーブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `blocks.0.` ～ `blocks.27.` | 28個のメインブロックそれぞれのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | +| `last.` | 最後のブロックのブレンド比率（デフォルト：1.0） | FLOAT | はい | 0.0～1.0（ステップ：0.01） | + +各ブレンド比率は、その特定のコンポーネントに対して`model2`をどの程度使用するかを制御します。0.0は`model1`のみを使用し、1.0は`model2`のみを使用し、中間の値は加重ブレンドを作成します。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `MODEL` | 指定された比率に従って2つの入力モデルをブレンドした結果のマージモデル | MODEL | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeKrea2/ja.md) + +--- +**Source fingerprint (SHA-256):** `ece35524f77fd906dc3109a0818d4d7d3986ec9debb518fd04893048843d7e88` diff --git a/ja/built-in-nodes/ModelMergeLTXV.mdx b/ja/built-in-nodes/ModelMergeLTXV.mdx index cc382ce0e..38070b781 100644 --- a/ja/built-in-nodes/ModelMergeLTXV.mdx +++ b/ja/built-in-nodes/ModelMergeLTXV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeLTXV" icon: "circle" mode: wide --- + ModelMergeLTXV ノードは、LTXV モデルアーキテクチャ専用に設計された高度なモデルマージ操作を実行します。このノードを使用すると、トランスフォーマーブロック、プロジェクション層、その他の特殊モジュールなど、さまざまなモデルコンポーネントの補間ウェイトを調整することで、2つの異なるモデルをブレンドできます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeMochiPreview.mdx b/ja/built-in-nodes/ModelMergeMochiPreview.mdx index 3f8e8a51d..1daab5059 100644 --- a/ja/built-in-nodes/ModelMergeMochiPreview.mdx +++ b/ja/built-in-nodes/ModelMergeMochiPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeMochiPreview" icon: "circle" mode: wide --- + このノードは、ブロックベースのアプローチを使用して2つのAIモデルをマージし、異なるモデルコンポーネントを細かく制御します。位置周波数、埋め込み層、個々のトランスフォーマーブロックなど、特定のセクションの補間ウェイトを調整することで、モデルをブレンドできます。マージ処理では、指定されたウェイト値に従って、両方の入力モデルのアーキテクチャとパラメータが結合されます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeQwenImage.mdx b/ja/built-in-nodes/ModelMergeQwenImage.mdx index 6f3df0a15..e44f3f2f8 100644 --- a/ja/built-in-nodes/ModelMergeQwenImage.mdx +++ b/ja/built-in-nodes/ModelMergeQwenImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeQwenImage" icon: "circle" mode: wide --- + ModelMergeQwenImage ノードは、2つのAIモデルのコンポーネントを調整可能な重みで結合し、マージします。Qwen画像モデルの特定の部分（トランスフォーマーブロック、位置埋め込み、テキスト処理コンポーネントなど）をブレンドできます。マージ結果の異なるセクションに対して、各モデルの影響度を制御することが可能です。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeSD1.mdx b/ja/built-in-nodes/ModelMergeSD1.mdx index 0ae83576a..c4f1a4c91 100644 --- a/ja/built-in-nodes/ModelMergeSD1.mdx +++ b/ja/built-in-nodes/ModelMergeSD1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD1" icon: "circle" mode: wide --- + ModelMergeSD1 ノードを使用すると、2つのStable Diffusion 1.xモデルをブレンドし、異なるモデルコンポーネントの影響度を調整することができます。このノードは、時間埋め込み、ラベル埋め込み、およびすべての入力ブロック、中間ブロック、出力ブロックを個別に制御できるため、特定のユースケースに合わせた微調整済みのモデルマージが可能です。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeSD35_Large.mdx b/ja/built-in-nodes/ModelMergeSD35_Large.mdx index bcab7a397..28da6c93a 100644 --- a/ja/built-in-nodes/ModelMergeSD35_Large.mdx +++ b/ja/built-in-nodes/ModelMergeSD35_Large.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD35_Large" icon: "circle" mode: wide --- + ModelMergeSD35_Large ノードを使用すると、2つのStable Diffusion 3.5 Largeモデルをブレンドし、異なるモデルコンポーネントの影響度を調整できます。このノードは、埋め込み層からジョイントブロック、最終層に至るまで、2つ目のモデルの各部分が最終的なマージモデルにどの程度寄与するかを精密に制御します。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeSD3_2B.mdx b/ja/built-in-nodes/ModelMergeSD3_2B.mdx index 3e314f6ce..b3a78c1ce 100644 --- a/ja/built-in-nodes/ModelMergeSD3_2B.mdx +++ b/ja/built-in-nodes/ModelMergeSD3_2B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD3_2B" icon: "circle" mode: wide --- + ModelMergeSD3_2B ノードを使用すると、2つのStable Diffusion 3 2Bモデルを、その構成要素を調整可能な重みでブレンドしてマージできます。このノードは、埋め込みレイヤーとトランスフォーマーブロックを個別に制御できるため、特殊な生成タスク向けに微調整されたモデルの組み合わせが可能です。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeSDXL.mdx b/ja/built-in-nodes/ModelMergeSDXL.mdx index 08ccfe46f..4e91f7d18 100644 --- a/ja/built-in-nodes/ModelMergeSDXL.mdx +++ b/ja/built-in-nodes/ModelMergeSDXL.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSDXL" icon: "circle" mode: wide --- + ModelMergeSDXL ノードを使用すると、2つのSDXLモデルをブレンドし、アーキテクチャの各部分に対する各モデルの影響度を調整できます。タイムエンベディング、ラベルエンベディング、およびモデル構造内のさまざまなブロックに対して、各モデルの寄与度を制御できます。これにより、両方の入力モデルの特徴を組み合わせたハイブリッドモデルが作成されます。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeSimple.mdx b/ja/built-in-nodes/ModelMergeSimple.mdx index 892b71fad..7f4a1d8d2 100644 --- a/ja/built-in-nodes/ModelMergeSimple.mdx +++ b/ja/built-in-nodes/ModelMergeSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSimple" icon: "circle" mode: wide --- + ModelMergeSimple ノードは、指定された比率に基づいて2つのモデルのパラメータをブレンドし、マージするために設計されています。このノードは、両方の入力モデルの強みや特性を組み合わせたハイブリッドモデルの作成を容易にします。 `ratio` パラメータは、2つのモデル間のブレンド比率を決定します。この値が1の場合は出力モデルが100% `model1` となり、0の場合は出力モデルが100% `model2` となります。 diff --git a/ja/built-in-nodes/ModelMergeSubtract.mdx b/ja/built-in-nodes/ModelMergeSubtract.mdx index c826c9fb0..ed91cca9a 100644 --- a/ja/built-in-nodes/ModelMergeSubtract.mdx +++ b/ja/built-in-nodes/ModelMergeSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSubtract" icon: "circle" mode: wide --- + このノードは高度なモデルマージ操作のために設計されており、具体的には指定された乗数に基づいて、あるモデルのパラメータを別のモデルから減算します。これにより、一方のモデルのパラメータが他方のモデルに与える影響を調整することで、モデルの動作をカスタマイズし、新しいハイブリッドモデルの作成を容易にします。 ## 入力 diff --git a/ja/built-in-nodes/ModelMergeWAN2_1.mdx b/ja/built-in-nodes/ModelMergeWAN2_1.mdx index f27d6f08a..fe7cb24be 100644 --- a/ja/built-in-nodes/ModelMergeWAN2_1.mdx +++ b/ja/built-in-nodes/ModelMergeWAN2_1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeWAN2_1" icon: "circle" mode: wide --- + ModelMergeWAN2_1 ノードは、2つのWAN2.1モデルを、その構成要素を加重平均でブレンドしてマージします。このノードは、30ブロックの1.3Bモデルや40ブロックの14Bモデルなど、異なるモデルサイズをサポートしており、画像から動画へのモデル（追加の画像埋め込みコンポーネントを含む）を特別に処理します。モデルの各コンポーネントには個別に重みを設定でき、2つの入力モデル間のブレンド比率を制御できます。 ## 入力 diff --git a/ja/built-in-nodes/ModelNoiseScale.mdx b/ja/built-in-nodes/ModelNoiseScale.mdx index bd3cb184e..626690b7e 100644 --- a/ja/built-in-nodes/ModelNoiseScale.mdx +++ b/ja/built-in-nodes/ModelNoiseScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelNoiseScale" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ModelPatchLoader.mdx b/ja/built-in-nodes/ModelPatchLoader.mdx index 8e191b896..7aa664dec 100644 --- a/ja/built-in-nodes/ModelPatchLoader.mdx +++ b/ja/built-in-nodes/ModelPatchLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelPatchLoader" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 ## 概要 diff --git a/ja/built-in-nodes/ModelSamplingAuraFlow.mdx b/ja/built-in-nodes/ModelSamplingAuraFlow.mdx index db5355b20..cf727a658 100644 --- a/ja/built-in-nodes/ModelSamplingAuraFlow.mdx +++ b/ja/built-in-nodes/ModelSamplingAuraFlow.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingAuraFlow" icon: "circle" mode: wide --- + ModelSamplingAuraFlow ノードは、拡散モデルに特殊なサンプリング設定を適用します。このノードは特に AuraFlow モデルアーキテクチャ向けに設計されており、サンプリング分布を調整するシフトパラメータを適用することで、モデルのサンプリング動作を変更します。SD3 モデルサンプリングフレームワークを継承し、サンプリングプロセスを細かく制御できます。 ## 入力 diff --git a/ja/built-in-nodes/ModelSamplingContinuousEDM.mdx b/ja/built-in-nodes/ModelSamplingContinuousEDM.mdx index 098462268..5b964b1b8 100644 --- a/ja/built-in-nodes/ModelSamplingContinuousEDM.mdx +++ b/ja/built-in-nodes/ModelSamplingContinuousEDM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingContinuousEDM" icon: "circle" mode: wide --- + このノードは、連続EDM（エネルギーベース拡散モデル）サンプリング技術を統合することで、モデルのサンプリング機能を強化するために設計されています。これにより、モデルのサンプリングプロセス内でノイズレベルを動的に調整でき、生成品質と多様性をより精密に制御できるようになります。 ## 入力 diff --git a/ja/built-in-nodes/ModelSamplingContinuousV.mdx b/ja/built-in-nodes/ModelSamplingContinuousV.mdx index f2a88164a..699db9882 100644 --- a/ja/built-in-nodes/ModelSamplingContinuousV.mdx +++ b/ja/built-in-nodes/ModelSamplingContinuousV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingContinuousV" icon: "circle" mode: wide --- + ModelSamplingContinuousV ノードは、連続的な V 予測サンプリングパラメータを適用することで、モデルのサンプリング動作を変更します。入力モデルのクローンを作成し、高度なサンプリング制御のためのカスタムシグマ範囲設定で構成します。これにより、ユーザーは最小および最大シグマ値を指定してサンプリングプロセスを微調整できます。 ## 入力 diff --git a/ja/built-in-nodes/ModelSamplingDiscrete.mdx b/ja/built-in-nodes/ModelSamplingDiscrete.mdx index 3c8afbefd..cd6c5258d 100644 --- a/ja/built-in-nodes/ModelSamplingDiscrete.mdx +++ b/ja/built-in-nodes/ModelSamplingDiscrete.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingDiscrete" icon: "circle" mode: wide --- + このノードは、離散サンプリング戦略を適用することでモデルのサンプリング動作を変更するように設計されています。イプシロン、v_prediction、lcm、x0などの異なるサンプリング方法を選択でき、オプションでゼロショットノイズ比（zsnr）設定に基づいてモデルのノイズ低減戦略を調整します。 ## 入力 diff --git a/ja/built-in-nodes/ModelSamplingFlux.mdx b/ja/built-in-nodes/ModelSamplingFlux.mdx index 98a35f21a..0461f692d 100644 --- a/ja/built-in-nodes/ModelSamplingFlux.mdx +++ b/ja/built-in-nodes/ModelSamplingFlux.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingFlux" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ModelSamplingFlux ノードは、画像の寸法に基づいてシフトパラメータを計算し、Flux モデルのサンプリングを指定されたモデルに適用します。このノードは、指定された幅、高さ、およびシフトパラメータに応じてモデルの動作を調整する特殊なサンプリング設定を作成し、新しいサンプリング設定が適用された変更済みモデルを返します。 diff --git a/ja/built-in-nodes/ModelSamplingLTXV.mdx b/ja/built-in-nodes/ModelSamplingLTXV.mdx index 12fa553e0..ccd0c3a16 100644 --- a/ja/built-in-nodes/ModelSamplingLTXV.mdx +++ b/ja/built-in-nodes/ModelSamplingLTXV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingLTXV" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ModelSamplingLTXV ノードは、トークン数に基づいて高度なサンプリングパラメータをモデルに適用します。ベースシフト値と最大シフト値の間の線形補間を使用してシフト値を計算し、その計算は入力潜在変数のトークン数に依存します。その後、ノードは特殊なモデルサンプリング設定を作成し、それを入力モデルに適用します。 diff --git a/ja/built-in-nodes/ModelSamplingSD3.mdx b/ja/built-in-nodes/ModelSamplingSD3.mdx index 5a8f33f3f..f29379f1c 100644 --- a/ja/built-in-nodes/ModelSamplingSD3.mdx +++ b/ja/built-in-nodes/ModelSamplingSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingSD3" icon: "circle" mode: wide --- + ModelSamplingSD3 ノードは、Stable Diffusion 3 のサンプリングパラメータをモデルに適用します。シフトパラメータを調整することでモデルのサンプリング動作を変更し、サンプリング分布の特性を制御します。このノードは、指定されたサンプリング設定を適用した、入力モデルの変更済みコピーを作成します。 ## 入力 diff --git a/ja/built-in-nodes/ModelSamplingStableCascade.mdx b/ja/built-in-nodes/ModelSamplingStableCascade.mdx index 6899178f2..fda4bffcd 100644 --- a/ja/built-in-nodes/ModelSamplingStableCascade.mdx +++ b/ja/built-in-nodes/ModelSamplingStableCascade.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingStableCascade" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ModelSamplingStableCascade ノードは、シフト値を使用してサンプリングパラメータを調整することにより、モデルに安定カスケードサンプリングを適用します。安定カスケード生成用のカスタムサンプリング設定を備えた、入力モデルの修正バージョンを作成します。 diff --git a/ja/built-in-nodes/ModelSave.mdx b/ja/built-in-nodes/ModelSave.mdx index b22357e2a..1e112cf18 100644 --- a/ja/built-in-nodes/ModelSave.mdx +++ b/ja/built-in-nodes/ModelSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSave" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSave/en.md) ModelSaveノードは、トレーニングまたは変更されたモデルをコンピューターのストレージに保存します。モデルを入力として受け取り、指定されたファイル名でファイルに書き込みます。これにより、作業内容を保存し、将来のプロジェクトでモデルを再利用できるようになります。 diff --git a/ja/built-in-nodes/MoonvalleyImg2VideoNode.mdx b/ja/built-in-nodes/MoonvalleyImg2VideoNode.mdx index 4de9c1c6c..9d86608a2 100644 --- a/ja/built-in-nodes/MoonvalleyImg2VideoNode.mdx +++ b/ja/built-in-nodes/MoonvalleyImg2VideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoonvalleyImg2VideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Moonvalley Marey 画像から動画へのノードは、Moonvalley API を使用して参照画像を動画に変換します。入力画像とテキストプロンプトを受け取り、指定された解像度、品質設定、およびクリエイティブコントロールに基づいて動画を生成します。このノードは、画像のアップロードから動画の生成、ダウンロードまでのプロセス全体を処理します。 diff --git a/ja/built-in-nodes/MoonvalleyTxt2VideoNode.mdx b/ja/built-in-nodes/MoonvalleyTxt2VideoNode.mdx index e21948cc4..a3e469d89 100644 --- a/ja/built-in-nodes/MoonvalleyTxt2VideoNode.mdx +++ b/ja/built-in-nodes/MoonvalleyTxt2VideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoonvalleyTxt2VideoNode" icon: "circle" mode: wide --- + あなたは ComfyUI ノードドキュメントを英語から日本語に翻訳する技術翻訳の専門家です。 ## 翻訳ルール diff --git a/ja/built-in-nodes/MoonvalleyVideo2VideoNode.mdx b/ja/built-in-nodes/MoonvalleyVideo2VideoNode.mdx index a922e4ce4..8b82b774d 100644 --- a/ja/built-in-nodes/MoonvalleyVideo2VideoNode.mdx +++ b/ja/built-in-nodes/MoonvalleyVideo2VideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoonvalleyVideo2VideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Moonvalley Marey Video to Video ノードは、入力された動画をテキスト記述に基づいて新しい動画に変換します。このノードは Moonvalley API を使用して、元の動画の動きやポーズの特徴を保持しつつ、プロンプトに一致する動画を生成します。テキストプロンプトや各種生成パラメータを通じて、出力動画のスタイルや内容を制御できます。 diff --git a/ja/built-in-nodes/Morphology.mdx b/ja/built-in-nodes/Morphology.mdx index 774e99375..40800753f 100644 --- a/ja/built-in-nodes/Morphology.mdx +++ b/ja/built-in-nodes/Morphology.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Morphology" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 形態変換ノードは、画像内の形状を処理・解析するための数学的操作である、さまざまな形態変換処理を画像に適用します。このノードでは、収縮、膨張、オープニング、クロージングなどの処理を、カスタマイズ可能なカーネルサイズで実行し、効果の強さを制御できます。 diff --git a/ja/built-in-nodes/MultiGPU_Options.mdx b/ja/built-in-nodes/MultiGPU_Options.mdx index 766fc5ed8..02228621e 100644 --- a/ja/built-in-nodes/MultiGPU_Options.mdx +++ b/ja/built-in-nodes/MultiGPU_Options.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MultiGPU_Options" icon: "circle" mode: wide --- + ## 概要 このノードを使用すると、速度の異なる複数のグラフィックカードを使用する際に、各GPUの相対的なパフォーマンスを指定できます。複数のデバイス間で処理を分散するために使用できるGPUオプションのグループを作成しますが、現在のバージョンでは速度に基づいた処理負荷の分散はまだ実装されていません。 diff --git a/ja/built-in-nodes/MultiGPU_WorkUnits.mdx b/ja/built-in-nodes/MultiGPU_WorkUnits.mdx index 5ffe84d86..9a89054f5 100644 --- a/ja/built-in-nodes/MultiGPU_WorkUnits.mdx +++ b/ja/built-in-nodes/MultiGPU_WorkUnits.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MultiGPU_WorkUnits" icon: "circle" mode: wide --- + ## 概要 MultiGPU CFG Split ノードは、同じPCに入っている複数のGPUで拡散サンプリングを分担できるようにします。実際の速度向上はワークフローによって変わりますが、一般的なワークフローでは最大で約1.95倍の高速化が確認されています。 diff --git a/ja/built-in-nodes/NAGuidance.mdx b/ja/built-in-nodes/NAGuidance.mdx index afd0e53ac..8da9a0f8e 100644 --- a/ja/built-in-nodes/NAGuidance.mdx +++ b/ja/built-in-nodes/NAGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NAGuidance" icon: "circle" mode: wide --- + NAGuidance ノードは、モデルに正規化注意ガイダンス（Normalized Attention Guidance）を適用します。この技術により、サンプリングプロセス中にモデルの注意機構を変更して、生成を望ましくない概念から遠ざけることで、蒸留モデルや高速モデルでネガティブプロンプトを使用できるようになります。 ## 入力 diff --git a/ja/built-in-nodes/NormalizeImages.mdx b/ja/built-in-nodes/NormalizeImages.mdx index cd7d0938d..7cb916d70 100644 --- a/ja/built-in-nodes/NormalizeImages.mdx +++ b/ja/built-in-nodes/NormalizeImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NormalizeImages" icon: "circle" mode: wide --- + このノードは、数学的な正規化処理を使用して入力画像のピクセル値を調整します。各ピクセルから指定された平均値を減算し、その結果を指定された標準偏差で除算します。これは、他の機械学習モデル用に画像データを準備するための一般的な前処理手順です。 ## 入力 @@ -19,7 +20,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `image` | 正規化処理が適用された結果の画像です。 | IMAGE | +| `画像` | 正規化処理が適用された結果の画像です。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeImages/ja.md) diff --git a/ja/built-in-nodes/NormalizeVideoLatentStart.mdx b/ja/built-in-nodes/NormalizeVideoLatentStart.mdx index 040bfba16..540f99f31 100644 --- a/ja/built-in-nodes/NormalizeVideoLatentStart.mdx +++ b/ja/built-in-nodes/NormalizeVideoLatentStart.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NormalizeVideoLatentStart" icon: "circle" mode: wide --- + このノードは、ビデオ潜在表現の最初の数フレームを調整し、後続のフレームにより近い見た目にします。ビデオ内の後方にある参照フレーム群から平均と分散を計算し、それらと同じ特性を開始フレームに適用します。これにより、ビデオの開始部分でより滑らかで一貫性のある視覚的遷移を実現します。 ## 入力 diff --git a/ja/built-in-nodes/Note.mdx b/ja/built-in-nodes/Note.mdx index 31f0e53df..c06d086d0 100644 --- a/ja/built-in-nodes/Note.mdx +++ b/ja/built-in-nodes/Note.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Note" icon: "circle" mode: wide --- -# ワークフローに注釈を追加するノードです。 ## 入力 diff --git a/ja/built-in-nodes/OpenAIChatConfig.mdx b/ja/built-in-nodes/OpenAIChatConfig.mdx index 2ad0cf638..03c00dc69 100644 --- a/ja/built-in-nodes/OpenAIChatConfig.mdx +++ b/ja/built-in-nodes/OpenAIChatConfig.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIChatConfig" icon: "circle" mode: wide --- + OpenAIChatConfigノードは、OpenAI Chatノードに追加の設定オプションを提供します。このノードは、モデルが応答を生成する方法を制御する高度な設定を提供します。これには、トランケーション動作、出力長の制限、カスタム指示が含まれます。 ## 入力 diff --git a/ja/built-in-nodes/OpenAIChatNode.mdx b/ja/built-in-nodes/OpenAIChatNode.mdx index 0c68152b5..1a0ec3e3c 100644 --- a/ja/built-in-nodes/OpenAIChatNode.mdx +++ b/ja/built-in-nodes/OpenAIChatNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIChatNode" icon: "circle" mode: wide --- + このノードは、OpenAIモデルからテキスト応答を生成します。テキストプロンプト（およびオプションで画像やファイル）をOpenAIモデルに送信し、生成されたテキスト応答を返します。 ## 入力 diff --git a/ja/built-in-nodes/OpenAIDalle2.mdx b/ja/built-in-nodes/OpenAIDalle2.mdx index 2d4266046..fcd3c5ffd 100644 --- a/ja/built-in-nodes/OpenAIDalle2.mdx +++ b/ja/built-in-nodes/OpenAIDalle2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "OpenAIDalle2" icon: "circle" mode: wide --- -# OpenAIDalle2 OpenAIのDALL·E 2エンドポイントを介して画像を同期的に生成します。 diff --git a/ja/built-in-nodes/OpenAIDalle3.mdx b/ja/built-in-nodes/OpenAIDalle3.mdx index a222cfaa3..f85155ed8 100644 --- a/ja/built-in-nodes/OpenAIDalle3.mdx +++ b/ja/built-in-nodes/OpenAIDalle3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIDalle3" icon: "circle" mode: wide --- + OpenAIのDALL·E 3エンドポイントを介して同期的に画像を生成します。このノードはテキストプロンプトを受け取り、OpenAIのDALL·E 3モデルを使用して対応する画像を作成します。画像の品質、スタイル、サイズを指定することができます。 ## 入力 diff --git a/ja/built-in-nodes/OpenAIGPTImage1.mdx b/ja/built-in-nodes/OpenAIGPTImage1.mdx index 5ecd4f228..7efe84f84 100644 --- a/ja/built-in-nodes/OpenAIGPTImage1.mdx +++ b/ja/built-in-nodes/OpenAIGPTImage1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIGPTImage1" icon: "circle" mode: wide --- + OpenAIのGPT Imageエンドポイントを介して同期的に画像を生成します。このノードは、テキストプロンプトから新しい画像を作成したり、入力画像とオプションのマスクが提供された場合に既存の画像を編集したりできます。gpt-image-1、gpt-image-1.5、gpt-image-2を含む複数のGPT Imageモデルをサポートしています。 ## 入力 diff --git a/ja/built-in-nodes/OpenAIGPTImageNodeV2.mdx b/ja/built-in-nodes/OpenAIGPTImageNodeV2.mdx index 1ef9cefe5..12a6a1854 100644 --- a/ja/built-in-nodes/OpenAIGPTImageNodeV2.mdx +++ b/ja/built-in-nodes/OpenAIGPTImageNodeV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIGPTImageNodeV2" icon: "circle" mode: wide --- + 以下は、ご依頼いただいたComfyUIノードドキュメントの日本語翻訳です。 ## 概要 diff --git a/ja/built-in-nodes/OpenAIInputFiles.mdx b/ja/built-in-nodes/OpenAIInputFiles.mdx index 761b58d68..b0ed24a27 100644 --- a/ja/built-in-nodes/OpenAIInputFiles.mdx +++ b/ja/built-in-nodes/OpenAIInputFiles.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIInputFiles" icon: "circle" mode: wide --- + OpenAI API 用の入力ファイルを読み込み、フォーマットします。このノードは、テキスト（.txt）ファイルとPDF（.pdf）ファイルを準備し、OpenAI Chat ノードのコンテキスト入力として含めます。これらのファイルは、応答生成時に OpenAI モデルによって読み取られます。複数の OpenAI Input Files ノードをチェーン接続することで、1 つのメッセージに複数のファイルを含めることができます。 ## 入力 diff --git a/ja/built-in-nodes/OpenAIVideoSora2.mdx b/ja/built-in-nodes/OpenAIVideoSora2.mdx index 812799846..842ef700d 100644 --- a/ja/built-in-nodes/OpenAIVideoSora2.mdx +++ b/ja/built-in-nodes/OpenAIVideoSora2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIVideoSora2" icon: "circle" mode: wide --- + 以下は、ご依頼いただいた技術翻訳の結果です。 --- diff --git a/ja/built-in-nodes/OpenRouterLLMNode.mdx b/ja/built-in-nodes/OpenRouterLLMNode.mdx index 0c1e2dc2f..57f5ca820 100644 --- a/ja/built-in-nodes/OpenRouterLLMNode.mdx +++ b/ja/built-in-nodes/OpenRouterLLMNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenRouterLLMNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/OpticalFlowLoader.mdx b/ja/built-in-nodes/OpticalFlowLoader.mdx index f894e1b4e..d1e0ec49d 100644 --- a/ja/built-in-nodes/OpticalFlowLoader.mdx +++ b/ja/built-in-nodes/OpticalFlowLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpticalFlowLoader" icon: "circle" mode: wide --- + ## 概要 `models/optical_flow/` フォルダからオプティカルフローモデルを読み込みます。現在は、VOIDWarpedNoise ノードで使用される torchvision の RAFT-large 形式のみをサポートしています。ComfyUI はオプティカルフローの重みを自動的にダウンロードしません。チェックポイントファイルを手動で `models/optical_flow/` ディレクトリに配置する必要があります。 diff --git a/ja/built-in-nodes/OptimalStepsScheduler.mdx b/ja/built-in-nodes/OptimalStepsScheduler.mdx index c4a17f6f8..791887934 100644 --- a/ja/built-in-nodes/OptimalStepsScheduler.mdx +++ b/ja/built-in-nodes/OptimalStepsScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OptimalStepsScheduler" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください。[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OptimalStepsScheduler/en.md) OptimalStepsSchedulerノードは、選択されたモデルタイプとステップ設定に基づいて、拡散モデルのノイズスケジュールシグマを計算します。このノードは、denoiseパラメータに応じて総ステップ数を調整し、要求されたステップ数に一致するようにノイズレベルを補間します。出力として、拡散サンプリングプロセス中に使用されるノイズレベルを決定するシグマ値のシーケンスを返します。 diff --git a/ja/built-in-nodes/Painter.mdx b/ja/built-in-nodes/Painter.mdx index c75c8bc56..1afc548b5 100644 --- a/ja/built-in-nodes/Painter.mdx +++ b/ja/built-in-nodes/Painter.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Painter" icon: "circle" mode: wide --- + Painterノードは、ComfyUI内で直接画像やマスクを作成・編集するためのインタラクティブなキャンバスを提供します。空白のキャンバスから始めることも、既存の画像にペイントすることも可能で、ブラシツールを使用して描画し、結果の画像と対応するアルファマスクの両方を出力します。マスクはペイントされた領域を定義し、その領域がベース画像または背景色の上に合成されます。 ## 入力 diff --git a/ja/built-in-nodes/PairConditioningCombine.mdx b/ja/built-in-nodes/PairConditioningCombine.mdx index 05c446107..0a77cd2d1 100644 --- a/ja/built-in-nodes/PairConditioningCombine.mdx +++ b/ja/built-in-nodes/PairConditioningCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningCombine" icon: "circle" mode: wide --- + 以下は、指定された英語ドキュメントを日本語に翻訳したものです。 PairConditioningCombineノードは、2つの個別のコンディショニングペア（それぞれポジティブとネガティブのコンディショニングで構成）を1つの結合ペアに統合します。このノードは、2つの異なるソースからポジティブとネガティブのコンディショニングを受け取り、ComfyUIの内部ロジックを使用してそれらを結合し、最終的な1つのポジティブコンディショニングと1つのネガティブコンディショニングを出力します。このノードは実験的なものであり、高度なコンディショニング操作ワークフロー向けに設計されています。 @@ -22,8 +23,8 @@ PairConditioningCombineノードは、2つの個別のコンディショニン | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 結合されたポジティブコンディショニング出力 | CONDITIONING | -| `negative` | 結合されたネガティブコンディショニング出力 | CONDITIONING | +| `ポジティブ` | 結合されたポジティブコンディショニング出力 | CONDITIONING | +| `ネガティブ` | 結合されたネガティブコンディショニング出力 | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningCombine/ja.md) diff --git a/ja/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx b/ja/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx index 2cdabee7d..21a31cedc 100644 --- a/ja/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx +++ b/ja/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetDefaultAndCombine" icon: "circle" mode: wide --- + **PairConditioningSetDefaultAndCombine** ノードは、デフォルトの条件付け値を設定し、それを入力条件付けデータと結合します。ポジティブおよびネガティブの条件付け入力と、それぞれに対応するデフォルト値を受け取り、ComfyUIのフックシステムを通じて処理することで、デフォルト値を組み込んだ最終的な条件付け出力を生成します。 ## 入力 diff --git a/ja/built-in-nodes/PairConditioningSetProperties.mdx b/ja/built-in-nodes/PairConditioningSetProperties.mdx index f1d70b17e..027356e08 100644 --- a/ja/built-in-nodes/PairConditioningSetProperties.mdx +++ b/ja/built-in-nodes/PairConditioningSetProperties.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetProperties" icon: "circle" mode: wide --- + **PairConditioningSetProperties** ノードを使用すると、ポジティブとネガティブの両方のコンディショニングペアのプロパティを同時に変更できます。このノードは、強度調整、コンディショニング領域の設定、オプションのマスクやタイミング制御を両方のコンディショニング入力に適用し、変更後のポジティブおよびネガティブコンディショニングデータを返します。 ## 入力 @@ -23,8 +24,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 適用されたプロパティを持つ変更後のポジティブコンディショニング | CONDITIONING | -| `negative` | 適用されたプロパティを持つ変更後のネガティブコンディショニング | CONDITIONING | +| `ポジティブ` | 適用されたプロパティを持つ変更後のポジティブコンディショニング | CONDITIONING | +| `ネガティブ` | 適用されたプロパティを持つ変更後のネガティブコンディショニング | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetProperties/ja.md) diff --git a/ja/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx b/ja/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx index 8127cab73..c2b1420cc 100644 --- a/ja/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx +++ b/ja/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetPropertiesAndCombine" icon: "circle" mode: wide --- + 以下は、指定された英語ドキュメントを日本語に翻訳したものです。 --- @@ -29,7 +30,7 @@ PairConditioningSetPropertiesAndCombine ノードは、既存のポジティブ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 結合されたポジティブ conditioning の出力 | CONDITIONING | +| `ポジティブ` | 結合されたポジティブ conditioning の出力 | CONDITIONING | | `ネガティブ` | 結合されたネガティブ conditioning の出力 | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetPropertiesAndCombine/ja.md) diff --git a/ja/built-in-nodes/PatchModelAddDownscale.mdx b/ja/built-in-nodes/PatchModelAddDownscale.mdx index 10989e7f2..35ce44f07 100644 --- a/ja/built-in-nodes/PatchModelAddDownscale.mdx +++ b/ja/built-in-nodes/PatchModelAddDownscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PatchModelAddDownscale" icon: "circle" mode: wide --- + PatchModelAddDownscale ノードは、モデル内の特定のブロックにダウンスケールおよびアップスケール処理を適用することで、Kohya Deep Shrink 機能を実装します。処理中の中間特徴量の解像度を低下させ、その後元のサイズに復元することで、品質を維持しながらパフォーマンスを向上させることができます。このノードは、モデルの実行中にこれらのスケーリング処理をいつ、どのように行うかを正確に制御できます。 ## 入力 diff --git a/ja/built-in-nodes/PerpNeg.mdx b/ja/built-in-nodes/PerpNeg.mdx index 327baba2c..be1b50929 100644 --- a/ja/built-in-nodes/PerpNeg.mdx +++ b/ja/built-in-nodes/PerpNeg.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerpNeg" icon: "circle" mode: wide --- + PerpNegノードは、モデルのサンプリングプロセスに垂直ネガティブガイダンスを適用します。このノードはモデルの設定関数を変更し、ネガティブ条件付けとスケーリング係数を使用してノイズ予測を調整します。このノードは非推奨となり、機能改善のためにPerpNegGuiderノードに置き換えられました。 ## 入力 diff --git a/ja/built-in-nodes/PerpNegGuider.mdx b/ja/built-in-nodes/PerpNegGuider.mdx index 03847e5b2..35f5ce8a8 100644 --- a/ja/built-in-nodes/PerpNegGuider.mdx +++ b/ja/built-in-nodes/PerpNegGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerpNegGuider" icon: "circle" mode: wide --- + PerpNegGuiderノードは、垂直ネガティブ条件付けを使用して画像生成を制御するガイダンスシステムを作成します。ポジティブ、ネガティブ、および空の条件付け入力を取得し、特殊なガイダンスアルゴリズムを適用して生成プロセスを誘導します。このノードは実験的なテスト用に設計されており、ガイダンスの強度とネガティブスケーリングを細かく制御できます。 ## 入力 diff --git a/ja/built-in-nodes/PerturbedAttentionGuidance.mdx b/ja/built-in-nodes/PerturbedAttentionGuidance.mdx index 7bd1fb8a9..6f709187a 100644 --- a/ja/built-in-nodes/PerturbedAttentionGuidance.mdx +++ b/ja/built-in-nodes/PerturbedAttentionGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerturbedAttentionGuidance" icon: "circle" mode: wide --- + {PerturbedAttentionGuidance}ノードは、摂動注意誘導（Perturbed Attention Guidance）を拡散モデルに適用し、生成品質を向上させます。このノードは、サンプリング中にモデルの自己注意機構を、値の射影に焦点を当てた簡略化バージョンに置き換えます。この手法により、条件付きノイズ除去プロセスを調整し、生成画像の一貫性と品質を向上させます。 ## 入力 diff --git a/ja/built-in-nodes/PhotoMakerEncode.mdx b/ja/built-in-nodes/PhotoMakerEncode.mdx index 132063951..19f089b17 100644 --- a/ja/built-in-nodes/PhotoMakerEncode.mdx +++ b/ja/built-in-nodes/PhotoMakerEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PhotoMakerEncode" icon: "circle" mode: wide --- + PhotoMakerEncode ノードは、画像とテキストを処理し、AI画像生成のためのコンディショニングデータを生成します。参照画像とテキストプロンプトを受け取り、参照画像の視覚的特徴に基づいて画像生成をガイドするための埋め込み（エンベディング）を作成します。このノードは特に、テキスト内の「photomaker」トークンを検出し、画像ベースのコンディショニングを適用する位置を決定します。 ## 入力 diff --git a/ja/built-in-nodes/PhotoMakerLoader.mdx b/ja/built-in-nodes/PhotoMakerLoader.mdx index 8c03d3db1..81b8c6271 100644 --- a/ja/built-in-nodes/PhotoMakerLoader.mdx +++ b/ja/built-in-nodes/PhotoMakerLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PhotoMakerLoader" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/PiDConditioning.mdx b/ja/built-in-nodes/PiDConditioning.mdx index aea99c2c6..e73205d7a 100644 --- a/ja/built-in-nodes/PiDConditioning.mdx +++ b/ja/built-in-nodes/PiDConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PiDConditioning" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/PikaImageToVideoNode2_2.mdx b/ja/built-in-nodes/PikaImageToVideoNode2_2.mdx index cd8ba8114..191750840 100644 --- a/ja/built-in-nodes/PikaImageToVideoNode2_2.mdx +++ b/ja/built-in-nodes/PikaImageToVideoNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaImageToVideoNode2_2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/PikaScenesV2_2.mdx b/ja/built-in-nodes/PikaScenesV2_2.mdx index 1f5891072..e9778cede 100644 --- a/ja/built-in-nodes/PikaScenesV2_2.mdx +++ b/ja/built-in-nodes/PikaScenesV2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaScenesV2_2" icon: "circle" mode: wide --- + PikaScenes v2.2 ノードは、複数の画像を組み合わせて、すべての入力画像のオブジェクトを取り入れた動画を生成します。最大5つの異なる画像を材料としてアップロードし、それらをシームレスに融合した高品質な動画を生成できます。 ## 入力 diff --git a/ja/built-in-nodes/PikaStartEndFrameNode2_2.mdx b/ja/built-in-nodes/PikaStartEndFrameNode2_2.mdx index 2f9b00a2c..70c1d7b61 100644 --- a/ja/built-in-nodes/PikaStartEndFrameNode2_2.mdx +++ b/ja/built-in-nodes/PikaStartEndFrameNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaStartEndFrameNode2_2" icon: "circle" mode: wide --- + PikaFrames v2.2 ノードは、最初と最後のフレームを組み合わせて動画を生成します。開始点と終了点を定義する2枚の画像をアップロードすると、AIがそれらの間のスムーズな遷移を作成し、完全な動画を生成します。 ## 入力 diff --git a/ja/built-in-nodes/PikaTextToVideoNode2_2.mdx b/ja/built-in-nodes/PikaTextToVideoNode2_2.mdx index 0b959a17f..9cd3cf6f5 100644 --- a/ja/built-in-nodes/PikaTextToVideoNode2_2.mdx +++ b/ja/built-in-nodes/PikaTextToVideoNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaTextToVideoNode2_2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Pika Text2Video v2.2 ノードは、テキストプロンプトを Pika API バージョン 2.2 に送信して動画を生成します。このノードは、テキストによる説明を Pika の AI 動画生成サービスを使用して動画に変換します。アスペクト比、再生時間、解像度など、動画生成プロセスのさまざまな側面をカスタマイズすることができます。 diff --git a/ja/built-in-nodes/Pikadditions.mdx b/ja/built-in-nodes/Pikadditions.mdx index f8f3032d4..ac695dfe5 100644 --- a/ja/built-in-nodes/Pikadditions.mdx +++ b/ja/built-in-nodes/Pikadditions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikadditions" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Pikadditions ノードを使用すると、任意のオブジェクトや画像を動画に追加できます。動画をアップロードし、追加したい内容を指定するだけで、シームレスに統合された結果が生成されます。このノードは Pika API を利用して、自然な見た目で画像を動画に挿入します。 diff --git a/ja/built-in-nodes/Pikaffects.mdx b/ja/built-in-nodes/Pikaffects.mdx index 7170d7ec9..335828449 100644 --- a/ja/built-in-nodes/Pikaffects.mdx +++ b/ja/built-in-nodes/Pikaffects.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikaffects" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- diff --git a/ja/built-in-nodes/Pikaswaps.mdx b/ja/built-in-nodes/Pikaswaps.mdx index 5eff30547..2a904a543 100644 --- a/ja/built-in-nodes/Pikaswaps.mdx +++ b/ja/built-in-nodes/Pikaswaps.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikaswaps" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/PixverseImageToVideoNode.mdx b/ja/built-in-nodes/PixverseImageToVideoNode.mdx index c4fb57933..f587d37fa 100644 --- a/ja/built-in-nodes/PixverseImageToVideoNode.mdx +++ b/ja/built-in-nodes/PixverseImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseImageToVideoNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！ 入力画像とテキストプロンプトに基づいて動画を生成します。このノードは画像を受け取り、指定されたモーションと品質設定を適用して、静止画像を動きのあるシーケンスに変換することでアニメーション動画を作成します。 diff --git a/ja/built-in-nodes/PixverseTemplateNode.mdx b/ja/built-in-nodes/PixverseTemplateNode.mdx index 32e052400..edf8f235b 100644 --- a/ja/built-in-nodes/PixverseTemplateNode.mdx +++ b/ja/built-in-nodes/PixverseTemplateNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTemplateNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 PixVerse テンプレートノードを使用すると、PixVerse 動画生成で利用可能なテンプレートを選択できます。選択したテンプレート名を、PixVerse API が動画作成に必要とする対応するテンプレート ID に変換します。 diff --git a/ja/built-in-nodes/PixverseTextToVideoNode.mdx b/ja/built-in-nodes/PixverseTextToVideoNode.mdx index 465ba96bb..3ef051b3d 100644 --- a/ja/built-in-nodes/PixverseTextToVideoNode.mdx +++ b/ja/built-in-nodes/PixverseTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTextToVideoNode" icon: "circle" mode: wide --- + このドキュメントは AI によって生成されました。誤りや改善のための提案があれば、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTextToVideoNode/en.md) テキストプロンプトと様々な生成パラメータに基づいて動画を生成します。このノードは PixVerse API を使用して動画コンテンツを作成し、アスペクト比、品質、長さ、モーションスタイルなどを制御できます。 diff --git a/ja/built-in-nodes/PixverseTransitionVideoNode.mdx b/ja/built-in-nodes/PixverseTransitionVideoNode.mdx index dc3706874..680a111b2 100644 --- a/ja/built-in-nodes/PixverseTransitionVideoNode.mdx +++ b/ja/built-in-nodes/PixverseTransitionVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTransitionVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 PixVerse API を使用して、2つの入力画像間のトランジションビデオを生成します。開始画像と終了画像を指定すると、テキストプロンプトと選択した設定に基づいて、一方から他方へスムーズに移行するビデオを作成します。 diff --git a/ja/built-in-nodes/PolyexponentialScheduler.mdx b/ja/built-in-nodes/PolyexponentialScheduler.mdx index d517392ca..bf726233c 100644 --- a/ja/built-in-nodes/PolyexponentialScheduler.mdx +++ b/ja/built-in-nodes/PolyexponentialScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PolyexponentialScheduler" icon: "circle" mode: wide --- + PolyexponentialScheduler ノードは、多項式指数ノイズスケジュールに基づいてノイズレベル（シグマ）のシーケンスを生成するように設計されています。このスケジュールはシグマの対数における多項式関数であり、拡散プロセス全体を通じてノイズレベルを柔軟かつカスタマイズ可能な進行で変化させることができます。 ## 入力 diff --git a/ja/built-in-nodes/PorterDuffImageComposite.mdx b/ja/built-in-nodes/PorterDuffImageComposite.mdx index ecf438289..e6a205298 100644 --- a/ja/built-in-nodes/PorterDuffImageComposite.mdx +++ b/ja/built-in-nodes/PorterDuffImageComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PorterDuffImageComposite" icon: "circle" mode: wide --- + 以下は、指定されたルールに従った日本語翻訳です。 PorterDuffImageComposite ノードは、Porter-Duff 合成オペレーターを使用して画像合成を実行するために設計されています。このノードは、様々なブレンドモードに従ってソース画像とデスティネーション画像を組み合わせることを可能にし、画像の透明度を操作したり、画像を創造的に重ね合わせることで、複雑な視覚効果を生成できます。 diff --git a/ja/built-in-nodes/Preview3D.mdx b/ja/built-in-nodes/Preview3D.mdx index a062db0b9..f10592f8b 100644 --- a/ja/built-in-nodes/Preview3D.mdx +++ b/ja/built-in-nodes/Preview3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Preview3D" icon: "circle" mode: wide --- + 以下は、提供された英語ドキュメントを日本語に翻訳したものです。 Preview3Dノードは、主に3Dモデルの出力をプレビューするために使用されます。このノードは2つの入力を受け取ります。1つはLoad3Dノードからの`camera_info`、もう1つは3Dモデルファイルへのパスです。モデルファイルのパスは、`ComfyUI/output`フォルダ内に配置されている必要があります。 diff --git a/ja/built-in-nodes/Preview3DAdvanced.mdx b/ja/built-in-nodes/Preview3DAdvanced.mdx index 4fd3b02b9..18b50a455 100644 --- a/ja/built-in-nodes/Preview3DAdvanced.mdx +++ b/ja/built-in-nodes/Preview3DAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Preview3DAdvanced" icon: "circle" mode: wide --- -# プレビュー3D（詳細設定） このノードは、カメラとモデル情報の出力を伴う高度な3Dモデルプレビューを提供します。3Dモデルを一時ファイルに保存してUIに表示するとともに、モデルデータ、カメラ情報、ビューポートの寸法を後続の処理に渡します。 @@ -24,10 +23,10 @@ mode: wide | 出力名 | 説明 | データ型 | |-------------|-------------|-----------| -| `カメラ情報` | 入力から渡された3Dモデルファイルです。 | FILE3D | -| `3Dモデル情報` | 入力またはビューポート状態からのモデル情報メタデータです。 | LOAD3DMODELINFO | -| `幅` | 入力またはビューポート状態からのカメラ設定です。 | LOAD3DCAMERA | -| `高さ` | プレビューの幅（ピクセル単位）です。 | INT | +| `model_file` | 入力から渡された3Dモデルファイルです。 | FILE3D | +| `カメラ情報` | 入力またはビューポート状態からのモデル情報メタデータです。 | LOAD3DMODELINFO | +| `3Dモデル情報` | 入力またはビューポート状態からのカメラ設定です。 | LOAD3DCAMERA | +| `幅` | プレビューの幅（ピクセル単位）です。 | INT | | `高さ` | プレビューの高さ（ピクセル単位）です。 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Preview3DAdvanced/ja.md) diff --git a/ja/built-in-nodes/Preview3DAnimation.mdx b/ja/built-in-nodes/Preview3DAnimation.mdx index 3f2167b29..b6b3d03ef 100644 --- a/ja/built-in-nodes/Preview3DAnimation.mdx +++ b/ja/built-in-nodes/Preview3DAnimation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Preview3DAnimation" icon: "circle" mode: wide --- + 以下は、ご指定の翻訳ルールに従って日本語に翻訳したドキュメントです。 Preview3DAnimationノードは、主に3Dモデルの出力をプレビューするために使用されます。このノードは2つの入力を受け取ります。1つはLoad3Dノードからの`camera_info`、もう1つは3Dモデルファイルへのパスです。モデルファイルのパスは、`ComfyUI/output`フォルダ内に存在する必要があります。 diff --git a/ja/built-in-nodes/PreviewAny.mdx b/ja/built-in-nodes/PreviewAny.mdx index e18c50bec..da13f3ee4 100644 --- a/ja/built-in-nodes/PreviewAny.mdx +++ b/ja/built-in-nodes/PreviewAny.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewAny" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご貢献ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAny/en.md) PreviewAnyノードは、任意の入力データ型のプレビューをテキスト形式で表示します。あらゆるデータ型を入力として受け付け、読み取り可能な文字列表現に変換して表示します。このノードは、文字列、数値、ブーリアン、複雑なオブジェクトなど、さまざまなデータ型を自動的に処理し、JSON形式へのシリアライズを試みます。 diff --git a/ja/built-in-nodes/PreviewAudio.mdx b/ja/built-in-nodes/PreviewAudio.mdx index 36db68739..8a75b5cb8 100644 --- a/ja/built-in-nodes/PreviewAudio.mdx +++ b/ja/built-in-nodes/PreviewAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 PreviewAudioノードは、インターフェース上で直接再生可能な一時的なオーディオプレビューを作成します。オーディオデータを入力として受け取り、プレビューウィジェットを生成することで、ユーザーが永続的なファイルを保存することなくオーディオ出力を聴くことを可能にします。 @@ -19,7 +20,7 @@ PreviewAudioノードは、インターフェース上で直接再生可能な | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ui` | インターフェース上にオーディオプレイヤーウィジェットを表示し、オーディオをプレビューします | UI | +| `audio` | インターフェース上にオーディオプレイヤーウィジェットを表示し、オーディオをプレビューします | UI | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAudio/ja.md) diff --git a/ja/built-in-nodes/PreviewGaussianSplat.mdx b/ja/built-in-nodes/PreviewGaussianSplat.mdx index f7c5fc82b..a02c508e4 100644 --- a/ja/built-in-nodes/PreviewGaussianSplat.mdx +++ b/ja/built-in-nodes/PreviewGaussianSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PreviewGaussianSplat" icon: "circle" mode: wide --- -# PreviewGaussianSplat PreviewGaussianSplat ノードを使用すると、ComfyUI インターフェース内で3Dガウシアンスプラットファイルをプレビューできます。様々なガウシアンスプラット形式の3Dモデルファイルを受け入れ、3Dプレビューウィンドウにレンダリングし、モデルデータをそのまま後続の処理に渡します。 diff --git a/ja/built-in-nodes/PreviewImage.mdx b/ja/built-in-nodes/PreviewImage.mdx index 8302a248f..554c2e98b 100644 --- a/ja/built-in-nodes/PreviewImage.mdx +++ b/ja/built-in-nodes/PreviewImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewImage" icon: "circle" mode: wide --- + ## 概要 PreviewImageノードは、一時的なプレビュー画像を作成するために設計されています。各画像に対して一意の一時ファイル名を自動生成し、指定された圧縮レベルで画像を圧縮して一時ディレクトリに保存します。この機能は、元のファイルに影響を与えることなく、処理中の画像のプレビューを生成する場合に特に便利です。 diff --git a/ja/built-in-nodes/PreviewPointCloud.mdx b/ja/built-in-nodes/PreviewPointCloud.mdx index 0b3088a77..722ff0e3f 100644 --- a/ja/built-in-nodes/PreviewPointCloud.mdx +++ b/ja/built-in-nodes/PreviewPointCloud.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PreviewPointCloud" icon: "circle" mode: wide --- -# プレビューポイントクラウド Preview Point Cloud ノードを使用すると、ComfyUI インターフェース内で3Dポイントクラウドファイルを表示できます。このノードはポイントクラウドを一時ファイルに保存し、3Dプレビューウィンドウに表示するとともに、モデルデータとビューポート設定を後続の処理に渡します。 diff --git a/ja/built-in-nodes/PrimitiveBoolean.mdx b/ja/built-in-nodes/PrimitiveBoolean.mdx index 68e557c3d..c3c58208d 100644 --- a/ja/built-in-nodes/PrimitiveBoolean.mdx +++ b/ja/built-in-nodes/PrimitiveBoolean.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveBoolean" icon: "circle" mode: wide --- + このドキュメントはAIが生成しました。誤りや改善の提案があれば、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveBoolean/en.md) ブールノードは、ワークフローを通じてブール値（true/false）を渡すためのシンプルな方法を提供します。ブール値の入力を受け取り、その値を変更せずにそのまま出力することで、他のノードのブールパラメータを制御できます。 diff --git a/ja/built-in-nodes/PrimitiveBoundingBox.mdx b/ja/built-in-nodes/PrimitiveBoundingBox.mdx index 66091cac0..e50e085b5 100644 --- a/ja/built-in-nodes/PrimitiveBoundingBox.mdx +++ b/ja/built-in-nodes/PrimitiveBoundingBox.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveBoundingBox" icon: "circle" mode: wide --- + PrimitiveBoundingBox ノードは、位置とサイズによって定義される単純な矩形領域を作成します。左上隅の X 座標と Y 座標、および幅と高さの値を受け取り、ワークフロー内の他のノードで使用できるバウンディングボックスのデータ構造を出力します。 ## 入力 diff --git a/ja/built-in-nodes/PrimitiveFloat.mdx b/ja/built-in-nodes/PrimitiveFloat.mdx index 4c7f3fe2a..d3503773c 100644 --- a/ja/built-in-nodes/PrimitiveFloat.mdx +++ b/ja/built-in-nodes/PrimitiveFloat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveFloat" icon: "circle" mode: wide --- + PrimitiveFloatノードは、ワークフロー内で使用できる浮動小数点数値を作成します。単一の数値入力を受け取り、その値をそのまま出力することで、ComfyUIパイプライン内の異なるノード間で浮動小数点値を定義して受け渡すことができます。 ## 入力 diff --git a/ja/built-in-nodes/PrimitiveInt.mdx b/ja/built-in-nodes/PrimitiveInt.mdx index b3c014d4b..b5ac12455 100644 --- a/ja/built-in-nodes/PrimitiveInt.mdx +++ b/ja/built-in-nodes/PrimitiveInt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveInt" icon: "circle" mode: wide --- + PrimitiveIntノードは、ワークフロー内で整数値を扱うためのシンプルな方法を提供します。整数値の入力を受け取り、同じ値を出力することで、ノード間で整数パラメーターを渡したり、他の操作に特定の数値を設定するのに便利です。 ## 入力 diff --git a/ja/built-in-nodes/PrimitiveString.mdx b/ja/built-in-nodes/PrimitiveString.mdx index cf98fe2f2..d816f5de5 100644 --- a/ja/built-in-nodes/PrimitiveString.mdx +++ b/ja/built-in-nodes/PrimitiveString.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveString" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveString/en.md) Stringノードは、ワークフロー内でテキストデータを簡単に入力および受け渡しする方法を提供します。テキスト文字列を入力として受け取り、変更せずに同じ文字列を出力するため、文字列パラメータを必要とする他のノードにテキスト入力を提供するのに便利です。 diff --git a/ja/built-in-nodes/PrimitiveStringMultiline.mdx b/ja/built-in-nodes/PrimitiveStringMultiline.mdx index 9da01430d..740402b65 100644 --- a/ja/built-in-nodes/PrimitiveStringMultiline.mdx +++ b/ja/built-in-nodes/PrimitiveStringMultiline.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveStringMultiline" icon: "circle" mode: wide --- + ## 概要 PrimitiveStringMultiline ノードは、複数行のテキスト入力フィールドを提供し、ワークフロー内で文字列値を入力および受け渡しするために使用します。このノードは複数行にわたるテキスト入力を受け付け、入力された文字列値をそのまま出力します。長いテキストコンテンツや複数行にわたるフォーマット済みテキストを入力する必要がある場合に便利です。 diff --git a/ja/built-in-nodes/QuadrupleCLIPLoader.mdx b/ja/built-in-nodes/QuadrupleCLIPLoader.mdx index a4244cb4b..215585a57 100644 --- a/ja/built-in-nodes/QuadrupleCLIPLoader.mdx +++ b/ja/built-in-nodes/QuadrupleCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QuadrupleCLIPLoader" icon: "circle" mode: wide --- + 以下は、ご指定の翻訳ルールに従った日本語訳です。 --- diff --git a/ja/built-in-nodes/QuiverImageToSVGNode.mdx b/ja/built-in-nodes/QuiverImageToSVGNode.mdx index a4edaa407..20205b4e8 100644 --- a/ja/built-in-nodes/QuiverImageToSVGNode.mdx +++ b/ja/built-in-nodes/QuiverImageToSVGNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QuiverImageToSVGNode" icon: "circle" mode: wide --- + このノードは、Quiver AIのベクトル化モデルを使用して、ラスター画像をスケーラブルベクターグラフィック（SVG）に変換します。画像を外部APIに送信し、処理後にベクトル化された結果を返します。 ## 入力 diff --git a/ja/built-in-nodes/QuiverTextToSVGNode.mdx b/ja/built-in-nodes/QuiverTextToSVGNode.mdx index a1048cc90..d4374eb25 100644 --- a/ja/built-in-nodes/QuiverTextToSVGNode.mdx +++ b/ja/built-in-nodes/QuiverTextToSVGNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QuiverTextToSVGNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/QwenImageDiffsynthControlnet.mdx b/ja/built-in-nodes/QwenImageDiffsynthControlnet.mdx index 347817e5e..23f60575c 100644 --- a/ja/built-in-nodes/QwenImageDiffsynthControlnet.mdx +++ b/ja/built-in-nodes/QwenImageDiffsynthControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QwenImageDiffsynthControlnet" icon: "circle" mode: wide --- + 以下が翻訳結果です。 **QwenImageDiffsynthControlnet** ノードは、拡散合成制御ネットワークパッチを適用してベースモデルの動作を変更します。画像入力とオプションのマスクを使用して、調整可能な強度でモデルの生成プロセスをガイドし、制御ネットワークの影響を組み込んだパッチ適用済みモデルを作成することで、より制御された画像合成を実現します。 diff --git a/ja/built-in-nodes/RTDETR_detect.mdx b/ja/built-in-nodes/RTDETR_detect.mdx index 9af7183b6..ac43f04ad 100644 --- a/ja/built-in-nodes/RTDETR_detect.mdx +++ b/ja/built-in-nodes/RTDETR_detect.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RTDETR_detect" icon: "circle" mode: wide --- + RT-DETR Detect ノードは、RT-DETRモデルを使用して入力画像に対して物体検出を実行します。オブジェクトを識別し、その周囲にバウンディングボックスを描画し、COCOデータセットのクラスに従ってラベルを付けます。信頼度スコア、オブジェクトクラスによる結果のフィルタリング、および検出数の上限設定が可能です。 ## 入力 diff --git a/ja/built-in-nodes/RandomCropImages.mdx b/ja/built-in-nodes/RandomCropImages.mdx index ae6271b13..bb4963ab2 100644 --- a/ja/built-in-nodes/RandomCropImages.mdx +++ b/ja/built-in-nodes/RandomCropImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RandomCropImages" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- @@ -26,7 +27,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `image` | ランダムクロップが適用された結果の画像です。 | IMAGE | +| `images` | ランダムクロップが適用された結果の画像です。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RandomCropImages/ja.md) diff --git a/ja/built-in-nodes/RandomNoise.mdx b/ja/built-in-nodes/RandomNoise.mdx index fb392e062..b4b3358e9 100644 --- a/ja/built-in-nodes/RandomNoise.mdx +++ b/ja/built-in-nodes/RandomNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RandomNoise" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 RandomNoise ノードは、シード値に基づいてランダムなノイズパターンを生成します。このノードは再現可能なノイズを作成し、さまざまな画像処理や生成タスクに利用できます。同じシード値を使用すれば常に同じノイズパターンが生成されるため、複数回の実行で一貫した結果を得ることができます。 diff --git a/ja/built-in-nodes/RebatchImages.mdx b/ja/built-in-nodes/RebatchImages.mdx index 5bee72f3f..7ce75d95d 100644 --- a/ja/built-in-nodes/RebatchImages.mdx +++ b/ja/built-in-nodes/RebatchImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RebatchImages" icon: "circle" mode: wide --- + RebatchImagesノードは、画像のバッチを新しいバッチ構成に再編成し、指定されたバッチサイズに調整するために設計されています。この処理は、バッチ操作における画像データの処理を管理・最適化し、効率的な処理のために画像が目的のバッチサイズに従ってグループ化されることを保証するために不可欠です。 ## 入力 diff --git a/ja/built-in-nodes/RebatchLatents.mdx b/ja/built-in-nodes/RebatchLatents.mdx index 2cdf39882..aaefa5d46 100644 --- a/ja/built-in-nodes/RebatchLatents.mdx +++ b/ja/built-in-nodes/RebatchLatents.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RebatchLatents" icon: "circle" mode: wide --- + RebatchLatents ノードは、指定されたバッチサイズに基づいて、潜在表現のバッチを新しいバッチ構成に再編成するように設計されています。これにより、潜在サンプルが適切にグループ化され、次元やサイズのばらつきが処理され、さらなる処理やモデル推論が容易になります。 ## 入力 diff --git a/ja/built-in-nodes/RecordAudio.mdx b/ja/built-in-nodes/RecordAudio.mdx index 6f702c2e0..344d4e8b2 100644 --- a/ja/built-in-nodes/RecordAudio.mdx +++ b/ja/built-in-nodes/RecordAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecordAudio" icon: "circle" mode: wide --- + 以下は、指定された翻訳ルールに従った日本語訳です。 ## 概要 diff --git a/ja/built-in-nodes/RecraftColorRGB.mdx b/ja/built-in-nodes/RecraftColorRGB.mdx index 3f6e7461c..7b7376726 100644 --- a/ja/built-in-nodes/RecraftColorRGB.mdx +++ b/ja/built-in-nodes/RecraftColorRGB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftColorRGB" icon: "circle" mode: wide --- + 赤、緑、青の各値を個別に指定してRecraftカラーを作成します。このノードはRGB整数値（0～255）を受け取り、他のRecraft操作で使用可能なRecraftカラーフォーマットに変換します。既存のRecraftカラーチェーンをオプションで指定し、新しい色で拡張することもできます。 ## 入力 diff --git a/ja/built-in-nodes/RecraftControls.mdx b/ja/built-in-nodes/RecraftControls.mdx index 5cf2930d2..76923d408 100644 --- a/ja/built-in-nodes/RecraftControls.mdx +++ b/ja/built-in-nodes/RecraftControls.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftControls" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 Recraft 生成をカスタマイズするための Recraft コントロールを作成します。このノードを使用すると、Recraft 画像生成プロセス中に使用されるカラー設定を構成できます。 diff --git a/ja/built-in-nodes/RecraftCreateStyleNode.mdx b/ja/built-in-nodes/RecraftCreateStyleNode.mdx index 6fc8fa66f..f323ff218 100644 --- a/ja/built-in-nodes/RecraftCreateStyleNode.mdx +++ b/ja/built-in-nodes/RecraftCreateStyleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCreateStyleNode" icon: "circle" mode: wide --- + このノードは、参照画像をアップロードすることで、画像生成用のカスタムスタイルを作成します。1～5枚の画像をアップロードして新しいスタイルを定義すると、ノードは他のRecraftノードで使用できる一意のスタイルIDを返します。アップロードするすべての画像の合計ファイルサイズは5 MBを超えてはなりません。 ## 入力 @@ -20,7 +21,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `style_id` | 新しく作成されたカスタムスタイルの一意の識別子。 | STRING | +| `スタイルID` | 新しく作成されたカスタムスタイルの一意の識別子。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreateStyleNode/ja.md) diff --git a/ja/built-in-nodes/RecraftCreativeUpscaleNode.mdx b/ja/built-in-nodes/RecraftCreativeUpscaleNode.mdx index db4395fef..d8940d7a5 100644 --- a/ja/built-in-nodes/RecraftCreativeUpscaleNode.mdx +++ b/ja/built-in-nodes/RecraftCreativeUpscaleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCreativeUpscaleNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご貢献ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreativeUpscaleNode/en.md) Recraft Creative Upscale Image ノードは、ラスター画像の解像度を高めて拡大します。このノードは「クリエイティブアップスケール」処理を使用し、画像内の細かいディテールや顔の部分を重点的に改善します。この処理は外部APIを通じて同期的に実行されます。 diff --git a/ja/built-in-nodes/RecraftCrispUpscaleNode.mdx b/ja/built-in-nodes/RecraftCrispUpscaleNode.mdx index 6aca113fd..e71ca919d 100644 --- a/ja/built-in-nodes/RecraftCrispUpscaleNode.mdx +++ b/ja/built-in-nodes/RecraftCrispUpscaleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCrispUpscaleNode" icon: "circle" mode: wide --- + 画像を同期的にアップスケールします。'crisp upscale'ツールを使用して指定されたラスター画像を強化し、画像の解像度を向上させ、よりシャープでクリアな画像にします。 ## 入力 diff --git a/ja/built-in-nodes/RecraftImageInpaintingNode.mdx b/ja/built-in-nodes/RecraftImageInpaintingNode.mdx index 1b1d707ed..0a1d20dac 100644 --- a/ja/built-in-nodes/RecraftImageInpaintingNode.mdx +++ b/ja/built-in-nodes/RecraftImageInpaintingNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftImageInpaintingNode" icon: "circle" mode: wide --- + このノードは、テキストプロンプトとマスクに基づいて、画像の特定の領域を修正します。Recraft APIを使用して、マスクされた領域のみをインテリジェントに編集し、画像の残りの部分は変更しません。 ## 入力 diff --git a/ja/built-in-nodes/RecraftImageToImageNode.mdx b/ja/built-in-nodes/RecraftImageToImageNode.mdx index d0d49e49f..a625c1638 100644 --- a/ja/built-in-nodes/RecraftImageToImageNode.mdx +++ b/ja/built-in-nodes/RecraftImageToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftImageToImageNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageToImageNode/en.md) このノードは、テキストプロンプトと強度パラメータに基づいて、既存の画像を変更します。Recraft APIを使用して、提供された説明に従って入力画像を変換し、強度設定に基づいて元の画像との類似性を維持します。 diff --git a/ja/built-in-nodes/RecraftRemoveBackgroundNode.mdx b/ja/built-in-nodes/RecraftRemoveBackgroundNode.mdx index c4860baf3..daaacb57c 100644 --- a/ja/built-in-nodes/RecraftRemoveBackgroundNode.mdx +++ b/ja/built-in-nodes/RecraftRemoveBackgroundNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftRemoveBackgroundNode" icon: "circle" mode: wide --- + このノードは、Recraft API サービスを使用して画像から背景を除去します。入力バッチ内の各画像を処理し、透明な背景を持つ処理済み画像と、除去された背景領域を示す対応するアルファマスクの両方を返します。 ## 入力 diff --git a/ja/built-in-nodes/RecraftReplaceBackgroundNode.mdx b/ja/built-in-nodes/RecraftReplaceBackgroundNode.mdx index a48508233..ed6a9ef1e 100644 --- a/ja/built-in-nodes/RecraftReplaceBackgroundNode.mdx +++ b/ja/built-in-nodes/RecraftReplaceBackgroundNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftReplaceBackgroundNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftReplaceBackgroundNode/en.md) 提供されたプロンプトに基づいて、画像の背景を置き換えます。このノードはRecraft APIを使用して、テキストによる説明に従って画像に新しい背景を生成し、主要な被写体をそのままに背景を完全に変更することができます。 diff --git a/ja/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx b/ja/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx index 865a30881..9ff11c5cb 100644 --- a/ja/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx +++ b/ja/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3DigitalIllustration" icon: "circle" mode: wide --- + このノードは、Recraft APIで使用するスタイルを設定するもので、特に「digital_illustration（デジタルイラスト）」スタイルを選択します。生成される画像の芸術的な方向性をさらに絞り込むために、オプションのサブスタイルを選択できます。 ## 入力 diff --git a/ja/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx b/ja/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx index a9edcf9e8..86b78f26a 100644 --- a/ja/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx +++ b/ja/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3InfiniteStyleLibrary" icon: "circle" mode: wide --- + このノードは、既存のUUIDを使用してRecraftのInfinite Style Libraryからスタイルを選択できます。提供されたスタイル識別子に基づいてスタイル情報を取得し、他のRecraftノードで使用できるように返します。 ## 入力 diff --git a/ja/built-in-nodes/RecraftStyleV3LogoRaster.mdx b/ja/built-in-nodes/RecraftStyleV3LogoRaster.mdx index 97c325a9a..24dbbc861 100644 --- a/ja/built-in-nodes/RecraftStyleV3LogoRaster.mdx +++ b/ja/built-in-nodes/RecraftStyleV3LogoRaster.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3LogoRaster" icon: "circle" mode: wide --- + このノードは、ロゴ画像を生成するためのロゴラスタースタイルとオプションのサブスタイルを選択します。ラスターベースのビジュアル処理を用いたロゴデザインの作成に特化しています。 ## 入力 diff --git a/ja/built-in-nodes/RecraftStyleV3RealisticImage.mdx b/ja/built-in-nodes/RecraftStyleV3RealisticImage.mdx index fa9a6ea1b..8ac86d144 100644 --- a/ja/built-in-nodes/RecraftStyleV3RealisticImage.mdx +++ b/ja/built-in-nodes/RecraftStyleV3RealisticImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3RealisticImage" icon: "circle" mode: wide --- + このノードは、RecraftのAPIを使用してリアルな画像を生成するためのスタイル設定を作成します。`realistic_image`スタイルを選択し、出力の外観を微調整するためのオプションのサブスタイルを指定できます。 ## 入力 diff --git a/ja/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx b/ja/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx index bafb9148d..fe60bb196 100644 --- a/ja/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx +++ b/ja/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3VectorIllustrationNode" icon: "circle" mode: wide --- + このノードは、Recraft APIで使用するスタイルを設定するもので、特に`vector_illustration`スタイルを選択します。このカテゴリ内で、より具体的なサブスタイルをオプションで選択できます。このノードは、他のRecraft APIノードに渡すことができるスタイル設定オブジェクトを出力します。 ## 入力 diff --git a/ja/built-in-nodes/RecraftTextToImageNode.mdx b/ja/built-in-nodes/RecraftTextToImageNode.mdx index 519f5c809..49918cb83 100644 --- a/ja/built-in-nodes/RecraftTextToImageNode.mdx +++ b/ja/built-in-nodes/RecraftTextToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftTextToImageNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善のご提案がございましたら、お気軽にご貢献ください！ [GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftTextToImageNode/en.md) プロンプトと解像度に基づいて同期的に画像を生成します。このノードはRecraft APIに接続し、指定された寸法とオプションのスタイルおよび制御パラメータを使用して、テキスト記述から画像を作成します。 diff --git a/ja/built-in-nodes/RecraftTextToVectorNode.mdx b/ja/built-in-nodes/RecraftTextToVectorNode.mdx index 9b0edfd57..2cee26f52 100644 --- a/ja/built-in-nodes/RecraftTextToVectorNode.mdx +++ b/ja/built-in-nodes/RecraftTextToVectorNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftTextToVectorNode" icon: "circle" mode: wide --- + テキストプロンプトと解像度に基づいて、同期的にSVGベクターイラストを生成します。このノードはプロンプトをRecraft APIに送信し、生成されたSVGコンテンツを返します。 ## 入力 diff --git a/ja/built-in-nodes/RecraftV4TextToImageNode.mdx b/ja/built-in-nodes/RecraftV4TextToImageNode.mdx index 66a1b4d8f..45cd36f2e 100644 --- a/ja/built-in-nodes/RecraftV4TextToImageNode.mdx +++ b/ja/built-in-nodes/RecraftV4TextToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftV4TextToImageNode" icon: "circle" mode: wide --- + このノードは、Recraft V4 または V4 Pro AI モデルを使用して、テキスト説明から画像を生成します。プロンプトを外部APIに送信し、生成された画像を返します。モデル、画像サイズ、生成枚数を指定して出力を制御できます。 ## 入力 diff --git a/ja/built-in-nodes/RecraftV4TextToVectorNode.mdx b/ja/built-in-nodes/RecraftV4TextToVectorNode.mdx index ba6e1eb2a..241fc2d23 100644 --- a/ja/built-in-nodes/RecraftV4TextToVectorNode.mdx +++ b/ja/built-in-nodes/RecraftV4TextToVectorNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftV4TextToVectorNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/RecraftVectorizeImageNode.mdx b/ja/built-in-nodes/RecraftVectorizeImageNode.mdx index f43efae48..63e98b15e 100644 --- a/ja/built-in-nodes/RecraftVectorizeImageNode.mdx +++ b/ja/built-in-nodes/RecraftVectorizeImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftVectorizeImageNode" icon: "circle" mode: wide --- + 以下は、指定された翻訳ルールに従って日本語に翻訳したドキュメントです。 入力画像から同期的にSVGを生成します。このノードは、入力バッチ内の各画像を処理し、その結果を1つのSVG出力に結合することで、ラスター画像をベクターグラフィックス形式に変換します。 diff --git a/ja/built-in-nodes/ReferenceLatent.mdx b/ja/built-in-nodes/ReferenceLatent.mdx index ca4382a44..007927411 100644 --- a/ja/built-in-nodes/ReferenceLatent.mdx +++ b/ja/built-in-nodes/ReferenceLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReferenceLatent" icon: "circle" mode: wide --- + このノードは、編集モデル用のガイド用潜在変数を設定します。条件付けデータとオプションの潜在変数入力を受け取り、参照潜在変数情報を含むように条件付けを変更します。モデルが対応している場合、複数のReferenceLatentノードを連鎖させて、複数の参照画像を設定することもできます。 ## 入力 diff --git a/ja/built-in-nodes/ReferenceTimbreAudio.mdx b/ja/built-in-nodes/ReferenceTimbreAudio.mdx index d2bac5239..60926ac85 100644 --- a/ja/built-in-nodes/ReferenceTimbreAudio.mdx +++ b/ja/built-in-nodes/ReferenceTimbreAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReferenceTimbreAudio" icon: "circle" mode: wide --- + このノードは、「ace step 1.5」プロセスで使用する参照音声の音色を設定します。条件付け入力と、オプションで音声の潜在表現を受け取り、その潜在データを条件付けに付加することで、ワークフロー内の後続ノードで使用できるようにします。 ## 入力 diff --git a/ja/built-in-nodes/RegexExtract.mdx b/ja/built-in-nodes/RegexExtract.mdx index 612b64f3a..27a3f1c64 100644 --- a/ja/built-in-nodes/RegexExtract.mdx +++ b/ja/built-in-nodes/RegexExtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexExtract" icon: "circle" mode: wide --- + 以下が翻訳結果です。 RegexExtract ノードは、正規表現を使用してテキスト内のパターンを検索します。最初の一致、すべての一致、一致結果の特定のグループ、または複数の一致にわたるすべてのグループを検索できます。このノードは、大文字と小文字の区別、複数行マッチング、ドットオール動作など、さまざまな正規表現フラグをサポートしています。 diff --git a/ja/built-in-nodes/RegexMatch.mdx b/ja/built-in-nodes/RegexMatch.mdx index f9961422d..00a94555b 100644 --- a/ja/built-in-nodes/RegexMatch.mdx +++ b/ja/built-in-nodes/RegexMatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexMatch" icon: "circle" mode: wide --- + このドキュメントは AI が生成しました。誤りを見つけたり、改善の提案がある場合は、ぜひコントリビュートしてください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexMatch/en.md) RegexMatch ノードは、テキスト文字列が指定された正規表現パターンに一致するかどうかを確認します。入力文字列を検索し、パターンがテキスト内のどこかに見つかったかどうかを示す単純な yes/no の結果を返します。大文字と小文字を区別しないマッチングやマルチラインモードなどのオプションを有効にすることで、検索の動作を調整できます。 @@ -23,7 +24,7 @@ RegexMatch ノードは、テキスト文字列が指定された正規表現パ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `matches` | 正規表現パターンが入力文字列の一部に一致する場合は True、それ以外の場合は False を返します | BOOLEAN | +| `マッチ` | 正規表現パターンが入力文字列の一部に一致する場合は True、それ以外の場合は False を返します | BOOLEAN | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexMatch/ja.md) diff --git a/ja/built-in-nodes/RegexReplace.mdx b/ja/built-in-nodes/RegexReplace.mdx index 5baf80810..26335fad4 100644 --- a/ja/built-in-nodes/RegexReplace.mdx +++ b/ja/built-in-nodes/RegexReplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexReplace" icon: "circle" mode: wide --- + 以下が翻訳結果です。 RegexReplaceノードは、正規表現パターンを使用して文字列内のテキストを検索および置換します。テキストパターンを検索し、新しいテキストに置き換えることができます。パターンマッチングの動作を制御するオプションとして、大文字と小文字の区別、複数行マッチング、置換回数の制限などがあります。 diff --git a/ja/built-in-nodes/RemoveBackground.mdx b/ja/built-in-nodes/RemoveBackground.mdx index 6c13dc705..1b395d251 100644 --- a/ja/built-in-nodes/RemoveBackground.mdx +++ b/ja/built-in-nodes/RemoveBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RemoveBackground" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -22,7 +23,7 @@ Remove Background ノードは、背景除去モデルを使用して、入力 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `mask` | 入力画像の主要な被写体を強調表示する生成された前景マスク | MASK | +| `マスク` | 入力画像の主要な被写体を強調表示する生成された前景マスク | MASK | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RemoveBackground/ja.md) diff --git a/ja/built-in-nodes/RenderSplat.mdx b/ja/built-in-nodes/RenderSplat.mdx index faa2ac1fa..ba3b194cc 100644 --- a/ja/built-in-nodes/RenderSplat.mdx +++ b/ja/built-in-nodes/RenderSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RenderSplat" icon: "circle" mode: wide --- -# Render Splat 異方性EWAラスタライザーを使用してガウシアンスプラットを画像としてレンダリングします。配向楕円スプラット、アンチエイリアシング、奥行きソートによる前面から背面へのレンダリングを採用しています。カメラは`camera_info`入力から取得するか、空のままにしてスプラットを自動フレーミングすることもできます。1より大きいフレーム数を設定すると、ビデオノードに供給するためのターンテーブルバッチ画像を生成します。 @@ -30,8 +29,8 @@ mode: wide | 出力名 | 説明 | データ型 | |-------------|-------------|-----------| -| `マスク` | ガウシアンスプラットのレンダリング画像 | IMAGE | -| `mask` | レンダリングされたスプラットのアルファマスク | MASK | +| `画像` | ガウシアンスプラットのレンダリング画像 | IMAGE | +| `マスク` | レンダリングされたスプラットのアルファマスク | MASK | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RenderSplat/ja.md) diff --git a/ja/built-in-nodes/RenormCFG.mdx b/ja/built-in-nodes/RenormCFG.mdx index 738c2f284..96c92da60 100644 --- a/ja/built-in-nodes/RenormCFG.mdx +++ b/ja/built-in-nodes/RenormCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RenormCFG" icon: "circle" mode: wide --- + 以下が翻訳結果です。 RenormCFGノードは、条件付きスケーリングと正規化を適用することで、拡散モデルにおける分類器フリーガイダンス（CFG）プロセスを変更します。指定されたタイムステップしきい値と再正規化係数に基づいてノイズ除去プロセスを調整し、画像生成中における条件付き予測と無条件予測の影響を制御します。 diff --git a/ja/built-in-nodes/RepeatImageBatch.mdx b/ja/built-in-nodes/RepeatImageBatch.mdx index 7c6bdbdf4..0bbdd6a3e 100644 --- a/ja/built-in-nodes/RepeatImageBatch.mdx +++ b/ja/built-in-nodes/RepeatImageBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RepeatImageBatch" icon: "circle" mode: wide --- + RepeatImageBatchノードは、指定された画像を指定回数複製し、同一画像のバッチを作成するために設計されています。この機能は、バッチ処理やデータ拡張など、同じ画像の複数インスタンスを必要とする操作に役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/RepeatLatentBatch.mdx b/ja/built-in-nodes/RepeatLatentBatch.mdx index 05599041f..f20a24ed7 100644 --- a/ja/built-in-nodes/RepeatLatentBatch.mdx +++ b/ja/built-in-nodes/RepeatLatentBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RepeatLatentBatch" icon: "circle" mode: wide --- + RepeatLatentBatchノードは、指定された潜在表現のバッチを指定回数複製するように設計されています。これには、ノイズマスクやバッチインデックスなどの追加データも含まれる可能性があります。この機能は、データ拡張や特定の生成タスクなど、同じ潜在データの複数のインスタンスを必要とする操作において重要です。 ## 入力 diff --git a/ja/built-in-nodes/ReplaceText.mdx b/ja/built-in-nodes/ReplaceText.mdx index 8ca8ab9ba..dfc4d5c7f 100644 --- a/ja/built-in-nodes/ReplaceText.mdx +++ b/ja/built-in-nodes/ReplaceText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReplaceText" icon: "circle" mode: wide --- + テキスト置換ノードは、単純なテキスト置換を実行します。入力内で指定されたテキストを検索し、そのすべての出現箇所を新しいテキストに置き換えます。この操作は、ノードに提供されたすべてのテキスト入力に適用されます。 ## 入力 @@ -19,7 +20,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `text` | `find`テキストのすべての出現箇所が`replace`テキストに置き換えられた処理済みテキスト。 | STRING | +| `texts` | `find`テキストのすべての出現箇所が`replace`テキストに置き換えられた処理済みテキスト。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReplaceText/ja.md) diff --git a/ja/built-in-nodes/ReplaceVideoLatentFrames.mdx b/ja/built-in-nodes/ReplaceVideoLatentFrames.mdx index 20e8ff891..d6f742cb5 100644 --- a/ja/built-in-nodes/ReplaceVideoLatentFrames.mdx +++ b/ja/built-in-nodes/ReplaceVideoLatentFrames.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReplaceVideoLatentFrames" icon: "circle" mode: wide --- + ReplaceVideoLatentFrames ノードは、ソースの潜在ビデオからフレームを抽出し、指定されたフレームインデックスから宛先の潜在ビデオに挿入します。ソースの潜在情報が提供されない場合は、宛先の潜在情報がそのまま返されます。このノードは負のインデックスを処理し、ソースフレームが宛先に収まらない場合は警告を発行します。 ## 入力 diff --git a/ja/built-in-nodes/Reroute.mdx b/ja/built-in-nodes/Reroute.mdx index 78ed961ae..2836b5b7f 100644 --- a/ja/built-in-nodes/Reroute.mdx +++ b/ja/built-in-nodes/Reroute.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Reroute" icon: "circle" mode: wide --- + 以下は、指定されたルールに従った日本語翻訳です。 --- diff --git a/ja/built-in-nodes/RescaleCFG.mdx b/ja/built-in-nodes/RescaleCFG.mdx index 5d6e52587..c4ba8aa7a 100644 --- a/ja/built-in-nodes/RescaleCFG.mdx +++ b/ja/built-in-nodes/RescaleCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RescaleCFG" icon: "circle" mode: wide --- + RescaleCFGノードは、指定された乗数に基づいてモデルの出力における条件付きスケールと無条件スケールを調整し、よりバランスが取れ制御された生成プロセスを実現するように設計されています。このノードは、モデルの出力をリスケーリングすることで、条件付き成分と無条件成分の影響を変更し、それによりモデルのパフォーマンスや出力品質を向上させる可能性があります。 ## 入力 diff --git a/ja/built-in-nodes/ResizeAndPadImage.mdx b/ja/built-in-nodes/ResizeAndPadImage.mdx index 5c63eec91..783dd6068 100644 --- a/ja/built-in-nodes/ResizeAndPadImage.mdx +++ b/ja/built-in-nodes/ResizeAndPadImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeAndPadImage" icon: "circle" mode: wide --- + ResizeAndPadImage ノードは、画像を指定された寸法に収まるようにリサイズし、元のアスペクト比を維持します。ターゲットの幅と高さに収まるように画像を比例的に縮小した後、残りのスペースを埋めるためにエッジにパディングを追加します。パディングの色と補間方法をカスタマイズして、パディング領域の外観とリサイズの品質を制御できます。 ## 入力 diff --git a/ja/built-in-nodes/ResizeImageMaskNode.mdx b/ja/built-in-nodes/ResizeImageMaskNode.mdx index 5820eb574..15b803cc7 100644 --- a/ja/built-in-nodes/ResizeImageMaskNode.mdx +++ b/ja/built-in-nodes/ResizeImageMaskNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImageMaskNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 画像/マスクのリサイズノードは、入力された画像やマスクの寸法を変更するための複数の方法を提供します。倍率によるスケーリング、特定の寸法の指定、別の入力に合わせたサイズ変更、またはピクセル数に基づく調整が可能で、品質に応じたさまざまな補間方法を使用できます。 diff --git a/ja/built-in-nodes/ResizeImagesByLongerEdge.mdx b/ja/built-in-nodes/ResizeImagesByLongerEdge.mdx index c967fd7da..3b1d3f9cf 100644 --- a/ja/built-in-nodes/ResizeImagesByLongerEdge.mdx +++ b/ja/built-in-nodes/ResizeImagesByLongerEdge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImagesByLongerEdge" icon: "circle" mode: wide --- + ## 概要「長辺で画像リサイズ」ノードは、1つ以上の画像の最も長い辺が指定されたターゲット長に一致するようにリサイズします。幅と高さのどちらが長いかを自動的に判定し、元のアスペクト比を維持しながら、もう一方の寸法を比例的に拡大・縮小します。これは、画像の最大寸法に基づいて画像サイズを標準化する際に便利です。 ## 入力 @@ -18,7 +19,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `image` | リサイズされた画像、または画像のバッチ。出力は入力と同じ数の画像を持ち、各画像の長辺が指定された `longer_edge` の長さに一致します。 | IMAGE | +| `images` | リサイズされた画像、または画像のバッチ。出力は入力と同じ数の画像を持ち、各画像の長辺が指定された `longer_edge` の長さに一致します。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByLongerEdge/ja.md) diff --git a/ja/built-in-nodes/ResizeImagesByShorterEdge.mdx b/ja/built-in-nodes/ResizeImagesByShorterEdge.mdx index dbeb8f4af..0b4cf7c6e 100644 --- a/ja/built-in-nodes/ResizeImagesByShorterEdge.mdx +++ b/ja/built-in-nodes/ResizeImagesByShorterEdge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImagesByShorterEdge" icon: "circle" mode: wide --- + このノードは、元のアスペクト比を維持しながら、短い方の辺が指定された長さに一致するように画像をリサイズします。短い辺のターゲット長に基づいて新しい寸法を計算し、リサイズされた画像を返します。 ## 入力 @@ -18,7 +19,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `image` | 短い辺が指定されたターゲット長に一致するようにリサイズされた画像です。 | IMAGE | +| `images` | 短い辺が指定されたターゲット長に一致するようにリサイズされた画像です。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByShorterEdge/ja.md) diff --git a/ja/built-in-nodes/ResolutionBucket.mdx b/ja/built-in-nodes/ResolutionBucket.mdx index f7db12a82..82a9a1809 100644 --- a/ja/built-in-nodes/ResolutionBucket.mdx +++ b/ja/built-in-nodes/ResolutionBucket.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResolutionBucket" icon: "circle" mode: wide --- + このノードは、潜在画像のリストとそれに対応するコンディショニングデータを解像度ごとに整理します。同じ高さと幅を持つアイテムをグループ化し、解像度ごとに個別のバッチを作成します。この処理は、効率的なトレーニング用にデータを準備する際に有用であり、モデルが同じサイズの複数のアイテムをまとめて処理できるようにします。 ## 入力 @@ -20,7 +21,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `conditioning` | 解像度バケットごとに1つずつ、バッチ処理された潜在辞書のリスト。 | LATENT | +| `latents` | 解像度バケットごとに1つずつ、バッチ処理された潜在辞書のリスト。 | LATENT | | `conditioning` | 解像度バケットごとに1つずつ、コンディションリストのリスト。 | CONDITIONING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResolutionBucket/ja.md) diff --git a/ja/built-in-nodes/ResolutionSelector.mdx b/ja/built-in-nodes/ResolutionSelector.mdx index a2e3c15c6..f00ebf3b7 100644 --- a/ja/built-in-nodes/ResolutionSelector.mdx +++ b/ja/built-in-nodes/ResolutionSelector.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResolutionSelector" icon: "circle" mode: wide --- + ### 概要 Resolution Selector ノードは、選択したアスペクト比と目標とする総メガピクセル数に基づいて、画像の幅と高さ（ピクセル単位）を計算します。このノードは、Empty Latent Image ノードなど、他のノードに一貫した寸法を生成するのに便利です。出力される寸法は、常に最も近い8の倍数に丸められます。 diff --git a/ja/built-in-nodes/ReveImageCreateNode.mdx b/ja/built-in-nodes/ReveImageCreateNode.mdx index 29e37a3f4..c4e933a49 100644 --- a/ja/built-in-nodes/ReveImageCreateNode.mdx +++ b/ja/built-in-nodes/ReveImageCreateNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReveImageCreateNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ReveImageEditNode.mdx b/ja/built-in-nodes/ReveImageEditNode.mdx index dc11920c8..a99111f4c 100644 --- a/ja/built-in-nodes/ReveImageEditNode.mdx +++ b/ja/built-in-nodes/ReveImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReveImageEditNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Reve Image Edit ノードを使用すると、テキストによる説明に基づいて既存の画像を変更できます。このノードは Reve API を利用して指示を解釈し、提供された画像に対して要求された変更を適用します。 diff --git a/ja/built-in-nodes/ReveImageRemixNode.mdx b/ja/built-in-nodes/ReveImageRemixNode.mdx index 31c981d87..16650a8bc 100644 --- a/ja/built-in-nodes/ReveImageRemixNode.mdx +++ b/ja/built-in-nodes/ReveImageRemixNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReveImageRemixNode" icon: "circle" mode: wide --- + 以下が日本語翻訳です。 Reve Image Remix ノードは、Reve API を使用して新しい画像を生成します。1つ以上の参照画像とテキストプロンプトを組み合わせ、指定された説明に基づいて新しいリミックス画像を作成します。 diff --git a/ja/built-in-nodes/Rodin3D_Detail.mdx b/ja/built-in-nodes/Rodin3D_Detail.mdx index a2fb66cd9..7ab5bc53f 100644 --- a/ja/built-in-nodes/Rodin3D_Detail.mdx +++ b/ja/built-in-nodes/Rodin3D_Detail.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Detail" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- @@ -24,7 +25,7 @@ Rodin 3D Detail ノードは、Rodin API を使用して詳細な 3D アセッ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `GLB` | 生成された 3D モデルのファイルパス（後方互換性のため） | STRING | +| `3Dモデルパス` | 生成された 3D モデルのファイルパス（後方互換性のため） | STRING | | `GLB` | GLB 形式で出力された 3D モデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Detail/ja.md) diff --git a/ja/built-in-nodes/Rodin3D_Gen2.mdx b/ja/built-in-nodes/Rodin3D_Gen2.mdx index ee38f5dff..0ab7ccb82 100644 --- a/ja/built-in-nodes/Rodin3D_Gen2.mdx +++ b/ja/built-in-nodes/Rodin3D_Gen2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Rodin3D_Gen2 ノードは、Rodin API を使用して 3D アセットを生成します。入力画像を受け取り、さまざまなマテリアルタイプとポリゴン数で 3D モデルに変換します。このノードは、タスク作成、ステータスのポーリング、ファイルのダウンロードを含む生成プロセス全体を自動的に処理します。 @@ -23,7 +24,7 @@ Rodin3D_Gen2 ノードは、Rodin API を使用して 3D アセットを生成 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `GLB` | 生成された 3D モデルへのファイルパス（後方互換性のため） | STRING | +| `3Dモデルパス` | 生成された 3D モデルへのファイルパス（後方互換性のため） | STRING | | `GLB` | GLB 形式で生成された 3D モデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen2/ja.md) diff --git a/ja/built-in-nodes/Rodin3D_Gen25_Image.mdx b/ja/built-in-nodes/Rodin3D_Gen25_Image.mdx index bd446065d..fdb2068bd 100644 --- a/ja/built-in-nodes/Rodin3D_Gen25_Image.mdx +++ b/ja/built-in-nodes/Rodin3D_Gen25_Image.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen25_Image" icon: "circle" mode: wide --- + ## 概要 このノードは、Rodin Gen-2.5 APIを使用して、1～5枚の参照画像から3Dモデルを生成します。生成速度とコストのバランスを調整するために、Fast、Regular、Extreme-Highの品質モードから選択できます。 diff --git a/ja/built-in-nodes/Rodin3D_Gen25_Text.mdx b/ja/built-in-nodes/Rodin3D_Gen25_Text.mdx index 73780a117..26a46e95d 100644 --- a/ja/built-in-nodes/Rodin3D_Gen25_Text.mdx +++ b/ja/built-in-nodes/Rodin3D_Gen25_Text.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen25_Text" icon: "circle" mode: wide --- + ## 概要 Rodin Gen-2.5 APIを使用して、テキストプロンプトから3Dモデルを生成します。生成速度と出力品質のバランスを調整するために、異なる品質モード（Fast、Regular、Extreme-High）から選択できます。 @@ -34,7 +35,7 @@ Rodin Gen-2.5 APIを使用して、テキストプロンプトから3Dモデル | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `model_file` | 指定された形式で生成された3Dモデルファイル。 | FILE3DANY | +| `モデルファイル` | 指定された形式で生成された3Dモデルファイル。 | FILE3DANY | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen25_Text/ja.md) diff --git a/ja/built-in-nodes/Rodin3D_Regular.mdx b/ja/built-in-nodes/Rodin3D_Regular.mdx index 34c0bbcb2..228e26ac8 100644 --- a/ja/built-in-nodes/Rodin3D_Regular.mdx +++ b/ja/built-in-nodes/Rodin3D_Regular.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Regular" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -24,7 +25,7 @@ Rodin 3D Regular ノードは、Rodin API を使用して 3D アセットを生 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `GLB` | 生成された 3D モデルへのファイルパスです（後方互換性のために維持されています）。 | STRING | +| `3Dモデルパス` | 生成された 3D モデルへのファイルパスです（後方互換性のために維持されています）。 | STRING | | `GLB` | GLB 形式で生成された 3D モデルです。 | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Regular/ja.md) diff --git a/ja/built-in-nodes/Rodin3D_Sketch.mdx b/ja/built-in-nodes/Rodin3D_Sketch.mdx index 8c80bbb26..489ba9830 100644 --- a/ja/built-in-nodes/Rodin3D_Sketch.mdx +++ b/ja/built-in-nodes/Rodin3D_Sketch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Sketch" icon: "circle" mode: wide --- + このノードは、Rodin APIを使用して3Dアセットを生成します。入力画像を受け取り、外部サービスを通じて3Dモデルに変換します。このノードは、タスクの作成から最終的な3Dモデルファイルのダウンロードまでのプロセス全体を処理します。 ## 入力 @@ -18,7 +19,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `GLB` | 生成された3Dモデルのファイルパス（下位互換性のため） | STRING | +| `3Dモデルパス` | 生成された3Dモデルのファイルパス（下位互換性のため） | STRING | | `GLB` | GLB形式で生成された3Dモデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Sketch/ja.md) diff --git a/ja/built-in-nodes/Rodin3D_Smooth.mdx b/ja/built-in-nodes/Rodin3D_Smooth.mdx index 0b06800d2..d146ab27e 100644 --- a/ja/built-in-nodes/Rodin3D_Smooth.mdx +++ b/ja/built-in-nodes/Rodin3D_Smooth.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Smooth" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Smooth/en.md) Rodin 3D Smoothノードは、Rodin APIを使用して入力画像を処理し、スムーズな3Dモデルに変換することで3Dアセットを生成します。複数の画像を入力として受け取り、ダウンロード可能な3Dモデルファイルを出力します。このノードは、タスク作成、ステータスのポーリング、ファイルのダウンロードを含む生成プロセス全体を自動的に処理します。 @@ -22,7 +23,7 @@ Rodin 3D Smoothノードは、Rodin APIを使用して入力画像を処理し | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `GLB` | ダウンロードされた3Dモデルのファイルパス（後方互換性のため）。 | STRING | +| `3Dモデルパス` | ダウンロードされた3Dモデルのファイルパス（後方互換性のため）。 | STRING | | `GLB` | GLB形式で生成された3Dモデル。 | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Smooth/ja.md) diff --git a/ja/built-in-nodes/RunwayAleph2KeyframeNode.mdx b/ja/built-in-nodes/RunwayAleph2KeyframeNode.mdx new file mode 100644 index 000000000..ff61e80c3 --- /dev/null +++ b/ja/built-in-nodes/RunwayAleph2KeyframeNode.mdx @@ -0,0 +1,37 @@ +--- +title: "RunwayAleph2KeyframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2KeyframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2KeyframeNode" +icon: "circle" +mode: wide +--- + +このノードは、ガイダンス画像を入力動画の特定の瞬間に固定します。これにより、Aleph2モデルはその時点で編集を誘導します。このノードをRunway Aleph2 Video to Videoノードの「keyframes」入力に接続し、オプションの「keyframes」入力を介して複数（最大5つ）をチェーン接続します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `画像` | 入力動画の選択した瞬間に適用するガイダンス画像です。 | IMAGE | はい | - | +| `タイミング` | この画像を入力動画のタイムライン上に配置する方法です。 | COMBO | はい | 下記参照 | +| `キーフレーム` | このキーフレームとチェーン接続する、オプションの先行キーフレームです。 | KEYFRAME | いいえ | - | + +### Timing パラメータのオプション + +`timing` パラメータには2つのモードがあります： + +| モード | サブパラメータ | 説明 | 範囲 | +|------|--------------|-------------|-------| +| "Absolute seconds"（絶対秒数） | `seconds` | この画像が適用される入力動画の開始からの時間（秒）（デフォルト：0.0） | 0.0 ～ 30.0、ステップ 0.1 | +| "Fraction of duration"（再生時間に対する割合） | `fraction` | この画像が適用される入力動画内の位置を、再生時間に対する割合で指定（0.0 = 開始、1.0 = 終了）（デフォルト：0.0） | 0.0 ～ 1.0、ステップ 0.01 | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `キーフレーム` | このキーフレームと、以前に接続されたキーフレームを含むキーフレームのチェーンです。 | KEYFRAME | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2KeyframeNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `b5ac6553166b7366fd35f97740861be163f91bc2353f5f83bdc2f04bf40f8478` diff --git a/ja/built-in-nodes/RunwayAleph2PromptImageNode.mdx b/ja/built-in-nodes/RunwayAleph2PromptImageNode.mdx new file mode 100644 index 000000000..84ea8f3f7 --- /dev/null +++ b/ja/built-in-nodes/RunwayAleph2PromptImageNode.mdx @@ -0,0 +1,34 @@ +--- +title: "RunwayAleph2PromptImageNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2PromptImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2PromptImageNode" +icon: "circle" +mode: wide +--- + +このノードは、ガイダンス画像を出力ビデオ内の特定の瞬間に固定し、その時点での編集済みビデオの見た目を制御します。このノードをRunway Aleph2 Video to Videoノードの`prompt_images`入力に接続し、オプションの`prompt_images`入力を使用して複数（最大5つ）をチェーン接続します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `画像` | 出力ビデオの選択した瞬間に配置するガイダンス画像です。 | IMAGE | はい | - | +| `位置` | この画像を出力ビデオのタイムライン上に配置する方法です。絶対時間（開始からの秒数）または割合時間（ビデオ長に対するパーセンテージ）から選択します。 | COMBO | はい | `Absolute (seconds)`
`Fraction (0.0 to 1.0)` | +| `プロンプト画像` | この画像とチェーン接続するオプションの先行プロンプト画像です。別のRunway Aleph2 Prompt Imageノードの出力をここに接続して、最大5つのガイダンス画像のチェーンを構築します。 | PROMPT_IMAGE_CHAIN | いいえ | - | + +**位置モードの詳細：** + +`position`が`Absolute (seconds)`に設定されている場合、`seconds`値を指定する必要があります（デフォルト：0.0、範囲：0.0～30.0、ステップ：0.1）。これは、この画像が適用される出力ビデオの開始からの正確な時間を秒単位で指定します。 + +`position`が`Fraction (0.0 to 1.0)`に設定されている場合、`fraction`値を指定する必要があります（デフォルト：0.0、範囲：0.0～1.0、ステップ：0.01）。これは、この画像が出力ビデオの合計長さに対する割合としてどこに適用されるかを指定します（0.0＝開始、1.0＝終了）。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `プロンプト画像` | Runway Aleph2 Video to Videoノードの`プロンプト画像`入力に接続できるプロンプト画像のチェーンです。 | PROMPT_IMAGE_CHAIN | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2PromptImageNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `a8b86fb5d73d27cc58aa59c195ca058eec8a5c9433ea09522ff3e905f6b88193` diff --git a/ja/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx b/ja/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx new file mode 100644 index 000000000..170480fce --- /dev/null +++ b/ja/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx @@ -0,0 +1,37 @@ +--- +title: "RunwayAleph2VideoToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2VideoToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2VideoToVideoNode" +icon: "circle" +mode: wide +--- + +このノードは、Runway の Aleph2 モデルを使用して、テキストプロンプトに基づいて動画を編集します。元の動きやタイミングを保持しながら、スタイルの変更、照明の調整、要素の追加・削除、または視点の変更によって映像を変換します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `プロンプト` | 出力に表示する内容を記述します（1～1000文字）。 | STRING | はい | 1～1000文字 | +| `ビデオ` | 編集する入力動画。2～30秒、30fps以下である必要があります。 | VIDEO | はい | 2～30秒の長さ、最大30fps | +| `シード` | 生成用のランダムシード（デフォルト：0）。 | INT | はい | 0～4294967295 | +| `著名人しきい値` | 認識可能な公人に対するコンテンツモデレーション（デフォルト："low"）。 | COMBO | はい | "auto"
"low" | +| `キーフレーム` | 入力動画に固定されたガイダンス画像。Aleph2 キーフレームノードから取得（最大5つ）。キーフレームまたはプロンプト画像のいずれかを使用し、両方は使用できません。 | KEYFRAME | いいえ | 最大5項目 | +| `プロンプト画像` | 出力動画に固定されたガイダンス画像。Aleph2 プロンプト画像ノードから取得（最大5つ）。キーフレームまたはプロンプト画像のいずれかを使用し、両方は使用できません。 | PROMPT_IMAGE | いいえ | 最大5項目 | + +**重要な制約事項：** +- 入力動画は2～30秒の長さで、フレームレートが30fps以下である必要があります。 +- ガイダンスには `keyframes` または `prompt_images` のいずれかを使用でき、両方を同時に使用することはできません。 +- 各ガイダンス入力（キーフレームまたはプロンプト画像）は、最大5項目までサポートします。 +- キーフレームのタイムスタンプとプロンプト画像のタイムスタンプは、入力動画の長さを超えてはなりません。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `ビデオ` | Aleph2 モデルによって生成された編集済み動画。 | VIDEO | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2VideoToVideoNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `bda4d0f49843c1a8f311ddbce5911a2a157cae798a26f7a183b31fe41686d0b7` diff --git a/ja/built-in-nodes/RunwayFirstLastFrameNode.mdx b/ja/built-in-nodes/RunwayFirstLastFrameNode.mdx index aa810c8ee..29fe07c5c 100644 --- a/ja/built-in-nodes/RunwayFirstLastFrameNode.mdx +++ b/ja/built-in-nodes/RunwayFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayFirstLastFrameNode" icon: "circle" mode: wide --- + ## 概要 Runway First-Last-Frame to Video ノードは、最初と最後のキーフレームとテキストプロンプトをアップロードすることで動画を生成します。Runway の Gen-3 モデルを使用して、指定された開始フレームと終了フレームの間のスムーズな遷移を作成します。これは、終了フレームが開始フレームと大きく異なる複雑なトランジションに特に有用です。 diff --git a/ja/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx b/ja/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx index a49115cc7..44878e1a3 100644 --- a/ja/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx +++ b/ja/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayImageToVideoNodeGen3a" icon: "circle" mode: wide --- + 以下、ご依頼内容に従い、ComfyUI ノードドキュメントを日本語に翻訳しました。 --- diff --git a/ja/built-in-nodes/RunwayImageToVideoNodeGen4.mdx b/ja/built-in-nodes/RunwayImageToVideoNodeGen4.mdx index a9ce1cc7b..345ae1a3b 100644 --- a/ja/built-in-nodes/RunwayImageToVideoNodeGen4.mdx +++ b/ja/built-in-nodes/RunwayImageToVideoNodeGen4.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayImageToVideoNodeGen4" icon: "circle" mode: wide --- + 以下が、指定されたルールに従った日本語翻訳です。 Runway Image to Video (Gen4 Turbo) ノードは、Runway の Gen4 Turbo モデルを使用して、単一の開始フレームから動画を生成します。テキストプロンプトと初期画像フレームを受け取り、指定された長さとアスペクト比の設定に基づいて動画シーケンスを作成します。このノードは、開始フレームを Runway の API にアップロードし、生成された動画を返します。 diff --git a/ja/built-in-nodes/RunwayTextToImageNode.mdx b/ja/built-in-nodes/RunwayTextToImageNode.mdx index 32b3d8ae5..cac88fd1a 100644 --- a/ja/built-in-nodes/RunwayTextToImageNode.mdx +++ b/ja/built-in-nodes/RunwayTextToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayTextToImageNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Runway Text to Image ノードは、Runway の Gen 4 モデルを使用して、テキストプロンプトから画像を生成します。テキストによる説明を提供し、必要に応じて参照画像を含めることで、画像生成プロセスをガイドできます。このノードは API 通信を処理し、生成された画像を返します。 diff --git a/ja/built-in-nodes/SAM3_Detect.mdx b/ja/built-in-nodes/SAM3_Detect.mdx index 6f988d23f..6abb56808 100644 --- a/ja/built-in-nodes/SAM3_Detect.mdx +++ b/ja/built-in-nodes/SAM3_Detect.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SAM3_Detect" icon: "circle" mode: wide --- -# SAM3 Detect ノード ## 概要 @@ -38,7 +37,7 @@ SAM3 Detect ノードは、テキストによる説明、バウンディング | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `bboxes` | セグメンテーションマスク。`individual_masks` が False（デフォルト）の場合、フレームごとに単一の結合マスクを返します。True の場合、検出された各オブジェクトの個別のマスクを返します | MASK | +| `masks` | セグメンテーションマスク。`individual_masks` が False（デフォルト）の場合、フレームごとに単一の結合マスクを返します。True の場合、検出された各オブジェクトの個別のマスクを返します | MASK | | `bboxes` | 座標と信頼度スコアを含む検出されたバウンディングボックス。各ボックスには `x`、`y`、`width`、`height`、`score` の値が含まれます | BOUNDING_BOX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SAM3_Detect/ja.md) diff --git a/ja/built-in-nodes/SAM3_TrackPreview.mdx b/ja/built-in-nodes/SAM3_TrackPreview.mdx index 37bdc0fe0..f3f0a94ce 100644 --- a/ja/built-in-nodes/SAM3_TrackPreview.mdx +++ b/ja/built-in-nodes/SAM3_TrackPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_TrackPreview" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご貢献ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SAM3_TrackPreview/en.md) ## 概要 diff --git a/ja/built-in-nodes/SAM3_TrackToMask.mdx b/ja/built-in-nodes/SAM3_TrackToMask.mdx index 9bf059ea9..401f846f1 100644 --- a/ja/built-in-nodes/SAM3_TrackToMask.mdx +++ b/ja/built-in-nodes/SAM3_TrackToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_TrackToMask" icon: "circle" mode: wide --- + これはComfyUIノードドキュメントの技術翻訳です。以下が日本語訳になります。 ## 概要 diff --git a/ja/built-in-nodes/SAM3_VideoTrack.mdx b/ja/built-in-nodes/SAM3_VideoTrack.mdx index 60cafcb54..919580093 100644 --- a/ja/built-in-nodes/SAM3_VideoTrack.mdx +++ b/ja/built-in-nodes/SAM3_VideoTrack.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_VideoTrack" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/SCAIL2ColoredMask.mdx b/ja/built-in-nodes/SCAIL2ColoredMask.mdx new file mode 100644 index 000000000..ba0a9e192 --- /dev/null +++ b/ja/built-in-nodes/SCAIL2ColoredMask.mdx @@ -0,0 +1,31 @@ +--- +title: "SCAIL2ColoredMask - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the SCAIL2ColoredMask node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "SCAIL2ColoredMask" +icon: "circle" +mode: wide +--- + +このノードは、SAM3のトラッキングデータを、WanSCAILToVideoノードで使用されるカラーマスクに変換します。ドライビングポーズ動画とオプションで参照画像からのトラッキングデータを処理し、両方の出力で各追跡人物に一貫した色を割り当てます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `ドライビングトラックデータ` | ドライビングポーズ動画のSAM3トラックです。pose_video_mask出力にレンダリングされます。 | SAM3_TRACK_DATA | はい | - | +| `リファレンストラックデータ` | 参照画像のSAM3トラックです。 | SAM3_TRACK_DATA | いいえ | - | +| `オブジェクトインデックス` | 含める人物インデックスのカンマ区切りリスト（例：'0,2,3'）。参照画像とポーズ動画の両方のマスクに適用されます。空の場合はすべての人物が対象となります。 | STRING | はい | - | +| `並び順` | パレット色を追跡オブジェクトに割り当てる順序です（参照画像とポーズ動画の両方に適用され、各人物が同じ色を維持します）。left_to_right = 左端のオブジェクト（最初のフレームの重心による）が最初の色を取得します。area = 最も大きいオブジェクト（最初のフレームのマスク面積による）が最初の色を取得します。none = SAM3の順序を維持します。（デフォルト："left_to_right"） | COMBO | はい | `"none"`
`"left_to_right"`
`"area"` | +| `置換モード` | False = アニメーションモード（pose_video_maskは黒背景、reference_image_maskは白背景）。True = 置換モード（pose_video_maskは白背景、reference_image_maskは黒背景）。（デフォルト：False） | BOOLEAN | はい | False
True | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `pose_video_mask` | ドライビングポーズ動画のトラッキングデータからレンダリングされたカラーマスクです。背景色はreplacement_modeの設定に従います。 | IMAGE | +| `reference_image_mask` | 参照画像のトラッキングデータからレンダリングされたカラーマスクです。モデルの仕様により、常に黒背景でレンダリングされます。 | IMAGE | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SCAIL2ColoredMask/ja.md) + +--- +**Source fingerprint (SHA-256):** `c9f6d87410b8bd4082ffb06ef1cf973829566ed222be643db3528cbc241d3c14` diff --git a/ja/built-in-nodes/SDPoseDrawKeypoints.mdx b/ja/built-in-nodes/SDPoseDrawKeypoints.mdx index 71fd919c8..11b007053 100644 --- a/ja/built-in-nodes/SDPoseDrawKeypoints.mdx +++ b/ja/built-in-nodes/SDPoseDrawKeypoints.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDPoseDrawKeypoints" icon: "circle" mode: wide --- + SDPoseDrawKeypoints ノードは、姿勢推定データ（キーポイント）を受け取り、空白のキャンバス上に視覚的なスケルトンとして描画します。身体、手、顔、足など、姿勢の異なる部位を選択的に描画でき、線の太さや点のサイズもカスタマイズ可能です。生成された画像は可視化用途や、姿勢画像を必要とする他のノードへの入力として使用できます。 ## 入力 diff --git a/ja/built-in-nodes/SDPoseFaceBBoxes.mdx b/ja/built-in-nodes/SDPoseFaceBBoxes.mdx index 1d38e9f35..c162cfe60 100644 --- a/ja/built-in-nodes/SDPoseFaceBBoxes.mdx +++ b/ja/built-in-nodes/SDPoseFaceBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDPoseFaceBBoxes" icon: "circle" mode: wide --- + 以下が翻訳です。 SDPoseFaceBBoxesノードは、ポーズのキーポイントデータを処理して、人間の顔の周囲にバウンディングボックスを検出および生成します。フレーム内の各人物について2D顔キーポイントを分析し、それらのポイントに基づいてバウンディングボックスを計算し、ボックスのサイズや形状を調整することができます。生成されたバウンディングボックスは、SDPoseKeypointExtractorなどのSDPoseワークフロー内の他のノードと互換性のある形式になっています。 @@ -23,7 +24,7 @@ SDPoseFaceBBoxesノードは、ポーズのキーポイントデータを処理 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `bboxes` | 各フレームの顔バウンディングボックスのリストです。各バウンディングボックスは、左上隅の座標（`x`、`y`）、`width`、および`height`によって定義されます。この出力は、SDPoseKeypointExtractorノードの`bboxes`入力と互換性があります。 | BOUNDINGBOX | +| `バウンディングボックス` | 各フレームの顔バウンディングボックスのリストです。各バウンディングボックスは、左上隅の座標（`x`、`y`）、`width`、および`height`によって定義されます。この出力は、SDPoseKeypointExtractorノードの`bboxes`入力と互換性があります。 | BOUNDINGBOX | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SDPoseFaceBBoxes/ja.md) diff --git a/ja/built-in-nodes/SDPoseKeypointExtractor.mdx b/ja/built-in-nodes/SDPoseKeypointExtractor.mdx index ecc4f9c5f..55ab7d42d 100644 --- a/ja/built-in-nodes/SDPoseKeypointExtractor.mdx +++ b/ja/built-in-nodes/SDPoseKeypointExtractor.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDPoseKeypointExtractor" icon: "circle" mode: wide --- + 以下が翻訳結果です。 SDPoseKeypointExtractor ノードは、SDPose モデルを使用して入力画像から人体のポーズキーポイントを検出します。このノードは、画像全体またはバウンディングボックスで定義された特定の領域を処理でき、検出されたキーポイントを OpenPose 形式で出力します。この形式には、各人物の座標と各キーポイントの信頼度スコアが含まれます。 @@ -29,7 +30,7 @@ SDPoseKeypointExtractor ノードは、SDPose モデルを使用して入力画 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `keypoints` | OpenPose フレーム形式（canvas_width、canvas_height、people）のキーポイントです。出力には検出された人物が含まれ、各人物にはキーポイント座標（x、y）の配列と、対応する信頼度スコアが含まれます。 | POSE_KEYPOINT | +| `キーポイント` | OpenPose フレーム形式（canvas_width、canvas_height、people）のキーポイントです。出力には検出された人物が含まれ、各人物にはキーポイント座標（x、y）の配列と、対応する信頼度スコアが含まれます。 | POSE_KEYPOINT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SDPoseKeypointExtractor/ja.md) diff --git a/ja/built-in-nodes/SDTurboScheduler.mdx b/ja/built-in-nodes/SDTurboScheduler.mdx index 16450f144..4788879b0 100644 --- a/ja/built-in-nodes/SDTurboScheduler.mdx +++ b/ja/built-in-nodes/SDTurboScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDTurboScheduler" icon: "circle" mode: wide --- + SDTurboSchedulerは、画像サンプリング用のシグマ値のシーケンスを生成するために設計されており、指定されたノイズ除去レベルとステップ数に基づいてシーケンスを調整します。このスケジューラーは、特定のモデルのサンプリング機能を活用してこれらのシグマ値を生成します。これらの値は、画像生成中のノイズ除去プロセスを制御する上で重要です。 ## 入力 diff --git a/ja/built-in-nodes/SD_4XUpscale_Conditioning.mdx b/ja/built-in-nodes/SD_4XUpscale_Conditioning.mdx index c2d174d8f..9b15d72ae 100644 --- a/ja/built-in-nodes/SD_4XUpscale_Conditioning.mdx +++ b/ja/built-in-nodes/SD_4XUpscale_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SD_4XUpscale_Conditioning" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください。 SD_4XUpscale_Conditioningノードは、拡散モデルを使用して画像をアップスケールするための条件付けデータを準備します。入力画像と条件付けデータを受け取り、スケーリングとノイズ拡張を適用して、アップスケールプロセスを導く修正済み条件付けを作成します。このノードは、アップスケールされた次元に対応する潜在表現とともに、ポジティブ条件付けとネガティブ条件付けの両方を出力します。 @@ -23,9 +24,9 @@ SD_4XUpscale_Conditioningノードは、拡散モデルを使用して画像を | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | アップスケール情報が適用された修正済みポジティブ条件付け | CONDITIONING | -| `潜在` | アップスケール情報が適用された修正済みネガティブ条件付け | CONDITIONING | -| `latent` | アップスケールされた次元に一致する空の潜在表現 | LATENT | +| `ポジティブ` | アップスケール情報が適用された修正済みポジティブ条件付け | CONDITIONING | +| `ネガティブ` | アップスケール情報が適用された修正済みネガティブ条件付け | CONDITIONING | +| `潜在` | アップスケールされた次元に一致する空の潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SD_4XUpscale_Conditioning/ja.md) diff --git a/ja/built-in-nodes/SUPIRApply.mdx b/ja/built-in-nodes/SUPIRApply.mdx index 0ac73d005..e5ee28193 100644 --- a/ja/built-in-nodes/SUPIRApply.mdx +++ b/ja/built-in-nodes/SUPIRApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SUPIRApply" icon: "circle" mode: wide --- + SUPIRApplyノードは、SUPIRモデルパッチを拡散モデルに適用します。このパッチを使用してモデルの動作を変更し、サンプリングプロセス中に入力画像からのガイダンスを組み込むことを可能にします。また、このガイダンスの強度を時間経過に応じて調整するための制御機能と、元の入力への忠実度を維持するためのオプション機能も提供します。 ## 入力 diff --git a/ja/built-in-nodes/SV3D_Conditioning.mdx b/ja/built-in-nodes/SV3D_Conditioning.mdx index 21672db1e..d9bbb4c99 100644 --- a/ja/built-in-nodes/SV3D_Conditioning.mdx +++ b/ja/built-in-nodes/SV3D_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SV3D_Conditioning" icon: "circle" mode: wide --- + SV3D_Conditioning ノードは、SV3Dモデルを使用した3D動画生成のための条件付けデータを準備します。初期画像を受け取り、CLIPビジョンエンコーダーとVAEエンコーダーで処理することで、ポジティブおよびネガティブな条件付けデータと、潜在表現を生成します。このノードは、指定された動画フレーム数に基づいて、マルチフレーム動画生成のためのカメラ仰角と方位角のシーケンスを生成します。 ## 入力 @@ -23,9 +24,9 @@ SV3D_Conditioning ノードは、SV3Dモデルを使用した3D動画生成の | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 画像埋め込みとカメラパラメータを含む、生成用のポジティブ条件付けデータ | CONDITIONING | -| `潜在` | 対照的な生成のための、ゼロ埋め込みを含むネガティブ条件付けデータ | CONDITIONING | -| `latent` | 指定された動画フレーム数と解像度に一致する次元を持つ、空の潜在テンソル | LATENT | +| `ポジティブ` | 画像埋め込みとカメラパラメータを含む、生成用のポジティブ条件付けデータ | CONDITIONING | +| `ネガティブ` | 対照的な生成のための、ゼロ埋め込みを含むネガティブ条件付けデータ | CONDITIONING | +| `潜在` | 指定された動画フレーム数と解像度に一致する次元を持つ、空の潜在テンソル | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SV3D_Conditioning/ja.md) diff --git a/ja/built-in-nodes/SVD_img2vid_Conditioning.mdx b/ja/built-in-nodes/SVD_img2vid_Conditioning.mdx index a636c7a66..ba314fe33 100644 --- a/ja/built-in-nodes/SVD_img2vid_Conditioning.mdx +++ b/ja/built-in-nodes/SVD_img2vid_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SVD_img2vid_Conditioning" icon: "circle" mode: wide --- + SVD_img2vid_Conditioning ノードは、Stable Video Diffusion を使用した動画生成のための条件付けデータを準備します。初期画像を受け取り、CLIP vision エンコーダーと VAE エンコーダーを通して処理し、ポジティブおよびネガティブな条件付けペアと、動画生成用の空の潜在空間を作成します。このノードは、生成される動画における動き、フレームレート、および拡張レベルの制御に必要なパラメーターを設定します。 ## 入力 @@ -25,9 +26,9 @@ SVD_img2vid_Conditioning ノードは、Stable Video Diffusion を使用した | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 画像埋め込みと動画パラメーターを含むポジティブ条件付けデータ | CONDITIONING | -| `潜在` | ゼロ埋めされた埋め込みと動画パラメーターを含むネガティブ条件付けデータ | CONDITIONING | -| `latent` | 動画生成の準備が整った空の潜在空間テンソル | LATENT | +| `ポジティブ` | 画像埋め込みと動画パラメーターを含むポジティブ条件付けデータ | CONDITIONING | +| `ネガティブ` | ゼロ埋めされた埋め込みと動画パラメーターを含むネガティブ条件付けデータ | CONDITIONING | +| `潜在` | 動画生成の準備が整った空の潜在空間テンソル | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SVD_img2vid_Conditioning/ja.md) diff --git a/ja/built-in-nodes/SamplerARVideo.mdx b/ja/built-in-nodes/SamplerARVideo.mdx index 6269c0f14..bca823749 100644 --- a/ja/built-in-nodes/SamplerARVideo.mdx +++ b/ja/built-in-nodes/SamplerARVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerARVideo" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Sampler AR Video ノードは、Causal Forcing や Self-Forcing 技術を使用する自己回帰ビデオモデル向けの特殊なサンプリング手法を提供します。ワークフロー内で自己回帰（AR）ループに関連するすべてのパラメータを直接管理し、モデルがビデオフレームを1ステップずつ生成する方法を簡単に設定できます。 diff --git a/ja/built-in-nodes/SamplerCustom.mdx b/ja/built-in-nodes/SamplerCustom.mdx index 2708b14ea..538cb2e91 100644 --- a/ja/built-in-nodes/SamplerCustom.mdx +++ b/ja/built-in-nodes/SamplerCustom.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerCustom" icon: "circle" mode: wide --- + SamplerCustomノードは、様々なアプリケーションに対して柔軟かつカスタマイズ可能なサンプリングメカニズムを提供するために設計されています。これにより、ユーザーは特定のニーズに合わせて異なるサンプリング戦略を選択および設定でき、サンプリングプロセスの適応性と効率性が向上します。 ## 入力 @@ -25,7 +26,7 @@ SamplerCustomノードは、様々なアプリケーションに対して柔軟 | パラメータ | 説明 | データ型 | | --- | --- | --- | -| `ノイズ除去出力` | 「output」はサンプリングプロセスの主要な結果を表し、生成されたサンプルを含みます。 | `LATENT` | -| `denoised_output` | 「denoised_output」は、ノイズ除去処理が適用された後のサンプルを表します。生成されたサンプルの明瞭さと品質を向上させる可能性があります。 | `LATENT` | +| `出力` | 「output」はサンプリングプロセスの主要な結果を表し、生成されたサンプルを含みます。 | `LATENT` | +| `ノイズ除去出力` | 「denoised_output」は、ノイズ除去処理が適用された後のサンプルを表します。生成されたサンプルの明瞭さと品質を向上させる可能性があります。 | `LATENT` | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerCustom/ja.md) diff --git a/ja/built-in-nodes/SamplerCustomAdvanced.mdx b/ja/built-in-nodes/SamplerCustomAdvanced.mdx index 5965b6afb..446a96617 100644 --- a/ja/built-in-nodes/SamplerCustomAdvanced.mdx +++ b/ja/built-in-nodes/SamplerCustomAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerCustomAdvanced" icon: "circle" mode: wide --- + SamplerCustomAdvanced ノードは、カスタムノイズ、ガイダンス、およびサンプリング設定を使用して、高度な潜在空間サンプリングを実行します。カスタマイズ可能なノイズ生成とシグマスケジュールを用いたガイド付きサンプリングプロセスを通じて潜在画像を処理し、最終的なサンプリング出力と、利用可能な場合にはノイズ除去されたバージョンの両方を生成します。 ## 入力 @@ -21,8 +22,8 @@ SamplerCustomAdvanced ノードは、カスタムノイズ、ガイダンス、 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ノイズ除去出力` | サンプリングプロセス完了後の最終的なサンプリング済み潜在表現 | LATENT | -| `denoised_output` | 利用可能な場合の出力のノイズ除去バージョン。それ以外の場合は出力と同じものを返します | LATENT | +| `出力` | サンプリングプロセス完了後の最終的なサンプリング済み潜在表現 | LATENT | +| `ノイズ除去出力` | 利用可能な場合の出力のノイズ除去バージョン。それ以外の場合は出力と同じものを返します | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerCustomAdvanced/ja.md) diff --git a/ja/built-in-nodes/SamplerDPMAdaptative.mdx b/ja/built-in-nodes/SamplerDPMAdaptative.mdx index 9be741400..eacd61199 100644 --- a/ja/built-in-nodes/SamplerDPMAdaptative.mdx +++ b/ja/built-in-nodes/SamplerDPMAdaptative.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMAdaptative" icon: "circle" mode: wide --- + SamplerDPMAdaptative ノードは、サンプリングプロセス中にステップサイズを自動的に調整する適応型DPM（拡散確率モデル）サンプラーを実装します。許容誤差ベースの誤差制御を使用して最適なステップサイズを決定し、計算効率とサンプリング精度のバランスを取ります。この適応的アプローチは、必要なステップ数を削減しながら品質を維持するのに役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/SamplerDPMPP_2M_SDE.mdx b/ja/built-in-nodes/SamplerDPMPP_2M_SDE.mdx index b92568f5f..a699e1e2d 100644 --- a/ja/built-in-nodes/SamplerDPMPP_2M_SDE.mdx +++ b/ja/built-in-nodes/SamplerDPMPP_2M_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_2M_SDE" icon: "circle" mode: wide --- + SamplerDPMPP_2M_SDE ノードは、拡散モデル用の DPM++ 2M SDE サンプラーを作成します。このサンプラーは、確率微分方程式を伴う2次微分方程式ソルバーを使用してサンプルを生成します。サンプリングプロセスを制御するために、異なるソルバータイプとノイズ処理オプションを提供します。 ## 入力 diff --git a/ja/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx b/ja/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx index de09cf646..cbdb6af26 100644 --- a/ja/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx +++ b/ja/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_2S_Ancestral" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/SamplerDPMPP_3M_SDE.mdx b/ja/built-in-nodes/SamplerDPMPP_3M_SDE.mdx index aca064023..4aa412fb0 100644 --- a/ja/built-in-nodes/SamplerDPMPP_3M_SDE.mdx +++ b/ja/built-in-nodes/SamplerDPMPP_3M_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_3M_SDE" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/SamplerDPMPP_SDE.mdx b/ja/built-in-nodes/SamplerDPMPP_SDE.mdx index 58e1500ca..a95cf4477 100644 --- a/ja/built-in-nodes/SamplerDPMPP_SDE.mdx +++ b/ja/built-in-nodes/SamplerDPMPP_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_SDE" icon: "circle" mode: wide --- + SamplerDPMPP_SDE ノードは、サンプリングプロセスで使用するDPM++ SDE（確率的微分方程式）サンプラーを作成します。このサンプラーは、設定可能なノイズパラメータとデバイス選択を備えた確率的サンプリング手法を提供します。サンプリングパイプラインで使用可能なサンプラーオブジェクトを返します。 ## 入力 diff --git a/ja/built-in-nodes/SamplerDpmpp2mSde.mdx b/ja/built-in-nodes/SamplerDpmpp2mSde.mdx index 4133d68c0..f0519a537 100644 --- a/ja/built-in-nodes/SamplerDpmpp2mSde.mdx +++ b/ja/built-in-nodes/SamplerDpmpp2mSde.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDpmpp2mSde" icon: "circle" mode: wide --- + このノードは、DPMPP_2M_SDEモデル用のサンプラーを生成するために設計されており、指定されたソルバータイプ、ノイズレベル、および計算デバイスの設定に基づいてサンプルを作成できます。サンプラーの設定の複雑さを抽象化し、カスタマイズされた設定でサンプルを生成するための合理化されたインターフェースを提供します。 ## 入力 diff --git a/ja/built-in-nodes/SamplerDpmppSde.mdx b/ja/built-in-nodes/SamplerDpmppSde.mdx index c5cd1a190..eba896dd9 100644 --- a/ja/built-in-nodes/SamplerDpmppSde.mdx +++ b/ja/built-in-nodes/SamplerDpmppSde.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDpmppSde" icon: "circle" mode: wide --- + このノードは、DPM++ SDE（確率微分方程式）モデル用のサンプラーを生成するために設計されています。CPUとGPUの両方の実行環境に対応し、利用可能なハードウェアに基づいてサンプラーの実装を最適化します。 ## 入力 diff --git a/ja/built-in-nodes/SamplerER_SDE.mdx b/ja/built-in-nodes/SamplerER_SDE.mdx index 272e7f713..976a05992 100644 --- a/ja/built-in-nodes/SamplerER_SDE.mdx +++ b/ja/built-in-nodes/SamplerER_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerER_SDE" icon: "circle" mode: wide --- + ## 概要 SamplerER_SDE ノードは、拡散モデル向けの特殊なサンプリング手法を提供し、ER-SDE、Reverse-time SDE、ODE といった異なるソルバータイプを備えています。サンプリングプロセスにおける確率的挙動と計算段階を制御できます。このノードは、選択されたソルバータイプに基づいてパラメータを自動調整し、適切な機能を保証します。 diff --git a/ja/built-in-nodes/SamplerEulerAncestral.mdx b/ja/built-in-nodes/SamplerEulerAncestral.mdx index c7197e220..1088d994b 100644 --- a/ja/built-in-nodes/SamplerEulerAncestral.mdx +++ b/ja/built-in-nodes/SamplerEulerAncestral.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerAncestral" icon: "circle" mode: wide --- + SamplerEulerAncestral ノードは、画像生成のためのEuler Ancestralサンプラーを作成します。このサンプラーは、オイラー積分と祖先サンプリング手法を組み合わせた特定の数学的アプローチを使用して、画像のバリエーションを生成します。このノードでは、生成プロセス中のランダム性とステップサイズを制御するパラメータを調整することで、サンプリング動作を設定できます。 ## 入力 diff --git a/ja/built-in-nodes/SamplerEulerAncestralCFGPP.mdx b/ja/built-in-nodes/SamplerEulerAncestralCFGPP.mdx index d5d30c1c8..3076d4852 100644 --- a/ja/built-in-nodes/SamplerEulerAncestralCFGPP.mdx +++ b/ja/built-in-nodes/SamplerEulerAncestralCFGPP.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerAncestralCFGPP" icon: "circle" mode: wide --- + SamplerEulerAncestralCFGPP ノードは、画像生成のために分類器フリーガイダンス（CFG++）を組み合わせたオイラー祖先法を使用するサンプラーを作成します。このサンプラーは、祖先サンプリング技術とガイダンス条件付けを組み合わせることで、多様な画像バリエーションを生成しつつ一貫性を維持し、ノイズとステップサイズの調整を制御するパラメータを通じて微調整を可能にします。 ## 入力 diff --git a/ja/built-in-nodes/SamplerEulerCFGpp.mdx b/ja/built-in-nodes/SamplerEulerCFGpp.mdx index b22fe51f4..1a550071a 100644 --- a/ja/built-in-nodes/SamplerEulerCFGpp.mdx +++ b/ja/built-in-nodes/SamplerEulerCFGpp.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerCFGpp" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/SamplerLCM.mdx b/ja/built-in-nodes/SamplerLCM.mdx index 0254aa74f..cc6b95e0f 100644 --- a/ja/built-in-nodes/SamplerLCM.mdx +++ b/ja/built-in-nodes/SamplerLCM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLCM" icon: "circle" mode: wide --- + SamplerLCMノードは、調整可能なステップごとのノイズパラメータを備えたLCM（潜在整合性モデル）サンプラーを提供します。各サンプリングステップで適用されるノイズを制御できるため、サンプリングプロセスを細かく調整することが可能です。 ## 入力 diff --git a/ja/built-in-nodes/SamplerLCMUpscale.mdx b/ja/built-in-nodes/SamplerLCMUpscale.mdx index 022700bc2..e14b3caa7 100644 --- a/ja/built-in-nodes/SamplerLCMUpscale.mdx +++ b/ja/built-in-nodes/SamplerLCMUpscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLCMUpscale" icon: "circle" mode: wide --- + SamplerLCMUpscale ノードは、潜在整合性モデル（LCM）サンプリングと画像アップスケーリング機能を組み合わせた、特殊なサンプリング手法を提供します。このノードを使用すると、サンプリング処理中に様々な補間方式を用いて画像をアップスケールでき、画質を維持しながら高解像度の出力を生成するのに役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/SamplerLMS.mdx b/ja/built-in-nodes/SamplerLMS.mdx index 92ff5c279..c33dd7893 100644 --- a/ja/built-in-nodes/SamplerLMS.mdx +++ b/ja/built-in-nodes/SamplerLMS.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLMS" icon: "circle" mode: wide --- + SamplerLMSノードは、拡散モデルで使用するための最小二乗平均（LMS）サンプラーを作成します。このノードは、サンプリングプロセスで使用可能なサンプラーオブジェクトを生成し、数値的な安定性と精度を確保するためにLMSアルゴリズムの次数を制御できます。 ## 入力 diff --git a/ja/built-in-nodes/SamplerSASolver.mdx b/ja/built-in-nodes/SamplerSASolver.mdx index 7290678ee..5af8099d4 100644 --- a/ja/built-in-nodes/SamplerSASolver.mdx +++ b/ja/built-in-nodes/SamplerSASolver.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerSASolver" icon: "circle" mode: wide --- + 以下が翻訳結果です。 **SamplerSASolver** ノードは、拡散モデル向けのカスタムサンプリングアルゴリズムを実装します。予測子・修正子アプローチと、設定可能な次数設定および確率微分方程式（SDE）パラメータを使用して、入力モデルからサンプルを生成します。 diff --git a/ja/built-in-nodes/SamplerSEEDS2.mdx b/ja/built-in-nodes/SamplerSEEDS2.mdx index 9019d41c5..beaafae11 100644 --- a/ja/built-in-nodes/SamplerSEEDS2.mdx +++ b/ja/built-in-nodes/SamplerSEEDS2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerSEEDS2" icon: "circle" mode: wide --- + このノードは、画像生成のための設定可能なサンプラーを提供します。確率的微分方程式（SDE）ソルバーであるSEEDS-2アルゴリズムを実装しています。パラメータを調整することで、`seeds_2`、`exp_heun_2_x0`、`exp_heun_2_x0_sde`などの特定のサンプラーと同様の動作に設定できます。 ## 入力 diff --git a/ja/built-in-nodes/SamplingPercentToSigma.mdx b/ja/built-in-nodes/SamplingPercentToSigma.mdx index f3c2c65db..c3d7a589e 100644 --- a/ja/built-in-nodes/SamplingPercentToSigma.mdx +++ b/ja/built-in-nodes/SamplingPercentToSigma.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplingPercentToSigma" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -22,7 +23,7 @@ SamplingPercentToSigma ノードは、モデルのサンプリングパラメー | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `sigma_value` | 入力されたサンプリングパーセンテージに対応する変換後のシグマ値 | FLOAT | +| `シグマ値` | 入力されたサンプリングパーセンテージに対応する変換後のシグマ値 | FLOAT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplingPercentToSigma/ja.md) diff --git a/ja/built-in-nodes/SaveAnimatedPNG.mdx b/ja/built-in-nodes/SaveAnimatedPNG.mdx index 6e7a0cd8c..414afd9d1 100644 --- a/ja/built-in-nodes/SaveAnimatedPNG.mdx +++ b/ja/built-in-nodes/SaveAnimatedPNG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAnimatedPNG" icon: "circle" mode: wide --- + SaveAnimatedPNGノードは、フレームシーケンスからアニメーションPNG画像を作成および保存するために設計されています。個々の画像フレームをまとめて一貫性のあるアニメーションに組み立て、フレームの表示時間、ループ設定、メタデータの包含をカスタマイズできます。 ## 入力 @@ -20,6 +21,6 @@ SaveAnimatedPNGノードは、フレームシーケンスからアニメーシ | フィールド | 説明 | データ型 | | --- | --- | --- | -| `ui` | 生成されたアニメーションPNG画像を表示し、アニメーションが単一フレームか複数フレームかを示すUIコンポーネントを提供します。 | N/A | +| `images` | 生成されたアニメーションPNG画像を表示し、アニメーションが単一フレームか複数フレームかを示すUIコンポーネントを提供します。 | N/A | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAnimatedPNG/ja.md) diff --git a/ja/built-in-nodes/SaveAnimatedWEBP.mdx b/ja/built-in-nodes/SaveAnimatedWEBP.mdx index a96a49eef..09f20139e 100644 --- a/ja/built-in-nodes/SaveAnimatedWEBP.mdx +++ b/ja/built-in-nodes/SaveAnimatedWEBP.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAnimatedWEBP" icon: "circle" mode: wide --- + このノードは、一連の画像をアニメーションWEBPファイルとして保存するために設計されています。個々のフレームを統合して一貫性のあるアニメーションにまとめ、指定されたメタデータを適用し、品質と圧縮設定に基づいて出力を最適化します。 ## 入力 @@ -22,6 +23,6 @@ mode: wide | フィールド | 説明 | データ型 | | --- | --- | --- | -| `ui` | 保存されたアニメーションWEBP画像とそのメタデータを表示するUIコンポーネントを提供し、アニメーションが有効かどうかを示します。 | N/A | +| `images` | 保存されたアニメーションWEBP画像とそのメタデータを表示するUIコンポーネントを提供し、アニメーションが有効かどうかを示します。 | N/A | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAnimatedWEBP/ja.md) diff --git a/ja/built-in-nodes/SaveAudio.mdx b/ja/built-in-nodes/SaveAudio.mdx index 490c5457c..f7bfbb388 100644 --- a/ja/built-in-nodes/SaveAudio.mdx +++ b/ja/built-in-nodes/SaveAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/SaveAudioAdvanced.mdx b/ja/built-in-nodes/SaveAudioAdvanced.mdx index 23d79faf8..fded1914c 100644 --- a/ja/built-in-nodes/SaveAudioAdvanced.mdx +++ b/ja/built-in-nodes/SaveAudioAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveAudioAdvanced" icon: "circle" mode: wide --- -# Save Audio (Advanced)（音声保存（詳細）） 入力された音声をComfyUIの出力ディレクトリに保存します。このノードを使用すると、FLAC、MP3、Opusなど様々な形式で、品質設定を構成可能な状態で音声をエクスポートできます。 @@ -25,7 +24,7 @@ mode: wide | 出力名 | 説明 | データ型 | |-------------|-------------|-----------| -| `ui` | 保存された音声ファイル情報を含むUI出力です。 | UI | +| `audio` | 保存された音声ファイル情報を含むUI出力です。 | UI | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioAdvanced/ja.md) diff --git a/ja/built-in-nodes/SaveAudioMP3.mdx b/ja/built-in-nodes/SaveAudioMP3.mdx index fbcac127b..053b9f64b 100644 --- a/ja/built-in-nodes/SaveAudioMP3.mdx +++ b/ja/built-in-nodes/SaveAudioMP3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAudioMP3" icon: "circle" mode: wide --- + SaveAudioMP3 ノードは、オーディオデータを MP3 ファイルとして保存します。このノードはオーディオ入力を受け取り、カスタマイズ可能なファイル名と品質設定を使用して、指定された出力ディレクトリにエクスポートします。ノードは自動的にファイル名の処理とフォーマット変換を行い、再生可能な MP3 ファイルを作成します。 ## 入力 diff --git a/ja/built-in-nodes/SaveAudioOpus.mdx b/ja/built-in-nodes/SaveAudioOpus.mdx index 8a2db0a24..0da6d62eb 100644 --- a/ja/built-in-nodes/SaveAudioOpus.mdx +++ b/ja/built-in-nodes/SaveAudioOpus.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAudioOpus" icon: "circle" mode: wide --- + 以下が翻訳結果です。 SaveAudioOpus ノードは、オーディオデータを Opus 形式のファイルに保存します。オーディオ入力を受け取り、設定可能な品質設定で圧縮された Opus ファイルとして出力します。このノードはファイル名を自動的に処理し、指定された出力ディレクトリに出力を保存します。 diff --git a/ja/built-in-nodes/SaveGLB.mdx b/ja/built-in-nodes/SaveGLB.mdx index 4b5243844..e9a3ec49f 100644 --- a/ja/built-in-nodes/SaveGLB.mdx +++ b/ja/built-in-nodes/SaveGLB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveGLB" icon: "circle" mode: wide --- + SaveGLBノードは、3Dメッシュデータまたは3Dファイルを出力ディレクトリに保存します。メッシュデータやさまざまな3Dファイル形式（GLB、GLTF、OBJ、FBX、STL、USDZ）を受け入れ、指定されたファイル名プレフィックスでエクスポートします。メッシュデータを保存する際には、複数のメッシュを処理でき、メタデータが有効な場合にはファイルにワークフローメタデータが自動的に追加されます。 ## 入力 diff --git a/ja/built-in-nodes/SaveImage.mdx b/ja/built-in-nodes/SaveImage.mdx index bc72520fd..74a245d7f 100644 --- a/ja/built-in-nodes/SaveImage.mdx +++ b/ja/built-in-nodes/SaveImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImage" icon: "circle" mode: wide --- + SaveImageノードは、受け取った画像を`ComfyUI/output`ディレクトリに保存します。各画像はPNGファイルとして保存され、プロンプトなどのワークフローメタデータを保存ファイルに埋め込むことで、後で参照できるようにします。 ## 入力 @@ -18,7 +19,7 @@ SaveImageノードは、受け取った画像を`ComfyUI/output`ディレクト | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ui` | このノードは、保存された画像のリスト（ファイル名とサブフォルダを含む）を含むUI結果を出力します。他のノードに接続するためのデータは出力しません。 | UI_RESULT | +| `images` | このノードは、保存された画像のリスト（ファイル名とサブフォルダを含む）を含むUI結果を出力します。他のノードに接続するためのデータは出力しません。 | UI_RESULT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImage/ja.md) diff --git a/ja/built-in-nodes/SaveImageAdvanced.mdx b/ja/built-in-nodes/SaveImageAdvanced.mdx index 5986938fe..1813711fc 100644 --- a/ja/built-in-nodes/SaveImageAdvanced.mdx +++ b/ja/built-in-nodes/SaveImageAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveImageAdvanced" icon: "circle" mode: wide --- -# SaveImageAdvanced **SaveImageAdvanced**ノードは、ファイル形式、ビット深度、色空間を高度に制御しながら、画像をComfyUIの出力ディレクトリに保存します。PNGまたはEXRファイルとしての保存に対応しており、ワークフローのメタデータを保存ファイルに埋め込むことができます。 @@ -32,7 +31,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `画像` | 保存された画像結果のリストです。各結果にはファイル名、サブフォルダ、タイプ（"output"）が含まれます。この出力はUI表示用に使用されます。 | IMAGE | +| `images` | 保存された画像結果のリストです。各結果にはファイル名、サブフォルダ、タイプ（"output"）が含まれます。この出力はUI表示用に使用されます。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageAdvanced/ja.md) diff --git a/ja/built-in-nodes/SaveImageDataSetToFolder.mdx b/ja/built-in-nodes/SaveImageDataSetToFolder.mdx index df71ee7b6..4dfd55597 100644 --- a/ja/built-in-nodes/SaveImageDataSetToFolder.mdx +++ b/ja/built-in-nodes/SaveImageDataSetToFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImageDataSetToFolder" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageDataSetToFolder/en.md) このノードは、画像のリストをComfyUIの出力ディレクトリ内の指定フォルダに保存します。複数の画像を入力として受け取り、カスタマイズ可能なファイル名プレフィックスを付けてディスクに書き込みます。 diff --git a/ja/built-in-nodes/SaveImageTextDataSetToFolder.mdx b/ja/built-in-nodes/SaveImageTextDataSetToFolder.mdx index 0df20a5a1..2ac026302 100644 --- a/ja/built-in-nodes/SaveImageTextDataSetToFolder.mdx +++ b/ja/built-in-nodes/SaveImageTextDataSetToFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImageTextDataSetToFolder" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageTextDataSetToFolder/en.md) 画像とテキストデータセットをフォルダに保存するノードは、画像のリストとそれに対応するテキストキャプションを、ComfyUIの出力ディレクトリ内の指定されたフォルダに保存します。各画像がPNGファイルとして保存される際に、同じベース名を持つテキストファイルが作成され、そのキャプションが格納されます。これは、生成された画像とその説明文からなる整理されたデータセットを作成する際に便利です。 diff --git a/ja/built-in-nodes/SaveLatent.mdx b/ja/built-in-nodes/SaveLatent.mdx index d7e423d3a..1a8ce71ae 100644 --- a/ja/built-in-nodes/SaveLatent.mdx +++ b/ja/built-in-nodes/SaveLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLatent" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLatent/en.md) SaveLatentノードは、潜在テンソルを後で使用したり共有したりするために、ファイルとしてディスクに保存します。このノードは潜在サンプルを受け取り、プロンプト情報を含むオプションのメタデータとともに出力ディレクトリに保存します。ノードはファイルの命名と整理を自動的に処理し、潜在データ構造を保持します。 @@ -22,7 +23,7 @@ SaveLatentノードは、潜在テンソルを後で使用したり共有した | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ui` | ComfyUIインターフェースで保存された潜在データのファイル位置情報を提供します | UI | +| `samples` | ComfyUIインターフェースで保存された潜在データのファイル位置情報を提供します | UI | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLatent/ja.md) diff --git a/ja/built-in-nodes/SaveLoRA.mdx b/ja/built-in-nodes/SaveLoRA.mdx index 5818e70d8..0e332c98c 100644 --- a/ja/built-in-nodes/SaveLoRA.mdx +++ b/ja/built-in-nodes/SaveLoRA.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLoRA" icon: "circle" mode: wide --- + SaveLoRA ノードは、LoRA（Low-Rank Adaptation）モデルをファイルに保存します。LoRA モデルを入力として受け取り、出力ディレクトリに `.safetensors` ファイルとして書き込みます。ファイル名のプレフィックスと、最終的なファイル名に含めるオプションのステップ数を指定できます。 ## 入力 diff --git a/ja/built-in-nodes/SaveLoRANode.mdx b/ja/built-in-nodes/SaveLoRANode.mdx index 30f094c9b..2aa40bb29 100644 --- a/ja/built-in-nodes/SaveLoRANode.mdx +++ b/ja/built-in-nodes/SaveLoRANode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLoRANode" icon: "circle" mode: wide --- + SaveLoRAノードは、LoRA（Low-Rank Adaptation）モデルを出力ディレクトリに保存します。入力としてLoRAモデルを受け取り、自動生成されたファイル名でsafetensorsファイルを作成します。ファイル名のプレフィックスをカスタマイズしたり、オプションでトレーニングステップ数をファイル名に含めて整理しやすくすることができます。 ## 入力 diff --git a/ja/built-in-nodes/SaveSVGNode.mdx b/ja/built-in-nodes/SaveSVGNode.mdx index 9a1e48569..08f347d3d 100644 --- a/ja/built-in-nodes/SaveSVGNode.mdx +++ b/ja/built-in-nodes/SaveSVGNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveSVGNode" icon: "circle" mode: wide --- + SVGファイルをディスクに保存します。このノードはSVGデータを入力として受け取り、オプションでメタデータを埋め込みながら出力ディレクトリに保存します。ファイル名にはカウンターサフィックスが自動的に付与され、ワークフローのプロンプト情報をSVGファイルに直接埋め込むことができます。 ## 入力 @@ -18,7 +19,7 @@ SVGファイルをディスクに保存します。このノードはSVGデー | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ui` | ファイル名、サブフォルダ、タイプを含むファイル情報を返し、ComfyUIインターフェースに表示します | DICT | +| `svg` | ファイル名、サブフォルダ、タイプを含むファイル情報を返し、ComfyUIインターフェースに表示します | DICT | **注意:** このノードは、利用可能な場合にワークフローのメタデータ（プロンプトおよび追加のPNG情報）をSVGファイルに自動的に埋め込みます。メタデータはSVGのmetadata要素内にCDATAセクションとして挿入されます。 diff --git a/ja/built-in-nodes/SaveTrainingDataset.mdx b/ja/built-in-nodes/SaveTrainingDataset.mdx index 8e8a0aaf0..503981054 100644 --- a/ja/built-in-nodes/SaveTrainingDataset.mdx +++ b/ja/built-in-nodes/SaveTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveTrainingDataset" icon: "circle" mode: wide --- + このノードは、準備されたトレーニングデータセットをコンピュータのハードドライブに保存します。画像の潜在表現とそれに対応するテキストコンディショニングを含むエンコード済みデータを受け取り、管理を容易にするために「シャード」と呼ばれる複数の小さなファイルに整理します。このノードは出力ディレクトリ内に自動的にフォルダを作成し、データファイルとデータセットを説明するメタデータファイルの両方を保存します。 ## 入力 diff --git a/ja/built-in-nodes/SaveVideo.mdx b/ja/built-in-nodes/SaveVideo.mdx index 333b92f20..a7630ecd4 100644 --- a/ja/built-in-nodes/SaveVideo.mdx +++ b/ja/built-in-nodes/SaveVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveVideo" icon: "circle" mode: wide --- + SaveVideoノードは、入力された動画コンテンツをComfyUIの出力ディレクトリに保存します。このノードでは、保存するファイルのファイル名プレフィックス、動画フォーマット、およびコーデックを指定できます。また、カウンターのインクリメントによる自動ファイル名管理に対応しており、保存された動画にワークフローメタデータを含めることも可能です。 ## 入力 diff --git a/ja/built-in-nodes/SaveWEBM.mdx b/ja/built-in-nodes/SaveWEBM.mdx index 005a2a24c..ff34f7871 100644 --- a/ja/built-in-nodes/SaveWEBM.mdx +++ b/ja/built-in-nodes/SaveWEBM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveWEBM" icon: "circle" mode: wide --- + SaveWEBMノードは、画像のシーケンスをWEBMビデオファイルとして保存します。複数の入力画像を受け取り、VP9またはAV1コーデックを使用して、設定可能な品質設定とフレームレートでビデオにエンコードします。生成されたビデオファイルは、プロンプト情報を含むメタデータとともに出力ディレクトリに保存されます。 ## 入力 @@ -21,7 +22,7 @@ SaveWEBMノードは、画像のシーケンスをWEBMビデオファイルと | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ui` | 保存されたWEBMファイルを表示するビデオプレビュー | PREVIEW | +| `images` | 保存されたWEBMファイルを表示するビデオプレビュー | PREVIEW | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveWEBM/ja.md) diff --git a/ja/built-in-nodes/ScaleROPE.mdx b/ja/built-in-nodes/ScaleROPE.mdx index 10522e7a6..2ae012eb9 100644 --- a/ja/built-in-nodes/ScaleROPE.mdx +++ b/ja/built-in-nodes/ScaleROPE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ScaleROPE" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/Sd4xupscaleConditioning.mdx b/ja/built-in-nodes/Sd4xupscaleConditioning.mdx index d60070f1b..32a6ebc2f 100644 --- a/ja/built-in-nodes/Sd4xupscaleConditioning.mdx +++ b/ja/built-in-nodes/Sd4xupscaleConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Sd4xupscaleConditioning" icon: "circle" mode: wide --- + このノードは、4倍のアップスケール処理を通じて画像の解像度を向上させることに特化しており、出力を洗練するための条件付け要素を組み込んでいます。拡散技術を活用して画像をアップスケールするとともに、スケール比率やノイズ増強の調整を可能にし、拡張処理を微調整します。 ## 入力 diff --git a/ja/built-in-nodes/SeedNode.mdx b/ja/built-in-nodes/SeedNode.mdx new file mode 100644 index 000000000..ddb99d121 --- /dev/null +++ b/ja/built-in-nodes/SeedNode.mdx @@ -0,0 +1,28 @@ +--- +title: "SeedNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the SeedNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "SeedNode" +icon: "circle" +mode: wide +--- + +## 概要 + +Seedノードは、固定またはランダムな整数値を生成します。このノードは、他のノードにおけるランダム操作の再現性を制御するために一般的に使用され、乱数生成の一貫した開始点を提供します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `シード` | 使用するシード値です。生成後の制御オプションによって、値が固定されたままになるか、生成ごとに変化するかが決まります。 | INT | はい | 0 ～ 9223372036854775807 | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `シード` | 生成されたシード値です。 | INT | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SeedNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `19f9b22945bb152ff5066195067f1b6b4c006589f26c7533fad905044ac3b7fa` diff --git a/ja/built-in-nodes/SeedVR2Conditioning.mdx b/ja/built-in-nodes/SeedVR2Conditioning.mdx index efdda40c1..d52249419 100644 --- a/ja/built-in-nodes/SeedVR2Conditioning.mdx +++ b/ja/built-in-nodes/SeedVR2Conditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2Conditioning" icon: "circle" mode: wide --- -# Apply SeedVR2 Conditioning このノードは、VAE潜在変数からSeedVR2モデルで使用するポジティブおよびネガティブなコンディショニングを構築します。画像や動画の生成プロセスを導くコンディショニングデータを準備します。 diff --git a/ja/built-in-nodes/SeedVR2PostProcessing.mdx b/ja/built-in-nodes/SeedVR2PostProcessing.mdx index b236cbfe2..0624fbe56 100644 --- a/ja/built-in-nodes/SeedVR2PostProcessing.mdx +++ b/ja/built-in-nodes/SeedVR2PostProcessing.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2PostProcessing" icon: "circle" mode: wide --- -# Post-Process SeedVR2 出力 このノードは、生成された画像を元のリサイズ画像に合わせて調整し、オプションで色補正を適用します。SeedVR2 アップスケーリング処理の出力を受け取り、元の参照画像の色と寸法に合わせて調整します。 diff --git a/ja/built-in-nodes/SeedVR2Preprocess.mdx b/ja/built-in-nodes/SeedVR2Preprocess.mdx index 0f1fd7bd4..3d9344c42 100644 --- a/ja/built-in-nodes/SeedVR2Preprocess.mdx +++ b/ja/built-in-nodes/SeedVR2Preprocess.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2Preprocess" icon: "circle" mode: wide --- -# Pre-Process SeedVR2 Input（SeedVR2 入力前処理） このノードは、リサイズされた画像にパディングを施し、SeedVR2 モデルで処理できる状態に準備します。処理中にアルファチャンネルを除去し、その後、後続の Post-Process SeedVR2 Output（SeedVR2 出力後処理）ノードが元のリサイズ画像を使用してアルファチャンネルを復元します。 diff --git a/ja/built-in-nodes/SeedVR2ProgressiveSampler.mdx b/ja/built-in-nodes/SeedVR2ProgressiveSampler.mdx index 2a9b3da01..2df430d30 100644 --- a/ja/built-in-nodes/SeedVR2ProgressiveSampler.mdx +++ b/ja/built-in-nodes/SeedVR2ProgressiveSampler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2ProgressiveSampler" icon: "circle" mode: wide --- -# SeedVR2ProgressiveSampler SeedVR2ネイティブワークフロー向けのシーケンシャル時間チャンクサンプラーです。このノードは、長い動画の潜在表現をより小さな時間チャンクに分割し、各チャンクを順次サンプリングして、結果をブレンドすることで処理を行います。メモリ不足エラーが発生するようなシーケンスでSeedVR2モデルを使用する際に、標準のKSamplerの代替として使用できます。 diff --git a/ja/built-in-nodes/SelectCLIPDevice.mdx b/ja/built-in-nodes/SelectCLIPDevice.mdx index b10d72e40..354643ed5 100644 --- a/ja/built-in-nodes/SelectCLIPDevice.mdx +++ b/ja/built-in-nodes/SelectCLIPDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectCLIPDevice" icon: "circle" mode: wide --- + ## 概要 Select CLIP Device ノードを使用すると、CLIPテキストエンコーダーを実行するデバイス（CPUまたは特定のGPU）を選択できます。デフォルトでは、デバイスはモデルローダーによって割り当てられますが、CPUまたは特定のGPUを使用するように上書きできます。要求されたデバイスがお使いのマシンに存在しない場合、ノードはエラーを発生させずにCLIPをそのまま通過させ、メッセージをログに記録します。 diff --git a/ja/built-in-nodes/SelectModelDevice.mdx b/ja/built-in-nodes/SelectModelDevice.mdx index 798f79a9d..9fba26787 100644 --- a/ja/built-in-nodes/SelectModelDevice.mdx +++ b/ja/built-in-nodes/SelectModelDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectModelDevice" icon: "circle" mode: wide --- + ## 概要 SelectModelDeviceノードを使用すると、拡散モデルを実行するデバイス（CPUまたは特定のGPU）を手動で選択できます。モデルを別のデバイスに移動することができ、他のマルチGPUノードとの競合を自動的に処理します。 diff --git a/ja/built-in-nodes/SelectVAEDevice.mdx b/ja/built-in-nodes/SelectVAEDevice.mdx index 3cf89295a..1c3fec33f 100644 --- a/ja/built-in-nodes/SelectVAEDevice.mdx +++ b/ja/built-in-nodes/SelectVAEDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectVAEDevice" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/SelfAttentionGuidance.mdx b/ja/built-in-nodes/SelfAttentionGuidance.mdx index fdcba1b6c..0d9f4b4ef 100644 --- a/ja/built-in-nodes/SelfAttentionGuidance.mdx +++ b/ja/built-in-nodes/SelfAttentionGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelfAttentionGuidance" icon: "circle" mode: wide --- + ## 概要 Self-Attention Guidanceノードは、サンプリング処理中にアテンションメカニズムを変更することで、拡散モデルにガイダンスを適用します。無条件ノイズ除去ステップからアテンションスコアを取得し、それらを使用して最終出力に影響を与えるぼかしガイダンスマップを作成します。この技術は、モデル自身のアテンションパターンを活用することで、生成プロセスを誘導するのに役立ちます。 diff --git a/ja/built-in-nodes/SetClipHooks.mdx b/ja/built-in-nodes/SetClipHooks.mdx index b5b1d791a..57a05928a 100644 --- a/ja/built-in-nodes/SetClipHooks.mdx +++ b/ja/built-in-nodes/SetClipHooks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetClipHooks" icon: "circle" mode: wide --- + SetClipHooks ノードを使用すると、CLIPモデルにカスタムフックを適用し、その動作を高度に変更できます。このノードは、コンディショニング出力にフックを適用したり、オプションでクリップスケジューリング機能を有効にしたりできます。指定されたフック設定が適用された、入力CLIPモデルのクローンコピーを作成します。 ## 入力 diff --git a/ja/built-in-nodes/SetFirstSigma.mdx b/ja/built-in-nodes/SetFirstSigma.mdx index 923cf84ab..e7cfb6dfc 100644 --- a/ja/built-in-nodes/SetFirstSigma.mdx +++ b/ja/built-in-nodes/SetFirstSigma.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetFirstSigma" icon: "circle" mode: wide --- + SetFirstSigma ノードは、シグマ値のシーケンスを変更し、その最初のシグマ値をカスタム値に置き換えます。既存のシグマシーケンスと新しいシグマ値を入力として受け取り、最初の要素のみが変更され、他のすべてのシグマ値は変更されていない新しいシグマシーケンスを返します。 ## 入力 diff --git a/ja/built-in-nodes/SetHookKeyframes.mdx b/ja/built-in-nodes/SetHookKeyframes.mdx index 88389c834..9298159b3 100644 --- a/ja/built-in-nodes/SetHookKeyframes.mdx +++ b/ja/built-in-nodes/SetHookKeyframes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetHookKeyframes" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要概要 diff --git a/ja/built-in-nodes/SetLatentNoiseMask.mdx b/ja/built-in-nodes/SetLatentNoiseMask.mdx index a4d3c804e..dca51820a 100644 --- a/ja/built-in-nodes/SetLatentNoiseMask.mdx +++ b/ja/built-in-nodes/SetLatentNoiseMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetLatentNoiseMask" icon: "circle" mode: wide --- + このノードは、潜在サンプルのセットにノイズマスクを適用するために設計されています。指定されたマスクを統合することで入力サンプルを変更し、ノイズ特性を変化させます。 ## 入力 diff --git a/ja/built-in-nodes/SetModelHooksOnCond.mdx b/ja/built-in-nodes/SetModelHooksOnCond.mdx index 44f523476..b250aa5cc 100644 --- a/ja/built-in-nodes/SetModelHooksOnCond.mdx +++ b/ja/built-in-nodes/SetModelHooksOnCond.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetModelHooksOnCond" icon: "circle" mode: wide --- + このドキュメントは AI が生成したものです。誤りや改善の提案がありましたら、ぜひご協力ください。[GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetModelHooksOnCond/en.md) このノードは、コンディショニングデータにカスタムフックをアタッチし、モデル実行中にコンディショニングプロセスをインターセプトして変更できるようにします。一連のフックを受け取り、提供されたコンディショニングデータに適用することで、テキストから画像を生成するワークフローの高度なカスタマイズを実現します。フックがアタッチされた変更後のコンディショニングは、後続の処理ステップで使用するために返されます。 diff --git a/ja/built-in-nodes/SetUnionControlNetType.mdx b/ja/built-in-nodes/SetUnionControlNetType.mdx index d5017a13a..93055f63e 100644 --- a/ja/built-in-nodes/SetUnionControlNetType.mdx +++ b/ja/built-in-nodes/SetUnionControlNetType.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetUnionControlNetType" icon: "circle" mode: wide --- + SetUnionControlNetType ノードを使用すると、条件付けに使用するコントロールネットワークのタイプを指定できます。既存のコントロールネットワークを入力として受け取り、選択に基づいてそのコントロールタイプを設定し、指定されたタイプ構成でコントロールネットワークの修正済みコピーを作成します。 ## 入力 diff --git a/ja/built-in-nodes/ShuffleDataset.mdx b/ja/built-in-nodes/ShuffleDataset.mdx index 8807863e1..e2825c077 100644 --- a/ja/built-in-nodes/ShuffleDataset.mdx +++ b/ja/built-in-nodes/ShuffleDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ShuffleDataset" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要データセットシャッフルノードは、画像のリストを受け取り、その順序をランダムに変更します。シード値を使用してランダム性を制御し、同じシャッフル順序を再現できるようにします。これは、データセット内の画像の順序を処理前にランダム化する際に便利です。 diff --git a/ja/built-in-nodes/ShuffleImageTextDataset.mdx b/ja/built-in-nodes/ShuffleImageTextDataset.mdx index fa46afe28..e4f42565c 100644 --- a/ja/built-in-nodes/ShuffleImageTextDataset.mdx +++ b/ja/built-in-nodes/ShuffleImageTextDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ShuffleImageTextDataset" icon: "circle" mode: wide --- + このノードは、画像のリストとテキストのリストを一緒にシャッフルし、それらのペアリングを維持します。ランダムシードを使用してシャッフル順序を決定し、同じ入力リストが同じシードで毎回同じようにシャッフルされることを保証します。 ## 入力 @@ -21,7 +22,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `texts` | シャッフルされた画像のリスト。 | IMAGE | +| `images` | シャッフルされた画像のリスト。 | IMAGE | | `texts` | シャッフルされたテキストのリスト。画像との元のペアリングを維持します。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ShuffleImageTextDataset/ja.md) diff --git a/ja/built-in-nodes/SkipLayerGuidanceDiT.mdx b/ja/built-in-nodes/SkipLayerGuidanceDiT.mdx index 22be580a3..971e95c6f 100644 --- a/ja/built-in-nodes/SkipLayerGuidanceDiT.mdx +++ b/ja/built-in-nodes/SkipLayerGuidanceDiT.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceDiT" icon: "circle" mode: wide --- + 以下、英語ドキュメントを日本語に翻訳しました。 スキップレイヤーを使用した別のCFGネガティブセットを用いて、詳細な構造へのガイダンスを強化します。この汎用版のSkipLayerGuidanceは、すべてのDiTモデルで使用可能であり、Perturbed Attention Guidanceに着想を得ています。元の実験的実装はSD3用に作成されました。 diff --git a/ja/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx b/ja/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx index 0a69f7b37..47b72ecb2 100644 --- a/ja/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx +++ b/ja/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceDiTSimple" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/SkipLayerGuidanceSD3.mdx b/ja/built-in-nodes/SkipLayerGuidanceSD3.mdx index f1baa6ec0..e85ed90ea 100644 --- a/ja/built-in-nodes/SkipLayerGuidanceSD3.mdx +++ b/ja/built-in-nodes/SkipLayerGuidanceSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceSD3" icon: "circle" mode: wide --- + 以下が翻訳結果です。 SkipLayerGuidanceSD3 ノードは、スキップされたレイヤーを使用して追加の分類器フリーガイダンスを適用することで、詳細な構造へのガイダンスを強化します。この実験的な実装は、Perturbed Attention Guidance に着想を得ており、ネガティブ条件付けプロセス中に特定のレイヤーを選択的にバイパスすることで、生成出力の構造的詳細を改善します。 diff --git a/ja/built-in-nodes/SolidMask.mdx b/ja/built-in-nodes/SolidMask.mdx index acf3eb3f8..88d862704 100644 --- a/ja/built-in-nodes/SolidMask.mdx +++ b/ja/built-in-nodes/SolidMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SolidMask" icon: "circle" mode: wide --- + SolidMaskノードは、指定された値で全面が均一なマスクを生成します。特定の寸法と強度を持つマスクを作成するために設計されており、さまざまな画像処理やマスキングタスクで役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/SoniloTextToMusic.mdx b/ja/built-in-nodes/SoniloTextToMusic.mdx index 9af063ec9..e7bade971 100644 --- a/ja/built-in-nodes/SoniloTextToMusic.mdx +++ b/ja/built-in-nodes/SoniloTextToMusic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SoniloTextToMusic" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Sonilo Text to Music ノードは、Sonilo の AI モデルを使用して、テキストによる説明から音楽を生成します。生成したい音楽を説明するプロンプトを入力すると、ノードが Sonilo サービスにリクエストを送信し、オーディオファイルを作成します。ターゲットとなる再生時間を指定するか、モデルにプロンプトから推測させることもできます。 diff --git a/ja/built-in-nodes/SoniloVideoToMusic.mdx b/ja/built-in-nodes/SoniloVideoToMusic.mdx index 5c5095280..bb07602a7 100644 --- a/ja/built-in-nodes/SoniloVideoToMusic.mdx +++ b/ja/built-in-nodes/SoniloVideoToMusic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SoniloVideoToMusic" icon: "circle" mode: wide --- + 以下が翻訳結果です。 SoniloのAIモデルを使用して、動画から音楽を生成します。このノードは入力された動画の内容を分析し、それに合った楽曲を作成します。動画の処理と音声の生成には、外部のAIサービスを利用します。 diff --git a/ja/built-in-nodes/SplatToFile3D.mdx b/ja/built-in-nodes/SplatToFile3D.mdx index 03824d2c0..bb89ec6f0 100644 --- a/ja/built-in-nodes/SplatToFile3D.mdx +++ b/ja/built-in-nodes/SplatToFile3D.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SplatToFile3D" icon: "circle" mode: wide --- -# SplatToFile3D ノードドキュメント ## 概要 @@ -22,7 +21,7 @@ SplatToFile3Dノードは、ガウシアンスプラットをFile3Dオブジェ | 出力名 | 説明 | データ型 | |-------------|-------------|-----------| -| `model_3d` | 選択された形式でシリアライズされたガウシアンスプラットデータを含むFile3Dオブジェクト。保存またはプレビューの準備ができています | FILE3D | +| `3Dモデル` | 選択された形式でシリアライズされたガウシアンスプラットデータを含むFile3Dオブジェクト。保存またはプレビューの準備ができています | FILE3D | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplatToFile3D/ja.md) diff --git a/ja/built-in-nodes/SplatToMesh.mdx b/ja/built-in-nodes/SplatToMesh.mdx index 2a5cc1f4b..a8f367a07 100644 --- a/ja/built-in-nodes/SplatToMesh.mdx +++ b/ja/built-in-nodes/SplatToMesh.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SplatToMesh" icon: "circle" mode: wide --- -# スプラットからメッシュを抽出 このノードは、3Dガウシアンスプラットを色付きメッシュサーフェスに変換します。ガウシアンを密度グリッドにラスタライズし、選択した密度レベルで等値面を抽出し、必要に応じてスムージングとクリーンアップを適用することで、クリーンな色付き三角形メッシュを生成します。 @@ -26,7 +25,7 @@ mode: wide | 出力名 | 説明 | データ型 | |-------------|-------------|-----------| -| `mesh` | スプラットの外観に合わせて非照明レンダリング（発光風）で抽出された色付きメッシュ | MESH | +| `メッシュ` | スプラットの外観に合わせて非照明レンダリング（発光風）で抽出された色付きメッシュ | MESH | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplatToMesh/ja.md) diff --git a/ja/built-in-nodes/SplitAudioChannels.mdx b/ja/built-in-nodes/SplitAudioChannels.mdx index 0ae731bed..476c015c2 100644 --- a/ja/built-in-nodes/SplitAudioChannels.mdx +++ b/ja/built-in-nodes/SplitAudioChannels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitAudioChannels" icon: "circle" mode: wide --- + SplitAudioChannelsノードは、ステレオ音声を左右個別のチャンネルに分離します。2チャンネルのステレオ音声入力を受け取り、左チャンネルと右チャンネルの2つの個別の音声ストリームを出力します。 ## 入力 @@ -19,8 +20,8 @@ SplitAudioChannelsノードは、ステレオ音声を左右個別のチャン | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `右` | 分離された左チャンネルの音声 | AUDIO | -| `right` | 分離された右チャンネルの音声 | AUDIO | +| `左` | 分離された左チャンネルの音声 | AUDIO | +| `右` | 分離された右チャンネルの音声 | AUDIO | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitAudioChannels/ja.md) diff --git a/ja/built-in-nodes/SplitImageToTileList.mdx b/ja/built-in-nodes/SplitImageToTileList.mdx index 7f663a9a1..65196af23 100644 --- a/ja/built-in-nodes/SplitImageToTileList.mdx +++ b/ja/built-in-nodes/SplitImageToTileList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitImageToTileList" icon: "circle" mode: wide --- + 以下が翻訳結果です。 画像をタイルリストに分割ノードは、単一の入力画像を、タイルと呼ばれるより小さな重なり合う長方形の領域のシリーズに分割します。このノードは、これらのタイルのバッチ化されたリストを作成し、他のノードで個別に処理できるようにします。各タイルのサイズとタイル間の重なり量を指定できます。 diff --git a/ja/built-in-nodes/SplitImageWithAlpha.mdx b/ja/built-in-nodes/SplitImageWithAlpha.mdx index 59f728aff..1da6d26c8 100644 --- a/ja/built-in-nodes/SplitImageWithAlpha.mdx +++ b/ja/built-in-nodes/SplitImageWithAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitImageWithAlpha" icon: "circle" mode: wide --- + ### SplitImageWithAlpha ノード SplitImageWithAlpha ノードは、画像の色成分とアルファ成分を分離するために設計されています。入力画像テンソルを処理し、RGBチャンネルを色成分として、アルファチャンネルを透明度成分として抽出することで、これらの異なる画像要素の操作を必要とする処理を容易にします。 diff --git a/ja/built-in-nodes/SplitSigmas.mdx b/ja/built-in-nodes/SplitSigmas.mdx index c27d2e663..faa54b4fb 100644 --- a/ja/built-in-nodes/SplitSigmas.mdx +++ b/ja/built-in-nodes/SplitSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitSigmas" icon: "circle" mode: wide --- + SplitSigmasノードは、指定されたステップに基づいてシグマ値のシーケンスを2つの部分に分割するために設計されています。この機能は、シグマシーケンスの最初の部分と後続部分に対して異なる処理や操作が必要な場合に重要であり、これらの値のより柔軟かつターゲットを絞った操作を可能にします。 ## 入力 @@ -18,6 +19,6 @@ SplitSigmasノードは、指定されたステップに基づいてシグマ値 | パラメータ | 説明 | データ型 | | --- | --- | --- | -| `低シグマ` | ノードは2つのシグマ値シーケンスを出力します。それぞれは、指定されたステップで分割された元のシーケンスの一部を表します。これらの出力は、シグマ値の異なる処理が必要な後続の操作にとって重要です。 | `SIGMAS` | +| `高シグマ` | ノードは2つのシグマ値シーケンスを出力します。それぞれは、指定されたステップで分割された元のシーケンスの一部を表します。これらの出力は、シグマ値の異なる処理が必要な後続の操作にとって重要です。 | `SIGMAS` | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitSigmas/ja.md) diff --git a/ja/built-in-nodes/SplitSigmasDenoise.mdx b/ja/built-in-nodes/SplitSigmasDenoise.mdx index 80459fce0..96670ceb1 100644 --- a/ja/built-in-nodes/SplitSigmasDenoise.mdx +++ b/ja/built-in-nodes/SplitSigmasDenoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitSigmasDenoise" icon: "circle" mode: wide --- + SplitSigmasDenoiseノードは、ノイズ除去強度パラメータに基づいてシグマ値のシーケンスを2つの部分に分割します。入力されたシグマを高シグマシーケンスと低シグマシーケンスに分割し、分割点は総ステップ数にノイズ除去係数を乗じて決定されます。これにより、ノイズスケジュールを異なる強度範囲に分離し、特殊な処理を行うことが可能になります。 ## 入力 @@ -18,8 +19,8 @@ SplitSigmasDenoiseノードは、ノイズ除去強度パラメータに基づ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `低シグマ` | より高いシグマ値を含むシグマシーケンスの前半部分 | SIGMAS | -| `low_sigmas` | より低いシグマ値を含むシグマシーケンスの後半部分 | SIGMAS | +| `高シグマ` | より高いシグマ値を含むシグマシーケンスの前半部分 | SIGMAS | +| `低シグマ` | より低いシグマ値を含むシグマシーケンスの後半部分 | SIGMAS | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitSigmasDenoise/ja.md) diff --git a/ja/built-in-nodes/StabilityAudioInpaint.mdx b/ja/built-in-nodes/StabilityAudioInpaint.mdx index a4a909779..e33a40e3e 100644 --- a/ja/built-in-nodes/StabilityAudioInpaint.mdx +++ b/ja/built-in-nodes/StabilityAudioInpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityAudioInpaint" icon: "circle" mode: wide --- + 以下が翻訳結果です。 テキスト指示を使用して、既存のオーディオサンプルの一部を変換します。このノードでは、説明的なプロンプトを提供することでオーディオの特定のセクションを変更し、残りの部分を保持しながら選択した部分を効果的に「インペイント」または再生成できます。 diff --git a/ja/built-in-nodes/StabilityAudioToAudio.mdx b/ja/built-in-nodes/StabilityAudioToAudio.mdx index 14d5a1b15..683043b9f 100644 --- a/ja/built-in-nodes/StabilityAudioToAudio.mdx +++ b/ja/built-in-nodes/StabilityAudioToAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityAudioToAudio" icon: "circle" mode: wide --- + 既存のオーディオサンプルをテキスト指示に基づいて新しい高品質な作品に変換します。このノードは入力オーディオファイルを受け取り、テキストプロンプトに従ってオーディオコンテンツを変更します。 ## 入力 diff --git a/ja/built-in-nodes/StabilityStableImageSD_3_5Node.mdx b/ja/built-in-nodes/StabilityStableImageSD_3_5Node.mdx index b150c7df6..63be8de32 100644 --- a/ja/built-in-nodes/StabilityStableImageSD_3_5Node.mdx +++ b/ja/built-in-nodes/StabilityStableImageSD_3_5Node.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityStableImageSD_3_5Node" icon: "circle" mode: wide --- + このノードは、Stability AI の Stable Diffusion 3.5 モデルを使用して画像を同期的に生成します。テキストプロンプトに基づいて画像を作成し、入力として既存の画像が提供された場合はその画像を修正することもできます。出力をカスタマイズするために、さまざまなアスペクト比やスタイルプリセットをサポートしています。 ## 入力 diff --git a/ja/built-in-nodes/StabilityStableImageUltraNode.mdx b/ja/built-in-nodes/StabilityStableImageUltraNode.mdx index 4c304b141..f2695087c 100644 --- a/ja/built-in-nodes/StabilityStableImageUltraNode.mdx +++ b/ja/built-in-nodes/StabilityStableImageUltraNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityStableImageUltraNode" icon: "circle" mode: wide --- + プロンプトと解像度に基づいて画像を同期的に生成します。このノードは、Stability AI の Stable Image Ultra モデルを使用して画像を作成し、テキストプロンプトを処理して、指定されたアスペクト比とスタイルで対応する画像を生成します。 ## 入力 diff --git a/ja/built-in-nodes/StabilityTextToAudio.mdx b/ja/built-in-nodes/StabilityTextToAudio.mdx index c0e5a1767..b0c8f224e 100644 --- a/ja/built-in-nodes/StabilityTextToAudio.mdx +++ b/ja/built-in-nodes/StabilityTextToAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityTextToAudio" icon: "circle" mode: wide --- + テキスト記述から高品質な音楽や効果音を生成します。このノードはStability AIの音声生成技術を使用して、テキストプロンプトに基づいたオーディオコンテンツを作成します。 ## 入力 diff --git a/ja/built-in-nodes/StabilityUpscaleConservativeNode.mdx b/ja/built-in-nodes/StabilityUpscaleConservativeNode.mdx index 992c7062d..a1b398009 100644 --- a/ja/built-in-nodes/StabilityUpscaleConservativeNode.mdx +++ b/ja/built-in-nodes/StabilityUpscaleConservativeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityUpscaleConservativeNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 画像への変更を最小限に抑えながら、4K解像度にアップスケールします。このノードはStability AIの保守的なアップスケーリングを使用して、元のコンテンツを保持しつつ、微妙な変更のみを加えて画像解像度を向上させます。 diff --git a/ja/built-in-nodes/StabilityUpscaleCreativeNode.mdx b/ja/built-in-nodes/StabilityUpscaleCreativeNode.mdx index 5fae09b19..909d8c594 100644 --- a/ja/built-in-nodes/StabilityUpscaleCreativeNode.mdx +++ b/ja/built-in-nodes/StabilityUpscaleCreativeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityUpscaleCreativeNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityUpscaleCreativeNode/en.md) 画像を最小限の変更で4K解像度にアップスケールします。このノードはStability AIのクリエイティブアップスケーリング技術を使用して、元のコンテンツを保持しながら画像解像度を向上させ、微妙な創造的なディテールを追加します。 diff --git a/ja/built-in-nodes/StabilityUpscaleFastNode.mdx b/ja/built-in-nodes/StabilityUpscaleFastNode.mdx index 8d7ccbeab..2685553a9 100644 --- a/ja/built-in-nodes/StabilityUpscaleFastNode.mdx +++ b/ja/built-in-nodes/StabilityUpscaleFastNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityUpscaleFastNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/StableCascade_EmptyLatentImage.mdx b/ja/built-in-nodes/StableCascade_EmptyLatentImage.mdx index e5aae54ac..495c91c45 100644 --- a/ja/built-in-nodes/StableCascade_EmptyLatentImage.mdx +++ b/ja/built-in-nodes/StableCascade_EmptyLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_EmptyLatentImage" icon: "circle" mode: wide --- + StableCascade_EmptyLatentImage ノードは、Stable Cascade モデル用の空の潜在テンソルを作成します。入力解像度と圧縮設定に基づいて、ステージ C 用とステージ B 用の2つの別々の潜在表現を適切な次元で生成します。このノードは、Stable Cascade 生成パイプラインの開始点を提供します。 ## 入力 @@ -20,8 +21,8 @@ StableCascade_EmptyLatentImage ノードは、Stable Cascade モデル用の空 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ステージB` | 次元 [batch_size, 16, height//compression, width//compression] のステージ C 潜在テンソル | LATENT | -| `stage_b` | 次元 [batch_size, 4, height//4, width//4] のステージ B 潜在テンソル | LATENT | +| `ステージC` | 次元 [batch_size, 16, height//compression, width//compression] のステージ C 潜在テンソル | LATENT | +| `ステージB` | 次元 [batch_size, 4, height//4, width//4] のステージ B 潜在テンソル | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_EmptyLatentImage/ja.md) diff --git a/ja/built-in-nodes/StableCascade_StageB_Conditioning.mdx b/ja/built-in-nodes/StableCascade_StageB_Conditioning.mdx index cda54cd58..6ea0ff1b6 100644 --- a/ja/built-in-nodes/StableCascade_StageB_Conditioning.mdx +++ b/ja/built-in-nodes/StableCascade_StageB_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_StageB_Conditioning" icon: "circle" mode: wide --- + ## 概要 StableCascade_StageB_Conditioning ノードは、既存の条件付け情報とステージCからの事前潜在表現を組み合わせることで、Stable Cascade ステージB生成用の条件付けデータを準備します。このノードは、ステージCの潜在サンプルを含むように条件付けデータを変更し、生成プロセスが事前情報を活用してより一貫性のある出力を生成できるようにします。 diff --git a/ja/built-in-nodes/StableCascade_StageC_VAEEncode.mdx b/ja/built-in-nodes/StableCascade_StageC_VAEEncode.mdx index cc3b9e17a..09737933d 100644 --- a/ja/built-in-nodes/StableCascade_StageC_VAEEncode.mdx +++ b/ja/built-in-nodes/StableCascade_StageC_VAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_StageC_VAEEncode" icon: "circle" mode: wide --- + StableCascade_StageC_VAEEncode ノードは、VAEエンコーダーを通じて画像を処理し、Stable Cascadeモデル用の潜在表現を生成します。入力画像を受け取り、指定されたVAEモデルを使用して圧縮し、ステージC用の潜在表現とステージB用のプレースホルダーの2つの潜在表現を出力します。圧縮パラメーターは、エンコード前に画像がどの程度縮小されるかを制御します。 ## 入力 @@ -19,8 +20,8 @@ StableCascade_StageC_VAEEncode ノードは、VAEエンコーダーを通じて | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ステージB` | Stable CascadeモデルのステージC用にエンコードされた潜在表現 | LATENT | -| `stage_b` | ステージB用のプレースホルダー潜在表現（現在はゼロを返します） | LATENT | +| `ステージC` | Stable CascadeモデルのステージC用にエンコードされた潜在表現 | LATENT | +| `ステージB` | ステージB用のプレースホルダー潜在表現（現在はゼロを返します） | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_StageC_VAEEncode/ja.md) diff --git a/ja/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx b/ja/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx index 91bb4d65f..9fb91f82a 100644 --- a/ja/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx +++ b/ja/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_SuperResolutionControlnet" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_SuperResolutionControlnet/en.md) StableCascade_SuperResolutionControlnet ノードは、Stable Cascade の超解像処理用の入力を準備します。入力画像を受け取り、VAE を使用してエンコードすることで controlnet 入力を生成すると同時に、Stable Cascade パイプラインのステージ C およびステージ B 用のプレースホルダー潜在表現を作成します。 @@ -20,9 +21,9 @@ StableCascade_SuperResolutionControlnet ノードは、Stable Cascade の超解 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ステージC` | controlnet 入力に適したエンコード済み画像表現 | IMAGE | -| `ステージB` | Stable Cascade 処理のステージ C 用プレースホルダー潜在表現 | LATENT | -| `stage_b` | Stable Cascade 処理のステージ B 用プレースホルダー潜在表現 | LATENT | +| `コントロールネット入力` | controlnet 入力に適したエンコード済み画像表現 | IMAGE | +| `ステージC` | Stable Cascade 処理のステージ C 用プレースホルダー潜在表現 | LATENT | +| `ステージB` | Stable Cascade 処理のステージ B 用プレースホルダー潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_SuperResolutionControlnet/ja.md) diff --git a/ja/built-in-nodes/StableZero123_Conditioning.mdx b/ja/built-in-nodes/StableZero123_Conditioning.mdx index 134d8e150..d5f392221 100644 --- a/ja/built-in-nodes/StableZero123_Conditioning.mdx +++ b/ja/built-in-nodes/StableZero123_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableZero123_Conditioning" icon: "circle" mode: wide --- + StableZero123_Conditioning ノードは、入力画像とカメラ角度を処理し、3Dモデル生成のための条件付けデータと潜在表現を生成します。CLIPビジョンモデルを使用して画像特徴をエンコードし、仰角と方位角に基づくカメラ埋め込み情報と組み合わせて、ポジティブ条件付けとネガティブ条件付け、および下流の3D生成タスクのための潜在表現を生成します。 ## 入力 @@ -26,9 +27,9 @@ StableZero123_Conditioning ノードは、入力画像とカメラ角度を処 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 画像特徴とカメラ埋め込みを組み合わせたポジティブ条件付けデータ | CONDITIONING | -| `潜在` | ゼロ初期化された特徴を持つネガティブ条件付けデータ | CONDITIONING | -| `latent` | 次元が [batch_size, 4, height//8, width//8] の潜在表現 | LATENT | +| `ポジティブ` | 画像特徴とカメラ埋め込みを組み合わせたポジティブ条件付けデータ | CONDITIONING | +| `ネガティブ` | ゼロ初期化された特徴を持つネガティブ条件付けデータ | CONDITIONING | +| `潜在` | 次元が [batch_size, 4, height//8, width//8] の潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning/ja.md) diff --git a/ja/built-in-nodes/StableZero123_Conditioning_Batched.mdx b/ja/built-in-nodes/StableZero123_Conditioning_Batched.mdx index 6e31a862d..c53388689 100644 --- a/ja/built-in-nodes/StableZero123_Conditioning_Batched.mdx +++ b/ja/built-in-nodes/StableZero123_Conditioning_Batched.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableZero123_Conditioning_Batched" icon: "circle" mode: wide --- + 以下が翻訳結果です。 StableZero123_Conditioning_Batched ノードは、入力画像を処理し、3D モデル生成のための条件付けデータを生成します。CLIP vision モデルと VAE モデルを使用して画像をエンコードし、仰角と方位角に基づいてカメラ埋め込みを作成します。これにより、バッチ処理用のポジティブ条件付け、ネガティブ条件付け、および潜在表現が生成されます。 @@ -30,9 +31,9 @@ StableZero123_Conditioning_Batched ノードは、入力画像を処理し、3D | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 画像埋め込みとカメラパラメータを含むポジティブ条件付けデータ | CONDITIONING | -| `潜在` | ゼロ初期化された埋め込みを含むネガティブ条件付けデータ | CONDITIONING | -| `latent` | バッチインデックス情報を含む、処理済み画像の潜在表現 | LATENT | +| `ポジティブ` | 画像埋め込みとカメラパラメータを含むポジティブ条件付けデータ | CONDITIONING | +| `ネガティブ` | ゼロ初期化された埋め込みを含むネガティブ条件付けデータ | CONDITIONING | +| `潜在` | バッチインデックス情報を含む、処理済み画像の潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning_Batched/ja.md) diff --git a/ja/built-in-nodes/Stablezero123Conditioning.mdx b/ja/built-in-nodes/Stablezero123Conditioning.mdx index 6ae94188f..4a0d60596 100644 --- a/ja/built-in-nodes/Stablezero123Conditioning.mdx +++ b/ja/built-in-nodes/Stablezero123Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Stablezero123Conditioning" icon: "circle" mode: wide --- + このノードは、StableZero123モデルで使用するデータを処理および条件付けするために設計されており、これらのモデルに互換性があり最適化された特定の形式で入力を準備することに重点を置いています。 ## 入力 diff --git a/ja/built-in-nodes/Stablezero123ConditioningBatched.mdx b/ja/built-in-nodes/Stablezero123ConditioningBatched.mdx index 03d505726..330a28fe4 100644 --- a/ja/built-in-nodes/Stablezero123ConditioningBatched.mdx +++ b/ja/built-in-nodes/Stablezero123ConditioningBatched.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Stablezero123ConditioningBatched" icon: "circle" mode: wide --- + このノードは、StableZero123モデルに特化した条件付け情報をバッチ処理するために設計されています。複数の条件付けデータセットを同時に効率的に処理し、バッチ処理が重要なシナリオにおけるワークフローを最適化することに重点を置いています。 ## 入力 diff --git a/ja/built-in-nodes/StringCompare.mdx b/ja/built-in-nodes/StringCompare.mdx index 12066dde8..f6eed5d0e 100644 --- a/ja/built-in-nodes/StringCompare.mdx +++ b/ja/built-in-nodes/StringCompare.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringCompare" icon: "circle" mode: wide --- + 以下が翻訳結果です。 StringCompareノードは、異なる比較方法を使用して2つのテキスト文字列を比較します。一方の文字列がもう一方で始まるか、終わるか、または両方の文字列が完全に等しいかを確認できます。比較は、大文字と小文字の違いを考慮するかどうかを選択して実行できます。 diff --git a/ja/built-in-nodes/StringConcatenate.mdx b/ja/built-in-nodes/StringConcatenate.mdx index c99c71324..e3cf6f9b6 100644 --- a/ja/built-in-nodes/StringConcatenate.mdx +++ b/ja/built-in-nodes/StringConcatenate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringConcatenate" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りを見つけた場合や改善の提案がある場合は、ぜひご貢献ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringConcatenate/en.md) StringConcatenateノードは、指定された区切り文字を使用して2つのテキスト文字列を結合します。2つの入力文字列と区切り文字（または文字列）を受け取り、2つの入力の間に区切り文字を挿入した単一の文字列を出力します。 diff --git a/ja/built-in-nodes/StringContains.mdx b/ja/built-in-nodes/StringContains.mdx index 70d1ae4b9..ab125d906 100644 --- a/ja/built-in-nodes/StringContains.mdx +++ b/ja/built-in-nodes/StringContains.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringContains" icon: "circle" mode: wide --- + ## 概要 StringContainsノードは、指定された文字列に特定の部分文字列が含まれているかどうかをチェックします。このチェックは、大文字と小文字を区別する方法と区別しない方法のいずれでも実行でき、メイン文字列内に部分文字列が見つかったかどうかを示すブール値の結果を返します。 diff --git a/ja/built-in-nodes/StringFormat.mdx b/ja/built-in-nodes/StringFormat.mdx index 9c813c1f5..9815ba519 100644 --- a/ja/built-in-nodes/StringFormat.mdx +++ b/ja/built-in-nodes/StringFormat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringFormat" icon: "circle" mode: wide --- + ## 概要 このノードは、Pythonの文字列フォーマットメソッドを使用してテキストを整形します。プレースホルダーを含むテキストパターンを定義し、それらのプレースホルダーを埋めるための値を指定するテンプレートとして機能します。Pythonのすべてのフォーマットオプションと機能をサポートしています。 diff --git a/ja/built-in-nodes/StringLength.mdx b/ja/built-in-nodes/StringLength.mdx index 4633a29ab..589ad1d10 100644 --- a/ja/built-in-nodes/StringLength.mdx +++ b/ja/built-in-nodes/StringLength.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringLength" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がある場合は、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringLength/en.md) StringLengthノードは、テキスト文字列の文字数を計算します。任意のテキスト入力を受け取り、スペースや句読点を含む文字の総数を返します。これは、テキストの長さを測定したり、文字列のサイズ要件を検証したりするのに便利です。 diff --git a/ja/built-in-nodes/StringReplace.mdx b/ja/built-in-nodes/StringReplace.mdx index 32e8dfdab..c02c90efc 100644 --- a/ja/built-in-nodes/StringReplace.mdx +++ b/ja/built-in-nodes/StringReplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringReplace" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がある場合は、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringReplace/en.md) StringReplaceノードは、入力文字列に対してテキスト置換操作を実行します。入力テキスト内で指定された部分文字列を検索し、すべての出現箇所を別の部分文字列に置き換えます。このノードは、すべての置換が適用された変更後の文字列を返します。 diff --git a/ja/built-in-nodes/StringSubstring.mdx b/ja/built-in-nodes/StringSubstring.mdx index 3a79befc9..288371f4e 100644 --- a/ja/built-in-nodes/StringSubstring.mdx +++ b/ja/built-in-nodes/StringSubstring.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringSubstring" icon: "circle" mode: wide --- + ## 概要 StringSubstringノードは、大きな文字列からテキストの一部を抽出します。抽出したい範囲を開始位置と終了位置で指定し、その間のテキストを返します。 diff --git a/ja/built-in-nodes/StringTrim.mdx b/ja/built-in-nodes/StringTrim.mdx index ff01c4863..ab96187c6 100644 --- a/ja/built-in-nodes/StringTrim.mdx +++ b/ja/built-in-nodes/StringTrim.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringTrim" icon: "circle" mode: wide --- + ## 概要 StringTrimノードは、テキスト文字列の先頭、末尾、または両端から空白文字を削除します。左側、右側、または文字列の両側からトリミングするモードを選択できます。不要なスペース、タブ、改行文字を除去してテキスト入力をクリーンアップするのに便利です。 diff --git a/ja/built-in-nodes/StripWhitespace.mdx b/ja/built-in-nodes/StripWhitespace.mdx index 62b769564..31dcaa0db 100644 --- a/ja/built-in-nodes/StripWhitespace.mdx +++ b/ja/built-in-nodes/StripWhitespace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StripWhitespace" icon: "circle" mode: wide --- + このノードは、テキスト文字列の先頭と末尾から余分なスペース、タブ、改行を削除します。テキスト入力を受け取り、先頭と末尾の空白を除去したクリーンなバージョンを返します。 ## 入力 @@ -17,7 +18,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `text` | すべての先頭および末尾の空白文字が除去された処理済みテキスト。 | STRING | +| `テキスト` | すべての先頭および末尾の空白文字が除去された処理済みテキスト。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StripWhitespace/ja.md) diff --git a/ja/built-in-nodes/StyleModelApply.mdx b/ja/built-in-nodes/StyleModelApply.mdx index 14242261b..5066468ba 100644 --- a/ja/built-in-nodes/StyleModelApply.mdx +++ b/ja/built-in-nodes/StyleModelApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StyleModelApply" icon: "circle" mode: wide --- + このノードは、スタイルモデルを指定された条件付け（conditioning）に適用し、CLIPビジョンモデルの出力に基づいてスタイルを強化または変更します。スタイルモデルの条件付けを既存の条件付けに統合することで、生成プロセスにおいてスタイルをシームレスにブレンドすることを可能にします。 ## 入力 diff --git a/ja/built-in-nodes/StyleModelLoader.mdx b/ja/built-in-nodes/StyleModelLoader.mdx index 7814eecd6..3b2089492 100644 --- a/ja/built-in-nodes/StyleModelLoader.mdx +++ b/ja/built-in-nodes/StyleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StyleModelLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/style_models` フォルダ内にあるモデルを検出し、さらに extra_model_paths.yaml ファイルで設定された追加パスからもモデルを読み込みます。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、該当フォルダからモデルファイルを読み取らせる必要があります。 StyleModelLoader ノードは、指定されたパスからスタイルモデルを読み込むために設計されています。このノードは、画像に特定の芸術的なスタイルを適用するために使用できるスタイルモデルを取得および初期化することに特化しており、読み込まれたスタイルモデルに基づいて視覚的な出力をカスタマイズすることを可能にします。 diff --git a/ja/built-in-nodes/SvdImg2vidConditioning.mdx b/ja/built-in-nodes/SvdImg2vidConditioning.mdx index c5bc351aa..21239e985 100644 --- a/ja/built-in-nodes/SvdImg2vidConditioning.mdx +++ b/ja/built-in-nodes/SvdImg2vidConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SvdImg2vidConditioning" icon: "circle" mode: wide --- + このノードは、ビデオ生成タスク用の条件付けデータを生成するために設計されており、特にSVD_img2vidモデルでの使用に最適化されています。初期画像、ビデオパラメータ、VAEモデルなど様々な入力を受け取り、ビデオフレームの生成を導くための条件付けデータを生成します。 ## 入力 diff --git a/ja/built-in-nodes/T5TokenizerOptions.mdx b/ja/built-in-nodes/T5TokenizerOptions.mdx index 5c96cc00d..2107a2edb 100644 --- a/ja/built-in-nodes/T5TokenizerOptions.mdx +++ b/ja/built-in-nodes/T5TokenizerOptions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "T5TokenizerOptions" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/TCFG.mdx b/ja/built-in-nodes/TCFG.mdx index 1bc632ae4..ada9242e4 100644 --- a/ja/built-in-nodes/TCFG.mdx +++ b/ja/built-in-nodes/TCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TCFG" icon: "circle" mode: wide --- + 以下が翻訳結果です。 TCFG（接線減衰CFG）は、サンプリングプロセス中に無条件（ネガティブ）予測を洗練し、条件付き（ポジティブ）予測とより良く整合させる手法です。この技術は、研究論文2503.18137に基づき、無条件ガイダンスに接線減衰を適用することで出力品質を向上させます。このノードは、分類器フリーガイダンス中に無条件予測が処理される方法を調整することで、モデルのサンプリング動作を変更します。 @@ -19,7 +20,7 @@ TCFG（接線減衰CFG）は、サンプリングプロセス中に無条件（ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `patched_model` | 接線減衰CFGが適用された修正済みモデル | MODEL | +| `パッチ適用済みモデル` | 接線減衰CFGが適用された修正済みモデル | MODEL | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TCFG/ja.md) diff --git a/ja/built-in-nodes/TemporalScoreRescaling.mdx b/ja/built-in-nodes/TemporalScoreRescaling.mdx index 27988adc9..36c88ca55 100644 --- a/ja/built-in-nodes/TemporalScoreRescaling.mdx +++ b/ja/built-in-nodes/TemporalScoreRescaling.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TemporalScoreRescaling" icon: "circle" mode: wide --- + このノードは、拡散モデルに Temporal Score Rescaling（TSR）を適用します。ノイズ除去プロセス中に予測されたノイズまたはスコアをリスケーリングすることで、モデルのサンプリング動作を変更し、生成出力の多様性を調整できます。これは、Post-CFG（分類器不要ガイダンス）関数として実装されています。 ## 入力 @@ -19,7 +20,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `patched_model` | 入力モデルに、サンプリングプロセスに Temporal Score Rescaling 関数が適用されたパッチが適用されたものです。 | MODEL | +| `パッチ適用済みモデル` | 入力モデルに、サンプリングプロセスに Temporal Score Rescaling 関数が適用されたパッチが適用されたものです。 | MODEL | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TemporalScoreRescaling/ja.md) diff --git a/ja/built-in-nodes/Tencent3DPartNode.mdx b/ja/built-in-nodes/Tencent3DPartNode.mdx index 66443870e..360bd2052 100644 --- a/ja/built-in-nodes/Tencent3DPartNode.mdx +++ b/ja/built-in-nodes/Tencent3DPartNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Tencent3DPartNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DPartNode/en.md) このノードは、Tencent Hunyuan3D APIを使用して3Dモデルを自動解析し、その構造に基づいてコンポーネントを生成または識別します。モデルを処理し、新しいFBXファイルを返します。 diff --git a/ja/built-in-nodes/Tencent3DTextureEditNode.mdx b/ja/built-in-nodes/Tencent3DTextureEditNode.mdx index a49299fa2..d1d87bfea 100644 --- a/ja/built-in-nodes/Tencent3DTextureEditNode.mdx +++ b/ja/built-in-nodes/Tencent3DTextureEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Tencent3DTextureEditNode" icon: "circle" mode: wide --- + このノードは、Tencent Hunyuan3D API を使用して 3D モデルのテクスチャを編集します。3D モデルと希望する変更内容のテキスト説明を入力すると、プロンプトに従ってテクスチャが再描画された新しいバージョンのモデルが返されます。 ## 入力 @@ -21,8 +22,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `OBJ` | 処理済みの 3D モデル（GLB 形式）。 | FILE3D | -| `texture_image` | 処理済みの 3D モデル（OBJ 形式）。 | FILE3D | +| `GLB` | 処理済みの 3D モデル（GLB 形式）。 | FILE3D | +| `OBJ` | 処理済みの 3D モデル（OBJ 形式）。 | FILE3D | | `texture_image` | 新しく生成された 3D モデル用のテクスチャ画像。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DTextureEditNode/ja.md) diff --git a/ja/built-in-nodes/TencentImageToModelNode.mdx b/ja/built-in-nodes/TencentImageToModelNode.mdx index 03f085f85..fd5fda561 100644 --- a/ja/built-in-nodes/TencentImageToModelNode.mdx +++ b/ja/built-in-nodes/TencentImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentImageToModelNode" icon: "circle" mode: wide --- + このノードは、TencentのHunyuan3D Pro APIを使用して、1つ以上の入力画像から3Dモデルを生成します。画像を処理し、APIに送信して、生成された3DモデルファイルをGLBおよびOBJ形式で、オプションのテクスチャマップとともに返します。 ## 入力 @@ -28,12 +29,12 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `GLB` | 下位互換性のためのレガシー出力です。 | STRING | -| `OBJ` | GLB（Binary GL Transmission Format）ファイル形式で生成された3Dモデルです。 | FILE3DGLB | -| `texture_image` | OBJ（Wavefront）ファイル形式で生成された3Dモデルです。 | FILE3DOBJ | -| `optional_metallic` | 生成された3Dモデルのテクスチャ画像です。 | IMAGE | -| `optional_normal` | PBRマテリアル用のメタリックマップです。利用できない場合は黒画像を返します。 | IMAGE | -| `optional_roughness` | PBRマテリアル用の法線マップです。利用できない場合は黒画像を返します。 | IMAGE | +| `モデルファイル` | 下位互換性のためのレガシー出力です。 | STRING | +| `GLB` | GLB（Binary GL Transmission Format）ファイル形式で生成された3Dモデルです。 | FILE3DGLB | +| `OBJ` | OBJ（Wavefront）ファイル形式で生成された3Dモデルです。 | FILE3DOBJ | +| `texture_image` | 生成された3Dモデルのテクスチャ画像です。 | IMAGE | +| `optional_metallic` | PBRマテリアル用のメタリックマップです。利用できない場合は黒画像を返します。 | IMAGE | +| `optional_normal` | PBRマテリアル用の法線マップです。利用できない場合は黒画像を返します。 | IMAGE | | `optional_roughness` | PBRマテリアル用のラフネスマップです。利用できない場合は黒画像を返します。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentImageToModelNode/ja.md) diff --git a/ja/built-in-nodes/TencentModelTo3DUVNode.mdx b/ja/built-in-nodes/TencentModelTo3DUVNode.mdx index 0353e4166..23ca78675 100644 --- a/ja/built-in-nodes/TencentModelTo3DUVNode.mdx +++ b/ja/built-in-nodes/TencentModelTo3DUVNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentModelTo3DUVNode" icon: "circle" mode: wide --- + このノードは、Tencent Hunyuan3D APIを使用して3DモデルのUV展開を実行します。3Dモデルファイルを入力として受け取り、APIに送信して処理し、処理済みのモデルをOBJおよびFBX形式で、生成されたUVテクスチャ画像とともに返します。入力モデルの面数は30,000未満である必要があります。 ## 入力 @@ -18,9 +19,9 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `FBX` | OBJ形式で処理された3Dモデルファイル。 | FILE3D | -| `uv画像` | FBX形式で処理された3Dモデルファイル。 | FILE3D | -| `uv_image` | 生成されたUVテクスチャ画像。 | IMAGE | +| `OBJ` | OBJ形式で処理された3Dモデルファイル。 | FILE3D | +| `FBX` | FBX形式で処理された3Dモデルファイル。 | FILE3D | +| `uv画像` | 生成されたUVテクスチャ画像。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentModelTo3DUVNode/ja.md) diff --git a/ja/built-in-nodes/TencentSmartTopologyNode.mdx b/ja/built-in-nodes/TencentSmartTopologyNode.mdx index 5c7546f28..c354a9d05 100644 --- a/ja/built-in-nodes/TencentSmartTopologyNode.mdx +++ b/ja/built-in-nodes/TencentSmartTopologyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentSmartTopologyNode" icon: "circle" mode: wide --- + このノードは、3Dモデルに対してスマートリトポロジを実行し、最適化されたポリゴン数の新しいクリーンなメッシュを自動生成します。Tencent Hunyuan 3D APIに接続してモデルを処理し、最大200MBまでのGLBおよびOBJファイル形式に対応しています。処理後のモデルはOBJファイルとして出力されます。 ## 入力 diff --git a/ja/built-in-nodes/TencentTextToModelNode.mdx b/ja/built-in-nodes/TencentTextToModelNode.mdx index 33ca1a534..1a117336f 100644 --- a/ja/built-in-nodes/TencentTextToModelNode.mdx +++ b/ja/built-in-nodes/TencentTextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentTextToModelNode" icon: "circle" mode: wide --- + このノードは、TencentのHunyuan3D Pro APIを使用して、テキスト説明から3Dモデルを生成します。生成タスクを作成するリクエストを送信し、結果をポーリングして、最終的なモデルファイルをGLBおよびOBJ形式でダウンロードします。 ## 入力 @@ -25,9 +26,9 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `GLB` | 後方互換性のためのレガシー出力です。 | STRING | -| `OBJ` | GLBファイル形式で生成された3Dモデルです。 | FILE3DGLB | -| `texture_image` | OBJファイル形式で生成された3Dモデルです。 | FILE3DOBJ | +| `モデルファイル` | 後方互換性のためのレガシー出力です。 | STRING | +| `GLB` | GLBファイル形式で生成された3Dモデルです。 | FILE3DGLB | +| `OBJ` | OBJファイル形式で生成された3Dモデルです。 | FILE3DOBJ | | `texture_image` | 生成されたOBJファイルから抽出されたテクスチャ画像です（利用可能な場合）。 | IMAGE | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentTextToModelNode/ja.md) diff --git a/ja/built-in-nodes/TerminalLog.mdx b/ja/built-in-nodes/TerminalLog.mdx index 303265f01..42dbd22db 100644 --- a/ja/built-in-nodes/TerminalLog.mdx +++ b/ja/built-in-nodes/TerminalLog.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TerminalLog" icon: "circle" mode: wide --- + ## 概要 Terminal Log（Manager）ノードは、主にComfyUIのターミナル上で実行されている情報をComfyUIインターフェース内に表示するために使用されます。使用するには、`mode`を**logging**モードに設定する必要があります。これにより、画像生成タスク中に対応するログ情報を記録できるようになります。`mode`が**stop**モードに設定されている場合、ログ情報は記録されません。 リモート接続やローカルエリアネットワーク接続を介してComfyUIにアクセスして使用する場合、Terminal Log（Manager）ノードは特に有用です。これにより、ComfyUIインターフェース内でCMDからのエラーメッセージを直接表示できるため、ComfyUIの動作状況を把握しやすくなります。 diff --git a/ja/built-in-nodes/TextEncodeAceStepAudio.mdx b/ja/built-in-nodes/TextEncodeAceStepAudio.mdx index 6acc44a8a..18423bb55 100644 --- a/ja/built-in-nodes/TextEncodeAceStepAudio.mdx +++ b/ja/built-in-nodes/TextEncodeAceStepAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeAceStepAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 このドキュメントは AI によって生成されました。誤りを見つけた場合や改善の提案がある場合は、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeAceStepAudio/en.md) diff --git a/ja/built-in-nodes/TextEncodeAceStepAudio1.5.mdx b/ja/built-in-nodes/TextEncodeAceStepAudio1.5.mdx index 89e9918a3..cf1a6ef09 100644 --- a/ja/built-in-nodes/TextEncodeAceStepAudio1.5.mdx +++ b/ja/built-in-nodes/TextEncodeAceStepAudio1.5.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeAceStepAudio1.5" icon: "circle" mode: wide --- + TextEncodeAceStepAudio1.5 ノードは、AceStepAudio 1.5 モデルで使用するためのテキストおよびオーディオ関連のメタデータを準備します。このノードは、説明タグ、歌詞、音楽パラメータを受け取り、CLIP モデルを使用してオーディオ生成に適した条件付け形式に変換します。 ## 入力 diff --git a/ja/built-in-nodes/TextEncodeBooguEdit.mdx b/ja/built-in-nodes/TextEncodeBooguEdit.mdx new file mode 100644 index 000000000..82cf50168 --- /dev/null +++ b/ja/built-in-nodes/TextEncodeBooguEdit.mdx @@ -0,0 +1,31 @@ +--- +title: "TextEncodeBooguEdit - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the TextEncodeBooguEdit node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "TextEncodeBooguEdit" +icon: "circle" +mode: wide +--- + +このノードは、Boogu を使用した画像編集のための conditioning を準備します。参照画像を処理して、ポジティブおよびネガティブの両方の conditioning 出力を作成します。参照画像は2回使用されます。画像からのビジョントークンはポジティブ conditioning にのみ追加され、編集指示を増幅します。一方、VAE 参照潜在変数はポジティブとネガティブの両方の conditioning に追加されるため、CFG 下で相殺され、元の画像の同一性が保持されます。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `clip` | テキストエンコーディングに使用される CLIP モデル | CLIP | はい | | +| `プロンプト` | 目的の編集内容を説明するテキストプロンプト | STRING | はい | | +| `ネガティブプロンプト` | 編集で避けるべき内容を説明するテキストプロンプト | STRING | いいえ | | +| `vae` | 参照画像を潜在空間にエンコードするために使用される VAE モデル | VAE | いいえ | | +| `画像` | 編集する参照画像。Boogu はサンプルごとに1つの参照に焦点を当てますが、複数も許可されます。 | IMAGE | いいえ | 最大16枚 | + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `ポジティブ` | ビジョントークンと参照潜在変数を含むテキストプロンプトの両方を含む conditioning | CONDITIONING | +| `ネガティブ` | ネガティブテキストプロンプトと参照潜在変数を含む conditioning | CONDITIONING | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeBooguEdit/ja.md) + +--- +**Source fingerprint (SHA-256):** `170979acf5b2e9f25f96231a4b23a4376cfddcd4bda2fdd6e03528417e6931b0` diff --git a/ja/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx b/ja/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx index d8bf70e09..c920f346a 100644 --- a/ja/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx +++ b/ja/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeHunyuanVideo_ImageToVideo" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください。[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeHunyuanVideo_ImageToVideo/en.md) TextEncodeHunyuanVideo_ImageToVideo ノードは、テキストプロンプトと画像埋め込みを組み合わせることで、動画生成用の条件付けデータを作成します。CLIPモデルを使用してテキスト入力とCLIPビジョン出力からの視覚情報の両方を処理し、指定された画像インターリーブ設定に従ってこれら2つの情報源を融合したトークンを生成します。 diff --git a/ja/built-in-nodes/TextEncodeQwenImageEdit.mdx b/ja/built-in-nodes/TextEncodeQwenImageEdit.mdx index 2f219b6f4..f813fbbcc 100644 --- a/ja/built-in-nodes/TextEncodeQwenImageEdit.mdx +++ b/ja/built-in-nodes/TextEncodeQwenImageEdit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeQwenImageEdit" icon: "circle" mode: wide --- + 以下が翻訳結果です。 TextEncodeQwenImageEdit ノードは、テキストプロンプトとオプションの画像を処理し、画像生成または編集のための条件付けデータを生成します。CLIP モデルを使用して入力をトークン化し、オプションで VAE を使用して参照画像をエンコードし、参照潜在変数を作成します。画像が提供された場合、一貫した処理寸法を維持するために自動的にリサイズされます。 diff --git a/ja/built-in-nodes/TextEncodeQwenImageEditPlus.mdx b/ja/built-in-nodes/TextEncodeQwenImageEditPlus.mdx index 6cfedb1fb..cc8c4e68b 100644 --- a/ja/built-in-nodes/TextEncodeQwenImageEditPlus.mdx +++ b/ja/built-in-nodes/TextEncodeQwenImageEditPlus.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeQwenImageEditPlus" icon: "circle" mode: wide --- + TextEncodeQwenImageEditPlus ノードは、テキストプロンプトとオプションの画像を処理し、画像生成や編集タスクのための条件付けデータを生成します。このノードは専用のテンプレートを使用して入力画像を分析し、テキスト指示が画像をどのように変更すべきかを理解した上で、その情報をエンコードして後続の生成ステップで使用できるようにします。最大3つの入力画像を処理でき、VAEが提供された場合はオプションで参照用の潜在表現を生成します。 ## 入力 diff --git a/ja/built-in-nodes/TextEncodeZImageOmni.mdx b/ja/built-in-nodes/TextEncodeZImageOmni.mdx index 1e3fdd8b0..eca68dc84 100644 --- a/ja/built-in-nodes/TextEncodeZImageOmni.mdx +++ b/ja/built-in-nodes/TextEncodeZImageOmni.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeZImageOmni" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください。[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeZImageOmni/en.md) TextEncodeZImageOmniノードは、テキストプロンプトとオプションの参照画像を、画像生成モデルに適した条件付け形式にエンコードする高度な条件付けノードです。最大3枚の画像を処理し、オプションでビジョンエンコーダーやVAEを使用して参照潜在表現を生成し、特定のテンプレート構造を用いてこれらの視覚的参照をテキストプロンプトと統合します。 diff --git a/ja/built-in-nodes/TextGenerate.mdx b/ja/built-in-nodes/TextGenerate.mdx index c68511a6b..9e2451f86 100644 --- a/ja/built-in-nodes/TextGenerate.mdx +++ b/ja/built-in-nodes/TextGenerate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextGenerate" icon: "circle" mode: wide --- + TextGenerateノードは、CLIPモデルを使用してユーザーのプロンプトに基づいたテキストを生成します。オプションで画像、動画、音声を追加のコンテキストとして使用し、テキスト生成をガイドすることもできます。出力の長さを制御したり、対応モデルで思考モードを有効にしたり、さまざまな設定でランダムサンプリングを使用するか、サンプリングなしでテキストを生成するかを選択できます。 ## 入力 @@ -34,7 +35,7 @@ TextGenerateノードは、CLIPモデルを使用してユーザーのプロン | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `generated_text` | 入力プロンプトとオプションの画像、動画、または音声に基づいてモデルが生成したテキスト。 | STRING | +| `生成テキスト` | 入力プロンプトとオプションの画像、動画、または音声に基づいてモデルが生成したテキスト。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerate/ja.md) diff --git a/ja/built-in-nodes/TextGenerateLTX2Prompt.mdx b/ja/built-in-nodes/TextGenerateLTX2Prompt.mdx index 269ac5351..636de21bf 100644 --- a/ja/built-in-nodes/TextGenerateLTX2Prompt.mdx +++ b/ja/built-in-nodes/TextGenerateLTX2Prompt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextGenerateLTX2Prompt" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -30,7 +31,7 @@ TextGenerateLTX2Prompt ノードは、テキスト生成ノードの特殊バー | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `output` | 言語モデルによって生成された、拡張または補完されたテキスト文字列です。 | STRING | +| `生成テキスト` | 言語モデルによって生成された、拡張または補完されたテキスト文字列です。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerateLTX2Prompt/ja.md) diff --git a/ja/built-in-nodes/TextToLowercase.mdx b/ja/built-in-nodes/TextToLowercase.mdx index ce305c7ae..d627d89c3 100644 --- a/ja/built-in-nodes/TextToLowercase.mdx +++ b/ja/built-in-nodes/TextToLowercase.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextToLowercase" icon: "circle" mode: wide --- + Text to Lowercaseノードは、入力されたテキスト文字列を受け取り、そのすべての文字を小文字に変換します。テキストの大文字小文字を統一するためのシンプルなユーティリティです。 ## 入力 @@ -17,7 +18,7 @@ Text to Lowercaseノードは、入力されたテキスト文字列を受け取 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `text` | すべての文字が小文字に変換された入力テキスト。 | STRING | +| `テキスト` | すべての文字が小文字に変換された入力テキスト。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToLowercase/ja.md) diff --git a/ja/built-in-nodes/TextToUppercase.mdx b/ja/built-in-nodes/TextToUppercase.mdx index 66c60bb9d..b0a909bca 100644 --- a/ja/built-in-nodes/TextToUppercase.mdx +++ b/ja/built-in-nodes/TextToUppercase.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextToUppercase" icon: "circle" mode: wide --- + このドキュメントはAIが生成しました。誤りや改善の提案があれば、ぜひご連絡ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToUppercase/en.md) Text to Uppercase ノードは、テキスト入力を受け取り、そのすべての文字を大文字に変換します。これは、指定された文字列の大文字小文字を変更するシンプルなテキスト処理ユーティリティです。 @@ -19,7 +20,7 @@ Text to Uppercase ノードは、テキスト入力を受け取り、そのす | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `text` | すべての文字が大文字に変換された結果のテキスト。 | STRING | +| `テキスト` | すべての文字が大文字に変換された結果のテキスト。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToUppercase/ja.md) diff --git a/ja/built-in-nodes/ThresholdMask.mdx b/ja/built-in-nodes/ThresholdMask.mdx index beaf99678..f039665c3 100644 --- a/ja/built-in-nodes/ThresholdMask.mdx +++ b/ja/built-in-nodes/ThresholdMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ThresholdMask" icon: "circle" mode: wide --- + ThresholdMaskノードは、しきい値を適用してマスクをバイナリマスクに変換します。入力マスクの各ピクセルを指定されたしきい値と比較し、しきい値を超えるピクセルは1（白）、しきい値以下のピクセルは0（黒）となる新しいマスクを生成します。 ## 入力 diff --git a/ja/built-in-nodes/TomePatchModel.mdx b/ja/built-in-nodes/TomePatchModel.mdx index 6e46d7317..36b651b6e 100644 --- a/ja/built-in-nodes/TomePatchModel.mdx +++ b/ja/built-in-nodes/TomePatchModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TomePatchModel" icon: "circle" mode: wide --- + 以下が翻訳結果です。 TomePatchModelノードは、トークン統合（ToMe）を拡散モデルに適用し、推論時の計算リソース要件を削減します。このノードは、アテンション機構内で類似したトークンを選択的に統合することで、モデルが処理するトークン数を減らしながら画質を維持します。この手法により、品質を大きく損なうことなく生成を高速化できます。 diff --git a/ja/built-in-nodes/TopazImageEnhance.mdx b/ja/built-in-nodes/TopazImageEnhance.mdx index d94388bf9..62e87d16d 100644 --- a/ja/built-in-nodes/TopazImageEnhance.mdx +++ b/ja/built-in-nodes/TopazImageEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TopazImageEnhance" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/TopazVideoEnhance.mdx b/ja/built-in-nodes/TopazVideoEnhance.mdx index 9b491cc6f..32ed09ba4 100644 --- a/ja/built-in-nodes/TopazVideoEnhance.mdx +++ b/ja/built-in-nodes/TopazVideoEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TopazVideoEnhance" icon: "circle" mode: wide --- + 以下が日本語翻訳です。 このドキュメントは AI によって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazVideoEnhance/en.md) diff --git a/ja/built-in-nodes/TopazVideoEnhanceV2.mdx b/ja/built-in-nodes/TopazVideoEnhanceV2.mdx index 4894af8db..a1382008b 100644 --- a/ja/built-in-nodes/TopazVideoEnhanceV2.mdx +++ b/ja/built-in-nodes/TopazVideoEnhanceV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TopazVideoEnhanceV2" icon: "circle" mode: wide --- + 以下が翻訳結果です。 # Topaz Video Enhance V2 diff --git a/ja/built-in-nodes/TorchCompileModel.mdx b/ja/built-in-nodes/TorchCompileModel.mdx index d82c3db54..ac1d79942 100644 --- a/ja/built-in-nodes/TorchCompileModel.mdx +++ b/ja/built-in-nodes/TorchCompileModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TorchCompileModel" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 TorchCompileModel ノードは、PyTorch のコンパイル機能をモデルに適用し、パフォーマンスを最適化します。入力モデルのコピーを作成し、指定されたバックエンドを使用して PyTorch のコンパイル機能でラップします。これにより、推論時のモデルの実行速度が向上する可能性があります。 diff --git a/ja/built-in-nodes/TrainLoraNode.mdx b/ja/built-in-nodes/TrainLoraNode.mdx index 159cee7e7..43cef988c 100644 --- a/ja/built-in-nodes/TrainLoraNode.mdx +++ b/ja/built-in-nodes/TrainLoraNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrainLoraNode" icon: "circle" mode: wide --- + TrainLoraNodeは、提供された潜在変数と条件付けデータを使用して、拡散モデル上でLoRA（低ランク適応）モデルを作成し、トレーニングします。カスタムトレーニングパラメータ、オプティマイザ、損失関数を使用してモデルをファインチューニングできます。このノードは、トレーニングされたLoRA重み、損失履歴マップ、および完了した総トレーニングステップ数を出力します。 ## 入力 @@ -45,8 +46,8 @@ TrainLoraNodeは、提供された潜在変数と条件付けデータを使用 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `損失マップ` | トレーニングされたLoRA重み。保存したり、他のモデルに適用したりできます。 | LORA_MODEL | -| `ステップ数` | 時間経過に伴うトレーニング損失値を含む辞書。 | LOSS_MAP | +| `lora` | トレーニングされたLoRA重み。保存したり、他のモデルに適用したりできます。 | LORA_MODEL | +| `損失マップ` | 時間経過に伴うトレーニング損失値を含む辞書。 | LOSS_MAP | | `ステップ数` | 完了したトレーニングステップの総数（既存のLoRAからの以前のステップを含む）。 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrainLoraNode/ja.md) diff --git a/ja/built-in-nodes/TransformSplat.mdx b/ja/built-in-nodes/TransformSplat.mdx index d44443850..5229f7859 100644 --- a/ja/built-in-nodes/TransformSplat.mdx +++ b/ja/built-in-nodes/TransformSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TransformSplat" icon: "circle" mode: wide --- -# Transform Splat Transform Splat ノードは、ガウシアンスプラットに対して移動、回転、スケーリングの変換を適用します。スプラット全体を1つのオブジェクトとして移動、回転、リサイズし、不均一なスケーリングが適用された場合には、正確な結果を得るために個々のガウシアンスプラットも再形成します。 diff --git a/ja/built-in-nodes/TrimAudioDuration.mdx b/ja/built-in-nodes/TrimAudioDuration.mdx index 52e39a29f..5eb24e826 100644 --- a/ja/built-in-nodes/TrimAudioDuration.mdx +++ b/ja/built-in-nodes/TrimAudioDuration.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrimAudioDuration" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrimAudioDuration/en.md) TrimAudioDuration ノードを使用すると、オーディオファイルから特定の時間範囲を切り出すことができます。トリミングを開始するタイミングと、結果のオーディオクリップの長さを指定できます。このノードは、時間値をオーディオフレーム位置に変換し、対応するオーディオ波形の部分を抽出することで動作します。 diff --git a/ja/built-in-nodes/TrimVideoLatent.mdx b/ja/built-in-nodes/TrimVideoLatent.mdx index 3e82c7dca..c435eea12 100644 --- a/ja/built-in-nodes/TrimVideoLatent.mdx +++ b/ja/built-in-nodes/TrimVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrimVideoLatent" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/TripleCLIPLoader.mdx b/ja/built-in-nodes/TripleCLIPLoader.mdx index 4177579e0..dea2cb4dc 100644 --- a/ja/built-in-nodes/TripleCLIPLoader.mdx +++ b/ja/built-in-nodes/TripleCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripleCLIPLoader" icon: "circle" mode: wide --- + TripleCLIPLoaderノードは、3つの異なるテキストエンコーダーモデルを同時に読み込み、それらを1つのCLIPモデルに結合します。これは、clip-l、clip-g、t5モデルを連携させるSD3ワークフローなど、複数のテキストエンコーダーが必要な高度なテキストエンコードシナリオで役立ちます。 ## 入力 diff --git a/ja/built-in-nodes/TripoConversionNode.mdx b/ja/built-in-nodes/TripoConversionNode.mdx index 7e325a4e2..9386a78e2 100644 --- a/ja/built-in-nodes/TripoConversionNode.mdx +++ b/ja/built-in-nodes/TripoConversionNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoConversionNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 TripoConversionNode は、Tripo API を使用して 3D モデルを異なるファイル形式に変換します。以前の Tripo 操作（モデル生成、リギング、またはリターゲティング）のタスク ID を受け取り、様々なエクスポートオプションを使用して結果のモデルを目的の形式に変換します。 diff --git a/ja/built-in-nodes/TripoImageToModelNode.mdx b/ja/built-in-nodes/TripoImageToModelNode.mdx index a382aa16e..8d67e9f9c 100644 --- a/ja/built-in-nodes/TripoImageToModelNode.mdx +++ b/ja/built-in-nodes/TripoImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoImageToModelNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Tripo の API を使用して、単一の画像から同期的に 3D モデルを生成します。このノードは入力画像を受け取り、テクスチャ、品質、モデルプロパティに関するさまざまなカスタマイズオプションを使用して 3D モデルに変換します。 @@ -33,8 +34,8 @@ Tripo の API を使用して、単一の画像から同期的に 3D モデル | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデルタスクID` | 生成された 3D モデルファイル（下位互換性のため） | STRING | -| `GLB` | モデル生成プロセスを追跡するためのタスク ID | MODEL_TASK_ID | +| `モデルファイル` | 生成された 3D モデルファイル（下位互換性のため） | STRING | +| `モデルタスクID` | モデル生成プロセスを追跡するためのタスク ID | MODEL_TASK_ID | | `GLB` | GLB 形式で生成された 3D モデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImageToModelNode/ja.md) diff --git a/ja/built-in-nodes/TripoImportModelNode.mdx b/ja/built-in-nodes/TripoImportModelNode.mdx new file mode 100644 index 000000000..ba2398d83 --- /dev/null +++ b/ja/built-in-nodes/TripoImportModelNode.mdx @@ -0,0 +1,28 @@ +--- +title: "TripoImportModelNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the TripoImportModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "TripoImportModelNode" +icon: "circle" +mode: wide +--- + +このノードは、外部の3DモデルファイルをTripoのシステムにインポートし、Texture、Rig、ConvertといったTripoの後処理ノードで使用できるようにします。モデルをアップロードし、他のTripoノードがインポートしたモデルを参照するために使用できるタスクIDを返します。 + +## 入力 + +| パラメータ | 説明 | データ型 | 必須 | 範囲 | +|-----------|-------------|-----------|----------|-------| +| `model_3d` | インポートする3Dモデル（GLB / FBX / OBJ / STL、最大150 MB）。OBJおよびSTLファイルには埋め込みテクスチャは含まれません。 | FILE3D | はい | GLB
FBX
OBJ
STL
任意の3D形式 | + +**注記：** テクスチャはファイルに直接埋め込まれている場合にのみ保持されるため、GLB形式を推奨します。OBJおよびSTLファイルは埋め込みテクスチャをサポートしていません。GLTF（.gltf）形式は外部ファイルを参照するためサポートされておらず、代わりに単一ファイルのGLBを使用してください。 + +## 出力 + +| 出力名 | 説明 | データ型 | +|-------------|-------------|-----------| +| `model task_id` | Tripo後処理ノードで使用するためにインポートされたモデルを識別するタスクID | MODEL_TASK_ID | + +> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImportModelNode/ja.md) + +--- +**Source fingerprint (SHA-256):** `4fa13a108804f2a52190a85b5b5d58ff18190e9d182b556abada444788012fab` diff --git a/ja/built-in-nodes/TripoMultiviewToModelNode.mdx b/ja/built-in-nodes/TripoMultiviewToModelNode.mdx index d492533f6..90d31274b 100644 --- a/ja/built-in-nodes/TripoMultiviewToModelNode.mdx +++ b/ja/built-in-nodes/TripoMultiviewToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoMultiviewToModelNode" icon: "circle" mode: wide --- + このノードは、TripoのAPIを使用して、オブジェクトの異なるビューを示す最大4つの画像を処理し、3Dモデルを同期的に生成します。テクスチャとマテリアルオプションを備えた完全な3Dモデルを作成するには、正面画像と少なくとも1つの追加ビュー（左、背面、または右）が必要です。 ## 入力 @@ -33,8 +34,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデルタスクID` | 生成された3Dモデルのファイルパスまたは識別子（下位互換性のため） | STRING | -| `GLB` | モデル生成プロセスを追跡するためのタスク識別子 | MODEL_TASK_ID | +| `モデルファイル` | 生成された3Dモデルのファイルパスまたは識別子（下位互換性のため） | STRING | +| `モデルタスクID` | モデル生成プロセスを追跡するためのタスク識別子 | MODEL_TASK_ID | | `GLB` | GLB形式で生成された3Dモデルファイル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoMultiviewToModelNode/ja.md) diff --git a/ja/built-in-nodes/TripoP1ImageToModelNode.mdx b/ja/built-in-nodes/TripoP1ImageToModelNode.mdx index 798cc6ce7..3a5895f24 100644 --- a/ja/built-in-nodes/TripoP1ImageToModelNode.mdx +++ b/ja/built-in-nodes/TripoP1ImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoP1ImageToModelNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -28,8 +29,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデルタスクID` | 生成された3Dモデルのファイルパスです。この出力は後方互換性のためにのみ提供されています。 | STRING | -| `GLB` | モデル生成リクエストの一意のタスクIDです。 | MODEL_TASK_ID | +| `モデルファイル` | 生成された3Dモデルのファイルパスです。この出力は後方互換性のためにのみ提供されています。 | STRING | +| `モデルタスクID` | モデル生成リクエストの一意のタスクIDです。 | MODEL_TASK_ID | | `GLB` | GLB形式で生成された3Dモデルです。 | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoP1ImageToModelNode/ja.md) diff --git a/ja/built-in-nodes/TripoP1MultiviewToModelNode.mdx b/ja/built-in-nodes/TripoP1MultiviewToModelNode.mdx index 6aac148eb..d4c3c5509 100644 --- a/ja/built-in-nodes/TripoP1MultiviewToModelNode.mdx +++ b/ja/built-in-nodes/TripoP1MultiviewToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoP1MultiviewToModelNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -32,8 +33,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデルタスクID` | 生成されたGLBモデルのファイル名です（後方互換性のため）。 | STRING | -| `GLB` | このモデル生成リクエストの一意のタスクIDです。 | MODEL_TASK_ID | +| `モデルファイル` | 生成されたGLBモデルのファイル名です（後方互換性のため）。 | STRING | +| `モデルタスクID` | このモデル生成リクエストの一意のタスクIDです。 | MODEL_TASK_ID | | `GLB` | GLB形式で生成された3Dモデルです。 | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoP1MultiviewToModelNode/ja.md) diff --git a/ja/built-in-nodes/TripoP1TextToModelNode.mdx b/ja/built-in-nodes/TripoP1TextToModelNode.mdx index 96089b641..19a51cfd0 100644 --- a/ja/built-in-nodes/TripoP1TextToModelNode.mdx +++ b/ja/built-in-nodes/TripoP1TextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoP1TextToModelNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -29,8 +30,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデルタスクID` | 生成された3Dモデルのファイルパス（後方互換性のため）。 | STRING | -| `GLB` | モデル生成リクエストの一意のタスクID。 | MODEL_TASK_ID | +| `モデルファイル` | 生成された3Dモデルのファイルパス（後方互換性のため）。 | STRING | +| `モデルタスクID` | モデル生成リクエストの一意のタスクID。 | MODEL_TASK_ID | | `GLB` | GLB形式で生成された3Dモデル。 | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoP1TextToModelNode/ja.md) diff --git a/ja/built-in-nodes/TripoRefineNode.mdx b/ja/built-in-nodes/TripoRefineNode.mdx index 269139101..918505bac 100644 --- a/ja/built-in-nodes/TripoRefineNode.mdx +++ b/ja/built-in-nodes/TripoRefineNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoRefineNode" icon: "circle" mode: wide --- + TripoRefineNodeは、特にTripo v1.4モデルによって作成されたドラフト3Dモデルを精緻化します。モデルタスクIDを受け取り、Tripo APIを通じて処理し、改良版のモデルを生成します。このノードは、Tripo v1.4モデルが生成したドラフトモデルでのみ動作するように設計されています。 ## 入力 @@ -19,8 +20,8 @@ TripoRefineNodeは、特にTripo v1.4モデルによって作成されたドラ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデルタスクID` | 精緻化されたモデルのファイルパスまたは参照（後方互換性のため） | STRING | -| `GLB` | 精緻化されたモデル操作のタスク識別子 | MODEL_TASK_ID | +| `モデルファイル` | 精緻化されたモデルのファイルパスまたは参照（後方互換性のため） | STRING | +| `モデルタスクID` | 精緻化されたモデル操作のタスク識別子 | MODEL_TASK_ID | | `GLB` | GLB形式の精緻化された3Dモデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/ja.md) diff --git a/ja/built-in-nodes/TripoRetargetNode.mdx b/ja/built-in-nodes/TripoRetargetNode.mdx index d65fad813..0e9d51374 100644 --- a/ja/built-in-nodes/TripoRetargetNode.mdx +++ b/ja/built-in-nodes/TripoRetargetNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoRetargetNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 TripoRetargetNodeは、モーションデータのリターゲティングにより、3Dキャラクターモデルに定義済みアニメーションを適用します。このノードは、事前にリギングされた3Dモデルを受け取り、いくつかのプリセットアニメーションのうち1つを適用して、アニメーション化された3Dモデルファイルを出力として生成します。このノードはTripo APIと通信して、アニメーションリターゲティング操作を処理します。 @@ -23,8 +24,8 @@ TripoRetargetNodeは、モーションデータのリターゲティングによ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `リターゲット タスクID` | 生成されたアニメーション化3Dモデルファイル（下位互換性のため） | STRING | -| `GLB` | リターゲティング操作を追跡するためのタスクID | RETARGET_TASK_ID | +| `リターゲットタスクID` | 生成されたアニメーション化3Dモデルファイル（下位互換性のため） | STRING | +| `リターゲット タスクID` | リターゲティング操作を追跡するためのタスクID | RETARGET_TASK_ID | | `GLB` | GLB形式のアニメーション化3Dモデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRetargetNode/ja.md) diff --git a/ja/built-in-nodes/TripoRigNode.mdx b/ja/built-in-nodes/TripoRigNode.mdx index d93bb823c..4ccc21ce5 100644 --- a/ja/built-in-nodes/TripoRigNode.mdx +++ b/ja/built-in-nodes/TripoRigNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoRigNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 TripoRigNodeは、元のモデルのタスクIDからリギング済み3Dモデルを生成します。Tripo APIにリクエストを送信し、Tripo仕様に従ってGLB形式のアニメーションリグを作成した後、リグ生成タスクが完了するまでAPIをポーリングします。 @@ -22,8 +23,8 @@ TripoRigNodeは、元のモデルのタスクIDからリギング済み3Dモデ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `リグタスクID` | 生成されたリギング済み3Dモデルファイル（後方互換性のために保持） | STRING | -| `GLB` | リグ生成プロセスを追跡するためのタスクID | RIG_TASK_ID | +| `モデルファイル` | 生成されたリギング済み3Dモデルファイル（後方互換性のために保持） | STRING | +| `リグタスクID` | リグ生成プロセスを追跡するためのタスクID | RIG_TASK_ID | | `GLB` | GLB形式で生成されたリギング済み3Dモデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRigNode/ja.md) diff --git a/ja/built-in-nodes/TripoSplatConditioning.mdx b/ja/built-in-nodes/TripoSplatConditioning.mdx index 39964bc39..04a88fd3d 100644 --- a/ja/built-in-nodes/TripoSplatConditioning.mdx +++ b/ja/built-in-nodes/TripoSplatConditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatConditioning" icon: "circle" mode: wide --- -# TripoSplat Conditioning（コンディショニング） このノードは、DINOv3とFlux2 VAEを使用して入力画像をエンコードし、TripoSplatモデル用のポジティブおよびネガティブなコンディショニングデータを作成します。また、KSamplerの開始点となる固定サイズのノイズターゲット（潜在変数とカメラデータ）も生成します。 @@ -21,8 +20,8 @@ mode: wide | 出力名 | 説明 | データ型 | |-------------|-------------|-----------| -| `ネガティブ` | DINOv3特徴量とFlux2 VAE潜在変数を含むポジティブコンディショニングデータ | CONDITIONING | -| `latent` | ゼロ埋めされたDINOv3特徴量とゼロ埋めされたFlux2 VAE潜在変数を含むネガティブコンディショニングデータ | CONDITIONING | +| `ポジティブ` | DINOv3特徴量とFlux2 VAE潜在変数を含むポジティブコンディショニングデータ | CONDITIONING | +| `ネガティブ` | ゼロ埋めされたDINOv3特徴量とゼロ埋めされたFlux2 VAE潜在変数を含むネガティブコンディショニングデータ | CONDITIONING | | `latent` | KSampler用の固定サイズノイズターゲット（潜在変数シーケンスとカメラトークン） | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoSplatConditioning/ja.md) diff --git a/ja/built-in-nodes/TripoSplatPreprocessImage.mdx b/ja/built-in-nodes/TripoSplatPreprocessImage.mdx index 01844af06..e95f8ff32 100644 --- a/ja/built-in-nodes/TripoSplatPreprocessImage.mdx +++ b/ja/built-in-nodes/TripoSplatPreprocessImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatPreprocessImage" icon: "circle" mode: wide --- -# TripoSplat 画像前処理ノード このノードは、各入力画像を黒背景の中央正方形にクロップし、指定された出力サイズに達するようにパディングを追加します。TripoSplat 3Dモデル用に画像を準備するために設計されており、一貫した正方形フレーミングと、境界アーティファクトを防ぐためのオプションのアルファマット収縮を保証します。 diff --git a/ja/built-in-nodes/TripoSplatSamplingPreview.mdx b/ja/built-in-nodes/TripoSplatSamplingPreview.mdx index f9249878b..b78686560 100644 --- a/ja/built-in-nodes/TripoSplatSamplingPreview.mdx +++ b/ja/built-in-nodes/TripoSplatSamplingPreview.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatSamplingPreview" icon: "circle" mode: wide --- -# TripoSplat サンプリングプレビュー このノードはTripoSplatモデルをパッチ処理し、標準のKSamplerノードで使用した際に、各サンプリングステップでデコードされたガウシアンスプラットのライブプレビューを表示します。サンプラーのコールバックをラップして、各ステップ後にモデルの出力をプレビュー画像にデコードすることで機能します。 diff --git a/ja/built-in-nodes/TripoTextToModelNode.mdx b/ja/built-in-nodes/TripoTextToModelNode.mdx index f84dafee3..b20783b19 100644 --- a/ja/built-in-nodes/TripoTextToModelNode.mdx +++ b/ja/built-in-nodes/TripoTextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoTextToModelNode" icon: "circle" mode: wide --- + TripoのAPIを使用して、テキストプロンプトに基づいて3Dモデルを同期的に生成します。このノードは、テキストの説明を受け取り、オプションのテクスチャとマテリアルプロパティを備えた3Dモデルを作成します。 ## 入力 @@ -31,8 +32,8 @@ TripoのAPIを使用して、テキストプロンプトに基づいて3Dモデ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデルタスクID` | 生成された3Dモデルファイル（下位互換性のため） | STRING | -| `GLB` | モデル生成プロセスの一意のタスク識別子 | MODEL_TASK_ID | +| `モデルファイル` | 生成された3Dモデルファイル（下位互換性のため） | STRING | +| `モデルタスクID` | モデル生成プロセスの一意のタスク識別子 | MODEL_TASK_ID | | `GLB` | GLB形式で生成された3Dモデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextToModelNode/ja.md) diff --git a/ja/built-in-nodes/TripoTextureNode.mdx b/ja/built-in-nodes/TripoTextureNode.mdx index c29e3de99..0270f5365 100644 --- a/ja/built-in-nodes/TripoTextureNode.mdx +++ b/ja/built-in-nodes/TripoTextureNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoTextureNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 TripoTextureNodeは、Tripo APIを使用してテクスチャ付きの3Dモデルを生成します。モデルタスクIDを受け取り、PBRマテリアル、テクスチャ品質設定、およびアライメント方法を含むさまざまなオプションでテクスチャ生成を適用します。このノードはTripo APIと通信してテクスチャ生成リクエストを処理し、結果のモデルファイルとタスクIDを返します。 @@ -26,8 +27,8 @@ TripoTextureNodeは、Tripo APIを使用してテクスチャ付きの3Dモデ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `モデルタスクID` | テクスチャが適用された生成モデルファイル（後方互換性のため） | STRING | -| `GLB` | テクスチャ生成プロセスを追跡するためのタスクID | MODEL_TASK_ID | +| `モデルファイル` | テクスチャが適用された生成モデルファイル（後方互換性のため） | STRING | +| `モデルタスクID` | テクスチャ生成プロセスを追跡するためのタスクID | MODEL_TASK_ID | | `GLB` | テクスチャが適用されたGLB形式の生成3Dモデル | FILE3DGLB | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextureNode/ja.md) diff --git a/ja/built-in-nodes/TruncateText.mdx b/ja/built-in-nodes/TruncateText.mdx index aa50d50db..8db42f9ce 100644 --- a/ja/built-in-nodes/TruncateText.mdx +++ b/ja/built-in-nodes/TruncateText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TruncateText" icon: "circle" mode: wide --- + このノードは、指定された最大長でテキストを切り詰めることで短縮します。任意の入力テキストを受け取り、設定した文字数までの最初の部分のみを返します。テキストが特定のサイズを超えないようにするためのシンプルな方法です。 ## 入力 @@ -18,7 +19,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `string` | 切り詰められたテキスト。入力の最初の`最大長`文字のみを含みます。 | STRING | +| `テキスト` | 切り詰められたテキスト。入力の最初の`最大長`文字のみを含みます。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TruncateText/ja.md) diff --git a/ja/built-in-nodes/UNETLoader.mdx b/ja/built-in-nodes/UNETLoader.mdx index 34a947a8c..3e3d6c24e 100644 --- a/ja/built-in-nodes/UNETLoader.mdx +++ b/ja/built-in-nodes/UNETLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNETLoader" icon: "circle" mode: wide --- + UNETLoaderノードは、U-Netモデルを名前で読み込むために設計されており、システム内で事前学習済みのU-Netアーキテクチャを利用できるようにします。 このノードは、`ComfyUI/models/diffusion_models`フォルダ内にあるモデルを検出します。 diff --git a/ja/built-in-nodes/UNetCrossAttentionMultiply.mdx b/ja/built-in-nodes/UNetCrossAttentionMultiply.mdx index 880832902..713f467e4 100644 --- a/ja/built-in-nodes/UNetCrossAttentionMultiply.mdx +++ b/ja/built-in-nodes/UNetCrossAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetCrossAttentionMultiply" icon: "circle" mode: wide --- + 以下が翻訳結果です。 UNetCrossAttentionMultiply ノードは、UNet モデルのクロスアテンション機構に乗算係数を適用します。クエリ、キー、バリュー、および出力の各コンポーネントをスケーリングすることで、さまざまなアテンション動作や効果を試すことができます。 diff --git a/ja/built-in-nodes/UNetSelfAttentionMultiply.mdx b/ja/built-in-nodes/UNetSelfAttentionMultiply.mdx index 2f453e43b..707f812ea 100644 --- a/ja/built-in-nodes/UNetSelfAttentionMultiply.mdx +++ b/ja/built-in-nodes/UNetSelfAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetSelfAttentionMultiply" icon: "circle" mode: wide --- + UNetSelfAttentionMultiply ノードは、UNet モデル内のセルフアテンション機構におけるクエリ、キー、バリュー、および出力コンポーネントに乗算係数を適用します。アテンション計算の各部分をスケーリングすることで、アテンションの重みがモデルの動作にどのように影響するかを実験できます。 ## 入力 diff --git a/ja/built-in-nodes/UNetTemporalAttentionMultiply.mdx b/ja/built-in-nodes/UNetTemporalAttentionMultiply.mdx index ad7e5cdb2..827e4cac1 100644 --- a/ja/built-in-nodes/UNetTemporalAttentionMultiply.mdx +++ b/ja/built-in-nodes/UNetTemporalAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetTemporalAttentionMultiply" icon: "circle" mode: wide --- + UNetTemporalAttentionMultiplyノードは、時間的UNetモデルにおける異なる種類のアテンションメカニズムに乗算係数を適用します。このノードは、自己アテンションとクロスアテンション層の重みを調整し、構造的要素と時間的要素を区別することでモデルを変更します。これにより、各アテンションタイプがモデルの出力に与える影響の度合いを微調整できます。 ## 入力 diff --git a/ja/built-in-nodes/USOStyleReference.mdx b/ja/built-in-nodes/USOStyleReference.mdx index 7b80bceaa..3449ae527 100644 --- a/ja/built-in-nodes/USOStyleReference.mdx +++ b/ja/built-in-nodes/USOStyleReference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "USOStyleReference" icon: "circle" mode: wide --- + USOStyleReference ノードは、CLIPビジョン出力からエンコードされた画像特徴量を使用して、モデルにスタイル参照パッチを適用します。視覚入力から抽出されたスタイル情報を組み込むことで、入力モデルの修正バージョンを作成し、スタイル転送や参照ベースの生成機能を実現します。 ## 入力 diff --git a/ja/built-in-nodes/UpscaleModelLoader.mdx b/ja/built-in-nodes/UpscaleModelLoader.mdx index 114dc1388..8030f2c24 100644 --- a/ja/built-in-nodes/UpscaleModelLoader.mdx +++ b/ja/built-in-nodes/UpscaleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UpscaleModelLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/upscale_models` フォルダ内のモデルを検出し、さらに extra_model_paths.yaml ファイルで設定された追加パスからもモデルを読み込みます。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、対応するフォルダからモデルファイルを読み取らせる必要があります。 UpscaleModelLoader ノードは、指定されたディレクトリからアップスケールモデルを読み込むために設計されています。このノードは、画像アップスケールタスク用のアップスケールモデルの取得と準備を容易にし、モデルが正しく読み込まれ、評価用に設定されていることを保証します。 diff --git a/ja/built-in-nodes/VAEDecode.mdx b/ja/built-in-nodes/VAEDecode.mdx index 37960bbe9..448f28d55 100644 --- a/ja/built-in-nodes/VAEDecode.mdx +++ b/ja/built-in-nodes/VAEDecode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecode" icon: "circle" mode: wide --- + VAEDecode ノードは、指定された変分オートエンコーダ（VAE）を使用して、潜在表現を画像にデコードするために設計されています。このノードは、圧縮されたデータ表現から画像を生成し、潜在空間エンコーディングから画像を再構築する処理を実現します。 ## 入力 diff --git a/ja/built-in-nodes/VAEDecodeAudio.mdx b/ja/built-in-nodes/VAEDecodeAudio.mdx index b852815b2..acd421827 100644 --- a/ja/built-in-nodes/VAEDecodeAudio.mdx +++ b/ja/built-in-nodes/VAEDecodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeAudio" icon: "circle" mode: wide --- + 以下は、提供された英語ドキュメントの日本語翻訳です。 VAEDecodeAudioノードは、変分オートエンコーダ（VAE）を使用して、潜在表現をオーディオ波形に戻します。エンコードされたオーディオサンプルを受け取り、VAEを通して処理することで元のオーディオを再構築し、正規化を適用して一貫した出力レベルを確保します。結果のオーディオは、標準のサンプルレート44100 Hzで返されます。 diff --git a/ja/built-in-nodes/VAEDecodeAudioTiled.mdx b/ja/built-in-nodes/VAEDecodeAudioTiled.mdx index 55c12d5cf..82aafde82 100644 --- a/ja/built-in-nodes/VAEDecodeAudioTiled.mdx +++ b/ja/built-in-nodes/VAEDecodeAudioTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeAudioTiled" icon: "circle" mode: wide --- + このノードは、Variational Autoencoder（VAE）を使用して、圧縮された音声表現（潜在サンプル）を音声波形に戻します。メモリ使用量を管理するために、データをより小さな重なり合うセクション（タイル）に分割して処理するため、長い音声シーケンスの処理に適しています。 ## 入力 diff --git a/ja/built-in-nodes/VAEDecodeHunyuan3D.mdx b/ja/built-in-nodes/VAEDecodeHunyuan3D.mdx index 6a796e9db..7e20864dc 100644 --- a/ja/built-in-nodes/VAEDecodeHunyuan3D.mdx +++ b/ja/built-in-nodes/VAEDecodeHunyuan3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeHunyuan3D" icon: "circle" mode: wide --- + VAEDecodeHunyuan3D ノードは、VAE デコーダーを使用して潜在表現を 3D ボクセルデータに変換します。設定可能なチャンク数と解像度の設定で、VAE モデルを通じて潜在サンプルを処理し、3D アプリケーションに適したボリュームデータを生成します。 ## 入力 diff --git a/ja/built-in-nodes/VAEDecodeTiled.mdx b/ja/built-in-nodes/VAEDecodeTiled.mdx index a127d17b1..b8707f0d6 100644 --- a/ja/built-in-nodes/VAEDecodeTiled.mdx +++ b/ja/built-in-nodes/VAEDecodeTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeTiled" icon: "circle" mode: wide --- + VAEDecodeTiled ノードは、タイル方式を使用して潜在表現を画像にデコードし、大きな画像を効率的に処理します。メモリ使用量を管理しながら画質を維持するため、入力を小さなタイルに分割して処理します。また、時間的フレームを重複付きのチャンクで処理することで、ビデオVAEにも対応し、スムーズな遷移を実現します。 ## 入力 diff --git a/ja/built-in-nodes/VAEDecodeTripoSplat.mdx b/ja/built-in-nodes/VAEDecodeTripoSplat.mdx index 149aee1e1..5020aab68 100644 --- a/ja/built-in-nodes/VAEDecodeTripoSplat.mdx +++ b/ja/built-in-nodes/VAEDecodeTripoSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VAEDecodeTripoSplat" icon: "circle" mode: wide --- -# VAEDecodeTripoSplat TripoSplatの潜在表現を3Dガウシアンスプラットにデコードします。このノードは、TripoSplatモデルからサンプリングされた潜在表現を受け取り、それを3Dガウシアンの集合として再構築します。生成されるガウシアンの数を変更することで、密度を調整することができます。 diff --git a/ja/built-in-nodes/VAEEncode.mdx b/ja/built-in-nodes/VAEEncode.mdx index b68dc2bcf..eb537432a 100644 --- a/ja/built-in-nodes/VAEEncode.mdx +++ b/ja/built-in-nodes/VAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncode" icon: "circle" mode: wide --- + このノードは、指定されたVAEモデルを使用して画像を潜在空間表現にエンコードするために設計されています。エンコード処理の複雑さを抽象化し、画像をその潜在表現に変換する簡単な方法を提供します。 ## 入力 diff --git a/ja/built-in-nodes/VAEEncodeAudio.mdx b/ja/built-in-nodes/VAEEncodeAudio.mdx index 491597950..d158dc12f 100644 --- a/ja/built-in-nodes/VAEEncodeAudio.mdx +++ b/ja/built-in-nodes/VAEEncodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeAudio" icon: "circle" mode: wide --- + VAEEncodeAudio ノードは、Variational Autoencoder（VAE）を使用してオーディオデータを潜在表現に変換します。オーディオ入力を受け取り、VAE を通して処理することで、さらなるオーディオ生成や操作タスクに使用できる圧縮された潜在サンプルを生成します。このノードは、必要に応じてエンコード前にオーディオを VAE の期待するサンプルレートに自動的にリサンプリングします。 ## 入力 diff --git a/ja/built-in-nodes/VAEEncodeForInpaint.mdx b/ja/built-in-nodes/VAEEncodeForInpaint.mdx index 3e5c654f7..948d00891 100644 --- a/ja/built-in-nodes/VAEEncodeForInpaint.mdx +++ b/ja/built-in-nodes/VAEEncodeForInpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeForInpaint" icon: "circle" mode: wide --- + このノードは、インペイントタスクに適した潜在表現に画像をエンコードするために設計されており、VAEモデルによる最適なエンコードのために入力画像とマスクを調整する追加の前処理手順を組み込んでいます。 ## 入力 diff --git a/ja/built-in-nodes/VAEEncodeTiled.mdx b/ja/built-in-nodes/VAEEncodeTiled.mdx index 3c8865f7c..8253fc864 100644 --- a/ja/built-in-nodes/VAEEncodeTiled.mdx +++ b/ja/built-in-nodes/VAEEncodeTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeTiled" icon: "circle" mode: wide --- + VAEEncodeTiled ノードは、画像を小さなタイルに分割し、変分オートエンコーダ（VAE）を使用してエンコードすることで処理を行います。このタイル分割アプローチにより、メモリ制限を超える可能性のある大きな画像も処理できるようになります。このノードは画像用と動画用の両方のVAEをサポートしており、空間次元と時間次元に対して個別のタイル制御が可能です。 ## 入力 diff --git a/ja/built-in-nodes/VAELoader.mdx b/ja/built-in-nodes/VAELoader.mdx index d577e3f4d..066de4df0 100644 --- a/ja/built-in-nodes/VAELoader.mdx +++ b/ja/built-in-nodes/VAELoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAELoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/vae` フォルダ内に配置されたモデルを検出し、さらに extra_model_paths.yaml ファイルで設定された追加パスからもモデルを読み込みます。場合によっては、**ComfyUI インターフェースを更新（リフレッシュ）** して、対応するフォルダからモデルファイルを読み込ませる必要があります。 VAELoader ノードは、Variational Autoencoder（VAE）モデルを読み込むために設計されており、標準的な VAE と近似 VAE の両方を処理できるように特別に調整されています。名前による VAE の読み込みをサポートし、'taesd' や 'taesdxl' モデルに対する特別な処理を含み、VAE の特定の設定に基づいて動的に調整します。 diff --git a/ja/built-in-nodes/VAESave.mdx b/ja/built-in-nodes/VAESave.mdx index 04485868e..1773d0963 100644 --- a/ja/built-in-nodes/VAESave.mdx +++ b/ja/built-in-nodes/VAESave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAESave" icon: "circle" mode: wide --- + VAESaveノードは、VAEモデルをプロンプトや追加のPNG情報などのメタデータとともに、指定された出力ディレクトリに保存するために設計されています。このノードは、モデルの状態と関連情報をファイルにシリアライズする機能をカプセル化しており、学習済みモデルの保存と共有を容易にします。 ## 入力 diff --git a/ja/built-in-nodes/VOIDInpaintConditioning.mdx b/ja/built-in-nodes/VOIDInpaintConditioning.mdx index 1a21d13d0..6b083609a 100644 --- a/ja/built-in-nodes/VOIDInpaintConditioning.mdx +++ b/ja/built-in-nodes/VOIDInpaintConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDInpaintConditioning" icon: "circle" mode: wide --- + VOIDInpaintConditioning ノードは、CogVideoX モデルでインペインティングを行うために必要な条件付けデータを準備します。ソース動画と前処理済みのクワッドマスクを受け取り、VAE を通じてエンコードし、それらを 32 チャンネルの条件付け信号に結合します。この信号は、モデルがマスク領域を補完するために使用します。 ## 入力 @@ -25,8 +26,8 @@ VOIDInpaintConditioning ノードは、CogVideoX モデルでインペインテ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `negative` | インペインティング潜在情報が追加されたポジティブ条件付け | CONDITIONING | -| `latent` | インペインティング潜在情報が追加されたネガティブ条件付け | CONDITIONING | +| `positive` | インペインティング潜在情報が追加されたポジティブ条件付け | CONDITIONING | +| `negative` | インペインティング潜在情報が追加されたネガティブ条件付け | CONDITIONING | | `latent` | 形状 [batch_size, 16, latent_t, latent_h, latent_w] のゼロ埋めノイズ潜在テンソル | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VOIDInpaintConditioning/ja.md) diff --git a/ja/built-in-nodes/VOIDQuadmaskPreprocess.mdx b/ja/built-in-nodes/VOIDQuadmaskPreprocess.mdx index e0caeb63d..5a85de702 100644 --- a/ja/built-in-nodes/VOIDQuadmaskPreprocess.mdx +++ b/ja/built-in-nodes/VOIDQuadmaskPreprocess.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDQuadmaskPreprocess" icon: "circle" mode: wide --- + ## 概要 VOIDQuadmaskPreprocess ノードは、マスクを特殊な4段階の「クアッドマスク」に変換することで、VOID インペインティング用のマスクを準備します。入力マスクを受け取り、必要に応じて主要領域を膨張させた後、マスク値を4つの異なるレベルに量子化します。これらは異なる意味領域（主要オブジェクト、重なり領域、影響領域、背景）を表します。最後にマスクを反転・正規化し、出力値が [0, 1] の範囲になるようにします。ここで 1.0 は削除する領域、0.0 は保持する領域を示します。 diff --git a/ja/built-in-nodes/VOIDSampler.mdx b/ja/built-in-nodes/VOIDSampler.mdx index a1970a34f..d7315ee1b 100644 --- a/ja/built-in-nodes/VOIDSampler.mdx +++ b/ja/built-in-nodes/VOIDSampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDSampler" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 ## 概要 diff --git a/ja/built-in-nodes/VOIDWarpedNoise.mdx b/ja/built-in-nodes/VOIDWarpedNoise.mdx index a688c7715..6971e5e5f 100644 --- a/ja/built-in-nodes/VOIDWarpedNoise.mdx +++ b/ja/built-in-nodes/VOIDWarpedNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDWarpedNoise" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/VOIDWarpedNoiseSource.mdx b/ja/built-in-nodes/VOIDWarpedNoiseSource.mdx index 34cd05a33..b232c4856 100644 --- a/ja/built-in-nodes/VOIDWarpedNoiseSource.mdx +++ b/ja/built-in-nodes/VOIDWarpedNoiseSource.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDWarpedNoiseSource" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/VPScheduler.mdx b/ja/built-in-nodes/VPScheduler.mdx index f51df7a26..1ad1d1cf7 100644 --- a/ja/built-in-nodes/VPScheduler.mdx +++ b/ja/built-in-nodes/VPScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VPScheduler" icon: "circle" mode: wide --- + VPSchedulerノードは、Variance Preserving（VP）スケジューリング方式に基づいてノイズレベルのシーケンス（シグマ）を生成するように設計されています。このシーケンスは、拡散モデルにおけるノイズ除去プロセスを導くために重要であり、画像やその他のデータタイプの制御された生成を可能にします。 ## 入力 diff --git a/ja/built-in-nodes/Veo3FirstLastFrameNode.mdx b/ja/built-in-nodes/Veo3FirstLastFrameNode.mdx index 1c05b1100..07c5f2348 100644 --- a/ja/built-in-nodes/Veo3FirstLastFrameNode.mdx +++ b/ja/built-in-nodes/Veo3FirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Veo3FirstLastFrameNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善のご提案がございましたら、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3FirstLastFrameNode/en.md) Veo3FirstLastFrameNodeは、GoogleのVeo 3モデルを使用して、テキストプロンプトに基づき、動画シーケンスの開始と終了を定義する最初と最後のフレームを指定して動画を生成します。 diff --git a/ja/built-in-nodes/Veo3VideoGenerationNode.mdx b/ja/built-in-nodes/Veo3VideoGenerationNode.mdx index f6a5fe652..59fddbf64 100644 --- a/ja/built-in-nodes/Veo3VideoGenerationNode.mdx +++ b/ja/built-in-nodes/Veo3VideoGenerationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Veo3VideoGenerationNode" icon: "circle" mode: wide --- + ## 概要 GoogleのVeo 3 APIを使用して、テキストプロンプトから動画を生成します。このノードは高速版や軽量版を含む複数のVeo 3モデルをサポートしており、動画の解像度、長さ、音声生成を指定できます。 diff --git a/ja/built-in-nodes/VeoVideoGenerationNode.mdx b/ja/built-in-nodes/VeoVideoGenerationNode.mdx index 9edb74027..8a27ab076 100644 --- a/ja/built-in-nodes/VeoVideoGenerationNode.mdx +++ b/ja/built-in-nodes/VeoVideoGenerationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VeoVideoGenerationNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 GoogleのVeo 2 APIを使用して、テキストプロンプトから動画を生成します。このノードは、テキスト説明とオプションの画像入力から動画を作成し、アスペクト比や再生時間などのパラメータを制御できます。 diff --git a/ja/built-in-nodes/Video Slice.mdx b/ja/built-in-nodes/Video Slice.mdx index 7f52e08ee..220abe1f8 100644 --- a/ja/built-in-nodes/Video Slice.mdx +++ b/ja/built-in-nodes/Video Slice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Video Slice" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- diff --git a/ja/built-in-nodes/VideoLinearCFGGuidance.mdx b/ja/built-in-nodes/VideoLinearCFGGuidance.mdx index 046a1ce49..ab2ed0ddb 100644 --- a/ja/built-in-nodes/VideoLinearCFGGuidance.mdx +++ b/ja/built-in-nodes/VideoLinearCFGGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VideoLinearCFGGuidance" icon: "circle" mode: wide --- + VideoLinearCFGGuidance ノードは、ビデオモデルに線形条件付きガイダンススケールを適用し、指定された範囲にわたって条件付き成分と無条件成分の影響を調整します。これにより、生成プロセスを動的に制御し、所望の条件付けレベルに基づいてモデルの出力を微調整することが可能になります。 ## 入力 diff --git a/ja/built-in-nodes/VideoTriangleCFGGuidance.mdx b/ja/built-in-nodes/VideoTriangleCFGGuidance.mdx index 8d820ea7f..20b17b53e 100644 --- a/ja/built-in-nodes/VideoTriangleCFGGuidance.mdx +++ b/ja/built-in-nodes/VideoTriangleCFGGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VideoTriangleCFGGuidance" icon: "circle" mode: wide --- + 以下が日本語翻訳です。 VideoTriangleCFGGuidance ノードは、ビデオモデルに三角波状の分類器フリーガイダンス（CFG）スケーリングパターンを適用します。最小CFG値と元の条件付けスケールの間を振動する三角波関数を用いて、時間経過に伴い条件付けスケールを変化させます。これにより動的なガイダンスパターンが生成され、ビデオ生成の一貫性と品質向上に役立ちます。 diff --git a/ja/built-in-nodes/Vidu2ImageToVideoNode.mdx b/ja/built-in-nodes/Vidu2ImageToVideoNode.mdx index 98d7bf12d..fd88d5a24 100644 --- a/ja/built-in-nodes/Vidu2ImageToVideoNode.mdx +++ b/ja/built-in-nodes/Vidu2ImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2ImageToVideoNode" icon: "circle" mode: wide --- + ## 概要 Vidu2 画像から動画への生成ノードは、1枚の入力画像から動画シーケンスを作成します。指定されたVidu2モデルを使用し、オプションのテキストプロンプトに基づいてシーンをアニメーション化し、動画の長さ、解像度、および動きの強度を制御します。 diff --git a/ja/built-in-nodes/Vidu2ReferenceVideoNode.mdx b/ja/built-in-nodes/Vidu2ReferenceVideoNode.mdx index 718e0eecc..99876dae5 100644 --- a/ja/built-in-nodes/Vidu2ReferenceVideoNode.mdx +++ b/ja/built-in-nodes/Vidu2ReferenceVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2ReferenceVideoNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2ReferenceVideoNode/en.md) Vidu2 参照動画生成ノードは、テキストプロンプトと複数の参照画像から動画を生成します。最大7つの被写体を定義でき、各被写体に独自の参照画像セットを設定できます。プロンプト内では `@subject{subject_id}` を使用して被写体を参照します。このノードは、再生時間、アスペクト比、動きの大きさを設定可能な動画を生成します。 diff --git a/ja/built-in-nodes/Vidu2StartEndToVideoNode.mdx b/ja/built-in-nodes/Vidu2StartEndToVideoNode.mdx index ab95f7d5b..1e941076b 100644 --- a/ja/built-in-nodes/Vidu2StartEndToVideoNode.mdx +++ b/ja/built-in-nodes/Vidu2StartEndToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2StartEndToVideoNode" icon: "circle" mode: wide --- + このノードは、提供された開始フレームと終了フレームの間を補間し、テキストプロンプトに従ってビデオを生成します。指定されたViduモデルを使用して、設定された時間にわたって2つの画像間のスムーズな遷移を作成します。 ## 入力 diff --git a/ja/built-in-nodes/Vidu2TextToVideoNode.mdx b/ja/built-in-nodes/Vidu2TextToVideoNode.mdx index 37edd0fbe..a48ce2632 100644 --- a/ja/built-in-nodes/Vidu2TextToVideoNode.mdx +++ b/ja/built-in-nodes/Vidu2TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2TextToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/Vidu3ImageToVideoNode.mdx b/ja/built-in-nodes/Vidu3ImageToVideoNode.mdx index c5d1ea109..392088012 100644 --- a/ja/built-in-nodes/Vidu3ImageToVideoNode.mdx +++ b/ja/built-in-nodes/Vidu3ImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3ImageToVideoNode" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3ImageToVideoNode/en.md) Vidu Q3 画像から動画への生成ノードは、入力画像から動画シーケンスを作成します。Vidu Q3 モデルを使用して画像をアニメーション化し、必要に応じてテキストプロンプトでガイドし、動画ファイルを出力します。 diff --git a/ja/built-in-nodes/Vidu3StartEndToVideoNode.mdx b/ja/built-in-nodes/Vidu3StartEndToVideoNode.mdx index beadc9868..c3f80416f 100644 --- a/ja/built-in-nodes/Vidu3StartEndToVideoNode.mdx +++ b/ja/built-in-nodes/Vidu3StartEndToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3StartEndToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 このノードは、開始フレームと終了フレームの間を補間し、テキストプロンプトに従ってビデオを生成します。Vidu Q3モデルを使用して2つの画像間のシームレスな遷移を作成し、指定された長さと解像度のビデオを生成します。 diff --git a/ja/built-in-nodes/Vidu3TextToVideoNode.mdx b/ja/built-in-nodes/Vidu3TextToVideoNode.mdx index 62bcac3af..53a982477 100644 --- a/ja/built-in-nodes/Vidu3TextToVideoNode.mdx +++ b/ja/built-in-nodes/Vidu3TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3TextToVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/ViduExtendVideoNode.mdx b/ja/built-in-nodes/ViduExtendVideoNode.mdx index 2df4f25ff..bde086b89 100644 --- a/ja/built-in-nodes/ViduExtendVideoNode.mdx +++ b/ja/built-in-nodes/ViduExtendVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduExtendVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ViduExtendVideoNode は、既存の動画にフレームを追加して長さを延長します。指定された AI モデルを使用し、ソース動画とオプションのテキストプロンプトに基づいて、シームレスな続きを生成します。 diff --git a/ja/built-in-nodes/ViduImageToVideoNode.mdx b/ja/built-in-nodes/ViduImageToVideoNode.mdx index 9e51e83e3..dfc397a55 100644 --- a/ja/built-in-nodes/ViduImageToVideoNode.mdx +++ b/ja/built-in-nodes/ViduImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduImageToVideoNode" icon: "circle" mode: wide --- + Vidu 画像動画生成ノードは、開始画像とオプションのテキスト説明から短い動画を生成します。AIモデルを使用して、提供された画像フレームから続く動画コンテンツを生成し、結果の動画を返します。 ## 入力 diff --git a/ja/built-in-nodes/ViduMultiFrameVideoNode.mdx b/ja/built-in-nodes/ViduMultiFrameVideoNode.mdx index 8bad59956..36312ea9a 100644 --- a/ja/built-in-nodes/ViduMultiFrameVideoNode.mdx +++ b/ja/built-in-nodes/ViduMultiFrameVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduMultiFrameVideoNode" icon: "circle" mode: wide --- + このノードは、複数のキーフレーム間のトランジションを生成して動画を作成します。初期画像から開始し、ユーザーが定義した一連の終了画像とプロンプトを通じてアニメーションを生成し、単一の動画ファイルを出力します。 ## 入力 diff --git a/ja/built-in-nodes/ViduReferenceVideoNode.mdx b/ja/built-in-nodes/ViduReferenceVideoNode.mdx index cb3802866..6b1722181 100644 --- a/ja/built-in-nodes/ViduReferenceVideoNode.mdx +++ b/ja/built-in-nodes/ViduReferenceVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduReferenceVideoNode" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/ViduStartEndToVideoNode.mdx b/ja/built-in-nodes/ViduStartEndToVideoNode.mdx index 68796fe8e..31d77d75b 100644 --- a/ja/built-in-nodes/ViduStartEndToVideoNode.mdx +++ b/ja/built-in-nodes/ViduStartEndToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduStartEndToVideoNode" icon: "circle" mode: wide --- + 以下、ご依頼いただいた内容を翻訳ルールに従い日本語に翻訳いたします。 > このドキュメントはAIによって生成されました。誤りや改善のためのご提案がございましたら、ぜひご貢献ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduStartEndToVideoNode/en.md) diff --git a/ja/built-in-nodes/ViduTextToVideoNode.mdx b/ja/built-in-nodes/ViduTextToVideoNode.mdx index 257864e0a..6463257ed 100644 --- a/ja/built-in-nodes/ViduTextToVideoNode.mdx +++ b/ja/built-in-nodes/ViduTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduTextToVideoNode" icon: "circle" mode: wide --- + 以下は、ご依頼いただいた英語ドキュメントを日本語に翻訳したものです。 --- diff --git a/ja/built-in-nodes/VoxelToMesh.mdx b/ja/built-in-nodes/VoxelToMesh.mdx index 9ab742c36..1bbb7ea27 100644 --- a/ja/built-in-nodes/VoxelToMesh.mdx +++ b/ja/built-in-nodes/VoxelToMesh.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VoxelToMesh" icon: "circle" mode: wide --- + 以下が翻訳結果です。 VoxelToMeshBasic ノードは、指定されたしきい値で表面を抽出することにより、3D ボクセルデータをメッシュジオメトリに変換します。入力内の各ボクセルグリッドを処理し、3D メッシュ表現を構成する頂点と面を生成します。 diff --git a/ja/built-in-nodes/VoxelToMeshBasic.mdx b/ja/built-in-nodes/VoxelToMeshBasic.mdx index 202d67ab2..6c13313e4 100644 --- a/ja/built-in-nodes/VoxelToMeshBasic.mdx +++ b/ja/built-in-nodes/VoxelToMeshBasic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VoxelToMeshBasic" icon: "circle" mode: wide --- + 以下が翻訳です。 VoxelToMeshBasic ノードは、3D ボクセルデータをメッシュジオメトリに変換します。ボクセルボリュームにしきい値を適用し、ボリュームのどの部分が結果のメッシュでソリッドサーフェスになるかを決定します。このノードは、3D レンダリングやモデリングに使用できる、頂点と面を含む完全なメッシュ構造を出力します。 diff --git a/ja/built-in-nodes/Wan22FunControlToVideo.mdx b/ja/built-in-nodes/Wan22FunControlToVideo.mdx index 818161bd6..f41e1f061 100644 --- a/ja/built-in-nodes/Wan22FunControlToVideo.mdx +++ b/ja/built-in-nodes/Wan22FunControlToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan22FunControlToVideo" icon: "circle" mode: wide --- + このドキュメントはAIによって生成されました。誤りや改善の提案がありましたら、ぜひご貢献ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22FunControlToVideo/en.md) Wan22FunControlToVideo ノードは、Wan ビデオモデルアーキテクチャを使用してビデオ生成のための条件付けと潜在表現を準備します。ポジティブおよびネガティブな条件付け入力と、オプションの参照画像および制御ビデオを処理し、ビデオ合成に必要な潜在空間表現を作成します。このノードは、空間スケーリングと時間次元を処理して、ビデオモデルに適した条件付けデータを生成します。 @@ -29,9 +30,9 @@ Wan22FunControlToVideo ノードは、Wan ビデオモデルアーキテクチ | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 連結潜在変数、マスク、およびオプションの参照潜在変数を含む、ビデオ固有の潜在データで変更されたポジティブ条件付け | CONDITIONING | -| `潜在変数` | 連結潜在変数、マスク、およびオプションの参照潜在変数を含む、ビデオ固有の潜在データで変更されたネガティブ条件付け | CONDITIONING | -| `latent` | バッチサイズ、潜在チャンネル数、および空間/時間スケーリングに基づいて、ビデオ生成に適した次元を持つ空の潜在テンソル | LATENT | +| `ポジティブ` | 連結潜在変数、マスク、およびオプションの参照潜在変数を含む、ビデオ固有の潜在データで変更されたポジティブ条件付け | CONDITIONING | +| `ネガティブ` | 連結潜在変数、マスク、およびオプションの参照潜在変数を含む、ビデオ固有の潜在データで変更されたネガティブ条件付け | CONDITIONING | +| `潜在変数` | バッチサイズ、潜在チャンネル数、および空間/時間スケーリングに基づいて、ビデオ生成に適した次元を持つ空の潜在テンソル | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22FunControlToVideo/ja.md) diff --git a/ja/built-in-nodes/Wan22ImageToVideoLatent.mdx b/ja/built-in-nodes/Wan22ImageToVideoLatent.mdx index 02a5c53f9..5200fc2bc 100644 --- a/ja/built-in-nodes/Wan22ImageToVideoLatent.mdx +++ b/ja/built-in-nodes/Wan22ImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan22ImageToVideoLatent" icon: "circle" mode: wide --- + このドキュメントは AI によって生成されました。誤りや改善の提案がありましたら、ぜひご協力ください！ [GitHub で編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22ImageToVideoLatent/en.md) **Wan22ImageToVideoLatent** ノードは、画像からビデオの潜在表現を生成します。指定された寸法で空白のビデオ潜在空間を作成し、オプションで開始画像シーケンスを先頭フレームにエンコードできます。開始画像が提供されると、画像を潜在空間にエンコードし、インペイント領域に対応するノイズマスクを生成します。 diff --git a/ja/built-in-nodes/Wan2ImageToVideoApi.mdx b/ja/built-in-nodes/Wan2ImageToVideoApi.mdx index 432a08980..838e4dc89 100644 --- a/ja/built-in-nodes/Wan2ImageToVideoApi.mdx +++ b/ja/built-in-nodes/Wan2ImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2ImageToVideoApi" icon: "circle" mode: wide --- + 以下が翻訳です。 Wan 2.7 Image to Video ノードは、最初のフレーム画像から動画を生成します。オプションで最終フレーム画像を指定して2つのフレーム間の遷移を作成したり、オーディオファイルを指定して動画の動きやタイミングをガイドすることもできます。このノードは、テキストによる説明に基づいてシーンをアニメーション化するためにAIモデルを使用します。 diff --git a/ja/built-in-nodes/Wan2ReferenceVideoApi.mdx b/ja/built-in-nodes/Wan2ReferenceVideoApi.mdx index 22610288d..2fc224126 100644 --- a/ja/built-in-nodes/Wan2ReferenceVideoApi.mdx +++ b/ja/built-in-nodes/Wan2ReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2ReferenceVideoApi" icon: "circle" mode: wide --- + このノードは、提供された参照素材に基づいて、人物やオブジェクトを特徴とする動画を生成します。Wan 2.7モデルを使用してテキストプロンプトから動画を作成し、単一キャラクターのパフォーマンスや複数キャラクターのインタラクションをサポートします。生成を機能させるには、少なくとも1つの参照動画または画像を提供する必要があります。 ## 入力 diff --git a/ja/built-in-nodes/Wan2TextToVideoApi.mdx b/ja/built-in-nodes/Wan2TextToVideoApi.mdx index 37a7b67d8..ff661b4c4 100644 --- a/ja/built-in-nodes/Wan2TextToVideoApi.mdx +++ b/ja/built-in-nodes/Wan2TextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2TextToVideoApi" icon: "circle" mode: wide --- + このノードは、Wan 2.7モデルを使用してテキスト記述から動画を生成します。リクエストを外部APIに送信し、プロンプトを処理して動画ファイルを返します。必要に応じて、動画の動きやタイミングに影響を与えるオーディオクリップを提供することもできます。 ## 入力 diff --git a/ja/built-in-nodes/Wan2VideoContinuationApi.mdx b/ja/built-in-nodes/Wan2VideoContinuationApi.mdx index c99b1a2cd..9fcb87acb 100644 --- a/ja/built-in-nodes/Wan2VideoContinuationApi.mdx +++ b/ja/built-in-nodes/Wan2VideoContinuationApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2VideoContinuationApi" icon: "circle" mode: wide --- + 以下は、指定された英語ドキュメントを日本語に翻訳したものです。 --- diff --git a/ja/built-in-nodes/Wan2VideoEditApi.mdx b/ja/built-in-nodes/Wan2VideoEditApi.mdx index 172cdc731..76fcb06f7 100644 --- a/ja/built-in-nodes/Wan2VideoEditApi.mdx +++ b/ja/built-in-nodes/Wan2VideoEditApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2VideoEditApi" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Wan2VideoEditApi ノードは、Wan 2.7 モデルを使用して、テキスト指示、参照画像、またはスタイル転送に基づいて動画を編集します。入力動画を処理し、解像度、長さ、アスペクト比などの指定されたパラメータに従って新しい動画を生成します。 diff --git a/ja/built-in-nodes/WanAnimateToVideo.mdx b/ja/built-in-nodes/WanAnimateToVideo.mdx index 5fd85f104..055fa4a45 100644 --- a/ja/built-in-nodes/WanAnimateToVideo.mdx +++ b/ja/built-in-nodes/WanAnimateToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanAnimateToVideo" icon: "circle" mode: wide --- + WanAnimateToVideo ノードは、ポーズ参照、表情、背景要素を含む複数の条件付け入力を組み合わせてビデオコンテンツを生成します。様々なビデオ入力を処理して、フレーム間の時間的一貫性を維持しながら、一貫性のあるアニメーションシーケンスを作成します。このノードは潜在空間の操作を処理し、モーションパターンを継続することで既存のビデオを拡張することもできます。 ## 入力 @@ -43,11 +44,11 @@ WanAnimateToVideo ノードは、ポーズ参照、表情、背景要素を含 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | CLIPビジョン出力、ポーズビデオ潜在、顔ビデオピクセル、連結された潜在画像、連結されたマスクを含む追加のビデオコンテキストを持つ修正済みポジティブ条件付け | CONDITIONING | -| `潜在変数` | CLIPビジョン出力、ポーズビデオ潜在、顔ビデオピクセル（反転）、連結された潜在画像、連結されたマスクを含む追加のビデオコンテキストを持つ修正済みネガティブ条件付け | CONDITIONING | -| `トリム潜在変数` | 形状 [batch_size, 16, latent_length + trim_latent, latent_height, latent_width] の潜在空間形式で生成されたビデオコンテンツ | LATENT | -| `トリム画像` | 先頭からトリミングする潜在フレーム数を示す潜在空間トリミング情報（参照画像の潜在フレームに対応） | INT | -| `動画フレームオフセット` | 参照モーションフレームの画像空間トリミング情報。先頭からトリミングする画像フレーム数を示します | INT | +| `ポジティブ` | CLIPビジョン出力、ポーズビデオ潜在、顔ビデオピクセル、連結された潜在画像、連結されたマスクを含む追加のビデオコンテキストを持つ修正済みポジティブ条件付け | CONDITIONING | +| `ネガティブ` | CLIPビジョン出力、ポーズビデオ潜在、顔ビデオピクセル（反転）、連結された潜在画像、連結されたマスクを含む追加のビデオコンテキストを持つ修正済みネガティブ条件付け | CONDITIONING | +| `潜在変数` | 形状 [batch_size, 16, latent_length + trim_latent, latent_height, latent_width] の潜在空間形式で生成されたビデオコンテンツ | LATENT | +| `トリム潜在変数` | 先頭からトリミングする潜在フレーム数を示す潜在空間トリミング情報（参照画像の潜在フレームに対応） | INT | +| `トリム画像` | 参照モーションフレームの画像空間トリミング情報。先頭からトリミングする画像フレーム数を示します | INT | | `動画フレームオフセット` | チャンク単位でビデオ生成を継続するための更新されたフレームオフセット。以前のオフセットに生成された長さを加算して計算されます | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanAnimateToVideo/ja.md) diff --git a/ja/built-in-nodes/WanCameraEmbedding.mdx b/ja/built-in-nodes/WanCameraEmbedding.mdx index 7139ba69a..f480bd3a7 100644 --- a/ja/built-in-nodes/WanCameraEmbedding.mdx +++ b/ja/built-in-nodes/WanCameraEmbedding.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanCameraEmbedding" icon: "circle" mode: wide --- + 以下が翻訳結果です。 WanCameraEmbedding ノードは、カメラモーションパラメータに基づいてプレッカー埋め込みを使用し、カメラ軌跡の埋め込みを生成します。さまざまなカメラの動きをシミュレートする一連のカメラポーズを作成し、動画生成パイプラインに適した埋め込みテンソルに変換します。 @@ -27,9 +28,9 @@ WanCameraEmbedding ノードは、カメラモーションパラメータに基 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `幅` | 軌跡シーケンスを含む、生成されたカメラ埋め込みテンソル | TENSOR | -| `高さ` | 処理に使用された幅の値 | INT | -| `長さ` | 処理に使用された高さの値 | INT | +| `カメラ埋め込み` | 軌跡シーケンスを含む、生成されたカメラ埋め込みテンソル | TENSOR | +| `幅` | 処理に使用された幅の値 | INT | +| `高さ` | 処理に使用された高さの値 | INT | | `長さ` | 処理に使用された長さの値 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraEmbedding/ja.md) diff --git a/ja/built-in-nodes/WanCameraImageToVideo.mdx b/ja/built-in-nodes/WanCameraImageToVideo.mdx index 844397ea0..646e3728c 100644 --- a/ja/built-in-nodes/WanCameraImageToVideo.mdx +++ b/ja/built-in-nodes/WanCameraImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanCameraImageToVideo" icon: "circle" mode: wide --- + WanCameraImageToVideo ノードは、画像を動画シーケンスに変換するために、潜在表現を生成します。このノードは、条件付け入力とオプションの開始画像を処理し、動画モデルで使用可能な動画潜在表現を作成します。カメラ条件とクリップビジョン出力をサポートし、動画生成の制御を強化します。 ## 入力 @@ -28,9 +29,9 @@ WanCameraImageToVideo ノードは、画像を動画シーケンスに変換す | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | カメラ条件とクリップビジョン出力が適用された、変更後のポジティブ条件付け | CONDITIONING | -| `潜在変数` | カメラ条件とクリップビジョン出力が適用された、変更後のネガティブ条件付け | CONDITIONING | -| `latent` | 動画モデルで使用するために生成された動画潜在表現。潜在テンソルの次元は [batch_size, 16, frames, height/8, width/8] です。ここで frames は ((length - 1) // 4) + 1 として計算されます。 | LATENT | +| `ポジティブ` | カメラ条件とクリップビジョン出力が適用された、変更後のポジティブ条件付け | CONDITIONING | +| `ネガティブ` | カメラ条件とクリップビジョン出力が適用された、変更後のネガティブ条件付け | CONDITIONING | +| `潜在変数` | 動画モデルで使用するために生成された動画潜在表現。潜在テンソルの次元は [batch_size, 16, frames, height/8, width/8] です。ここで frames は ((length - 1) // 4) + 1 として計算されます。 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraImageToVideo/ja.md) diff --git a/ja/built-in-nodes/WanContextWindowsManual.mdx b/ja/built-in-nodes/WanContextWindowsManual.mdx index 9aae69626..e2d0843dc 100644 --- a/ja/built-in-nodes/WanContextWindowsManual.mdx +++ b/ja/built-in-nodes/WanContextWindowsManual.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanContextWindowsManual" icon: "circle" mode: wide --- + 以下が日本語訳です。 WAN Context Windows (Manual) ノードを使用すると、2次元処理を行うWAN系モデル向けにコンテキストウィンドウを手動で設定できます。サンプリング中に、ウィンドウの長さ、オーバーラップ、スケジューリング方法、フュージョン手法を指定することで、カスタムのコンテキストウィンドウ設定を適用します。これにより、モデルが異なるコンテキスト領域間で情報を処理する方法を正確に制御できます。 diff --git a/ja/built-in-nodes/WanDancerEncodeAudio.mdx b/ja/built-in-nodes/WanDancerEncodeAudio.mdx index 60d67ba55..c2d9cd66d 100644 --- a/ja/built-in-nodes/WanDancerEncodeAudio.mdx +++ b/ja/built-in-nodes/WanDancerEncodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerEncodeAudio" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -23,7 +24,7 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `fps_string` | 処理済みの音声特徴量、計算されたフレームレート（fps）、および音声注入スケールを含む辞書です。この出力は動画生成モデルの条件付けに使用されます。 | AUDIO_ENCODER_OUTPUT | +| `audio_encoder_output` | 処理済みの音声特徴量、計算されたフレームレート（fps）、および音声注入スケールを含む辞書です。この出力は動画生成モデルの条件付けに使用されます。 | AUDIO_ENCODER_OUTPUT | | `fps_string` | 音声の長さと動画のフレーム数に基づいて計算されたフレームレート（fps）を説明するテキスト文字列です。この文字列は動画モデルのプロンプトで使用することを目的としています。 | STRING | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerEncodeAudio/ja.md) diff --git a/ja/built-in-nodes/WanDancerPadKeyframes.mdx b/ja/built-in-nodes/WanDancerPadKeyframes.mdx index 2ec48a8b9..7c2934bb2 100644 --- a/ja/built-in-nodes/WanDancerPadKeyframes.mdx +++ b/ja/built-in-nodes/WanDancerPadKeyframes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerPadKeyframes" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -24,8 +25,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `keyframes_mask` | 指定されたセグメント用にパディングされたキーフレームシーケンス。 | IMAGE | -| `audio_segment` | 有効フレームを示すマスク（キーフレーム位置は1、パディング位置は0）。 | MASK | +| `keyframes_sequence` | 指定されたセグメント用にパディングされたキーフレームシーケンス。 | IMAGE | +| `keyframes_mask` | 有効フレームを示すマスク（キーフレーム位置は1、パディング位置は0）。 | MASK | | `audio_segment` | この動画セグメントに対応するオーディオセグメント。 | AUDIO | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerPadKeyframes/ja.md) diff --git a/ja/built-in-nodes/WanDancerPadKeyframesList.mdx b/ja/built-in-nodes/WanDancerPadKeyframesList.mdx index 9dc107d28..03e8610d4 100644 --- a/ja/built-in-nodes/WanDancerPadKeyframesList.mdx +++ b/ja/built-in-nodes/WanDancerPadKeyframesList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerPadKeyframesList" icon: "circle" mode: wide --- + 以下は、指定されたルールに従って翻訳した日本語版ドキュメントです。 --- @@ -26,8 +27,8 @@ mode: wide | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `keyframes_mask` | 各セグメントに対応するパディング済みキーフレームシーケンスのリスト。 | IMAGE | -| `audio_segment` | 各セグメントの有効なフレームを示すマスクのリスト。 | MASK | +| `keyframes_sequence` | 各セグメントに対応するパディング済みキーフレームシーケンスのリスト。 | IMAGE | +| `keyframes_mask` | 各セグメントの有効なフレームを示すマスクのリスト。 | MASK | | `audio_segment` | 各動画セグメントに対応するオーディオセグメントのリスト。 | AUDIO | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerPadKeyframesList/ja.md) diff --git a/ja/built-in-nodes/WanDancerVideo.mdx b/ja/built-in-nodes/WanDancerVideo.mdx index 3196edbf9..65831a414 100644 --- a/ja/built-in-nodes/WanDancerVideo.mdx +++ b/ja/built-in-nodes/WanDancerVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerVideo" icon: "circle" mode: wide --- + 以下が翻訳結果です。 WanDancerVideo ノードは、WanDancer モデルによる動画生成のために、コンディショニングデータと空の潜在テンソルを準備します。このノードは、ポジティブコンディショニングとネガティブコンディショニングを、開始画像、マスク、CLIPビジョン埋め込み、オーディオ特徴量などのオプション入力と組み合わせて、生成される動画を制御します。 @@ -34,8 +35,8 @@ WanDancerVideo ノードは、WanDancer モデルによる動画生成のため | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `negative` | 追加データ（連結潜在変数、CLIPビジョン、オーディオ）が付加されたポジティブコンディショニング。 | CONDITIONING | -| `latent` | 追加データ（連結潜在変数、CLIPビジョン、オーディオ）が付加されたネガティブコンディショニング。 | CONDITIONING | +| `positive` | 追加データ（連結潜在変数、CLIPビジョン、オーディオ）が付加されたポジティブコンディショニング。 | CONDITIONING | +| `negative` | 追加データ（連結潜在変数、CLIPビジョン、オーディオ）が付加されたネガティブコンディショニング。 | CONDITIONING | | `latent` | 指定された動画の長さ、高さ、幅に一致する次元を持つ空の潜在テンソル。 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerVideo/ja.md) diff --git a/ja/built-in-nodes/WanFirstLastFrameToVideo.mdx b/ja/built-in-nodes/WanFirstLastFrameToVideo.mdx index 3a9e6cbb5..7f12f5b39 100644 --- a/ja/built-in-nodes/WanFirstLastFrameToVideo.mdx +++ b/ja/built-in-nodes/WanFirstLastFrameToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFirstLastFrameToVideo" icon: "circle" mode: wide --- + WanFirstLastFrameToVideo ノードは、開始フレームと終了フレームをテキストプロンプトと組み合わせてビデオ条件付けを生成します。最初と最後のフレームをエンコードし、マスクを適用して生成プロセスをガイドし、利用可能な場合はCLIPビジョン特徴量を組み込むことで、ビデオ生成用の潜在表現を作成します。このノードは、指定された開始点と終了点の間で一貫性のあるシーケンスを生成するために、ビデオモデル用のポジティブ条件付けとネガティブ条件付けの両方を準備します。 ## 入力 @@ -29,8 +30,8 @@ WanFirstLastFrameToVideo ノードは、開始フレームと終了フレーム | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | ビデオフレームエンコーディングとCLIPビジョン特徴量が適用されたポジティブ条件付け | CONDITIONING | -| `latent` | ビデオフレームエンコーディングとCLIPビジョン特徴量が適用されたネガティブ条件付け | CONDITIONING | +| `ポジティブ` | ビデオフレームエンコーディングとCLIPビジョン特徴量が適用されたポジティブ条件付け | CONDITIONING | +| `ネガティブ` | ビデオフレームエンコーディングとCLIPビジョン特徴量が適用されたネガティブ条件付け | CONDITIONING | | `latent` | 指定されたビデオパラメータに一致する次元を持つ空の潜在テンソル | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFirstLastFrameToVideo/ja.md) diff --git a/ja/built-in-nodes/WanFunControlToVideo.mdx b/ja/built-in-nodes/WanFunControlToVideo.mdx index 0666ff3d6..44e4eb849 100644 --- a/ja/built-in-nodes/WanFunControlToVideo.mdx +++ b/ja/built-in-nodes/WanFunControlToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFunControlToVideo" icon: "circle" mode: wide --- + このノードは、動画生成のためのAlibaba Wan Fun Controlモデルをサポートするために追加されました。[このコミット](https://github.com/comfyanonymous/ComfyUI/commit/3661c833bcc41b788a7c9f0e7bc48524f8ee5f82)の後に追加されています。 - **目的:** Wan 2.1 Fun Controlモデルを使用して、動画生成に必要な条件付け情報を準備します。 diff --git a/ja/built-in-nodes/WanFunInpaintToVideo.mdx b/ja/built-in-nodes/WanFunInpaintToVideo.mdx index 4b8121b53..e72c445a7 100644 --- a/ja/built-in-nodes/WanFunInpaintToVideo.mdx +++ b/ja/built-in-nodes/WanFunInpaintToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFunInpaintToVideo" icon: "circle" mode: wide --- + 以下は、ご依頼いただいた技術翻訳の結果です。 --- @@ -30,8 +31,8 @@ WanFunInpaintToVideo ノードは、開始画像と終了画像の間をイン | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 処理済みのポジティブ条件付け出力 | CONDITIONING | -| `latent` | 処理済みのネガティブ条件付け出力 | CONDITIONING | +| `ポジティブ` | 処理済みのポジティブ条件付け出力 | CONDITIONING | +| `ネガティブ` | 処理済みのネガティブ条件付け出力 | CONDITIONING | | `latent` | 生成されたビデオの潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFunInpaintToVideo/ja.md) diff --git a/ja/built-in-nodes/WanHuMoImageToVideo.mdx b/ja/built-in-nodes/WanHuMoImageToVideo.mdx index 357423b19..2dd0d2330 100644 --- a/ja/built-in-nodes/WanHuMoImageToVideo.mdx +++ b/ja/built-in-nodes/WanHuMoImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanHuMoImageToVideo" icon: "circle" mode: wide --- + 以下は、ご依頼の翻訳ルールに従って作成した日本語訳です。 ## 概要 @@ -30,9 +31,9 @@ WanHuMoImageToVideo ノードは、ビデオフレームの潜在表現を生成 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 参照画像やオーディオ埋め込みが組み込まれた、修正済みのポジティブ条件付け | CONDITIONING | -| `潜在表現` | 参照画像やオーディオ埋め込みが組み込まれた、修正済みのネガティブ条件付け | CONDITIONING | -| `latent` | ビデオシーケンスデータを含む、生成された潜在表現 | LATENT | +| `ポジティブ` | 参照画像やオーディオ埋め込みが組み込まれた、修正済みのポジティブ条件付け | CONDITIONING | +| `ネガティブ` | 参照画像やオーディオ埋め込みが組み込まれた、修正済みのネガティブ条件付け | CONDITIONING | +| `潜在表現` | ビデオシーケンスデータを含む、生成された潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanHuMoImageToVideo/ja.md) diff --git a/ja/built-in-nodes/WanImageToImageApi.mdx b/ja/built-in-nodes/WanImageToImageApi.mdx index 8a981f1ca..88b8806be 100644 --- a/ja/built-in-nodes/WanImageToImageApi.mdx +++ b/ja/built-in-nodes/WanImageToImageApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToImageApi" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/WanImageToVideo.mdx b/ja/built-in-nodes/WanImageToVideo.mdx index 47b45fbe8..416b120d5 100644 --- a/ja/built-in-nodes/WanImageToVideo.mdx +++ b/ja/built-in-nodes/WanImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToVideo" icon: "circle" mode: wide --- + 以下が翻訳結果です。 WanImageToVideo ノードは、動画生成タスクのための条件付けと潜在表現を準備します。空の潜在空間を動画生成用に作成し、オプションで開始画像とCLIPビジョン出力を組み込んで動画生成プロセスをガイドすることができます。このノードは、提供された画像とビジョンデータに基づいて、ポジティブおよびネガティブの両方の条件付け入力を変更します。 @@ -29,9 +30,9 @@ WanImageToVideo ノードは、動画生成タスクのための条件付けと | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 画像とビジョンデータが組み込まれた、変更後のポジティブ条件付け | CONDITIONING | -| `潜在` | 画像とビジョンデータが組み込まれた、変更後のネガティブ条件付け | CONDITIONING | -| `latent` | 動画生成用に準備された空の潜在空間テンソル | LATENT | +| `ポジティブ` | 画像とビジョンデータが組み込まれた、変更後のポジティブ条件付け | CONDITIONING | +| `ネガティブ` | 画像とビジョンデータが組み込まれた、変更後のネガティブ条件付け | CONDITIONING | +| `潜在` | 動画生成用に準備された空の潜在空間テンソル | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToVideo/ja.md) diff --git a/ja/built-in-nodes/WanImageToVideoApi.mdx b/ja/built-in-nodes/WanImageToVideoApi.mdx index c48fde8a2..2408abc08 100644 --- a/ja/built-in-nodes/WanImageToVideoApi.mdx +++ b/ja/built-in-nodes/WanImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToVideoApi" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Wan Image to Video ノードは、1枚の入力画像とテキストプロンプトから動画を生成します。提供された画像を最初のフレームとして使用し、説明に基づいて動画シーケンスを作成します。解像度、長さ、オーディオ、その他の高度な設定オプションを備えています。 diff --git a/ja/built-in-nodes/WanInfiniteTalkToVideo.mdx b/ja/built-in-nodes/WanInfiniteTalkToVideo.mdx index 3a443d74a..c641082e1 100644 --- a/ja/built-in-nodes/WanInfiniteTalkToVideo.mdx +++ b/ja/built-in-nodes/WanInfiniteTalkToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanInfiniteTalkToVideo" icon: "circle" mode: wide --- + WanInfiniteTalkToVideo ノードは、音声入力からビデオシーケンスを生成します。このノードは、1人または2人の話者から抽出された音声特徴量を条件として、ビデオ拡散モデルを使用し、トーキングヘッドビデオの潜在表現を生成します。新しいシーケンスを生成することも、モーションコンテキストとして以前のフレームを使用して既存のシーケンスを拡張することもできます。 ## 入力 @@ -41,11 +42,11 @@ WanInfiniteTalkToVideo ノードは、音声入力からビデオシーケンス | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ポジティブ` | 音声条件付けが適用されたパッチ済みモデル。 | MODEL | -| `ネガティブ` | 追加コンテキスト（開始画像、CLIPビジョンなど）で変更される可能性のあるポジティブ条件付け。 | CONDITIONING | -| `潜在` | 追加コンテキストで変更される可能性のあるネガティブ条件付け。 | CONDITIONING | -| `トリム画像` | 潜在空間で生成されたビデオシーケンス。 | LATENT | -| `trim_image` | シーケンスを拡張する際に、モーションコンテキストの先頭からトリミングする必要があるフレーム数。 | INT | +| `モデル` | 音声条件付けが適用されたパッチ済みモデル。 | MODEL | +| `ポジティブ` | 追加コンテキスト（開始画像、CLIPビジョンなど）で変更される可能性のあるポジティブ条件付け。 | CONDITIONING | +| `ネガティブ` | 追加コンテキストで変更される可能性のあるネガティブ条件付け。 | CONDITIONING | +| `潜在` | 潜在空間で生成されたビデオシーケンス。 | LATENT | +| `トリム画像` | シーケンスを拡張する際に、モーションコンテキストの先頭からトリミングする必要があるフレーム数。 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanInfiniteTalkToVideo/ja.md) diff --git a/ja/built-in-nodes/WanMoveConcatTrack.mdx b/ja/built-in-nodes/WanMoveConcatTrack.mdx index 545d7bd5f..6b0b521c9 100644 --- a/ja/built-in-nodes/WanMoveConcatTrack.mdx +++ b/ja/built-in-nodes/WanMoveConcatTrack.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveConcatTrack" icon: "circle" mode: wide --- + WanMoveConcatTrack ノードは、2つのモーショントラッキングデータセットを結合し、1つのより長いシーケンスにします。このノードは、入力されたトラックのパスと可視性マスクをそれぞれの次元に沿って結合することで機能します。トラック入力が1つだけ提供された場合は、そのデータを変更せずにそのまま通過させます。 ## 入力 diff --git a/ja/built-in-nodes/WanMoveTrackToVideo.mdx b/ja/built-in-nodes/WanMoveTrackToVideo.mdx index 99872d8d7..5d03b3935 100644 --- a/ja/built-in-nodes/WanMoveTrackToVideo.mdx +++ b/ja/built-in-nodes/WanMoveTrackToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveTrackToVideo" icon: "circle" mode: wide --- + WanMoveTrackToVideo ノードは、動画生成用のコンディショニングと潜在空間データを準備し、オプションで動き追跡情報を組み込みます。開始画像シーケンスを潜在表現にエンコードし、オブジェクトトラックからの位置データをブレンドして、生成される動画の動きをガイドします。このノードは、修正されたポジティブおよびネガティブコンディショニングと、動画モデル用に準備された空の潜在テンソルを出力します。 ## 入力 @@ -29,8 +30,8 @@ WanMoveTrackToVideo ノードは、動画生成用のコンディショニング | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `negative` | `concat_latent_image`、`concat_mask`、`clip_vision_output` を潜在的に含む、修正されたポジティブコンディショニング。 | CONDITIONING | -| `latent` | `concat_latent_image`、`concat_mask`、`clip_vision_output` を潜在的に含む、修正されたネガティブコンディショニング。 | CONDITIONING | +| `positive` | `concat_latent_image`、`concat_mask`、`clip_vision_output` を潜在的に含む、修正されたポジティブコンディショニング。 | CONDITIONING | +| `negative` | `concat_latent_image`、`concat_mask`、`clip_vision_output` を潜在的に含む、修正されたネガティブコンディショニング。 | CONDITIONING | | `latent` | `バッチサイズ`、`長さ`、`高さ`、`幅` の入力によって形状が決定される空の潜在テンソル。 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTrackToVideo/ja.md) diff --git a/ja/built-in-nodes/WanMoveTracksFromCoords.mdx b/ja/built-in-nodes/WanMoveTracksFromCoords.mdx index 6f72f16db..ba56a7595 100644 --- a/ja/built-in-nodes/WanMoveTracksFromCoords.mdx +++ b/ja/built-in-nodes/WanMoveTracksFromCoords.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveTracksFromCoords" icon: "circle" mode: wide --- + WanMoveTracksFromCoords ノードは、JSON形式の座標文字列からモーショントラックを生成します。座標データをテンソル形式に変換し、他の動画処理ノードで使用できるようにします。また、オプションでマスクを適用して、時間経過に伴うトラックの可視性を制御することもできます。 ## 入力 @@ -21,7 +22,7 @@ WanMoveTracksFromCoords ノードは、JSON形式の座標文字列からモー | 出力名 | 説明 | データ型 | | --- | --- | --- | | `トラック長` | 生成されたトラックデータです。各トラックのパス座標と可視性情報を含みます。 | TRACKS | -| `track_length` | 生成されたトラックの総フレーム数です。 | INT | +| `トラック長` | 生成されたトラックの総フレーム数です。 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTracksFromCoords/ja.md) diff --git a/ja/built-in-nodes/WanMoveVisualizeTracks.mdx b/ja/built-in-nodes/WanMoveVisualizeTracks.mdx index 297a275d5..4717fa87c 100644 --- a/ja/built-in-nodes/WanMoveVisualizeTracks.mdx +++ b/ja/built-in-nodes/WanMoveVisualizeTracks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveVisualizeTracks" icon: "circle" mode: wide --- + ## 概要 WanMoveVisualizeTracks ノードは、画像シーケンスまたは動画フレーム上にモーショントラッキングデータをオーバーレイ表示します。トラッキングされたポイントの移動経路や現在位置を視覚的に描画することで、モーションデータを可視化し、分析しやすくします。 diff --git a/ja/built-in-nodes/WanPhantomSubjectToVideo.mdx b/ja/built-in-nodes/WanPhantomSubjectToVideo.mdx index 3e2db61e3..165bf8d63 100644 --- a/ja/built-in-nodes/WanPhantomSubjectToVideo.mdx +++ b/ja/built-in-nodes/WanPhantomSubjectToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanPhantomSubjectToVideo" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善のご提案がございましたら、ぜひご協力ください！ [GitHubで編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanPhantomSubjectToVideo/en.md) WanPhantomSubjectToVideo ノードは、条件付け入力とオプションの参照画像を処理してビデオコンテンツを生成します。ビデオ生成用の潜在表現を作成し、入力画像が提供された場合には、その画像からの視覚的なガイダンスを組み込むことができます。このノードは、ビデオモデル向けに時間次元の連結を行った条件付けデータを準備し、修正された条件付けと生成された潜在ビデオデータを出力します。 @@ -28,10 +29,10 @@ WanPhantomSubjectToVideo ノードは、条件付け入力とオプションの | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブテキスト` | 画像が提供された場合に時間次元の連結が行われた、修正済みポジティブ条件付け | CONDITIONING | -| `ネガティブ画像テキスト` | 画像が提供された場合に時間次元の連結が行われた、修正済みネガティブ条件付け | CONDITIONING | -| `潜在表現` | 画像が提供された場合に時間次元の連結がゼロに設定された、ネガティブ条件付け | CONDITIONING | -| `latent` | 指定された寸法と長さで生成された潜在ビデオ表現 | LATENT | +| `ポジティブ` | 画像が提供された場合に時間次元の連結が行われた、修正済みポジティブ条件付け | CONDITIONING | +| `ネガティブテキスト` | 画像が提供された場合に時間次元の連結が行われた、修正済みネガティブ条件付け | CONDITIONING | +| `ネガティブ画像テキスト` | 画像が提供された場合に時間次元の連結がゼロに設定された、ネガティブ条件付け | CONDITIONING | +| `潜在表現` | 指定された寸法と長さで生成された潜在ビデオ表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanPhantomSubjectToVideo/ja.md) diff --git a/ja/built-in-nodes/WanReferenceVideoApi.mdx b/ja/built-in-nodes/WanReferenceVideoApi.mdx index 035d6d5d2..f2711afb4 100644 --- a/ja/built-in-nodes/WanReferenceVideoApi.mdx +++ b/ja/built-in-nodes/WanReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanReferenceVideoApi" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 diff --git a/ja/built-in-nodes/WanSCAILToVideo.mdx b/ja/built-in-nodes/WanSCAILToVideo.mdx index de319affb..62a9d48c6 100644 --- a/ja/built-in-nodes/WanSCAILToVideo.mdx +++ b/ja/built-in-nodes/WanSCAILToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSCAILToVideo" icon: "circle" mode: wide --- + WanSCAILToVideo ノードは、動画生成のためのコンディショニングと空の潜在空間を準備します。参照画像、ポーズ動画、CLIPビジョン出力などのオプション入力を処理し、それらを動画モデルのポジティブおよびネガティブコンディショニングに埋め込みます。このノードは、変更されたコンディショニングと、指定された動画サイズの空白の潜在テンソルを出力します。 ## 入力 @@ -31,8 +32,8 @@ WanSCAILToVideo ノードは、動画生成のためのコンディショニン | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `negative` | 変更されたポジティブコンディショニングです。参照画像の潜在、CLIPビジョン出力、またはポーズ動画の潜在が埋め込まれている可能性があります。 | CONDITIONING | -| `latent` | 変更されたネガティブコンディショニングです。参照画像の潜在、CLIPビジョン出力、またはポーズ動画の潜在が埋め込まれている可能性があります。 | CONDITIONING | +| `positive` | 変更されたポジティブコンディショニングです。参照画像の潜在、CLIPビジョン出力、またはポーズ動画の潜在が埋め込まれている可能性があります。 | CONDITIONING | +| `negative` | 変更されたネガティブコンディショニングです。参照画像の潜在、CLIPビジョン出力、またはポーズ動画の潜在が埋め込まれている可能性があります。 | CONDITIONING | | `latent` | 形状が `[batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8]` の空の潜在テンソルです。 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSCAILToVideo/ja.md) diff --git a/ja/built-in-nodes/WanSoundImageToVideo.mdx b/ja/built-in-nodes/WanSoundImageToVideo.mdx index ba8f6aa7e..8c32fbaa8 100644 --- a/ja/built-in-nodes/WanSoundImageToVideo.mdx +++ b/ja/built-in-nodes/WanSoundImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSoundImageToVideo" icon: "circle" mode: wide --- + WanSoundImageToVideo ノードは、オプションのオーディオ条件付けを伴う画像から動画コンテンツを生成します。ポジティブおよびネガティブの条件付けプロンプトとVAEモデルを入力として受け取り、動画の潜在表現を生成します。また、参照画像、オーディオエンコーディング、制御動画、モーション参照を組み込むことで、動画生成プロセスを誘導することができます。 ## 入力 @@ -27,9 +28,9 @@ WanSoundImageToVideo ノードは、オプションのオーディオ条件付 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 動画生成用に変更された処理済みのポジティブ条件付け | CONDITIONING | -| `潜在表現` | 動画生成用に変更された処理済みのネガティブ条件付け | CONDITIONING | -| `latent` | 最終的な動画フレームにデコード可能な、潜在空間で表現された生成動画 | LATENT | +| `ポジティブ` | 動画生成用に変更された処理済みのポジティブ条件付け | CONDITIONING | +| `ネガティブ` | 動画生成用に変更された処理済みのネガティブ条件付け | CONDITIONING | +| `潜在表現` | 最終的な動画フレームにデコード可能な、潜在空間で表現された生成動画 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideo/ja.md) diff --git a/ja/built-in-nodes/WanSoundImageToVideoExtend.mdx b/ja/built-in-nodes/WanSoundImageToVideoExtend.mdx index d6e930b09..7427acb9a 100644 --- a/ja/built-in-nodes/WanSoundImageToVideoExtend.mdx +++ b/ja/built-in-nodes/WanSoundImageToVideoExtend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSoundImageToVideoExtend" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ## 概要 @@ -27,9 +28,9 @@ WanSoundImageToVideoExtend ノードは、既存のビデオ潜在表現を拡 | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | ビデオコンテキストが適用された処理済みポジティブ条件付け | CONDITIONING | -| `潜在表現` | ビデオコンテキストが適用された処理済みネガティブ条件付け | CONDITIONING | -| `latent` | 拡張されたビデオシーケンスを含む生成済みビデオ潜在表現 | LATENT | +| `ポジティブ` | ビデオコンテキストが適用された処理済みポジティブ条件付け | CONDITIONING | +| `ネガティブ` | ビデオコンテキストが適用された処理済みネガティブ条件付け | CONDITIONING | +| `潜在表現` | 拡張されたビデオシーケンスを含む生成済みビデオ潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideoExtend/ja.md) diff --git a/ja/built-in-nodes/WanTextToImageApi.mdx b/ja/built-in-nodes/WanTextToImageApi.mdx index 466827bec..c96d1738a 100644 --- a/ja/built-in-nodes/WanTextToImageApi.mdx +++ b/ja/built-in-nodes/WanTextToImageApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTextToImageApi" icon: "circle" mode: wide --- + Wan Text to Image ノードは、テキストの説明に基づいて画像を生成します。AIモデルを使用して、記述されたプロンプトから視覚的なコンテンツを作成し、英語と中国語の両方のテキスト入力をサポートします。このノードは、出力画像のサイズ、品質、スタイルの設定を調整するためのさまざまなコントロールを提供します。 ## 入力 diff --git a/ja/built-in-nodes/WanTextToVideoApi.mdx b/ja/built-in-nodes/WanTextToVideoApi.mdx index 0271f8a36..6144a9bc4 100644 --- a/ja/built-in-nodes/WanTextToVideoApi.mdx +++ b/ja/built-in-nodes/WanTextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTextToVideoApi" icon: "circle" mode: wide --- + 以下が翻訳結果です。 Wan Text to Video ノードは、テキストの説明に基づいて動画コンテンツを生成します。AIモデルを使用してプロンプトから動画を作成し、さまざまな動画サイズ、長さ、およびオプションの音声入力をサポートします。このノードは、必要に応じて音声を自動生成でき、プロンプトの拡張や透かしの追加オプションも提供します。 diff --git a/ja/built-in-nodes/WanTrackToVideo.mdx b/ja/built-in-nodes/WanTrackToVideo.mdx index f0754e5be..59b0f28f3 100644 --- a/ja/built-in-nodes/WanTrackToVideo.mdx +++ b/ja/built-in-nodes/WanTrackToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTrackToVideo" icon: "circle" mode: wide --- + WanTrackToVideoノードは、トラックポイントを処理して対応するビデオフレームを生成することで、モーショントラッキングデータをビデオシーケンスに変換します。トラッキング座標を入力として受け取り、ビデオ生成に使用できるビデオコンディショニングと潜在表現を生成します。トラックが提供されない場合は、標準の画像からビデオへの変換にフォールバックします。 ## 入力 @@ -30,8 +31,8 @@ WanTrackToVideoノードは、トラックポイントを処理して対応す | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `negative` | モーショントラック情報が適用されたポジティブコンディショニング | CONDITIONING | -| `latent` | モーショントラック情報が適用されたネガティブコンディショニング | CONDITIONING | +| `positive` | モーショントラック情報が適用されたポジティブコンディショニング | CONDITIONING | +| `negative` | モーショントラック情報が適用されたネガティブコンディショニング | CONDITIONING | | `latent` | 生成されたビデオの潜在表現 | LATENT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTrackToVideo/ja.md) diff --git a/ja/built-in-nodes/WanVaceToVideo.mdx b/ja/built-in-nodes/WanVaceToVideo.mdx index bc6accc17..9b898066a 100644 --- a/ja/built-in-nodes/WanVaceToVideo.mdx +++ b/ja/built-in-nodes/WanVaceToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanVaceToVideo" icon: "circle" mode: wide --- + WanVaceToVideo ノードは、動画生成モデル向けの動画条件付けデータを処理します。ポジティブおよびネガティブの条件付け入力と動画制御データを受け取り、動画生成のための潜在表現を準備します。このノードは、動画のアップスケーリング、マスキング、VAEエンコーディングを処理し、動画モデルに適した条件付け構造を作成します。 ## 入力 @@ -29,10 +30,10 @@ WanVaceToVideo ノードは、動画生成モデル向けの動画条件付け | 出力名 | 説明 | データ型 | | --- | --- | --- | -| `ネガティブ` | 動画制御データが適用されたポジティブ条件付け | CONDITIONING | -| `latent` | 動画制御データが適用されたネガティブ条件付け | CONDITIONING | -| `トリムlatent` | 動画生成用の空の潜在テンソル | LATENT | -| `trim_latent` | 参照画像が使用される場合にトリミングする潜在フレーム数 | INT | +| `ポジティブ` | 動画制御データが適用されたポジティブ条件付け | CONDITIONING | +| `ネガティブ` | 動画制御データが適用されたネガティブ条件付け | CONDITIONING | +| `latent` | 動画生成用の空の潜在テンソル | LATENT | +| `トリムlatent` | 参照画像が使用される場合にトリミングする潜在フレーム数 | INT | > このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください！ [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanVaceToVideo/ja.md) diff --git a/ja/built-in-nodes/WavespeedFlashVSRNode.mdx b/ja/built-in-nodes/WavespeedFlashVSRNode.mdx index 6c74ba28a..119346f65 100644 --- a/ja/built-in-nodes/WavespeedFlashVSRNode.mdx +++ b/ja/built-in-nodes/WavespeedFlashVSRNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WavespeedFlashVSRNode" icon: "circle" mode: wide --- + このドキュメントはAI生成です。誤りや改善の提案がありましたら、ぜひご協力ください！[GitHubで編集する](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WavespeedFlashVSRNode/en.md) WavespeedFlashVSRNodeは、低解像度やぼやけた映像の解像度を向上させ、鮮明さを復元する高速・高品質なビデオアップスケーラーです。ビデオ入力を処理し、ユーザーが選択した高解像度で新しいビデオを出力します。 diff --git a/ja/built-in-nodes/WavespeedImageUpscaleNode.mdx b/ja/built-in-nodes/WavespeedImageUpscaleNode.mdx index d6ea3e337..acea9c780 100644 --- a/ja/built-in-nodes/WavespeedImageUpscaleNode.mdx +++ b/ja/built-in-nodes/WavespeedImageUpscaleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WavespeedImageUpscaleNode" icon: "circle" mode: wide --- + WaveSpeed Image Upscale ノードは、外部AIサービスを利用して画像の解像度と品質を向上させます。1枚の入力画像を受け取り、2K、4K、8Kなどのより高いターゲット解像度にアップスケールし、より鮮明で詳細な結果を生成します。 ## 入力 diff --git a/ja/built-in-nodes/WebcamCapture.mdx b/ja/built-in-nodes/WebcamCapture.mdx index 127020c7a..6fec21135 100644 --- a/ja/built-in-nodes/WebcamCapture.mdx +++ b/ja/built-in-nodes/WebcamCapture.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WebcamCapture" icon: "circle" mode: wide --- + 以下が翻訳結果です。 --- diff --git a/ja/built-in-nodes/ZImageFunControlnet.mdx b/ja/built-in-nodes/ZImageFunControlnet.mdx index d1ae846e4..064fb25b0 100644 --- a/ja/built-in-nodes/ZImageFunControlnet.mdx +++ b/ja/built-in-nodes/ZImageFunControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ZImageFunControlnet" icon: "circle" mode: wide --- + 以下が翻訳結果です。 ZImageFunControlnet ノードは、特殊な制御ネットワークを適用して画像生成または編集プロセスに影響を与えます。ベースモデル、モデルパッチ、VAE を使用し、制御効果の強度を調整できます。このノードは、ベース画像、インペイント画像、マスクと組み合わせて、よりターゲットを絞った編集を行うことができます。 diff --git a/ja/built-in-nodes/unCLIPCheckpointLoader.mdx b/ja/built-in-nodes/unCLIPCheckpointLoader.mdx index 5d1c466f2..fbe0b1d79 100644 --- a/ja/built-in-nodes/unCLIPCheckpointLoader.mdx +++ b/ja/built-in-nodes/unCLIPCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "unCLIPCheckpointLoader" icon: "circle" mode: wide --- + このノードは、`ComfyUI/models/checkpoints` フォルダ内のモデルを検出し、さらに `extra_model_paths.yaml` ファイルで設定された追加パスからもモデルを読み込みます。場合によっては、対応するフォルダからモデルファイルを読み込むために、**ComfyUI インターフェースを更新（リフレッシュ）** する必要があります。 unCLIPCheckpointLoader ノードは、unCLIP モデル専用に調整されたチェックポイントを読み込むために設計されています。指定されたチェックポイントからモデル、CLIP ビジョンモジュール、VAE の取得と初期化を容易にし、その後の操作や分析のためのセットアッププロセスを効率化します。 diff --git a/ja/built-in-nodes/unCLIPConditioning.mdx b/ja/built-in-nodes/unCLIPConditioning.mdx index 90ce64ab5..46d8cf580 100644 --- a/ja/built-in-nodes/unCLIPConditioning.mdx +++ b/ja/built-in-nodes/unCLIPConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "unCLIPConditioning" icon: "circle" mode: wide --- + このノードは、CLIPビジョン出力を条件付けプロセスに統合し、指定された強度とノイズ拡張パラメータに基づいてこれらの出力の影響を調整するように設計されています。視覚的なコンテキストで条件付けを強化し、生成プロセスを向上させます。 ## 入力 diff --git a/ja/built-in-nodes/wanBlockSwap.mdx b/ja/built-in-nodes/wanBlockSwap.mdx index 7692f6446..84c3b471e 100644 --- a/ja/built-in-nodes/wanBlockSwap.mdx +++ b/ja/built-in-nodes/wanBlockSwap.mdx @@ -5,6 +5,7 @@ sidebarTitle: "wanBlockSwap" icon: "circle" mode: wide --- + このノードは非推奨であり、機能はありません。モデルを入力として受け取り、変更せずに同じモデルを返します。「NOP」という説明は、何の操作も行わないことを示しています。 ## 入力 diff --git a/ko/built-in-nodes/APG.mdx b/ko/built-in-nodes/APG.mdx index f5fe6358a..40defdb96 100644 --- a/ko/built-in-nodes/APG.mdx +++ b/ko/built-in-nodes/APG.mdx @@ -5,7 +5,6 @@ sidebarTitle: "APG" icon: "circle" mode: wide --- -# APG (적응형 투영 안내) 노드 APG(Adaptive Projected Guidance) 노드는 확산 과정에서 안내가 적용되는 방식을 조정하여 샘플링 과정을 수정합니다. 조건부 출력을 기준으로 안내 벡터를 평행 성분과 직교 성분으로 분리하여, 보다 제어된 이미지 생성을 가능하게 합니다. 이 노드는 안내의 크기 조정, 크기 정규화, 그리고 확산 단계 간 부드러운 전환을 위한 모멘텀 적용을 위한 매개변수를 제공합니다. diff --git a/ko/built-in-nodes/ARVideoI2V.mdx b/ko/built-in-nodes/ARVideoI2V.mdx index 9055112ff..7b8b098ec 100644 --- a/ko/built-in-nodes/ARVideoI2V.mdx +++ b/ko/built-in-nodes/ARVideoI2V.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ARVideoI2V" icon: "circle" mode: wide --- + ## 개요 이 노드는 AR(자동 회귀) 비디오 모델을 위한 이미지-투-비디오 생성 설정을 준비합니다. 시작 이미지를 가져와 VAE를 사용하여 잠재 공간으로 인코딩한 후, 인코딩된 이미지를 모델 구성에 저장합니다. 이를 통해 비디오 샘플링 프로세스에서 해당 이미지를 첫 번째 프레임으로 사용할 수 있으며, 별도의 이미지-투-비디오 모델 아키텍처 없이도 생성을 효과적으로 시드할 수 있습니다. diff --git a/ko/built-in-nodes/AddNoise.mdx b/ko/built-in-nodes/AddNoise.mdx index 38dfacd0c..9e1d7cf77 100644 --- a/ko/built-in-nodes/AddNoise.mdx +++ b/ko/built-in-nodes/AddNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddNoise" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddNoise/en.md) 이 노드는 지정된 노이즈 생성기와 시그마 값을 사용하여 잠재 이미지에 제어된 노이즈를 추가합니다. 모델의 샘플링 시스템을 통해 입력을 처리하여 주어진 시그마 범위에 적합한 노이즈 스케일링을 적용하고, 노이즈가 적용된 새로운 잠재 표현을 반환합니다. diff --git a/ko/built-in-nodes/AddTextPrefix.mdx b/ko/built-in-nodes/AddTextPrefix.mdx index 7b8caa107..b4c4301bd 100644 --- a/ko/built-in-nodes/AddTextPrefix.mdx +++ b/ko/built-in-nodes/AddTextPrefix.mdx @@ -5,7 +5,6 @@ sidebarTitle: "AddTextPrefix" icon: "circle" mode: wide --- -# Add Text Prefix 노드 Add Text Prefix 노드는 각 입력 텍스트의 시작 부분에 지정된 문자열을 추가하여 텍스트를 수정합니다. 이 노드는 텍스트와 접두사를 입력으로 받아 결합된 결과를 반환합니다. @@ -20,7 +19,7 @@ Add Text Prefix 노드는 각 입력 텍스트의 시작 부분에 지정된 문 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `text` | 접두사가 앞에 추가된 결과 텍스트입니다. | STRING | +| `texts` | 접두사가 앞에 추가된 결과 텍스트입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextPrefix/ko.md) diff --git a/ko/built-in-nodes/AddTextSuffix.mdx b/ko/built-in-nodes/AddTextSuffix.mdx index d943f6597..4f5111252 100644 --- a/ko/built-in-nodes/AddTextSuffix.mdx +++ b/ko/built-in-nodes/AddTextSuffix.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddTextSuffix" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextSuffix/en.md) 이 노드는 입력 텍스트 문자열의 끝에 지정된 접미사를 추가합니다. 원본 텍스트와 접미사를 입력으로 받아 결합된 결과를 반환합니다. @@ -20,7 +21,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `text` | 접미사가 추가된 후의 결과 텍스트입니다. | STRING | +| `texts` | 접미사가 추가된 후의 결과 텍스트입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextSuffix/ko.md) diff --git a/ko/built-in-nodes/AdjustBrightness.mdx b/ko/built-in-nodes/AdjustBrightness.mdx index 65e16afee..9dd68e428 100644 --- a/ko/built-in-nodes/AdjustBrightness.mdx +++ b/ko/built-in-nodes/AdjustBrightness.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AdjustBrightness" icon: "circle" mode: wide --- + 밝기 조정(Adjust Brightness) 노드는 입력 이미지의 밝기를 수정합니다. 각 픽셀 값에 지정된 계수를 곱한 후, 결과 값이 유효 범위 내에 유지되도록 클램핑(clamping)하여 작동합니다. 계수가 1.0이면 이미지가 변경되지 않고, 1.0 미만이면 어두워지며, 1.0 초과이면 밝아집니다. ## 입력 @@ -18,7 +19,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `image` | 밝기가 조정된 출력 이미지입니다. | IMAGE | +| `images` | 밝기가 조정된 출력 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustBrightness/ko.md) diff --git a/ko/built-in-nodes/AdjustContrast.mdx b/ko/built-in-nodes/AdjustContrast.mdx index 2659dc367..6991260d6 100644 --- a/ko/built-in-nodes/AdjustContrast.mdx +++ b/ko/built-in-nodes/AdjustContrast.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AdjustContrast" icon: "circle" mode: wide --- + ## 입력 | 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | @@ -16,7 +17,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `image` | 대비가 조정된 결과 이미지입니다. | IMAGE | +| `images` | 대비가 조정된 결과 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustContrast/ko.md) diff --git a/ko/built-in-nodes/AlignYourStepsScheduler.mdx b/ko/built-in-nodes/AlignYourStepsScheduler.mdx index 6b64d9236..9992ff14e 100644 --- a/ko/built-in-nodes/AlignYourStepsScheduler.mdx +++ b/ko/built-in-nodes/AlignYourStepsScheduler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "AlignYourStepsScheduler" icon: "circle" mode: wide --- -# AlignYourStepsScheduler 노드 AlignYourStepsScheduler 노드는 다양한 모델 유형에 기반하여 노이즈 제거 프로세스를 위한 시그마 값을 생성합니다. 샘플링 과정의 각 단계에 적합한 노이즈 레벨을 계산하고, denoise 매개변수에 따라 전체 단계 수를 조정합니다. 이를 통해 다양한 확산 모델의 특정 요구사항에 맞게 샘플링 단계를 정렬할 수 있습니다. diff --git a/ko/built-in-nodes/AudioAdjustVolume.mdx b/ko/built-in-nodes/AudioAdjustVolume.mdx index 0d0b60c6f..17ebd612f 100644 --- a/ko/built-in-nodes/AudioAdjustVolume.mdx +++ b/ko/built-in-nodes/AudioAdjustVolume.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioAdjustVolume" icon: "circle" mode: wide --- + AudioAdjustVolume 노드는 데시벨(dB) 단위의 볼륨 조정을 적용하여 오디오의 음량을 수정합니다. 오디오 입력을 받아 지정된 볼륨 레벨에 따라 게인(gain) 계수를 적용하며, 양수 값은 볼륨을 높이고 음수 값은 낮춥니다. 이 노드는 원본과 동일한 샘플 레이트로 수정된 오디오를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/AudioConcat.mdx b/ko/built-in-nodes/AudioConcat.mdx index bd4fba008..5f945e4a4 100644 --- a/ko/built-in-nodes/AudioConcat.mdx +++ b/ko/built-in-nodes/AudioConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioConcat" icon: "circle" mode: wide --- + 다음은 요청하신 조건에 따라 번역한 결과입니다. --- diff --git a/ko/built-in-nodes/AudioEncoderEncode.mdx b/ko/built-in-nodes/AudioEncoderEncode.mdx index 1ca264050..b73eaa7ca 100644 --- a/ko/built-in-nodes/AudioEncoderEncode.mdx +++ b/ko/built-in-nodes/AudioEncoderEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEncoderEncode" icon: "circle" mode: wide --- + AudioEncoderEncode 노드는 오디오 인코더 모델을 사용하여 오디오 데이터를 인코딩합니다. 오디오 입력을 받아 컨디셔닝 파이프라인에서 추가 처리에 사용할 수 있는 인코딩된 표현으로 변환합니다. 이 노드는 원시 오디오 파형을 오디오 기반 머신러닝 애플리케이션에 적합한 형식으로 변환합니다. ## 입력 diff --git a/ko/built-in-nodes/AudioEncoderLoader.mdx b/ko/built-in-nodes/AudioEncoderLoader.mdx index e0a035a1f..98fddae98 100644 --- a/ko/built-in-nodes/AudioEncoderLoader.mdx +++ b/ko/built-in-nodes/AudioEncoderLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEncoderLoader" icon: "circle" mode: wide --- + AudioEncoderLoader 노드는 오디오 인코더 폴더에 있는 파일에서 오디오 인코더 모델을 로드합니다. 입력으로 오디오 인코더 모델의 파일 이름을 받아 로드된 모델을 반환하며, 이 모델은 워크플로우에서 오디오 처리 작업에 사용할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/AudioEqualizer3Band.mdx b/ko/built-in-nodes/AudioEqualizer3Band.mdx index f5fc80b33..2a02c5238 100644 --- a/ko/built-in-nodes/AudioEqualizer3Band.mdx +++ b/ko/built-in-nodes/AudioEqualizer3Band.mdx @@ -5,7 +5,6 @@ sidebarTitle: "AudioEqualizer3Band" icon: "circle" mode: wide --- -# 오디오 이퀄라이저(3밴드) 오디오 이퀄라이저(3밴드) 노드는 오디오 파형의 저음, 중음, 고음 주파수를 조정할 수 있게 해줍니다. 저음을 위한 로우 쉘프 필터, 중음을 위한 피킹 필터, 고음을 위한 하이 쉘프 필터 등 세 개의 개별 필터를 적용합니다. 각 밴드는 게인, 주파수, 대역폭 설정으로 독립적으로 제어할 수 있습니다. diff --git a/ko/built-in-nodes/AudioMerge.mdx b/ko/built-in-nodes/AudioMerge.mdx index d8147369d..4b23243d7 100644 --- a/ko/built-in-nodes/AudioMerge.mdx +++ b/ko/built-in-nodes/AudioMerge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioMerge" icon: "circle" mode: wide --- + AudioMerge 노드는 두 개의 오디오 트랙을 파형을 오버레이하여 결합합니다. 두 오디오 입력의 샘플 속도를 자동으로 일치시키고, 병합 전에 길이를 동일하게 조정합니다. 이 노드는 오디오 신호를 결합하기 위한 여러 수학적 방법을 제공하며, 출력이 허용 가능한 볼륨 수준 내에 유지되도록 보장합니다. ## 입력 diff --git a/ko/built-in-nodes/AutogrowNamesTestNode.mdx b/ko/built-in-nodes/AutogrowNamesTestNode.mdx index e700fc83c..3302df7a8 100644 --- a/ko/built-in-nodes/AutogrowNamesTestNode.mdx +++ b/ko/built-in-nodes/AutogrowNamesTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AutogrowNamesTestNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AutogrowNamesTestNode/en.md) 이 노드는 Autogrow 입력 기능을 테스트하기 위한 노드입니다. 각각 특정 이름이 지정된 동적 개수의 float 입력을 받아, 해당 값들을 쉼표로 구분된 하나의 문자열로 결합합니다. diff --git a/ko/built-in-nodes/AutogrowPrefixTestNode.mdx b/ko/built-in-nodes/AutogrowPrefixTestNode.mdx index bf6bc80ea..d431ea947 100644 --- a/ko/built-in-nodes/AutogrowPrefixTestNode.mdx +++ b/ko/built-in-nodes/AutogrowPrefixTestNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "AutogrowPrefixTestNode" icon: "circle" mode: wide --- -# AutogrowPrefixTestNode AutogrowPrefixTestNode는 자동 증가 입력 기능을 테스트하기 위해 설계된 로직 노드입니다. 동적인 개수의 float 입력을 받아들이고, 해당 값들을 쉼표로 구분된 문자열로 결합한 후 출력합니다. diff --git a/ko/built-in-nodes/BasicGuider.mdx b/ko/built-in-nodes/BasicGuider.mdx index 161eb38e7..bea157d5c 100644 --- a/ko/built-in-nodes/BasicGuider.mdx +++ b/ko/built-in-nodes/BasicGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BasicGuider" icon: "circle" mode: wide --- + BasicGuider 노드는 샘플링 과정을 위한 간단한 안내 메커니즘을 생성합니다. 모델과 컨디셔닝 데이터를 입력으로 받아 샘플링 중 생성 과정을 안내하는 데 사용할 수 있는 가이더 객체를 출력합니다. 이 노드는 제어된 생성을 위해 필요한 기본적인 안내 기능을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/BasicScheduler.mdx b/ko/built-in-nodes/BasicScheduler.mdx index 077bc5da6..98de4bc99 100644 --- a/ko/built-in-nodes/BasicScheduler.mdx +++ b/ko/built-in-nodes/BasicScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BasicScheduler" icon: "circle" mode: wide --- + `BasicScheduler` 노드는 제공된 스케줄러, 모델 및 디노이징 매개변수를 기반으로 확산 모델에 대한 시그마 값 시퀀스를 계산하도록 설계되었습니다. 디노이즈 팩터에 따라 총 단계 수를 동적으로 조정하여 확산 과정을 미세 조정하며, 정밀한 제어가 필요한 고급 샘플링 프로세스(예: 다단계 샘플링)의 다양한 단계에 정확한 "레시피"를 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/BatchImagesMasksLatentsNode.mdx b/ko/built-in-nodes/BatchImagesMasksLatentsNode.mdx index 8fdb3b17c..3a294aea6 100644 --- a/ko/built-in-nodes/BatchImagesMasksLatentsNode.mdx +++ b/ko/built-in-nodes/BatchImagesMasksLatentsNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BatchImagesMasksLatentsNode" icon: "circle" mode: wide --- -# 배치 이미지/마스크/잠재 표현 노드 배치 이미지/마스크/잠재 표현 노드는 동일한 유형의 여러 입력을 단일 배치로 결합합니다. 입력이 이미지, 마스크 또는 잠재 표현인지 자동으로 감지하여 적절한 배치 방법을 사용합니다. 이는 배치 입력을 허용하는 노드에서 처리할 여러 항목을 준비할 때 유용합니다. diff --git a/ko/built-in-nodes/BatchImagesNode.mdx b/ko/built-in-nodes/BatchImagesNode.mdx index 2336c2d55..194904a0c 100644 --- a/ko/built-in-nodes/BatchImagesNode.mdx +++ b/ko/built-in-nodes/BatchImagesNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BatchImagesNode" icon: "circle" mode: wide --- -# Batch Images 노드 Batch Images 노드는 여러 개의 개별 이미지를 하나의 배치로 결합합니다. 가변 개수의 이미지 입력을 받아 하나의 배치 이미지 텐서로 출력하여, 후속 노드에서 함께 처리할 수 있도록 합니다. diff --git a/ko/built-in-nodes/BatchLatentsNode.mdx b/ko/built-in-nodes/BatchLatentsNode.mdx index ff9152fde..00a1527f9 100644 --- a/ko/built-in-nodes/BatchLatentsNode.mdx +++ b/ko/built-in-nodes/BatchLatentsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchLatentsNode" icon: "circle" mode: wide --- + **Batch Latents 노드** Batch Latents 노드는 여러 개의 잠재(Latent) 입력을 단일 배치로 결합합니다. 가변 개수의 잠재 샘플을 입력받아 배치 차원을 따라 병합함으로써, 이후 노드에서 함께 처리될 수 있도록 합니다. 이는 단일 작업으로 여러 이미지를 생성하거나 처리할 때 유용합니다. diff --git a/ko/built-in-nodes/BatchMasksNode.mdx b/ko/built-in-nodes/BatchMasksNode.mdx index 14429f6b9..8c542d83f 100644 --- a/ko/built-in-nodes/BatchMasksNode.mdx +++ b/ko/built-in-nodes/BatchMasksNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BatchMasksNode" icon: "circle" mode: wide --- -# Batch Masks 노드 Batch Masks 노드는 여러 개별 마스크 입력을 하나의 배치로 결합합니다. 가변 개수의 마스크 입력을 받아 단일 배치 마스크 텐서로 출력하여, 후속 노드에서 마스크를 배치 처리할 수 있도록 합니다. diff --git a/ko/built-in-nodes/BeebleSwitchXImageEdit.mdx b/ko/built-in-nodes/BeebleSwitchXImageEdit.mdx index cdc19c285..399994b51 100644 --- a/ko/built-in-nodes/BeebleSwitchXImageEdit.mdx +++ b/ko/built-in-nodes/BeebleSwitchXImageEdit.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BeebleSwitchXImageEdit" icon: "circle" mode: wide --- -# BeebleSwitchXImageEdit ## 개요 @@ -28,7 +27,7 @@ Beeble SwitchX를 사용하여 단일 이미지를 편집합니다. 이 노드 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `alpha` | 장면 요소가 전환된 편집된 이미지입니다. | IMAGE | +| `image` | 장면 요소가 전환된 편집된 이미지입니다. | IMAGE | | `alpha` | Beeble에서 사용하는 알파 매트입니다. "fill" 모드에서는 별도의 매트가 없으므로 비어 있습니다. | MASK | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BeebleSwitchXImageEdit/ko.md) diff --git a/ko/built-in-nodes/BeebleSwitchXVideoEdit.mdx b/ko/built-in-nodes/BeebleSwitchXVideoEdit.mdx index e8176e771..65fb559fd 100644 --- a/ko/built-in-nodes/BeebleSwitchXVideoEdit.mdx +++ b/ko/built-in-nodes/BeebleSwitchXVideoEdit.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BeebleSwitchXVideoEdit" icon: "circle" mode: wide --- -# Beeble SwitchX 비디오 편집 Beeble SwitchX로 비디오를 편집합니다. 이 노드는 원본 피사체의 픽셀과 움직임을 유지하면서 장면의 모든 요소(배경, 조명, 의상)를 전환할 수 있습니다. 새로운 모습을 설명하는 참조 이미지 및/또는 텍스트 프롬프트를 제공하세요. @@ -34,7 +33,7 @@ Beeble SwitchX로 비디오를 편집합니다. 이 노드는 원본 피사체 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `alpha` | 장면 변경이 적용된 편집된 비디오입니다. | VIDEO | +| `video` | 장면 변경이 적용된 편집된 비디오입니다. | VIDEO | | `alpha` | Beeble에서 사용한 알파 매트입니다. "fill" 모드에서는 별도의 매트가 없으므로 비어 있습니다. | VIDEO | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BeebleSwitchXVideoEdit/ko.md) diff --git a/ko/built-in-nodes/BerniniConditioning.mdx b/ko/built-in-nodes/BerniniConditioning.mdx new file mode 100644 index 000000000..7462f1583 --- /dev/null +++ b/ko/built-in-nodes/BerniniConditioning.mdx @@ -0,0 +1,45 @@ +--- +title: "BerniniConditioning - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the BerniniConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "BerniniConditioning" +icon: "circle" +mode: wide +--- + +BerniniConditioning 노드는 Wan2.2-A14B 모델을 위한 비디오 및 이미지 컨디셔닝 데이터를 준비합니다. 제공된 VAE를 사용하여 소스 비디오, 참조 비디오 및 참조 이미지를 인코딩한 후, 이를 컨텍스트 내 생성 작업을 위한 컨디셔닝 데이터에 첨부합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `positive` | 긍정 컨디셔닝 데이터 | CONDITIONING | 예 | - | +| `negative` | 부정 컨디셔닝 데이터 | CONDITIONING | 예 | - | +| `vae` | 비디오 및 이미지 입력을 인코딩하는 데 사용되는 VAE 모델 | VAE | 예 | - | +| `width` | 출력 잠재 변수의 너비(기본값: 832) | INT | 예 | 16 ~ 8192 (단위: 16) | +| `height` | 출력 잠재 변수의 높이(기본값: 480) | INT | 예 | 16 ~ 8192 (단위: 16) | +| `length` | 출력 잠재 변수의 프레임 수(기본값: 81) | INT | 예 | 1 ~ 8192 (단위: 4) | +| `batch_size` | 단일 배치에서 생성할 비디오 수(기본값: 1) | INT | 예 | 1 ~ 4096 | +| `source_video` | 편집 또는 스타일 변경할 소스 비디오(v2v, rv2v). 너비/높이로 크기 조정되고 길이에 맞게 잘립니다. | IMAGE | 아니요 | - | +| `reference_video` | 소스 비디오에 삽입할 비디오(ads2v). | IMAGE | 아니요 | - | +| `reference_images` | 컨텍스트 내 토큰으로 주입되는 참조 이미지(r2v, rv2v). 최대 8개의 이미지를 제공할 수 있습니다. | IMAGE | 아니요 | 0 ~ 8개 이미지 | +| `ref_max_size` | reference_video 및 reference_images의 긴 쪽 최대 크기. 종횡비를 유지하며 크기 조정되고 16px 단위로 맞춰집니다(기본값: 848). | INT | 아니요 | 16 ~ 8192 (단위: 16) | + +**참고:** 작업은 어떤 입력이 연결되었는지에 따라 결정됩니다: +- 연결된 입력 없음 → 텍스트-투-비디오 (t2v) +- `source_video`만 연결됨 → 비디오-투-비디오 (v2v) +- `source_video` + `reference_images` → 참조 기반 비디오 편집 (rv2v) +- `reference_images`만 연결됨 → 참조-투-비디오 (r2v) +- `source_video` + `reference_video` → 비디오에 이미지/비디오 삽입 (ads2v) + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `positive` | 컨텍스트 잠재 변수가 첨부된 긍정 컨디셔닝 | CONDITIONING | +| `negative` | 컨텍스트 잠재 변수가 첨부된 부정 컨디셔닝 | CONDITIONING | +| `latent` | 지정된 너비, 높이, 길이 및 배치 크기와 일치하는 차원의 빈 잠재 변수 텐서 | LATENT | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BerniniConditioning/ko.md) + +--- +**Source fingerprint (SHA-256):** `3535bbe9a1ae007dc579242b44787ab315479a820eb0da680eab9b870ab60699` diff --git a/ko/built-in-nodes/BetaSamplingScheduler.mdx b/ko/built-in-nodes/BetaSamplingScheduler.mdx index b68c40edb..ea2cb61e7 100644 --- a/ko/built-in-nodes/BetaSamplingScheduler.mdx +++ b/ko/built-in-nodes/BetaSamplingScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BetaSamplingScheduler" icon: "circle" mode: wide --- + BetaSamplingScheduler 노드는 베타 스케줄링 알고리즘을 사용하여 샘플링 프로세스에 필요한 노이즈 레벨(시그마) 시퀀스를 생성합니다. 모델과 구성 매개변수를 입력받아 이미지 생성 중 디노이징 과정을 제어하는 맞춤형 노이즈 스케줄을 만듭니다. 이 스케줄러는 알파 및 베타 매개변수를 통해 노이즈 감소 궤적을 세밀하게 조정할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/BriaImageEditNode.mdx b/ko/built-in-nodes/BriaImageEditNode.mdx index b0ed0895c..94b8c2107 100644 --- a/ko/built-in-nodes/BriaImageEditNode.mdx +++ b/ko/built-in-nodes/BriaImageEditNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaImageEditNode" icon: "circle" mode: wide --- -# Bria FIBO 이미지 편집 노드 Bria FIBO 이미지 편집 노드를 사용하면 텍스트 명령어를 통해 기존 이미지를 수정할 수 있습니다. 이 노드는 이미지와 프롬프트를 Bria API로 전송하며, API는 FIBO 모델을 사용하여 요청에 기반한 새로운 편집 버전의 이미지를 생성합니다. 또한 마스크를 제공하여 편집을 특정 영역으로 제한할 수 있습니다. diff --git a/ko/built-in-nodes/BriaRemoveImageBackground.mdx b/ko/built-in-nodes/BriaRemoveImageBackground.mdx index e05e5eddd..ab14971dc 100644 --- a/ko/built-in-nodes/BriaRemoveImageBackground.mdx +++ b/ko/built-in-nodes/BriaRemoveImageBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BriaRemoveImageBackground" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaRemoveImageBackground/en.md) 이 노드는 Bria RMBG 2.0 서비스를 사용하여 이미지에서 배경을 제거합니다. 이미지를 외부 API로 전송하여 처리한 후 배경이 제거된 결과를 반환합니다. diff --git a/ko/built-in-nodes/BriaRemoveVideoBackground.mdx b/ko/built-in-nodes/BriaRemoveVideoBackground.mdx index 57631ce2c..7c67bb96f 100644 --- a/ko/built-in-nodes/BriaRemoveVideoBackground.mdx +++ b/ko/built-in-nodes/BriaRemoveVideoBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BriaRemoveVideoBackground" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaRemoveVideoBackground/en.md) 이 노드는 Bria AI 서비스를 사용하여 비디오에서 배경을 제거합니다. 입력 비디오를 처리하고 원본 배경을 선택한 단색으로 대체합니다. 작업은 외부 API를 통해 수행되며, 결과는 새 비디오 파일로 반환됩니다. diff --git a/ko/built-in-nodes/BriaTransparentVideoBackground.mdx b/ko/built-in-nodes/BriaTransparentVideoBackground.mdx index 0bc90a839..6b94b4130 100644 --- a/ko/built-in-nodes/BriaTransparentVideoBackground.mdx +++ b/ko/built-in-nodes/BriaTransparentVideoBackground.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaTransparentVideoBackground" icon: "circle" mode: wide --- -# Bria 비디오 배경 제거 (투명) 이 노드는 Bria의 AI 서비스를 사용하여 비디오에서 배경을 제거하고, 컷아웃된 프레임과 알파 마스크를 출력합니다. 두 출력을 합성 노드에 연결하거나, Save WEBM 노드에 전달하여 투명 비디오를 작성하십시오. @@ -20,7 +19,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | |-------------|-------------|-----------| -| `mask` | 배경이 제거된 비디오 프레임 | IMAGE | +| `이미지` | 배경이 제거된 비디오 프레임 | IMAGE | | `mask` | 비디오 프레임의 알파 마스크 | MASK | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BriaTransparentVideoBackground/ko.md) diff --git a/ko/built-in-nodes/BriaVideoGreenScreen.mdx b/ko/built-in-nodes/BriaVideoGreenScreen.mdx index 5d8412124..3136a0bc7 100644 --- a/ko/built-in-nodes/BriaVideoGreenScreen.mdx +++ b/ko/built-in-nodes/BriaVideoGreenScreen.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaVideoGreenScreen" icon: "circle" mode: wide --- -# Bria 비디오 그린 스크린 이 노드는 Bria API를 사용하여 비디오의 배경을 단색 크로마키 화면으로 대체합니다. 입력 비디오를 처리하여 원본 배경이 제거되고 균일한 녹색 또는 파란색 화면 색상으로 대체된 새 비디오를 반환합니다. diff --git a/ko/built-in-nodes/BriaVideoReplaceBackground.mdx b/ko/built-in-nodes/BriaVideoReplaceBackground.mdx index 62e1eb3c9..081382fab 100644 --- a/ko/built-in-nodes/BriaVideoReplaceBackground.mdx +++ b/ko/built-in-nodes/BriaVideoReplaceBackground.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaVideoReplaceBackground" icon: "circle" mode: wide --- -# Bria 비디오 배경 교체 이 노드는 Bria의 API를 사용하여 비디오의 배경을 제공된 이미지 또는 비디오로 교체합니다. 출력물은 전경 비디오의 해상도와 프레임 속도를 유지하며, 종횡비가 다른 배경은 맞춰지기 위해 늘어나므로 종횡비를 일치시키면 왜곡 없는 결과를 얻을 수 있습니다. diff --git a/ko/built-in-nodes/BuildJsonPromptIdeogram.mdx b/ko/built-in-nodes/BuildJsonPromptIdeogram.mdx new file mode 100644 index 000000000..f55bc3988 --- /dev/null +++ b/ko/built-in-nodes/BuildJsonPromptIdeogram.mdx @@ -0,0 +1,37 @@ +--- +title: "BuildJsonPromptIdeogram - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the BuildJsonPromptIdeogram node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "BuildJsonPromptIdeogram" +icon: "circle" +mode: wide +--- + +이 노드는 Ideogram 4 이미지 생성 모델에 특화된 구조화된 JSON 프롬프트를 구성합니다. 텍스트 지침, 스타일 선호도 및 색상 팔레트를 모델이 요구하는 JSON 구조로 정리합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `요소` | "Create Bounding Boxes" 노드의 프롬프트 요소입니다. | ARRAY | 예 | - | +| `상위 설명` | 이미지에 대한 선택적 설명입니다(한두 문장). 강력히 권장됩니다. (기본값: 비어 있음) | STRING | 아니요 | - | +| `배경` | 이미지 배경 또는 환경에 대한 필수 설명입니다. (기본값: 비어 있음) | STRING | 예 | - | +| `스타일` | 생성된 이미지의 시각적 스타일 범주입니다. (기본값: "none") | COMBO | 예 | `"none"`
`"photo"`
`"art_style"` | +| `photo` | 사진 출력을 위한 카메라 또는 렌즈 세부 정보입니다(예: 35mm, f/1.4, 보케). 스타일이 "photo"로 설정된 경우에만 사용 가능합니다. (기본값: 비어 있음) | STRING | 아니요 | - | +| `art_style` | 아트 스타일 설명입니다(예: 평면 벡터 일러스트레이션, 굵은 윤곽선). 스타일이 "art_style"로 설정된 경우에만 사용 가능합니다. (기본값: 비어 있음) | STRING | 아니요 | - | +| `미적 요소` | 필수 미적 키워드입니다(예: 무드 있는, 영화 같은, 채도 낮춤). (기본값: 비어 있음) | STRING | 예 | - | +| `조명` | 필수 조명 설명입니다(예: 골든 아워, 림 라이트, 드라마틱한 그림자). (기본값: 비어 있음) | STRING | 예 | - | +| `매체` | 필수 매체 유형입니다(예: 사진, 일러스트레이션, 3D 렌더링, 페인팅, 그래픽 디자인). 스타일이 photo인 경우 photograph으로 설정하세요. (기본값: 비어 있음) | STRING | 예 | - | +| `컬러 팔레트` | 이미지의 주요 색상을 조정하는 16진수 색상 코드입니다. 최대 16개 항목까지 가능합니다. | COLORS | 아니요 | - | + +**참고:** `style` 매개변수가 "photo"로 설정되면 `photo` 입력이 활성화되며, `medium` 매개변수를 "photograph"로 설정해야 합니다. `style`이 "art_style"로 설정되면 `art_style` 입력이 활성화됩니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `프롬프트` | 상위 수준 설명, 스타일 설명(해당하는 경우), 배경 및 요소가 포함된 구성적 분해를 담은 구조화된 JSON 딕셔너리입니다. | DICT | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BuildJsonPromptIdeogram/ko.md) + +--- +**Source fingerprint (SHA-256):** `56a045e0c7c19531e6443696c0bdf3946df066d03eea7d2d217b7d92f052592f` diff --git a/ko/built-in-nodes/ByteDance2FirstLastFrameNode.mdx b/ko/built-in-nodes/ByteDance2FirstLastFrameNode.mdx index aba62f23b..fad07f273 100644 --- a/ko/built-in-nodes/ByteDance2FirstLastFrameNode.mdx +++ b/ko/built-in-nodes/ByteDance2FirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2FirstLastFrameNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDance2FirstLastFrameNode/en.md) 이 노드는 ByteDance의 Seedance 2.0 모델을 사용하여 비디오를 생성합니다. 텍스트 프롬프트와 필수 첫 번째 프레임 이미지를 기반으로 비디오를 만듭니다. 선택적으로 마지막 프레임 이미지를 제공하여 비디오 시퀀스의 종료를 안내할 수 있습니다. diff --git a/ko/built-in-nodes/ByteDance2ReferenceNode.mdx b/ko/built-in-nodes/ByteDance2ReferenceNode.mdx index 3e06e6da3..f7eeb1023 100644 --- a/ko/built-in-nodes/ByteDance2ReferenceNode.mdx +++ b/ko/built-in-nodes/ByteDance2ReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2ReferenceNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDance2ReferenceNode/en.md) ByteDance Seedance 2.0 참조 영상 노드는 Seedance 2.0 AI 모델을 사용하여 텍스트 프롬프트와 제공된 참조 자료를 기반으로 영상을 생성, 편집 또는 확장합니다. 이미지, 영상 및 오디오를 참조로 사용하여 생성 과정을 안내할 수 있으며, 영상 편집 및 확장과 같은 작업을 지원합니다. diff --git a/ko/built-in-nodes/ByteDance2TextToVideoNode.mdx b/ko/built-in-nodes/ByteDance2TextToVideoNode.mdx index 50289ba8d..71cc0b075 100644 --- a/ko/built-in-nodes/ByteDance2TextToVideoNode.mdx +++ b/ko/built-in-nodes/ByteDance2TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2TextToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDance2TextToVideoNode/en.md) 이 노드는 ByteDance의 Seedance 2.0 API를 사용하여 텍스트 설명으로부터 비디오를 생성합니다. 선택한 모델에 프롬프트를 전송하고, 비디오가 처리될 때까지 대기한 후 최종 결과를 반환합니다. diff --git a/ko/built-in-nodes/ByteDanceCreateImageAsset.mdx b/ko/built-in-nodes/ByteDanceCreateImageAsset.mdx index 9204e1c49..6f91bf864 100644 --- a/ko/built-in-nodes/ByteDanceCreateImageAsset.mdx +++ b/ko/built-in-nodes/ByteDanceCreateImageAsset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceCreateImageAsset" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateImageAsset/en.md) 이 노드는 ByteDance Seedance 2.0 서비스를 위한 개인 이미지 자산을 생성합니다. 입력 이미지를 업로드하고 지정된 자산 그룹에 등록합니다. 그룹 ID가 제공되지 않으면, 자산을 추가하기 전에 브라우저에서 실물 인증 절차를 시작하여 새 그룹을 생성합니다. @@ -25,7 +26,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `group_id` | 새로 생성된 이미지 자산의 고유 식별자입니다. | STRING | +| `asset_id` | 새로 생성된 이미지 자산의 고유 식별자입니다. | STRING | | `group_id` | 자산 그룹의 식별자입니다. 제공된 `group_id` 또는 새로 생성된 그룹 ID가 됩니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateImageAsset/ko.md) diff --git a/ko/built-in-nodes/ByteDanceCreateVideoAsset.mdx b/ko/built-in-nodes/ByteDanceCreateVideoAsset.mdx index 6c3e457a3..08f26294c 100644 --- a/ko/built-in-nodes/ByteDanceCreateVideoAsset.mdx +++ b/ko/built-in-nodes/ByteDanceCreateVideoAsset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceCreateVideoAsset" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateVideoAsset/en.md) 이 노드는 Seedance 2.0용 개인 비디오 자산을 생성합니다. 입력 비디오를 업로드하고 지정된 자산 그룹에 등록합니다. 그룹 ID를 제공하지 않으면 브라우저에서 실물 인증 절차를 안내하여 먼저 새 그룹을 생성합니다. @@ -27,7 +28,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `group_id` | 새로 생성된 비디오 자산의 고유 식별자입니다. | STRING | +| `asset_id` | 새로 생성된 비디오 자산의 고유 식별자입니다. | STRING | | `group_id` | 새 비디오가 포함된 자산 그룹의 식별자입니다. 제공된 `group_id`이거나 새로 생성된 ID입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateVideoAsset/ko.md) diff --git a/ko/built-in-nodes/ByteDanceFirstLastFrameNode.mdx b/ko/built-in-nodes/ByteDanceFirstLastFrameNode.mdx index 8180d3f8a..cbf545aea 100644 --- a/ko/built-in-nodes/ByteDanceFirstLastFrameNode.mdx +++ b/ko/built-in-nodes/ByteDanceFirstLastFrameNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceFirstLastFrameNode" icon: "circle" mode: wide --- -# 개요 이 노드는 텍스트 프롬프트와 첫 번째 및 마지막 프레임 이미지를 사용하여 비디오를 생성합니다. 사용자의 설명과 두 개의 키 프레임을 바탕으로 두 프레임 사이를 자연스럽게 전환하는 완전한 비디오 시퀀스를 생성합니다. 이 노드는 비디오의 해상도, 화면 비율, 길이 및 기타 생성 매개변수를 제어할 수 있는 다양한 옵션을 제공합니다. diff --git a/ko/built-in-nodes/ByteDanceImageEditNode.mdx b/ko/built-in-nodes/ByteDanceImageEditNode.mdx index 35812930b..561161572 100644 --- a/ko/built-in-nodes/ByteDanceImageEditNode.mdx +++ b/ko/built-in-nodes/ByteDanceImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageEditNode" icon: "circle" mode: wide --- + 다음은 제공된 영어 문서를 한국어로 번역한 결과입니다. --- diff --git a/ko/built-in-nodes/ByteDanceImageNode.mdx b/ko/built-in-nodes/ByteDanceImageNode.mdx index bb6299b88..4dc842cde 100644 --- a/ko/built-in-nodes/ByteDanceImageNode.mdx +++ b/ko/built-in-nodes/ByteDanceImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceImageNode" icon: "circle" mode: wide --- -# ByteDance 이미지 노드 ByteDance 이미지 노드는 텍스트 프롬프트를 기반으로 API를 통해 ByteDance 모델을 사용하여 이미지를 생성합니다. 모델을 선택하고, 이미지 크기를 지정하며, 시드 및 안내 척도와 같은 다양한 생성 매개변수를 제어할 수 있습니다. 이 노드는 ByteDance의 이미지 생성 서비스에 연결되어 생성된 이미지를 반환합니다. diff --git a/ko/built-in-nodes/ByteDanceImageReferenceNode.mdx b/ko/built-in-nodes/ByteDanceImageReferenceNode.mdx index 2315b3a4c..3aebe7938 100644 --- a/ko/built-in-nodes/ByteDanceImageReferenceNode.mdx +++ b/ko/built-in-nodes/ByteDanceImageReferenceNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceImageReferenceNode" icon: "circle" mode: wide --- -# ByteDance 이미지 참조 노드 ByteDance 이미지 참조 노드는 텍스트 프롬프트와 1~4개의 참조 이미지를 사용하여 비디오를 생성합니다. 이 노드는 이미지와 프롬프트를 외부 API 서비스로 전송하여, 사용자의 설명과 일치하면서 참조 이미지의 시각적 스타일과 콘텐츠를 반영한 비디오를 생성합니다. 또한 비디오 해상도, 화면 비율, 길이 및 기타 생성 매개변수를 제어할 수 있는 다양한 옵션을 제공합니다. diff --git a/ko/built-in-nodes/ByteDanceImageToVideoNode.mdx b/ko/built-in-nodes/ByteDanceImageToVideoNode.mdx index a04fbff5d..93605b13f 100644 --- a/ko/built-in-nodes/ByteDanceImageToVideoNode.mdx +++ b/ko/built-in-nodes/ByteDanceImageToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceImageToVideoNode" icon: "circle" mode: wide --- -# ByteDance Image to Video 노드 ByteDance Image to Video 노드는 입력 이미지와 텍스트 프롬프트를 기반으로 API를 통해 ByteDance 모델을 사용하여 비디오를 생성합니다. 시작 이미지 프레임을 받아 제공된 설명을 따르는 비디오 시퀀스를 생성합니다. 이 노드는 비디오 해상도, 화면 비율, 길이 및 기타 생성 매개변수에 대한 다양한 사용자 지정 옵션을 제공합니다. diff --git a/ko/built-in-nodes/ByteDanceSeedAudio.mdx b/ko/built-in-nodes/ByteDanceSeedAudio.mdx new file mode 100644 index 000000000..25bd06bc0 --- /dev/null +++ b/ko/built-in-nodes/ByteDanceSeedAudio.mdx @@ -0,0 +1,49 @@ +--- +title: "ByteDanceSeedAudio - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ByteDanceSeedAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ByteDanceSeedAudio" +icon: "circle" +mode: wide +--- + +ByteDance Seed Audio 1.0을 사용하여 단일 프롬프트로 음성, 음악, 음향 효과 및 다중 화자 대화를 생성합니다. 프롬프트에 음성, 감정, 분위기, 배경 음악 및 음향 효과를 설명하고, 말할 대사를 포함하세요. 선택적으로 내장된 사전 설정 음성을 선택하거나, 최대 3개의 참조 클립(프롬프트에서 @Audio1-3으로 태그 지정)에서 음성을 복제하거나, 캐릭터 이미지에서 음성을 추출할 수 있습니다. 실행당 최대 2분의 오디오를 생성합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `text_prompt` | 음성, 감정, 말하기 속도, 분위기, 배경 음악 및 음향 효과를 설명하고, 말할 대사를 포함하세요(대화의 경우 캐릭터 이름을 인라인으로 지정). '오디오 참조' 모드에서는 연결된 클립을 @Audio1, @Audio2, @Audio3 순서로 참조합니다. 최대 3000자입니다. | STRING | 예 | 1~3000자 | +| `reference_mode` | 음성을 조건화하는 방법: '텍스트 전용'(프롬프트에 모든 내용 설명), '오디오 참조'(최대 3개 음성 복제, @Audio1-3으로 태그 지정), '이미지 참조'(하나의 캐릭터 이미지에서 음성 추출) 또는 '사전 설정 음성'(프롬프트를 읽어주는 내장된 명명된 음성 선택). | COMBO | 예 | `"text only"`
`"audio reference"`
`"image reference"`
`"preset voice"` | +| `reference_audio_1` | 음성 복제를 위한 참조 클립이며, 프롬프트에서 @Audio1로 태그 지정됩니다. 최대 30초입니다. `reference_mode`가 "audio reference"인 경우에만 사용 가능합니다. | AUDIO | 아니요 | 최대 30초 | +| `reference_audio_2` | 프롬프트에서 @Audio2로 태그 지정된 참조 클립입니다. 최대 30초입니다. `reference_mode`가 "audio reference"인 경우에만 사용 가능합니다. | AUDIO | 아니요 | 최대 30초 | +| `reference_audio_3` | 프롬프트에서 @Audio3로 태그 지정된 참조 클립입니다. 최대 30초입니다. `reference_mode`가 "audio reference"인 경우에만 사용 가능합니다. | AUDIO | 아니요 | 최대 30초 | +| `reference_image` | 단일 캐릭터 이미지입니다. 모델이 이 이미지에서 음성을 추출합니다. 참조 오디오와 함께 사용할 수 없습니다. `reference_mode`가 "image reference"인 경우에만 사용 가능합니다. | IMAGE | 아니요 | - | +| `preset_voice` | 프롬프트를 읽어주는 내장 TTS 2.0 음성입니다. 참조 클립이 필요하지 않으며, 이 모드에서는 @AudioN 태그가 사용되지 않습니다. `reference_mode`가 "preset voice"인 경우에만 사용 가능합니다. | COMBO | 아니요 | 여러 옵션 사용 가능 (설명 참조) | +| `sample_rate` | 출력 샘플 속도(Hz)입니다. (기본값: "24000") | COMBO | 예 | `"8000"`
`"16000"`
`"24000"`
`"32000"`
`"44100"`
`"48000"` | +| `speech_rate` | 말하기 속도입니다. 0 = 보통, 100 = 2.0배, -50 = 0.5배입니다. (기본값: 0) | INT | 예 | -50 ~ 100 | +| `loudness_rate` | 음량입니다. 0 = 보통, 100 = 2.0배, -50 = 0.5배입니다. (기본값: 0) | INT | 예 | -50 ~ 100 | +| `pitch_rate` | 반음 단위의 피치 이동(-12 ~ 12)입니다. (기본값: 0) | INT | 예 | -12 ~ 12 | +| `seed` | 시드는 노드 재실행 여부를 제어합니다. 시드와 관계없이 결과는 비결정적입니다. (기본값: 42) | INT | 예 | 0 ~ 2147483647 | + +### 매개변수 제약 조건 + +- **참조 모드 종속성**: `reference_mode` 매개변수는 필요한 다른 입력을 결정합니다. + - **"text only"**: 추가 입력이 필요하지 않습니다. 프롬프트에 @AudioN 태그가 포함되어서는 안 됩니다. + - **"audio reference"**: `reference_audio_1`, `reference_audio_2` 또는 `reference_audio_3` 중 하나 이상이 연결되어야 합니다. 참조 클립은 순서대로 연결되어야 하며 중간에 비어 있으면 안 됩니다(예: _1, 그 다음 _2, 그 다음 _3). 각 클립은 최대 30초로 제한됩니다. 프롬프트는 @Audio1, @Audio2, @Audio3 태그를 사용하여 연결된 클립을 참조해야 합니다. + - **"image reference"**: `reference_image`가 연결되어야 합니다. 프롬프트에 @AudioN 태그가 포함되어서는 안 됩니다. + - **"preset voice"**: `preset_voice`가 선택되어야 합니다. 프롬프트에 @AudioN 태그가 포함되어서는 안 됩니다(전체 프롬프트가 선택된 음성으로 읽힙니다). + +- **오디오 참조 순서**: "audio reference" 모드를 사용할 때, 참조 오디오 입력은 `reference_audio_1`부터 시작하여 순차적으로 연결되어야 하며 중간에 비어 있으면 안 됩니다. 예를 들어, _1과 _2는 연결할 수 있지만, _2 없이 _1과 _3만 연결할 수는 없습니다. + +- **최대 오디오 태그**: "audio reference" 모드에서 프롬프트는 최대 3개의 오디오 클립(@Audio1, @Audio2, @Audio3)을 참조할 수 있습니다. 가장 높은 번호의 태그는 연결된 참조 오디오 입력 수를 초과할 수 없습니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `AUDIO` | ByteDance Seed Audio 1.0에서 생성된 오디오 출력으로, 프롬프트에 설명된 대로 음성, 음악, 음향 효과 또는 다중 화자 대화를 포함합니다. | AUDIO | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedAudio/ko.md) + +--- +**Source fingerprint (SHA-256):** `cefd5fca496b02c35022d25be3d99d3911c1304b6e3a751751b58841d5895ef7` diff --git a/ko/built-in-nodes/ByteDanceSeedNode.mdx b/ko/built-in-nodes/ByteDanceSeedNode.mdx index 8613db02d..57bc6e313 100644 --- a/ko/built-in-nodes/ByteDanceSeedNode.mdx +++ b/ko/built-in-nodes/ByteDanceSeedNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceSeedNode" icon: "circle" mode: wide --- -# 개요 ByteDance의 Seed 2.0 모델을 사용하여 텍스트 응답을 생성합니다. 텍스트 프롬프트를 제공하고, 멀티모달 컨텍스트를 위해 이미지나 비디오를 선택적으로 포함할 수 있습니다. diff --git a/ko/built-in-nodes/ByteDanceSeedreamNode.mdx b/ko/built-in-nodes/ByteDanceSeedreamNode.mdx index 39c1673b0..890243e17 100644 --- a/ko/built-in-nodes/ByteDanceSeedreamNode.mdx +++ b/ko/built-in-nodes/ByteDanceSeedreamNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceSeedreamNode" icon: "circle" mode: wide --- -# ByteDance Seedream 노드 ByteDance Seedream 4.5 및 5.0 노드는 최대 4K 해상도에서 통합된 텍스트-이미지 생성 및 정밀한 단일 문장 편집 기능을 제공합니다. 텍스트 프롬프트로 새 이미지를 생성하거나 텍스트 명령어를 사용하여 기존 이미지를 편집할 수 있습니다. 이 노드는 단일 이미지 생성과 여러 관련 이미지의 순차적 생성을 모두 지원합니다. diff --git a/ko/built-in-nodes/ByteDanceSeedreamNodeV2.mdx b/ko/built-in-nodes/ByteDanceSeedreamNodeV2.mdx index 2b0f7fb1b..edaad672d 100644 --- a/ko/built-in-nodes/ByteDanceSeedreamNodeV2.mdx +++ b/ko/built-in-nodes/ByteDanceSeedreamNodeV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceSeedreamNodeV2" icon: "circle" mode: wide --- -# 개요 이 노드는 ByteDance의 Seedream 모델(버전 4.0, 4.5, 5.0 Lite)을 사용하여 이미지를 생성하거나 편집합니다. 텍스트 프롬프트로 새 이미지를 만들거나 참조 이미지를 제공하여 기존 이미지를 편집할 수 있으며, 최대 4K 해상도를 지원합니다. diff --git a/ko/built-in-nodes/ByteDanceTextToVideoNode.mdx b/ko/built-in-nodes/ByteDanceTextToVideoNode.mdx index b2e160e3c..93a8fdc15 100644 --- a/ko/built-in-nodes/ByteDanceTextToVideoNode.mdx +++ b/ko/built-in-nodes/ByteDanceTextToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceTextToVideoNode" icon: "circle" mode: wide --- -# ByteDance Text to Video 노드 ByteDance Text to Video 노드는 API를 통해 ByteDance 모델을 사용하여 텍스트 프롬프트를 기반으로 비디오를 생성합니다. 텍스트 설명과 다양한 비디오 설정을 입력으로 받아 지정된 사양에 맞는 비디오를 생성합니다. 이 노드는 API 통신을 처리하고 생성된 비디오를 출력으로 반환합니다. diff --git a/ko/built-in-nodes/CFGGuider.mdx b/ko/built-in-nodes/CFGGuider.mdx index da1950c3c..71a4050a4 100644 --- a/ko/built-in-nodes/CFGGuider.mdx +++ b/ko/built-in-nodes/CFGGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGGuider" icon: "circle" mode: wide --- + 다음은 ComfyUI CFGGuider 노드 문서의 한국어 번역입니다. --- diff --git a/ko/built-in-nodes/CFGNorm.mdx b/ko/built-in-nodes/CFGNorm.mdx index 07a820ace..39b3e38e3 100644 --- a/ko/built-in-nodes/CFGNorm.mdx +++ b/ko/built-in-nodes/CFGNorm.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CFGNorm" icon: "circle" mode: wide --- -# CFGNorm 노드 CFGNorm 노드는 확산 모델의 분류기-자유 유도(CFG) 과정에 정규화 기법을 적용합니다. 조건부 출력과 비조건부 출력의 노름(norm)을 비교하여 잡음 제거 예측의 스케일을 조정한 후, 강도 승수를 적용하여 효과를 제어합니다. 이는 유도 스케일링에서 극단적인 값을 방지하여 생성 과정을 안정화하는 데 도움을 줍니다. diff --git a/ko/built-in-nodes/CFGOverride.mdx b/ko/built-in-nodes/CFGOverride.mdx index f364e8401..d41493438 100644 --- a/ko/built-in-nodes/CFGOverride.mdx +++ b/ko/built-in-nodes/CFGOverride.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CFGOverride" icon: "circle" mode: wide --- -# CFG 재정의 CFG 재정의 노드는 샘플링 과정의 특정 범위(전체 단계의 백분율로 정의)에 대해 고정된 CFG(분류기-자유 안내) 스케일 값을 설정할 수 있게 해줍니다. 여러 개의 CFG 재정의 노드가 연결된 경우, 체인에서 샘플러에 가장 가까운 노드가 중복되는 범위에 대해 우선순위를 갖습니다. diff --git a/ko/built-in-nodes/CFGZeroStar.mdx b/ko/built-in-nodes/CFGZeroStar.mdx index 6781362d6..4b8a4bb90 100644 --- a/ko/built-in-nodes/CFGZeroStar.mdx +++ b/ko/built-in-nodes/CFGZeroStar.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGZeroStar" icon: "circle" mode: wide --- + CFGZeroStar 노드는 확산 모델에 특수한 안내 스케일링 기법을 적용합니다. 조건부 예측과 무조건부 예측 간의 차이를 기반으로 최적화된 스케일 팩터를 계산하여 분류기 없는 안내 과정을 수정합니다. 이 접근 방식은 모델 안정성을 유지하면서 생성 과정에 대한 향상된 제어를 제공하도록 최종 출력을 조정합니다. ## 입력 @@ -17,7 +18,7 @@ CFGZeroStar 노드는 확산 모델에 특수한 안내 스케일링 기법을 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `patched_model` | CFGZeroStar 안내 스케일링이 적용된 수정된 모델 | MODEL | +| `패치된 모델` | CFGZeroStar 안내 스케일링이 적용된 수정된 모델 | MODEL | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGZeroStar/ko.md) diff --git a/ko/built-in-nodes/Canny.mdx b/ko/built-in-nodes/Canny.mdx index 467a97dc2..7d8a2ccae 100644 --- a/ko/built-in-nodes/Canny.mdx +++ b/ko/built-in-nodes/Canny.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Canny" icon: "circle" mode: wide --- + 사진에서 모든 가장자리 선을 추출합니다. 마치 펜으로 사진의 윤곽을 따라 그리듯이, 객체의 윤곽과 세부 경계선을 그려냅니다. ## 작동 원리 diff --git a/ko/built-in-nodes/CaseConverter.mdx b/ko/built-in-nodes/CaseConverter.mdx index 88d71c453..35a86835d 100644 --- a/ko/built-in-nodes/CaseConverter.mdx +++ b/ko/built-in-nodes/CaseConverter.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CaseConverter" icon: "circle" mode: wide --- + 케이스 변환기 노드는 텍스트 문자열을 다양한 대소문자 형식으로 변환합니다. 입력 문자열을 받아 선택된 모드에 따라 변환하며, 지정된 대소문자 형식이 적용된 출력 문자열을 생성합니다. 이 노드는 텍스트의 대소문자를 수정하는 네 가지 변환 옵션을 지원합니다. ## 입력 diff --git a/ko/built-in-nodes/CenterCropImages.mdx b/ko/built-in-nodes/CenterCropImages.mdx index f46498294..5dd0da26e 100644 --- a/ko/built-in-nodes/CenterCropImages.mdx +++ b/ko/built-in-nodes/CenterCropImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CenterCropImages" icon: "circle" mode: wide --- + 중앙 자르기 이미지 노드는 이미지의 중앙에서 지정된 너비와 높이로 자르기를 수행합니다. 입력 이미지의 중앙 영역을 계산하고 정의된 크기의 직사각형 영역을 추출합니다. 요청된 자르기 크기가 이미지보다 큰 경우, 자르기는 이미지 경계 내로 제한됩니다. ## 입력 @@ -19,7 +20,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `image` | 중앙 자르기 작업 후 생성된 결과 이미지입니다. | IMAGE | +| `images` | 중앙 자르기 작업 후 생성된 결과 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CenterCropImages/ko.md) diff --git a/ko/built-in-nodes/CheckpointLoader.mdx b/ko/built-in-nodes/CheckpointLoader.mdx index 59b3fe3b0..f40f5ee37 100644 --- a/ko/built-in-nodes/CheckpointLoader.mdx +++ b/ko/built-in-nodes/CheckpointLoader.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CheckpointLoader" icon: "circle" mode: wide --- -# CheckpointLoader 노드 CheckpointLoader 노드는 사전 학습된 모델 체크포인트와 해당 설정 파일을 불러옵니다. 설정 파일과 체크포인트 파일을 입력으로 받아, 워크플로우에서 사용할 주 모델, CLIP 모델, VAE 모델을 포함한 로드된 모델 구성 요소를 반환합니다. diff --git a/ko/built-in-nodes/CheckpointLoaderSimple.mdx b/ko/built-in-nodes/CheckpointLoaderSimple.mdx index d28bf920b..ca5e5b174 100644 --- a/ko/built-in-nodes/CheckpointLoaderSimple.mdx +++ b/ko/built-in-nodes/CheckpointLoaderSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointLoaderSimple" icon: "circle" mode: wide --- + ## 개요 확산 모델 체크포인트 파일을 로드하여 잠재 노이즈 제거에 사용되는 메인 모델, CLIP 텍스트 인코더, VAE 이미지 인코더/디코더의 세 가지 핵심 구성 요소로 분해합니다. 이 노드는 `ComfyUI/models/checkpoints` 폴더와 `extra_model_paths.yaml` 파일에 구성된 추가 경로에 있는 모든 모델 파일을 자동으로 감지합니다. diff --git a/ko/built-in-nodes/CheckpointSave.mdx b/ko/built-in-nodes/CheckpointSave.mdx index 36fbbb0e0..1a8dcd0e5 100644 --- a/ko/built-in-nodes/CheckpointSave.mdx +++ b/ko/built-in-nodes/CheckpointSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointSave" icon: "circle" mode: wide --- + `Save Checkpoint` 노드는 UNet, CLIP 및 VAE 구성 요소를 포함한 완전한 Stable Diffusion 모델을 **.safetensors** 형식의 체크포인트 파일로 저장하도록 설계되었습니다. Save Checkpoint 노드는 주로 모델 병합 워크플로우에서 사용됩니다. `ModelMergeSimple`, `ModelMergeBlocks` 등의 노드를 통해 새로운 병합 모델을 생성한 후, 이 노드를 사용하여 결과를 재사용 가능한 체크포인트 파일로 저장할 수 있습니다. diff --git a/ko/built-in-nodes/ChromaRadianceOptions.mdx b/ko/built-in-nodes/ChromaRadianceOptions.mdx index 1fa9bac53..d32c81a40 100644 --- a/ko/built-in-nodes/ChromaRadianceOptions.mdx +++ b/ko/built-in-nodes/ChromaRadianceOptions.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ChromaRadianceOptions" icon: "circle" mode: wide --- -# ChromaRadianceOptions 노드 ChromaRadianceOptions 노드는 Chroma Radiance 모델의 고급 설정을 구성할 수 있도록 합니다. 기존 모델을 래핑하고 시그마 값에 기반하여 노이즈 제거 과정 중 특정 옵션을 적용함으로써, NeRF 타일 크기 및 기타 방사 관련 매개변수를 세밀하게 제어할 수 있습니다. diff --git a/ko/built-in-nodes/ClaudeNode.mdx b/ko/built-in-nodes/ClaudeNode.mdx index 0e60b04bb..8d1167b90 100644 --- a/ko/built-in-nodes/ClaudeNode.mdx +++ b/ko/built-in-nodes/ClaudeNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ClaudeNode" icon: "circle" mode: wide --- -# 개요 Anthropic Claude 모델로부터 텍스트 응답을 생성합니다. 이 노드는 텍스트 프롬프트와 선택적 이미지를 Claude 모델에 전송하고 생성된 텍스트 응답을 반환합니다. diff --git a/ko/built-in-nodes/ClipAttentionMultiply.mdx b/ko/built-in-nodes/ClipAttentionMultiply.mdx index ea5640603..917261977 100644 --- a/ko/built-in-nodes/ClipAttentionMultiply.mdx +++ b/ko/built-in-nodes/ClipAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPAttentionMultiply" icon: "circle" mode: wide --- + CLIPAttentionMultiply 노드는 CLIP 모델의 셀프 어텐션 레이어에 있는 다양한 구성 요소에 곱셈 계수를 적용하여 어텐션 메커니즘을 조정할 수 있게 해줍니다. 이 노드는 CLIP 모델 어텐션 메커니즘의 쿼리, 키, 값 및 출력 투영 가중치와 편향을 수정하여 작동합니다. 이 실험적인 노드는 지정된 스케일링 계수가 적용된 입력 CLIP 모델의 수정된 복사본을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipLoader.mdx b/ko/built-in-nodes/ClipLoader.mdx index 6dff94dfb..9074a8434 100644 --- a/ko/built-in-nodes/ClipLoader.mdx +++ b/ko/built-in-nodes/ClipLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPLoader" icon: "circle" mode: wide --- + CLIPLoader 노드는 텍스트 인코더 모델(CLIP, T5 또는 이와 유사한 모델)을 파일에서 로드하여, 텍스트 프롬프트를 수치 표현으로 변환해야 하는 다른 노드에서 사용할 수 있도록 제공합니다. 다양한 모델 아키텍처를 지원하며, 각 아키텍처에는 특정 인코더 유형이 필요합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipMergeAdd.mdx b/ko/built-in-nodes/ClipMergeAdd.mdx index f0f332ab0..d51eab0ab 100644 --- a/ko/built-in-nodes/ClipMergeAdd.mdx +++ b/ko/built-in-nodes/ClipMergeAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeAdd" icon: "circle" mode: wide --- + CLIPMergeAdd 노드는 두 개의 CLIP 모델을 결합하여 첫 번째 모델에 두 번째 모델의 패치를 추가합니다. 첫 번째 CLIP 모델의 복사본을 생성하고, 위치 ID 및 로짓 스케일 매개변수를 제외한 두 번째 모델의 주요 키 패치를 선택적으로 통합합니다. 이를 통해 기본 모델의 구조를 유지하면서 CLIP 모델 구성 요소를 병합할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ClipMergeSimple.mdx b/ko/built-in-nodes/ClipMergeSimple.mdx index d47b58a9b..36b0336ba 100644 --- a/ko/built-in-nodes/ClipMergeSimple.mdx +++ b/ko/built-in-nodes/ClipMergeSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeSimple" icon: "circle" mode: wide --- + 다음은 요청하신 번역 결과입니다. --- diff --git a/ko/built-in-nodes/ClipMergeSubtract.mdx b/ko/built-in-nodes/ClipMergeSubtract.mdx index 7a1c34b2c..3cb72e794 100644 --- a/ko/built-in-nodes/ClipMergeSubtract.mdx +++ b/ko/built-in-nodes/ClipMergeSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeSubtract" icon: "circle" mode: wide --- + CLIPMergeSubtract 노드는 하나의 CLIP 모델에서 다른 모델의 가중치를 차감하여 모델 병합을 수행합니다. 첫 번째 모델을 복제한 후 두 번째 모델의 키 패치를 차감하여 새로운 CLIP 모델을 생성하며, 조정 가능한 승수를 통해 차감 강도를 제어할 수 있습니다. 이를 통해 기본 모델에서 특정 특성을 제거하여 세밀하게 조정된 모델 블렌딩이 가능합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipSave.mdx b/ko/built-in-nodes/ClipSave.mdx index bb2013fcb..230990845 100644 --- a/ko/built-in-nodes/ClipSave.mdx +++ b/ko/built-in-nodes/ClipSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPSave" icon: "circle" mode: wide --- + `CLIPSave` 노드는 CLIP 텍스트 인코더 모델을 SafeTensors 형식으로 디스크에 저장합니다. 고급 모델 병합 워크플로우를 위해 설계되었으며, 모델의 내부 구조에 따라 CLIP 모델을 구성 요소(예: CLIP-L, CLIP-G 또는 T5XXL)로 자동 분리하여 각 구성 요소를 별도의 파일로 저장합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipSetLastLayer.mdx b/ko/built-in-nodes/ClipSetLastLayer.mdx index ed5d74c27..4f910ba57 100644 --- a/ko/built-in-nodes/ClipSetLastLayer.mdx +++ b/ko/built-in-nodes/ClipSetLastLayer.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPSetLastLayer" icon: "circle" mode: wide --- + `CLIP Set Last Layer`는 CLIP 모델의 처리 깊이를 제어하는 ComfyUI의 핵심 노드입니다. 사용자가 CLIP 텍스트 인코더의 처리 중단 지점을 정밀하게 지정하여 텍스트 이해의 깊이와 생성되는 이미지 스타일에 영향을 줄 수 있습니다. CLIP 모델을 24개 층으로 이루어진 지능형 두뇌로 상상해 보세요. diff --git a/ko/built-in-nodes/ClipTextEncode.mdx b/ko/built-in-nodes/ClipTextEncode.mdx index 75d9354f7..9227532a3 100644 --- a/ko/built-in-nodes/ClipTextEncode.mdx +++ b/ko/built-in-nodes/ClipTextEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncode" icon: "circle" mode: wide --- + `CLIP Text Encode (CLIPTextEncode)`는 번역기 역할을 수행하여, 사용자의 텍스트 설명을 AI가 이해할 수 있는 형식으로 변환합니다. 이를 통해 AI가 입력을 해석하고 원하는 이미지를 생성할 수 있도록 돕습니다. 마치 다른 언어를 사용하는 아티스트와 소통하는 것과 같습니다. 방대한 이미지-텍스트 쌍으로 훈련된 CLIP 모델은 사용자의 설명을 AI 모델이 따를 수 있는 "명령어"로 변환하여 이러한 간극을 메워줍니다. diff --git a/ko/built-in-nodes/ClipTextEncodeControlnet.mdx b/ko/built-in-nodes/ClipTextEncodeControlnet.mdx index 9850a1ab1..9bfb84291 100644 --- a/ko/built-in-nodes/ClipTextEncodeControlnet.mdx +++ b/ko/built-in-nodes/ClipTextEncodeControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeControlnet" icon: "circle" mode: wide --- + CLIPTextEncodeControlnet 노드는 CLIP 모델을 사용하여 텍스트 입력을 처리하고, 이를 기존 컨디셔닝 데이터와 결합하여 컨트롤넷 애플리케이션을 위한 향상된 컨디셔닝 출력을 생성합니다. 입력 텍스트를 토큰화하고 CLIP 모델을 통해 인코딩한 후, 결과 임베딩을 제공된 컨디셔닝 데이터에 크로스 어텐션 컨트롤넷 매개변수로 추가합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodeFlux.mdx b/ko/built-in-nodes/ClipTextEncodeFlux.mdx index cf361cd23..33463b181 100644 --- a/ko/built-in-nodes/ClipTextEncodeFlux.mdx +++ b/ko/built-in-nodes/ClipTextEncodeFlux.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeFlux" icon: "circle" mode: wide --- + `CLIPTextEncodeFlux`는 Flux 아키텍처를 위해 설계된 고급 텍스트 인코딩 노드입니다. 두 개의 개별 텍스트 입력을 CLIP-L과 T5XXL이라는 서로 다른 인코더를 통해 처리하고, 이를 안내 척도(guidance scale)와 결합하여 이미지 생성을 위한 통합 컨디셔닝 출력을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodeHiDream.mdx b/ko/built-in-nodes/ClipTextEncodeHiDream.mdx index ef25afd5c..bb66c09d3 100644 --- a/ko/built-in-nodes/ClipTextEncodeHiDream.mdx +++ b/ko/built-in-nodes/ClipTextEncodeHiDream.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeHiDream" icon: "circle" mode: wide --- + CLIPTextEncodeHiDream 노드는 CLIP-L, CLIP-G, T5-XXL 및 LLaMA 등 서로 다른 언어 모델을 사용하여 네 개의 개별 텍스트 입력을 처리하고, 이를 단일 컨디셔닝 출력으로 결합합니다. 각 텍스트 입력을 해당 모델로 토큰화하고, 예약된 인코딩 방식을 사용하여 함께 인코딩함으로써 여러 언어 모델을 동시에 활용하여 더 정교한 텍스트 컨디셔닝을 가능하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodeHunyuanDiT.mdx b/ko/built-in-nodes/ClipTextEncodeHunyuanDiT.mdx index 18a84e36c..8c4042666 100644 --- a/ko/built-in-nodes/ClipTextEncodeHunyuanDiT.mdx +++ b/ko/built-in-nodes/ClipTextEncodeHunyuanDiT.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeHunyuanDiT" icon: "circle" mode: wide --- + `CLIPTextEncodeHunyuanDiT` 노드는 텍스트 설명을 HunyuanDiT 모델이 이해할 수 있는 형식으로 변환합니다. 이는 HunyuanDiT의 이중 텍스트 인코더 아키텍처를 위해 설계된 고급 컨디셔닝 노드로, 서로 다른 토크나이저를 통해 두 개의 개별 텍스트 입력을 처리합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodeKandinsky5.mdx b/ko/built-in-nodes/ClipTextEncodeKandinsky5.mdx index 4c93f49a8..fcb040ea6 100644 --- a/ko/built-in-nodes/ClipTextEncodeKandinsky5.mdx +++ b/ko/built-in-nodes/ClipTextEncodeKandinsky5.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeKandinsky5" icon: "circle" mode: wide --- + CLIPTextEncodeKandinsky5 노드는 Kandinsky 5 모델과 함께 사용할 텍스트 프롬프트를 준비합니다. 두 개의 개별 텍스트 입력을 받아 제공된 CLIP 모델을 사용하여 토큰화하고, 이를 단일 조건부 출력으로 결합합니다. 이 출력은 이미지 생성 과정을 안내하는 데 사용됩니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodeLumina2.mdx b/ko/built-in-nodes/ClipTextEncodeLumina2.mdx index d5db45928..0ded4a225 100644 --- a/ko/built-in-nodes/ClipTextEncodeLumina2.mdx +++ b/ko/built-in-nodes/ClipTextEncodeLumina2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeLumina2" icon: "circle" mode: wide --- + CLIP 텍스트 인코딩 for Lumina2 노드는 CLIP 모델을 사용하여 시스템 프롬프트와 사용자 프롬프트를 인코딩하여 확산 모델이 특정 이미지를 생성하도록 안내하는 임베딩을 생성합니다. 사전 정의된 시스템 프롬프트를 사용자 정의 텍스트 프롬프트와 결합하여 CLIP 모델을 통해 처리함으로써 이미지 생성을 위한 컨디셔닝 데이터를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodePixArtAlpha.mdx b/ko/built-in-nodes/ClipTextEncodePixArtAlpha.mdx index 0b8250286..f4cd72738 100644 --- a/ko/built-in-nodes/ClipTextEncodePixArtAlpha.mdx +++ b/ko/built-in-nodes/ClipTextEncodePixArtAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodePixArtAlpha" icon: "circle" mode: wide --- + 텍스트를 인코딩하고 PixArt Alpha의 해상도 조건을 설정합니다. 이 노드는 텍스트 입력을 처리하고 너비 및 높이 정보를 추가하여 PixArt Alpha 모델 전용 조건 데이터를 생성합니다. PixArt Sigma 모델에는 적용되지 않습니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodeSD3.mdx b/ko/built-in-nodes/ClipTextEncodeSD3.mdx index d5cd8f4a9..1334407aa 100644 --- a/ko/built-in-nodes/ClipTextEncodeSD3.mdx +++ b/ko/built-in-nodes/ClipTextEncodeSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSD3" icon: "circle" mode: wide --- + CLIPTextEncodeSD3 노드는 여러 개의 텍스트 프롬프트를 서로 다른 CLIP 모델을 사용하여 인코딩함으로써 Stable Diffusion 3 모델용 텍스트 입력을 처리합니다. 이 노드는 세 개의 개별 텍스트 입력(`clip_g`, `clip_l`, `t5xxl`)을 처리하며, 빈 텍스트 패딩을 관리하기 위한 옵션을 제공합니다. 또한, 서로 다른 텍스트 입력 간의 적절한 토큰 정렬을 보장하고 SD3 생성 파이프라인에 적합한 컨디셔닝 데이터를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodeSDXL.mdx b/ko/built-in-nodes/ClipTextEncodeSDXL.mdx index ead566b5b..e551f494a 100644 --- a/ko/built-in-nodes/ClipTextEncodeSDXL.mdx +++ b/ko/built-in-nodes/ClipTextEncodeSDXL.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSDXL" icon: "circle" mode: wide --- + 이 노드는 SDXL 아키텍처에 특화된 CLIP 모델을 사용하여 텍스트 입력을 인코딩하도록 설계되었습니다. 이중 인코더 시스템(CLIP-L 및 CLIP-G)을 활용하여 텍스트 설명을 처리함으로써 보다 정확한 이미지 생성을 가능하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/ClipTextEncodeSDXLRefiner.mdx b/ko/built-in-nodes/ClipTextEncodeSDXLRefiner.mdx index 8e4d63683..8d6213907 100644 --- a/ko/built-in-nodes/ClipTextEncodeSDXLRefiner.mdx +++ b/ko/built-in-nodes/ClipTextEncodeSDXLRefiner.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSDXLRefiner" icon: "circle" mode: wide --- + 이 노드는 SDXL Refiner 모델을 위해 특별히 설계되어, 미적 점수와 차원 정보를 통합하여 텍스트 프롬프트를 조건 정보로 변환함으로써 생성 작업의 조건을 강화하고 최종 정제 효과를 개선합니다. 이는 전문 아트 디렉터처럼 작동하여 창작 의도를 전달할 뿐만 아니라 작품에 정밀한 미적 기준과 사양 요구 사항을 주입합니다. ## SDXL Refiner 정보 diff --git a/ko/built-in-nodes/ClipVisionEncode.mdx b/ko/built-in-nodes/ClipVisionEncode.mdx index abd277c3e..54ee0e6d3 100644 --- a/ko/built-in-nodes/ClipVisionEncode.mdx +++ b/ko/built-in-nodes/ClipVisionEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPVisionEncode" icon: "circle" mode: wide --- + `CLIP Vision Encode` 노드는 ComfyUI의 이미지 인코딩 노드로, CLIP Vision 모델을 통해 입력 이미지를 시각적 특징 벡터로 변환합니다. 이 노드는 이미지와 텍스트 이해를 연결하는 중요한 브릿지 역할을 하며, 다양한 AI 이미지 생성 및 처리 워크플로우에서 널리 사용됩니다. **노드 기능** diff --git a/ko/built-in-nodes/ClipVisionLoader.mdx b/ko/built-in-nodes/ClipVisionLoader.mdx index 66285321b..65b6db831 100644 --- a/ko/built-in-nodes/ClipVisionLoader.mdx +++ b/ko/built-in-nodes/ClipVisionLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPVisionLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/clip_vision` 폴더에 있는 모델과 `extra_model_paths.yaml` 파일에 설정된 추가 모델 경로를 자동으로 감지합니다. ComfyUI를 시작한 후 모델을 추가한 경우, 최신 모델 파일이 목록에 표시되도록 **ComfyUI 인터페이스를 새로고침**해 주십시오. ## 입력 diff --git a/ko/built-in-nodes/ColorToRGBInt.mdx b/ko/built-in-nodes/ColorToRGBInt.mdx index 5e520dd45..35fa3c9b2 100644 --- a/ko/built-in-nodes/ColorToRGBInt.mdx +++ b/ko/built-in-nodes/ColorToRGBInt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ColorToRGBInt" icon: "circle" mode: wide --- + ColorToRGBInt 노드는 16진수 형식으로 지정된 색상을 단일 정수 값으로 변환합니다. `#FF5733`과 같은 색상 문자열을 입력받아 빨간색, 녹색, 파란색 구성 요소를 결합하여 해당 RGB 정수를 계산합니다. ## 입력 @@ -19,7 +20,7 @@ ColorToRGBInt 노드는 16진수 형식으로 지정된 색상을 단일 정수 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `rgb_int` | 계산된 RGB 정수 값입니다. 이 값은 `(Red * 65536) + (Green * 256) + Blue` 공식에서 파생됩니다. | INT | +| `rgb_정수` | 계산된 RGB 정수 값입니다. 이 값은 `(Red * 65536) + (Green * 256) + Blue` 공식에서 파생됩니다. | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ColorToRGBInt/ko.md) diff --git a/ko/built-in-nodes/ColorTransfer.mdx b/ko/built-in-nodes/ColorTransfer.mdx index b16c3a2cf..9dba3fa99 100644 --- a/ko/built-in-nodes/ColorTransfer.mdx +++ b/ko/built-in-nodes/ColorTransfer.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ColorTransfer" icon: "circle" mode: wide --- -# ColorTransfer (색상 전송) ColorTransfer 노드는 대상 이미지의 색상 팔레트를 참조 이미지의 색상과 일치하도록 조정합니다. 밝기, 대비, 색조 분포와 같은 색상 특성을 분석하고 전송하기 위해 다양한 수학적 알고리즘을 사용합니다. 이는 여러 이미지 간의 시각적 일관성을 만들거나 특정 색상 그레이드를 적용하는 데 유용합니다. diff --git a/ko/built-in-nodes/CombineHooks.mdx b/ko/built-in-nodes/CombineHooks.mdx index dd6eb71dd..b5547270d 100644 --- a/ko/built-in-nodes/CombineHooks.mdx +++ b/ko/built-in-nodes/CombineHooks.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CombineHooks" icon: "circle" mode: wide --- -# Combine Hooks [2] 노드 Combine Hooks [2] 노드는 두 개의 훅 그룹을 하나의 결합된 훅 그룹으로 병합합니다. 두 개의 선택적 훅 입력을 받아 ComfyUI의 훅 결합 기능을 사용하여 결합합니다. 이를 통해 여러 훅 구성을 통합하여 간소화된 처리가 가능합니다. diff --git a/ko/built-in-nodes/CombineHooksEight.mdx b/ko/built-in-nodes/CombineHooksEight.mdx index 15b563a22..1ecc5274b 100644 --- a/ko/built-in-nodes/CombineHooksEight.mdx +++ b/ko/built-in-nodes/CombineHooksEight.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CombineHooksEight" icon: "circle" mode: wide --- -# Combine Hooks [8] 노드 Combine Hooks [8] 노드는 최대 8개의 서로 다른 훅 그룹을 하나의 결합된 훅 그룹으로 병합합니다. 여러 훅 입력을 받아 ComfyUI의 훅 결합 기능을 사용하여 이를 통합합니다. 이를 통해 고급 워크플로우에서 여러 훅 구성을 통합하여 효율적으로 처리할 수 있습니다. diff --git a/ko/built-in-nodes/CombineHooksFour.mdx b/ko/built-in-nodes/CombineHooksFour.mdx index f08feec95..921f4f7ec 100644 --- a/ko/built-in-nodes/CombineHooksFour.mdx +++ b/ko/built-in-nodes/CombineHooksFour.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooksFour" icon: "circle" mode: wide --- + **Combine Hooks [4] 노드**는 최대 4개의 개별 후크 그룹을 하나의 결합된 후크 그룹으로 병합합니다. 4개의 사용 가능한 후크 입력을 조합하여 ComfyUI의 후크 결합 시스템을 통해 결합합니다. 이를 통해 여러 후크 구성을 통합하여 고급 워크플로우에서 간소화된 처리를 수행할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ComboOptionTestNode.mdx b/ko/built-in-nodes/ComboOptionTestNode.mdx index f1c12aff8..c48921bd5 100644 --- a/ko/built-in-nodes/ComboOptionTestNode.mdx +++ b/ko/built-in-nodes/ComboOptionTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComboOptionTestNode" icon: "circle" mode: wide --- + ComboOptionTestNode는 콤보 박스 선택을 테스트하고 전달하는 로직 노드입니다. 두 개의 콤보 박스 입력을 받으며, 각 입력에는 미리 정의된 옵션 집합이 있습니다. 선택된 값을 수정 없이 그대로 출력합니다. ## 입력 diff --git a/ko/built-in-nodes/ComfyAndNode.mdx b/ko/built-in-nodes/ComfyAndNode.mdx index 7cf66e5f3..b2e52d0d8 100644 --- a/ko/built-in-nodes/ComfyAndNode.mdx +++ b/ko/built-in-nodes/ComfyAndNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyAndNode" icon: "circle" mode: wide --- + ## 개요 And 노드는 입력 값 집합에 대해 논리적 AND 연산을 수행합니다. 제공된 모든 값이 Python의 참값 규칙에 따라 참으로 간주되는 경우에만 `true`를 반환합니다. 이 노드는 여러 조건이 모두 충족되었는지 확인해야 할 때 유용합니다. diff --git a/ko/built-in-nodes/ComfyMathExpression.mdx b/ko/built-in-nodes/ComfyMathExpression.mdx index ff47896e0..476e6a45d 100644 --- a/ko/built-in-nodes/ComfyMathExpression.mdx +++ b/ko/built-in-nodes/ComfyMathExpression.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyMathExpression" icon: "circle" mode: wide --- + ComfyMathExpression 노드는 입력 값 집합을 사용하여 수학 공식을 계산합니다. `a`, `b`, `c`와 같은 변수 이름을 사용하여 표현식을 작성할 수 있으며, 노드가 결과를 계산합니다. 계산에 필요한 만큼 입력 값을 동적으로 추가할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ComfyNotNode.mdx b/ko/built-in-nodes/ComfyNotNode.mdx index 657f2102f..99912f44a 100644 --- a/ko/built-in-nodes/ComfyNotNode.mdx +++ b/ko/built-in-nodes/ComfyNotNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyNotNode" icon: "circle" mode: wide --- + ## 개요 Not 노드는 입력된 모든 값에 대해 논리적 NOT 연산을 수행합니다. 입력 값이 거짓으로 간주되는 경우(예: 0, 빈 문자열, None, False) True를 반환하고, 입력 값이 참으로 간주되는 경우 False를 반환합니다. 진리값 판별에는 Python의 표준 규칙이 사용됩니다. diff --git a/ko/built-in-nodes/ComfyNumberConvert.mdx b/ko/built-in-nodes/ComfyNumberConvert.mdx index 7e61361fb..5a0e09a5e 100644 --- a/ko/built-in-nodes/ComfyNumberConvert.mdx +++ b/ko/built-in-nodes/ComfyNumberConvert.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ComfyNumberConvert" icon: "circle" mode: wide --- -# 숫자 변환 숫자 변환 노드는 다양한 입력 데이터 유형을 숫자 값으로 변환합니다. 정수, 실수, 문자열 또는 부울 유형의 단일 입력을 받아 부동소수점 숫자와 정수라는 두 가지 출력을 생성합니다. 이는 텍스트나 논리 값을 워크플로우의 다른 수학 또는 처리 노드에서 사용할 수 있는 형식으로 변환하는 데 유용합니다. diff --git a/ko/built-in-nodes/ComfyOrNode.mdx b/ko/built-in-nodes/ComfyOrNode.mdx index 1966a8c83..971dd7a8d 100644 --- a/ko/built-in-nodes/ComfyOrNode.mdx +++ b/ko/built-in-nodes/ComfyOrNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ComfyOrNode" icon: "circle" mode: wide --- -# ComfyOrNode ComfyOrNode는 입력 값 집합에 대해 논리적 OR 연산을 수행합니다. 제공된 값 중 하나라도 Python의 표준 진리값 규칙에 따라 참(true)으로 간주되면 `true`를 반환합니다. diff --git a/ko/built-in-nodes/ComfySoftSwitchNode.mdx b/ko/built-in-nodes/ComfySoftSwitchNode.mdx index 57caafa38..932599f02 100644 --- a/ko/built-in-nodes/ComfySoftSwitchNode.mdx +++ b/ko/built-in-nodes/ComfySoftSwitchNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfySoftSwitchNode" icon: "circle" mode: wide --- + 소프트 스위치 노드는 부울 조건에 따라 두 개의 입력 값 중 하나를 선택합니다. `switch`가 참(true)이면 `on_true` 입력의 값을 출력하고, `switch`가 거짓(false)이면 `on_false` 입력의 값을 출력합니다. 이 노드는 지연 평가(lazy) 방식으로 설계되어, 스위치 상태에 따라 필요한 입력만 평가합니다. ## 입력 diff --git a/ko/built-in-nodes/ComfySwitchNode.mdx b/ko/built-in-nodes/ComfySwitchNode.mdx index a63e0eae3..b1eb8a656 100644 --- a/ko/built-in-nodes/ComfySwitchNode.mdx +++ b/ko/built-in-nodes/ComfySwitchNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfySwitchNode" icon: "circle" mode: wide --- + Switch 노드는 불리언 조건에 따라 두 개의 입력 중 하나를 선택합니다. `switch`가 활성화된 경우 `on_true` 입력을 출력하고, `switch`가 비활성화된 경우 `on_false` 입력을 출력합니다. 이를 통해 워크플로우에서 조건부 로직을 생성하고 서로 다른 데이터 경로를 선택할 수 있습니다. ## 입력 @@ -21,7 +22,7 @@ Switch 노드는 불리언 조건에 따라 두 개의 입력 중 하나를 선 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `output` | 선택된 데이터입니다. `스위치`가 true이면 `참일 때` 입력의 값이고, `스위치`가 false이면 `거짓일 때` 입력의 값입니다. | MATCH_TYPE | +| `출력` | 선택된 데이터입니다. `스위치`가 true이면 `참일 때` 입력의 값이고, `스위치`가 false이면 `거짓일 때` 입력의 값입니다. | MATCH_TYPE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfySwitchNode/ko.md) diff --git a/ko/built-in-nodes/ConditioningAverage.mdx b/ko/built-in-nodes/ConditioningAverage.mdx index cd47016cd..ff0d72f1c 100644 --- a/ko/built-in-nodes/ConditioningAverage.mdx +++ b/ko/built-in-nodes/ConditioningAverage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningAverage" icon: "circle" mode: wide --- + `ConditioningAverage` 노드는 두 개의 서로 다른 컨디셔닝(예: 텍스트 프롬프트) 세트를 지정된 가중치에 따라 혼합하여, 두 컨디셔닝 사이에 위치하는 새로운 컨디셔닝 벡터를 생성합니다. 가중치 매개변수를 조정함으로써 최종 결과에 대한 각 컨디셔닝의 영향을 유연하게 제어할 수 있습니다. 이는 프롬프트 보간, 스타일 융합 등 고급 사용 사례에 특히 적합합니다. 아래 그림과 같이 `conditioning_to`의 강도를 조정하여 두 컨디셔닝 사이의 결과를 출력할 수 있습니다. diff --git a/ko/built-in-nodes/ConditioningCombine.mdx b/ko/built-in-nodes/ConditioningCombine.mdx index be1cae4fb..9efb40628 100644 --- a/ko/built-in-nodes/ConditioningCombine.mdx +++ b/ko/built-in-nodes/ConditioningCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningCombine" icon: "circle" mode: wide --- + 이 노드는 두 개의 컨디셔닝 입력을 단일 출력으로 결합하여 정보를 효과적으로 병합합니다. 두 조건은 리스트 연결(list concatenation)을 사용하여 결합됩니다. ## 입력 diff --git a/ko/built-in-nodes/ConditioningConcat.mdx b/ko/built-in-nodes/ConditioningConcat.mdx index 56b01b6cf..ca4d6d52c 100644 --- a/ko/built-in-nodes/ConditioningConcat.mdx +++ b/ko/built-in-nodes/ConditioningConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningConcat" icon: "circle" mode: wide --- + ConditioningConcat 노드는 컨디셔닝 벡터를 연결(concatenate)하도록 설계되었으며, 특히 'conditioning_from' 벡터를 'conditioning_to' 벡터에 병합합니다. 이 작업은 두 소스의 컨디셔닝 정보를 하나의 통합된 표현으로 결합해야 하는 시나리오에서 필수적입니다. ## 입력 diff --git a/ko/built-in-nodes/ConditioningMultiply.mdx b/ko/built-in-nodes/ConditioningMultiply.mdx new file mode 100644 index 000000000..6aed19583 --- /dev/null +++ b/ko/built-in-nodes/ConditioningMultiply.mdx @@ -0,0 +1,27 @@ +--- +title: "ConditioningMultiply - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConditioningMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConditioningMultiply" +icon: "circle" +mode: wide +--- + +이 노드는 컨디셔닝 값에 지정된 배율을 곱하여 생성 과정에서 컨디셔닝의 영향을 조정할 수 있도록 합니다. 기본 컨디셔닝 텐서와 풀링된 출력 값 모두에 배율을 적용하는 방식으로 작동합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `conditioning` | 조정할 컨디셔닝 데이터 | CONDITIONING | 예 | - | +| `multiplier` | 컨디셔닝 값에 곱할 배율 (기본값: 1.0) | FLOAT | 예 | -100.0 ~ 100.0 (단계: 0.01) | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `CONDITIONING` | 값이 곱해져 조정된 컨디셔닝 데이터 | CONDITIONING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningMultiply/ko.md) + +--- +**Source fingerprint (SHA-256):** `8d241e3d5d91e513c24ade5b4bece4bf879fe093a4be6d53dab11a5a0bf55616` diff --git a/ko/built-in-nodes/ConditioningSetArea.mdx b/ko/built-in-nodes/ConditioningSetArea.mdx index 03d356957..1454332ef 100644 --- a/ko/built-in-nodes/ConditioningSetArea.mdx +++ b/ko/built-in-nodes/ConditioningSetArea.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetArea" icon: "circle" mode: wide --- + 이 노드는 컨디셔닝 컨텍스트 내에서 특정 영역을 설정하여 컨디셔닝 정보를 수정하도록 설계되었습니다. 컨디셔닝 요소의 정밀한 공간 조작을 가능하게 하며, 지정된 치수와 강도에 따라 목표 지향적인 조정 및 개선을 수행할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ConditioningSetAreaPercentage.mdx b/ko/built-in-nodes/ConditioningSetAreaPercentage.mdx index 9572e8a0c..cacf5348e 100644 --- a/ko/built-in-nodes/ConditioningSetAreaPercentage.mdx +++ b/ko/built-in-nodes/ConditioningSetAreaPercentage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaPercentage" icon: "circle" mode: wide --- + ## 개요 ConditioningSetAreaPercentage 노드는 컨디셔닝 요소의 영향 영역을 백분율 값에 기반하여 조정하는 데 특화되어 있습니다. 이 노드는 전체 이미지 크기 대비 백분율로 영역의 크기와 위치를 지정할 수 있게 하며, 강도 매개변수를 통해 컨디셔닝 효과의 세기를 조절할 수 있습니다. diff --git a/ko/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx b/ko/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx index f26e7828c..c6c6bbd3d 100644 --- a/ko/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx +++ b/ko/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ConditioningSetAreaPercentageVideo" icon: "circle" mode: wide --- -# ConditioningSetAreaPercentageVideo ConditioningSetAreaPercentageVideo 노드는 비디오 생성을 위한 특정 영역과 시간적 범위를 정의하여 컨디셔닝 데이터를 수정합니다. 전체 차원에 대한 백분율 값을 사용하여 컨디셔닝이 적용될 영역의 위치, 크기 및 지속 시간을 설정할 수 있습니다. 이는 비디오 시퀀스의 특정 부분에 생성을 집중시키는 데 유용합니다. diff --git a/ko/built-in-nodes/ConditioningSetAreaStrength.mdx b/ko/built-in-nodes/ConditioningSetAreaStrength.mdx index a6d597208..c41dea548 100644 --- a/ko/built-in-nodes/ConditioningSetAreaStrength.mdx +++ b/ko/built-in-nodes/ConditioningSetAreaStrength.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaStrength" icon: "circle" mode: wide --- + 이 노드는 주어진 컨디셔닝 세트의 강도 속성을 수정하여, 생성 과정에 대한 컨디셔닝의 영향이나 강도를 조정할 수 있도록 설계되었습니다. ## 입력 diff --git a/ko/built-in-nodes/ConditioningSetDefaultAndCombine.mdx b/ko/built-in-nodes/ConditioningSetDefaultAndCombine.mdx index 1ca214774..dcf7bfb85 100644 --- a/ko/built-in-nodes/ConditioningSetDefaultAndCombine.mdx +++ b/ko/built-in-nodes/ConditioningSetDefaultAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetDefaultAndCombine" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningSetDefaultAndCombine/en.md) 이 노드는 후크 기반 시스템을 사용하여 기본 컨디셔닝 입력과 기본값 컨디셔닝 입력을 결합합니다. 두 컨디셔닝 소스를 단일 출력으로 병합하여, 기본 컨디셔닝이 불완전할 경우 기본값 컨디셔닝이 대체 또는 기반 역할을 수행할 수 있도록 합니다. diff --git a/ko/built-in-nodes/ConditioningSetMask.mdx b/ko/built-in-nodes/ConditioningSetMask.mdx index 76c8138ed..49d499853 100644 --- a/ko/built-in-nodes/ConditioningSetMask.mdx +++ b/ko/built-in-nodes/ConditioningSetMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetMask" icon: "circle" mode: wide --- + 이 노드는 지정된 강도로 마스크를 특정 영역에 적용하여 생성 모델의 컨디셔닝을 수정하도록 설계되었습니다. 컨디셔닝 내에서 대상 조정이 가능하므로 생성 과정을 보다 정밀하게 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ConditioningSetProperties.mdx b/ko/built-in-nodes/ConditioningSetProperties.mdx index e9b74bb0f..9f8af9c49 100644 --- a/ko/built-in-nodes/ConditioningSetProperties.mdx +++ b/ko/built-in-nodes/ConditioningSetProperties.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetProperties" icon: "circle" mode: wide --- + ConditioningSetProperties 노드는 강도, 영역 설정을 조정하고 선택적 마스크, 훅 또는 타임스텝 범위를 적용하여 컨디셔닝 데이터의 속성을 수정합니다. 이 노드를 사용하면 이미지 생성 중 컨디셔닝 데이터 적용에 영향을 주는 특정 매개변수를 설정하여 컨디셔닝이 생성 과정에 미치는 영향을 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx b/ko/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx index 462074681..349479d89 100644 --- a/ko/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx +++ b/ko/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetPropertiesAndCombine" icon: "circle" mode: wide --- + ConditioningSetPropertiesAndCombine 노드는 기존 컨디셔닝 입력에 새 컨디셔닝 입력의 속성을 적용하여 컨디셔닝 데이터를 수정합니다. 이 노드는 두 컨디셔닝 세트를 결합하면서 새 컨디셔닝의 강도를 제어하고 컨디셔닝 영역이 적용되는 방식을 지정합니다. ## 입력 diff --git a/ko/built-in-nodes/ConditioningSetTimestepRange.mdx b/ko/built-in-nodes/ConditioningSetTimestepRange.mdx index f4d71ca33..1a977ce97 100644 --- a/ko/built-in-nodes/ConditioningSetTimestepRange.mdx +++ b/ko/built-in-nodes/ConditioningSetTimestepRange.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetTimestepRange" icon: "circle" mode: wide --- + 이 노드는 특정 시간 단위 범위를 설정하여 컨디셔닝의 시간적 측면을 조정하도록 설계되었습니다. 컨디셔닝 프로세스의 시작점과 종료점을 정밀하게 제어할 수 있어 보다 목표 지향적이고 효율적인 생성을 가능하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/ConditioningStableAudio.mdx b/ko/built-in-nodes/ConditioningStableAudio.mdx index d8d0ae6b0..3735f8003 100644 --- a/ko/built-in-nodes/ConditioningStableAudio.mdx +++ b/ko/built-in-nodes/ConditioningStableAudio.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ConditioningStableAudio" icon: "circle" mode: wide --- -# ConditioningStableAudio 노드 ConditioningStableAudio 노드는 오디오 생성을 위해 긍정 및 부정 조건 입력에 타이밍 정보를 추가합니다. 이 노드는 시작 시간과 전체 지속 시간 매개변수를 설정하여 오디오 콘텐츠가 생성되어야 하는 시점과 지속 시간을 제어합니다. 오디오 특화 타이밍 메타데이터를 추가하여 기존 조건 데이터를 수정합니다. @@ -22,8 +21,8 @@ ConditioningStableAudio 노드는 오디오 생성을 위해 긍정 및 부정 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 오디오 타이밍 정보가 적용된 수정된 긍정 조건 | CONDITIONING | -| `부정 조건` | 오디오 타이밍 정보가 적용된 수정된 부정 조건 | CONDITIONING | +| `positive` | 오디오 타이밍 정보가 적용된 수정된 긍정 조건 | CONDITIONING | +| `negative` | 오디오 타이밍 정보가 적용된 수정된 부정 조건 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningStableAudio/ko.md) diff --git a/ko/built-in-nodes/ConditioningTimestepsRange.mdx b/ko/built-in-nodes/ConditioningTimestepsRange.mdx index cb9108bfd..e22d286b5 100644 --- a/ko/built-in-nodes/ConditioningTimestepsRange.mdx +++ b/ko/built-in-nodes/ConditioningTimestepsRange.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ConditioningTimestepsRange" icon: "circle" mode: wide --- -# ConditioningTimestepsRange 노드 ConditioningTimestepsRange 노드는 생성 과정에서 컨디셔닝 효과가 적용되는 시점을 제어하기 위해 세 개의 개별적인 타임스텝 범위를 생성합니다. 시작 및 종료 백분율 값을 입력받아 전체 타임스텝 범위(0.0~1.0)를 세 개의 구간으로 나눕니다: 지정된 백분율 사이의 주 범위, 시작 백분율 이전의 범위, 종료 백분율 이후의 범위입니다. @@ -21,8 +20,8 @@ ConditioningTimestepsRange 노드는 생성 과정에서 컨디셔닝 효과가 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `이전 범위` | start_percent와 end_percent로 정의된 주 타임스텝 범위 | TIMESTEPS_RANGE | -| `이후 범위` | 0.0부터 start_percent까지의 타임스텝 범위 | TIMESTEPS_RANGE | -| `AFTER_RANGE` | end_percent부터 1.0까지의 타임스텝 범위 | TIMESTEPS_RANGE | +| `이전 범위` | 0.0부터 start_percent까지의 타임스텝 범위 | TIMESTEPS_RANGE | +| `이후 범위` | end_percent부터 1.0까지의 타임스텝 범위 | TIMESTEPS_RANGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningTimestepsRange/ko.md) diff --git a/ko/built-in-nodes/ConditioningZeroOut.mdx b/ko/built-in-nodes/ConditioningZeroOut.mdx index 7eb01adf5..8ccf23fc0 100644 --- a/ko/built-in-nodes/ConditioningZeroOut.mdx +++ b/ko/built-in-nodes/ConditioningZeroOut.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningZeroOut" icon: "circle" mode: wide --- + 이 노드는 컨디셔닝 데이터 구조 내의 특정 요소를 0으로 설정하여, 이후 처리 단계에서 해당 요소의 영향을 효과적으로 중화합니다. 컨디셔닝의 내부 표현을 직접 조작해야 하는 고급 컨디셔닝 작업을 위해 설계되었습니다. ## 입력 diff --git a/ko/built-in-nodes/ContextWindowsManual.mdx b/ko/built-in-nodes/ContextWindowsManual.mdx index 6c85cdcba..66dd291e0 100644 --- a/ko/built-in-nodes/ContextWindowsManual.mdx +++ b/ko/built-in-nodes/ContextWindowsManual.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ContextWindowsManual" icon: "circle" mode: wide --- -# 컨텍스트 윈도우(수동) 노드 컨텍스트 윈도우(수동) 노드는 샘플링 중 모델에 대한 컨텍스트 윈도우를 수동으로 구성할 수 있게 해줍니다. 지정된 길이, 중첩 및 스케줄링 패턴으로 중첩되는 컨텍스트 세그먼트를 생성하여, 세그먼트 간 연속성을 유지하면서 데이터를 관리 가능한 청크 단위로 처리합니다. 이 노드는 노이즈 셔플링, 컨디셔닝 유지 및 인과적 윈도우 수정을 포함하여 컨텍스트 윈도우 적용 방식을 제어하기 위한 고급 옵션을 제공합니다. diff --git a/ko/built-in-nodes/ControlNetApply.mdx b/ko/built-in-nodes/ControlNetApply.mdx index 366baafdd..474ca6e3a 100644 --- a/ko/built-in-nodes/ControlNetApply.mdx +++ b/ko/built-in-nodes/ControlNetApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApply" icon: "circle" mode: wide --- + ControlNet을 사용하려면 입력 이미지의 전처리가 필요합니다. ComfyUI 기본 노드에는 전처리기와 ControlNet 모델이 포함되어 있지 않으므로, 먼저 ControlNet 전처리기 [여기서 전처리기 다운로드](https://github.com/Fannovel16/comfy_controlnet_preprocessors)와 해당 ControlNet 모델을 설치해 주시기 바랍니다. ## 입력 diff --git a/ko/built-in-nodes/ControlNetApplyAdvanced.mdx b/ko/built-in-nodes/ControlNetApplyAdvanced.mdx index 92a07de9f..c2f00af5c 100644 --- a/ko/built-in-nodes/ControlNetApplyAdvanced.mdx +++ b/ko/built-in-nodes/ControlNetApplyAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApplyAdvanced" icon: "circle" mode: wide --- + 이 노드는 이미지와 컨트롤 넷 모델을 기반으로 컨디셔닝 데이터에 고급 컨트롤 넷 변환을 적용합니다. 컨트롤 넷이 생성 콘텐츠에 미치는 영향력을 세밀하게 조정하여 컨디셔닝에 대한 보다 정밀하고 다양한 수정을 가능하게 합니다. ## 입력 @@ -23,7 +24,7 @@ mode: wide | 매개변수 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 컨트롤 넷 변환 적용 후 수정된 긍정 컨디셔닝 데이터로, 입력 매개변수에 기반한 개선 사항을 반영합니다. | `CONDITIONING` | +| `긍정 조건` | 컨트롤 넷 변환 적용 후 수정된 긍정 컨디셔닝 데이터로, 입력 매개변수에 기반한 개선 사항을 반영합니다. | `CONDITIONING` | | `부정 조건` | 컨트롤 넷 변환 적용 후 수정된 부정 컨디셔닝 데이터로, 입력 매개변수에 기반한 특정 특징의 억제 또는 제거를 반영합니다. | `CONDITIONING` | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetApplyAdvanced/ko.md) diff --git a/ko/built-in-nodes/ControlNetApplySD3.mdx b/ko/built-in-nodes/ControlNetApplySD3.mdx index 149445698..d14cd54b4 100644 --- a/ko/built-in-nodes/ControlNetApplySD3.mdx +++ b/ko/built-in-nodes/ControlNetApplySD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApplySD3" icon: "circle" mode: wide --- + 이 노드는 ControlNet 안내(guidance)를 Stable Diffusion 3 컨디셔닝에 적용합니다. 긍정 및 부정 컨디셔닝 입력과 함께 ControlNet 모델 및 이미지를 입력받아, 조정 가능한 강도 및 타이밍 매개변수로 제어 안내를 적용하여 생성 과정에 영향을 줍니다. **참고:** 이 노드는 더 이상 사용되지 않음(deprecated)으로 표시되었으며, 향후 버전에서 제거될 수 있습니다. @@ -26,7 +27,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | ControlNet 안내가 적용된 수정된 긍정 컨디셔닝 | CONDITIONING | +| `긍정 조건` | ControlNet 안내가 적용된 수정된 긍정 컨디셔닝 | CONDITIONING | | `부정 조건` | ControlNet 안내가 적용된 수정된 부정 컨디셔닝 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetApplySD3/ko.md) diff --git a/ko/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx b/ko/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx index 457c3a90f..1683dc3e7 100644 --- a/ko/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx +++ b/ko/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ControlNetInpaintingAliMamaApply" icon: "circle" mode: wide --- -# ControlNetInpaintingAliMamaApply ControlNetInpaintingAliMamaApply 노드는 인페인팅 작업을 위해 ControlNet 컨디셔닝을 적용하여, 포지티브 및 네거티브 컨디셔닝을 제어 이미지 및 마스크와 결합합니다. 입력 이미지와 마스크를 처리하여 생성 과정을 안내하는 수정된 컨디셔닝을 생성하므로, 이미지의 어느 영역을 인페인팅할지 정밀하게 제어할 수 있습니다. 이 노드는 생성 과정의 여러 단계에서 ControlNet의 영향을 미세 조정하기 위한 강도 조정 및 타이밍 제어 기능을 지원합니다. @@ -29,7 +28,7 @@ ControlNetInpaintingAliMamaApply 노드는 인페인팅 작업을 위해 Control | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 인페인팅을 위해 ControlNet이 적용된 수정된 포지티브 컨디셔닝 | CONDITIONING | +| `긍정 조건` | 인페인팅을 위해 ControlNet이 적용된 수정된 포지티브 컨디셔닝 | CONDITIONING | | `부정 조건` | 인페인팅을 위해 ControlNet이 적용된 수정된 네거티브 컨디셔닝 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetInpaintingAliMamaApply/ko.md) diff --git a/ko/built-in-nodes/ControlNetLoader.mdx b/ko/built-in-nodes/ControlNetLoader.mdx index 83b7b52be..be955c9f9 100644 --- a/ko/built-in-nodes/ControlNetLoader.mdx +++ b/ko/built-in-nodes/ControlNetLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/controlnet` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 설정된 추가 경로의 모델도 함께 읽어옵니다. 때로는 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수도 있습니다. ControlNetLoader 노드는 지정된 경로에서 ControlNet 모델을 로드하도록 설계되었습니다. 이 노드는 생성된 콘텐츠에 제어 메커니즘을 적용하거나 제어 신호를 기반으로 기존 콘텐츠를 수정하는 데 필수적인 ControlNet 모델을 초기화하는 중요한 역할을 합니다. diff --git a/ko/built-in-nodes/ConvertArrayToString.mdx b/ko/built-in-nodes/ConvertArrayToString.mdx new file mode 100644 index 000000000..41eb1baa6 --- /dev/null +++ b/ko/built-in-nodes/ConvertArrayToString.mdx @@ -0,0 +1,29 @@ +--- +title: "ConvertArrayToString - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConvertArrayToString node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConvertArrayToString" +icon: "circle" +mode: wide +--- + +## 개요 + +Convert Array to String 노드는 항목 배열(리스트)을 받아서 형식화된 JSON 문자열로 변환합니다. 이는 배열 데이터를 표시, 로깅 또는 문자열 입력을 기대하는 다른 시스템으로 전달하기 위해 직렬화해야 할 때 유용합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `배열` | JSON 문자열로 변환할 배열 | ARRAY | 예 | - | +| `들여쓰기` | 들여쓰기 레벨당 공백 수. 0은 압축된 한 줄 문자열을 생성합니다 (기본값: 2) | INT | 아니요 | 0 ~ 8 | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `STRING` | JSON 형식의 문자열로 변환된 배열 | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertArrayToString/ko.md) + +--- +**Source fingerprint (SHA-256):** `ac8397fed0336f546403ee3e1f17d7e8f5973190b102e74943f098bf6905f726` diff --git a/ko/built-in-nodes/ConvertDictionaryToString.mdx b/ko/built-in-nodes/ConvertDictionaryToString.mdx new file mode 100644 index 000000000..0c96486a6 --- /dev/null +++ b/ko/built-in-nodes/ConvertDictionaryToString.mdx @@ -0,0 +1,27 @@ +--- +title: "ConvertDictionaryToString - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConvertDictionaryToString node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConvertDictionaryToString" +icon: "circle" +mode: wide +--- + +이 노드는 딕셔너리(키-값 쌍의 집합)를 일반적으로 JSON 형식의 텍스트 문자열로 변환합니다. 들여쓰기 수준을 조절하여 출력 결과를 더 읽기 쉽게 만들거나 간결하게 만들 수 있습니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `딕셔너리` | 문자열로 변환할 딕셔너리 | DICT | 예 | - | +| `들여쓰기` | 들여쓰기 수준당 공백 수입니다. 0으로 설정하면 간결한 한 줄 문자열이 생성됩니다(기본값: 2) | INT | 아니요 | 0 ~ 8 | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `STRING` | JSON 형식의 문자열로 변환된 딕셔너리 | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertDictionaryToString/ko.md) + +--- +**Source fingerprint (SHA-256):** `ae4e9889d5347acfc69166bac66f2ba63f5cd37dafab25a9e0aff6bfe7381219` diff --git a/ko/built-in-nodes/ConvertStringToComboNode.mdx b/ko/built-in-nodes/ConvertStringToComboNode.mdx index f44c553b5..0b8c9cf52 100644 --- a/ko/built-in-nodes/ConvertStringToComboNode.mdx +++ b/ko/built-in-nodes/ConvertStringToComboNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConvertStringToComboNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertStringToComboNode/en.md) Convert String to Combo 노드는 텍스트 문자열을 입력으로 받아 Combo 데이터 유형으로 변환합니다. 이를 통해 Combo 입력이 필요한 다른 노드에서 텍스트 값을 선택 항목으로 사용할 수 있습니다. 문자열 값을 변경하지 않고 그대로 전달하되 데이터 유형만 변경합니다. diff --git a/ko/built-in-nodes/CosmosImageToVideoLatent.mdx b/ko/built-in-nodes/CosmosImageToVideoLatent.mdx index 38189dd26..3d8bf1b39 100644 --- a/ko/built-in-nodes/CosmosImageToVideoLatent.mdx +++ b/ko/built-in-nodes/CosmosImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CosmosImageToVideoLatent" icon: "circle" mode: wide --- + CosmosImageToVideoLatent 노드는 입력 이미지로부터 비디오 잠재 표현을 생성합니다. 빈 비디오 잠재를 생성하고, 선택적으로 시작 및/또는 종료 이미지를 비디오 시퀀스의 첫 프레임과 마지막 프레임에 인코딩합니다. 이미지가 제공되면, 생성 중에 잠재의 어느 부분을 보존해야 하는지 나타내는 해당 노이즈 마스크도 함께 생성됩니다. ## 입력 diff --git a/ko/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx b/ko/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx index 3033dd5f8..31ac11be9 100644 --- a/ko/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx +++ b/ko/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CosmosPredict2ImageToVideoLatent" icon: "circle" mode: wide --- + CosmosPredict2ImageToVideoLatent 노드는 이미지로부터 비디오 생성을 위한 비디오 잠재 표현을 생성합니다. 빈 비디오 잠재 표현을 생성하거나 시작 이미지와 종료 이미지를 통합하여 지정된 크기와 길이의 비디오 시퀀스를 생성할 수 있습니다. 이 노드는 이미지를 비디오 처리에 적합한 잠재 공간 형식으로 인코딩합니다. ## 입력 diff --git a/ko/built-in-nodes/CreateBoundingBoxes.mdx b/ko/built-in-nodes/CreateBoundingBoxes.mdx new file mode 100644 index 000000000..c03591b3c --- /dev/null +++ b/ko/built-in-nodes/CreateBoundingBoxes.mdx @@ -0,0 +1,31 @@ +--- +title: "CreateBoundingBoxes - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the CreateBoundingBoxes node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "CreateBoundingBoxes" +icon: "circle" +mode: wide +--- + +이 노드는 이미지 내 객체나 텍스트 영역 주위에 경계 상자를 그릴 수 있는 캔버스 인터페이스를 제공합니다. 픽셀 공간의 경계 상자 좌표, Ideogram 프롬프트 형식과 호환되는 구조화된 요소 데이터, 그리고 레이블과 색상 팔레트가 포함된 그려진 상자를 보여주는 미리보기 이미지를 출력합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `배경` | 캔버스 및 미리보기의 배경으로 사용되는 선택적 이미지입니다. | IMAGE | 아니요 | - | +| `너비` | 캔버스 및 경계 상자용 픽셀 그리드의 너비입니다(기본값: 1024). | INT | 예 | 64 ~ 16384 (단위: 16) | +| `높이` | 캔버스 및 경계 상자용 픽셀 그리드의 높이입니다(기본값: 1024). | INT | 예 | 64 ~ 16384 (단위: 16) | +| `에디터 상태` | 경계 상자를 그리고 각 상자의 유형, 텍스트, 설명, 색상 팔레트를 설정합니다. 배경 요소부터 시작하여 전경 요소를 마지막으로 배치하십시오. | BOUNDING_BOXES | 예 | - | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `미리보기` | 모든 경계 상자가 렌더링된 캔버스를 보여주는 RGB 이미지로, 레이블, 색상 팔레트 견본, 설명 텍스트가 포함됩니다. | IMAGE | +| `바운딩 박스` | 픽셀 좌표로 표현된 경계 상자 목록으로, 각 상자는 x, y, 너비, 높이 값을 포함합니다. | BOUNDING_BOX | +| `요소` | 요소 객체의 구조화된 배열로, 각 객체는 유형, 경계 상자 좌표(0-1000으로 정규화), 텍스트(텍스트 유형의 경우), 설명, 색상 팔레트를 포함합니다. | ARRAY | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateBoundingBoxes/ko.md) + +--- +**Source fingerprint (SHA-256):** `a63939f13edc6c6507590a390dcd6d0a3321febb5831baab1655d9952228612c` diff --git a/ko/built-in-nodes/CreateCameraInfo.mdx b/ko/built-in-nodes/CreateCameraInfo.mdx index d667c1cca..3ddc76476 100644 --- a/ko/built-in-nodes/CreateCameraInfo.mdx +++ b/ko/built-in-nodes/CreateCameraInfo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateCameraInfo" icon: "circle" mode: wide --- -# 카메라 정보 생성 카메라 정보 생성 노드는 3D 렌더링을 위한 카메라 정보 구조를 구축합니다. 카메라 정의를 위해 세 가지 모드를 지원합니다: 궤도(대상 주위의 요/피치/거리), 시점(명시적 월드 위치), 쿼터니언(위치 및 회전). 좌표계는 Y축이 위쪽 방향인 오른손 좌표계입니다. diff --git a/ko/built-in-nodes/CreateHookKeyframe.mdx b/ko/built-in-nodes/CreateHookKeyframe.mdx index 15309be1a..8bd0f6ee3 100644 --- a/ko/built-in-nodes/CreateHookKeyframe.mdx +++ b/ko/built-in-nodes/CreateHookKeyframe.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateHookKeyframe" icon: "circle" mode: wide --- -# Create Hook Keyframe (후크 키프레임 생성) Create Hook Keyframe 노드는 생성 과정에서 후크 동작이 변경되는 특정 지점을 정의할 수 있게 해줍니다. 이 노드는 생성 진행률의 특정 백분율 지점에서 후크 강도를 수정하는 키프레임을 생성하며, 이러한 키프레임들을 연결하여 복잡한 스케줄링 패턴을 만들 수 있습니다. @@ -21,7 +20,7 @@ Create Hook Keyframe 노드는 생성 과정에서 후크 동작이 변경되는 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `HOOK_KF` | 새로 생성된 키프레임을 포함한 후크 키프레임 그룹 | HOOK_KEYFRAMES | +| `KF 후크` | 새로 생성된 키프레임을 포함한 후크 키프레임 그룹 | HOOK_KEYFRAMES | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframe/ko.md) diff --git a/ko/built-in-nodes/CreateHookKeyframesFromFloats.mdx b/ko/built-in-nodes/CreateHookKeyframesFromFloats.mdx index 59224803d..967087e8b 100644 --- a/ko/built-in-nodes/CreateHookKeyframesFromFloats.mdx +++ b/ko/built-in-nodes/CreateHookKeyframesFromFloats.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframesFromFloats" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesFromFloats/en.md) 이 노드는 부동소수점 강도 값 목록에서 후크 키프레임을 생성하며, 지정된 시작 및 종료 백분율 사이에 균등하게 분배합니다. 각 강도 값이 애니메이션 타임라인의 특정 백분율 위치에 할당된 키프레임 시퀀스를 생성합니다. 이 노드는 새 키프레임 그룹을 생성하거나 기존 그룹에 추가할 수 있으며, 디버깅 목적으로 생성된 키프레임을 출력하는 옵션을 제공합니다. @@ -25,7 +26,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `HOOK_KF` | 새로 생성된 키프레임을 포함하는 후크 키프레임 그룹입니다. 새 그룹이거나 입력 키프레임 그룹에 추가된 그룹입니다 | HOOK_KEYFRAMES | +| `KF 후크` | 새로 생성된 키프레임을 포함하는 후크 키프레임 그룹입니다. 새 그룹이거나 입력 키프레임 그룹에 추가된 그룹입니다 | HOOK_KEYFRAMES | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesFromFloats/ko.md) diff --git a/ko/built-in-nodes/CreateHookKeyframesInterpolated.mdx b/ko/built-in-nodes/CreateHookKeyframesInterpolated.mdx index cc7958a99..b2adff880 100644 --- a/ko/built-in-nodes/CreateHookKeyframesInterpolated.mdx +++ b/ko/built-in-nodes/CreateHookKeyframesInterpolated.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateHookKeyframesInterpolated" icon: "circle" mode: wide --- -# CreateHookKeyframesInterpolated 시작점과 끝점 사이에 보간된 강도 값을 사용하여 후크 키프레임 시퀀스를 생성합니다. 이 노드는 생성 과정의 지정된 백분율 범위에 걸쳐 강도 매개변수가 부드럽게 전환되는 여러 키프레임을 생성하며, 다양한 보간 방법을 사용하여 전환 곡선을 제어합니다. @@ -26,7 +25,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `HOOK_KF` | 보간된 시퀀스를 포함하는 생성된 후크 키프레임 그룹 | HOOK_KEYFRAMES | +| `KF 후크` | 보간된 시퀀스를 포함하는 생성된 후크 키프레임 그룹 | HOOK_KEYFRAMES | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesInterpolated/ko.md) diff --git a/ko/built-in-nodes/CreateHookLora.mdx b/ko/built-in-nodes/CreateHookLora.mdx index 511215d96..4c3de6c09 100644 --- a/ko/built-in-nodes/CreateHookLora.mdx +++ b/ko/built-in-nodes/CreateHookLora.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateHookLora" icon: "circle" mode: wide --- -# Create Hook LoRA 노드 Create Hook LoRA 노드는 모델에 LoRA(Low-Rank Adaptation) 수정을 적용하기 위한 훅 객체를 생성합니다. 지정된 LoRA 파일을 로드하고 모델 및 CLIP 강도를 조정할 수 있는 훅을 만든 다음, 전달된 기존 훅과 결합합니다. 이 노드는 이전에 로드된 LoRA 파일을 캐싱하여 중복 작업을 방지함으로써 LoRA 로딩을 효율적으로 관리합니다. diff --git a/ko/built-in-nodes/CreateHookLoraModelOnly.mdx b/ko/built-in-nodes/CreateHookLoraModelOnly.mdx index 6b1d29a20..17f791612 100644 --- a/ko/built-in-nodes/CreateHookLoraModelOnly.mdx +++ b/ko/built-in-nodes/CreateHookLoraModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookLoraModelOnly" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookLoraModelOnly/en.md) 이 노드는 모델 구성 요소에만 적용되는 LoRA(Low-Rank Adaptation) 후크를 생성하며, CLIP 구성 요소는 완전히 변경되지 않은 상태로 유지합니다. LoRA 파일을 로드하고 지정된 강도로 모델에 적용하는 동시에 CLIP 강도를 0으로 설정합니다. 이 노드는 이전 후크와 연결되어 복잡한 수정 파이프라인을 구축할 수 있습니다. diff --git a/ko/built-in-nodes/CreateHookModelAsLora.mdx b/ko/built-in-nodes/CreateHookModelAsLora.mdx index acd39ecd3..bb09c9e9e 100644 --- a/ko/built-in-nodes/CreateHookModelAsLora.mdx +++ b/ko/built-in-nodes/CreateHookModelAsLora.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookModelAsLora" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookModelAsLora/en.md) 이 노드는 체크포인트 가중치를 로드하고 모델 및 CLIP 구성 요소에 강도 조정을 적용하여 LoRA(저차 적응) 방식의 훅 모델을 생성합니다. 훅 기반 접근 방식을 통해 기존 모델에 LoRA 스타일 수정을 적용할 수 있어, 영구적인 모델 변경 없이 미세 조정 및 적응이 가능합니다. 이 노드는 이전 훅과 결합할 수 있으며, 로드된 가중치를 캐싱하여 효율성을 높입니다. diff --git a/ko/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx b/ko/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx index c97423b20..bf2981aaf 100644 --- a/ko/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx +++ b/ko/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookModelAsLoraModelOnly" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookModelAsLoraModelOnly/en.md) 이 노드는 LoRA(저차원 적응) 모델을 적용하여 신경망의 모델 구성 요소만 수정하는 훅을 생성합니다. 체크포인트 파일을 로드하고 지정된 강도로 모델에 적용하며, CLIP 구성 요소는 변경하지 않습니다. 이는 기본 CreateHookModelAsLora 클래스의 기능을 확장한 실험적 노드입니다. diff --git a/ko/built-in-nodes/CreateList.mdx b/ko/built-in-nodes/CreateList.mdx index 8cb6c778c..a9b0c7be0 100644 --- a/ko/built-in-nodes/CreateList.mdx +++ b/ko/built-in-nodes/CreateList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateList" icon: "circle" mode: wide --- + **Create List (목록 생성)** Create List 노드는 여러 입력을 하나의 순차적인 목록으로 결합합니다. 동일한 데이터 타입의 여러 입력을 받아 연결된 순서대로 연결합니다. 이 노드는 워크플로우에서 다른 노드가 처리할 이미지나 텍스트와 같은 데이터 배치를 준비하는 데 유용합니다. @@ -21,7 +22,7 @@ Create List 노드는 여러 입력을 하나의 순차적인 목록으로 결 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `list` | 연결된 입력의 모든 항목을 제공된 순서대로 연결한 단일 목록입니다. 출력 데이터 타입은 입력 데이터 타입과 일치합니다. | 다양함 | +| `목록` | 연결된 입력의 모든 항목을 제공된 순서대로 연결한 단일 목록입니다. 출력 데이터 타입은 입력 데이터 타입과 일치합니다. | 다양함 | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateList/ko.md) diff --git a/ko/built-in-nodes/CreateVideo.mdx b/ko/built-in-nodes/CreateVideo.mdx index 18d54d49e..58d2dbd7e 100644 --- a/ko/built-in-nodes/CreateVideo.mdx +++ b/ko/built-in-nodes/CreateVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateVideo" icon: "circle" mode: wide --- -# Create Video 노드 Create Video 노드는 이미지 시퀀스로부터 비디오 파일을 생성합니다. 초당 프레임 수를 사용하여 재생 속도를 지정할 수 있으며, 선택적으로 비디오에 오디오를 추가할 수 있습니다. 이 노드는 이미지들을 지정된 프레임 속도로 재생 가능한 비디오 형식으로 결합합니다. diff --git a/ko/built-in-nodes/CropByBBoxes.mdx b/ko/built-in-nodes/CropByBBoxes.mdx index f8da8e28d..95b2631a5 100644 --- a/ko/built-in-nodes/CropByBBoxes.mdx +++ b/ko/built-in-nodes/CropByBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CropByBBoxes" icon: "circle" mode: wide --- + CropByBBoxes 노드는 입력 이미지 배치에서 특정 직사각형 영역을 추출하고 크기를 조정합니다. 제공된 경계 상자 좌표를 사용하여 각 이미지에서 자를 영역을 정의합니다. 잘린 영역은 지정된 출력 크기로 조정되며, 자른 영역을 늘리거나 원본 종횡비를 유지하도록 패딩하는 옵션이 있습니다. ## 입력 diff --git a/ko/built-in-nodes/CropMask.mdx b/ko/built-in-nodes/CropMask.mdx index 13c8fb71b..c79d9b47d 100644 --- a/ko/built-in-nodes/CropMask.mdx +++ b/ko/built-in-nodes/CropMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CropMask" icon: "circle" mode: wide --- + CropMask 노드는 주어진 마스크에서 지정된 영역을 자르기 위해 설계되었습니다. 사용자는 좌표와 크기를 지정하여 관심 영역을 정의할 수 있으며, 이를 통해 마스크의 일부를 효과적으로 추출하여 추가 처리 또는 분석에 사용할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/CurveEditor.mdx b/ko/built-in-nodes/CurveEditor.mdx index 1b076d0d8..0fec1188f 100644 --- a/ko/built-in-nodes/CurveEditor.mdx +++ b/ko/built-in-nodes/CurveEditor.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CurveEditor" icon: "circle" mode: wide --- + Curve Editor 노드는 곡선을 조정하고 미세 조정할 수 있는 시각적 인터페이스를 제공합니다. 입력 곡선의 형태를 수정할 수 있으며, 선택적으로 히스토그램을 통해 분포를 시각화할 수 있습니다. 이 노드는 수정된 곡선을 출력하여 워크플로우의 다른 부분에서 사용할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/CustomCombo.mdx b/ko/built-in-nodes/CustomCombo.mdx index 07189dffd..58d081b27 100644 --- a/ko/built-in-nodes/CustomCombo.mdx +++ b/ko/built-in-nodes/CustomCombo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CustomCombo" icon: "circle" mode: wide --- -# Custom Combo 노드 Custom Combo 노드를 사용하면 사용자 정의 텍스트 옵션 목록이 포함된 드롭다운 메뉴를 만들 수 있습니다. 이 노드는 워크플로우 내에서 호환성을 보장하기 위해 백엔드 표현을 제공하는 프론트엔드 중심 노드입니다. 드롭다운에서 옵션을 선택하면 노드는 해당 텍스트를 문자열로 출력하고 해당 인덱스 위치도 함께 출력합니다. diff --git a/ko/built-in-nodes/DA3GeometryToMesh.mdx b/ko/built-in-nodes/DA3GeometryToMesh.mdx new file mode 100644 index 000000000..95cdd9fe0 --- /dev/null +++ b/ko/built-in-nodes/DA3GeometryToMesh.mdx @@ -0,0 +1,32 @@ +--- +title: "DA3GeometryToMesh - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3GeometryToMesh node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3GeometryToMesh" +icon: "circle" +mode: wide +--- + +이 노드는 깊이 맵을 역투영하고 결과 포인트 클라우드를 삼각 측량하여 DA3_GEOMETRY 패킷을 3D 메시로 변환합니다. 배치에서 단일 이미지를 처리하고 3D 렌더링에 적합한 텍스처가 있거나 없는 메시를 생성합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 깊이 맵, 선택적 신뢰도 맵, 선택적 하늘 맵 및 소스 이미지를 포함하는 DA3_GEOMETRY 패킷 | DA3_GEOMETRY | 예 | - | +| `batch_index` | 변환할 배치의 이미지 인덱스입니다. 이미지별 정점 개수가 다르므로 배치를 쌓을 수 없습니다(기본값: 0) | INT | 예 | 0 ~ 4096 | +| `decimation` | 정점 간격입니다. 1 = 전체 해상도, 2 = 절반 해상도 등(기본값: 1) | INT | 예 | 1 ~ 8 | +| `discontinuity_threshold` | 3x3 깊이 범위가 이 비율을 초과하는 삼각형을 제거합니다. 0 = 비활성화(기본값: 0.04) | FLOAT | 예 | 0.0 ~ 1.0 | +| `confidence_threshold` | 이미지별 정규화된 신뢰도가 이 값보다 낮은 픽셀을 제외합니다. 0 = 모두 유지, 1 = 가장 신뢰도가 높은 단일 픽셀만 유지합니다. 지오메트리에 신뢰도 맵이 있는 경우 사용됩니다(Small/Base 모델)(기본값: 0.1) | FLOAT | 예 | 0.0 ~ 1.0 | +| `use_sky_mask` | 하늘 확률 픽셀(하늘 >= 0.5)을 메시에서 제외합니다. 지오메트리에 하늘 맵이 있는 경우 사용됩니다(Mono/Metric 모델)(기본값: True) | BOOLEAN | 예 | True 또는 False | +| `texture` | 소스 이미지를 기본 색상 텍스처로 사용합니다(기본값: True) | BOOLEAN | 예 | True 또는 False | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `MESH` | 정점, 면, UV 좌표 및 선택적 텍스처가 포함된 삼각 측량된 3D 메시 | MESH | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToMesh/ko.md) + +--- +**Source fingerprint (SHA-256):** `1d311223a8d131030bcd4930d21852a21ac9dd5758e7f8b8d20b1cf68698893b` diff --git a/ko/built-in-nodes/DA3GeometryToPointCloud.mdx b/ko/built-in-nodes/DA3GeometryToPointCloud.mdx new file mode 100644 index 000000000..cc17ca3e4 --- /dev/null +++ b/ko/built-in-nodes/DA3GeometryToPointCloud.mdx @@ -0,0 +1,30 @@ +--- +title: "DA3GeometryToPointCloud - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3GeometryToPointCloud node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3GeometryToPointCloud" +icon: "circle" +mode: wide +--- + +이 노드는 DA3_GEOMETRY 객체의 깊이 맵을 3D 포인트 클라우드로 변환합니다. 신뢰도 및 하늘 마스크를 기반으로 필터링을 적용하며, 다중 뷰 장면에 적합한 공통 월드 좌표계로 포인트를 변환합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 깊이 데이터와 선택적 이미지, 신뢰도 및 하늘 맵을 포함하는 DA3_GEOMETRY 객체 | DA3_GEOMETRY | 예 | - | +| `batch_index` | 배치 중 변환할 이미지 (기본값: 0) | INT | 예 | 0 ~ 4096 | +| `confidence_threshold` | 이미지별 정규화된 신뢰도가 이 값보다 낮은 픽셀을 제외합니다 (0 = 모두 유지). 지오메트리에 신뢰도 맵이 있는 경우 사용됩니다 (Small/Base 모델). (기본값: 0.1) | FLOAT | 예 | 0.0 ~ 1.0 | +| `use_sky_mask` | 하늘 확률 픽셀(하늘 >= 0.5)을 제외합니다. 지오메트리에 하늘 맵이 있는 경우 사용됩니다 (Mono/Metric 모델). (기본값: True) | BOOLEAN | 예 | True 또는 False | +| `downsample` | 매 N번째 픽셀을 사용합니다 (1 = 전체 해상도). 값이 높을수록 포인트가 적어지고 처리 속도가 빨라집니다. (기본값: 1) | INT | 예 | 1 ~ 16 | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `point_cloud` | 필터링된 3D 포인트, 선택적 색상 및 선택적 신뢰도 값을 포함하는 포인트 클라우드 객체 | DA3_POINT_CLOUD | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToPointCloud/ko.md) + +--- +**Source fingerprint (SHA-256):** `3cf5bdbb8afdfcfc02f9832a8cbc5a3df49da755dea6df01792aa6ef9e5d7287` diff --git a/ko/built-in-nodes/DA3Inference.mdx b/ko/built-in-nodes/DA3Inference.mdx new file mode 100644 index 000000000..5d503d9f4 --- /dev/null +++ b/ko/built-in-nodes/DA3Inference.mdx @@ -0,0 +1,38 @@ +--- +title: "DA3Inference - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3Inference node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3Inference" +icon: "circle" +mode: wide +--- + +이 노드는 이미지에 Depth Anything 3 모델을 실행하여 깊이와 형상 정보를 추정합니다. 다중 뷰 모드에서는 여러 이미지를 동일한 장면의 서로 다른 뷰로 함께 처리하여 기하학적으로 일관된 깊이 맵과 카메라 포즈를 생성합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `da3_model` | 추론에 사용할 Depth Anything 3 모델 | DA3_MODEL | 예 | - | +| `image` | 처리할 입력 이미지 또는 이미지들 | IMAGE | 예 | - | +| `resolution` | 모델이 실행되는 해상도(가장 긴 변 기준, 14의 배수). 값이 낮을수록 빠르고 VRAM을 적게 사용합니다. 값이 높을수록 더 세밀한 결과를 제공합니다. 출력은 원본 크기로 업스케일링됩니다(기본값: 504) | INT | 예 | 140 ~ 2520 (간격: 14) | +| `resize_method` | upper_bound_resize: 가장 긴 변이 해상도와 같아지도록 크기 조정(메모리 제한, 기본값). lower_bound_resize: 가장 짧은 변이 해상도와 같아지도록 크기 조정(세로/가로가 긴 이미지에서 더 많은 세부 정보 보존, 더 많은 메모리 사용) | COMBO | 예 | `"upper_bound_resize"`
`"lower_bound_resize"` | +| `mode` | mono: 단일 뷰 이미지 처리(모든 모델 변형에서 작동). multiview: 모든 이미지를 함께 처리하여 기하학적 일관성과 카메라 포즈 추정(Small 및 Base 모델만 해당) | COMBO | 예 | `"mono"`
`"multiview"` | +| `ref_view_strategy` | 다중 뷰 모드에서 기하학적 기준점 역할을 하는 뷰. saddle_balanced: 다른 모든 뷰와 가장 평균적인 뷰(일반적으로 최선의 선택). saddle_sim_range: 다른 뷰와 시각적으로 가장 구별되는 뷰. first / middle: 고정된 위치 선택 | COMBO | 아니요(조건부) | `"saddle_balanced"`
`"saddle_sim_range"`
`"first"`
`"middle"` | +| `pose_method` | 카메라 시야각 추정 방법(Small 및 Base 모델만 해당). cam_dec: 이미지 특징에서 학습. ray_pose: 모델의 3D 광선 출력에서 기하학적으로 도출. 3D 출력의 원근 정확도에 영향을 미칩니다 | COMBO | 아니요(조건부) | `"cam_dec"`
`"ray_pose"` | + +**매개변수 제약 조건 참고사항:** +- `ref_view_strategy` 및 `pose_method` 매개변수는 `mode`가 `"multiview"`로 설정된 경우에만 사용 가능합니다 +- 다중 뷰 모드는 Small 또는 Base 모델 변형이 필요합니다. 다른 헤드 유형(Metric 또는 Mono 등)의 모델은 교차 뷰 주의 메커니즘 또는 카메라 포즈 추정을 지원하지 않습니다 +- `pose_method`가 `"cam_dec"`로 설정된 경우 모델에 카메라 디코더가 있어야 합니다. `"ray_pose"`로 설정된 경우 모델에 DualDPT 헤드가 있어야 합니다 +- 선택한 `pose_method`가 로드된 모델과 호환되지 않으면 오류가 발생합니다 + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `da3_geometry` | 정규화되지 않은 텐서의 딕셔너리입니다. 항상 depth, image, mode 키를 포함합니다. 선택적 키로는 sky(Mono/Metric 모델용), confidence(Small/Base 모델용), extrinsics 및 intrinsics(다중 뷰 모드용)가 있습니다 | DA3_GEOMETRY | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3Inference/ko.md) + +--- +**Source fingerprint (SHA-256):** `e91dd47e6a01719cdd6b6ce8a9bcc45933cac72c5e147ac42906d2f83ab7c250` diff --git a/ko/built-in-nodes/DA3Render.mdx b/ko/built-in-nodes/DA3Render.mdx new file mode 100644 index 000000000..3dc4db242 --- /dev/null +++ b/ko/built-in-nodes/DA3Render.mdx @@ -0,0 +1,54 @@ +--- +title: "DA3Render - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3Render node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3Render" +icon: "circle" +mode: wide +--- + +이 노드는 Depth Anything 3 형상 데이터에서 시각화를 렌더링합니다. 선택한 출력 모드에 따라 깊이 맵, 신뢰도 맵 또는 하늘 마스크를 출력할 수 있습니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 깊이 텐서와 선택적으로 하늘 및 신뢰도 텐서를 포함하는 Depth Anything 3 형상 데이터 패킷 | DA3_GEOMETRY | 예 | - | +| `output` | 렌더링할 시각화 유형입니다. 옵션으로는 depth, depth_colored, sky_mask, confidence가 있습니다. 각 옵션은 고유한 하위 매개변수 집합을 가집니다. | COMBO | 예 | `"depth"`
`"depth_colored"`
`"sky_mask"`
`"confidence"` | + +### `output` 옵션의 하위 매개변수 + +`output`이 `"depth"` 또는 `"depth_colored"`로 설정된 경우: + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `normalization` | 깊이 정규화 방법입니다. v2_style은 지각적으로 균형 잡힌 결과를 위해 평균/표준편차 정규화를 사용합니다(기본값). min_max는 최대 대비를 위해 전체 깊이 범위를 [0, 1]로 늘립니다. raw는 스케일링 없이 Metric 모델의 미터법 단위를 유지합니다. | COMBO | 예 | `"v2_style"`
`"min_max"`
`"raw"` | +| `apply_sky_clip` | 정규화 전에 하늘 영역 깊이를 전경 깊이의 99번째 백분위수로 클리핑합니다. da3_geometry 입력에 sky 키가 필요합니다(Mono/Metric 모델 전용). 기본값: False | BOOLEAN | 예 | True
False | + +`output`이 `"sky_mask"`로 설정된 경우: + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `colored` | 하늘 마스크에 Turbo 컬러맵을 적용합니다. 기본값: False | BOOLEAN | 예 | True
False | + +`output`이 `"confidence"`로 설정된 경우: + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `colored` | 신뢰도 맵에 Turbo 컬러맵을 적용합니다. 기본값: False | BOOLEAN | 예 | True
False | + +### 매개변수 제약 조건 + +- `apply_sky_clip`이 True로 설정된 경우, `da3_geometry` 입력에 sky 텐서가 포함되어야 합니다. 이는 Mono 또는 Metric 모델을 사용할 때만 가능합니다. sky 텐서가 없으면 노드에서 오류가 발생합니다. +- `sky_mask` 출력 옵션은 `da3_geometry` 입력에 sky 텐서가 필요합니다. 이는 Mono 또는 Metric 모델에서만 사용 가능합니다. +- `confidence` 출력 옵션은 `da3_geometry` 입력에 confidence 텐서가 필요합니다. 이는 Small 또는 Base 모델에서만 사용 가능합니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `IMAGE` | 렌더링된 시각화 이미지 텐서입니다. 깊이 출력의 경우 회색조 또는 컬러 깊이 맵을 반환합니다. sky_mask 및 confidence의 경우 colored 매개변수에 따라 회색조 또는 컬러 시각화를 반환합니다. | IMAGE | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3Render/ko.md) + +--- +**Source fingerprint (SHA-256):** `54d4cde95a916cac26c8a2e19c5623e794d46c0d7652f1c8204f9f2a0deabe0c` diff --git a/ko/built-in-nodes/DCTestNode.mdx b/ko/built-in-nodes/DCTestNode.mdx index 491a4890e..c572e1b8c 100644 --- a/ko/built-in-nodes/DCTestNode.mdx +++ b/ko/built-in-nodes/DCTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DCTestNode" icon: "circle" mode: wide --- + DCTestNode는 사용자가 동적 콤보 상자에서 선택한 내용에 따라 서로 다른 유형의 데이터를 반환하는 논리 노드입니다. 이 노드는 조건부 라우터 역할을 하며, 선택된 옵션에 따라 활성화되는 입력 필드와 노드가 출력할 값의 유형이 결정됩니다. ## 입력 diff --git a/ko/built-in-nodes/DeprecatedCheckpointLoader.mdx b/ko/built-in-nodes/DeprecatedCheckpointLoader.mdx index 4111ce079..684774199 100644 --- a/ko/built-in-nodes/DeprecatedCheckpointLoader.mdx +++ b/ko/built-in-nodes/DeprecatedCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DeprecatedCheckpointLoader" icon: "circle" mode: wide --- + CheckpointLoader 노드는 고급 로딩 작업을 위해 설계되었으며, 특히 모델 체크포인트와 해당 구성을 로드합니다. 이 노드는 생성 모델을 초기화하고 실행하는 데 필요한 모델 구성 요소(지정된 디렉터리의 구성 및 체크포인트 포함)를 검색하는 기능을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/DeprecatedDiffusersLoader.mdx b/ko/built-in-nodes/DeprecatedDiffusersLoader.mdx index d09a6a456..22f1d284c 100644 --- a/ko/built-in-nodes/DeprecatedDiffusersLoader.mdx +++ b/ko/built-in-nodes/DeprecatedDiffusersLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DeprecatedDiffusersLoader" icon: "circle" mode: wide --- + DiffusersLoader 노드는 diffusers 라이브러리에서 모델을 로드하기 위해 설계되었으며, 제공된 모델 경로를 기반으로 UNet, CLIP 및 VAE 모델을 로드하는 작업을 처리합니다. 이 노드는 이러한 모델을 ComfyUI 프레임워크에 통합하여 텍스트-이미지 생성, 이미지 조작 등과 같은 고급 기능을 가능하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/DiffControlNetLoader.mdx b/ko/built-in-nodes/DiffControlNetLoader.mdx index 5dced6d84..df4538244 100644 --- a/ko/built-in-nodes/DiffControlNetLoader.mdx +++ b/ko/built-in-nodes/DiffControlNetLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DiffControlNetLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/controlnet` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 설정된 추가 경로의 모델도 읽어옵니다. 때로는 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수도 있습니다. DiffControlNetLoader 노드는 차등 제어 네트워크를 로드하기 위해 설계되었습니다. 차등 제어 네트워크는 제어 사양에 따라 다른 모델의 동작을 수정할 수 있는 특수 모델입니다. 이 노드는 차등 제어 네트워크를 적용하여 모델 동작을 동적으로 조정할 수 있게 하며, 맞춤형 모델 출력을 생성하는 데 도움을 줍니다. diff --git a/ko/built-in-nodes/DifferentialDiffusion.mdx b/ko/built-in-nodes/DifferentialDiffusion.mdx index fdd4cb865..e2ab5557e 100644 --- a/ko/built-in-nodes/DifferentialDiffusion.mdx +++ b/ko/built-in-nodes/DifferentialDiffusion.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DifferentialDiffusion" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DifferentialDiffusion/en.md) Differential Diffusion 노드는 시간 단계 임계값을 기반으로 이진 마스크를 적용하여 노이즈 제거 과정을 수정합니다. 이 노드는 원본 노이즈 제거 마스크와 임계값 기반 이진 마스크 사이를 혼합하는 마스크를 생성하여 확산 과정의 강도를 제어할 수 있도록 합니다. diff --git a/ko/built-in-nodes/DiffusersLoader.mdx b/ko/built-in-nodes/DiffusersLoader.mdx index 0667f8e7f..3ac5e795d 100644 --- a/ko/built-in-nodes/DiffusersLoader.mdx +++ b/ko/built-in-nodes/DiffusersLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DiffusersLoader" icon: "circle" mode: wide --- + DiffusersLoader 노드는 diffusers 형식의 사전 학습된 모델을 불러옵니다. `model_index.json` 파일이 포함된 유효한 diffusers 모델 디렉터리를 검색하여 파이프라인에서 사용할 MODEL, CLIP, VAE 구성 요소로 로드합니다. 이 노드는 더 이상 사용되지 않는 로더 범주에 속하며, Hugging Face diffusers 모델과의 호환성을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/DisableNoise.mdx b/ko/built-in-nodes/DisableNoise.mdx index cfe873fc3..757fca153 100644 --- a/ko/built-in-nodes/DisableNoise.mdx +++ b/ko/built-in-nodes/DisableNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DisableNoise" icon: "circle" mode: wide --- + DisableNoise 노드는 샘플링 과정에서 노이즈 생성을 비활성화하는 데 사용할 수 있는 빈 노이즈 구성을 제공합니다. 이 노드는 노이즈 데이터가 포함되지 않은 특수 노이즈 객체를 반환하며, 이 출력에 연결된 다른 노드가 노이즈 관련 작업을 건너뛸 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/DrawBBoxes.mdx b/ko/built-in-nodes/DrawBBoxes.mdx index c6c333381..4a3b487ec 100644 --- a/ko/built-in-nodes/DrawBBoxes.mdx +++ b/ko/built-in-nodes/DrawBBoxes.mdx @@ -5,7 +5,6 @@ sidebarTitle: "DrawBBoxes" icon: "circle" mode: wide --- -# DrawBBoxes 노드 DrawBBoxes 노드는 이미지에 경계 상자, 레이블 및 신뢰도 점수를 그려 객체 탐지 결과를 시각화합니다. 입력 이미지가 제공되지 않으면 모든 그려진 상자를 포함할 수 있을 만큼 충분히 큰 빈 캔버스를 생성합니다. 배치 처리를 지원하므로 여러 이미지에 대해 서로 다른 탐지 결과를 그리거나 동일한 탐지 결과를 배치 전체에 반복할 수 있습니다. diff --git a/ko/built-in-nodes/DualCFGGuider.mdx b/ko/built-in-nodes/DualCFGGuider.mdx index 62b886ae8..feeacc7f1 100644 --- a/ko/built-in-nodes/DualCFGGuider.mdx +++ b/ko/built-in-nodes/DualCFGGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DualCFGGuider" icon: "circle" mode: wide --- + DualCFGGuider 노드는 이중 분류기-프리 가이던스 샘플링을 위한 가이던스 시스템을 생성합니다. 두 개의 긍정 조건부 입력과 하나의 부정 조건부 입력을 결합하여, 각 조건부 쌍에 서로 다른 가이던스 스케일을 적용함으로써 생성된 출력물에 대한 각 프롬프트의 영향을 제어합니다. ## 입력 diff --git a/ko/built-in-nodes/DualCLIPLoader.mdx b/ko/built-in-nodes/DualCLIPLoader.mdx index a78e4b2ef..dfabb8798 100644 --- a/ko/built-in-nodes/DualCLIPLoader.mdx +++ b/ko/built-in-nodes/DualCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DualCLIPLoader" icon: "circle" mode: wide --- + DualCLIPLoader 노드는 두 개의 CLIP 모델을 동시에 로드하여, 두 모델의 특징을 통합하거나 비교하는 작업을 용이하게 하도록 설계되었습니다. 이 노드는 `ComfyUI/models/text_encoders` 폴더에 있는 모델을 감지합니다. diff --git a/ko/built-in-nodes/DualModelGuider.mdx b/ko/built-in-nodes/DualModelGuider.mdx index fceeb1803..4aa6f9b27 100644 --- a/ko/built-in-nodes/DualModelGuider.mdx +++ b/ko/built-in-nodes/DualModelGuider.mdx @@ -5,7 +5,6 @@ sidebarTitle: "DualModelGuider" icon: "circle" mode: wide --- -# 이중 모델 CFG 가이더 이 노드는 안내된 CFG 샘플링 과정에서 두 개의 서로 다른 모델을 사용할 수 있게 해줍니다. 하나의 모델은 양(조건부) 패스에 사용되고, 다른 별도의 모델은 음(무조건부) 패스에 사용됩니다. 음 모델이 제공되지 않으면 단일 모델을 사용하는 표준 CFG 가이더처럼 작동합니다. diff --git a/ko/built-in-nodes/EasyCache.mdx b/ko/built-in-nodes/EasyCache.mdx index 34310596c..6f6032660 100644 --- a/ko/built-in-nodes/EasyCache.mdx +++ b/ko/built-in-nodes/EasyCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EasyCache" icon: "circle" mode: wide --- + EasyCache 노드는 모델을 위한 네이티브 캐싱 시스템을 구현하여 샘플링 과정에서 이전에 계산된 단계를 재사용함으로써 성능을 향상시킵니다. 샘플링 타임라인에서 캐시 사용을 시작하고 중지할 시점에 대한 구성 가능한 임계값을 사용하여 모델에 EasyCache 기능을 추가합니다. ## 입력 diff --git a/ko/built-in-nodes/ElevenLabsAudioIsolation.mdx b/ko/built-in-nodes/ElevenLabsAudioIsolation.mdx index 9a92cdcf2..38e13d6aa 100644 --- a/ko/built-in-nodes/ElevenLabsAudioIsolation.mdx +++ b/ko/built-in-nodes/ElevenLabsAudioIsolation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsAudioIsolation" icon: "circle" mode: wide --- + ElevenLabs 음성 분리 노드는 오디오 파일에서 배경 소음을 제거하여 보컬 또는 음성을 분리합니다. 오디오를 ElevenLabs API로 전송하여 처리한 후, 정리된 오디오를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/ElevenLabsInstantVoiceClone.mdx b/ko/built-in-nodes/ElevenLabsInstantVoiceClone.mdx index 8c8244d65..5aed259fe 100644 --- a/ko/built-in-nodes/ElevenLabsInstantVoiceClone.mdx +++ b/ko/built-in-nodes/ElevenLabsInstantVoiceClone.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsInstantVoiceClone" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsInstantVoiceClone/en.md) ElevenLabs Instant Voice Clone 노드는 사람 목소리의 오디오 녹음 1~8개를 분석하여 새롭고 고유한 음성 모델을 생성합니다. 이 샘플들을 ElevenLabs API로 전송하면, API가 이를 처리하여 텍스트 음성 변환에 사용할 수 있는 음성 복제본을 생성합니다. diff --git a/ko/built-in-nodes/ElevenLabsSpeechToSpeech.mdx b/ko/built-in-nodes/ElevenLabsSpeechToSpeech.mdx index 42e0aa96b..275301bce 100644 --- a/ko/built-in-nodes/ElevenLabsSpeechToSpeech.mdx +++ b/ko/built-in-nodes/ElevenLabsSpeechToSpeech.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsSpeechToSpeech" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToSpeech/en.md) ElevenLabs Speech to Speech 노드는 입력 오디오 파일의 음성을 다른 음성으로 변환합니다. ElevenLabs API를 사용하여 음성을 변환하며, 원본 오디오의 내용과 감정적 톤을 보존합니다. diff --git a/ko/built-in-nodes/ElevenLabsSpeechToText.mdx b/ko/built-in-nodes/ElevenLabsSpeechToText.mdx index 370905bb3..3540820c0 100644 --- a/ko/built-in-nodes/ElevenLabsSpeechToText.mdx +++ b/ko/built-in-nodes/ElevenLabsSpeechToText.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ElevenLabsSpeechToText" icon: "circle" mode: wide --- -# ElevenLabs 음성-텍스트 노드 ElevenLabs 음성-텍스트 노드는 오디오 파일을 텍스트로 변환합니다. ElevenLabs의 API를 사용하여 음성 단어를 문자 기록으로 변환하며, 자동 언어 감지, 화자 식별, 음악이나 웃음과 같은 비음성 사운드 태깅 기능을 지원합니다. @@ -30,8 +29,8 @@ ElevenLabs 음성-텍스트 노드는 오디오 파일을 텍스트로 변환합 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `language_code` | 오디오에서 변환된 텍스트입니다. | STRING | -| `words_json` | 감지된 오디오의 언어 코드입니다. | STRING | +| `text` | 오디오에서 변환된 텍스트입니다. | STRING | +| `language_code` | 감지된 오디오의 언어 코드입니다. | STRING | | `words_json` | 타임스탬프와 활성화된 경우 화자 레이블을 포함한 상세한 단어 수준 정보가 포함된 JSON 형식 문자열입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToText/ko.md) diff --git a/ko/built-in-nodes/ElevenLabsTextToDialogue.mdx b/ko/built-in-nodes/ElevenLabsTextToDialogue.mdx index 64308cb7c..3c876d39c 100644 --- a/ko/built-in-nodes/ElevenLabsTextToDialogue.mdx +++ b/ko/built-in-nodes/ElevenLabsTextToDialogue.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ElevenLabsTextToDialogue" icon: "circle" mode: wide --- -# ElevenLabs 텍스트-대화 노드 ElevenLabs 텍스트-대화 노드는 텍스트로부터 여러 화자가 참여하는 오디오 대화를 생성합니다. 각 참여자에 대해 서로 다른 텍스트 줄과 개별 음성을 지정하여 대화를 만들 수 있습니다. 이 노드는 ElevenLabs API로 대화 요청을 전송하고 생성된 오디오를 반환합니다. diff --git a/ko/built-in-nodes/ElevenLabsTextToSoundEffects.mdx b/ko/built-in-nodes/ElevenLabsTextToSoundEffects.mdx index 497a5a4c5..924a5d2e9 100644 --- a/ko/built-in-nodes/ElevenLabsTextToSoundEffects.mdx +++ b/ko/built-in-nodes/ElevenLabsTextToSoundEffects.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ElevenLabsTextToSoundEffects" icon: "circle" mode: wide --- -# ElevenLabs 텍스트-음향 효과 노드 ElevenLabs 텍스트-음향 효과 노드는 텍스트 설명으로부터 오디오 음향 효과를 생성합니다. ElevenLabs API를 사용하여 프롬프트를 기반으로 음향 효과를 만들며, 지속 시간, 반복 동작, 텍스트와 소리의 일치 정도를 제어할 수 있습니다. diff --git a/ko/built-in-nodes/ElevenLabsTextToSpeech.mdx b/ko/built-in-nodes/ElevenLabsTextToSpeech.mdx index 12e38edec..b81b05d88 100644 --- a/ko/built-in-nodes/ElevenLabsTextToSpeech.mdx +++ b/ko/built-in-nodes/ElevenLabsTextToSpeech.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ElevenLabsTextToSpeech" icon: "circle" mode: wide --- -# ElevenLabs 텍스트 음성 변환 노드 ElevenLabs 텍스트 음성 변환 노드는 ElevenLabs API를 사용하여 작성된 텍스트를 음성 오디오로 변환합니다. 특정 음성을 선택하고 안정성, 속도, 스타일과 같은 다양한 음성 특성을 미세 조정하여 맞춤형 오디오 출력을 생성할 수 있습니다. diff --git a/ko/built-in-nodes/ElevenLabsVoiceSelector.mdx b/ko/built-in-nodes/ElevenLabsVoiceSelector.mdx index ad8dd3225..3b9131ced 100644 --- a/ko/built-in-nodes/ElevenLabsVoiceSelector.mdx +++ b/ko/built-in-nodes/ElevenLabsVoiceSelector.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsVoiceSelector" icon: "circle" mode: wide --- + ElevenLabs 음성 선택 노드는 미리 정의된 ElevenLabs 텍스트 음성 변환 음성 목록에서 특정 음성을 선택할 수 있도록 합니다. 음성 이름을 입력으로 받아들이고, 오디오 생성에 필요한 해당 음성 식별자를 출력합니다. 이 노드는 다른 ElevenLabs 오디오 노드와 함께 사용할 호환 가능한 음성을 선택하는 과정을 간소화합니다. ## 입력 diff --git a/ko/built-in-nodes/EmptyARVideoLatent.mdx b/ko/built-in-nodes/EmptyARVideoLatent.mdx index 73a5af93a..609c8b79e 100644 --- a/ko/built-in-nodes/EmptyARVideoLatent.mdx +++ b/ko/built-in-nodes/EmptyARVideoLatent.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyARVideoLatent" icon: "circle" mode: wide --- -# 개요 EmptyARVideoLatent 노드는 비디오 생성을 위한 빈 잠재 표현(Latent Representation)을 생성합니다. 지정된 크기, 화면 비율 및 길이를 가진 0으로 채워진 텐서를 제공하여 비디오 생성 프로세스를 초기화하는 데 사용됩니다. diff --git a/ko/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx b/ko/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx index 2e25a5c4f..ffaac392e 100644 --- a/ko/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx +++ b/ko/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyAceStep1.5LatentAudio" icon: "circle" mode: wide --- -# Empty Ace Step 1.5 Latent Audio 노드 Empty Ace Step 1.5 Latent Audio 노드는 오디오 처리를 위해 설계된 빈 잠재 텐서를 생성합니다. 지정된 길이와 배치 크기의 무음 오디오 잠재를 생성하며, ComfyUI에서 오디오 생성 워크플로우의 시작점으로 사용할 수 있습니다. 이 노드는 입력된 초(seconds)와 고정 샘플 레이트를 기반으로 잠재 길이를 계산합니다. diff --git a/ko/built-in-nodes/EmptyAceStepLatentAudio.mdx b/ko/built-in-nodes/EmptyAceStepLatentAudio.mdx index e5da645f3..2a35af797 100644 --- a/ko/built-in-nodes/EmptyAceStepLatentAudio.mdx +++ b/ko/built-in-nodes/EmptyAceStepLatentAudio.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyAceStepLatentAudio" icon: "circle" mode: wide --- -# EmptyAceStepLatentAudio 노드 EmptyAceStepLatentAudio 노드는 지정된 길이의 빈 잠재 오디오 샘플을 생성합니다. 0으로 채워진 무음 오디오 잠재 텐서 배치를 생성하며, 길이는 입력된 초(seconds)와 오디오 처리 매개변수를 기반으로 계산됩니다. 이 노드는 잠재 표현이 필요한 오디오 처리 워크플로우를 초기화할 때 유용합니다. diff --git a/ko/built-in-nodes/EmptyAudio.mdx b/ko/built-in-nodes/EmptyAudio.mdx index 5bcd74fc3..bc14093b0 100644 --- a/ko/built-in-nodes/EmptyAudio.mdx +++ b/ko/built-in-nodes/EmptyAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAudio" icon: "circle" mode: wide --- + 빈 오디오(EmptyAudio) 노드는 지정된 길이, 샘플 레이트 및 채널 구성으로 무음 오디오 클립을 생성합니다. 모든 값이 0인 파형을 만들어 지정된 시간 동안 완전한 무음을 생성합니다. 이 노드는 오디오 워크플로우에서 자리 표시자 오디오를 만들거나 무음 구간을 생성하는 데 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/EmptyChromaRadianceLatentImage.mdx b/ko/built-in-nodes/EmptyChromaRadianceLatentImage.mdx index 502162d67..ccab6163e 100644 --- a/ko/built-in-nodes/EmptyChromaRadianceLatentImage.mdx +++ b/ko/built-in-nodes/EmptyChromaRadianceLatentImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyChromaRadianceLatentImage" icon: "circle" mode: wide --- -# EmptyChromaRadianceLatentImage 노드 EmptyChromaRadianceLatentImage 노드는 크로마 래디언스 워크플로우에서 사용하기 위해 지정된 크기의 빈 잠재 이미지를 생성합니다. 이 노드는 잠재 공간 연산의 시작점으로 사용되는 0으로 채워진 텐서를 생성합니다. 빈 잠재 이미지의 너비, 높이 및 배치 크기를 정의할 수 있습니다. diff --git a/ko/built-in-nodes/EmptyCosmosLatentVideo.mdx b/ko/built-in-nodes/EmptyCosmosLatentVideo.mdx index f3f9740af..ade61ba78 100644 --- a/ko/built-in-nodes/EmptyCosmosLatentVideo.mdx +++ b/ko/built-in-nodes/EmptyCosmosLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyCosmosLatentVideo" icon: "circle" mode: wide --- + EmptyCosmosLatentVideo 노드는 지정된 크기의 빈 잠재 비디오 텐서를 생성합니다. 이 노드는 너비, 높이, 길이 및 배치 크기 매개변수를 구성할 수 있으며, 비디오 생성 워크플로우의 시작점으로 사용할 수 있는 0으로 채워진 잠재 표현을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/EmptyFlux2LatentImage.mdx b/ko/built-in-nodes/EmptyFlux2LatentImage.mdx index 4ab4c5b2b..da8a7cae7 100644 --- a/ko/built-in-nodes/EmptyFlux2LatentImage.mdx +++ b/ko/built-in-nodes/EmptyFlux2LatentImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyFlux2LatentImage" icon: "circle" mode: wide --- -# EmptyFlux2LatentImage 노드 EmptyFlux2LatentImage 노드는 비어 있는 빈 잠재 표현을 생성합니다. 0으로 채워진 텐서를 생성하며, 이는 Flux 모델의 노이즈 제거 과정을 위한 시작점 역할을 합니다. 잠재 표현의 차원은 입력 너비와 높이에 의해 결정되며, 16배로 축소됩니다. diff --git a/ko/built-in-nodes/EmptyHiDreamO1LatentImage.mdx b/ko/built-in-nodes/EmptyHiDreamO1LatentImage.mdx index 1b94f72ef..ee48faedc 100644 --- a/ko/built-in-nodes/EmptyHiDreamO1LatentImage.mdx +++ b/ko/built-in-nodes/EmptyHiDreamO1LatentImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyHiDreamO1LatentImage" icon: "circle" mode: wide --- -# 개요 이 노드는 HiDream-O1-Image 모델을 위해 특별히 설계된 픽셀 공간의 빈 잠재 이미지를 생성합니다. 너비, 높이 및 배치 크기 입력으로 정의된 차원을 가진 0으로 채워진 빈 텐서를 생성하며, 이는 이미지 생성을 위한 시작점 역할을 합니다. diff --git a/ko/built-in-nodes/EmptyHunyuanImageLatent.mdx b/ko/built-in-nodes/EmptyHunyuanImageLatent.mdx index 7de68526d..8e794fd3e 100644 --- a/ko/built-in-nodes/EmptyHunyuanImageLatent.mdx +++ b/ko/built-in-nodes/EmptyHunyuanImageLatent.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyHunyuanImageLatent" icon: "circle" mode: wide --- -# EmptyHunyuanImageLatent 노드 EmptyHunyuanImageLatent 노드는 Hunyuan 이미지 생성 모델과 함께 사용하기 위해 특정 차원의 빈 잠재 텐서를 생성합니다. 워크플로우의 후속 노드에서 처리할 수 있는 빈 시작점을 생성합니다. 이 노드를 사용하면 잠재 공간의 너비, 높이 및 배치 크기를 지정할 수 있습니다. diff --git a/ko/built-in-nodes/EmptyHunyuanLatentVideo.mdx b/ko/built-in-nodes/EmptyHunyuanLatentVideo.mdx index a248fa9b7..88564643d 100644 --- a/ko/built-in-nodes/EmptyHunyuanLatentVideo.mdx +++ b/ko/built-in-nodes/EmptyHunyuanLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanLatentVideo" icon: "circle" mode: wide --- + `EmptyHunyuanLatentVideo` 노드는 `EmptyLatentImage` 노드와 유사합니다. 이를 비디오 생성을 위한 빈 캔버스로 간주할 수 있으며, 너비, 높이 및 길이가 캔버스의 속성을 정의하고 배치 크기는 생성할 캔버스의 수를 결정합니다. 이 노드는 후속 비디오 생성 작업을 위해 준비된 빈 캔버스를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/EmptyHunyuanVideo15Latent.mdx b/ko/built-in-nodes/EmptyHunyuanVideo15Latent.mdx index 972e24b8d..189b64f02 100644 --- a/ko/built-in-nodes/EmptyHunyuanVideo15Latent.mdx +++ b/ko/built-in-nodes/EmptyHunyuanVideo15Latent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanVideo15Latent" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyHunyuanVideo15Latent/en.md) 이 노드는 HunyuanVideo 1.5 모델에 특화된 형식의 빈 잠재 텐서를 생성합니다. 모델의 잠재 공간에 적합한 채널 수와 공간 차원을 가진 0으로 채워진 텐서를 할당하여 비디오 생성을 위한 빈 시작점을 만듭니다. diff --git a/ko/built-in-nodes/EmptyImage.mdx b/ko/built-in-nodes/EmptyImage.mdx index eaaec4323..e936d2579 100644 --- a/ko/built-in-nodes/EmptyImage.mdx +++ b/ko/built-in-nodes/EmptyImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyImage" icon: "circle" mode: wide --- + ## 기능 설명 EmptyImage 노드는 지정된 크기와 색상의 빈 이미지를 생성하는 데 사용됩니다. 단색 배경 이미지를 생성할 수 있으며, 주로 이미지 처리 워크플로우의 시작점이나 배경 이미지로 활용됩니다. diff --git a/ko/built-in-nodes/EmptyLTXVLatentVideo.mdx b/ko/built-in-nodes/EmptyLTXVLatentVideo.mdx index ddaa56eae..637eba83a 100644 --- a/ko/built-in-nodes/EmptyLTXVLatentVideo.mdx +++ b/ko/built-in-nodes/EmptyLTXVLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLTXVLatentVideo" icon: "circle" mode: wide --- + EmptyLTXVLatentVideo 노드는 비디오 처리를 위한 빈 잠재 텐서를 생성합니다. 지정된 차원으로 빈 시작점을 만들어 비디오 생성 워크플로우의 입력으로 사용할 수 있습니다. 이 노드는 설정된 너비, 높이, 길이 및 배치 크기로 0으로 채워진 잠재 표현을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/EmptyLatentAudio.mdx b/ko/built-in-nodes/EmptyLatentAudio.mdx index d30d8a5c3..2d98809ff 100644 --- a/ko/built-in-nodes/EmptyLatentAudio.mdx +++ b/ko/built-in-nodes/EmptyLatentAudio.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyLatentAudio" icon: "circle" mode: wide --- -# EmptyLatentAudio 노드 EmptyLatentAudio 노드는 오디오 처리를 위한 빈 잠재 텐서를 생성합니다. 지정된 지속 시간과 배치 크기를 가진 빈 오디오 잠재 표현을 생성하며, 이는 오디오 생성 또는 처리 워크플로우의 시작점으로 사용할 수 있습니다. 이 노드는 오디오 지속 시간과 샘플 속도를 기반으로 적절한 잠재 차원을 자동으로 계산합니다. diff --git a/ko/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx b/ko/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx index 8e0bb8a20..f40fa707d 100644 --- a/ko/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx +++ b/ko/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyLatentHunyuan3Dv2" icon: "circle" mode: wide --- -# EmptyLatentHunyuan3Dv2 노드 EmptyLatentHunyuan3Dv2 노드는 Hunyuan3Dv2 3D 생성 모델에 특화된 빈 잠재 텐서를 생성합니다. Hunyuan3Dv2 아키텍처에 필요한 올바른 차원과 구조를 가진 빈 잠재 공간을 생성하여, 처음부터 3D 생성 워크플로우를 시작할 수 있도록 합니다. 이 노드는 후속 3D 생성 프로세스의 기반이 되는 0으로 채워진 잠재 텐서를 생성합니다. diff --git a/ko/built-in-nodes/EmptyLatentImage.mdx b/ko/built-in-nodes/EmptyLatentImage.mdx index e20a70079..42bbba3e5 100644 --- a/ko/built-in-nodes/EmptyLatentImage.mdx +++ b/ko/built-in-nodes/EmptyLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentImage" icon: "circle" mode: wide --- + `EmptyLatentImage` 노드는 지정된 크기와 배치 크기로 빈 잠재 공간 표현을 생성하도록 설계되었습니다. 이 노드는 잠재 공간에서 이미지를 생성하거나 조작하는 기본 단계 역할을 하며, 추가 이미지 합성 또는 수정 프로세스를 위한 시작점을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/EmptyMochiLatentVideo.mdx b/ko/built-in-nodes/EmptyMochiLatentVideo.mdx index 5f72b8978..ddf50d3eb 100644 --- a/ko/built-in-nodes/EmptyMochiLatentVideo.mdx +++ b/ko/built-in-nodes/EmptyMochiLatentVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptyMochiLatentVideo" icon: "circle" mode: wide --- -# EmptyMochiLatentVideo 노드 EmptyMochiLatentVideo 노드는 지정된 차원의 빈 잠재 비디오 텐서를 생성합니다. 이 노드는 0으로 채워진 잠재 표현을 생성하며, 비디오 생성 워크플로우의 시작점으로 사용할 수 있습니다. 노드에서는 잠재 비디오 텐서의 너비, 높이, 길이 및 배치 크기를 정의할 수 있습니다. diff --git a/ko/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx b/ko/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx index 5cf021ec5..d4d618341 100644 --- a/ko/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx +++ b/ko/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyQwenImageLayeredLatentImage" icon: "circle" mode: wide --- + 빈 Qwen 이미지 계층형 잠재 노드는 Qwen 이미지 모델과 함께 사용할 빈 다중 계층 잠재 표현을 생성합니다. 지정된 계층 수, 배치 크기 및 공간 차원으로 구성된 0으로 채워진 텐서를 생성합니다. 이 빈 잠재 표현은 이후 이미지 생성 또는 조작 워크플로의 시작점 역할을 합니다. ## 입력 diff --git a/ko/built-in-nodes/EmptySD3LatentImage.mdx b/ko/built-in-nodes/EmptySD3LatentImage.mdx index 7cc3bfd99..0bc7f4196 100644 --- a/ko/built-in-nodes/EmptySD3LatentImage.mdx +++ b/ko/built-in-nodes/EmptySD3LatentImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "EmptySD3LatentImage" icon: "circle" mode: wide --- -# EmptySD3LatentImage 노드 EmptySD3LatentImage 노드는 Stable Diffusion 3 모델용으로 특별히 형식화된 빈 잠재 이미지 텐서를 생성합니다. SD3 파이프라인에서 요구하는 올바른 차원과 구조를 가진 0으로 채워진 텐서를 생성합니다. 이는 일반적으로 이미지 생성 워크플로우의 시작점으로 사용됩니다. diff --git a/ko/built-in-nodes/Epsilon Scaling.mdx b/ko/built-in-nodes/Epsilon Scaling.mdx index f1bb114ce..dc5acefbd 100644 --- a/ko/built-in-nodes/Epsilon Scaling.mdx +++ b/ko/built-in-nodes/Epsilon Scaling.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Epsilon Scaling" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon%20Scaling/en.md) 이 노드는 연구 논문 "Elucidating the Exposure Bias in Diffusion Models"(arxiv.org/abs/2308.15321v6)의 Epsilon Scaling 방법을 구현합니다. 샘플링 과정에서 예측된 노이즈를 스케일링하여 노출 편향을 줄이는 방식으로 작동하며, 이를 통해 생성된 이미지의 품질을 향상시킬 수 있습니다. 이 구현은 실용성과 효율성을 위해 논문에서 권장하는 "균일 스케줄(uniform schedule)"을 사용합니다. diff --git a/ko/built-in-nodes/ExponentialScheduler.mdx b/ko/built-in-nodes/ExponentialScheduler.mdx index 231592059..5dd099b23 100644 --- a/ko/built-in-nodes/ExponentialScheduler.mdx +++ b/ko/built-in-nodes/ExponentialScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ExponentialScheduler" icon: "circle" mode: wide --- + `ExponentialScheduler` 노드는 확산 샘플링 과정에서 지수 스케줄을 따라 시그마 값 시퀀스를 생성하도록 설계되었습니다. 이 노드는 확산 과정의 각 단계에 적용되는 노이즈 수준을 제어하는 사용자 정의 방식을 제공하여 샘플링 동작을 세밀하게 조정할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/ExtendIntermediateSigmas.mdx b/ko/built-in-nodes/ExtendIntermediateSigmas.mdx index 4b9480a77..239ce24b3 100644 --- a/ko/built-in-nodes/ExtendIntermediateSigmas.mdx +++ b/ko/built-in-nodes/ExtendIntermediateSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ExtendIntermediateSigmas" icon: "circle" mode: wide --- + ExtendIntermediateSigmas 노드는 기존 시그마 값 시퀀스를 가져와 그 사이에 추가적인 중간 시그마 값을 삽입합니다. 추가할 단계 수, 보간을 위한 간격 설정 방법, 그리고 시그마 시퀀스 내에서 확장이 발생할 위치를 제어하는 선택적 시작 및 종료 시그마 경계를 지정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/FeatherMask.mdx b/ko/built-in-nodes/FeatherMask.mdx index abf003109..97af42a3f 100644 --- a/ko/built-in-nodes/FeatherMask.mdx +++ b/ko/built-in-nodes/FeatherMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FeatherMask" icon: "circle" mode: wide --- + `FeatherMask` 노드는 지정된 마스크의 가장자리에 페더링 효과를 적용하여, 각 가장자리로부터 지정된 거리에 따라 마스크 가장자리의 불투명도를 부드럽게 전환합니다. 이를 통해 더 부드럽고 자연스럽게 혼합된 가장자리 효과를 만들어냅니다. ## 입력 diff --git a/ko/built-in-nodes/File3DToSplat.mdx b/ko/built-in-nodes/File3DToSplat.mdx index b6bb6c150..03d00fc68 100644 --- a/ko/built-in-nodes/File3DToSplat.mdx +++ b/ko/built-in-nodes/File3DToSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "File3DToSplat" icon: "circle" mode: wide --- -# File3DToSplat 이 노드는 가우시안 스플랫 데이터가 포함된 3D 파일을 노드 그래프에서 사용할 수 있는 가우시안 스플랫 형식으로 변환합니다. PLY, SPLAT, KSPLAT 및 SPZ 파일 형식을 지원하며, 파일 형식은 파일 내용에서 자동으로 감지됩니다. diff --git a/ko/built-in-nodes/FlipSigmas.mdx b/ko/built-in-nodes/FlipSigmas.mdx index 2ca3152da..03bf17152 100644 --- a/ko/built-in-nodes/FlipSigmas.mdx +++ b/ko/built-in-nodes/FlipSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FlipSigmas" icon: "circle" mode: wide --- + `FlipSigmas` 노드는 확산 모델에 사용되는 시그마 값 시퀀스의 순서를 반전시키고, 첫 번째 값이 원래 0이었다면 0이 아닌 값으로 보장하여 조작하도록 설계되었습니다. 이 작업은 노이즈 수준을 역순으로 적용하여 데이터에서 점진적으로 노이즈를 줄이는 방식으로 작동하는 모델의 생성 과정을 용이하게 하는 데 중요합니다. ## 입력 diff --git a/ko/built-in-nodes/Flux2ImageNode.mdx b/ko/built-in-nodes/Flux2ImageNode.mdx index 4472f4c0b..9ce3eaf57 100644 --- a/ko/built-in-nodes/Flux2ImageNode.mdx +++ b/ko/built-in-nodes/Flux2ImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Flux2ImageNode" icon: "circle" mode: wide --- -# 개요 텍스트 프롬프트와 선택적 참조 이미지를 사용하여 Flux.2 [pro] 또는 Flux.2 [max] 모델로 이미지를 생성합니다. 이 노드는 요청을 BFL API로 전송하고, 결과를 폴링한 후 생성된 이미지를 텐서로 반환합니다. diff --git a/ko/built-in-nodes/Flux2Scheduler.mdx b/ko/built-in-nodes/Flux2Scheduler.mdx index 83d0fbcab..a43cfe112 100644 --- a/ko/built-in-nodes/Flux2Scheduler.mdx +++ b/ko/built-in-nodes/Flux2Scheduler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Flux2Scheduler" icon: "circle" mode: wide --- -# Flux2Scheduler Flux2Scheduler 노드는 Flux 모델에 특화된 노이즈 제거 프로세스를 위한 노이즈 수준 시퀀스(sigmas)를 생성합니다. 이 노드는 노이즈 제거 단계 수와 대상 이미지의 크기에 기반하여 스케줄을 계산하며, 이는 이미지 생성 중 노이즈 제거 진행 과정에 영향을 미칩니다. diff --git a/ko/built-in-nodes/FluxDisableGuidance.mdx b/ko/built-in-nodes/FluxDisableGuidance.mdx index d22d6b4f7..e22c21873 100644 --- a/ko/built-in-nodes/FluxDisableGuidance.mdx +++ b/ko/built-in-nodes/FluxDisableGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxDisableGuidance" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxDisableGuidance/en.md) 이 노드는 Flux 및 유사한 모델에 대한 가이던스 임베드 기능을 완전히 비활성화합니다. 컨디셔닝 데이터를 입력으로 받아 가이던스 구성 요소를 None으로 설정하여 제거함으로써, 생성 과정에서 가이던스 기반 컨디셔닝을 효과적으로 끕니다. diff --git a/ko/built-in-nodes/FluxEraseNode.mdx b/ko/built-in-nodes/FluxEraseNode.mdx index 2fe6a0585..da5bb1d77 100644 --- a/ko/built-in-nodes/FluxEraseNode.mdx +++ b/ko/built-in-nodes/FluxEraseNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxEraseNode" icon: "circle" mode: wide --- -# Flux Erase 노드 이미지에서 마스크 처리된 객체를 제거하고 배경을 재구성합니다. 지우고 싶은 영역 위에 마스크를 칠하면, 노드가 해당 영역을 그럴듯한 배경 콘텐츠로 채웁니다. diff --git a/ko/built-in-nodes/FluxGuidance.mdx b/ko/built-in-nodes/FluxGuidance.mdx index f663eb2f0..fa2fecef2 100644 --- a/ko/built-in-nodes/FluxGuidance.mdx +++ b/ko/built-in-nodes/FluxGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxGuidance" icon: "circle" mode: wide --- + ## 입력 | 매개변수 | 설명 | 데이터 타입 | diff --git a/ko/built-in-nodes/FluxKVCache.mdx b/ko/built-in-nodes/FluxKVCache.mdx index f626938a2..1ef2cea0d 100644 --- a/ko/built-in-nodes/FluxKVCache.mdx +++ b/ko/built-in-nodes/FluxKVCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKVCache" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxKVCache/en.md) Flux KV Cache 노드는 Flux 계열 모델에 대해 Key-Value(KV) 캐시 최적화를 활성화합니다. 이 최적화는 참조 이미지를 사용할 때 특정 계산을 캐싱하여 성능을 향상시키며, 생성 과정의 속도를 높일 수 있습니다. diff --git a/ko/built-in-nodes/FluxKontextImageScale.mdx b/ko/built-in-nodes/FluxKontextImageScale.mdx index acce0e3d2..0bc7bc1fc 100644 --- a/ko/built-in-nodes/FluxKontextImageScale.mdx +++ b/ko/built-in-nodes/FluxKontextImageScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKontextImageScale" icon: "circle" mode: wide --- + 이 노드는 입력 이미지의 종횡비를 기준으로 Lanczos 알고리즘을 사용하여 Flux Kontext 모델 학습 중 사용되는 최적 크기로 이미지를 조정합니다. 특히 큰 크기의 이미지를 입력할 때 유용하며, 과도하게 큰 입력은 모델 출력 품질 저하 또는 출력에 여러 객체가 나타나는 문제를 초래할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx b/ko/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx index 11072bb7d..0e9d35e2f 100644 --- a/ko/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx +++ b/ko/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxKontextMultiReferenceLatentMethod" icon: "circle" mode: wide --- -# FluxKontextMultiReferenceLatentMethod FluxKontextMultiReferenceLatentMethod 노드는 특정 참조 잠재 변수 방식을 설정하여 컨디셔닝 데이터를 수정합니다. 선택한 방식을 컨디셔닝 입력에 추가하며, 이는 후속 생성 단계에서 참조 잠재 변수가 처리되는 방식에 영향을 줍니다. 이 노드는 실험적 기능으로 표시되어 있으며 Flux 컨디셔닝 시스템의 일부입니다. diff --git a/ko/built-in-nodes/FluxProCannyNode.mdx b/ko/built-in-nodes/FluxProCannyNode.mdx index be74cadb8..95af6f9f0 100644 --- a/ko/built-in-nodes/FluxProCannyNode.mdx +++ b/ko/built-in-nodes/FluxProCannyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProCannyNode" icon: "circle" mode: wide --- + 제어 이미지(캐니)를 사용하여 이미지를 생성합니다. 이 노드는 제어 이미지를 입력받아, 제어 이미지에서 감지된 에지 구조를 따르면서 제공된 프롬프트를 기반으로 새 이미지를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/FluxProDepthNode.mdx b/ko/built-in-nodes/FluxProDepthNode.mdx index 4cd7a277d..3e1efca22 100644 --- a/ko/built-in-nodes/FluxProDepthNode.mdx +++ b/ko/built-in-nodes/FluxProDepthNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProDepthNode" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProDepthNode/en.md) 이 노드는 깊이 제어 이미지를 가이드로 사용하여 이미지를 생성합니다. 제어 이미지와 텍스트 프롬프트를 입력받아, 제어 이미지의 깊이 정보와 프롬프트의 설명을 모두 따르는 새로운 이미지를 만듭니다. 이 노드는 외부 API에 연결되어 이미지 생성 과정을 수행합니다. diff --git a/ko/built-in-nodes/FluxProExpandNode.mdx b/ko/built-in-nodes/FluxProExpandNode.mdx index c931c6af9..b4cda93f3 100644 --- a/ko/built-in-nodes/FluxProExpandNode.mdx +++ b/ko/built-in-nodes/FluxProExpandNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProExpandNode" icon: "circle" mode: wide --- + 프롬프트를 기반으로 이미지를 아웃페인팅합니다. 이 노드는 이미지의 상단, 하단, 좌측, 우측에 픽셀을 추가하여 이미지를 확장하면서 제공된 텍스트 설명과 일치하는 새로운 콘텐츠를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/FluxProFillNode.mdx b/ko/built-in-nodes/FluxProFillNode.mdx index 394aa16e6..4d869f0bf 100644 --- a/ko/built-in-nodes/FluxProFillNode.mdx +++ b/ko/built-in-nodes/FluxProFillNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProFillNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProFillNode/en.md) 마스크와 프롬프트를 기반으로 이미지를 인페인트합니다. 이 노드는 Flux.1 모델을 사용하여 제공된 텍스트 설명에 따라 이미지의 마스크 영역을 채우고, 주변 이미지와 일치하는 새로운 콘텐츠를 생성합니다. diff --git a/ko/built-in-nodes/FluxProImageNode.mdx b/ko/built-in-nodes/FluxProImageNode.mdx index d9d96bdcc..a006208ab 100644 --- a/ko/built-in-nodes/FluxProImageNode.mdx +++ b/ko/built-in-nodes/FluxProImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxProImageNode" icon: "circle" mode: wide --- -# 개요 프롬프트와 해상도를 기반으로 이미지를 동기적으로 생성합니다. 이 노드는 Flux 1.1 Pro 모델을 사용하여 API 엔드포인트에 요청을 보내고, 완전한 응답을 받은 후 생성된 이미지를 반환하여 이미지를 생성합니다. diff --git a/ko/built-in-nodes/FluxProUltraImageNode.mdx b/ko/built-in-nodes/FluxProUltraImageNode.mdx index 3f604fe6f..1913ea32d 100644 --- a/ko/built-in-nodes/FluxProUltraImageNode.mdx +++ b/ko/built-in-nodes/FluxProUltraImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProUltraImageNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProUltraImageNode/en.md) 프롬프트와 해상도를 기반으로 API를 통해 Flux Pro 1.1 Ultra를 사용하여 이미지를 생성합니다. 이 노드는 외부 서비스에 연결하여 텍스트 설명과 지정된 크기에 따라 이미지를 만듭니다. diff --git a/ko/built-in-nodes/FluxVTONode.mdx b/ko/built-in-nodes/FluxVTONode.mdx index 26556d92c..f2e96d71f 100644 --- a/ko/built-in-nodes/FluxVTONode.mdx +++ b/ko/built-in-nodes/FluxVTONode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxVTONode" icon: "circle" mode: wide --- -# Flux 가상 피팅 이 노드는 제공된 의류 이미지를 사람에게 입혀 가상 피팅을 수행합니다. BFL Flux VTO API를 사용하여 지정된 의류를 입은 사람의 사실적인 이미지를 생성합니다. diff --git a/ko/built-in-nodes/FrameInterpolate.mdx b/ko/built-in-nodes/FrameInterpolate.mdx index ecc7732d8..35ebbcfd7 100644 --- a/ko/built-in-nodes/FrameInterpolate.mdx +++ b/ko/built-in-nodes/FrameInterpolate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FrameInterpolate" icon: "circle" mode: wide --- + ## 개요 Frame Interpolate 노드는 이미지 시퀀스에서 기존 프레임 사이에 새 프레임을 생성하여 프레임 속도를 효과적으로 증가시킵니다. AI 모델을 사용하여 중간 프레임이 어떻게 보여야 하는지 예측하며, 이를 통해 부드러운 슬로우 모션 효과를 만들거나 비디오의 부드러움을 향상시킬 수 있습니다. diff --git a/ko/built-in-nodes/FrameInterpolationModelLoader.mdx b/ko/built-in-nodes/FrameInterpolationModelLoader.mdx index 21913e1ff..4da9537c0 100644 --- a/ko/built-in-nodes/FrameInterpolationModelLoader.mdx +++ b/ko/built-in-nodes/FrameInterpolationModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FrameInterpolationModelLoader" icon: "circle" mode: wide --- + ## 개요 이 노드는 파일에서 프레임 보간 모델을 로드하여 워크플로우에서 사용할 수 있도록 준비합니다. 모델 유형(FILM 또는 RIFE)을 자동으로 감지하고, 사용자의 하드웨어에 최적화된 성능을 위해 모델을 구성합니다. diff --git a/ko/built-in-nodes/FreSca.mdx b/ko/built-in-nodes/FreSca.mdx index f9606d3cb..5754909f3 100644 --- a/ko/built-in-nodes/FreSca.mdx +++ b/ko/built-in-nodes/FreSca.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreSca" icon: "circle" mode: wide --- + FreSca 노드는 샘플링 과정에서 안내(guidance)에 주파수 종속 스케일링을 적용합니다. 푸리에 필터링을 사용하여 안내 신호를 저주파 성분과 고주파 성분으로 분리한 후, 각 주파수 범위에 서로 다른 스케일링 계수를 적용한 다음 다시 결합합니다. 이를 통해 생성된 출력물의 다양한 측면에 안내가 미치는 영향을 더욱 세밀하게 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/FreeU.mdx b/ko/built-in-nodes/FreeU.mdx index 161089238..d1f412ac4 100644 --- a/ko/built-in-nodes/FreeU.mdx +++ b/ko/built-in-nodes/FreeU.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreeU" icon: "circle" mode: wide --- + FreeU 노드는 모델의 출력 블록에 주파수 영역 변형을 적용하여 이미지 생성 품질을 향상시킵니다. 서로 다른 채널 그룹을 스케일링하고 특정 특징 맵에 푸리에 필터링을 적용함으로써, 생성 과정에서 모델의 동작을 세밀하게 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/FreeU_V2.mdx b/ko/built-in-nodes/FreeU_V2.mdx index eb16982d7..b81699497 100644 --- a/ko/built-in-nodes/FreeU_V2.mdx +++ b/ko/built-in-nodes/FreeU_V2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreeU_V2" icon: "circle" mode: wide --- + FreeU_V2 노드는 확산 모델의 U-Net 아키텍처에 주파수 기반 변형을 적용하여 이미지 생성 품질을 향상시킵니다. 구성 가능한 스케일링 팩터를 사용하여 서로 다른 블록의 특징 채널을 조정하며, 추가 학습 없이 출력 품질을 개선합니다. ## 입력 diff --git a/ko/built-in-nodes/GITSScheduler.mdx b/ko/built-in-nodes/GITSScheduler.mdx index f14335582..b08ff2613 100644 --- a/ko/built-in-nodes/GITSScheduler.mdx +++ b/ko/built-in-nodes/GITSScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GITSScheduler" icon: "circle" mode: wide --- + GITSScheduler 노드는 GITS(Generative Iterative Time Steps) 샘플링 방법을 위한 노이즈 스케줄 시그마를 생성합니다. 계수 매개변수와 단계 수를 기반으로 시그마 값을 계산하며, 선택적 디노이징 요소를 통해 사용되는 전체 단계 수를 줄일 수 있습니다. 이 노드는 사전 정의된 노이즈 수준과 보간법을 사용하여 최종 시그마 스케줄을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/GLIGENLoader.mdx b/ko/built-in-nodes/GLIGENLoader.mdx index 8db64bdd7..730988bdc 100644 --- a/ko/built-in-nodes/GLIGENLoader.mdx +++ b/ko/built-in-nodes/GLIGENLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLIGENLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/gligen` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 설정된 추가 경로의 모델도 읽어옵니다. 때로는 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수도 있습니다. `GLIGENLoader` 노드는 특수 생성 모델인 GLIGEN 모델을 로드하기 위해 설계되었습니다. 이 노드는 지정된 경로에서 이러한 모델을 검색하고 초기화하는 과정을 용이하게 하여, 이후의 생성 작업에 사용할 수 있도록 준비합니다. diff --git a/ko/built-in-nodes/GLIGENTextBoxApply.mdx b/ko/built-in-nodes/GLIGENTextBoxApply.mdx index f872d445d..128ea1a6f 100644 --- a/ko/built-in-nodes/GLIGENTextBoxApply.mdx +++ b/ko/built-in-nodes/GLIGENTextBoxApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLIGENTextBoxApply" icon: "circle" mode: wide --- + `GLIGENTextBoxApply` 노드는 텍스트 기반 컨디셔닝을 생성 모델의 입력에 통합하도록 설계되었습니다. 특히 텍스트 상자 매개변수를 적용하고 CLIP 모델을 사용하여 이를 인코딩합니다. 이 과정은 공간 및 텍스트 정보로 컨디셔닝을 강화하여 보다 정밀하고 맥락을 인식한 생성을 가능하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/GLSLShader.mdx b/ko/built-in-nodes/GLSLShader.mdx index 9d7ad2a70..1bdeb2e6c 100644 --- a/ko/built-in-nodes/GLSLShader.mdx +++ b/ko/built-in-nodes/GLSLShader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLSLShader" icon: "circle" mode: wide --- + The **GLSL Shader** node lets you write custom fragment shaders in **GLSL ES 3.00** (WebGL 2.0 compatible) to process images directly on the GPU. You can create image effects like blurs, color grading, film grain, glow, and much more - all running at GPU speed. diff --git a/ko/built-in-nodes/GeminiImage2Node.mdx b/ko/built-in-nodes/GeminiImage2Node.mdx index a794a8eb8..6a7db71ce 100644 --- a/ko/built-in-nodes/GeminiImage2Node.mdx +++ b/ko/built-in-nodes/GeminiImage2Node.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GeminiImage2Node" icon: "circle" mode: wide --- -# GeminiImage2Node GeminiImage2Node는 Google의 Vertex AI Gemini 모델을 사용하여 이미지를 생성하거나 편집합니다. 텍스트 프롬프트와 선택적 참조 이미지 또는 파일을 API로 전송하고 생성된 이미지 및/또는 텍스트 설명을 반환합니다. diff --git a/ko/built-in-nodes/GeminiImageNode.mdx b/ko/built-in-nodes/GeminiImageNode.mdx index ed445f612..8cc2f16e9 100644 --- a/ko/built-in-nodes/GeminiImageNode.mdx +++ b/ko/built-in-nodes/GeminiImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiImageNode" icon: "circle" mode: wide --- + GeminiImage 노드는 Google의 Gemini AI 모델로부터 텍스트 및 이미지 응답을 생성합니다. 텍스트 프롬프트, 이미지, 파일을 포함한 멀티모달 입력을 제공하여 일관된 텍스트 및 이미지 출력을 생성할 수 있습니다. 이 노드는 최신 Gemini 모델과의 모든 API 통신 및 응답 구문 분석을 처리합니다. ## 입력 diff --git a/ko/built-in-nodes/GeminiInputFiles.mdx b/ko/built-in-nodes/GeminiInputFiles.mdx index 5979de65f..2c6c90b5e 100644 --- a/ko/built-in-nodes/GeminiInputFiles.mdx +++ b/ko/built-in-nodes/GeminiInputFiles.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GeminiInputFiles" icon: "circle" mode: wide --- -# Gemini 입력 파일 Gemini API와 함께 사용하기 위해 입력 파일을 로드하고 형식을 지정합니다. 이 노드를 사용하면 사용자가 텍스트(.txt) 및 PDF(.pdf) 파일을 Gemini 모델의 입력 컨텍스트로 포함할 수 있습니다. 파일은 API에 필요한 적절한 형식으로 변환되며, 여러 파일을 연결하여 단일 요청에 포함시킬 수 있습니다. diff --git a/ko/built-in-nodes/GeminiNanoBanana2.mdx b/ko/built-in-nodes/GeminiNanoBanana2.mdx index c3f4c7a9b..9a614c70f 100644 --- a/ko/built-in-nodes/GeminiNanoBanana2.mdx +++ b/ko/built-in-nodes/GeminiNanoBanana2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GeminiNanoBanana2" icon: "circle" mode: wide --- -# GeminiNanoBanana2 GeminiNanoBanana2 노드는 Google의 Vertex AI Gemini 모델을 사용하여 이미지를 생성하거나 편집합니다. 이 노드는 텍스트 프롬프트와 선택적 참조 이미지 또는 파일을 API로 전송한 후, 생성된 이미지와 함께 제공되는 텍스트를 반환합니다. diff --git a/ko/built-in-nodes/GeminiNanoBanana2V2.mdx b/ko/built-in-nodes/GeminiNanoBanana2V2.mdx index 7b63d5621..bcb76026f 100644 --- a/ko/built-in-nodes/GeminiNanoBanana2V2.mdx +++ b/ko/built-in-nodes/GeminiNanoBanana2V2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GeminiNanoBanana2V2" icon: "circle" mode: wide --- -# 개요 이 노드는 Google의 Vertex AI API에 텍스트 프롬프트를 전송하여 이미지를 생성하거나 편집합니다. 특정 Gemini 모델을 사용하여 사용자의 지시에 따라 새 이미지를 만들거나 기존 이미지를 수정합니다. diff --git a/ko/built-in-nodes/GeminiNode.mdx b/ko/built-in-nodes/GeminiNode.mdx index 34d906594..b318042fc 100644 --- a/ko/built-in-nodes/GeminiNode.mdx +++ b/ko/built-in-nodes/GeminiNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiNode/en.md) 이 노드는 사용자가 Google의 Gemini AI 모델과 상호작용하여 텍스트 응답을 생성할 수 있도록 합니다. 모델이 더 관련성 높고 의미 있는 응답을 생성할 수 있도록 텍스트, 이미지, 오디오, 비디오 및 파일을 포함한 여러 유형의 입력을 컨텍스트로 제공할 수 있습니다. 이 노드는 모든 API 통신 및 응답 구문 분석을 자동으로 처리합니다. diff --git a/ko/built-in-nodes/GeminiNodeV2.mdx b/ko/built-in-nodes/GeminiNodeV2.mdx index 7c6a15b3b..964f38364 100644 --- a/ko/built-in-nodes/GeminiNodeV2.mdx +++ b/ko/built-in-nodes/GeminiNodeV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GeminiNodeV2" icon: "circle" mode: wide --- -# Google Gemini Google의 Gemini 모델을 사용하여 텍스트 응답을 생성합니다. 텍스트 프롬프트와 선택적으로 하나 이상의 이미지, 오디오 클립, 비디오 또는 파일을 멀티모달 컨텍스트로 제공할 수 있습니다. diff --git a/ko/built-in-nodes/GeminiVideoOmni.mdx b/ko/built-in-nodes/GeminiVideoOmni.mdx new file mode 100644 index 000000000..5686786b4 --- /dev/null +++ b/ko/built-in-nodes/GeminiVideoOmni.mdx @@ -0,0 +1,33 @@ +--- +title: "GeminiVideoOmni - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the GeminiVideoOmni node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "GeminiVideoOmni" +icon: "circle" +mode: wide +--- + +Google의 Gemini Omni Flash 모델을 사용하여 텍스트 프롬프트로 오디오가 포함된 비디오를 생성합니다. 필요에 따라 참조 이미지 및/또는 비디오를 제공하여 결과를 안내하거나 편집할 수 있습니다. 원하는 길이(3~10초)와 화면 비율(16:9 또는 9:16)을 프롬프트에 직접 설명하세요. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `model` | 비디오 생성에 사용되는 Gemini 비디오 모델입니다. | MODEL | 예 | "Omni Flash" | +| `seed` | 시드는 노드 재실행 여부를 제어합니다. 시드와 관계없이 결과는 비결정적입니다(기본값: 42). | INT | 예 | 0 ~ 2147483647 | +| `prompt` | 생성할 비디오를 설명하는 텍스트 프롬프트입니다. | STRING | 예 | 공백 제거 후 최소 1자 | +| `images` | 비디오 생성을 안내하는 선택적 참조 이미지입니다. 최대 14개의 이미지를 사용할 수 있습니다. | IMAGE | 아니요 | 여러 이미지 허용(최대 14개) | +| `videos` | 비디오 생성을 안내하거나 편집하는 선택적 참조 비디오입니다. 각각 최대 10초 길이의 비디오를 최대 3개까지 사용할 수 있습니다. | VIDEO | 아니요 | 여러 비디오 허용(최대 3개, 각 최대 10초) | +| `temperature` | 생성 과정의 무작위성을 제어합니다(기본값: 1.0). | FLOAT | 아니요 | 0.0 ~ 2.0 | +| `top_p` | 핵 샘플링 매개변수입니다(기본값: 0.95). | FLOAT | 아니요 | 0.0 ~ 1.0 | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `VIDEO` | Gemini 모델에서 생성된 오디오가 포함된 비디오입니다. | VIDEO | +| `STRING` | 추론 또는 설명과 같은 모델의 모든 텍스트 응답입니다. | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiVideoOmni/ko.md) + +--- +**Source fingerprint (SHA-256):** `046842b7ec736283bba355aaa038b02fcf2416020f5f7aee7b0150d2a05bcbe6` diff --git a/ko/built-in-nodes/GenerateTracks.mdx b/ko/built-in-nodes/GenerateTracks.mdx index f9c06ec4b..15eb563a4 100644 --- a/ko/built-in-nodes/GenerateTracks.mdx +++ b/ko/built-in-nodes/GenerateTracks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GenerateTracks" icon: "circle" mode: wide --- + `GenerateTracks` 노드는 비디오 생성을 위한 여러 개의 평행 이동 경로를 생성합니다. 시작점에서 끝점까지의 기본 경로를 정의한 후, 이 경로와 평행하게 일정 간격으로 배치된 트랙 세트를 생성합니다. 경로의 모양(직선 또는 베지어 곡선), 이동 속도, 트랙이 표시될 프레임을 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/GetICLoRAParameters.mdx b/ko/built-in-nodes/GetICLoRAParameters.mdx index a8ffdcb0c..ab0fa4786 100644 --- a/ko/built-in-nodes/GetICLoRAParameters.mdx +++ b/ko/built-in-nodes/GetICLoRAParameters.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetICLoRAParameters" icon: "circle" mode: wide --- + ## 개요 이 노드는 LoRA가 로드된 모델의 메타데이터에서 IC-LoRA 파라미터를 추출합니다. safetensors 메타데이터를 읽어 참조 다운스케일 팩터와 같은 값을 찾아 구조화된 파라미터 객체로 출력하며, 이 객체는 특수 가이드 처리를 위해 LTXVAddGuide 노드에 연결할 수 있습니다. diff --git a/ko/built-in-nodes/GetImageSize.mdx b/ko/built-in-nodes/GetImageSize.mdx index 48b2ac396..189939bb7 100644 --- a/ko/built-in-nodes/GetImageSize.mdx +++ b/ko/built-in-nodes/GetImageSize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetImageSize" icon: "circle" mode: wide --- + GetImageSize 노드는 입력 이미지의 크기와 배치 정보를 추출합니다. 이미지의 너비, 높이 및 배치 크기를 반환하며, 이 정보를 노드 인터페이스에 진행 텍스트로 표시합니다. 원본 이미지 데이터는 변경되지 않고 통과됩니다. ## 입력 @@ -17,8 +18,8 @@ GetImageSize 노드는 입력 이미지의 크기와 배치 정보를 추출합 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `height` | 입력 이미지의 너비(픽셀 단위) | INT | -| `batch_size` | 입력 이미지의 높이(픽셀 단위) | INT | +| `width` | 입력 이미지의 너비(픽셀 단위) | INT | +| `height` | 입력 이미지의 높이(픽셀 단위) | INT | | `batch_size` | 배치 내 이미지 개수 | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetImageSize/ko.md) diff --git a/ko/built-in-nodes/GetSplatCount.mdx b/ko/built-in-nodes/GetSplatCount.mdx index 3ddf93419..a184d786d 100644 --- a/ko/built-in-nodes/GetSplatCount.mdx +++ b/ko/built-in-nodes/GetSplatCount.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GetSplatCount" icon: "circle" mode: wide --- -# 스플랫 개수 가져오기 Get Splat Count 노드는 스플랫 배치에 포함된 총 스플랫(가우시안 포인트)의 개수를 반환하며, 배치 내 모든 항목의 개수를 합산합니다. 이 노드는 원본 스플랫 데이터를 변경하지 않고 그대로 전달하면서, 포함된 개별 스플랫의 수를 제공합니다. @@ -19,7 +18,7 @@ Get Splat Count 노드는 스플랫 배치에 포함된 총 스플랫(가우시 | 출력 이름 | 설명 | 데이터 타입 | |-------------|-------------|-----------| -| `count` | 변경되지 않고 그대로 전달된 원본 스플랫 데이터 | SPLAT | +| `splat` | 변경되지 않고 그대로 전달된 원본 스플랫 데이터 | SPLAT | | `count` | 배치 내 모든 스플랫의 총 개수를 합산한 값 | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetSplatCount/ko.md) diff --git a/ko/built-in-nodes/GetVideoComponents.mdx b/ko/built-in-nodes/GetVideoComponents.mdx index e6a2d047d..6aefe6c59 100644 --- a/ko/built-in-nodes/GetVideoComponents.mdx +++ b/ko/built-in-nodes/GetVideoComponents.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetVideoComponents" icon: "circle" mode: wide --- + Get Video Components 노드는 비디오 파일에서 모든 주요 구성 요소를 추출합니다. 비디오를 개별 프레임으로 분리하고, 오디오 트랙을 추출하며, 비디오의 프레임 속도 정보를 제공합니다. 이를 통해 각 구성 요소를 독립적으로 사용하여 추가 처리 또는 분석을 수행할 수 있습니다. ## 입력 @@ -17,8 +18,8 @@ Get Video Components 노드는 비디오 파일에서 모든 주요 구성 요 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `오디오` | 비디오에서 추출된 개별 프레임을 별도의 이미지로 제공합니다. | IMAGE | -| `fps` | 비디오에서 추출된 오디오 트랙입니다. | AUDIO | +| `이미지` | 비디오에서 추출된 개별 프레임을 별도의 이미지로 제공합니다. | IMAGE | +| `오디오` | 비디오에서 추출된 오디오 트랙입니다. | AUDIO | | `fps` | 초당 프레임 수로 표시된 비디오의 프레임 속도입니다. | FLOAT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetVideoComponents/ko.md) diff --git a/ko/built-in-nodes/GrokImageEditNode.mdx b/ko/built-in-nodes/GrokImageEditNode.mdx index 911c156ef..1b1cef6ba 100644 --- a/ko/built-in-nodes/GrokImageEditNode.mdx +++ b/ko/built-in-nodes/GrokImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokImageEditNode" icon: "circle" mode: wide --- + Grok Image Edit 노드는 텍스트 프롬프트를 기반으로 기존 이미지를 수정합니다. Grok API를 사용하여 입력 이미지의 변형으로, 사용자의 설명에 따라 하나 이상의 새 이미지를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/GrokImageEditNodeV2.mdx b/ko/built-in-nodes/GrokImageEditNodeV2.mdx index 47a63258a..76675a4d6 100644 --- a/ko/built-in-nodes/GrokImageEditNodeV2.mdx +++ b/ko/built-in-nodes/GrokImageEditNodeV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GrokImageEditNodeV2" icon: "circle" mode: wide --- -# Grok 이미지 편집 노드 V2 ## 개요 diff --git a/ko/built-in-nodes/GrokImageNode.mdx b/ko/built-in-nodes/GrokImageNode.mdx index 71926fffb..80e2e4957 100644 --- a/ko/built-in-nodes/GrokImageNode.mdx +++ b/ko/built-in-nodes/GrokImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GrokImageNode" icon: "circle" mode: wide --- -# Grok 이미지 노드 Grok 이미지 노드는 Grok AI 모델을 사용하여 텍스트 설명을 기반으로 하나 이상의 이미지를 생성합니다. 프롬프트를 외부 서비스로 전송하고 생성된 이미지를 워크플로우에서 사용할 수 있는 텐서로 반환합니다. diff --git a/ko/built-in-nodes/GrokVideoEditNode.mdx b/ko/built-in-nodes/GrokVideoEditNode.mdx index c46e6b3e5..31e7f3a01 100644 --- a/ko/built-in-nodes/GrokVideoEditNode.mdx +++ b/ko/built-in-nodes/GrokVideoEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoEditNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GrokVideoEditNode/en.md) 이 노드는 Grok API를 사용하여 텍스트 프롬프트를 기반으로 기존 비디오를 편집합니다. 비디오를 업로드하고, AI 모델에 요청을 보내 사용자의 설명에 따라 비디오를 수정한 후, 새로 생성된 비디오를 반환합니다. diff --git a/ko/built-in-nodes/GrokVideoExtendNode.mdx b/ko/built-in-nodes/GrokVideoExtendNode.mdx index fb110cd95..82a35f083 100644 --- a/ko/built-in-nodes/GrokVideoExtendNode.mdx +++ b/ko/built-in-nodes/GrokVideoExtendNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GrokVideoExtendNode" icon: "circle" mode: wide --- -# Grok 비디오 확장 노드 Grok 비디오 확장 노드는 AI 모델을 사용하여 기존 비디오의 자연스러운 연속 장면을 생성합니다. 짧은 비디오와 다음에 어떤 내용이 전개되어야 하는지 설명하는 텍스트 프롬프트를 제공하면, 노드가 원본 비디오에 이어지는 새로운 비디오 클립을 생성합니다. diff --git a/ko/built-in-nodes/GrokVideoNode.mdx b/ko/built-in-nodes/GrokVideoNode.mdx index 1549b2bee..548c00e8c 100644 --- a/ko/built-in-nodes/GrokVideoNode.mdx +++ b/ko/built-in-nodes/GrokVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GrokVideoNode" icon: "circle" mode: wide --- -# Grok Video 노드 Grok Video 노드는 텍스트 설명으로부터 짧은 비디오를 생성합니다. 프롬프트를 사용하여 처음부터 비디오를 만들거나, 프롬프트를 기반으로 단일 입력 이미지에 애니메이션을 적용할 수 있습니다. 이 노드는 외부 API에 요청을 보내고 생성된 비디오를 반환합니다. diff --git a/ko/built-in-nodes/GrokVideoReferenceNode.mdx b/ko/built-in-nodes/GrokVideoReferenceNode.mdx index 6a1dabee5..5bc3006b7 100644 --- a/ko/built-in-nodes/GrokVideoReferenceNode.mdx +++ b/ko/built-in-nodes/GrokVideoReferenceNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GrokVideoReferenceNode" icon: "circle" mode: wide --- -# Grok 참조-투-비디오 노드 Grok 참조-투-비디오 노드는 텍스트 프롬프트를 기반으로 비디오를 생성하며, 최대 7개의 참조 이미지를 사용하여 출력물의 스타일과 내용을 안내합니다. 외부 API에 연결하여 비디오를 생성한 후 다운로드하여 반환합니다. diff --git a/ko/built-in-nodes/GrowMask.mdx b/ko/built-in-nodes/GrowMask.mdx index f39d1b29f..67ddc8905 100644 --- a/ko/built-in-nodes/GrowMask.mdx +++ b/ko/built-in-nodes/GrowMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrowMask" icon: "circle" mode: wide --- + `GrowMask` 노드는 지정된 마스크의 크기를 확장 또는 축소하고, 선택적으로 모서리에 테이퍼 효과를 적용하도록 설계되었습니다. 이 기능은 이미지 처리 작업에서 마스크 경계를 동적으로 조정하여 관심 영역을 보다 유연하고 정밀하게 제어할 수 있도록 하는 데 중요합니다. ## 입력 diff --git a/ko/built-in-nodes/HappyHorseImageToVideoApi.mdx b/ko/built-in-nodes/HappyHorseImageToVideoApi.mdx index 70f4455c5..975ff047a 100644 --- a/ko/built-in-nodes/HappyHorseImageToVideoApi.mdx +++ b/ko/built-in-nodes/HappyHorseImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseImageToVideoApi" icon: "circle" mode: wide --- + ## 개요 이 노드는 HappyHorse 모델을 사용하여 단일 시작 이미지로부터 짧은 비디오를 생성합니다. 첫 번째 프레임 이미지와 원하는 동작 및 장면을 설명하는 텍스트 프롬프트를 제공하면, 노드가 해당 이미지에서 이어지는 비디오를 생성합니다. diff --git a/ko/built-in-nodes/HappyHorseReferenceVideoApi.mdx b/ko/built-in-nodes/HappyHorseReferenceVideoApi.mdx index 44d916006..5d0161520 100644 --- a/ko/built-in-nodes/HappyHorseReferenceVideoApi.mdx +++ b/ko/built-in-nodes/HappyHorseReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseReferenceVideoApi" icon: "circle" mode: wide --- + ## 개요 이 노드는 HappyHorse 모델을 사용하여 참조 이미지를 기반으로 사람이나 객체가 등장하는 비디오를 생성합니다. 단일 캐릭터 또는 여러 캐릭터가 상호 작용하는 비디오 제작을 지원합니다. diff --git a/ko/built-in-nodes/HappyHorseTextToVideoApi.mdx b/ko/built-in-nodes/HappyHorseTextToVideoApi.mdx index 0299129d1..93e45c573 100644 --- a/ko/built-in-nodes/HappyHorseTextToVideoApi.mdx +++ b/ko/built-in-nodes/HappyHorseTextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseTextToVideoApi" icon: "circle" mode: wide --- + ## 개요 HappyHorse 모델을 사용하여 텍스트 프롬프트를 기반으로 비디오를 생성합니다. 이 노드는 프롬프트와 설정을 HappyHorse API로 전송하고, 비디오가 생성될 때까지 대기한 후 결과를 다운로드합니다. diff --git a/ko/built-in-nodes/HappyHorseVideoEditApi.mdx b/ko/built-in-nodes/HappyHorseVideoEditApi.mdx index 7c2ed76f6..4d233da94 100644 --- a/ko/built-in-nodes/HappyHorseVideoEditApi.mdx +++ b/ko/built-in-nodes/HappyHorseVideoEditApi.mdx @@ -5,7 +5,6 @@ sidebarTitle: "HappyHorseVideoEditApi" icon: "circle" mode: wide --- -# 개요 HappyHorse 모델을 사용하여 텍스트 명령어나 참조 이미지를 통해 비디오를 편집합니다. 출력 길이는 3~15초이며 입력 비디오와 일치하고, 15초를 초과하는 입력은 잘립니다. diff --git a/ko/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx b/ko/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx index d14b4275c..91102940f 100644 --- a/ko/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx +++ b/ko/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HiDreamO1PatchSeamSmoothing" icon: "circle" mode: wide --- + ## 개요 이 노드는 샘플링 프로세스 후반부에 여러 개의 이동된 패치 그리드 위치에서 모델 출력을 평균화하여 HiDream-O1 모델이 생성한 이미지의 눈에 띄는 이음새를 줄입니다. 약간 다른 이미지 정렬로 모델을 여러 번 실행하고 결과를 혼합하여 패치 경계에서 나타날 수 있는 그리드 형태의 아티팩트를 상쇄하는 방식으로 작동합니다. diff --git a/ko/built-in-nodes/HiDreamO1ReferenceImages.mdx b/ko/built-in-nodes/HiDreamO1ReferenceImages.mdx index 45aa747ed..e18025d72 100644 --- a/ko/built-in-nodes/HiDreamO1ReferenceImages.mdx +++ b/ko/built-in-nodes/HiDreamO1ReferenceImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HiDreamO1ReferenceImages" icon: "circle" mode: wide --- + ## 개요 긍정 및 부정 컨디셔닝에 참조 이미지를 첨부합니다. 이 노드를 사용하면 하나 이상의 참조 이미지를 제공하여 이미지 생성 과정을 안내할 수 있으며, 명령어 기반 편집 또는 주제 기반 개인화에 사용됩니다. @@ -23,7 +24,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 참조 이미지가 첨부된 긍정 컨디셔닝입니다. | CONDITIONING | +| `positive` | 참조 이미지가 첨부된 긍정 컨디셔닝입니다. | CONDITIONING | | `negative` | 참조 이미지가 첨부된 부정 컨디셔닝입니다. | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HiDreamO1ReferenceImages/ko.md) diff --git a/ko/built-in-nodes/HitPawGeneralImageEnhance.mdx b/ko/built-in-nodes/HitPawGeneralImageEnhance.mdx index b670c1e2d..4fdeadb36 100644 --- a/ko/built-in-nodes/HitPawGeneralImageEnhance.mdx +++ b/ko/built-in-nodes/HitPawGeneralImageEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HitPawGeneralImageEnhance" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HitPawGeneralImageEnhance/en.md) 이 노드는 저해상도 이미지를 업스케일링하여 초고해상도로 향상시키고, 아티팩트와 노이즈를 제거합니다. 외부 API를 사용하여 이미지를 처리하며, 처리 제한을 초과하지 않도록 입력 크기를 자동으로 조정할 수 있습니다. 최대 허용 출력 크기는 4메가픽셀입니다. diff --git a/ko/built-in-nodes/HitPawVideoEnhance.mdx b/ko/built-in-nodes/HitPawVideoEnhance.mdx index 7e3cf9251..e0e7385d3 100644 --- a/ko/built-in-nodes/HitPawVideoEnhance.mdx +++ b/ko/built-in-nodes/HitPawVideoEnhance.mdx @@ -5,7 +5,6 @@ sidebarTitle: "HitPawVideoEnhance" icon: "circle" mode: wide --- -# HitPaw Video Enhance 노드 HitPaw Video Enhance 노드는 외부 API를 사용하여 비디오 품질을 향상시킵니다. 저해상도 비디오를 더 높은 해상도로 업스케일하고, 시각적 아티팩트를 제거하며, 노이즈를 줄입니다. 처리 비용은 입력 비디오의 초 단위로 계산됩니다. diff --git a/ko/built-in-nodes/Hunyuan3Dv2Conditioning.mdx b/ko/built-in-nodes/Hunyuan3Dv2Conditioning.mdx index d76a96e1c..b2784a1c6 100644 --- a/ko/built-in-nodes/Hunyuan3Dv2Conditioning.mdx +++ b/ko/built-in-nodes/Hunyuan3Dv2Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Hunyuan3Dv2Conditioning" icon: "circle" mode: wide --- + Hunyuan3Dv2Conditioning 노드는 CLIP 비전 출력을 처리하여 3D 모델을 위한 컨디셔닝 데이터를 생성합니다. 비전 출력에서 마지막 은닉 상태 임베딩을 추출하여 양성 및 음성 컨디셔닝 쌍을 만듭니다. 양성 컨디셔닝은 실제 임베딩을 사용하는 반면, 음성 컨디셔닝은 동일한 형태의 0값 임베딩을 사용합니다. ## 입력 @@ -17,7 +18,7 @@ Hunyuan3Dv2Conditioning 노드는 CLIP 비전 출력을 처리하여 3D 모델 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | CLIP 비전 임베딩을 포함하는 양성 컨디셔닝 데이터 | CONDITIONING | +| `positive` | CLIP 비전 임베딩을 포함하는 양성 컨디셔닝 데이터 | CONDITIONING | | `negative` | 양성 임베딩 형태와 일치하는 0값 임베딩을 포함하는 음성 컨디셔닝 데이터 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2Conditioning/ko.md) diff --git a/ko/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx b/ko/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx index 55eeba9c8..515170681 100644 --- a/ko/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx +++ b/ko/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Hunyuan3Dv2ConditioningMultiView" icon: "circle" mode: wide --- + Hunyuan3Dv2ConditioningMultiView 노드는 3D 비디오 생성을 위한 다중 뷰 CLIP 비전 임베딩을 처리합니다. 선택적으로 전면, 좌측, 후면 및 우측 뷰 임베딩을 입력받아 위치 인코딩과 결합하여 비디오 모델을 위한 컨디셔닝 데이터를 생성합니다. 이 노드는 결합된 임베딩으로부터의 포지티브 컨디셔닝과 0 값으로 구성된 네거티브 컨디셔닝을 모두 출력합니다. ## 입력 @@ -22,7 +23,7 @@ Hunyuan3Dv2ConditioningMultiView 노드는 3D 비디오 생성을 위한 다중 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 위치 인코딩이 적용된 결합 다중 뷰 임베딩을 포함하는 포지티브 컨디셔닝 | CONDITIONING | +| `positive` | 위치 인코딩이 적용된 결합 다중 뷰 임베딩을 포함하는 포지티브 컨디셔닝 | CONDITIONING | | `negative` | 대조 학습을 위한 0 값의 네거티브 컨디셔닝 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2ConditioningMultiView/ko.md) diff --git a/ko/built-in-nodes/HunyuanImageToVideo.mdx b/ko/built-in-nodes/HunyuanImageToVideo.mdx index 7e2aa1817..633dc346e 100644 --- a/ko/built-in-nodes/HunyuanImageToVideo.mdx +++ b/ko/built-in-nodes/HunyuanImageToVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "HunyuanImageToVideo" icon: "circle" mode: wide --- -# HunyuanImageToVideo 노드 HunyuanImageToVideo 노드는 Hunyuan 비디오 모델을 사용하여 이미지를 비디오 잠재 표현으로 변환합니다. 조건 입력과 선택적 시작 이미지를 받아 비디오 생성 모델에서 추가 처리할 수 있는 비디오 잠재를 생성합니다. 이 노드는 시작 이미지가 비디오 생성 과정에 영향을 미치는 방식을 제어하기 위한 다양한 안내 유형을 지원합니다. @@ -32,8 +31,8 @@ HunyuanImageToVideo 노드는 Hunyuan 비디오 모델을 사용하여 이미지 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `잠재 비디오` | start_image가 제공될 때 이미지 안내가 적용된 수정된 긍정 조건 | CONDITIONING | -| `latent` | 비디오 생성 모델에서 추가 처리를 위해 준비된 비디오 잠재 표현 | LATENT | +| `긍정 조건` | start_image가 제공될 때 이미지 안내가 적용된 수정된 긍정 조건 | CONDITIONING | +| `잠재 비디오` | 비디오 생성 모델에서 추가 처리를 위해 준비된 비디오 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanImageToVideo/ko.md) diff --git a/ko/built-in-nodes/HunyuanRefinerLatent.mdx b/ko/built-in-nodes/HunyuanRefinerLatent.mdx index 56c3725e5..a0a49e7f1 100644 --- a/ko/built-in-nodes/HunyuanRefinerLatent.mdx +++ b/ko/built-in-nodes/HunyuanRefinerLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanRefinerLatent" icon: "circle" mode: wide --- + HunyuanRefinerLatent 노드는 리파인먼트 작업을 위해 컨디셔닝 및 잠재 입력을 처리합니다. 양성 및 음성 컨디셔닝에 노이즈 증강을 적용하면서 잠재 이미지 데이터를 통합하고, 추가 처리를 위해 특정 차원의 새로운 잠재 출력을 생성합니다. ## 입력 @@ -20,8 +21,8 @@ HunyuanRefinerLatent 노드는 리파인먼트 작업을 위해 컨디셔닝 및 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정적` | 노이즈 증강 및 잠재 이미지 연결이 적용된 처리된 양성 컨디셔닝 | CONDITIONING | -| `잠재` | 노이즈 증강 및 잠재 이미지 연결이 적용된 처리된 음성 컨디셔닝 | CONDITIONING | +| `긍정적` | 노이즈 증강 및 잠재 이미지 연결이 적용된 처리된 양성 컨디셔닝 | CONDITIONING | +| `부정적` | 노이즈 증강 및 잠재 이미지 연결이 적용된 처리된 음성 컨디셔닝 | CONDITIONING | | `잠재` | [배치_크기, 32, 높이, 너비, 채널] 차원의 새로운 잠재 출력 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanRefinerLatent/ko.md) diff --git a/ko/built-in-nodes/HunyuanVideo15ImageToVideo.mdx b/ko/built-in-nodes/HunyuanVideo15ImageToVideo.mdx index 4ee62ae1a..ada779ef1 100644 --- a/ko/built-in-nodes/HunyuanVideo15ImageToVideo.mdx +++ b/ko/built-in-nodes/HunyuanVideo15ImageToVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "HunyuanVideo15ImageToVideo" icon: "circle" mode: wide --- -# HunyuanVideo15ImageToVideo HunyuanVideo15ImageToVideo 노드는 HunyuanVideo 1.5 모델을 기반으로 비디오 생성을 위한 컨디셔닝 및 잠재 공간 데이터를 준비합니다. 비디오 시퀀스의 초기 잠재 표현을 생성하며, 선택적으로 시작 이미지나 CLIP 비전 출력을 통합하여 생성 과정을 안내할 수 있습니다. @@ -29,8 +28,8 @@ HunyuanVideo15ImageToVideo 노드는 HunyuanVideo 1.5 모델을 기반으로 비 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 수정된 긍정 컨디셔닝으로, 이제 인코딩된 시작 이미지 또는 CLIP 비전 출력이 포함될 수 있습니다. | CONDITIONING | -| `latent` | 수정된 부정 컨디셔닝으로, 이제 인코딩된 시작 이미지 또는 CLIP 비전 출력이 포함될 수 있습니다. | CONDITIONING | +| `positive` | 수정된 긍정 컨디셔닝으로, 이제 인코딩된 시작 이미지 또는 CLIP 비전 출력이 포함될 수 있습니다. | CONDITIONING | +| `negative` | 수정된 부정 컨디셔닝으로, 이제 인코딩된 시작 이미지 또는 CLIP 비전 출력이 포함될 수 있습니다. | CONDITIONING | | `latent` | 지정된 배치 크기, 비디오 길이, 너비 및 높이에 맞게 차원이 구성된 빈 잠재 텐서입니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15ImageToVideo/ko.md) diff --git a/ko/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx b/ko/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx index a96818953..02050eab6 100644 --- a/ko/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx +++ b/ko/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx @@ -5,7 +5,6 @@ sidebarTitle: "HunyuanVideo15LatentUpscaleWithModel" icon: "circle" mode: wide --- -# Hunyuan Video 15 Latent Upscale With Model 노드 Hunyuan Video 15 Latent Upscale With Model 노드는 잠재 이미지 표현의 해상도를 높입니다. 먼저 선택한 보간 방법을 사용하여 잠재 샘플을 지정된 크기로 업스케일한 후, 전문화된 Hunyuan Video 1.5 업스케일 모델을 사용하여 업스케일된 결과를 정제하여 품질을 개선합니다. diff --git a/ko/built-in-nodes/HunyuanVideo15SuperResolution.mdx b/ko/built-in-nodes/HunyuanVideo15SuperResolution.mdx index df202327b..739ae4c28 100644 --- a/ko/built-in-nodes/HunyuanVideo15SuperResolution.mdx +++ b/ko/built-in-nodes/HunyuanVideo15SuperResolution.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15SuperResolution" icon: "circle" mode: wide --- + HunyuanVideo15SuperResolution 노드는 비디오 초고해상도 프로세스를 위한 컨디셔닝 데이터를 준비합니다. 비디오의 잠재 표현과 선택적으로 시작 이미지를 입력받아 노이즈 증강 및 CLIP 비전 데이터와 함께 패키징하여 모델이 더 높은 해상도의 출력을 생성하는 데 사용할 수 있는 형식으로 변환합니다. ## 입력 @@ -25,8 +26,8 @@ HunyuanVideo15SuperResolution 노드는 비디오 초고해상도 프로세스 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 연결된 잠재, 노이즈 증강 및 선택적 CLIP 비전 데이터를 포함하도록 수정된 긍정 컨디셔닝입니다. | CONDITIONING | -| `latent` | 연결된 잠재, 노이즈 증강 및 선택적 CLIP 비전 데이터를 포함하도록 수정된 부정 컨디셔닝입니다. | CONDITIONING | +| `positive` | 연결된 잠재, 노이즈 증강 및 선택적 CLIP 비전 데이터를 포함하도록 수정된 긍정 컨디셔닝입니다. | CONDITIONING | +| `negative` | 연결된 잠재, 노이즈 증강 및 선택적 CLIP 비전 데이터를 포함하도록 수정된 부정 컨디셔닝입니다. | CONDITIONING | | `latent` | 입력 잠재가 변경 없이 그대로 전달됩니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15SuperResolution/ko.md) diff --git a/ko/built-in-nodes/HyperTile.mdx b/ko/built-in-nodes/HyperTile.mdx index e959474e2..3c87aeb22 100644 --- a/ko/built-in-nodes/HyperTile.mdx +++ b/ko/built-in-nodes/HyperTile.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HyperTile" icon: "circle" mode: wide --- + HyperTile 노드는 확산 모델의 어텐션 메커니즘에 타일링 기법을 적용하여 이미지 생성 시 메모리 사용량을 최적화합니다. 잠재 공간을 더 작은 타일로 나누어 개별적으로 처리한 후 결과를 다시 조합합니다. 이를 통해 메모리 부족 없이 더 큰 이미지 크기로 작업할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/HypernetworkLoader.mdx b/ko/built-in-nodes/HypernetworkLoader.mdx index 8a4e27bfb..d48d4caab 100644 --- a/ko/built-in-nodes/HypernetworkLoader.mdx +++ b/ko/built-in-nodes/HypernetworkLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HypernetworkLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/hypernetworks` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 설정된 추가 경로의 모델도 함께 읽어옵니다. 때로는 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더의 모델 파일을 읽도록 해야 할 수도 있습니다. HypernetworkLoader 노드는 하이퍼네트워크를 적용하여 주어진 모델의 기능을 향상시키거나 수정하도록 설계되었습니다. 지정된 하이퍼네트워크를 로드하여 모델에 적용하며, 강도 매개변수에 따라 모델의 동작이나 성능을 변경할 수 있습니다. 이 과정을 통해 모델의 아키텍처나 매개변수를 동적으로 조정하여 보다 유연하고 적응력 있는 AI 시스템을 구현할 수 있습니다. diff --git a/ko/built-in-nodes/Ideogram4Scheduler.mdx b/ko/built-in-nodes/Ideogram4Scheduler.mdx index ac5e2e4c1..eb4b3a0cc 100644 --- a/ko/built-in-nodes/Ideogram4Scheduler.mdx +++ b/ko/built-in-nodes/Ideogram4Scheduler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Ideogram4Scheduler" icon: "circle" mode: wide --- -# Ideogram 4 스케줄러 Ideogram 4 스케줄러 노드는 Ideogram 4 참조 스케줄을 기반으로 확산 샘플링 과정에 사용되는 시그마 값(노이즈 수준)의 시퀀스를 생성합니다. 이미지 크기에 맞춰 조정되는 사용자 정의 노이즈 스케줄을 생성하며, 통계적 매개변수를 통해 미세 조정이 가능합니다. diff --git a/ko/built-in-nodes/IdeogramV1.mdx b/ko/built-in-nodes/IdeogramV1.mdx index b28f20017..f4d945fc6 100644 --- a/ko/built-in-nodes/IdeogramV1.mdx +++ b/ko/built-in-nodes/IdeogramV1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "IdeogramV1" icon: "circle" mode: wide --- + IdeogramV1 노드는 API를 통해 Ideogram V1 모델을 사용하여 이미지를 생성합니다. 텍스트 프롬프트와 다양한 생성 설정을 입력받아 하나 이상의 이미지를 생성합니다. 이 노드는 다양한 종횡비와 생성 모드를 지원하여 출력 결과를 사용자 지정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/IdeogramV2.mdx b/ko/built-in-nodes/IdeogramV2.mdx index 8e5c89426..6a170d52d 100644 --- a/ko/built-in-nodes/IdeogramV2.mdx +++ b/ko/built-in-nodes/IdeogramV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "IdeogramV2" icon: "circle" mode: wide --- -# Ideogram V2 노드 Ideogram V2 노드는 Ideogram V2 AI 모델을 사용하여 이미지를 생성합니다. 텍스트 프롬프트와 다양한 생성 설정을 입력받아 API 서비스를 통해 이미지를 생성합니다. 이 노드는 다양한 종횡비, 해상도 및 스타일 옵션을 지원하여 출력 이미지를 사용자 지정할 수 있습니다. diff --git a/ko/built-in-nodes/IdeogramV3.mdx b/ko/built-in-nodes/IdeogramV3.mdx index 349ef4007..f60c25008 100644 --- a/ko/built-in-nodes/IdeogramV3.mdx +++ b/ko/built-in-nodes/IdeogramV3.mdx @@ -5,7 +5,6 @@ sidebarTitle: "IdeogramV3" icon: "circle" mode: wide --- -# Ideogram V3 Ideogram V3 노드는 Ideogram V3 모델을 사용하여 이미지를 생성합니다. 텍스트 프롬프트로 일반 이미지 생성과 이미지와 마스크가 모두 제공될 때의 이미지 편집을 모두 지원합니다. 이 노드는 화면 비율, 해상도, 생성 속도 및 선택적 캐릭터 참조 이미지에 대한 다양한 제어 기능을 제공합니다. diff --git a/ko/built-in-nodes/IdeogramV4.mdx b/ko/built-in-nodes/IdeogramV4.mdx index 644288d46..a4bf66e12 100644 --- a/ko/built-in-nodes/IdeogramV4.mdx +++ b/ko/built-in-nodes/IdeogramV4.mdx @@ -5,7 +5,6 @@ sidebarTitle: "IdeogramV4" icon: "circle" mode: wide --- -# Ideogram V4 텍스트 프롬프트를 사용하여 Ideogram 4.0 모델로 이미지를 생성합니다. 이 노드는 텍스트 설명을 Ideogram API로 전송하고 생성된 이미지를 출력 텐서로 반환합니다. diff --git a/ko/built-in-nodes/ImageAddNoise.mdx b/ko/built-in-nodes/ImageAddNoise.mdx index f204c422c..d9ddb1fc8 100644 --- a/ko/built-in-nodes/ImageAddNoise.mdx +++ b/ko/built-in-nodes/ImageAddNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageAddNoise" icon: "circle" mode: wide --- + ImageAddNoise 노드는 입력 이미지에 무작위 노이즈를 추가합니다. 지정된 난수 시드를 사용하여 일관된 노이즈 패턴을 생성하고, 노이즈 효과의 강도를 제어할 수 있습니다. 결과 이미지는 입력 이미지와 동일한 크기를 유지하지만 시각적 텍스처가 추가됩니다. ## 입력 diff --git a/ko/built-in-nodes/ImageBatch.mdx b/ko/built-in-nodes/ImageBatch.mdx index 5ab45f8d2..989a01335 100644 --- a/ko/built-in-nodes/ImageBatch.mdx +++ b/ko/built-in-nodes/ImageBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBatch" icon: "circle" mode: wide --- + `ImageBatch` 노드는 두 개의 이미지를 하나의 배치로 결합하도록 설계되었습니다. 이미지의 크기가 일치하지 않는 경우, 결합하기 전에 두 번째 이미지를 첫 번째 이미지의 크기에 맞게 자동으로 크기를 조정합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageBlend.mdx b/ko/built-in-nodes/ImageBlend.mdx index 21775438b..91f912a87 100644 --- a/ko/built-in-nodes/ImageBlend.mdx +++ b/ko/built-in-nodes/ImageBlend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBlend" icon: "circle" mode: wide --- + `ImageBlend` 노드는 지정된 블렌드 모드와 블렌드 비율에 따라 두 이미지를 혼합하도록 설계되었습니다. 일반, 곱하기, 스크린, 오버레이, 부드러운 빛, 차이 등 다양한 블렌드 모드를 지원하여 다용도 이미지 조작 및 합성 기술을 가능하게 합니다. 이 노드는 두 이미지 레이어 간의 시각적 상호 작용을 조정하여 합성 이미지를 만드는 데 필수적입니다. ## 입력 diff --git a/ko/built-in-nodes/ImageBlur.mdx b/ko/built-in-nodes/ImageBlur.mdx index 22d700544..efaaede7d 100644 --- a/ko/built-in-nodes/ImageBlur.mdx +++ b/ko/built-in-nodes/ImageBlur.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBlur" icon: "circle" mode: wide --- + `ImageBlur` 노드는 이미지에 가우시안 블러를 적용하여 가장자리를 부드럽게 하고 세부 묘사와 노이즈를 줄입니다. 매개변수를 통해 블러의 강도와 확산 범위를 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ImageColorToMask.mdx b/ko/built-in-nodes/ImageColorToMask.mdx index 891815dfd..aaf354e25 100644 --- a/ko/built-in-nodes/ImageColorToMask.mdx +++ b/ko/built-in-nodes/ImageColorToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageColorToMask" icon: "circle" mode: wide --- + `ImageColorToMask` 노드는 이미지에서 지정된 색상을 마스크로 변환하도록 설계되었습니다. 이미지와 대상 색상을 처리하여 지정된 색상이 강조된 마스크를 생성하며, 색상 기반 분할이나 객체 분리와 같은 작업을 용이하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageCompare.mdx b/ko/built-in-nodes/ImageCompare.mdx index 83fbc2761..24a25b1db 100644 --- a/ko/built-in-nodes/ImageCompare.mdx +++ b/ko/built-in-nodes/ImageCompare.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ImageCompare" icon: "circle" mode: wide --- -# 이미지 비교(Image Compare) 이미지 비교 노드는 드래그 가능한 슬라이더를 사용하여 두 이미지를 나란히 비교할 수 있는 시각적 인터페이스를 제공합니다. 출력 노드로 설계되어 다른 노드에 데이터를 전달하지 않고, 대신 사용자 인터페이스에 이미지를 직접 표시하여 검사할 수 있도록 합니다. diff --git a/ko/built-in-nodes/ImageCompositeMasked.mdx b/ko/built-in-nodes/ImageCompositeMasked.mdx index d9f5485f7..1d1e8d524 100644 --- a/ko/built-in-nodes/ImageCompositeMasked.mdx +++ b/ko/built-in-nodes/ImageCompositeMasked.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCompositeMasked" icon: "circle" mode: wide --- + `ImageCompositeMasked` 노드는 이미지를 합성하기 위해 설계된 노드로, 소스 이미지를 대상 이미지 위에 지정된 좌표에 겹쳐 놓을 수 있으며, 선택적으로 크기 조정 및 마스킹 기능을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageCrop.mdx b/ko/built-in-nodes/ImageCrop.mdx index ff0b275b8..8704f191d 100644 --- a/ko/built-in-nodes/ImageCrop.mdx +++ b/ko/built-in-nodes/ImageCrop.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCrop" icon: "circle" mode: wide --- + `ImageCrop` 노드는 지정된 x, y 좌표에서 시작하여 설정된 너비와 높이로 이미지를 자르기 위해 설계되었습니다. 이 기능은 이미지의 특정 영역에 초점을 맞추거나 특정 요구 사항에 맞게 이미지 크기를 조정하는 데 필수적입니다. ## 입력 diff --git a/ko/built-in-nodes/ImageCropV2.mdx b/ko/built-in-nodes/ImageCropV2.mdx index 3435a158c..d3415796e 100644 --- a/ko/built-in-nodes/ImageCropV2.mdx +++ b/ko/built-in-nodes/ImageCropV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ImageCropV2" icon: "circle" mode: wide --- -# 이미지 자르기(Image Crop) 이미지 자르기 노드는 입력 이미지에서 직사각형 영역을 추출합니다. 유지할 영역의 왼쪽 상단 모서리 좌표와 너비 및 높이를 지정하여 정의할 수 있습니다. 그런 다음 노드는 원본 이미지에서 잘라낸 부분을 반환합니다. diff --git a/ko/built-in-nodes/ImageDeduplication.mdx b/ko/built-in-nodes/ImageDeduplication.mdx index c7e1d412d..5ff32303e 100644 --- a/ko/built-in-nodes/ImageDeduplication.mdx +++ b/ko/built-in-nodes/ImageDeduplication.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageDeduplication" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageDeduplication/en.md) 이 노드는 배치에서 중복되거나 매우 유사한 이미지를 제거합니다. 각 이미지에 대해 시각적 콘텐츠를 기반으로 한 간단한 숫자 지문인 지각적 해시를 생성한 후 이를 비교하는 방식으로 작동합니다. 설정된 임계값보다 해시 유사도가 높은 이미지는 중복으로 간주되어 필터링됩니다. diff --git a/ko/built-in-nodes/ImageFlip.mdx b/ko/built-in-nodes/ImageFlip.mdx index 7c81ded1f..f258e6148 100644 --- a/ko/built-in-nodes/ImageFlip.mdx +++ b/ko/built-in-nodes/ImageFlip.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageFlip" icon: "circle" mode: wide --- + ImageFlip 노드는 이미지를 다양한 축을 따라 뒤집습니다. x축을 따라 수직으로 또는 y축을 따라 수평으로 이미지를 뒤집을 수 있습니다. 이 노드는 선택한 방법에 따라 torch.flip 연산을 사용하여 뒤집기를 수행합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageFromBatch.mdx b/ko/built-in-nodes/ImageFromBatch.mdx index 065208dda..b50d424a1 100644 --- a/ko/built-in-nodes/ImageFromBatch.mdx +++ b/ko/built-in-nodes/ImageFromBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageFromBatch" icon: "circle" mode: wide --- + `ImageFromBatch` 노드는 제공된 인덱스와 길이를 기준으로 배치에서 특정 이미지 세그먼트를 추출하도록 설계되었습니다. 이를 통해 배치된 이미지를 보다 세밀하게 제어할 수 있으며, 더 큰 배치 내에서 개별 이미지 또는 이미지 하위 집합에 대한 작업을 수행할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ImageGrid.mdx b/ko/built-in-nodes/ImageGrid.mdx index 3e8db7be8..24622ce19 100644 --- a/ko/built-in-nodes/ImageGrid.mdx +++ b/ko/built-in-nodes/ImageGrid.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageGrid" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageGrid/en.md) Image Grid 노드는 여러 이미지를 하나의 정리된 그리드 또는 콜라주로 결합합니다. 이미지 목록을 받아 지정된 열 수에 맞게 배열하고, 각 이미지를 정의된 셀 크기에 맞게 크기를 조정하며, 선택적으로 이미지 사이에 여백을 추가합니다. 결과적으로 모든 입력 이미지가 그리드 레이아웃으로 배치된 단일 새 이미지가 생성됩니다. @@ -23,7 +24,7 @@ Image Grid 노드는 여러 이미지를 하나의 정리된 그리드 또는 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `image` | 모든 입력 이미지가 그리드로 배열된 단일 출력 이미지입니다. | IMAGE | +| `이미지` | 모든 입력 이미지가 그리드로 배열된 단일 출력 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageGrid/ko.md) diff --git a/ko/built-in-nodes/ImageHistogram.mdx b/ko/built-in-nodes/ImageHistogram.mdx index 02ec8faa6..70a6b39b0 100644 --- a/ko/built-in-nodes/ImageHistogram.mdx +++ b/ko/built-in-nodes/ImageHistogram.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageHistogram" icon: "circle" mode: wide --- + ImageHistogram 노드는 입력 이미지의 색상 분포를 분석합니다. 이 노드는 이미지에서 각 가능한 강도 값에 해당하는 픽셀 수를 보여주는 그래프인 여러 히스토그램을 계산하여 출력합니다. 빨간색, 녹색, 파란색 채널에 대한 개별 히스토그램, 복합 RGB 히스토그램, 그리고 표준 밝기 공식을 기반으로 한 휘도 히스토그램을 생성합니다. ## 입력 @@ -17,11 +18,11 @@ ImageHistogram 노드는 입력 이미지의 색상 분포를 분석합니다. | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `휘도` | 빨간색, 녹색, 파란색 채널의 평균 픽셀 강도를 나타내는 복합 히스토그램입니다. | HISTOGRAM | -| `레드` | ITU-R BT.709 표준 휘도 공식을 사용하여 계산된 이미지의 인지적 밝기에 대한 히스토그램입니다. | HISTOGRAM | -| `그린` | 빨간색 채널의 픽셀 강도 분포를 보여주는 히스토그램입니다. | HISTOGRAM | -| `블루` | 녹색 채널의 픽셀 강도 분포를 보여주는 히스토그램입니다. | HISTOGRAM | -| `blue` | 파란색 채널의 픽셀 강도 분포를 보여주는 히스토그램입니다. | HISTOGRAM | +| `RGB` | 빨간색, 녹색, 파란색 채널의 평균 픽셀 강도를 나타내는 복합 히스토그램입니다. | HISTOGRAM | +| `휘도` | ITU-R BT.709 표준 휘도 공식을 사용하여 계산된 이미지의 인지적 밝기에 대한 히스토그램입니다. | HISTOGRAM | +| `레드` | 빨간색 채널의 픽셀 강도 분포를 보여주는 히스토그램입니다. | HISTOGRAM | +| `그린` | 녹색 채널의 픽셀 강도 분포를 보여주는 히스토그램입니다. | HISTOGRAM | +| `블루` | 파란색 채널의 픽셀 강도 분포를 보여주는 히스토그램입니다. | HISTOGRAM | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageHistogram/ko.md) diff --git a/ko/built-in-nodes/ImageInvert.mdx b/ko/built-in-nodes/ImageInvert.mdx index ef76bfb4d..e473cff16 100644 --- a/ko/built-in-nodes/ImageInvert.mdx +++ b/ko/built-in-nodes/ImageInvert.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageInvert" icon: "circle" mode: wide --- + `ImageInvert` 노드는 이미지의 색상을 반전시키도록 설계되었으며, 각 픽셀의 색상 값을 색상환에서 보색으로 효과적으로 변환합니다. 이 작업은 네거티브 이미지를 만들거나 색상 반전이 필요한 시각적 효과에 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageMergeTileList.mdx b/ko/built-in-nodes/ImageMergeTileList.mdx index cba3a64d6..76c971a4e 100644 --- a/ko/built-in-nodes/ImageMergeTileList.mdx +++ b/ko/built-in-nodes/ImageMergeTileList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageMergeTileList" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageMergeTileList/en.md) 이 노드는 이미지 타일 목록을 가져와서 하나의 더 큰 이미지로 병합합니다. 이전에 겹치는 타일 그리드로 분할된 이미지를 재구성하도록 설계되었으며, 가중치 혼합 기법을 사용하여 매끄러운 최종 결과를 생성합니다. diff --git a/ko/built-in-nodes/ImageOnlyCheckpointLoader.mdx b/ko/built-in-nodes/ImageOnlyCheckpointLoader.mdx index 7347aa454..812e73556 100644 --- a/ko/built-in-nodes/ImageOnlyCheckpointLoader.mdx +++ b/ko/built-in-nodes/ImageOnlyCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageOnlyCheckpointLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/checkpoints` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 설정된 추가 경로의 모델도 함께 읽어옵니다. 때로는 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수도 있습니다. 이 노드는 비디오 생성 워크플로우 내에서 이미지 기반 모델을 위한 체크포인트 로딩에 특화되어 있습니다. 주어진 체크포인트에서 필요한 구성 요소를 효율적으로 검색 및 설정하며, 모델의 이미지 관련 측면에 중점을 둡니다. diff --git a/ko/built-in-nodes/ImageOnlyCheckpointSave.mdx b/ko/built-in-nodes/ImageOnlyCheckpointSave.mdx index 1451ebdd0..0f9d1d058 100644 --- a/ko/built-in-nodes/ImageOnlyCheckpointSave.mdx +++ b/ko/built-in-nodes/ImageOnlyCheckpointSave.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ImageOnlyCheckpointSave" icon: "circle" mode: wide --- -# ImageOnlyCheckpointSave 노드 ImageOnlyCheckpointSave 노드는 모델, CLIP 비전 인코더 및 VAE가 포함된 체크포인트 파일을 저장합니다. 지정된 파일명 접두사를 사용하여 safetensors 파일을 생성하고 출력 디렉토리에 저장합니다. 이 노드는 이미지 관련 모델 구성 요소를 단일 체크포인트 파일로 함께 저장하도록 특별히 설계되었습니다. diff --git a/ko/built-in-nodes/ImagePadForOutpaint.mdx b/ko/built-in-nodes/ImagePadForOutpaint.mdx index e024a8c7c..30879a4ec 100644 --- a/ko/built-in-nodes/ImagePadForOutpaint.mdx +++ b/ko/built-in-nodes/ImagePadForOutpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImagePadForOutpaint" icon: "circle" mode: wide --- + 이 노드는 이미지 주변에 패딩을 추가하여 아웃페인팅(outpainting) 프로세스를 위한 이미지를 준비하도록 설계되었습니다. 원본 경계를 넘어 확장된 이미지 영역을 생성하는 것을 용이하게 하기 위해, 아웃페인팅 알고리즘과의 호환성을 보장하도록 이미지 크기를 조정합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageQuantize.mdx b/ko/built-in-nodes/ImageQuantize.mdx index bf9fee325..443a2edbe 100644 --- a/ko/built-in-nodes/ImageQuantize.mdx +++ b/ko/built-in-nodes/ImageQuantize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageQuantize" icon: "circle" mode: wide --- + ImageQuantize 노드는 이미지의 색상 수를 지정된 개수로 줄이고, 필요에 따라 디더링 기법을 적용하여 시각적 품질을 유지하도록 설계되었습니다. 이 프로세스는 팔레트 기반 이미지를 만들거나 특정 응용 프로그램을 위해 색상 복잡성을 줄이는 데 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageRGBToYUV.mdx b/ko/built-in-nodes/ImageRGBToYUV.mdx index 779d8d889..24ffda877 100644 --- a/ko/built-in-nodes/ImageRGBToYUV.mdx +++ b/ko/built-in-nodes/ImageRGBToYUV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageRGBToYUV" icon: "circle" mode: wide --- + ImageRGBToYUV 노드는 RGB 컬러 이미지를 YUV 색 공간으로 변환합니다. 입력으로 RGB 이미지를 받아 Y(휘도), U(청색 투영), V(적색 투영)의 세 가지 개별 채널로 분리합니다. 각 출력 채널은 해당 YUV 구성 요소를 나타내는 별도의 그레이스케일 이미지로 반환됩니다. ## 입력 @@ -17,8 +18,8 @@ ImageRGBToYUV 노드는 RGB 컬러 이미지를 YUV 색 공간으로 변환합 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `U` | YUV 색 공간의 휘도(밝기) 구성 요소 | IMAGE | -| `V` | YUV 색 공간의 청색 투영 구성 요소 | IMAGE | +| `Y` | YUV 색 공간의 휘도(밝기) 구성 요소 | IMAGE | +| `U` | YUV 색 공간의 청색 투영 구성 요소 | IMAGE | | `V` | YUV 색 공간의 적색 투영 구성 요소 | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageRGBToYUV/ko.md) diff --git a/ko/built-in-nodes/ImageRotate.mdx b/ko/built-in-nodes/ImageRotate.mdx index d682c6c37..7c2bd2835 100644 --- a/ko/built-in-nodes/ImageRotate.mdx +++ b/ko/built-in-nodes/ImageRotate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageRotate" icon: "circle" mode: wide --- + ImageRotate 노드는 입력 이미지를 지정된 각도로 회전합니다. 회전 없음, 시계 방향 90도, 180도, 시계 방향 270도의 네 가지 회전 옵션을 지원합니다. 회전은 이미지 데이터 무결성을 유지하는 효율적인 텐서 연산을 사용하여 수행됩니다. ## 입력 diff --git a/ko/built-in-nodes/ImageScale.mdx b/ko/built-in-nodes/ImageScale.mdx index 7cde415d8..5eae4f519 100644 --- a/ko/built-in-nodes/ImageScale.mdx +++ b/ko/built-in-nodes/ImageScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScale" icon: "circle" mode: wide --- + ImageScale 노드는 이미지를 특정 크기로 조정하기 위해 설계되었으며, 다양한 업스케일 방법과 크기 조정된 이미지의 자르기 기능을 제공합니다. 이미지 업스케일링 및 자르기의 복잡성을 추상화하여 사용자 정의 매개변수에 따라 이미지 크기를 수정할 수 있는 직관적인 인터페이스를 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageScaleBy.mdx b/ko/built-in-nodes/ImageScaleBy.mdx index a10794554..d088e8841 100644 --- a/ko/built-in-nodes/ImageScaleBy.mdx +++ b/ko/built-in-nodes/ImageScaleBy.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleBy" icon: "circle" mode: wide --- + ImageScaleBy 노드는 다양한 보간 방법을 사용하여 지정된 배율로 이미지를 업스케일링하도록 설계되었습니다. 다양한 업스케일링 요구에 맞춰 유연하게 이미지 크기를 조정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ImageScaleToMaxDimension.mdx b/ko/built-in-nodes/ImageScaleToMaxDimension.mdx index 7f215cb3b..a2e76aa37 100644 --- a/ko/built-in-nodes/ImageScaleToMaxDimension.mdx +++ b/ko/built-in-nodes/ImageScaleToMaxDimension.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ImageScaleToMaxDimension" icon: "circle" mode: wide --- -# ImageScaleToMaxDimension 노드 ImageScaleToMaxDimension 노드는 원본 비율을 유지하면서 지정된 최대 크기에 맞게 이미지를 리사이즈합니다. 이미지가 세로 방향인지 가로 방향인지 계산한 후, 더 큰 쪽의 크기를 목표 크기에 맞추고 작은 쪽의 크기는 비례적으로 조정합니다. 이 노드는 다양한 품질과 성능 요구 사항에 맞는 여러 업스케일링 방법을 지원합니다. diff --git a/ko/built-in-nodes/ImageScaleToTotalPixels.mdx b/ko/built-in-nodes/ImageScaleToTotalPixels.mdx index 1af0259ad..09cba56aa 100644 --- a/ko/built-in-nodes/ImageScaleToTotalPixels.mdx +++ b/ko/built-in-nodes/ImageScaleToTotalPixels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleToTotalPixels" icon: "circle" mode: wide --- + **ImageScaleToTotalPixels** 노드는 이미지의 가로세로 비율을 유지하면서 지정된 총 픽셀 수로 크기를 조정하도록 설계되었습니다. 원하는 픽셀 수를 달성하기 위해 이미지를 업스케일링하는 다양한 방법을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageSharpen.mdx b/ko/built-in-nodes/ImageSharpen.mdx index a221c191b..80d33a9aa 100644 --- a/ko/built-in-nodes/ImageSharpen.mdx +++ b/ko/built-in-nodes/ImageSharpen.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageSharpen" icon: "circle" mode: wide --- + ImageSharpen 노드는 이미지의 가장자리와 세부 사항을 강조하여 선명도를 향상시킵니다. 이미지에 선명화 필터를 적용하며, 강도와 반경을 조정할 수 있어 이미지가 더 선명하고 또렷하게 보이도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageStitch.mdx b/ko/built-in-nodes/ImageStitch.mdx index 71d95e037..21dfc9e19 100644 --- a/ko/built-in-nodes/ImageStitch.mdx +++ b/ko/built-in-nodes/ImageStitch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageStitch" icon: "circle" mode: wide --- + 이 노드는 두 개의 이미지를 지정된 방향(위, 아래, 왼쪽, 오른쪽)으로 결합할 수 있으며, 크기 일치 및 이미지 간 간격 설정을 지원합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageToMask.mdx b/ko/built-in-nodes/ImageToMask.mdx index 9b98478b5..4f350d926 100644 --- a/ko/built-in-nodes/ImageToMask.mdx +++ b/ko/built-in-nodes/ImageToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageToMask" icon: "circle" mode: wide --- + ImageToMask 노드는 지정된 색상 채널을 기반으로 이미지를 마스크로 변환하도록 설계되었습니다. 이미지의 빨간색, 녹색, 파란색 또는 알파 채널에 해당하는 마스크 레이어를 추출할 수 있어, 채널별 마스킹이나 처리가 필요한 작업을 용이하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageUpscaleWithModel.mdx b/ko/built-in-nodes/ImageUpscaleWithModel.mdx index f2f754d35..dd8636f2c 100644 --- a/ko/built-in-nodes/ImageUpscaleWithModel.mdx +++ b/ko/built-in-nodes/ImageUpscaleWithModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageUpscaleWithModel" icon: "circle" mode: wide --- + 이 노드는 지정된 업스케일 모델을 사용하여 이미지를 업스케일링하도록 설계되었습니다. 이미지를 적절한 장치에 맞게 조정하고, 메모리 사용을 최적화하며, 잠재적인 메모리 부족 오류를 방지하기 위해 타일 방식으로 업스케일 모델을 적용하여 업스케일링 프로세스를 효율적으로 관리합니다. ## 입력 diff --git a/ko/built-in-nodes/ImageYUVToRGB.mdx b/ko/built-in-nodes/ImageYUVToRGB.mdx index 75921c305..322462ccb 100644 --- a/ko/built-in-nodes/ImageYUVToRGB.mdx +++ b/ko/built-in-nodes/ImageYUVToRGB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageYUVToRGB" icon: "circle" mode: wide --- + ImageYUVToRGB 노드는 YUV 색상 공간 이미지를 RGB 색상 공간으로 변환합니다. Y(휘도), U(청색 투영), V(적색 투영) 채널을 나타내는 세 개의 개별 입력 이미지를 받아 색상 공간 변환을 통해 하나의 RGB 이미지로 결합합니다. ## 입력 diff --git a/ko/built-in-nodes/InpaintModelConditioning.mdx b/ko/built-in-nodes/InpaintModelConditioning.mdx index 728dd9df6..2ded2a42b 100644 --- a/ko/built-in-nodes/InpaintModelConditioning.mdx +++ b/ko/built-in-nodes/InpaintModelConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InpaintModelConditioning" icon: "circle" mode: wide --- + InpaintModelConditioning 노드는 인페인팅 모델을 위한 컨디셔닝 프로세스를 용이하게 하도록 설계되어, 다양한 컨디셔닝 입력을 통합 및 조작하여 인페인팅 출력을 맞춤화할 수 있도록 합니다. 특정 모델 체크포인트 로드, 스타일 또는 컨트롤 넷 모델 적용부터 컨디셔닝 요소 인코딩 및 결합에 이르기까지 광범위한 기능을 포함하므로, 인페인팅 작업을 사용자 정의하기 위한 포괄적인 도구 역할을 합니다. ## 입력 @@ -21,8 +22,8 @@ InpaintModelConditioning 노드는 인페인팅 모델을 위한 컨디셔닝 | 매개변수 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 처리 후 수정된 긍정적 컨디셔닝 정보로, 인페인팅 모델에 적용할 준비가 되었습니다. 이 출력은 지정된 긍정적 조건에 따라 인페인팅 프로세스를 안내하는 데 필수적입니다. | `CONDITIONING` | -| `잠재 데이터` | 처리 후 수정된 부정적 컨디셔닝 정보로, 인페인팅 모델에 적용할 준비가 되었습니다. 이 출력은 지정된 부정적 조건에 따라 인페인팅 프로세스를 안내하는 데 필수적입니다. | `CONDITIONING` | -| `latent` | 컨디셔닝 프로세스에서 파생된 잠재 표현입니다. 이 출력은 인페인팅 중인 이미지의 기본 특징과 특성을 이해하는 데 중요합니다. | `LATENT` | +| `긍정 조건` | 처리 후 수정된 긍정적 컨디셔닝 정보로, 인페인팅 모델에 적용할 준비가 되었습니다. 이 출력은 지정된 긍정적 조건에 따라 인페인팅 프로세스를 안내하는 데 필수적입니다. | `CONDITIONING` | +| `부정 조건` | 처리 후 수정된 부정적 컨디셔닝 정보로, 인페인팅 모델에 적용할 준비가 되었습니다. 이 출력은 지정된 부정적 조건에 따라 인페인팅 프로세스를 안내하는 데 필수적입니다. | `CONDITIONING` | +| `잠재 데이터` | 컨디셔닝 프로세스에서 파생된 잠재 표현입니다. 이 출력은 인페인팅 중인 이미지의 기본 특징과 특성을 이해하는 데 중요합니다. | `LATENT` | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InpaintModelConditioning/ko.md) diff --git a/ko/built-in-nodes/InstructPixToPixConditioning.mdx b/ko/built-in-nodes/InstructPixToPixConditioning.mdx index 0eab2c84b..a63b11ea4 100644 --- a/ko/built-in-nodes/InstructPixToPixConditioning.mdx +++ b/ko/built-in-nodes/InstructPixToPixConditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "InstructPixToPixConditioning" icon: "circle" mode: wide --- -# InstructPixToPixConditioning InstructPixToPixConditioning 노드는 긍정 및 부정 텍스트 프롬프트를 이미지 데이터와 결합하여 InstructPix2Pix 이미지 편집을 위한 컨디셔닝 데이터를 준비합니다. VAE 인코더를 통해 입력 이미지를 처리하여 잠재 표현을 생성하고, 이 잠재 텐서를 긍정 및 부정 컨디셔닝 데이터에 모두 첨부합니다. 이 노드는 VAE 인코딩 프로세스와의 호환성을 위해 이미지 크기를 8픽셀 단위로 자동으로 자릅니다. @@ -24,9 +23,9 @@ InstructPixToPixConditioning 노드는 긍정 및 부정 텍스트 프롬프트 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 잠재 이미지 표현이 첨부된 긍정 컨디셔닝 데이터 | CONDITIONING | -| `잠재 이미지` | 잠재 이미지 표현이 첨부된 부정 컨디셔닝 데이터 | CONDITIONING | -| `latent` | 인코딩된 이미지와 동일한 크기의 빈 잠재 텐서 | LATENT | +| `긍정 조건` | 잠재 이미지 표현이 첨부된 긍정 컨디셔닝 데이터 | CONDITIONING | +| `부정 조건` | 잠재 이미지 표현이 첨부된 부정 컨디셔닝 데이터 | CONDITIONING | +| `잠재 이미지` | 인코딩된 이미지와 동일한 크기의 빈 잠재 텐서 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InstructPixToPixConditioning/ko.md) diff --git a/ko/built-in-nodes/InvertBooleanNode.mdx b/ko/built-in-nodes/InvertBooleanNode.mdx index ffde54c99..e1665a827 100644 --- a/ko/built-in-nodes/InvertBooleanNode.mdx +++ b/ko/built-in-nodes/InvertBooleanNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InvertBooleanNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InvertBooleanNode/en.md) 이 노드는 단일 부울(true/false) 입력을 받아 반대 값을 출력합니다. 논리적 NOT 연산을 수행하여 `true`를 `false`로, `false`를 `true`로 변환합니다. diff --git a/ko/built-in-nodes/InvertMask.mdx b/ko/built-in-nodes/InvertMask.mdx index 6ba93206d..556751473 100644 --- a/ko/built-in-nodes/InvertMask.mdx +++ b/ko/built-in-nodes/InvertMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InvertMask" icon: "circle" mode: wide --- + InvertMask 노드는 주어진 마스크의 값을 반전시켜 마스크 영역과 비마스크 영역을 효과적으로 뒤바꾸도록 설계되었습니다. 이 작업은 관심 영역을 전경과 배경 간에 전환해야 하는 이미지 처리 작업에서 기본적으로 사용됩니다. ## 입력 diff --git a/ko/built-in-nodes/JoinAudioChannels.mdx b/ko/built-in-nodes/JoinAudioChannels.mdx index 43f426bda..3ba4578d0 100644 --- a/ko/built-in-nodes/JoinAudioChannels.mdx +++ b/ko/built-in-nodes/JoinAudioChannels.mdx @@ -5,7 +5,6 @@ sidebarTitle: "JoinAudioChannels" icon: "circle" mode: wide --- -# 오디오 채널 결합 오디오 채널 결합 노드는 두 개의 개별 모노 오디오 입력을 하나의 스테레오 오디오 출력으로 결합합니다. 왼쪽 채널과 오른쪽 채널을 입력받아 호환되는 샘플 레이트와 길이를 보장한 후, 두 채널을 하나의 오디오 파형으로 병합합니다. diff --git a/ko/built-in-nodes/JoinImageWithAlpha.mdx b/ko/built-in-nodes/JoinImageWithAlpha.mdx index bea311be5..0621e849d 100644 --- a/ko/built-in-nodes/JoinImageWithAlpha.mdx +++ b/ko/built-in-nodes/JoinImageWithAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JoinImageWithAlpha" icon: "circle" mode: wide --- + 이 노드는 합성 작업을 위해 설계되었으며, 특히 이미지와 해당 알파 마스크를 결합하여 단일 출력 이미지를 생성합니다. 시각적 콘텐츠와 투명도 정보를 효과적으로 결합하여 특정 영역이 투명하거나 반투명한 이미지를 만들 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/JsonExtractString.mdx b/ko/built-in-nodes/JsonExtractString.mdx index d8a36ab26..26a56a82f 100644 --- a/ko/built-in-nodes/JsonExtractString.mdx +++ b/ko/built-in-nodes/JsonExtractString.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JsonExtractString" icon: "circle" mode: wide --- + JsonExtractString 노드는 JSON 데이터가 포함된 텍스트 문자열을 읽고 특정 키와 연결된 값을 추출합니다. 추출된 값을 문자열로 변환합니다. JSON이 유효하지 않거나, 키를 찾을 수 없거나, 값이 null인 경우 노드는 빈 문자열을 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/KSampler.mdx b/ko/built-in-nodes/KSampler.mdx index 1b840cb38..217caf572 100644 --- a/ko/built-in-nodes/KSampler.mdx +++ b/ko/built-in-nodes/KSampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSampler" icon: "circle" mode: wide --- + KSampler는 다음과 같이 작동합니다: 특정 모델과 긍정 및 부정 조건을 기반으로 제공된 원본 잠재 이미지 정보를 수정합니다. 먼저 설정된 **시드(seed)** 및 **디노이즈 강도(denoise strength)**에 따라 원본 이미지 데이터에 노이즈를 추가한 후, 사전 설정된 **모델(Model)**과 **긍정(positive)** 및 **부정(negative)** 안내 조건을 결합하여 이미지를 생성합니다. diff --git a/ko/built-in-nodes/KSamplerAdvanced.mdx b/ko/built-in-nodes/KSamplerAdvanced.mdx index 99049308b..6e38c8ca3 100644 --- a/ko/built-in-nodes/KSamplerAdvanced.mdx +++ b/ko/built-in-nodes/KSamplerAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSamplerAdvanced" icon: "circle" mode: wide --- + KSamplerAdvanced 노드는 고급 구성과 기술을 제공하여 샘플링 프로세스를 개선하도록 설계되었습니다. 기본 KSampler 기능을 개선하여 모델에서 샘플을 생성하기 위한 보다 정교한 옵션을 제공하는 것을 목표로 합니다. ## 입력 diff --git a/ko/built-in-nodes/KSamplerSelect.mdx b/ko/built-in-nodes/KSamplerSelect.mdx index 980322fea..355afc8fd 100644 --- a/ko/built-in-nodes/KSamplerSelect.mdx +++ b/ko/built-in-nodes/KSamplerSelect.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSamplerSelect" icon: "circle" mode: wide --- + KSamplerSelect 노드는 제공된 샘플러 이름을 기반으로 특정 샘플러를 선택하도록 설계되었습니다. 이 노드는 샘플러 선택의 복잡성을 추상화하여 사용자가 작업에 맞게 다양한 샘플링 전략을 쉽게 전환할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/Kandinsky5ImageToVideo.mdx b/ko/built-in-nodes/Kandinsky5ImageToVideo.mdx index d4f5101c9..971aaa4b2 100644 --- a/ko/built-in-nodes/Kandinsky5ImageToVideo.mdx +++ b/ko/built-in-nodes/Kandinsky5ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Kandinsky5ImageToVideo" icon: "circle" mode: wide --- + Kandinsky5ImageToVideo 노드는 Kandinsky 모델을 사용하여 비디오 생성을 위한 조건화(conditioning) 및 잠재 공간(latent space) 데이터를 준비합니다. 빈 비디오 잠재 텐서를 생성하고, 선택적으로 시작 이미지를 인코딩하여 생성된 비디오의 초기 프레임을 안내함으로써 긍정 및 부정 조건화를 수정할 수 있습니다. ## 입력 @@ -26,9 +27,9 @@ Kandinsky5ImageToVideo 노드는 Kandinsky 모델을 사용하여 비디오 생 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 인코딩된 시작 이미지 데이터로 잠재적으로 업데이트된 수정된 긍정 조건화입니다. | CONDITIONING | -| `latent` | 인코딩된 시작 이미지 데이터로 잠재적으로 업데이트된 수정된 부정 조건화입니다. | CONDITIONING | -| `cond_latent` | 지정된 차원에 맞게 형태가 조정된 0으로 채워진 빈 비디오 잠재 텐서입니다. | LATENT | +| `positive` | 인코딩된 시작 이미지 데이터로 잠재적으로 업데이트된 수정된 긍정 조건화입니다. | CONDITIONING | +| `negative` | 인코딩된 시작 이미지 데이터로 잠재적으로 업데이트된 수정된 부정 조건화입니다. | CONDITIONING | +| `latent` | 지정된 차원에 맞게 형태가 조정된 0으로 채워진 빈 비디오 잠재 텐서입니다. | LATENT | | `cond_latent` | 제공된 시작 이미지의 깨끗하고 인코딩된 잠재 표현입니다. 이는 생성된 비디오 잠재값의 노이즈가 있는 시작 부분을 대체하기 위해 내부적으로 사용됩니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Kandinsky5ImageToVideo/ko.md) diff --git a/ko/built-in-nodes/KarrasScheduler.mdx b/ko/built-in-nodes/KarrasScheduler.mdx index 6b7c30900..68b7181b5 100644 --- a/ko/built-in-nodes/KarrasScheduler.mdx +++ b/ko/built-in-nodes/KarrasScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KarrasScheduler" icon: "circle" mode: wide --- + KarrasScheduler 노드는 Karras 등(2022)의 노이즈 스케줄을 기반으로 일련의 노이즈 레벨(시그마)을 생성하도록 설계되었습니다. 이 스케줄러는 생성 모델의 확산 과정을 제어하는 데 유용하며, 생성 과정의 각 단계에 적용되는 노이즈 레벨을 세밀하게 조정할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/KlingAvatarNode.mdx b/ko/built-in-nodes/KlingAvatarNode.mdx index ee6ebc78e..becd936a2 100644 --- a/ko/built-in-nodes/KlingAvatarNode.mdx +++ b/ko/built-in-nodes/KlingAvatarNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingAvatarNode" icon: "circle" mode: wide --- -# Kling Avatar 2.0 노드 Kling Avatar 2.0 노드는 단일 참조 사진과 오디오 파일로부터 방송 스타일의 디지털 휴먼 비디오를 생성합니다. 선택적 텍스트 프롬프트를 통해 아바타의 동작, 감정 및 카메라 움직임을 정의하여 말하는 아바타 비디오를 제작합니다. diff --git a/ko/built-in-nodes/KlingCameraControlI2VNode.mdx b/ko/built-in-nodes/KlingCameraControlI2VNode.mdx index cf98103cc..daf57d5b7 100644 --- a/ko/built-in-nodes/KlingCameraControlI2VNode.mdx +++ b/ko/built-in-nodes/KlingCameraControlI2VNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingCameraControlI2VNode" icon: "circle" mode: wide --- -# Kling 이미지-투-비디오 카메라 제어 노드 Kling 이미지-투-비디오 카메라 제어 노드는 정적 이미지를 전문적인 카메라 움직임이 있는 시네마틱 비디오로 변환합니다. 이 특화된 이미지-투-비디오 노드를 사용하면 원본 이미지에 초점을 유지하면서 확대/축소, 회전, 패닝, 틸팅 및 1인칭 시점을 포함한 가상 카메라 동작을 제어할 수 있습니다. 카메라 제어는 현재 kling-v1-5 모델을 사용한 프로 모드에서 5초 길이로만 지원됩니다. @@ -25,8 +24,8 @@ Kling 이미지-투-비디오 카메라 제어 노드는 정적 이미지를 전 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | 생성된 비디오 출력 | VIDEO | -| `길이` | 생성된 비디오의 고유 식별자 | STRING | -| `duration` | 생성된 비디오의 길이 | STRING | +| `비디오 ID` | 생성된 비디오의 고유 식별자 | STRING | +| `길이` | 생성된 비디오의 길이 | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlI2VNode/ko.md) diff --git a/ko/built-in-nodes/KlingCameraControlT2VNode.mdx b/ko/built-in-nodes/KlingCameraControlT2VNode.mdx index 21ac2928c..29159fc7a 100644 --- a/ko/built-in-nodes/KlingCameraControlT2VNode.mdx +++ b/ko/built-in-nodes/KlingCameraControlT2VNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingCameraControlT2VNode" icon: "circle" mode: wide --- -# Kling 텍스트-비디오 카메라 제어 노드 Kling 텍스트-비디오 카메라 제어 노드는 텍스트를 실제 영화 촬영 기법을 시뮬레이션하는 전문적인 카메라 움직임이 있는 시네마틱 비디오로 변환합니다. 이 노드는 줌, 회전, 패닝, 틸트 및 1인칭 시점을 포함한 가상 카메라 동작을 제어하면서 원본 텍스트에 대한 초점을 유지합니다. 지속 시간, 모드 및 모델 이름은 하드코딩되어 있습니다. 카메라 제어는 kling-v1-5 모델의 프로 모드에서 5초 지속 시간으로만 지원되기 때문입니다. @@ -24,8 +23,8 @@ Kling 텍스트-비디오 카메라 제어 노드는 텍스트를 실제 영화 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | 카메라 제어 효과가 적용된 생성된 비디오 | VIDEO | -| `길이` | 생성된 비디오의 고유 식별자 | STRING | -| `duration` | 생성된 비디오의 지속 시간 | STRING | +| `비디오 ID` | 생성된 비디오의 고유 식별자 | STRING | +| `길이` | 생성된 비디오의 지속 시간 | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlT2VNode/ko.md) diff --git a/ko/built-in-nodes/KlingCameraControls.mdx b/ko/built-in-nodes/KlingCameraControls.mdx index a29e81c3c..4341f86fa 100644 --- a/ko/built-in-nodes/KlingCameraControls.mdx +++ b/ko/built-in-nodes/KlingCameraControls.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingCameraControls" icon: "circle" mode: wide --- -# Kling 카메라 컨트롤 노드 Kling 카메라 컨트롤 노드는 비디오 생성에서 모션 컨트롤 효과를 만들기 위한 다양한 카메라 이동 및 회전 매개변수를 구성할 수 있도록 합니다. 카메라 위치 지정, 회전 및 줌을 위한 컨트롤을 제공하여 다양한 카메라 움직임을 시뮬레이션합니다. @@ -27,7 +26,7 @@ Kling 카메라 컨트롤 노드는 비디오 생성에서 모션 컨트롤 효 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `camera_control` | 비디오 생성에 사용할 구성된 카메라 컨트롤 설정을 반환합니다 | CAMERA_CONTROL | +| `카메라 제어` | 비디오 생성에 사용할 구성된 카메라 컨트롤 설정을 반환합니다 | CAMERA_CONTROL | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControls/ko.md) diff --git a/ko/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx b/ko/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx index 0b7720e2d..122b25871 100644 --- a/ko/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx +++ b/ko/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingDualCharacterVideoEffectNode" icon: "circle" mode: wide --- -# Kling 듀얼 캐릭터 비디오 효과 노드 Kling 듀얼 캐릭터 비디오 효과 노드는 선택한 장면에 따라 특수 효과가 적용된 비디오를 생성합니다. 두 개의 이미지를 입력받아 첫 번째 이미지는 합성 비디오의 왼쪽에, 두 번째 이미지는 오른쪽에 배치합니다. 선택한 효과 장면에 따라 다양한 시각적 효과가 적용됩니다. diff --git a/ko/built-in-nodes/KlingFirstLastFrameNode.mdx b/ko/built-in-nodes/KlingFirstLastFrameNode.mdx index 2a193b0f9..8675cec6e 100644 --- a/ko/built-in-nodes/KlingFirstLastFrameNode.mdx +++ b/ko/built-in-nodes/KlingFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingFirstLastFrameNode" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingFirstLastFrameNode/en.md) 이 노드는 Kling 3.0 모델을 사용하여 비디오를 생성합니다. 텍스트 프롬프트, 지정된 길이, 그리고 제공된 두 개의 이미지(시작 프레임과 종료 프레임)를 기반으로 비디오를 생성합니다. 또한 비디오에 맞춰 오디오를 함께 생성할 수도 있습니다. diff --git a/ko/built-in-nodes/KlingImage2VideoNode.mdx b/ko/built-in-nodes/KlingImage2VideoNode.mdx index 2eb3b656a..c922c87f4 100644 --- a/ko/built-in-nodes/KlingImage2VideoNode.mdx +++ b/ko/built-in-nodes/KlingImage2VideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingImage2VideoNode" icon: "circle" mode: wide --- -# Kling 이미지-투-비디오 노드 Kling 이미지-투-비디오 노드는 시작 참조 이미지와 텍스트 프롬프트를 사용하여 비디오를 생성합니다. 이미지를 첫 번째 프레임으로 사용하고, 긍정 및 부정 텍스트 설명을 기반으로 비디오 시퀀스를 생성하며, 모델, 지속 시간, 화면 비율 및 생성 모드에 대한 구성 가능한 옵션을 제공합니다. @@ -27,7 +26,7 @@ Kling 이미지-투-비디오 노드는 시작 참조 이미지와 텍스트 프 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | 생성된 비디오 출력입니다. | VIDEO | -| `길이` | 생성된 비디오의 고유 식별자입니다. | STRING | +| `비디오 ID` | 생성된 비디오의 고유 식별자입니다. | STRING | | `길이` | 생성된 비디오의 지속 시간 정보입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImage2VideoNode/ko.md) diff --git a/ko/built-in-nodes/KlingImageGenerationNode.mdx b/ko/built-in-nodes/KlingImageGenerationNode.mdx index 11e698696..a2db82b9e 100644 --- a/ko/built-in-nodes/KlingImageGenerationNode.mdx +++ b/ko/built-in-nodes/KlingImageGenerationNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingImageGenerationNode" icon: "circle" mode: wide --- -# Kling 이미지 생성 노드 Kling 이미지 생성 노드는 텍스트 프롬프트로부터 이미지를 생성하며, 참조 이미지를 사용하여 가이드할 수 있는 옵션을 제공합니다. 텍스트 설명과 참조 설정을 기반으로 하나 이상의 이미지를 생성한 후, 생성된 이미지를 출력으로 반환합니다. diff --git a/ko/built-in-nodes/KlingImageToVideoWithAudio.mdx b/ko/built-in-nodes/KlingImageToVideoWithAudio.mdx index 1b98549a6..8684dabc8 100644 --- a/ko/built-in-nodes/KlingImageToVideoWithAudio.mdx +++ b/ko/built-in-nodes/KlingImageToVideoWithAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingImageToVideoWithAudio" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImageToVideoWithAudio/en.md) Kling Image(첫 번째 프레임) to Video with Audio 노드는 Kling AI 모델을 사용하여 단일 시작 이미지와 텍스트 프롬프트로 짧은 비디오를 생성합니다. 제공된 이미지로 시작하는 비디오 시퀀스를 만들며, 선택적으로 AI 생성 오디오를 시각 자료와 함께 포함할 수 있습니다. diff --git a/ko/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx b/ko/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx index 263a9737f..be8eeffd4 100644 --- a/ko/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx +++ b/ko/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingLipSyncAudioToVideoNode" icon: "circle" mode: wide --- -# Kling 립싱크 오디오-투-비디오 노드 Kling 립싱크 오디오-투-비디오 노드는 비디오 파일의 입 움직임을 오디오 파일의 음성 내용과 동기화합니다. 이 노드는 오디오의 음성 패턴을 분석하고 비디오의 얼굴 움직임을 조정하여 사실적인 립싱크를 생성합니다. 이 과정에는 뚜렷한 얼굴이 포함된 비디오와 명확하게 구분되는 음성이 포함된 오디오 파일이 모두 필요합니다. @@ -31,8 +30,8 @@ Kling 립싱크 오디오-투-비디오 노드는 비디오 파일의 입 움직 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | 립싱크된 입 움직임이 적용된 처리된 비디오 | VIDEO | -| `재생 시간` | 처리된 비디오의 고유 식별자 | STRING | -| `duration` | 처리된 비디오의 길이 | STRING | +| `비디오 ID` | 처리된 비디오의 고유 식별자 | STRING | +| `재생 시간` | 처리된 비디오의 길이 | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncAudioToVideoNode/ko.md) diff --git a/ko/built-in-nodes/KlingLipSyncTextToVideoNode.mdx b/ko/built-in-nodes/KlingLipSyncTextToVideoNode.mdx index c505d5740..585a0b63f 100644 --- a/ko/built-in-nodes/KlingLipSyncTextToVideoNode.mdx +++ b/ko/built-in-nodes/KlingLipSyncTextToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingLipSyncTextToVideoNode" icon: "circle" mode: wide --- -# Kling 립싱크 텍스트-투-비디오 노드 Kling 립 싱크 텍스트-투-비디오 노드는 비디오 파일의 입 움직임을 텍스트 프롬프트와 동기화합니다. 입력 비디오를 받아 캐릭터의 입술 움직임이 제공된 텍스트와 일치하는 새로운 비디오를 생성합니다. 이 노드는 음성 합성을 사용하여 자연스러운 발화 동기화를 구현합니다. @@ -29,8 +28,8 @@ Kling 립 싱크 텍스트-투-비디오 노드는 비디오 파일의 입 움 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | 립싱크 오디오가 적용된 생성된 비디오 | VIDEO | -| `길이` | 생성된 비디오의 고유 식별자 | STRING | -| `duration` | 생성된 비디오의 길이 정보 | STRING | +| `비디오 ID` | 생성된 비디오의 고유 식별자 | STRING | +| `길이` | 생성된 비디오의 길이 정보 | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncTextToVideoNode/ko.md) diff --git a/ko/built-in-nodes/KlingMotionControl.mdx b/ko/built-in-nodes/KlingMotionControl.mdx index 13ecb05b4..51beb3291 100644 --- a/ko/built-in-nodes/KlingMotionControl.mdx +++ b/ko/built-in-nodes/KlingMotionControl.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingMotionControl" icon: "circle" mode: wide --- + Kling Motion Control 노드는 참조 이미지와 텍스트 프롬프트로 정의된 캐릭터에 참조 비디오의 동작, 표정 및 카메라 움직임을 적용하여 비디오를 생성합니다. 캐릭터의 최종 방향을 참조 비디오에서 가져올지, 참조 이미지에서 가져올지 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/KlingOmniProEditVideoNode.mdx b/ko/built-in-nodes/KlingOmniProEditVideoNode.mdx index 0698d66eb..ac50594db 100644 --- a/ko/built-in-nodes/KlingOmniProEditVideoNode.mdx +++ b/ko/built-in-nodes/KlingOmniProEditVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProEditVideoNode" icon: "circle" mode: wide --- + Kling Omni Edit Video (Pro) 노드는 텍스트 설명을 기반으로 AI 모델을 사용하여 기존 비디오를 편집합니다. 소스 비디오와 프롬프트를 제공하면 노드가 요청된 변경 사항이 적용된 동일한 길이의 새 비디오를 생성합니다. 선택적으로 참조 이미지를 사용하여 스타일을 안내하고 소스 비디오의 원본 오디오를 유지할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx b/ko/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx index 51d68dea9..56588ee30 100644 --- a/ko/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx +++ b/ko/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProFirstLastFrameNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProFirstLastFrameNode/en.md) 이 노드는 최신 Kling AI 모델을 사용하여 시작 프레임, 선택적 종료 프레임 또는 참조 이미지로부터 비디오를 생성합니다. 단일 비디오 또는 각 세그먼트에 개별 프롬프트와 지속 시간을 적용한 멀티샷 스토리보드를 만들 수 있습니다. 이 노드는 이러한 입력을 처리하여 지정된 길이와 해상도의 비디오를 생성하며, 선택적으로 오디오를 생성할 수도 있습니다. diff --git a/ko/built-in-nodes/KlingOmniProImageNode.mdx b/ko/built-in-nodes/KlingOmniProImageNode.mdx index 5824a1503..90dd2ea4e 100644 --- a/ko/built-in-nodes/KlingOmniProImageNode.mdx +++ b/ko/built-in-nodes/KlingOmniProImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingOmniProImageNode" icon: "circle" mode: wide --- -# Kling Omni 이미지 (Pro) 노드 Kling Omni 이미지 (Pro) 노드는 최신 Kling AI 모델을 사용하여 이미지를 생성하거나 편집합니다. 텍스트 설명을 기반으로 이미지를 생성하며, 필요에 따라 참조 이미지를 사용하여 스타일이나 내용을 안내할 수 있습니다. 이 노드는 외부 API에 요청을 보내고, 해당 API가 작업을 처리한 후 최종 이미지를 반환합니다. diff --git a/ko/built-in-nodes/KlingOmniProImageToVideoNode.mdx b/ko/built-in-nodes/KlingOmniProImageToVideoNode.mdx index 907d0732d..889a9bc29 100644 --- a/ko/built-in-nodes/KlingOmniProImageToVideoNode.mdx +++ b/ko/built-in-nodes/KlingOmniProImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProImageToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProImageToVideoNode/en.md) 이 노드는 Kling AI 모델을 사용하여 텍스트 프롬프트와 최대 7개의 참조 이미지를 기반으로 비디오를 생성합니다. 비디오의 화면 비율, 길이, 해상도를 제어할 수 있으며, 선택적으로 스토리보드를 사용하거나 오디오를 생성할 수 있습니다. 이 노드는 외부 API에 요청을 전송하고 생성된 비디오를 반환합니다. diff --git a/ko/built-in-nodes/KlingOmniProTextToVideoNode.mdx b/ko/built-in-nodes/KlingOmniProTextToVideoNode.mdx index 0b22c8689..53486dcd8 100644 --- a/ko/built-in-nodes/KlingOmniProTextToVideoNode.mdx +++ b/ko/built-in-nodes/KlingOmniProTextToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingOmniProTextToVideoNode" icon: "circle" mode: wide --- -# 개요 이 노드는 최신 Kling AI 모델을 사용하여 텍스트 설명으로부터 비디오를 생성합니다. 사용자의 프롬프트를 원격 API로 전송하고 생성된 비디오를 반환합니다. 이 노드를 통해 비디오의 길이, 화면 비율, 품질을 제어할 수 있으며, 멀티 샷 스토리보드도 생성할 수 있습니다. diff --git a/ko/built-in-nodes/KlingOmniProVideoToVideoNode.mdx b/ko/built-in-nodes/KlingOmniProVideoToVideoNode.mdx index 2a3db240a..00b64644f 100644 --- a/ko/built-in-nodes/KlingOmniProVideoToVideoNode.mdx +++ b/ko/built-in-nodes/KlingOmniProVideoToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProVideoToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingOmniProVideoToVideoNode/en.md) 이 노드는 Kling AI 모델을 사용하여 입력 비디오와 선택적 참조 이미지를 기반으로 새로운 비디오를 생성합니다. 원하는 콘텐츠를 설명하는 텍스트 프롬프트를 제공하면 노드가 참조 비디오를 그에 맞게 변환합니다. 또한 최대 4개의 추가 참조 이미지를 통합하여 출력의 스타일과 콘텐츠를 안내할 수 있습니다. diff --git a/ko/built-in-nodes/KlingSingleImageVideoEffectNode.mdx b/ko/built-in-nodes/KlingSingleImageVideoEffectNode.mdx index 0e7882dea..a2bf72e56 100644 --- a/ko/built-in-nodes/KlingSingleImageVideoEffectNode.mdx +++ b/ko/built-in-nodes/KlingSingleImageVideoEffectNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingSingleImageVideoEffectNode" icon: "circle" mode: wide --- -# Kling 단일 이미지 비디오 효과 노드 Kling 단일 이미지 비디오 효과 노드는 단일 참조 이미지를 기반으로 다양한 특수 효과가 적용된 비디오를 생성합니다. 다양한 시각적 효과와 장면을 적용하여 정적 이미지를 동적 비디오 콘텐츠로 변환합니다. 이 노드는 다양한 효과 장면, 모델 옵션 및 비디오 길이를 지원하여 원하는 시각적 결과를 얻을 수 있습니다. @@ -25,7 +24,7 @@ Kling 단일 이미지 비디오 효과 노드는 단일 참조 이미지를 기 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | 효과가 적용된 생성된 비디오 | VIDEO | -| `길이` | 생성된 비디오의 고유 식별자 | STRING | +| `비디오 ID` | 생성된 비디오의 고유 식별자 | STRING | | `길이` | 생성된 비디오의 길이 | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingSingleImageVideoEffectNode/ko.md) diff --git a/ko/built-in-nodes/KlingStartEndFrameNode.mdx b/ko/built-in-nodes/KlingStartEndFrameNode.mdx index c4bea8a24..45b9bac2c 100644 --- a/ko/built-in-nodes/KlingStartEndFrameNode.mdx +++ b/ko/built-in-nodes/KlingStartEndFrameNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingStartEndFrameNode" icon: "circle" mode: wide --- -# Kling 시작-종료 프레임 비디오 노드 Kling 시작-종료 프레임 비디오 노드는 제공된 시작 이미지와 종료 이미지 사이를 전환하는 비디오 시퀀스를 생성합니다. 첫 번째 프레임에서 마지막 프레임까지 부드러운 변환을 위해 중간의 모든 프레임을 생성합니다. 이 노드는 이미지-투-비디오 API를 호출하지만 `image_tail` 요청 필드와 함께 작동하는 입력 옵션만 지원합니다. @@ -33,8 +32,8 @@ Kling 시작-종료 프레임 비디오 노드는 제공된 시작 이미지와 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | 생성된 비디오 시퀀스 | VIDEO | -| `길이` | 생성된 비디오의 고유 식별자 | STRING | -| `duration` | 생성된 비디오의 재생 시간 | STRING | +| `비디오 ID` | 생성된 비디오의 고유 식별자 | STRING | +| `길이` | 생성된 비디오의 재생 시간 | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingStartEndFrameNode/ko.md) diff --git a/ko/built-in-nodes/KlingTextToVideoNode.mdx b/ko/built-in-nodes/KlingTextToVideoNode.mdx index c09ae1126..74eb12ea7 100644 --- a/ko/built-in-nodes/KlingTextToVideoNode.mdx +++ b/ko/built-in-nodes/KlingTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingTextToVideoNode" icon: "circle" mode: wide --- + ## 개요 Kling 텍스트-비디오 노드는 텍스트 설명을 비디오 콘텐츠로 변환합니다. 텍스트 프롬프트를 입력받아 지정된 구성 설정에 따라 해당하는 비디오 시퀀스를 생성합니다. 이 노드는 다양한 화면 비율과 생성 모드를 지원하여 서로 다른 길이와 품질의 비디오를 제작할 수 있습니다. @@ -24,8 +25,8 @@ Kling 텍스트-비디오 노드는 텍스트 설명을 비디오 콘텐츠로 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | 생성된 비디오 출력 | VIDEO | -| `길이` | 생성된 비디오의 고유 식별자 | STRING | -| `duration` | 생성된 비디오의 지속 시간 정보 | STRING | +| `비디오 ID` | 생성된 비디오의 고유 식별자 | STRING | +| `길이` | 생성된 비디오의 지속 시간 정보 | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoNode/ko.md) diff --git a/ko/built-in-nodes/KlingTextToVideoWithAudio.mdx b/ko/built-in-nodes/KlingTextToVideoWithAudio.mdx index 4c9b80e84..52436385d 100644 --- a/ko/built-in-nodes/KlingTextToVideoWithAudio.mdx +++ b/ko/built-in-nodes/KlingTextToVideoWithAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingTextToVideoWithAudio" icon: "circle" mode: wide --- + 다음은 제공된 영어 문서를 번역 규칙에 따라 한국어로 번역한 결과입니다. --- diff --git a/ko/built-in-nodes/KlingVideoExtendNode.mdx b/ko/built-in-nodes/KlingVideoExtendNode.mdx index 53365c794..0322606af 100644 --- a/ko/built-in-nodes/KlingVideoExtendNode.mdx +++ b/ko/built-in-nodes/KlingVideoExtendNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingVideoExtendNode" icon: "circle" mode: wide --- -# Kling 비디오 확장 노드 Kling 비디오 확장 노드는 다른 Kling 노드에서 생성된 비디오를 확장할 수 있게 해줍니다. 비디오 ID로 식별되는 기존 비디오를 가져와 텍스트 프롬프트를 기반으로 추가 콘텐츠를 생성합니다. 이 노드는 확장 요청을 Kling API로 전송하고, 확장된 비디오와 함께 새로운 ID 및 재생 시간을 반환하는 방식으로 작동합니다. @@ -25,8 +24,8 @@ Kling 비디오 확장 노드는 다른 Kling 노드에서 생성된 비디오 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `비디오 ID` | Kling API에 의해 생성된 확장된 비디오 | VIDEO | -| `길이` | 확장된 비디오의 고유 식별자 | STRING | -| `duration` | 확장된 비디오의 재생 시간 | STRING | +| `비디오 ID` | 확장된 비디오의 고유 식별자 | STRING | +| `길이` | 확장된 비디오의 재생 시간 | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoExtendNode/ko.md) diff --git a/ko/built-in-nodes/KlingVideoNode.mdx b/ko/built-in-nodes/KlingVideoNode.mdx index 419ccb793..78dee4bf4 100644 --- a/ko/built-in-nodes/KlingVideoNode.mdx +++ b/ko/built-in-nodes/KlingVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoNode/en.md) 이 노드는 Kling V3 모델을 사용하여 비디오를 생성합니다. 텍스트 설명으로 비디오를 만드는 텍스트-비디오 모드와 기존 이미지에 애니메이션을 적용하는 이미지-비디오 모드, 두 가지 주요 모드를 지원합니다. 또한 각 부분에 대해 서로 다른 프롬프트를 사용하여 여러 세그먼트로 구성된 비디오(스토리보드)를 만들고 선택적으로 오디오를 생성하는 고급 기능도 제공합니다. diff --git a/ko/built-in-nodes/KlingVirtualTryOnNode.mdx b/ko/built-in-nodes/KlingVirtualTryOnNode.mdx index a757206c6..9258878e1 100644 --- a/ko/built-in-nodes/KlingVirtualTryOnNode.mdx +++ b/ko/built-in-nodes/KlingVirtualTryOnNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingVirtualTryOnNode" icon: "circle" mode: wide --- -# Kling 가상 피팅 노드 인물 이미지와 의류 이미지를 입력하여 인물에게 해당 의류를 입혀 보는 기능을 제공합니다. 여러 개의 의류 항목 이미지를 흰색 배경의 하나의 이미지로 병합할 수 있습니다. diff --git a/ko/built-in-nodes/Krea2ImageNode.mdx b/ko/built-in-nodes/Krea2ImageNode.mdx index d882db90c..6e711e201 100644 --- a/ko/built-in-nodes/Krea2ImageNode.mdx +++ b/ko/built-in-nodes/Krea2ImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Krea2ImageNode" icon: "circle" mode: wide --- -# 개요 Krea 2 이미지 노드는 Krea 2 AI 모델을 사용하여 이미지를 생성합니다. 표현력이 풍부한 일러스트레이션에 적합한 Medium과 표현력이 풍부한 포토리얼리즘에 적합한 Large의 두 가지 모델 변형을 지원합니다. 선택적으로 무드보드와 최대 10개의 이미지 스타일 참조를 포함하여 생성된 이미지에 영향을 줄 수 있습니다. diff --git a/ko/built-in-nodes/Krea2StyleReferenceNode.mdx b/ko/built-in-nodes/Krea2StyleReferenceNode.mdx index a2c73227a..6e3476b29 100644 --- a/ko/built-in-nodes/Krea2StyleReferenceNode.mdx +++ b/ko/built-in-nodes/Krea2StyleReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Krea2StyleReferenceNode" icon: "circle" mode: wide --- + 다음은 요청하신 번역 결과입니다. --- diff --git a/ko/built-in-nodes/LTXAVTextEncoderLoader.mdx b/ko/built-in-nodes/LTXAVTextEncoderLoader.mdx index 2d936a93c..ebe4783db 100644 --- a/ko/built-in-nodes/LTXAVTextEncoderLoader.mdx +++ b/ko/built-in-nodes/LTXAVTextEncoderLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXAVTextEncoderLoader" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXAVTextEncoderLoader/en.md) 이 노드는 LTXV 오디오 모델용 특수 텍스트 인코더를 로드합니다. 특정 텍스트 인코더 파일과 체크포인트 파일을 결합하여 오디오 관련 텍스트 조건화 작업에 사용할 수 있는 CLIP 모델을 생성합니다. diff --git a/ko/built-in-nodes/LTXVAddGuide.mdx b/ko/built-in-nodes/LTXVAddGuide.mdx index 83e88c2ba..fdbfedf41 100644 --- a/ko/built-in-nodes/LTXVAddGuide.mdx +++ b/ko/built-in-nodes/LTXVAddGuide.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LTXVAddGuide" icon: "circle" mode: wide --- -# LTXVAddGuide 노드 LTXVAddGuide 노드는 입력 이미지나 비디오를 VAE 인코더로 처리하여 잠재 시퀀스에 비디오 컨디셔닝 가이던스를 추가하고, 이를 키프레임으로 컨디셔닝 데이터에 통합합니다. 이 노드는 VAE 인코더를 통해 입력을 처리하고, 결과로 생성된 잠재값을 지정된 프레임 위치에 전략적으로 배치하며, 키프레임 정보로 긍정 및 부정 컨디셔닝을 모두 업데이트합니다. 또한 프레임 정렬 제약 조건을 처리하고 컨디셔닝 영향의 강도를 제어할 수 있습니다. @@ -27,8 +26,8 @@ LTXVAddGuide 노드는 입력 이미지나 비디오를 VAE 인코더로 처리 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 키프레임 가이던스 정보로 업데이트된 긍정 컨디셔닝 | CONDITIONING | -| `잠재 비디오` | 키프레임 가이던스 정보로 업데이트된 부정 컨디셔닝 | CONDITIONING | +| `긍정 조건` | 키프레임 가이던스 정보로 업데이트된 긍정 컨디셔닝 | CONDITIONING | +| `부정 조건` | 키프레임 가이던스 정보로 업데이트된 부정 컨디셔닝 | CONDITIONING | | `잠재 비디오` | 컨디셔닝 프레임과 업데이트된 노이즈 마스크가 통합된 잠재 시퀀스 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAddGuide/ko.md) diff --git a/ko/built-in-nodes/LTXVAudioVAEDecode.mdx b/ko/built-in-nodes/LTXVAudioVAEDecode.mdx index 2cd79b1e7..630aa0ca9 100644 --- a/ko/built-in-nodes/LTXVAudioVAEDecode.mdx +++ b/ko/built-in-nodes/LTXVAudioVAEDecode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAEDecode" icon: "circle" mode: wide --- + LTXV 오디오 VAE 디코드 노드는 오디오의 잠재 표현을 다시 오디오 파형으로 변환합니다. 이 노드는 특수 오디오 VAE 모델을 사용하여 디코딩 과정을 수행하며, 특정 샘플 레이트를 가진 오디오 출력을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/LTXVAudioVAEEncode.mdx b/ko/built-in-nodes/LTXVAudioVAEEncode.mdx index 9a4fcec37..68055d3aa 100644 --- a/ko/built-in-nodes/LTXVAudioVAEEncode.mdx +++ b/ko/built-in-nodes/LTXVAudioVAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAEEncode" icon: "circle" mode: wide --- + LTXV 오디오 VAE 인코딩 노드는 오디오 입력을 받아 지정된 오디오 VAE 모델을 사용하여 더 작은 잠재 표현으로 압축합니다. 이 프로세스는 원시 오디오 데이터를 파이프라인의 다른 노드가 이해하고 처리할 수 있는 형식으로 변환하므로, 잠재 공간 워크플로우 내에서 오디오를 생성하거나 조작하는 데 필수적입니다. ## 입력 diff --git a/ko/built-in-nodes/LTXVAudioVAELoader.mdx b/ko/built-in-nodes/LTXVAudioVAELoader.mdx index 26db61cc5..359168c1d 100644 --- a/ko/built-in-nodes/LTXVAudioVAELoader.mdx +++ b/ko/built-in-nodes/LTXVAudioVAELoader.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LTXVAudioVAELoader" icon: "circle" mode: wide --- -# LTXV 오디오 VAE 로더 LTXV 오디오 VAE 로더 노드는 사전 훈련된 오디오 변분 오토인코더(VAE) 모델을 체크포인트 파일에서 불러옵니다. 지정된 체크포인트를 읽고, 가중치와 메타데이터를 로드한 후, ComfyUI 내에서 오디오 생성 또는 처리 워크플로우에 사용할 수 있도록 모델을 준비합니다. diff --git a/ko/built-in-nodes/LTXVConcatAVLatent.mdx b/ko/built-in-nodes/LTXVConcatAVLatent.mdx index c89e916f9..4dcf22969 100644 --- a/ko/built-in-nodes/LTXVConcatAVLatent.mdx +++ b/ko/built-in-nodes/LTXVConcatAVLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVConcatAVLatent" icon: "circle" mode: wide --- + LTXVConcatAVLatent 노드는 비디오 잠재 표현과 오디오 잠재 표현을 하나의 결합된 잠재 출력으로 결합합니다. 두 입력의 `samples` 텐서를 병합하고, `noise_mask` 텐서가 있는 경우 함께 병합하여 비디오 생성 파이프라인에서 추가 처리를 준비합니다. ## 입력 diff --git a/ko/built-in-nodes/LTXVConditioning.mdx b/ko/built-in-nodes/LTXVConditioning.mdx index 9a28ced88..be75fc260 100644 --- a/ko/built-in-nodes/LTXVConditioning.mdx +++ b/ko/built-in-nodes/LTXVConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVConditioning" icon: "circle" mode: wide --- + LTXVConditioning 노드는 비디오 생성 모델을 위해 양성 및 음성 조건화 입력에 프레임 속도 정보를 추가합니다. 기존 조건화 데이터를 가져와 지정된 프레임 속도 값을 두 조건화 세트에 적용하여 비디오 모델 처리에 적합하도록 만듭니다. ## 입력 @@ -19,7 +20,7 @@ LTXVConditioning 노드는 비디오 생성 모델을 위해 양성 및 음성 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 프레임 속도 정보가 적용된 양성 조건화입니다 | CONDITIONING | +| `긍정 조건` | 프레임 속도 정보가 적용된 양성 조건화입니다 | CONDITIONING | | `부정 조건` | 프레임 속도 정보가 적용된 음성 조건화입니다 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVConditioning/ko.md) diff --git a/ko/built-in-nodes/LTXVContextWindows.mdx b/ko/built-in-nodes/LTXVContextWindows.mdx new file mode 100644 index 000000000..a1c9f6e5e --- /dev/null +++ b/ko/built-in-nodes/LTXVContextWindows.mdx @@ -0,0 +1,37 @@ +--- +title: "LTXVContextWindows - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LTXVContextWindows node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LTXVContextWindows" +icon: "circle" +mode: wide +--- + +이 노드는 샘플링 중 LTXV 유사 모델에 컨텍스트 윈도우를 설정합니다. 비디오 생성 과정을 겹치는 윈도우로 분할하여 메모리 사용량을 관리하고 시간적 일관성을 개선합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `model` | 샘플링 중 컨텍스트 윈도우를 적용할 모델입니다. | MODEL | 예 | - | +| `context_length` | 실제 프레임 기준 컨텍스트 윈도우의 길이입니다. 8*n + 1이어야 합니다. (기본값: 145) | INT | 예 | 최소: 1
최대: nodes.MAX_RESOLUTION
단계: 8 | +| `context_overlap` | 실제 프레임 기준 컨텍스트 윈도우의 중첩입니다. (기본값: 40) | INT | 예 | 최소: 0
단계: 8 | +| `context_schedule` | 컨텍스트 윈도우에 대한 단계 종속 스케줄링 알고리즘입니다. (기본값: UNIFORM_STANDARD) | COMBO | 예 | `STATIC_STANDARD`
`UNIFORM_STANDARD`
`UNIFORM_LOOPED`
`BATCHED` | +| `context_stride` | 컨텍스트 윈도우의 보폭입니다. 균일 스케줄에만 적용됩니다. (기본값: 1) | INT | 아니요 | 최소: 1 | +| `closed_loop` | 컨텍스트 윈도우 루프를 닫을지 여부입니다. 루프 스케줄에만 적용됩니다. (기본값: False) | BOOLEAN | 아니요 | True
False | +| `fuse_method` | 컨텍스트 윈도우를 융합하는 데 사용할 방법입니다. (기본값: PYRAMID) | COMBO | 예 | comfy.context_windows.ContextFuseMethods.LIST_STATIC의 옵션 | +| `freenoise` | FreeNoise 노이즈 셔플링을 적용할지 여부입니다. 윈도우 혼합을 개선합니다. (기본값: True) | BOOLEAN | 아니요 | True
False | +| `retain_first_frame` | 모든 컨텍스트 윈도우에서 첫 번째 잠재 프레임을 유지합니다. (초기 참조 유지에 도움이 될 수 있습니다.) (기본값: False) | BOOLEAN | 아니요 | True
False | +| `split_conds_to_windows` | ConditionCombine으로 생성된 여러 컨디셔닝을 영역 인덱스에 따라 각 윈도우로 분할할지 여부입니다. (기본값: False) | BOOLEAN | 아니요 | True
False | + +**참고:** `context_length` 매개변수는 8*n + 1 공식을 따라야 하며, 여기서 n은 양의 정수입니다. 노드는 실제 프레임을 잠재 프레임으로 변환하여 이 요구 사항을 충족하도록 값을 자동으로 조정합니다. `context_overlap`도 실제 프레임에서 잠재 프레임으로 변환됩니다(8로 나누기). + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `MODEL` | 샘플링을 위해 컨텍스트 윈도우가 적용된 모델입니다. | MODEL | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVContextWindows/ko.md) + +--- +**Source fingerprint (SHA-256):** `ad0b8c54acaab1853f6fe98dbad675478f033caf867df954b40b7db5208f5ae4` diff --git a/ko/built-in-nodes/LTXVCropGuides.mdx b/ko/built-in-nodes/LTXVCropGuides.mdx index 2384c7025..4268b9bd1 100644 --- a/ko/built-in-nodes/LTXVCropGuides.mdx +++ b/ko/built-in-nodes/LTXVCropGuides.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVCropGuides" icon: "circle" mode: wide --- + LTXVCropGuides 노드는 키프레임 정보를 제거하고 잠재 차원을 조정하여 비디오 생성을 위한 컨디셔닝 및 잠재 입력을 처리합니다. 잠재 이미지와 노이즈 마스크를 잘라내어 키프레임 섹션을 제외시키고, 양성 및 음성 컨디셔닝 입력 모두에서 키프레임 인덱스를 제거합니다. 이를 통해 키프레임 가이드가 필요 없는 비디오 생성 워크플로우를 위한 데이터를 준비합니다. ## 입력 @@ -19,8 +20,8 @@ LTXVCropGuides 노드는 키프레임 정보를 제거하고 잠재 차원을 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 키프레임 인덱스와 가이드 어텐션 항목이 제거된 처리된 양성 컨디셔닝 | CONDITIONING | -| `잠재 비디오` | 키프레임 인덱스와 가이드 어텐션 항목이 제거된 처리된 음성 컨디셔닝 | CONDITIONING | +| `긍정 조건` | 키프레임 인덱스와 가이드 어텐션 항목이 제거된 처리된 양성 컨디셔닝 | CONDITIONING | +| `부정 조건` | 키프레임 인덱스와 가이드 어텐션 항목이 제거된 처리된 음성 컨디셔닝 | CONDITIONING | | `잠재 비디오` | 키프레임 섹션이 제거되고 샘플과 노이즈 마스크가 조정된 잘라낸 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVCropGuides/ko.md) diff --git a/ko/built-in-nodes/LTXVEmptyLatentAudio.mdx b/ko/built-in-nodes/LTXVEmptyLatentAudio.mdx index 361f707ce..e05a54ab6 100644 --- a/ko/built-in-nodes/LTXVEmptyLatentAudio.mdx +++ b/ko/built-in-nodes/LTXVEmptyLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVEmptyLatentAudio" icon: "circle" mode: wide --- + LTXV 빈 잠재 오디오 노드는 빈(0으로 채워진) 잠재 오디오 텐서 배치를 생성합니다. 제공된 오디오 VAE 모델의 구성을 사용하여 채널 수 및 주파수 빈과 같은 잠재 공간의 올바른 차원을 결정합니다. 이 빈 잠재 텐서는 ComfyUI 내에서 오디오 생성 또는 조작 워크플로의 시작점 역할을 합니다. ## 입력 diff --git a/ko/built-in-nodes/LTXVImgToVideo.mdx b/ko/built-in-nodes/LTXVImgToVideo.mdx index 9898eaea8..e7e642e9e 100644 --- a/ko/built-in-nodes/LTXVImgToVideo.mdx +++ b/ko/built-in-nodes/LTXVImgToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVImgToVideo" icon: "circle" mode: wide --- + LTXVImgToVideo 노드는 입력 이미지를 비디오 생성 모델을 위한 비디오 잠재 표현으로 변환합니다. 단일 이미지를 가져와 VAE 인코더를 사용하여 프레임 시퀀스로 확장한 후, 강도 제어를 통해 조건화를 적용하여 비디오 생성 중 원본 이미지 콘텐츠가 보존되거나 수정되는 정도를 결정합니다. ## 입력 @@ -25,9 +26,9 @@ LTXVImgToVideo 노드는 입력 이미지를 비디오 생성 모델을 위한 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 비디오 프레임 마스킹이 적용된 처리된 긍정 조건화 | CONDITIONING | -| `잠재 데이터` | 비디오 프레임 마스킹이 적용된 처리된 부정 조건화 | CONDITIONING | -| `latent` | 비디오 생성을 위한 인코딩된 프레임과 노이즈 마스크를 포함하는 비디오 잠재 표현 | LATENT | +| `긍정 조건` | 비디오 프레임 마스킹이 적용된 처리된 긍정 조건화 | CONDITIONING | +| `부정 조건` | 비디오 프레임 마스킹이 적용된 처리된 부정 조건화 | CONDITIONING | +| `잠재 데이터` | 비디오 생성을 위한 인코딩된 프레임과 노이즈 마스크를 포함하는 비디오 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVImgToVideo/ko.md) diff --git a/ko/built-in-nodes/LTXVImgToVideoInplace.mdx b/ko/built-in-nodes/LTXVImgToVideoInplace.mdx index dc3412eff..f7d13d281 100644 --- a/ko/built-in-nodes/LTXVImgToVideoInplace.mdx +++ b/ko/built-in-nodes/LTXVImgToVideoInplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVImgToVideoInplace" icon: "circle" mode: wide --- + LTXVImgToVideoInplace 노드는 입력 이미지를 초기 프레임으로 인코딩하여 비디오 잠재 표현을 조건화합니다. VAE를 사용하여 이미지를 잠재 공간으로 인코딩한 후, 지정된 강도에 따라 기존 잠재 샘플과 혼합하는 방식으로 작동합니다. 이를 통해 이미지를 비디오 생성을 위한 시작점 또는 조건화 신호로 사용할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LTXVLatentUpsampler.mdx b/ko/built-in-nodes/LTXVLatentUpsampler.mdx index f7558581a..27f04a252 100644 --- a/ko/built-in-nodes/LTXVLatentUpsampler.mdx +++ b/ko/built-in-nodes/LTXVLatentUpsampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVLatentUpsampler" icon: "circle" mode: wide --- + LTXVLatentUpsampler 노드는 비디오 잠재 표현의 공간 해상도를 2배로 증가시킵니다. 이 노드는 특화된 업스케일 모델을 사용하여 잠재 데이터를 처리하며, 제공된 VAE의 채널 통계를 사용하여 먼저 정규화를 해제한 후 다시 정규화합니다. 이 노드는 잠재 공간 내에서의 비디오 워크플로우를 위해 설계되었습니다. ## 입력 diff --git a/ko/built-in-nodes/LTXVPreprocess.mdx b/ko/built-in-nodes/LTXVPreprocess.mdx index 8ad4e9eea..6cec6eae0 100644 --- a/ko/built-in-nodes/LTXVPreprocess.mdx +++ b/ko/built-in-nodes/LTXVPreprocess.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVPreprocess" icon: "circle" mode: wide --- + LTXVPreprocess 노드는 이미지에 압축 전처리를 적용합니다. 입력 이미지를 지정된 압축 수준으로 처리한 후, 적용된 압축 설정이 반영된 처리된 이미지를 출력합니다. ## 입력 @@ -18,7 +19,7 @@ LTXVPreprocess 노드는 이미지에 압축 전처리를 적용합니다. 입 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `output_image` | 압축이 적용된 처리된 출력 이미지 | IMAGE | +| `출력 이미지` | 압축이 적용된 처리된 출력 이미지 | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVPreprocess/ko.md) diff --git a/ko/built-in-nodes/LTXVReferenceAudio.mdx b/ko/built-in-nodes/LTXVReferenceAudio.mdx index cc01c787f..bb36bee1f 100644 --- a/ko/built-in-nodes/LTXVReferenceAudio.mdx +++ b/ko/built-in-nodes/LTXVReferenceAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVReferenceAudio" icon: "circle" mode: wide --- + LTXV 참조 오디오 노드는 오디오 생성에서 화자 정체성 전달을 위해 사용됩니다. 참조 오디오 클립을 모델의 컨디셔닝으로 인코딩하여, 생성된 오디오가 화자의 음성 특성을 채택할 수 있도록 합니다. 또한 정체성 가이던스를 적용할 수 있으며, 이는 추가 처리 단계를 실행하여 화자 정체성 효과를 증폭시킵니다. ## 입력 @@ -25,7 +26,7 @@ LTXV 참조 오디오 노드는 오디오 생성에서 화자 정체성 전달 | 출력 이름 | 설명 | 데이터 유형 | | --- | --- | --- | | `positive` | 정체성 가이던스 함수로 패치된 모델입니다. | MODEL | -| `negative` | 인코딩된 참조 오디오 데이터를 포함하는 포지티브 컨디셔닝입니다. | CONDITIONING | +| `positive` | 인코딩된 참조 오디오 데이터를 포함하는 포지티브 컨디셔닝입니다. | CONDITIONING | | `negative` | 인코딩된 참조 오디오 데이터를 포함하는 네거티브 컨디셔닝입니다. | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVReferenceAudio/ko.md) diff --git a/ko/built-in-nodes/LTXVScheduler.mdx b/ko/built-in-nodes/LTXVScheduler.mdx index 9ddb000a5..837e377cc 100644 --- a/ko/built-in-nodes/LTXVScheduler.mdx +++ b/ko/built-in-nodes/LTXVScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVScheduler" icon: "circle" mode: wide --- + LTXVScheduler 노드는 커스텀 샘플링 프로세스를 위한 시그마 값을 생성합니다. 입력 잠재 변수의 토큰 수를 기반으로 노이즈 스케줄 매개변수를 계산하고 시그모이드 변환을 적용하여 샘플링 스케줄을 생성합니다. 이 노드는 선택적으로 결과 시그마를 지정된 종료 값에 맞게 늘릴 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LTXVSeparateAVLatent.mdx b/ko/built-in-nodes/LTXVSeparateAVLatent.mdx index 78ccca5d3..75952a17e 100644 --- a/ko/built-in-nodes/LTXVSeparateAVLatent.mdx +++ b/ko/built-in-nodes/LTXVSeparateAVLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVSeparateAVLatent" icon: "circle" mode: wide --- + LTXVSeparateAVLatent 노드는 결합된 오디오-비디오 잠재 표현을 입력받아 비디오용과 오디오용의 두 개의 개별 부분으로 분할합니다. 입력 잠재 표현에서 샘플과 노이즈 마스크(있는 경우)를 분리하여 두 개의 새로운 잠재 객체를 생성합니다. ## 입력 @@ -19,7 +20,7 @@ LTXVSeparateAVLatent 노드는 결합된 오디오-비디오 잠재 표현을 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `audio_latent` | 분할된 비디오 데이터를 포함하는 잠재 표현입니다. | LATENT | +| `video_latent` | 분할된 비디오 데이터를 포함하는 잠재 표현입니다. | LATENT | | `audio_latent` | 분할된 오디오 데이터를 포함하는 잠재 표현입니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVSeparateAVLatent/ko.md) diff --git a/ko/built-in-nodes/LaplaceScheduler.mdx b/ko/built-in-nodes/LaplaceScheduler.mdx index 31a07321d..328ef01e2 100644 --- a/ko/built-in-nodes/LaplaceScheduler.mdx +++ b/ko/built-in-nodes/LaplaceScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LaplaceScheduler" icon: "circle" mode: wide --- + LaplaceScheduler 노드는 확산 샘플링에 사용하기 위해 라플라스 분포를 따르는 시그마 값 시퀀스를 생성합니다. 최대값에서 최소값으로 점차 감소하는 노이즈 레벨 스케줄을 생성하며, 라플라스 분포 매개변수를 사용하여 진행을 제어합니다. 이 스케줄러는 확산 모델의 노이즈 스케줄을 정의하기 위해 사용자 정의 샘플링 워크플로우에서 일반적으로 사용됩니다. ## 입력 diff --git a/ko/built-in-nodes/LatentAdd.mdx b/ko/built-in-nodes/LatentAdd.mdx index 762326db4..4d6290a4a 100644 --- a/ko/built-in-nodes/LatentAdd.mdx +++ b/ko/built-in-nodes/LatentAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentAdd" icon: "circle" mode: wide --- + LatentAdd 노드는 두 개의 잠재 표현을 더하기 위해 설계되었습니다. 이 노드는 요소별 덧셈을 수행하여 이러한 표현에 인코딩된 특징이나 특성을 결합합니다. ## 입력 diff --git a/ko/built-in-nodes/LatentApplyOperation.mdx b/ko/built-in-nodes/LatentApplyOperation.mdx index 5f8b99f42..05ac24416 100644 --- a/ko/built-in-nodes/LatentApplyOperation.mdx +++ b/ko/built-in-nodes/LatentApplyOperation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentApplyOperation" icon: "circle" mode: wide --- + LatentApplyOperation 노드는 잠재 샘플에 지정된 연산을 적용합니다. 이 노드는 잠재 데이터와 연산을 입력으로 받아 제공된 연산을 사용하여 잠재 샘플을 처리하고 수정된 잠재 데이터를 반환합니다. 이 노드를 사용하면 워크플로우에서 잠재 표현을 변환하거나 조작할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LatentApplyOperationCFG.mdx b/ko/built-in-nodes/LatentApplyOperationCFG.mdx index 2d531bc9e..c10e00941 100644 --- a/ko/built-in-nodes/LatentApplyOperationCFG.mdx +++ b/ko/built-in-nodes/LatentApplyOperationCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentApplyOperationCFG" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentApplyOperationCFG/en.md) LatentApplyOperationCFG 노드는 잠재 연산을 적용하여 모델의 조건화 유도 과정을 수정합니다. 이 노드는 분류기-자유 유도(CFG) 샘플링 과정 중 조건화 출력을 가로채고, 지정된 연산을 잠재 표현에 적용한 후 생성에 사용되도록 합니다. diff --git a/ko/built-in-nodes/LatentBatch.mdx b/ko/built-in-nodes/LatentBatch.mdx index 6c107fc5e..6523d4e24 100644 --- a/ko/built-in-nodes/LatentBatch.mdx +++ b/ko/built-in-nodes/LatentBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBatch" icon: "circle" mode: wide --- + LatentBatch 노드는 두 개의 잠재 샘플 세트를 단일 배치로 병합하며, 필요에 따라 한 세트의 크기를 다른 세트의 차원에 맞게 조정한 후 연결합니다. 이 작업은 서로 다른 잠재 표현을 결합하여 추가 처리 또는 생성 작업을 수행할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/LatentBatchSeedBehavior.mdx b/ko/built-in-nodes/LatentBatchSeedBehavior.mdx index 2bbe0f059..1a69f5189 100644 --- a/ko/built-in-nodes/LatentBatchSeedBehavior.mdx +++ b/ko/built-in-nodes/LatentBatchSeedBehavior.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBatchSeedBehavior" icon: "circle" mode: wide --- + `LatentBatchSeedBehavior` 노드는 잠재 샘플 배치의 시드 동작을 수정하도록 설계되었습니다. 배치 전체에 걸쳐 시드를 무작위화하거나 고정하여, 생성된 출력물에 다양성을 도입하거나 일관성을 유지함으로써 생성 과정에 영향을 줍니다. ## 입력 diff --git a/ko/built-in-nodes/LatentBlend.mdx b/ko/built-in-nodes/LatentBlend.mdx index c7afe2065..749da4b9d 100644 --- a/ko/built-in-nodes/LatentBlend.mdx +++ b/ko/built-in-nodes/LatentBlend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBlend" icon: "circle" mode: wide --- + LatentBlend 노드는 두 개의 잠재 샘플을 지정된 혼합 비율로 결합합니다. 두 개의 잠재 입력을 받아 첫 번째 샘플에는 혼합 비율을, 두 번째 샘플에는 역비율을 적용하여 새로운 출력을 생성합니다. 입력 샘플의 형태가 다른 경우, 두 번째 샘플이 첫 번째 샘플의 크기에 맞게 자동으로 조정됩니다. ## 입력 diff --git a/ko/built-in-nodes/LatentComposite.mdx b/ko/built-in-nodes/LatentComposite.mdx index 0f39fe5d3..009956c14 100644 --- a/ko/built-in-nodes/LatentComposite.mdx +++ b/ko/built-in-nodes/LatentComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentComposite" icon: "circle" mode: wide --- + LatentComposite 노드는 두 개의 잠재 표현을 하나의 출력으로 혼합하거나 병합하도록 설계되었습니다. 이 프로세스는 입력 잠재의 특성을 제어된 방식으로 결합하여 합성 이미지나 특징을 만드는 데 필수적입니다. ## 입력 diff --git a/ko/built-in-nodes/LatentCompositeMasked.mdx b/ko/built-in-nodes/LatentCompositeMasked.mdx index 5c1cfcfc6..6ac1e8257 100644 --- a/ko/built-in-nodes/LatentCompositeMasked.mdx +++ b/ko/built-in-nodes/LatentCompositeMasked.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCompositeMasked" icon: "circle" mode: wide --- + LatentCompositeMasked 노드는 두 개의 잠재 표현을 지정된 좌표에서 혼합하고, 선택적으로 마스크를 사용하여 보다 정밀한 합성을 수행하도록 설계되었습니다. 이 노드를 사용하면 한 이미지의 일부를 다른 이미지 위에 겹쳐 복잡한 잠재 이미지를 생성할 수 있으며, 소스 이미지 크기를 조정하여 완벽하게 맞출 수도 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LatentConcat.mdx b/ko/built-in-nodes/LatentConcat.mdx index f4ab815de..38693e6d8 100644 --- a/ko/built-in-nodes/LatentConcat.mdx +++ b/ko/built-in-nodes/LatentConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentConcat" icon: "circle" mode: wide --- + LatentConcat 노드는 선택한 차원을 따라 두 개의 잠재 샘플을 결합합니다. 두 개의 잠재 입력을 받아 x, y 또는 t 축을 따라 연결하며, 어떤 샘플이 먼저 올지 제어할 수 있는 옵션을 제공합니다. 이 노드는 연결을 수행하기 전에 두 번째 입력의 배치 크기를 첫 번째 입력과 일치하도록 자동으로 조정합니다. ## 입력 diff --git a/ko/built-in-nodes/LatentCrop.mdx b/ko/built-in-nodes/LatentCrop.mdx index dc8ed74c7..0b2c87d6a 100644 --- a/ko/built-in-nodes/LatentCrop.mdx +++ b/ko/built-in-nodes/LatentCrop.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCrop" icon: "circle" mode: wide --- + LatentCrop 노드는 이미지의 잠재 표현에 대한 자르기 작업을 수행하도록 설계되었습니다. 자르기 영역의 크기와 위치를 지정하여 잠재 공간을 대상으로 수정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LatentCut.mdx b/ko/built-in-nodes/LatentCut.mdx index fbecfe27a..6551c3117 100644 --- a/ko/built-in-nodes/LatentCut.mdx +++ b/ko/built-in-nodes/LatentCut.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LatentCut" icon: "circle" mode: wide --- -# LatentCut 노드 LatentCut 노드는 잠재 샘플에서 선택한 차원을 따라 특정 구간을 추출합니다. 차원(x, y 또는 t), 시작 위치 및 추출할 양을 지정하여 잠재 표현의 일부를 잘라낼 수 있습니다. 이 노드는 양수 및 음수 인덱싱을 모두 지원하며, 추출량을 사용 가능한 범위 내에 자동으로 조정합니다. diff --git a/ko/built-in-nodes/LatentCutToBatch.mdx b/ko/built-in-nodes/LatentCutToBatch.mdx index 37d266a87..8af2d686e 100644 --- a/ko/built-in-nodes/LatentCutToBatch.mdx +++ b/ko/built-in-nodes/LatentCutToBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCutToBatch" icon: "circle" mode: wide --- + LatentCutToBatch 노드는 잠재 표현을 선택한 차원을 따라 여러 조각으로 분할하고 이를 새로운 배치로 쌓습니다. 이를 통해 잠재 샘플의 서로 다른 부분을 독립적으로 처리할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LatentFlip.mdx b/ko/built-in-nodes/LatentFlip.mdx index 32b0b0440..cf02ba54c 100644 --- a/ko/built-in-nodes/LatentFlip.mdx +++ b/ko/built-in-nodes/LatentFlip.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentFlip" icon: "circle" mode: wide --- + LatentFlip 노드는 잠재 표현을 수직 또는 수평으로 뒤집어 조작하도록 설계되었습니다. 이 작업을 통해 잠재 공간을 변환하여 데이터 내에서 새로운 변형이나 관점을 발견할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LatentFromBatch.mdx b/ko/built-in-nodes/LatentFromBatch.mdx index 888f604b1..c19a4f78b 100644 --- a/ko/built-in-nodes/LatentFromBatch.mdx +++ b/ko/built-in-nodes/LatentFromBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentFromBatch" icon: "circle" mode: wide --- + 이 노드는 지정된 배치 인덱스와 길이에 따라 주어진 배치에서 잠재 샘플의 특정 하위 집합을 추출하도록 설계되었습니다. 잠재 샘플을 선택적으로 처리할 수 있게 하여 효율성이나 목표 조작을 위해 배치의 더 작은 세그먼트에 대한 작업을 용이하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/LatentInterpolate.mdx b/ko/built-in-nodes/LatentInterpolate.mdx index ca0eeb232..d3e5cde96 100644 --- a/ko/built-in-nodes/LatentInterpolate.mdx +++ b/ko/built-in-nodes/LatentInterpolate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentInterpolate" icon: "circle" mode: wide --- + LatentInterpolate 노드는 지정된 비율에 따라 두 잠재 샘플 세트 간의 보간을 수행하여, 두 세트의 특성을 혼합한 새로운 중간 잠재 샘플 세트를 생성하도록 설계되었습니다. ## 입력 diff --git a/ko/built-in-nodes/LatentMultiply.mdx b/ko/built-in-nodes/LatentMultiply.mdx index 7474375f9..532354d86 100644 --- a/ko/built-in-nodes/LatentMultiply.mdx +++ b/ko/built-in-nodes/LatentMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentMultiply" icon: "circle" mode: wide --- + LatentMultiply 노드는 샘플의 잠재 표현을 지정된 승수로 확장하도록 설계되었습니다. 이 작업을 통해 잠재 공간 내 특징의 강도나 크기를 조정할 수 있으며, 생성된 콘텐츠의 미세 조정이나 특정 잠재 방향 내 변형 탐색이 가능합니다. ## 입력 diff --git a/ko/built-in-nodes/LatentOperationSharpen.mdx b/ko/built-in-nodes/LatentOperationSharpen.mdx index 0174f8980..504803ff8 100644 --- a/ko/built-in-nodes/LatentOperationSharpen.mdx +++ b/ko/built-in-nodes/LatentOperationSharpen.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentOperationSharpen" icon: "circle" mode: wide --- + LatentOperationSharpen 노드는 가우시안 커널을 사용하여 잠재 표현에 선명화 효과를 적용합니다. 잠재 데이터를 정규화하고, 사용자 정의 선명화 커널로 컨볼루션을 적용한 후 원래 휘도를 복원하는 방식으로 작동합니다. 이를 통해 잠재 공간 표현의 세부 사항과 가장자리가 향상됩니다. ## 입력 diff --git a/ko/built-in-nodes/LatentOperationTonemapReinhard.mdx b/ko/built-in-nodes/LatentOperationTonemapReinhard.mdx index f4fa5f255..e92670d54 100644 --- a/ko/built-in-nodes/LatentOperationTonemapReinhard.mdx +++ b/ko/built-in-nodes/LatentOperationTonemapReinhard.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentOperationTonemapReinhard" icon: "circle" mode: wide --- + LatentOperationTonemapReinhard 노드는 잠재 벡터에 Reinhard 톤매핑을 적용합니다. 이 기술은 평균과 표준편차를 기반으로 한 통계적 접근 방식을 사용하여 잠재 벡터를 정규화하고 크기를 조정하며, 강도는 승수 매개변수로 제어됩니다. ## 입력 diff --git a/ko/built-in-nodes/LatentRotate.mdx b/ko/built-in-nodes/LatentRotate.mdx index 36b1b9f48..1ce9745b2 100644 --- a/ko/built-in-nodes/LatentRotate.mdx +++ b/ko/built-in-nodes/LatentRotate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentRotate" icon: "circle" mode: wide --- + LatentRotate 노드는 지정된 각도로 이미지의 잠재 표현을 회전시키도록 설계되었습니다. 회전 효과를 얻기 위해 잠재 공간을 조작하는 복잡성을 추상화하여, 사용자가 생성 모델의 잠재 공간에서 이미지를 쉽게 변환할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/LatentSubtract.mdx b/ko/built-in-nodes/LatentSubtract.mdx index 470aa143d..29c5a4e2c 100644 --- a/ko/built-in-nodes/LatentSubtract.mdx +++ b/ko/built-in-nodes/LatentSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentSubtract" icon: "circle" mode: wide --- + LatentSubtract 노드는 하나의 잠재 표현에서 다른 잠재 표현을 빼는 역할을 합니다. 이 연산은 한 잠재 공간에 포함된 특징이나 속성을 다른 잠재 공간에서 제거함으로써 생성 모델 출력의 특성을 조작하거나 수정하는 데 사용할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LatentUpscale.mdx b/ko/built-in-nodes/LatentUpscale.mdx index 92ae76c64..9a5a7018c 100644 --- a/ko/built-in-nodes/LatentUpscale.mdx +++ b/ko/built-in-nodes/LatentUpscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscale" icon: "circle" mode: wide --- + LatentUpscale 노드는 이미지의 잠재 표현을 업스케일링하기 위해 설계되었습니다. 출력 이미지의 크기와 업스케일링 방법을 조정할 수 있어 잠재 이미지의 해상도를 향상시키는 데 유연성을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/LatentUpscaleBy.mdx b/ko/built-in-nodes/LatentUpscaleBy.mdx index 18a4ac1f1..17fc1e1e4 100644 --- a/ko/built-in-nodes/LatentUpscaleBy.mdx +++ b/ko/built-in-nodes/LatentUpscaleBy.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscaleBy" icon: "circle" mode: wide --- + LatentUpscaleBy 노드는 이미지의 잠재 표현을 업스케일링하기 위해 설계되었습니다. 스케일 비율과 업스케일링 방법을 조정할 수 있어 잠재 샘플의 해상도를 향상시키는 유연성을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/LatentUpscaleModelLoader.mdx b/ko/built-in-nodes/LatentUpscaleModelLoader.mdx index 6de2f805b..f22dcc453 100644 --- a/ko/built-in-nodes/LatentUpscaleModelLoader.mdx +++ b/ko/built-in-nodes/LatentUpscaleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscaleModelLoader" icon: "circle" mode: wide --- + LatentUpscaleModelLoader 노드는 잠재 표현을 업스케일링하기 위해 설계된 특수 모델을 로드합니다. 시스템의 지정된 폴더에서 모델 파일을 읽고 해당 유형(720p, 1080p 또는 기타)을 자동으로 감지하여 올바른 내부 모델 아키텍처를 인스턴스화하고 구성합니다. 로드된 모델은 다른 노드에서 잠재 공간 초해상도 작업에 사용할 준비가 됩니다. ## 입력 diff --git a/ko/built-in-nodes/LazyCache.mdx b/ko/built-in-nodes/LazyCache.mdx index c39f215d2..11b92cb02 100644 --- a/ko/built-in-nodes/LazyCache.mdx +++ b/ko/built-in-nodes/LazyCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LazyCache" icon: "circle" mode: wide --- + LazyCache는 EasyCache의 홈브루 버전으로, 더욱 간편한 구현을 제공합니다. ComfyUI의 모든 모델과 함께 작동하며, 샘플링 중 계산량을 줄이기 위해 캐싱 기능을 추가합니다. 일반적으로 EasyCache보다 성능이 떨어지지만, 드물게 더 효과적일 수 있으며 보편적인 호환성을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/Load3D.mdx b/ko/built-in-nodes/Load3D.mdx index a1c0ac05c..760abf90a 100644 --- a/ko/built-in-nodes/Load3D.mdx +++ b/ko/built-in-nodes/Load3D.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Load3D" icon: "circle" mode: wide --- -# Load3D 노드 Load3D 노드는 3D 모델 파일을 불러오고 처리하는 핵심 노드입니다. 노드를 불러오면 `ComfyUI/input/3d/`에서 사용 가능한 3D 리소스를 자동으로 검색합니다. 또한 업로드 기능을 사용하여 지원되는 3D 파일을 업로드하여 미리 볼 수 있습니다. @@ -31,13 +30,13 @@ Load3D 노드는 3D 모델 파일을 불러오고 처리하는 핵심 노드입 | 매개변수 이름 | 설명 | 데이터 유형 | | --- | --- | --- | -| `mask` | 캔버스 렌더링 이미지 | IMAGE | -| `mesh_path` | 현재 모델 위치를 포함하는 마스크 | MASK | -| `normal` | 모델 파일 경로 | STRING | -| `camera_info` | 법선 맵 | IMAGE | -| `recording_video` | 라인 아트 이미지 출력, 해당 `edge_threshold`는 캔버스 모델 메뉴에서 조정 가능 | IMAGE | -| `model_3d` | 카메라 정보 | LOAD3D_CAMERA | -| `model_3d_info` | 녹화된 비디오(녹화가 있는 경우에만) | VIDEO | +| `image` | 캔버스 렌더링 이미지 | IMAGE | +| `mask` | 현재 모델 위치를 포함하는 마스크 | MASK | +| `mesh_path` | 모델 파일 경로 | STRING | +| `normal` | 법선 맵 | IMAGE | +| `camera_info` | 라인 아트 이미지 출력, 해당 `edge_threshold`는 캔버스 모델 메뉴에서 조정 가능 | IMAGE | +| `recording_video` | 카메라 정보 | LOAD3D_CAMERA | +| `model_3d` | 녹화된 비디오(녹화가 있는 경우에만) | VIDEO | 모든 출력 미리보기: ![보기 작업 데모](/images/built-in-nodes/Load3D/load3d_outputs.webp) diff --git a/ko/built-in-nodes/Load3DAdvanced.mdx b/ko/built-in-nodes/Load3DAdvanced.mdx new file mode 100644 index 000000000..651564b67 --- /dev/null +++ b/ko/built-in-nodes/Load3DAdvanced.mdx @@ -0,0 +1,38 @@ +--- +title: "Load3DAdvanced - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the Load3DAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "Load3DAdvanced" +icon: "circle" +mode: wide +--- + +이 노드는 ComfyUI 입력 디렉토리에서 3D 모델 파일을 불러와 모델 데이터와 함께 카메라 및 뷰포트 정보를 제공합니다. 일반적인 3D 파일 형식을 지원하며, 렌더링을 위한 출력 이미지 크기를 지정할 수 있습니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `model_file` | 불러올 3D 모델 파일입니다. 모델을 불러오지 않으려면 "none"을 선택하십시오. | STRING | 예 | `"none"`
input/3d 디렉토리 내 사용 가능한 3D 파일 목록 | +| `viewport_state` | 3D 뷰어에서 가져온 카메라 및 모델 정보가 포함된 현재 뷰포트 상태입니다. | LOAD3D | 예 | - | +| `width` | 출력 이미지의 가로 크기(픽셀 단위, 기본값: 1024) | INT | 예 | 최소: 1
최대: 4096
단계: 1 | +| `height` | 출력 이미지의 세로 크기(픽셀 단위, 기본값: 1024) | INT | 예 | 최소: 1
최대: 4096
단계: 1 | + +**매개변수 참고 사항:** +- `model_file` 매개변수는 다음 확장자를 가진 파일만 표시합니다: .gltf, .glb, .obj, .fbx, .stl +- 파일은 ComfyUI 설치 디렉토리의 `input/3d` 폴더에 위치해야 합니다. +- `model_file`을 "none"으로 설정하면 3D 모델 데이터가 불러와지지 않습니다(출력 `model_3d`는 비어 있게 됩니다). + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `model_3d` | 불러온 3D 모델 데이터입니다. 모델 파일을 선택하지 않으면 비어 있습니다. | FILE3DANY | +| `model_3d_info` | 뷰포트 상태에서 가져온 불러온 3D 모델에 대한 정보입니다. | LOAD3DMODELINFO | +| `camera_info` | 뷰포트 상태에서 가져온 카메라 정보입니다. | LOAD3DCAMERA | +| `width` | 지정된 출력 이미지 가로 크기입니다. | INT | +| `height` | 지정된 출력 이미지 세로 크기입니다. | INT | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Load3DAdvanced/ko.md) + +--- +**Source fingerprint (SHA-256):** `fdacea8abf627621150e1196743e36f61534333837c33cc9a7416a6d11700c4d` diff --git a/ko/built-in-nodes/Load3DAnimation.mdx b/ko/built-in-nodes/Load3DAnimation.mdx index 92b1c2314..2e24ff37a 100644 --- a/ko/built-in-nodes/Load3DAnimation.mdx +++ b/ko/built-in-nodes/Load3DAnimation.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Load3DAnimation" icon: "circle" mode: wide --- -# Load3DAnimation 노드 Load3DAnimation 노드는 3D 모델 파일을 불러오고 처리하는 핵심 노드입니다. 노드를 불러오면 `ComfyUI/input/3d/`에서 사용 가능한 3D 리소스를 자동으로 검색합니다. 또한 업로드 기능을 사용하여 지원되는 3D 파일을 업로드하여 미리 볼 수 있습니다. diff --git a/ko/built-in-nodes/LoadAudio.mdx b/ko/built-in-nodes/LoadAudio.mdx index 192ac1300..f9aa9981c 100644 --- a/ko/built-in-nodes/LoadAudio.mdx +++ b/ko/built-in-nodes/LoadAudio.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LoadAudio" icon: "circle" mode: wide --- -# LoadAudio 노드 LoadAudio 노드는 입력 디렉토리에서 오디오 파일을 불러와 ComfyUI의 다른 오디오 노드에서 처리할 수 있는 형식으로 변환합니다. 이 노드는 오디오 파일을 읽어 파형 데이터와 샘플 레이트를 추출하여 다운스트림 오디오 처리 작업에 사용할 수 있도록 제공합니다. diff --git a/ko/built-in-nodes/LoadBackgroundRemovalModel.mdx b/ko/built-in-nodes/LoadBackgroundRemovalModel.mdx index aa88369b4..0d97ab40c 100644 --- a/ko/built-in-nodes/LoadBackgroundRemovalModel.mdx +++ b/ko/built-in-nodes/LoadBackgroundRemovalModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadBackgroundRemovalModel" icon: "circle" mode: wide --- + ## 개요 파일에서 배경 제거 모델을 불러옵니다. 이 노드는 이미지에서 배경을 제거하는 데 사용할 모델을 준비합니다. diff --git a/ko/built-in-nodes/LoadDA3Model.mdx b/ko/built-in-nodes/LoadDA3Model.mdx new file mode 100644 index 000000000..031bf720a --- /dev/null +++ b/ko/built-in-nodes/LoadDA3Model.mdx @@ -0,0 +1,27 @@ +--- +title: "LoadDA3Model - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LoadDA3Model node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LoadDA3Model" +icon: "circle" +mode: wide +--- + +이 노드는 파일에서 Depth Anything 3 모델을 로드하여 깊이 추정 작업에 사용할 수 있도록 준비합니다. 모델 파일을 선택하고, 선택적으로 모델 가중치의 숫자 정밀도(데이터 타입)를 지정할 수 있습니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `model_name` | 로드할 Depth Anything 3 모델 파일의 이름입니다. | STRING | 예 | `geometry_estimation` 폴더에 있는 사용 가능한 모델 파일 목록 | +| `weight_dtype` | 모델 가중치의 숫자 정밀도(데이터 타입)입니다. "default" 옵션은 모델의 원래 정밀도를 사용합니다. (기본값: "default") | STRING | 아니요 | `"default"`
`"fp16"`
`"bf16"`
`"fp32"` | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `DA3_MODEL` | 깊이 추정 워크플로우에서 사용할 준비가 된 로드된 Depth Anything 3 모델입니다. | DA3_MODEL | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadDA3Model/ko.md) + +--- +**Source fingerprint (SHA-256):** `b1b3f4075cd9172bc1f274848b9300bca20d3cbd53b23d3c4a9f0986b36e409e` diff --git a/ko/built-in-nodes/LoadImage.mdx b/ko/built-in-nodes/LoadImage.mdx index 3fe1a9843..2b78f6639 100644 --- a/ko/built-in-nodes/LoadImage.mdx +++ b/ko/built-in-nodes/LoadImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImage" icon: "circle" mode: wide --- + LoadImage 노드는 지정된 경로에서 이미지를 불러와 전처리하도록 설계되었습니다. 여러 프레임이 있는 이미지 형식을 처리하고, EXIF 데이터에 기반한 회전 등 필요한 변환을 적용하며, 픽셀 값을 정규화하고, 알파 채널이 있는 이미지의 경우 선택적으로 마스크를 생성합니다. 이 노드는 파이프라인 내에서 추가 처리 또는 분석을 위해 이미지를 준비하는 데 필수적입니다. ## 입력 diff --git a/ko/built-in-nodes/LoadImageDataSetFromFolder.mdx b/ko/built-in-nodes/LoadImageDataSetFromFolder.mdx index e1036aeb8..476e5454f 100644 --- a/ko/built-in-nodes/LoadImageDataSetFromFolder.mdx +++ b/ko/built-in-nodes/LoadImageDataSetFromFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageDataSetFromFolder" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageDataSetFromFolder/en.md) 이 노드는 ComfyUI의 입력 디렉터리 내에 있는 지정된 하위 폴더에서 여러 이미지를 불러옵니다. 선택한 폴더에서 일반적인 이미지 파일 형식을 검색하여 목록으로 반환하므로, 일괄 처리나 데이터셋 준비에 유용합니다. @@ -19,7 +20,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `images` | 불러온 이미지 목록입니다. 이 노드는 선택한 폴더에서 발견된 모든 유효한 이미지 파일(PNG, JPG, JPEG, WEBP)을 불러옵니다. | IMAGE | +| `이미지` | 불러온 이미지 목록입니다. 이 노드는 선택한 폴더에서 발견된 모든 유효한 이미지 파일(PNG, JPG, JPEG, WEBP)을 불러옵니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageDataSetFromFolder/ko.md) diff --git a/ko/built-in-nodes/LoadImageMask.mdx b/ko/built-in-nodes/LoadImageMask.mdx index 6ffdb680e..806eb0205 100644 --- a/ko/built-in-nodes/LoadImageMask.mdx +++ b/ko/built-in-nodes/LoadImageMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageMask" icon: "circle" mode: wide --- + LoadImageMask 노드는 지정된 경로에서 이미지와 관련 마스크를 로드하여, 추가 이미지 조작 또는 분석 작업과의 호환성을 보장하도록 처리합니다. 이 노드는 알파 채널 유무 등 다양한 이미지 형식과 조건을 처리하는 데 중점을 두며, 이미지와 마스크를 표준화된 형식으로 변환하여 다운스트림 처리를 준비합니다. ## 입력 diff --git a/ko/built-in-nodes/LoadImageOutput.mdx b/ko/built-in-nodes/LoadImageOutput.mdx index 191708353..13379d91e 100644 --- a/ko/built-in-nodes/LoadImageOutput.mdx +++ b/ko/built-in-nodes/LoadImageOutput.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LoadImageOutput" icon: "circle" mode: wide --- -# LoadImageOutput 노드 LoadImageOutput 노드는 출력 폴더에서 이미지를 불러옵니다. 새로고침 버튼을 클릭하면 사용 가능한 이미지 목록이 업데이트되고 첫 번째 이미지가 자동으로 선택되어, 생성된 이미지를 순차적으로 확인하기 쉽습니다. diff --git a/ko/built-in-nodes/LoadImageSetFromFolderNode.mdx b/ko/built-in-nodes/LoadImageSetFromFolderNode.mdx index e3fbd41eb..583a03acc 100644 --- a/ko/built-in-nodes/LoadImageSetFromFolderNode.mdx +++ b/ko/built-in-nodes/LoadImageSetFromFolderNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageSetFromFolderNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageSetFromFolderNode/en.md) LoadImageSetFromFolderNode는 학습 목적으로 지정된 폴더 디렉터리에서 여러 이미지를 불러옵니다. 일반적인 이미지 형식을 자동으로 감지하며, 필요에 따라 다양한 방법을 사용하여 이미지 크기를 조정한 후 배치 형태로 반환할 수 있습니다. diff --git a/ko/built-in-nodes/LoadImageSetNode.mdx b/ko/built-in-nodes/LoadImageSetNode.mdx index b20ed55ee..45ecfae84 100644 --- a/ko/built-in-nodes/LoadImageSetNode.mdx +++ b/ko/built-in-nodes/LoadImageSetNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageSetNode" icon: "circle" mode: wide --- + LoadImageSetNode는 입력 디렉터리에서 여러 이미지를 로드하여 배치 처리 및 학습 목적으로 사용합니다. 다양한 이미지 형식을 지원하며, 필요에 따라 여러 방법을 사용하여 이미지 크기를 조정할 수 있습니다. 이 노드는 선택된 모든 이미지를 배치로 처리하여 단일 텐서로 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/LoadImageTextDataSetFromFolder.mdx b/ko/built-in-nodes/LoadImageTextDataSetFromFolder.mdx index 271a6995b..9106cbbe3 100644 --- a/ko/built-in-nodes/LoadImageTextDataSetFromFolder.mdx +++ b/ko/built-in-nodes/LoadImageTextDataSetFromFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageTextDataSetFromFolder" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextDataSetFromFolder/en.md) 이 노드는 지정된 폴더에서 이미지와 해당 텍스트 캡션으로 구성된 데이터셋을 불러옵니다. 이미지 파일을 검색하고, 동일한 기본 이름을 가진 일치하는 `.txt` 파일을 자동으로 찾아 캡션으로 사용합니다. 또한, 하위 폴더 이름에 숫자 접두사(예: `10_folder_name`)를 사용하여 해당 폴더 내 이미지가 출력에서 여러 번 반복되도록 지정할 수 있는 특정 폴더 구조를 지원합니다. @@ -21,8 +22,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `텍스트` | 불러온 이미지 텐서 목록입니다. | IMAGE | -| `texts` | 각 이미지에 해당하는 텍스트 캡션 목록입니다. | STRING | +| `이미지` | 불러온 이미지 텐서 목록입니다. | IMAGE | +| `텍스트` | 각 이미지에 해당하는 텍스트 캡션 목록입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextDataSetFromFolder/ko.md) diff --git a/ko/built-in-nodes/LoadImageTextSetFromFolderNode.mdx b/ko/built-in-nodes/LoadImageTextSetFromFolderNode.mdx index 08cf27d02..494bf5060 100644 --- a/ko/built-in-nodes/LoadImageTextSetFromFolderNode.mdx +++ b/ko/built-in-nodes/LoadImageTextSetFromFolderNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LoadImageTextSetFromFolderNode" icon: "circle" mode: wide --- -# LoadImageTextSetFromFolderNode 지정된 디렉토리에서 학습용 이미지 배치와 해당 이미지의 텍스트 캡션을 로드합니다. 이 노드는 자동으로 이미지 파일과 연결된 캡션 텍스트 파일을 검색하고, 지정된 크기 조정 설정에 따라 이미지를 처리한 후 제공된 CLIP 모델을 사용하여 캡션을 인코딩합니다. diff --git a/ko/built-in-nodes/LoadLatent.mdx b/ko/built-in-nodes/LoadLatent.mdx index a3d84c71a..34c690752 100644 --- a/ko/built-in-nodes/LoadLatent.mdx +++ b/ko/built-in-nodes/LoadLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadLatent" icon: "circle" mode: wide --- + LoadLatent 노드는 입력 디렉토리에 있는 .latent 파일에서 이전에 저장된 잠재 표현을 불러옵니다. 파일에서 잠재 텐서 데이터를 읽고 필요한 스케일링 조정을 적용한 후, 다른 노드에서 사용할 수 있도록 잠재 데이터를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx b/ko/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx index fed676d2a..db0583450 100644 --- a/ko/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx +++ b/ko/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LoadMediaPipeFaceLandmarker" icon: "circle" mode: wide --- -# 개요 이 노드는 이미지에서 얼굴과 얼굴 랜드마크(눈, 코, 입 등)를 감지할 수 있는 MediaPipe Face Landmarker v2 모델을 로드합니다. 근거리 탐지와 원거리 탐지의 두 가지 변형과 함께 얼굴 분석을 위한 공유 메시 데이터, 블렌드쉐이프, 표준 기하학 데이터를 포함합니다. diff --git a/ko/built-in-nodes/LoadMoGeModel.mdx b/ko/built-in-nodes/LoadMoGeModel.mdx index a62546045..0fb2adb81 100644 --- a/ko/built-in-nodes/LoadMoGeModel.mdx +++ b/ko/built-in-nodes/LoadMoGeModel.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LoadMoGeModel" icon: "circle" mode: wide --- -# 개요 MoGe(단안 기하학) 모델을 파일에서 불러와 기하학 추정 작업에 사용할 수 있도록 준비합니다. 이 노드는 `geometry_estimation` 폴더에서 모델 파일을 읽어 훈련된 가중치로 MoGe 모델을 초기화합니다. diff --git a/ko/built-in-nodes/LoadTrainingDataset.mdx b/ko/built-in-nodes/LoadTrainingDataset.mdx index ff9457825..4d76bccde 100644 --- a/ko/built-in-nodes/LoadTrainingDataset.mdx +++ b/ko/built-in-nodes/LoadTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadTrainingDataset" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadTrainingDataset/en.md) 이 노드는 이전에 디스크에 저장된 인코딩된 학습 데이터셋을 불러옵니다. ComfyUI 출력 디렉터리 내의 지정된 폴더에서 모든 데이터 샤드 파일을 검색하여 읽어온 후, 결합된 잠재 벡터와 컨디셔닝 데이터를 반환하여 학습 워크플로우에서 사용할 수 있도록 합니다. @@ -19,7 +20,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `conditioning` | 각 딕셔너리에 `"samples"` 키와 텐서가 포함된 잠재 딕셔너리 목록입니다. | LATENT | +| `latents` | 각 딕셔너리에 `"samples"` 키와 텐서가 포함된 잠재 딕셔너리 목록입니다. | LATENT | | `conditioning` | 각 내부 리스트에 해당 샘플의 컨디셔닝 데이터가 포함된 컨디셔닝 리스트 목록입니다. | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadTrainingDataset/ko.md) diff --git a/ko/built-in-nodes/LoadVideo.mdx b/ko/built-in-nodes/LoadVideo.mdx index 860b2696c..eac4f50dc 100644 --- a/ko/built-in-nodes/LoadVideo.mdx +++ b/ko/built-in-nodes/LoadVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LoadVideo" icon: "circle" mode: wide --- -# Load Video (비디오 로드) 비디오 로드 노드는 입력 디렉토리에서 비디오 파일을 불러와 워크플로우에서 처리할 수 있도록 제공합니다. 지정된 입력 폴더에서 비디오 파일을 읽어 다른 비디오 처리 노드에 연결할 수 있는 비디오 데이터로 출력합니다. diff --git a/ko/built-in-nodes/LoraLoader.mdx b/ko/built-in-nodes/LoraLoader.mdx index e1b2c1088..6b0f88d74 100644 --- a/ko/built-in-nodes/LoraLoader.mdx +++ b/ko/built-in-nodes/LoraLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoader" icon: "circle" mode: wide --- + 이 노드는 LoRA 폴더(하위 폴더 포함)에 있는 모델을 자동으로 감지하며, 해당 모델 경로는 `ComfyUI\models\loras`입니다. 자세한 내용은 LoRA 모델 설치를 참고하십시오. LoRA 로더 노드는 주로 LoRA 모델을 불러오는 데 사용됩니다. LoRA 모델을 이미지에 특정 스타일, 콘텐츠 및 세부 정보를 부여할 수 있는 필터라고 생각하시면 됩니다: diff --git a/ko/built-in-nodes/LoraLoaderBypass.mdx b/ko/built-in-nodes/LoraLoaderBypass.mdx index 051928f8d..e89310ddd 100644 --- a/ko/built-in-nodes/LoraLoaderBypass.mdx +++ b/ko/built-in-nodes/LoraLoaderBypass.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderBypass" icon: "circle" mode: wide --- + LoraLoaderBypass 노드는 특수한 "우회(bypass)" 모드로 확산 모델과 CLIP 모델에 LoRA(저차원 적응)를 적용합니다. 표준 LoRA 로더와 달리, 이 방식은 기본 모델의 가중치를 영구적으로 수정하지 않습니다. 대신 LoRA의 효과를 모델의 정상 순방향 전달에 추가하여 출력을 계산하므로, 학습 중이거나 가중치가 오프로드된 모델로 작업할 때 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/LoraLoaderBypassModelOnly.mdx b/ko/built-in-nodes/LoraLoaderBypassModelOnly.mdx index b8b358534..dc5c7eb98 100644 --- a/ko/built-in-nodes/LoraLoaderBypassModelOnly.mdx +++ b/ko/built-in-nodes/LoraLoaderBypassModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderBypassModelOnly" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraLoaderBypassModelOnly/en.md) 이 노드는 LoRA(저차원 적응)를 모델에 적용하여 동작을 수정하지만, 모델 구성 요소 자체에만 영향을 미칩니다. 지정된 LoRA 파일을 로드하고 주어진 강도로 모델의 가중치를 조정하며, CLIP 텍스트 인코더와 같은 다른 구성 요소는 변경하지 않습니다. diff --git a/ko/built-in-nodes/LoraLoaderModelOnly.mdx b/ko/built-in-nodes/LoraLoaderModelOnly.mdx index bac384a76..83e1a5214 100644 --- a/ko/built-in-nodes/LoraLoaderModelOnly.mdx +++ b/ko/built-in-nodes/LoraLoaderModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderModelOnly" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/loras` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 설정된 추가 경로의 모델도 읽어옵니다. 경우에 따라 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수 있습니다. 이 노드는 CLIP 모델 없이 LoRA 모델을 로드하는 데 특화되어 있으며, LoRA 매개변수를 기반으로 주어진 모델을 강화하거나 수정하는 데 중점을 둡니다. LoRA 매개변수를 통해 모델 강도를 동적으로 조정할 수 있어, 모델 동작에 대한 세밀한 제어를 가능하게 합니다. diff --git a/ko/built-in-nodes/LoraModelLoader.mdx b/ko/built-in-nodes/LoraModelLoader.mdx index d6995ad06..34c38eee5 100644 --- a/ko/built-in-nodes/LoraModelLoader.mdx +++ b/ko/built-in-nodes/LoraModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraModelLoader" icon: "circle" mode: wide --- + LoraModelLoader 노드는 학습된 LoRA(Low-Rank Adaptation) 가중치를 확산 모델에 적용합니다. 학습된 LoRA 모델에서 가중치를 불러오고 영향 강도를 조정하여 기본 모델을 수정합니다. 이를 통해 확산 모델을 처음부터 다시 학습시키지 않고도 동작을 사용자 지정할 수 있습니다. ## 입력 @@ -22,7 +23,7 @@ LoraModelLoader 노드는 학습된 LoRA(Low-Rank Adaptation) 가중치를 확 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `모델` | LoRA 가중치가 적용된 수정된 확산 모델입니다. | MODEL | +| `model` | LoRA 가중치가 적용된 수정된 확산 모델입니다. | MODEL | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoraModelLoader/ko.md) diff --git a/ko/built-in-nodes/LoraSave.mdx b/ko/built-in-nodes/LoraSave.mdx index a80e86769..eaa30a2d9 100644 --- a/ko/built-in-nodes/LoraSave.mdx +++ b/ko/built-in-nodes/LoraSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraSave" icon: "circle" mode: wide --- + LoraSave 노드는 모델 차이에서 LoRA(Low-Rank Adaptation) 파일을 추출하여 저장합니다. 확산 모델 차이, 텍스트 인코더 차이 또는 둘 다를 처리하여 지정된 순위와 유형의 LoRA 형식으로 변환할 수 있습니다. 생성된 LoRA 파일은 나중에 사용할 수 있도록 출력 디렉터리에 저장됩니다. ## 입력 diff --git a/ko/built-in-nodes/LossGraphNode.mdx b/ko/built-in-nodes/LossGraphNode.mdx index db8413345..a6ad174e4 100644 --- a/ko/built-in-nodes/LossGraphNode.mdx +++ b/ko/built-in-nodes/LossGraphNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LossGraphNode" icon: "circle" mode: wide --- + LossGraphNode는 시간에 따른 훈련 손실 값을 시각적 그래프로 생성하여 미리보기 이미지로 표시합니다. 훈련 프로세스의 손실 데이터를 받아 훈련 단계별 손실 변화를 보여주는 선 그래프를 생성합니다. 결과 그래프에는 축 레이블과 최소/최대 손실 값이 포함됩니다. ## 입력 diff --git a/ko/built-in-nodes/LotusConditioning.mdx b/ko/built-in-nodes/LotusConditioning.mdx index acb4d685d..0912850c0 100644 --- a/ko/built-in-nodes/LotusConditioning.mdx +++ b/ko/built-in-nodes/LotusConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LotusConditioning" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LotusConditioning/en.md) LotusConditioning 노드는 Lotus 모델을 위해 사전 계산된 컨디셔닝 임베딩을 제공합니다. 이 노드는 널 컨디셔닝이 적용된 고정 인코더를 사용하며, 추론이나 대용량 텐서 파일 로딩 없이 하드코딩된 프롬프트 임베딩을 반환하여 참조 구현과의 일관성을 유지합니다. 이 노드는 생성 파이프라인에서 직접 사용할 수 있는 고정 컨디셔닝 텐서를 출력합니다. @@ -19,7 +20,7 @@ LotusConditioning 노드는 Lotus 모델을 위해 사전 계산된 컨디셔닝 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `conditioning` | Lotus 모델을 위한 사전 계산된 컨디셔닝 임베딩으로, 고정 프롬프트 임베딩과 빈 딕셔너리를 포함합니다. | CONDITIONING | +| `조건` | Lotus 모델을 위한 사전 계산된 컨디셔닝 임베딩으로, 고정 프롬프트 임베딩과 빈 딕셔너리를 포함합니다. | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LotusConditioning/ko.md) diff --git a/ko/built-in-nodes/LtxvApiImageToVideo.mdx b/ko/built-in-nodes/LtxvApiImageToVideo.mdx index a9ba02468..05287ae51 100644 --- a/ko/built-in-nodes/LtxvApiImageToVideo.mdx +++ b/ko/built-in-nodes/LtxvApiImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LtxvApiImageToVideo" icon: "circle" mode: wide --- + LTXV 이미지-투-비디오 노드는 단일 시작 이미지로부터 전문가 수준의 비디오를 생성합니다. 외부 API를 사용하여 텍스트 프롬프트를 기반으로 비디오 시퀀스를 생성하며, 지속 시간, 해상도 및 프레임 속도를 사용자 지정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LtxvApiTextToVideo.mdx b/ko/built-in-nodes/LtxvApiTextToVideo.mdx index 35bdc49d0..1d290da37 100644 --- a/ko/built-in-nodes/LtxvApiTextToVideo.mdx +++ b/ko/built-in-nodes/LtxvApiTextToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LtxvApiTextToVideo" icon: "circle" mode: wide --- + 다음은 요청하신 번역 결과입니다. --- diff --git a/ko/built-in-nodes/LumaConceptsNode.mdx b/ko/built-in-nodes/LumaConceptsNode.mdx index 80383abda..a73f00591 100644 --- a/ko/built-in-nodes/LumaConceptsNode.mdx +++ b/ko/built-in-nodes/LumaConceptsNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LumaConceptsNode" icon: "circle" mode: wide --- -# Luma 개념 노드 Luma 텍스트-투-비디오 및 Luma 이미지-투-비디오 노드와 함께 사용할 하나 이상의 카메라 개념을 보관합니다. 이 노드를 사용하면 최대 4개의 카메라 개념을 선택하고, 선택적으로 기존 개념 체인과 결합할 수 있습니다. diff --git a/ko/built-in-nodes/LumaImageEditNode2.mdx b/ko/built-in-nodes/LumaImageEditNode2.mdx index 8d6559049..71adff62d 100644 --- a/ko/built-in-nodes/LumaImageEditNode2.mdx +++ b/ko/built-in-nodes/LumaImageEditNode2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LumaImageEditNode2" icon: "circle" mode: wide --- -# 개요 이 노드는 Luma UNI-1 모델을 기반으로 텍스트 프롬프트를 사용하여 기존 이미지를 편집합니다. 소스 이미지와 원하는 변경 사항에 대한 설명을 입력받아 편집된 새 이미지 버전을 생성합니다. diff --git a/ko/built-in-nodes/LumaImageModifyNode.mdx b/ko/built-in-nodes/LumaImageModifyNode.mdx index 0f0f97357..1bbccc9c5 100644 --- a/ko/built-in-nodes/LumaImageModifyNode.mdx +++ b/ko/built-in-nodes/LumaImageModifyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageModifyNode" icon: "circle" mode: wide --- + 다음은 제공된 영어 문서를 번역 규칙에 따라 한국어로 번역한 결과입니다. > 본 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageModifyNode/en.md) diff --git a/ko/built-in-nodes/LumaImageNode.mdx b/ko/built-in-nodes/LumaImageNode.mdx index b2d29452c..778e3f8da 100644 --- a/ko/built-in-nodes/LumaImageNode.mdx +++ b/ko/built-in-nodes/LumaImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LumaImageNode" icon: "circle" mode: wide --- -# 개요 텍스트 프롬프트와 종횡비를 기반으로 이미지를 동기식으로 생성합니다. 이 노드는 텍스트 설명을 사용하여 이미지를 생성하며, 캐릭터 이미지와 스타일 이미지를 포함한 다양한 참조 입력을 통해 이미지 크기와 스타일을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/LumaImageNode2.mdx b/ko/built-in-nodes/LumaImageNode2.mdx index a57d6a26f..c532bf9fd 100644 --- a/ko/built-in-nodes/LumaImageNode2.mdx +++ b/ko/built-in-nodes/LumaImageNode2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LumaImageNode2" icon: "circle" mode: wide --- -# 개요 이 노드는 Luma UNI-1 모델을 사용하여 텍스트 설명으로부터 이미지를 생성합니다. 텍스트 프롬프트와 종횡비, 스타일 같은 선택적 설정을 입력받아 Luma API에 요청을 보내 이미지를 생성합니다. diff --git a/ko/built-in-nodes/LumaImageToVideoNode.mdx b/ko/built-in-nodes/LumaImageToVideoNode.mdx index 8980fcac3..f2af35e5f 100644 --- a/ko/built-in-nodes/LumaImageToVideoNode.mdx +++ b/ko/built-in-nodes/LumaImageToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LumaImageToVideoNode" icon: "circle" mode: wide --- -# Luma 이미지-투-비디오 노드 텍스트 프롬프트와 선택적 시작/종료 이미지를 기반으로 동기식으로 비디오를 생성합니다. 이 노드는 Luma API를 사용하여 비디오를 생성하며, 프롬프트를 통해 비디오 콘텐츠를 정의하고 선택적으로 첫 번째 및/또는 마지막 프레임을 지정하여 비디오 구조를 제어할 수 있습니다. diff --git a/ko/built-in-nodes/LumaRay32ExtendVideoNode.mdx b/ko/built-in-nodes/LumaRay32ExtendVideoNode.mdx new file mode 100644 index 000000000..305ad18af --- /dev/null +++ b/ko/built-in-nodes/LumaRay32ExtendVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32ExtendVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32ExtendVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32ExtendVideoNode" +icon: "circle" +mode: wide +--- + +이 노드는 이전 Luma Ray 3.2 비디오 생성 결과를 확장하여, 기존 콘텐츠 뒤(순방향 확장) 또는 앞(역방향 확장)에 새로운 콘텐츠를 추가합니다. 이전 Luma Ray 3.2 노드의 생성 ID 출력을 연결하여 5초 길이의 매끄러운 확장 비디오를 생성할 수 있습니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `source_generation_id` | 확장할 이전 Ray 3.2 비디오의 생성 ID입니다. 다른 Luma Ray 3.2 노드의 generation_id 출력을 연결하십시오. | STRING | 예 | - | +| `direction` | 순방향은 이전 클립 뒤에 이어지고, 역방향은 이전 클립 앞에 추가됩니다. "순방향(뒤에 이어서)"을 선택하면 선택적으로 루프 모드를 활성화할 수 있습니다. | COMBO | 예 | "순방향(뒤에 이어서)"
"역방향(앞에 추가)" | +| `loop` | 확장된 비디오를 매끄럽게 반복합니다(순방향 확장 전용). | BOOLEAN | 아니요 | True
False | +| `prompt` | 생성할 새 콘텐츠를 설명하는 텍스트 프롬프트입니다. | STRING | 예 | - | +| `resolution` | 확장된 비디오 세그먼트의 출력 해상도입니다. | COMBO | 예 | "540p"
"720p"
"1080p" | +| `seed` | 재현 가능한 생성 결과를 위한 무작위 시드입니다. | INT | 예 | - | + +**참고:** `loop` 매개변수는 `direction`이 "순방향(뒤에 이어서)"으로 설정된 경우에만 사용할 수 있습니다. "역방향(앞에 추가)"을 사용하는 경우 루프 옵션을 사용할 수 없습니다. `prompt`는 1자에서 6000자 사이여야 합니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `generation_id` | 생성된 5초 길이의 확장 비디오 세그먼트입니다. | VIDEO | +| `generation_id` | 이 생성 결과의 고유 식별자로, 다른 Luma Ray 3.2 비디오 확장 노드에 연결하여 추가 확장에 사용할 수 있습니다. | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32ExtendVideoNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `a67ca53d4bcb9f3fd82bc0482b579f5f7fe4bf866f8d83cb922e1082ad320057` diff --git a/ko/built-in-nodes/LumaRay32ImageToVideoNode.mdx b/ko/built-in-nodes/LumaRay32ImageToVideoNode.mdx new file mode 100644 index 000000000..b70a87d31 --- /dev/null +++ b/ko/built-in-nodes/LumaRay32ImageToVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32ImageToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32ImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32ImageToVideoNode" +icon: "circle" +mode: wide +--- + +Luma의 Ray 3.2 모델을 사용하여 시작 및/또는 종료 프레임으로부터 비디오를 생성합니다. 이미지 기반 생성은 항상 5초 길이입니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `prompt` | 비디오 생성을 위한 텍스트 프롬프트입니다. | STRING | 예 | 1~6000자 | +| `resolution` | 생성된 비디오의 출력 해상도입니다(기본값: "720p"). | COMBO | 예 | "360p"
"540p"
"720p"
"1080p" | +| `loop` | 비디오를 끊김 없이 반복 재생되도록 설정합니다. 종료 프레임이 설정된 경우 사용할 수 없습니다. | BOOLEAN | 예 | True
False | +| `seed` | 재현 가능한 생성을 위한 시드 값입니다. | INT | 예 | 0~2147483647 | +| `start_frame` | 생성된 비디오의 첫 번째 프레임입니다. | IMAGE | 아니요 | - | +| `end_frame` | 생성된 비디오의 마지막 프레임입니다. | IMAGE | 아니요 | - | + +**참고:** `start_frame` 또는 `end_frame` 중 하나 이상을 반드시 제공해야 합니다. 두 프레임을 모두 제공하면 생성된 비디오가 시작 프레임에서 종료 프레임으로 전환됩니다. `end_frame`이 설정된 경우 `loop` 옵션을 활성화할 수 없습니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `generation_id` | 생성된 비디오 출력입니다. | VIDEO | +| `generation_id` | 생성 요청에 대한 고유 식별자입니다. | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32ImageToVideoNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `ff479c196f10153ffa09af6acfb4e286d1934aa28a5e9b413613097a2cfb5f2a` diff --git a/ko/built-in-nodes/LumaRay32KeyframeNode.mdx b/ko/built-in-nodes/LumaRay32KeyframeNode.mdx new file mode 100644 index 000000000..965415a84 --- /dev/null +++ b/ko/built-in-nodes/LumaRay32KeyframeNode.mdx @@ -0,0 +1,32 @@ +--- +title: "LumaRay32KeyframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32KeyframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32KeyframeNode" +icon: "circle" +mode: wide +--- + +이 노드는 가이드 이미지를 Luma Ray 3.2 출력 비디오 타임라인의 특정 위치에 고정합니다. 이 노드를 Luma Ray 3.2 Keyframes to Video 노드의 "keyframes" 입력에 연결하고, 선택적 "keyframes" 입력을 통해 여러 키프레임을 함께 연결할 수 있습니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `image` | 출력 비디오의 선택한 순간에 배치할 가이드 이미지입니다. | IMAGE | 예 | - | +| `position` | 출력 비디오 타임라인에 이 이미지를 배치하는 방법입니다. | COMBO | 예 | "Fraction of duration (0.0-1.0)"
"Absolute time (seconds)" | +| `keyframes` | 이 키프레임과 함께 연결할 선택적 이전 키프레임입니다. | LUMA_RAY32_KEYFRAME | 아니요 | - | + +`position` 매개변수에 "Fraction of duration (0.0-1.0)"을 선택하면, 출력 비디오에서 이 이미지가 적용되는 위치를 결정하는 `fraction` 값을 지정할 수 있습니다(기본값: 0.0, 범위: 0.0~1.0, 단계: 0.01). (0.0 = 시작, 1.0 = 끝) + +`position` 매개변수에 "Absolute time (seconds)"를 선택하면, 출력 비디오 시작부터 이 이미지가 적용되는 시간(초)을 결정하는 `seconds` 값을 지정할 수 있습니다(기본값: 0.0, 범위: 0.0~10.0, 단계: 0.1). + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `keyframes` | 선택적 이전 키프레임과 결합된 새 키프레임을 포함하는 키프레임 체인입니다. | LUMA_RAY32_KEYFRAME | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32KeyframeNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `b49d879888e6e83d6937068e799ea583ed5c90284e829ac496821eea330fe9c7` diff --git a/ko/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx b/ko/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx new file mode 100644 index 000000000..6c04ec20c --- /dev/null +++ b/ko/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32KeyframesToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32KeyframesToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32KeyframesToVideoNode" +icon: "circle" +mode: wide +--- + +이 노드는 Luma Ray 3.2를 사용하여 타임라인의 특정 위치에 고정된 일련의 가이드 이미지를 보간하는 비디오를 생성합니다. Luma Ray 3.2 키프레임 노드를 사용하여 키프레임 시퀀스를 구축하고, 애니메이션을 정의하려면 최소 2개의 키프레임을 연결하십시오. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `프롬프트` | 비디오 생성을 위한 텍스트 프롬프트입니다. | STRING | 예 | 1~6000자 | +| `해상도` | 생성된 비디오의 출력 해상도입니다(기본값: "720p"). | COMBO | 예 | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `길이` | 생성된 비디오의 길이입니다(기본값: "5s"). | COMBO | 예 | `"5s"`
`"10s"` | +| `시드` | 재현성 제어를 위한 난수 생성 시드입니다. | INT | 예 | 0~4294967295 | +| `키프레임` | Luma Ray 3.2 키프레임 노드의 키프레임 시퀀스입니다(최소 2개). | LUMA_RAY32_KEYFRAME | 예 | 2~64개 키프레임 | + +**참고:** 키프레임 시퀀스는 최소 2개, 최대 64개의 키프레임을 포함해야 합니다. 각 키프레임은 타임라인에서 고유한 위치를 가져야 합니다. 키프레임 위치는 선택한 길이(5초의 경우 120프레임, 10초의 경우 240프레임)에 따라 출력 프레임 인덱스로 변환됩니다. 초 단위 모드의 키프레임 위치는 전체 비디오 길이를 초과할 수 없습니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `generation_id` | 생성된 비디오 출력입니다. | VIDEO | +| `generation_id` | 생성 요청의 고유 식별자입니다. | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32KeyframesToVideoNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `28099e5990942860a20e23cfd5c71a36b23a6264b44097ca617f8bdd06e7857a` diff --git a/ko/built-in-nodes/LumaRay32TextToVideoNode.mdx b/ko/built-in-nodes/LumaRay32TextToVideoNode.mdx new file mode 100644 index 000000000..4dea20496 --- /dev/null +++ b/ko/built-in-nodes/LumaRay32TextToVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32TextToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32TextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32TextToVideoNode" +icon: "circle" +mode: wide +--- + +이 노드는 Luma의 Ray 3.2 모델을 사용하여 텍스트 프롬프트로부터 비디오를 생성합니다. 프롬프트와 비디오 설정을 Luma API로 전송하고, 생성된 비디오와 생성 ID를 반환합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `프롬프트` | 비디오 생성을 위한 텍스트 프롬프트입니다. | STRING | 예 | 1-6000자 | +| `화면비` | 생성된 비디오의 화면 비율입니다. | STRING | 예 | `"16:9"`
`"9:16"`
`"1:1"`
`"4:3"`
`"3:4"`
`"21:9"` | +| `해상도` | 비디오의 출력 해상도입니다(기본값: "720p"). | STRING | 예 | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `길이` | 생성된 비디오의 길이입니다. | STRING | 예 | `"5s"`
`"10s"` | +| `루프` | 비디오를 끊김 없이 반복 재생되도록 합니다. 5초 길이에서만 사용 가능합니다. | BOOLEAN | 아니요 | True/False (기본값: False) | +| `시드` | 재현 가능한 생성을 위한 시드 값입니다. | INT | 아니요 | 0 ~ 2147483647 | + +**참고:** `loop` 매개변수는 `duration`이 "5s"로 설정된 경우에만 활성화할 수 있습니다. "10s" 길이를 선택하고 반복 재생을 활성화하면 노드에서 오류가 반환됩니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `generation_id` | 생성된 비디오 파일입니다. | VIDEO | +| `generation_id` | 비디오 생성 요청에 대한 고유 식별자입니다. | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32TextToVideoNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `04358a872530e5a2622bf0f148a694f2c707ce8535586d8f860bdf9911e1fa6a` diff --git a/ko/built-in-nodes/LumaRay32VideoEditNode.mdx b/ko/built-in-nodes/LumaRay32VideoEditNode.mdx new file mode 100644 index 000000000..90ed62248 --- /dev/null +++ b/ko/built-in-nodes/LumaRay32VideoEditNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32VideoEditNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32VideoEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32VideoEditNode" +icon: "circle" +mode: wide +--- + +이 노드는 Luma Ray 3.2를 사용하여 기존 비디오를 새로운 프롬프트로 다시 렌더링하며, 원본 움직임을 유지하면서 스타일 변경, 조명 변경, 요소 추가 또는 제거를 할 수 있습니다. 소스 비디오는 최대 18초까지 가능하며, 편집된 비디오는 소스의 원본 길이를 유지합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `비디오` | 편집할 소스 비디오입니다. 최대 18초까지 가능합니다. | VIDEO | 예 | - | +| `프롬프트` | 원하는 편집 내용을 설명합니다. | STRING | 예 | - | +| `해상도` | 편집된 비디오의 출력 해상도입니다. | COMBO | 예 | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `강도` | 소스를 얼마나 강하게 보존할지 또는 재구성할지를 결정합니다. "auto"는 Ray 3.2가 선택하도록 합니다. adhere_*는 소스를 가장 많이 보존하고, flex_*는 균형을 유지하며, reimagine_*는 가장 많이 변경합니다. (기본값: "auto") | COMBO | 예 | `"auto"`
`"adhere_1"`
`"adhere_2"`
`"adhere_3"`
`"flex_1"`
`"flex_2"`
`"flex_3"`
`"reimagine_1"`
`"reimagine_2"`
`"reimagine_3"` | +| `시드` | 재현성을 위한 시드 값입니다. | INT | 예 | - | + +**참고:** `prompt`는 1자에서 6000자 사이여야 합니다. 소스 비디오의 길이는 18초를 초과할 수 없습니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `generation_id` | 편집된 비디오 출력입니다. | VIDEO | +| `generation_id` | 생성 요청의 고유 식별자입니다. | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32VideoEditNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `936d9d7da3fdee9b0b468781fd470751db01f772f3c5c20582da7fb1ff85e6e6` diff --git a/ko/built-in-nodes/LumaRay32VideoReframeNode.mdx b/ko/built-in-nodes/LumaRay32VideoReframeNode.mdx new file mode 100644 index 000000000..58ceb37cc --- /dev/null +++ b/ko/built-in-nodes/LumaRay32VideoReframeNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32VideoReframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32VideoReframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32VideoReframeNode" +icon: "circle" +mode: wide +--- + +이 노드는 Luma Ray 3.2를 사용하여 기존 비디오의 화면 비율을 변경하며, 새로 노출된 캔버스 영역을 생성된 콘텐츠로 채웁니다. 원본 비디오는 최대 30초까지 가능하며, 요금은 출력 시간(초) 단위로 부과됩니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `video` | 화면 비율을 변경할 원본 비디오입니다. 최대 30초까지 가능합니다. | VIDEO | 예 | - | +| `prompt` | 새로 노출된 캔버스 영역을 어떻게 채울지 설명합니다. | STRING | 예 | - | +| `aspect_ratio` | 변경된 비디오의 대상 화면 비율입니다(기본값: "16:9"). | STRING | 예 | "16:9"
"9:16"
"1:1"
"4:3"
"3:4"
"21:9" | +| `resolution` | 변경된 비디오의 출력 해상도입니다(기본값: "720p"). | STRING | 예 | "360p"
"540p"
"720p"
"1080p" | +| `seed` | 재현 가능한 생성을 위한 시드 값입니다. | INT | 예 | - | + +**참고:** 화면 비율을 변경할 때 세로 화면 비율(`9:16` 및 `3:4`)에서는 `1080p` 해상도를 사용할 수 없습니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `generation_id` | 새로운 화면 비율과 채워진 캔버스 영역이 적용된 변경된 비디오입니다. | VIDEO | +| `generation_id` | 생성 요청에 대한 고유 식별자입니다. | STRING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32VideoReframeNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `d35ff5b63a850e4e44a40857188918ab5cde00b9159e3720a189a81807cfa7cb` diff --git a/ko/built-in-nodes/LumaReferenceNode.mdx b/ko/built-in-nodes/LumaReferenceNode.mdx index 67592aabd..ef1c3e459 100644 --- a/ko/built-in-nodes/LumaReferenceNode.mdx +++ b/ko/built-in-nodes/LumaReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaReferenceNode" icon: "circle" mode: wide --- + 이 노드는 Luma Generate Image 노드와 함께 사용하기 위해 이미지와 가중치 값을 보관합니다. 이미지 생성을 제어하기 위해 다른 Luma 노드로 전달할 수 있는 참조 체인을 생성합니다. 이 노드는 새 참조 체인을 시작하거나 기존 체인에 추가할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/LumaVideoNode.mdx b/ko/built-in-nodes/LumaVideoNode.mdx index d422dc06e..494aeae11 100644 --- a/ko/built-in-nodes/LumaVideoNode.mdx +++ b/ko/built-in-nodes/LumaVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LumaVideoNode" icon: "circle" mode: wide --- -# 개요 텍스트 프롬프트와 출력 설정을 기반으로 동기식으로 비디오를 생성합니다. 이 노드는 텍스트 설명과 다양한 생성 매개변수를 사용하여 비디오 콘텐츠를 제작하며, 생성 과정이 완료되면 최종 비디오 출력을 제공합니다. diff --git a/ko/built-in-nodes/MagnificImageRelightNode.mdx b/ko/built-in-nodes/MagnificImageRelightNode.mdx index e6c72cafa..f4a54b3cc 100644 --- a/ko/built-in-nodes/MagnificImageRelightNode.mdx +++ b/ko/built-in-nodes/MagnificImageRelightNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MagnificImageRelightNode" icon: "circle" mode: wide --- -# Magnific Image Relight 노드 Magnific Image Relight 노드는 입력 이미지의 조명을 조정합니다. 텍스트 프롬프트를 기반으로 스타일리시한 조명을 적용하거나, 선택적 참조 이미지의 조명 특성을 전송할 수 있습니다. 이 노드는 최종 출력의 밝기, 대비 및 전반적인 분위기를 미세 조정하기 위한 다양한 제어 기능을 제공합니다. diff --git a/ko/built-in-nodes/MagnificImageSkinEnhancerNode.mdx b/ko/built-in-nodes/MagnificImageSkinEnhancerNode.mdx index d146a36c6..c94670d7d 100644 --- a/ko/built-in-nodes/MagnificImageSkinEnhancerNode.mdx +++ b/ko/built-in-nodes/MagnificImageSkinEnhancerNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MagnificImageSkinEnhancerNode" icon: "circle" mode: wide --- -# Magnific Image Skin Enhancer 노드 Magnific Image Skin Enhancer 노드는 인물 이미지에 특화된 AI 처리를 적용하여 피부 외관을 개선합니다. 세 가지 고유한 모드를 제공하여 각기 다른 향상 목표를 달성할 수 있습니다: 창의적인 예술 효과를 위한 creative 모드, 원본을 보존하는 faithful 모드, 조명이나 사실감 같은 특정 개선을 위한 flexible 모드입니다. 이 노드는 이미지를 외부 API에 업로드하여 처리한 후 향상된 결과를 반환합니다. diff --git a/ko/built-in-nodes/MagnificImageStyleTransferNode.mdx b/ko/built-in-nodes/MagnificImageStyleTransferNode.mdx index e485d26d0..582965f8b 100644 --- a/ko/built-in-nodes/MagnificImageStyleTransferNode.mdx +++ b/ko/built-in-nodes/MagnificImageStyleTransferNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageStyleTransferNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageStyleTransferNode/en.md) 이 노드는 참조 이미지의 시각적 스타일을 입력 이미지에 적용합니다. 외부 AI 서비스를 사용하여 이미지를 처리하며, 스타일 전이의 강도와 원본 이미지 구조 보존 정도를 제어할 수 있습니다. diff --git a/ko/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx b/ko/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx index cd08b44c7..8d71f3a9c 100644 --- a/ko/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx +++ b/ko/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageUpscalerCreativeNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MagnificImageUpscalerCreativeNode/en.md) 이 노드는 Magnific AI 서비스를 사용하여 이미지를 업스케일하고 창의적으로 향상시킵니다. 텍스트 프롬프트로 향상 과정을 안내하고, 최적화할 특정 스타일을 선택하며, 디테일, 원본 유사성, 양식화 강도 등 창의적 프로세스의 다양한 측면을 제어할 수 있습니다. 이 노드는 선택한 배율(2배, 4배, 8배 또는 16배)로 업스케일된 이미지를 출력하며, 최대 출력 크기는 25.3 메가픽셀입니다. diff --git a/ko/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx b/ko/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx index e16b8f4f1..845c6fa7e 100644 --- a/ko/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx +++ b/ko/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MagnificImageUpscalerPreciseV2Node" icon: "circle" mode: wide --- -# Magnific 이미지 업스케일(정밀 V2) 노드 Magnific 이미지 업스케일(정밀 V2) 노드는 선명도, 입자 및 디테일 향상을 정밀하게 제어하여 고충실도 이미지 업스케일링을 수행합니다. 외부 API를 통해 이미지를 처리하며, 최대 10060×10060 픽셀의 출력 해상도를 지원합니다. 이 노드는 다양한 처리 스타일을 제공하며, 요청된 출력이 최대 허용 크기를 초과할 경우 입력을 자동으로 다운스케일할 수 있습니다. diff --git a/ko/built-in-nodes/Mahiro.mdx b/ko/built-in-nodes/Mahiro.mdx index 3c9447b27..93a265edf 100644 --- a/ko/built-in-nodes/Mahiro.mdx +++ b/ko/built-in-nodes/Mahiro.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Mahiro" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Mahiro/en.md) Mahiro 노드는 긍정 프롬프트와 부정 프롬프트 간의 차이보다 긍정 프롬프트의 방향에 더 집중하도록 안내 함수를 수정합니다. 정규화된 조건부 및 무조건부 노이즈 제거 출력 간의 코사인 유사도를 사용하여 사용자 지정 안내 스케일링 방식을 적용하는 패치된 모델을 생성합니다. 이 실험적인 노드는 생성 과정을 긍정 프롬프트가 의도한 방향으로 더 강력하게 유도하는 데 도움을 줍니다. @@ -19,7 +20,7 @@ Mahiro 노드는 긍정 프롬프트와 부정 프롬프트 간의 차이보다 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `patched_model` | Mahiro 안내 함수가 적용된 수정된 모델 | MODEL | +| `변경된 모델` | Mahiro 안내 함수가 적용된 수정된 모델 | MODEL | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Mahiro/ko.md) diff --git a/ko/built-in-nodes/MakeTrainingDataset.mdx b/ko/built-in-nodes/MakeTrainingDataset.mdx index 92e242ca9..28e71c1f0 100644 --- a/ko/built-in-nodes/MakeTrainingDataset.mdx +++ b/ko/built-in-nodes/MakeTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MakeTrainingDataset" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MakeTrainingDataset/en.md) 이 노드는 이미지와 텍스트를 인코딩하여 학습 데이터를 준비합니다. 이미지 목록과 이에 대응하는 텍스트 캡션 목록을 입력받은 후, VAE 모델을 사용하여 이미지를 잠재 표현(latent representation)으로 변환하고 CLIP 모델을 사용하여 텍스트를 컨디셔닝 데이터로 변환합니다. 그 결과로 생성된 쌍을 이루는 잠재 표현과 컨디셔닝이 목록 형태로 출력되어 학습 워크플로우에서 바로 사용할 수 있습니다. @@ -26,7 +27,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `conditioning` | 잠재 표현 딕셔너리 목록입니다. | LATENT | +| `latents` | 잠재 표현 딕셔너리 목록입니다. | LATENT | | `conditioning` | 컨디셔닝 목록의 목록입니다. | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MakeTrainingDataset/ko.md) diff --git a/ko/built-in-nodes/ManualSigmas.mdx b/ko/built-in-nodes/ManualSigmas.mdx index 629aa869e..6894ff340 100644 --- a/ko/built-in-nodes/ManualSigmas.mdx +++ b/ko/built-in-nodes/ManualSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ManualSigmas" icon: "circle" mode: wide --- + **ManualSigmas 노드** ManualSigmas 노드를 사용하면 샘플링 과정에 사용할 노이즈 수준(시그마)의 사용자 지정 시퀀스를 수동으로 정의할 수 있습니다. 문자열 형태의 숫자 목록을 입력하면 노드가 이를 텐서로 변환하여 다른 샘플링 노드에서 사용할 수 있도록 합니다. 이는 특정 노이즈 스케줄을 테스트하거나 생성할 때 유용합니다. diff --git a/ko/built-in-nodes/MarkdownNote.mdx b/ko/built-in-nodes/MarkdownNote.mdx index 86fa304e2..1ba633ab5 100644 --- a/ko/built-in-nodes/MarkdownNote.mdx +++ b/ko/built-in-nodes/MarkdownNote.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MarkdownNote" icon: "circle" mode: wide --- -# ## 개요 워크플로우에 주석을 추가하는 노드입니다. Markdown 구문을 사용한 텍스트 서식을 지원합니다. diff --git a/ko/built-in-nodes/MaskComposite.mdx b/ko/built-in-nodes/MaskComposite.mdx index 232384082..8e0739cd5 100644 --- a/ko/built-in-nodes/MaskComposite.mdx +++ b/ko/built-in-nodes/MaskComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskComposite" icon: "circle" mode: wide --- + 이 노드는 덧셈, 뺄셈, 논리 연산 등 다양한 연산을 통해 두 개의 마스크 입력을 결합하여 새롭고 수정된 마스크를 생성하는 데 특화되어 있습니다. 복잡한 마스킹 효과를 얻기 위해 마스크 데이터 조작을 추상적으로 처리하며, 마스크 기반 이미지 편집 및 처리 워크플로우에서 중요한 구성 요소로 기능합니다. ## 입력 diff --git a/ko/built-in-nodes/MaskPreview.mdx b/ko/built-in-nodes/MaskPreview.mdx index d794ca7d1..5069cd252 100644 --- a/ko/built-in-nodes/MaskPreview.mdx +++ b/ko/built-in-nodes/MaskPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskPreview" icon: "circle" mode: wide --- + MaskPreview 노드는 마스크 데이터를 미리보기 이미지로 저장하여 ComfyUI 출력 디렉터리에 보관함으로써, 워크플로우 실행 중에 마스크 데이터를 시각적으로 확인할 수 있도록 합니다. 입력된 마스크를 이미지 표시에 적합한 형식으로 변환하고, 설정 가능한 파일 이름 접두사를 사용하여 저장합니다. ## 입력 diff --git a/ko/built-in-nodes/MaskToImage.mdx b/ko/built-in-nodes/MaskToImage.mdx index 573d785f5..68b0093ab 100644 --- a/ko/built-in-nodes/MaskToImage.mdx +++ b/ko/built-in-nodes/MaskToImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskToImage" icon: "circle" mode: wide --- + `MaskToImage` 노드는 마스크를 이미지 형식으로 변환하도록 설계되었습니다. 이 변환을 통해 마스크를 이미지로 시각화하고 추가로 처리할 수 있으며, 마스크 기반 작업과 이미지 기반 애플리케이션 간의 연결을 용이하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/MediaPipeFaceLandmarker.mdx b/ko/built-in-nodes/MediaPipeFaceLandmarker.mdx index ce2fb802e..433f538e3 100644 --- a/ko/built-in-nodes/MediaPipeFaceLandmarker.mdx +++ b/ko/built-in-nodes/MediaPipeFaceLandmarker.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceLandmarker" icon: "circle" mode: wide --- + ## 개요 이미지에서 얼굴을 감지하고 MediaPipe의 BlazeFace 및 FaceMesh 모델을 사용하여 각 얼굴의 468개 얼굴 랜드마크(주요 지점)를 식별합니다. 또한 표정 분석을 위한 ARKit-52 블렌드셰이프 계수를 계산합니다. 이 노드는 배치로 여러 이미지를 처리할 수 있으며, 감지된 각 얼굴에 대한 랜드마크 데이터와 경계 상자를 모두 출력합니다. @@ -24,7 +25,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `bboxes` | 프레임별 얼굴 감지 결과를 포함하는 구조화된 출력으로, 468개 얼굴 랜드마크, ARKit-52 블렌드셰이프 계수, 변환 행렬 및 메시 시각화를 위한 연결 집합을 포함합니다. | FACE_LANDMARKS | +| `face_landmarks` | 프레임별 얼굴 감지 결과를 포함하는 구조화된 출력으로, 468개 얼굴 랜드마크, ARKit-52 블렌드셰이프 계수, 변환 행렬 및 메시 시각화를 위한 연결 집합을 포함합니다. | FACE_LANDMARKS | | `bboxes` | 감지된 각 얼굴의 경계 상자 목록으로, 좌표(x, y, 너비, 높이), 레이블 "face" 및 신뢰도 점수를 포함합니다. 입력 프레임당 하나의 목록입니다. | BOUNDING_BOX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MediaPipeFaceLandmarker/ko.md) diff --git a/ko/built-in-nodes/MediaPipeFaceMask.mdx b/ko/built-in-nodes/MediaPipeFaceMask.mdx index e2c012e77..6c8100b94 100644 --- a/ko/built-in-nodes/MediaPipeFaceMask.mdx +++ b/ko/built-in-nodes/MediaPipeFaceMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceMask" icon: "circle" mode: wide --- + ## 개요 이 노드는 MediaPipe가 감지한 얼굴 랜드마크를 기반으로 이진 마스크(흑백 이미지)를 생성합니다. 감지된 각 얼굴 영역에 대해 채워진 다각형 모양을 그리며, 배치 내 각 프레임당 하나의 마스크를 생성합니다. 동일한 프레임에서 여러 얼굴이 감지되면 해당 마스크들이 하나의 마스크로 결합됩니다. diff --git a/ko/built-in-nodes/MediaPipeFaceMeshVisualize.mdx b/ko/built-in-nodes/MediaPipeFaceMeshVisualize.mdx index a1b81d56e..719115da1 100644 --- a/ko/built-in-nodes/MediaPipeFaceMeshVisualize.mdx +++ b/ko/built-in-nodes/MediaPipeFaceMeshVisualize.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MediaPipeFaceMeshVisualize" icon: "circle" mode: wide --- -# MediaPipe 얼굴 메시 시각화 ## 개요 diff --git a/ko/built-in-nodes/MergeImageLists.mdx b/ko/built-in-nodes/MergeImageLists.mdx index e55f8e049..c5af229da 100644 --- a/ko/built-in-nodes/MergeImageLists.mdx +++ b/ko/built-in-nodes/MergeImageLists.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MergeImageLists" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MergeImageLists/en.md) 이미지 리스트 병합 노드는 여러 개별 이미지 리스트를 하나의 연속된 리스트로 결합합니다. 각 연결된 입력에서 모든 이미지를 가져와 수신된 순서대로 차례로 추가하는 방식으로 작동합니다. 이는 다양한 소스의 이미지를 추가 처리하기 위해 구성하거나 일괄 처리할 때 유용합니다. diff --git a/ko/built-in-nodes/MergeSplat.mdx b/ko/built-in-nodes/MergeSplat.mdx index ab5142857..5adbf9275 100644 --- a/ko/built-in-nodes/MergeSplat.mdx +++ b/ko/built-in-nodes/MergeSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MergeSplat" icon: "circle" mode: wide --- -# 병합 스플랫 Merge Splats 노드는 여러 가우시안 스플랫 모델을 데이터를 연결하여 단일 스플랫으로 결합합니다. 이는 동일한 잠재 변수(latent)를 다른 시드(seed)로 생성한 여러 디코드 결과를 병합할 때 유용하며, 표면을 더 조밀하게 만들고 3D 메시 생성 시 품질을 향상시킬 수 있습니다. diff --git a/ko/built-in-nodes/MergeTextLists.mdx b/ko/built-in-nodes/MergeTextLists.mdx index c7b037c28..255c1061b 100644 --- a/ko/built-in-nodes/MergeTextLists.mdx +++ b/ko/built-in-nodes/MergeTextLists.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MergeTextLists" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MergeTextLists/en.md) 이 노드는 여러 텍스트 목록을 하나의 결합된 목록으로 병합합니다. 텍스트 입력을 목록 형태로 받아 연결하도록 설계되었습니다. 노드는 병합된 목록의 총 텍스트 개수를 기록합니다. diff --git a/ko/built-in-nodes/MeshyAnimateModelNode.mdx b/ko/built-in-nodes/MeshyAnimateModelNode.mdx index 68b0d526b..6c9627249 100644 --- a/ko/built-in-nodes/MeshyAnimateModelNode.mdx +++ b/ko/built-in-nodes/MeshyAnimateModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyAnimateModelNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyAnimateModelNode/en.md) 이 노드는 Meshy 서비스를 사용하여 이미 리깅된 3D 캐릭터 모델에 특정 애니메이션을 적용합니다. 이전 리깅 작업의 작업 ID와 라이브러리에서 원하는 애니메이션을 선택하기 위한 액션 ID를 입력받습니다. 그런 다음 노드는 요청을 처리하고 애니메이션된 모델을 GLB 및 FBX 파일 형식으로 반환합니다. @@ -20,8 +21,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `GLB` | 애니메이션된 모델의 문자열 식별자입니다. 이 출력은 이전 버전과의 호환성을 위해서만 제공됩니다. | STRING | -| `FBX` | GLB 형식의 애니메이션된 3D 모델 파일입니다. | FILE3DGLB | +| `model_file` | 애니메이션된 모델의 문자열 식별자입니다. 이 출력은 이전 버전과의 호환성을 위해서만 제공됩니다. | STRING | +| `GLB` | GLB 형식의 애니메이션된 3D 모델 파일입니다. | FILE3DGLB | | `FBX` | FBX 형식의 애니메이션된 3D 모델 파일입니다. | FILE3DFBX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyAnimateModelNode/ko.md) diff --git a/ko/built-in-nodes/MeshyImageToModelNode.mdx b/ko/built-in-nodes/MeshyImageToModelNode.mdx index f4295b24c..d15c88f63 100644 --- a/ko/built-in-nodes/MeshyImageToModelNode.mdx +++ b/ko/built-in-nodes/MeshyImageToModelNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MeshyImageToModelNode" icon: "circle" mode: wide --- -# Meshy: 이미지-모델 노드 Meshy: 이미지-모델 노드는 Meshy API를 사용하여 단일 입력 이미지로부터 3D 모델을 생성합니다. 이미지를 업로드하고 처리 작업을 제출한 후, 생성된 3D 모델 파일(GLB 및 FBX)과 참조용 작업 ID를 반환합니다. @@ -36,9 +35,9 @@ Meshy: 이미지-모델 노드는 Meshy API를 사용하여 단일 입력 이미 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `meshy_task_id` | 생성된 GLB 모델의 파일 이름입니다. (하위 호환성을 위해 유지됩니다). | STRING | -| `GLB` | Meshy API 작업의 고유 식별자로, 참조 또는 문제 해결에 사용할 수 있습니다. | MESHY_TASK_ID | -| `FBX` | GLB 파일 형식으로 생성된 3D 모델입니다. | FILE3DGLB | +| `model_file` | 생성된 GLB 모델의 파일 이름입니다. (하위 호환성을 위해 유지됩니다). | STRING | +| `meshy_task_id` | Meshy API 작업의 고유 식별자로, 참조 또는 문제 해결에 사용할 수 있습니다. | MESHY_TASK_ID | +| `GLB` | GLB 파일 형식으로 생성된 3D 모델입니다. | FILE3DGLB | | `FBX` | FBX 파일 형식으로 생성된 3D 모델입니다. | FILE3DFBX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyImageToModelNode/ko.md) diff --git a/ko/built-in-nodes/MeshyMultiImageToModelNode.mdx b/ko/built-in-nodes/MeshyMultiImageToModelNode.mdx index 79d9c4964..5373889eb 100644 --- a/ko/built-in-nodes/MeshyMultiImageToModelNode.mdx +++ b/ko/built-in-nodes/MeshyMultiImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyMultiImageToModelNode" icon: "circle" mode: wide --- + 이 노드는 Meshy API를 사용하여 여러 입력 이미지로부터 3D 모델을 생성합니다. 제공된 이미지를 업로드하고 처리 작업을 제출한 후, 결과 3D 모델 파일(GLB 및 FBX)과 참조용 작업 ID를 반환합니다. ## 입력 @@ -35,9 +36,9 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `meshy_task_id` | 생성된 GLB 모델의 파일 이름입니다. 이 출력은 하위 호환성을 위해 제공됩니다. | STRING | -| `GLB` | Meshy API 작업의 고유 식별자입니다. | MESHY_TASK_ID | -| `FBX` | GLB 형식으로 생성된 3D 모델입니다. | FILE3DGLB | +| `model_file` | 생성된 GLB 모델의 파일 이름입니다. 이 출력은 하위 호환성을 위해 제공됩니다. | STRING | +| `meshy_task_id` | Meshy API 작업의 고유 식별자입니다. | MESHY_TASK_ID | +| `GLB` | GLB 형식으로 생성된 3D 모델입니다. | FILE3DGLB | | `FBX` | FBX 형식으로 생성된 3D 모델입니다. | FILE3DFBX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyMultiImageToModelNode/ko.md) diff --git a/ko/built-in-nodes/MeshyRefineNode.mdx b/ko/built-in-nodes/MeshyRefineNode.mdx index 7a873d985..09092716d 100644 --- a/ko/built-in-nodes/MeshyRefineNode.mdx +++ b/ko/built-in-nodes/MeshyRefineNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MeshyRefineNode" icon: "circle" mode: wide --- -# Meshy: 정제 초안 모델 노드 Meshy: 정제 초안 모델 노드는 이전에 생성된 3D 초안 모델을 가져와 품질을 개선하고 선택적으로 텍스처를 추가합니다. Meshy API에 정제 작업을 제출하고 처리가 완료되면 최종 3D 모델 파일을 반환합니다. @@ -25,9 +24,9 @@ Meshy: 정제 초안 모델 노드는 이전에 생성된 3D 초안 모델을 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `meshy_task_id` | 생성된 GLB 모델의 파일 이름입니다. (하위 호환성 전용) | STRING | -| `GLB` | 제출된 정제 작업의 고유 작업 ID입니다. | MESHY_TASK_ID | -| `FBX` | GLB 형식의 최종 정제된 3D 모델입니다. | FILE3DGLB | +| `model_file` | 생성된 GLB 모델의 파일 이름입니다. (하위 호환성 전용) | STRING | +| `meshy_task_id` | 제출된 정제 작업의 고유 작업 ID입니다. | MESHY_TASK_ID | +| `GLB` | GLB 형식의 최종 정제된 3D 모델입니다. | FILE3DGLB | | `FBX` | FBX 형식의 최종 정제된 3D 모델입니다. | FILE3DFBX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRefineNode/ko.md) diff --git a/ko/built-in-nodes/MeshyRigModelNode.mdx b/ko/built-in-nodes/MeshyRigModelNode.mdx index 92aa0cb2e..24f4d7811 100644 --- a/ko/built-in-nodes/MeshyRigModelNode.mdx +++ b/ko/built-in-nodes/MeshyRigModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyRigModelNode" icon: "circle" mode: wide --- + Meshy: Rig Model 노드는 이전 Meshy 작업의 3D 모델을 가져와 자동으로 스켈레톤을 생성하여 포즈와 애니메이션을 적용할 수 있는 리깅된 캐릭터를 만듭니다. 이 노드는 리깅된 모델을 GLB 및 FBX 파일 형식으로 출력합니다. ## 입력 @@ -21,9 +22,9 @@ Meshy: Rig Model 노드는 이전 Meshy 작업의 3D 모델을 가져와 자동 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `rig_task_id` | 이전 버전과의 호환성을 위한 레거시 출력으로, GLB 모델의 파일 이름을 포함합니다. | STRING | -| `GLB` | 이 리깅 작업의 고유 작업 ID로, 결과를 참조하는 데 사용할 수 있습니다. | STRING | -| `FBX` | GLB 파일 형식으로 저장된 리깅된 3D 캐릭터 모델입니다. | FILE3DGLB | +| `model_file` | 이전 버전과의 호환성을 위한 레거시 출력으로, GLB 모델의 파일 이름을 포함합니다. | STRING | +| `rig_task_id` | 이 리깅 작업의 고유 작업 ID로, 결과를 참조하는 데 사용할 수 있습니다. | STRING | +| `GLB` | GLB 파일 형식으로 저장된 리깅된 3D 캐릭터 모델입니다. | FILE3DGLB | | `FBX` | FBX 파일 형식으로 저장된 리깅된 3D 캐릭터 모델입니다. | FILE3DFBX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRigModelNode/ko.md) diff --git a/ko/built-in-nodes/MeshyTextToModelNode.mdx b/ko/built-in-nodes/MeshyTextToModelNode.mdx index 52f7760c7..f968960ed 100644 --- a/ko/built-in-nodes/MeshyTextToModelNode.mdx +++ b/ko/built-in-nodes/MeshyTextToModelNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MeshyTextToModelNode" icon: "circle" mode: wide --- -# Meshy: 텍스트-모델 노드 Meshy: 텍스트-모델 노드는 Meshy API를 사용하여 텍스트 설명으로부터 3D 모델을 생성합니다. 프롬프트와 설정을 포함한 요청을 API에 전송한 후, 생성이 완료될 때까지 대기하고 결과 모델 파일을 다운로드합니다. @@ -29,9 +28,9 @@ Meshy: 텍스트-모델 노드는 Meshy API를 사용하여 텍스트 설명으 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `meshy_task_id` | 생성된 GLB 모델의 파일 이름입니다. 이 출력은 하위 호환성을 위해 제공됩니다. | STRING | -| `GLB` | Meshy API 작업의 고유 식별자입니다. | MESHY_TASK_ID | -| `FBX` | GLB 형식의 생성된 3D 모델 파일입니다. | FILE3DGLB | +| `모델 파일` | 생성된 GLB 모델의 파일 이름입니다. 이 출력은 하위 호환성을 위해 제공됩니다. | STRING | +| `meshy_task_id` | Meshy API 작업의 고유 식별자입니다. | MESHY_TASK_ID | +| `GLB` | GLB 형식의 생성된 3D 모델 파일입니다. | FILE3DGLB | | `FBX` | FBX 형식의 생성된 3D 모델 파일입니다. | FILE3DFBX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextToModelNode/ko.md) diff --git a/ko/built-in-nodes/MeshyTextureNode.mdx b/ko/built-in-nodes/MeshyTextureNode.mdx index c7b22a19f..ec984728e 100644 --- a/ko/built-in-nodes/MeshyTextureNode.mdx +++ b/ko/built-in-nodes/MeshyTextureNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MeshyTextureNode" icon: "circle" mode: wide --- -# Meshy: 텍스처 노드 Meshy: 텍스처 노드는 AI로 생성된 텍스처를 3D 모델에 적용합니다. 이전 Meshy 3D 생성 또는 변환 노드의 작업 ID를 받아 텍스트 설명이나 참조 이미지를 사용하여 모델에 새로운 텍스처를 생성합니다. 이 노드는 텍스처가 적용된 모델을 GLB 및 FBX 파일 형식으로 출력합니다. @@ -29,9 +28,9 @@ Meshy: 텍스처 노드는 AI로 생성된 텍스처를 3D 모델에 적용합 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `meshy_task_id` | 생성된 GLB 모델의 파일 이름입니다. 이 출력은 하위 호환성을 위해 제공됩니다. | STRING | -| `GLB` | 이 텍스처링 작업의 고유 작업 식별자로, 결과를 참조하는 데 사용할 수 있습니다. | MODEL_TASK_ID | -| `FBX` | GLB 파일 형식으로 저장된 텍스처가 적용된 3D 모델입니다. | FILE3DGLB | +| `모델 파일` | 생성된 GLB 모델의 파일 이름입니다. 이 출력은 하위 호환성을 위해 제공됩니다. | STRING | +| `meshy_task_id` | 이 텍스처링 작업의 고유 작업 식별자로, 결과를 참조하는 데 사용할 수 있습니다. | MODEL_TASK_ID | +| `GLB` | GLB 파일 형식으로 저장된 텍스처가 적용된 3D 모델입니다. | FILE3DGLB | | `FBX` | FBX 파일 형식으로 저장된 텍스처가 적용된 3D 모델입니다. | FILE3DFBX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextureNode/ko.md) diff --git a/ko/built-in-nodes/MinimaxHailuoVideoNode.mdx b/ko/built-in-nodes/MinimaxHailuoVideoNode.mdx index 4a29730f2..d6fa9d9b8 100644 --- a/ko/built-in-nodes/MinimaxHailuoVideoNode.mdx +++ b/ko/built-in-nodes/MinimaxHailuoVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxHailuoVideoNode" icon: "circle" mode: wide --- + 다음은 ComfyUI 노드 문서의 한국어 번역입니다. ## 개요 diff --git a/ko/built-in-nodes/MinimaxImageToVideoNode.mdx b/ko/built-in-nodes/MinimaxImageToVideoNode.mdx index 3750faaab..59be781ef 100644 --- a/ko/built-in-nodes/MinimaxImageToVideoNode.mdx +++ b/ko/built-in-nodes/MinimaxImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxImageToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxImageToVideoNode/en.md) MiniMax의 API를 사용하여 이미지, 프롬프트 및 선택적 매개변수를 기반으로 동영상을 동기식으로 생성합니다. 이 노드는 입력 이미지와 텍스트 설명을 사용하여 비디오 시퀀스를 생성하며, 다양한 모델 옵션과 구성 설정을 제공합니다. diff --git a/ko/built-in-nodes/MinimaxSubjectToVideoNode.mdx b/ko/built-in-nodes/MinimaxSubjectToVideoNode.mdx index fe8c9d0f2..e135f535e 100644 --- a/ko/built-in-nodes/MinimaxSubjectToVideoNode.mdx +++ b/ko/built-in-nodes/MinimaxSubjectToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxSubjectToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxSubjectToVideoNode/en.md) MiniMax의 API를 사용하여 대상 이미지와 텍스트 프롬프트를 기반으로 동영상을 동기식으로 생성합니다. 이 노드는 대상 이미지와 설명을 입력받아 프롬프트에 따라 해당 대상을 애니메이션화하거나 특징으로 하는 동영상을 만듭니다. diff --git a/ko/built-in-nodes/MinimaxTextToVideoNode.mdx b/ko/built-in-nodes/MinimaxTextToVideoNode.mdx index faa589aef..23bb20c00 100644 --- a/ko/built-in-nodes/MinimaxTextToVideoNode.mdx +++ b/ko/built-in-nodes/MinimaxTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxTextToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxTextToVideoNode/en.md) 프롬프트와 선택적 매개변수를 기반으로 MiniMax의 API를 사용하여 동기식으로 비디오를 생성합니다. 이 노드는 MiniMax의 텍스트-비디오 서비스에 연결하여 텍스트 설명으로부터 비디오 콘텐츠를 만듭니다. diff --git a/ko/built-in-nodes/MoGeInference.mdx b/ko/built-in-nodes/MoGeInference.mdx index e06cae9d5..bca9b418a 100644 --- a/ko/built-in-nodes/MoGeInference.mdx +++ b/ko/built-in-nodes/MoGeInference.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoGeInference" icon: "circle" mode: wide --- -# 개요 단일 이미지에 MoGe를 실행하여 깊이와 형상을 추정합니다. 이 노드는 MoGe 모델을 통해 입력 이미지를 처리하여 3D 포인트 클라우드, 깊이 맵, 카메라 내부 파라미터, 마스크 및 표면 법선을 생성합니다. diff --git a/ko/built-in-nodes/MoGePanoramaInference.mdx b/ko/built-in-nodes/MoGePanoramaInference.mdx index d60a1a260..80e973767 100644 --- a/ko/built-in-nodes/MoGePanoramaInference.mdx +++ b/ko/built-in-nodes/MoGePanoramaInference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGePanoramaInference" icon: "circle" mode: wide --- + ## 개요 이 노드는 정구형 파노라마 이미지에 대한 깊이 추정을 수행합니다. 파노라마를 12개의 원근 뷰로 분할하고, 각 뷰에 대해 MoGe 깊이 추정 모델을 실행한 후, 결과를 다시 원본 파노라마에 대한 단일 완전한 깊이 맵으로 병합하는 방식으로 작동합니다. diff --git a/ko/built-in-nodes/MoGePointMapToMesh.mdx b/ko/built-in-nodes/MoGePointMapToMesh.mdx index 431af8b69..e8c14f93d 100644 --- a/ko/built-in-nodes/MoGePointMapToMesh.mdx +++ b/ko/built-in-nodes/MoGePointMapToMesh.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGePointMapToMesh" icon: "circle" mode: wide --- + ## 개요 이 노드는 MoGe 포인트 맵을 3D 메시로 변환합니다. MoGe 깊이 추정 노드에서 생성된 형상 데이터를 가져와 UV 좌표와 선택적 텍스처가 포함된 메시로 삼각 측량합니다. diff --git a/ko/built-in-nodes/MoGeRender.mdx b/ko/built-in-nodes/MoGeRender.mdx index d7b5034f8..0f1879a1c 100644 --- a/ko/built-in-nodes/MoGeRender.mdx +++ b/ko/built-in-nodes/MoGeRender.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoGeRender" icon: "circle" mode: wide --- -# 개요 이 노드는 MOGE_GEOMETRY 패킷(MoGe 깊이/법선 추정 노드에서 생성됨)을 받아 표준 이미지 형식으로 렌더링합니다. 깊이 맵, 컬러 깊이 맵, 법선 맵 또는 마스크 중에서 출력을 선택할 수 있습니다. diff --git a/ko/built-in-nodes/ModelComputeDtype.mdx b/ko/built-in-nodes/ModelComputeDtype.mdx index 8de4c756f..ea9db9868 100644 --- a/ko/built-in-nodes/ModelComputeDtype.mdx +++ b/ko/built-in-nodes/ModelComputeDtype.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelComputeDtype" icon: "circle" mode: wide --- + ModelComputeDtype 노드는 모델 처리 중 사용되는 연산 데이터 타입(정밀도)을 변경합니다. 입력 모델의 복사본을 생성하고 선택한 정밀도 설정을 적용하여, 하드웨어에 따라 메모리 사용량과 성능을 최적화하는 데 도움을 줍니다. 다양한 정밀도 구성을 디버깅하고 테스트하는 데 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeAdd.mdx b/ko/built-in-nodes/ModelMergeAdd.mdx index 96963c816..33e4dc82f 100644 --- a/ko/built-in-nodes/ModelMergeAdd.mdx +++ b/ko/built-in-nodes/ModelMergeAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeAdd" icon: "circle" mode: wide --- + ## 개요 ModelMergeAdd 노드는 한 모델의 주요 패치를 다른 모델에 추가하여 두 모델을 병합하도록 설계되었습니다. 이 과정은 첫 번째 모델을 복제한 후 두 번째 모델의 패치를 적용하여, 두 모델의 특징이나 동작을 결합할 수 있도록 합니다. diff --git a/ko/built-in-nodes/ModelMergeAuraflow.mdx b/ko/built-in-nodes/ModelMergeAuraflow.mdx index 07cbd38b0..bbb9ef068 100644 --- a/ko/built-in-nodes/ModelMergeAuraflow.mdx +++ b/ko/built-in-nodes/ModelMergeAuraflow.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeAuraflow" icon: "circle" mode: wide --- + ModelMergeAuraflow 노드는 두 개의 서로 다른 모델을 혼합하여 다양한 모델 구성 요소에 대한 특정 혼합 가중치를 조정할 수 있도록 합니다. 초기 레이어부터 최종 출력까지 모델의 여러 부분이 병합되는 방식을 세밀하게 제어할 수 있습니다. 이 노드는 병합 과정을 정밀하게 제어하여 사용자 정의 모델 조합을 생성할 때 특히 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeBlocks.mdx b/ko/built-in-nodes/ModelMergeBlocks.mdx index c9ca858ae..20ad20374 100644 --- a/ko/built-in-nodes/ModelMergeBlocks.mdx +++ b/ko/built-in-nodes/ModelMergeBlocks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeBlocks" icon: "circle" mode: wide --- + ModelMergeBlocks는 고급 모델 병합 작업을 위해 설계된 노드로, 두 모델의 서로 다른 부분에 대해 사용자 지정 혼합 비율을 적용하여 통합할 수 있도록 합니다. 이 노드는 지정된 매개변수에 따라 두 소스 모델의 구성 요소를 선택적으로 병합하여 하이브리드 모델을 생성하는 기능을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeCosmos14B.mdx b/ko/built-in-nodes/ModelMergeCosmos14B.mdx index bd82cb053..aa81b454b 100644 --- a/ko/built-in-nodes/ModelMergeCosmos14B.mdx +++ b/ko/built-in-nodes/ModelMergeCosmos14B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmos14B" icon: "circle" mode: wide --- + **ModelMergeCosmos14B** 노드는 Cosmos 14B 모델 아키텍처를 위해 특별히 설계된 블록 기반 방식을 사용하여 두 개의 AI 모델을 병합합니다. 각 모델 블록 및 임베딩 레이어에 대해 0.0에서 1.0 사이의 가중치 값을 조정하여 모델의 서로 다른 구성 요소를 혼합할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeCosmos7B.mdx b/ko/built-in-nodes/ModelMergeCosmos7B.mdx index 70b2e017b..47e5928e4 100644 --- a/ko/built-in-nodes/ModelMergeCosmos7B.mdx +++ b/ko/built-in-nodes/ModelMergeCosmos7B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmos7B" icon: "circle" mode: wide --- + ModelMergeCosmos7B 노드는 두 개의 AI 모델을 특정 구성 요소의 가중치 혼합을 사용하여 병합합니다. 위치 임베딩, 트랜스포머 블록 및 최종 레이어에 대한 개별 가중치를 조정하여 모델의 서로 다른 부분이 결합되는 방식을 세밀하게 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx b/ko/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx index 0f94bbc5e..2172d6b3d 100644 --- a/ko/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx +++ b/ko/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmosPredict2_14B" icon: "circle" mode: wide --- + ModelMergeCosmosPredict2_14B 노드는 두 개의 AI 모델의 내부 구성 요소를 혼합하여 병합합니다. 이 노드는 특정 레이어와 구성 요소에 대해 조정 가능한 가중치 값을 사용하여 두 번째 모델의 각 부분이 최종 병합 결과에 미치는 영향을 정밀하게 제어할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx b/ko/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx index 2df5d3b50..1fb444087 100644 --- a/ko/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx +++ b/ko/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmosPredict2_2B" icon: "circle" mode: wide --- + ModelMergeCosmosPredict2_2B 노드는 블록 기반 접근 방식을 사용하여 두 개의 확산 모델을 병합하며, 다양한 모델 구성 요소에 대해 세밀한 제어를 제공합니다. 위치 임베더, 시간 임베더, 트랜스포머 블록 및 최종 레이어에 대한 보간 가중치를 조정하여 두 모델의 특정 부분을 혼합할 수 있습니다. 이를 통해 각 모델의 서로 다른 아키텍처 구성 요소가 최종 병합 결과에 기여하는 방식을 정밀하게 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeFlux1.mdx b/ko/built-in-nodes/ModelMergeFlux1.mdx index 958ccdf55..c18262ee5 100644 --- a/ko/built-in-nodes/ModelMergeFlux1.mdx +++ b/ko/built-in-nodes/ModelMergeFlux1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeFlux1" icon: "circle" mode: wide --- + ModelMergeFlux1 노드는 가중치 보간법을 사용하여 두 확산 모델의 구성 요소를 혼합하여 병합합니다. 이미지 처리 블록, 시간 임베딩 레이어, 안내 메커니즘, 벡터 입력, 텍스트 인코더 및 다양한 트랜스포머 블록을 포함하여 모델의 서로 다른 부분이 결합되는 방식을 세밀하게 제어할 수 있습니다. 이를 통해 두 소스 모델의 특성을 사용자 지정하여 하이브리드 모델을 생성할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeKrea2.mdx b/ko/built-in-nodes/ModelMergeKrea2.mdx new file mode 100644 index 000000000..d8d209924 --- /dev/null +++ b/ko/built-in-nodes/ModelMergeKrea2.mdx @@ -0,0 +1,40 @@ +--- +title: "ModelMergeKrea2 - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ModelMergeKrea2 node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ModelMergeKrea2" +icon: "circle" +mode: wide +--- + +이 노드는 두 모델의 내부 구성 요소를 세밀한 수준에서 혼합하여 병합하며, 각 모델의 특정 부분이 최종 결과에 영향을 미치는 정도를 제어할 수 있도록 합니다. 두 입력 모델을 가져와 아키텍처의 서로 다른 섹션에 별도의 혼합 비율을 적용하는 방식으로 작동합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `model1` | 병합할 첫 번째 모델 | MODEL | 예 | - | +| `model2` | 병합할 두 번째 모델 | MODEL | 예 | - | +| `first.` | 첫 번째 레이어 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `tmlp.` | 시간 MLP 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `txtmlp.` | 텍스트 MLP 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `tproj.` | 시간 투영 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `txtfusion.layerwise_blocks.0.` | 첫 번째 텍스트 융합 레이어별 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `txtfusion.layerwise_blocks.1.` | 두 번째 텍스트 융합 레이어별 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `txtfusion.projector.` | 텍스트 융합 투영기 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `txtfusion.refiner_blocks.0.` | 첫 번째 텍스트 융합 정제기 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `txtfusion.refiner_blocks.1.` | 두 번째 텍스트 융합 정제기 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `blocks.0.` ~ `blocks.27.` | 28개 주요 블록 각각의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | +| `last.` | 마지막 블록의 혼합 비율 (기본값: 1.0) | FLOAT | 예 | 0.0 ~ 1.0 (단계: 0.01) | + +각 혼합 비율은 해당 특정 구성 요소에 대해 `model2`를 얼마나 사용할지 제어합니다. 0.0은 `model1`만 사용하고, 1.0은 `model2`만 사용하며, 그 사이의 값은 가중치 혼합을 생성합니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `MODEL` | 지정된 비율에 따라 두 입력 모델을 혼합하여 생성된 병합 모델 | MODEL | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeKrea2/ko.md) + +--- +**Source fingerprint (SHA-256):** `ece35524f77fd906dc3109a0818d4d7d3986ec9debb518fd04893048843d7e88` diff --git a/ko/built-in-nodes/ModelMergeLTXV.mdx b/ko/built-in-nodes/ModelMergeLTXV.mdx index 7d72195e8..02bfe810c 100644 --- a/ko/built-in-nodes/ModelMergeLTXV.mdx +++ b/ko/built-in-nodes/ModelMergeLTXV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeLTXV" icon: "circle" mode: wide --- + ModelMergeLTXV 노드는 LTXV 모델 아키텍처를 위해 특별히 설계된 고급 모델 병합 작업을 수행합니다. 트랜스포머 블록, 프로젝션 레이어 및 기타 특수 모듈을 포함한 다양한 모델 구성 요소에 대한 보간 가중치를 조정하여 두 개의 서로 다른 모델을 혼합할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeMochiPreview.mdx b/ko/built-in-nodes/ModelMergeMochiPreview.mdx index 3345f3ec5..79e2c3f73 100644 --- a/ko/built-in-nodes/ModelMergeMochiPreview.mdx +++ b/ko/built-in-nodes/ModelMergeMochiPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeMochiPreview" icon: "circle" mode: wide --- + 이 노드는 블록 기반 접근 방식을 사용하여 두 AI 모델을 병합하며, 다양한 모델 구성 요소에 대해 세밀하게 제어할 수 있습니다. 위치 주파수, 임베딩 레이어 및 개별 트랜스포머 블록을 포함한 특정 섹션에 대한 보간 가중치를 조정하여 모델을 혼합할 수 있습니다. 병합 프로세스는 지정된 가중치 값에 따라 두 입력 모델의 아키텍처와 매개변수를 결합합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeQwenImage.mdx b/ko/built-in-nodes/ModelMergeQwenImage.mdx index 6f0fbda53..6416f49cf 100644 --- a/ko/built-in-nodes/ModelMergeQwenImage.mdx +++ b/ko/built-in-nodes/ModelMergeQwenImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeQwenImage" icon: "circle" mode: wide --- + ModelMergeQwenImage 노드는 두 개의 AI 모델의 구성 요소를 가중치 조절 가능하게 결합하여 병합합니다. 트랜스포머 블록, 위치 임베딩, 텍스트 처리 구성 요소 등 Qwen 이미지 모델의 특정 부분을 혼합할 수 있습니다. 각 모델이 병합 결과의 서로 다른 부분에 미치는 영향력을 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeSD1.mdx b/ko/built-in-nodes/ModelMergeSD1.mdx index 7e3272b0e..afa5e1adc 100644 --- a/ko/built-in-nodes/ModelMergeSD1.mdx +++ b/ko/built-in-nodes/ModelMergeSD1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD1" icon: "circle" mode: wide --- + ModelMergeSD1 노드는 두 개의 Stable Diffusion 1.x 모델을 혼합하여 서로 다른 모델 구성 요소의 영향을 조정할 수 있게 해줍니다. 시간 임베딩, 레이블 임베딩, 그리고 모든 입력, 중간, 출력 블록에 대한 개별 제어 기능을 제공하여 특정 사용 사례에 맞게 세밀하게 조정된 모델 병합을 가능하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeSD35_Large.mdx b/ko/built-in-nodes/ModelMergeSD35_Large.mdx index b6c1d2c09..303ab76b6 100644 --- a/ko/built-in-nodes/ModelMergeSD35_Large.mdx +++ b/ko/built-in-nodes/ModelMergeSD35_Large.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD35_Large" icon: "circle" mode: wide --- + ModelMergeSD35_Large 노드는 두 개의 Stable Diffusion 3.5 Large 모델을 혼합하여 서로 다른 모델 구성 요소의 영향을 조정할 수 있게 해줍니다. 임베딩 레이어부터 조인트 블록 및 최종 레이어에 이르기까지 두 번째 모델의 각 부분이 최종 병합 모델에 기여하는 정도를 정밀하게 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeSD3_2B.mdx b/ko/built-in-nodes/ModelMergeSD3_2B.mdx index 2cfbfc73e..1065685d2 100644 --- a/ko/built-in-nodes/ModelMergeSD3_2B.mdx +++ b/ko/built-in-nodes/ModelMergeSD3_2B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD3_2B" icon: "circle" mode: wide --- + ModelMergeSD3_2B 노드는 두 개의 Stable Diffusion 3 2B 모델을 구성 요소별로 가중치를 조정하여 병합할 수 있게 해줍니다. 임베딩 레이어와 트랜스포머 블록을 개별적으로 제어할 수 있어, 특수화된 생성 작업을 위한 세밀하게 조정된 모델 조합이 가능합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeSDXL.mdx b/ko/built-in-nodes/ModelMergeSDXL.mdx index 2e25bc80c..1332de375 100644 --- a/ko/built-in-nodes/ModelMergeSDXL.mdx +++ b/ko/built-in-nodes/ModelMergeSDXL.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSDXL" icon: "circle" mode: wide --- + ModelMergeSDXL 노드는 두 개의 SDXL 모델을 혼합하여 아키텍처의 각 부분에 대한 각 모델의 영향을 조정할 수 있도록 합니다. 시간 임베딩, 레이블 임베딩 및 모델 구조 내의 다양한 블록에 대해 각 모델이 기여하는 정도를 제어할 수 있습니다. 이를 통해 두 입력 모델의 특성을 결합한 하이브리드 모델이 생성됩니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeSimple.mdx b/ko/built-in-nodes/ModelMergeSimple.mdx index 90922ec97..cb6c4025c 100644 --- a/ko/built-in-nodes/ModelMergeSimple.mdx +++ b/ko/built-in-nodes/ModelMergeSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSimple" icon: "circle" mode: wide --- + ## 개요 ModelMergeSimple 노드는 지정된 비율에 따라 두 모델의 매개변수를 혼합하여 병합하도록 설계되었습니다. 이 노드는 두 입력 모델의 강점이나 특성을 결합한 하이브리드 모델을 생성할 수 있게 해줍니다. diff --git a/ko/built-in-nodes/ModelMergeSubtract.mdx b/ko/built-in-nodes/ModelMergeSubtract.mdx index 16e86c7a8..3daf729ce 100644 --- a/ko/built-in-nodes/ModelMergeSubtract.mdx +++ b/ko/built-in-nodes/ModelMergeSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSubtract" icon: "circle" mode: wide --- + 이 노드는 고급 모델 병합 작업을 위해 설계되었으며, 특히 지정된 승수에 따라 한 모델의 매개변수를 다른 모델에서 차감합니다. 이를 통해 한 모델의 매개변수가 다른 모델에 미치는 영향을 조정하여 모델 동작을 사용자 정의하고 새로운 하이브리드 모델을 생성할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelMergeWAN2_1.mdx b/ko/built-in-nodes/ModelMergeWAN2_1.mdx index b124e3b2e..197a71adb 100644 --- a/ko/built-in-nodes/ModelMergeWAN2_1.mdx +++ b/ko/built-in-nodes/ModelMergeWAN2_1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeWAN2_1" icon: "circle" mode: wide --- + ModelMergeWAN2_1 노드는 두 개의 WAN2.1 모델을 가중 평균을 사용하여 구성 요소를 혼합함으로써 병합합니다. 이 노드는 30개의 블록을 가진 1.3B 모델과 40개의 블록을 가진 14B 모델을 포함한 다양한 모델 크기를 지원하며, 추가 이미지 임베딩 구성 요소가 포함된 이미지-투-비디오 모델을 특별히 처리합니다. 각 모델 구성 요소는 개별적으로 가중치를 부여하여 두 입력 모델 간의 혼합 비율을 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelNoiseScale.mdx b/ko/built-in-nodes/ModelNoiseScale.mdx index 7c35d0ef3..60ee298c7 100644 --- a/ko/built-in-nodes/ModelNoiseScale.mdx +++ b/ko/built-in-nodes/ModelNoiseScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelNoiseScale" icon: "circle" mode: wide --- + ## 개요 이 노드는 모델 샘플링 중 사용되는 노이즈 스케일을 조정합니다. 특정 노이즈 스케일 값을 설정하여 모델의 샘플링 과정에 적용되는 노이즈 양을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/ModelPatchLoader.mdx b/ko/built-in-nodes/ModelPatchLoader.mdx index ade4ed1c6..4ed3afa09 100644 --- a/ko/built-in-nodes/ModelPatchLoader.mdx +++ b/ko/built-in-nodes/ModelPatchLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelPatchLoader" icon: "circle" mode: wide --- + ModelPatchLoader 노드는 model_patches 폴더에서 특화된 모델 패치를 로드합니다. 패치 파일의 유형을 자동으로 감지하여 적절한 모델 아키텍처를 로드한 후, 워크플로에서 사용할 수 있도록 ModelPatcher로 래핑합니다. 이 노드는 controlnet 블록, 특징 임베더 모델 및 기타 특수 아키텍처를 포함한 다양한 패치 유형을 지원합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelSamplingAuraFlow.mdx b/ko/built-in-nodes/ModelSamplingAuraFlow.mdx index f7c50e75e..3cc8aea33 100644 --- a/ko/built-in-nodes/ModelSamplingAuraFlow.mdx +++ b/ko/built-in-nodes/ModelSamplingAuraFlow.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingAuraFlow" icon: "circle" mode: wide --- + ModelSamplingAuraFlow 노드는 확산 모델에 특화된 샘플링 구성을 적용하며, 특히 AuraFlow 모델 아키텍처를 위해 설계되었습니다. 이 노드는 샘플링 분포를 조정하는 시프트 매개변수를 적용하여 모델의 샘플링 동작을 수정합니다. SD3 모델 샘플링 프레임워크를 상속받으며, 샘플링 과정을 세밀하게 제어할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelSamplingContinuousEDM.mdx b/ko/built-in-nodes/ModelSamplingContinuousEDM.mdx index 293c51957..cd91c5bd0 100644 --- a/ko/built-in-nodes/ModelSamplingContinuousEDM.mdx +++ b/ko/built-in-nodes/ModelSamplingContinuousEDM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingContinuousEDM" icon: "circle" mode: wide --- + 이 노드는 연속 EDM(에너지 기반 확산 모델) 샘플링 기법을 통합하여 모델의 샘플링 성능을 향상시키도록 설계되었습니다. 모델의 샘플링 과정에서 노이즈 수준을 동적으로 조정할 수 있게 하여, 생성 품질과 다양성을 보다 정밀하게 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelSamplingContinuousV.mdx b/ko/built-in-nodes/ModelSamplingContinuousV.mdx index 579e68624..cc2d50875 100644 --- a/ko/built-in-nodes/ModelSamplingContinuousV.mdx +++ b/ko/built-in-nodes/ModelSamplingContinuousV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingContinuousV" icon: "circle" mode: wide --- + ModelSamplingContinuousV 노드는 연속적인 V-예측 샘플링 매개변수를 적용하여 모델의 샘플링 동작을 수정합니다. 입력 모델의 복제본을 생성하고 사용자 정의 시그마 범위 설정으로 구성하여 고급 샘플링 제어를 가능하게 합니다. 이를 통해 사용자는 특정 최소 및 최대 시그마 값으로 샘플링 프로세스를 세밀하게 조정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ModelSamplingDiscrete.mdx b/ko/built-in-nodes/ModelSamplingDiscrete.mdx index dc0b38429..063ae3b16 100644 --- a/ko/built-in-nodes/ModelSamplingDiscrete.mdx +++ b/ko/built-in-nodes/ModelSamplingDiscrete.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingDiscrete" icon: "circle" mode: wide --- + 이 노드는 이산 샘플링 전략을 적용하여 모델의 샘플링 동작을 수정하도록 설계되었습니다. epsilon, v_prediction, lcm 또는 x0과 같은 다양한 샘플링 방법을 선택할 수 있으며, 선택적으로 제로샷 노이즈 비율(zsnr) 설정에 따라 모델의 노이즈 감소 전략을 조정합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelSamplingFlux.mdx b/ko/built-in-nodes/ModelSamplingFlux.mdx index ea5c3ca83..f9c63d7c6 100644 --- a/ko/built-in-nodes/ModelSamplingFlux.mdx +++ b/ko/built-in-nodes/ModelSamplingFlux.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ModelSamplingFlux" icon: "circle" mode: wide --- -# ModelSamplingFlux ModelSamplingFlux 노드는 이미지 크기를 기반으로 시프트 매개변수를 계산하여 주어진 모델에 Flux 모델 샘플링을 적용합니다. 이 노드는 지정된 너비, 높이 및 시프트 매개변수에 따라 모델의 동작을 조정하는 특수 샘플링 구성을 생성한 후, 새로운 샘플링 설정이 적용된 수정된 모델을 반환합니다. diff --git a/ko/built-in-nodes/ModelSamplingLTXV.mdx b/ko/built-in-nodes/ModelSamplingLTXV.mdx index b88ed099a..4e7a808a1 100644 --- a/ko/built-in-nodes/ModelSamplingLTXV.mdx +++ b/ko/built-in-nodes/ModelSamplingLTXV.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ModelSamplingLTXV" icon: "circle" mode: wide --- -# ModelSamplingLTXV 노드 ModelSamplingLTXV 노드는 토큰 수를 기반으로 모델에 고급 샘플링 매개변수를 적용합니다. 기본 시프트 값과 최대 시프트 값 사이의 선형 보간을 사용하여 시프트 값을 계산하며, 이 계산은 입력 잠재 변수의 토큰 수에 따라 달라집니다. 그런 다음 노드는 특수화된 모델 샘플링 구성을 생성하여 입력 모델에 적용합니다. diff --git a/ko/built-in-nodes/ModelSamplingSD3.mdx b/ko/built-in-nodes/ModelSamplingSD3.mdx index eac26f0d7..d74e891c0 100644 --- a/ko/built-in-nodes/ModelSamplingSD3.mdx +++ b/ko/built-in-nodes/ModelSamplingSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingSD3" icon: "circle" mode: wide --- + ModelSamplingSD3 노드는 Stable Diffusion 3 샘플링 매개변수를 모델에 적용합니다. 이 노드는 샘플링 분포 특성을 제어하는 shift 매개변수를 조정하여 모델의 샘플링 동작을 수정합니다. 지정된 샘플링 구성이 적용된 입력 모델의 수정된 복사본을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/ModelSamplingStableCascade.mdx b/ko/built-in-nodes/ModelSamplingStableCascade.mdx index 97e8191e7..28ed6b14b 100644 --- a/ko/built-in-nodes/ModelSamplingStableCascade.mdx +++ b/ko/built-in-nodes/ModelSamplingStableCascade.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ModelSamplingStableCascade" icon: "circle" mode: wide --- -# ModelSamplingStableCascade ModelSamplingStableCascade 노드는 시프트 값을 사용하여 샘플링 매개변수를 조정함으로써 모델에 안정적인 캐스케이드 샘플링을 적용합니다. 이 노드는 안정적인 캐스케이드 생성을 위한 사용자 지정 샘플링 구성으로 입력 모델의 수정된 버전을 생성합니다. diff --git a/ko/built-in-nodes/ModelSave.mdx b/ko/built-in-nodes/ModelSave.mdx index dbca107d8..fe24b6569 100644 --- a/ko/built-in-nodes/ModelSave.mdx +++ b/ko/built-in-nodes/ModelSave.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ModelSave" icon: "circle" mode: wide --- -# ModelSave 노드 ModelSave 노드는 학습되거나 수정된 모델을 컴퓨터 저장소에 저장합니다. 모델을 입력으로 받아 지정된 파일 이름으로 파일에 기록합니다. 이를 통해 작업을 보존하고 향후 프로젝트에서 모델을 재사용할 수 있습니다. diff --git a/ko/built-in-nodes/MoonvalleyImg2VideoNode.mdx b/ko/built-in-nodes/MoonvalleyImg2VideoNode.mdx index 1d7562f52..8ba8a99a9 100644 --- a/ko/built-in-nodes/MoonvalleyImg2VideoNode.mdx +++ b/ko/built-in-nodes/MoonvalleyImg2VideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoonvalleyImg2VideoNode" icon: "circle" mode: wide --- -# Moonvalley Marey 이미지-투-비디오 노드 Moonvalley Marey 이미지-투-비디오 노드는 Moonvalley API를 사용하여 참조 이미지를 비디오로 변환합니다. 입력 이미지와 텍스트 프롬프트를 받아 지정된 해상도, 품질 설정 및 창의적 제어 옵션으로 비디오를 생성합니다. 이 노드는 이미지 업로드부터 비디오 생성 및 다운로드까지 전체 프로세스를 처리합니다. diff --git a/ko/built-in-nodes/MoonvalleyTxt2VideoNode.mdx b/ko/built-in-nodes/MoonvalleyTxt2VideoNode.mdx index 921ca326f..f54f0951e 100644 --- a/ko/built-in-nodes/MoonvalleyTxt2VideoNode.mdx +++ b/ko/built-in-nodes/MoonvalleyTxt2VideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoonvalleyTxt2VideoNode" icon: "circle" mode: wide --- -# Moonvalley Marey 텍스트-투-비디오 노드 Moonvalley Marey 텍스트-투-비디오 노드는 Moonvalley API를 사용하여 텍스트 설명으로부터 비디오 콘텐츠를 생성합니다. 텍스트 프롬프트를 입력받아 해상도, 품질 및 스타일에 대한 사용자 정의 설정으로 비디오로 변환합니다. 이 노드는 생성 요청 전송부터 최종 비디오 출력 다운로드까지 전체 프로세스를 처리합니다. diff --git a/ko/built-in-nodes/MoonvalleyVideo2VideoNode.mdx b/ko/built-in-nodes/MoonvalleyVideo2VideoNode.mdx index 038cc4ea6..eb1209ccd 100644 --- a/ko/built-in-nodes/MoonvalleyVideo2VideoNode.mdx +++ b/ko/built-in-nodes/MoonvalleyVideo2VideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoonvalleyVideo2VideoNode" icon: "circle" mode: wide --- -# Moonvalley 비디오-투-비디오 노드 Moonvalley Marey 비디오-투-비디오 노드는 입력 비디오를 텍스트 설명에 기반하여 새로운 비디오로 변환합니다. Moonvalley API를 사용하여 사용자의 프롬프트와 일치하면서도 원본 비디오의 움직임이나 포즈 특성을 보존하는 비디오를 생성합니다. 텍스트 프롬프트와 다양한 생성 매개변수를 통해 출력 비디오의 스타일과 내용을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/Morphology.mdx b/ko/built-in-nodes/Morphology.mdx index d00a66802..587d3570f 100644 --- a/ko/built-in-nodes/Morphology.mdx +++ b/ko/built-in-nodes/Morphology.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Morphology" icon: "circle" mode: wide --- -# 형태학(Morphology) 노드 형태학 노드는 이미지에 다양한 형태학적 연산을 적용합니다. 형태학적 연산은 이미지의 형태를 처리하고 분석하는 데 사용되는 수학적 연산입니다. 이 노드는 침식, 팽창, 열기, 닫기 등의 연산을 사용자 정의 가능한 커널 크기로 수행하여 효과 강도를 제어할 수 있습니다. diff --git a/ko/built-in-nodes/MultiGPU_Options.mdx b/ko/built-in-nodes/MultiGPU_Options.mdx index 00e2afdff..9378aff58 100644 --- a/ko/built-in-nodes/MultiGPU_Options.mdx +++ b/ko/built-in-nodes/MultiGPU_Options.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MultiGPU_Options" icon: "circle" mode: wide --- + ## 개요 이 노드는 서로 다른 속도의 여러 그래픽 카드를 사용할 때 각 GPU의 상대적 성능을 지정할 수 있게 해줍니다. 여러 장치 간에 작업을 분산하는 데 사용할 수 있는 GPU 옵션 그룹을 생성하지만, 현재 버전에서는 실제 속도 기반 작업 부하 분산이 아직 구현되지 않았습니다. diff --git a/ko/built-in-nodes/MultiGPU_WorkUnits.mdx b/ko/built-in-nodes/MultiGPU_WorkUnits.mdx index 422c77ee3..df3bcb9e9 100644 --- a/ko/built-in-nodes/MultiGPU_WorkUnits.mdx +++ b/ko/built-in-nodes/MultiGPU_WorkUnits.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MultiGPU_WorkUnits" icon: "circle" mode: wide --- + ## 개요 MultiGPU CFG Split 노드는 같은 컴퓨터에 설치된 여러 GPU가 확산 샘플링을 함께 처리할 수 있게 해줍니다. 실제 속도 향상은 워크플로에 따라 다르지만, 일반적인 워크플로에서는 최대 약 1.95배까지 빨라진 사례가 확인되었습니다. diff --git a/ko/built-in-nodes/NAGuidance.mdx b/ko/built-in-nodes/NAGuidance.mdx index 34634293d..6132a8975 100644 --- a/ko/built-in-nodes/NAGuidance.mdx +++ b/ko/built-in-nodes/NAGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NAGuidance" icon: "circle" mode: wide --- + NAGuidance 노드는 모델에 정규화된 주의 유도(Normalized Attention Guidance)를 적용합니다. 이 기법은 샘플링 과정에서 모델의 주의 메커니즘을 수정하여 원치 않는 개념으로부터 생성을 멀어지게 함으로써, 증류되거나 schnell 모델에서 부정 프롬프트를 사용할 수 있게 합니다. ## 입력 diff --git a/ko/built-in-nodes/NormalizeImages.mdx b/ko/built-in-nodes/NormalizeImages.mdx index cc0b39ce3..6e1b43ded 100644 --- a/ko/built-in-nodes/NormalizeImages.mdx +++ b/ko/built-in-nodes/NormalizeImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NormalizeImages" icon: "circle" mode: wide --- + 이 노드는 수학적 정규화 과정을 사용하여 입력 이미지의 픽셀 값을 조정합니다. 각 픽셀에서 지정된 평균값을 뺀 다음, 그 결과를 지정된 표준 편차로 나눕니다. 이는 다른 머신러닝 모델을 위해 이미지 데이터를 준비하는 일반적인 전처리 단계입니다. ## 입력 @@ -19,7 +20,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `image` | 정규화 과정이 적용된 후의 결과 이미지입니다. | IMAGE | +| `이미지` | 정규화 과정이 적용된 후의 결과 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeImages/ko.md) diff --git a/ko/built-in-nodes/NormalizeVideoLatentStart.mdx b/ko/built-in-nodes/NormalizeVideoLatentStart.mdx index 362d6e017..950921641 100644 --- a/ko/built-in-nodes/NormalizeVideoLatentStart.mdx +++ b/ko/built-in-nodes/NormalizeVideoLatentStart.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NormalizeVideoLatentStart" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeVideoLatentStart/en.md) 이 노드는 비디오 잠재 변수의 처음 몇 프레임을 조정하여 이후 프레임과 더 유사하게 보이도록 만듭니다. 비디오 후반부의 참조 프레임 집합에서 평균과 변동을 계산하고, 동일한 특성을 시작 프레임에 적용합니다. 이를 통해 비디오 시작 부분에서 더 부드럽고 일관된 시각적 전환을 생성할 수 있습니다. diff --git a/ko/built-in-nodes/Note.mdx b/ko/built-in-nodes/Note.mdx index c843af198..188cff415 100644 --- a/ko/built-in-nodes/Note.mdx +++ b/ko/built-in-nodes/Note.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Note" icon: "circle" mode: wide --- -# 워크플로우에 주석을 추가하는 노드입니다. ## 입력 diff --git a/ko/built-in-nodes/OpenAIChatConfig.mdx b/ko/built-in-nodes/OpenAIChatConfig.mdx index 6f1efd957..a09fb4052 100644 --- a/ko/built-in-nodes/OpenAIChatConfig.mdx +++ b/ko/built-in-nodes/OpenAIChatConfig.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIChatConfig" icon: "circle" mode: wide --- + OpenAIChatConfig 노드는 OpenAI Chat 노드에 대한 추가 구성 옵션을 설정할 수 있도록 합니다. 이 노드는 모델이 응답을 생성하는 방식을 제어하는 고급 설정(잘라내기 동작, 출력 길이 제한 및 사용자 지정 지침 포함)을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/OpenAIChatNode.mdx b/ko/built-in-nodes/OpenAIChatNode.mdx index 2cccb839f..a6baead3b 100644 --- a/ko/built-in-nodes/OpenAIChatNode.mdx +++ b/ko/built-in-nodes/OpenAIChatNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIChatNode" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIChatNode/en.md) 이 노드는 OpenAI 모델로부터 텍스트 응답을 생성합니다. 텍스트 프롬프트(선택적으로 이미지 또는 파일 포함)를 OpenAI 모델에 전송하고 생성된 텍스트 응답을 반환합니다. diff --git a/ko/built-in-nodes/OpenAIDalle2.mdx b/ko/built-in-nodes/OpenAIDalle2.mdx index 3d70bf5c9..39af60018 100644 --- a/ko/built-in-nodes/OpenAIDalle2.mdx +++ b/ko/built-in-nodes/OpenAIDalle2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "OpenAIDalle2" icon: "circle" mode: wide --- -# OpenAIDalle2 OpenAI의 DALL·E 2 엔드포인트를 통해 이미지를 동기식으로 생성합니다. diff --git a/ko/built-in-nodes/OpenAIDalle3.mdx b/ko/built-in-nodes/OpenAIDalle3.mdx index c13f513a3..5a1446f81 100644 --- a/ko/built-in-nodes/OpenAIDalle3.mdx +++ b/ko/built-in-nodes/OpenAIDalle3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIDalle3" icon: "circle" mode: wide --- + OpenAI의 DALL·E 3 엔드포인트를 통해 이미지를 동기식으로 생성합니다. 이 노드는 텍스트 프롬프트를 받아 OpenAI의 DALL·E 3 모델을 사용하여 해당 이미지를 생성하며, 이미지 품질, 스타일 및 크기를 지정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/OpenAIGPTImage1.mdx b/ko/built-in-nodes/OpenAIGPTImage1.mdx index 97bb9b354..8e4faa3e1 100644 --- a/ko/built-in-nodes/OpenAIGPTImage1.mdx +++ b/ko/built-in-nodes/OpenAIGPTImage1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIGPTImage1" icon: "circle" mode: wide --- + 다음은 제공된 영어 문서를 번역 규칙에 따라 한국어로 번역한 결과입니다. > 본 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/OpenAIGPTImage1/en.md) diff --git a/ko/built-in-nodes/OpenAIGPTImageNodeV2.mdx b/ko/built-in-nodes/OpenAIGPTImageNodeV2.mdx index 6e9e40bc9..45a53fead 100644 --- a/ko/built-in-nodes/OpenAIGPTImageNodeV2.mdx +++ b/ko/built-in-nodes/OpenAIGPTImageNodeV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIGPTImageNodeV2" icon: "circle" mode: wide --- + ## 개요 이 노드는 OpenAI의 GPT 이미지 API를 사용하여 이미지를 생성합니다. 여러 모델을 지원하며, 편집을 위한 입력 이미지를 제공할 수 있고, 마스크를 사용하여 이미지의 특정 부분을 수정할 수 있습니다. diff --git a/ko/built-in-nodes/OpenAIInputFiles.mdx b/ko/built-in-nodes/OpenAIInputFiles.mdx index b9d5501e6..e060f56f4 100644 --- a/ko/built-in-nodes/OpenAIInputFiles.mdx +++ b/ko/built-in-nodes/OpenAIInputFiles.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIInputFiles" icon: "circle" mode: wide --- + OpenAI API용 입력 파일을 로드하고 형식을 지정합니다. 이 노드는 텍스트(.txt) 및 PDF(.pdf) 파일을 준비하여 OpenAI 채팅 노드의 컨텍스트 입력으로 포함시킵니다. 응답을 생성할 때 OpenAI 모델이 해당 파일을 읽습니다. 여러 개의 OpenAI 입력 파일 노드를 연결하여 단일 메시지에 여러 파일을 포함시킬 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/OpenAIVideoSora2.mdx b/ko/built-in-nodes/OpenAIVideoSora2.mdx index feedcd5e5..430e3c3a2 100644 --- a/ko/built-in-nodes/OpenAIVideoSora2.mdx +++ b/ko/built-in-nodes/OpenAIVideoSora2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "OpenAIVideoSora2" icon: "circle" mode: wide --- -# OpenAIVideoSora2 노드 OpenAIVideoSora2 노드는 OpenAI의 Sora 모델을 사용하여 비디오를 생성합니다. 텍스트 프롬프트와 선택적 입력 이미지를 기반으로 비디오 콘텐츠를 생성한 후, 생성된 비디오 출력을 반환합니다. 이 노드는 선택한 모델에 따라 다양한 비디오 길이와 해상도를 지원합니다. diff --git a/ko/built-in-nodes/OpenRouterLLMNode.mdx b/ko/built-in-nodes/OpenRouterLLMNode.mdx index f81f5e92a..398077655 100644 --- a/ko/built-in-nodes/OpenRouterLLMNode.mdx +++ b/ko/built-in-nodes/OpenRouterLLMNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "OpenRouterLLMNode" icon: "circle" mode: wide --- -# 개요 OpenRouter LLM 노드는 OpenRouter 서비스를 통해 제공되는 엄선된 인기 언어 모델 세트에 텍스트 프롬프트를 전송하고 생성된 텍스트 응답을 반환합니다. xAI, DeepSeek, Qwen, Mistral, Z.AI(GLM), Moonshot(Kimi), Perplexity Sonar와 같은 제공업체의 모델을 지원하며, 요청에 이미지나 비디오를 선택적으로 포함할 수 있습니다. diff --git a/ko/built-in-nodes/OpticalFlowLoader.mdx b/ko/built-in-nodes/OpticalFlowLoader.mdx index 8875443f1..af286f013 100644 --- a/ko/built-in-nodes/OpticalFlowLoader.mdx +++ b/ko/built-in-nodes/OpticalFlowLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpticalFlowLoader" icon: "circle" mode: wide --- + ## 개요 `models/optical_flow/` 폴더에서 광학 흐름(optical flow) 모델을 불러옵니다. 현재는 VOIDWarpedNoise 노드에서 사용하는 torchvision의 RAFT-large 형식만 지원됩니다. ComfyUI는 광학 흐름 가중치를 자동으로 다운로드하지 않습니다. 체크포인트 파일을 수동으로 `models/optical_flow/` 디렉터리에 배치해야 합니다. diff --git a/ko/built-in-nodes/OptimalStepsScheduler.mdx b/ko/built-in-nodes/OptimalStepsScheduler.mdx index 7e30a2f3e..739f8eb83 100644 --- a/ko/built-in-nodes/OptimalStepsScheduler.mdx +++ b/ko/built-in-nodes/OptimalStepsScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OptimalStepsScheduler" icon: "circle" mode: wide --- + OptimalStepsScheduler 노드는 선택한 모델 유형과 단계 구성에 기반하여 확산 모델의 노이즈 스케줄 시그마 값을 계산합니다. 노이즈 제거(denoise) 매개변수에 따라 전체 단계 수를 조정하고, 요청된 단계 수에 맞게 노이즈 수준을 보간합니다. 이 노드는 확산 샘플링 과정에서 사용되는 노이즈 수준을 결정하는 시그마 값 시퀀스를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/Painter.mdx b/ko/built-in-nodes/Painter.mdx index 596a1d2e1..c40f1d883 100644 --- a/ko/built-in-nodes/Painter.mdx +++ b/ko/built-in-nodes/Painter.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Painter" icon: "circle" mode: wide --- + Painter 노드는 ComfyUI 내에서 직접 이미지나 마스크를 생성하거나 편집할 수 있는 대화형 캔버스를 제공합니다. 빈 캔버스나 기존 이미지로 시작하여 브러시 도구로 그림을 그리고, 결과 이미지와 해당 알파 마스크를 모두 출력할 수 있습니다. 마스크는 그려진 영역을 정의하며, 이 영역은 기본 이미지나 배경색 위에 합성됩니다. ## 입력 diff --git a/ko/built-in-nodes/PairConditioningCombine.mdx b/ko/built-in-nodes/PairConditioningCombine.mdx index 28e0a87cb..577d15318 100644 --- a/ko/built-in-nodes/PairConditioningCombine.mdx +++ b/ko/built-in-nodes/PairConditioningCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningCombine" icon: "circle" mode: wide --- + PairConditioningCombine 노드는 두 개의 개별 컨디셔닝 쌍(각각 양성 및 음성 컨디셔닝으로 구성)을 하나의 결합된 쌍으로 병합합니다. 서로 다른 두 소스에서 양성 및 음성 컨디셔닝을 가져와 ComfyUI의 내부 로직을 사용하여 결합한 후, 최종적으로 하나의 양성 컨디셔닝과 하나의 음성 컨디셔닝을 출력합니다. 이 노드는 실험적이며 고급 컨디셔닝 조작 워크플로우를 위해 설계되었습니다. ## 입력 @@ -20,8 +21,8 @@ PairConditioningCombine 노드는 두 개의 개별 컨디셔닝 쌍(각각 양 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 결합된 양성 컨디셔닝 출력 | CONDITIONING | -| `negative` | 결합된 음성 컨디셔닝 출력 | CONDITIONING | +| `긍정 조건` | 결합된 양성 컨디셔닝 출력 | CONDITIONING | +| `부정 조건` | 결합된 음성 컨디셔닝 출력 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningCombine/ko.md) diff --git a/ko/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx b/ko/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx index 7af6ceb0a..f2a1e7837 100644 --- a/ko/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx +++ b/ko/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetDefaultAndCombine" icon: "circle" mode: wide --- + **PairConditioningSetDefaultAndCombine** 노드는 기본 컨디셔닝 값을 설정하고 이를 입력 컨디셔닝 데이터와 결합합니다. 양성 및 음성 컨디셔닝 입력과 해당 기본값을 받아 ComfyUI의 후크 시스템을 통해 처리하여 기본값이 통합된 최종 컨디셔닝 출력을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/PairConditioningSetProperties.mdx b/ko/built-in-nodes/PairConditioningSetProperties.mdx index 3be5520a7..2c9e4b36e 100644 --- a/ko/built-in-nodes/PairConditioningSetProperties.mdx +++ b/ko/built-in-nodes/PairConditioningSetProperties.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetProperties" icon: "circle" mode: wide --- + **PairConditioningSetProperties** 노드는 긍정 및 부정 컨디셔닝 쌍의 속성을 동시에 수정할 수 있도록 합니다. 두 컨디셔닝 입력에 강도 조정, 컨디셔닝 영역 설정, 선택적 마스킹 또는 타이밍 제어를 적용하여 수정된 긍정 및 부정 컨디셔닝 데이터를 반환합니다. ## 입력 @@ -23,8 +24,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 속성이 적용된 수정된 긍정 컨디셔닝 | CONDITIONING | -| `negative` | 속성이 적용된 수정된 부정 컨디셔닝 | CONDITIONING | +| `긍정 조건` | 속성이 적용된 수정된 긍정 컨디셔닝 | CONDITIONING | +| `부정 조건` | 속성이 적용된 수정된 부정 컨디셔닝 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetProperties/ko.md) diff --git a/ko/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx b/ko/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx index 86b3c5872..00fbcffc1 100644 --- a/ko/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx +++ b/ko/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PairConditioningSetPropertiesAndCombine" icon: "circle" mode: wide --- -# PairConditioningSetPropertiesAndCombine 노드 PairConditioningSetPropertiesAndCombine 노드는 기존의 긍정 및 부정 조건화 입력에 새로운 조건화 데이터를 적용하여 조건화 쌍을 수정하고 결합합니다. 적용되는 조건화의 강도를 조정하고 조건화 영역이 설정되는 방식을 제어할 수 있습니다. 이 노드는 여러 조건화 소스를 함께 혼합해야 하는 고급 조건화 조작 워크플로우에서 특히 유용합니다. @@ -27,7 +26,7 @@ PairConditioningSetPropertiesAndCombine 노드는 기존의 긍정 및 부정 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 결합된 긍정 조건화 출력 | CONDITIONING | +| `긍정 조건` | 결합된 긍정 조건화 출력 | CONDITIONING | | `부정 조건` | 결합된 부정 조건화 출력 | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetPropertiesAndCombine/ko.md) diff --git a/ko/built-in-nodes/PatchModelAddDownscale.mdx b/ko/built-in-nodes/PatchModelAddDownscale.mdx index 676843436..52dbbc41c 100644 --- a/ko/built-in-nodes/PatchModelAddDownscale.mdx +++ b/ko/built-in-nodes/PatchModelAddDownscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PatchModelAddDownscale" icon: "circle" mode: wide --- + PatchModelAddDownscale 노드는 모델의 특정 블록에 다운스케일링 및 업스케일링 연산을 적용하여 Kohya Deep Shrink 기능을 구현합니다. 처리 과정에서 중간 특징의 해상도를 낮춘 후 원래 크기로 복원함으로써 품질을 유지하면서 성능을 향상시킬 수 있습니다. 이 노드는 모델 실행 중 이러한 스케일링 연산이 발생하는 시점과 방식을 정밀하게 제어할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/PerpNeg.mdx b/ko/built-in-nodes/PerpNeg.mdx index d6ae592a2..c390f50a3 100644 --- a/ko/built-in-nodes/PerpNeg.mdx +++ b/ko/built-in-nodes/PerpNeg.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PerpNeg" icon: "circle" mode: wide --- -# PerpNeg (수직 부정 유도) PerpNeg 노드는 모델의 샘플링 과정에 수직 부정 유도(perpendicular negative guidance)를 적용합니다. 이 노드는 모델의 설정 함수를 수정하여 부정 조건화(negative conditioning)와 스케일링 팩터를 사용해 노이즈 예측을 조정합니다. 이 노드는 더 이상 사용되지 않으며, 향상된 기능을 위해 PerpNegGuider 노드로 대체되었습니다. diff --git a/ko/built-in-nodes/PerpNegGuider.mdx b/ko/built-in-nodes/PerpNegGuider.mdx index 604abdce6..d703b1e12 100644 --- a/ko/built-in-nodes/PerpNegGuider.mdx +++ b/ko/built-in-nodes/PerpNegGuider.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PerpNegGuider" icon: "circle" mode: wide --- -# PerpNegGuider 노드 PerpNegGuider 노드는 수직 네거티브 조건화(perpendicular negative conditioning)를 사용하여 이미지 생성을 제어하는 가이던스 시스템을 생성합니다. 이 노드는 포지티브, 네거티브 및 빈(empty) 조건화 입력을 받아 특화된 가이던스 알고리즘을 적용하여 생성 과정을 조정합니다. 실험적 테스트를 위해 설계되었으며, 가이던스 강도와 네거티브 스케일링을 세밀하게 제어할 수 있습니다. diff --git a/ko/built-in-nodes/PerturbedAttentionGuidance.mdx b/ko/built-in-nodes/PerturbedAttentionGuidance.mdx index c3307048d..9cd8629b8 100644 --- a/ko/built-in-nodes/PerturbedAttentionGuidance.mdx +++ b/ko/built-in-nodes/PerturbedAttentionGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerturbedAttentionGuidance" icon: "circle" mode: wide --- + **PerturbedAttentionGuidance** 노드는 확산 모델에 교란된 주의 유도(perturbed attention guidance)를 적용하여 생성 품질을 향상시킵니다. 샘플링 과정에서 모델의 자체 주의 메커니즘을 값 투영에 초점을 맞춘 단순화된 버전으로 대체하여 작동합니다. 이 기법은 조건부 잡음 제거 과정을 조정하여 생성된 이미지의 일관성과 품질을 개선하는 데 도움을 줍니다. ## 입력 diff --git a/ko/built-in-nodes/PhotoMakerEncode.mdx b/ko/built-in-nodes/PhotoMakerEncode.mdx index ea8fb2ce9..4d880f9aa 100644 --- a/ko/built-in-nodes/PhotoMakerEncode.mdx +++ b/ko/built-in-nodes/PhotoMakerEncode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PhotoMakerEncode" icon: "circle" mode: wide --- -# PhotoMakerEncode 노드 PhotoMakerEncode 노드는 이미지와 텍스트를 처리하여 AI 이미지 생성을 위한 컨디셔닝 데이터를 생성합니다. 참조 이미지와 텍스트 프롬프트를 입력받아, 참조 이미지의 시각적 특성을 기반으로 이미지 생성을 안내하는 임베딩을 생성합니다. 이 노드는 텍스트에서 "photomaker" 토큰을 찾아 이미지 기반 컨디셔닝을 적용할 위치를 결정합니다. diff --git a/ko/built-in-nodes/PhotoMakerLoader.mdx b/ko/built-in-nodes/PhotoMakerLoader.mdx index 543340bed..e8b0230fe 100644 --- a/ko/built-in-nodes/PhotoMakerLoader.mdx +++ b/ko/built-in-nodes/PhotoMakerLoader.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PhotoMakerLoader" icon: "circle" mode: wide --- -# PhotoMakerLoader 노드 PhotoMakerLoader 노드는 사용 가능한 모델 파일에서 PhotoMaker 모델을 로드합니다. 지정된 모델 파일을 읽고 신원 기반 이미지 생성 작업에 사용할 PhotoMaker ID 인코더를 준비합니다. 이 노드는 실험적 기능으로 표시되어 있으며 테스트 목적으로 사용됩니다. diff --git a/ko/built-in-nodes/PiDConditioning.mdx b/ko/built-in-nodes/PiDConditioning.mdx index 802e646bd..63d157662 100644 --- a/ko/built-in-nodes/PiDConditioning.mdx +++ b/ko/built-in-nodes/PiDConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PiDConditioning" icon: "circle" mode: wide --- + ## 개요 잠재 이미지와 열화 시그마 값을 CONDITIONING 데이터에 첨부합니다. 이는 PiD(Pixel-in-Detail) 디코딩 또는 업스케일링에 사용되며, 처리 전 잠재 이미지의 열화 정도를 제어할 수 있습니다. diff --git a/ko/built-in-nodes/PikaImageToVideoNode2_2.mdx b/ko/built-in-nodes/PikaImageToVideoNode2_2.mdx index 06e57f8be..cd57f301e 100644 --- a/ko/built-in-nodes/PikaImageToVideoNode2_2.mdx +++ b/ko/built-in-nodes/PikaImageToVideoNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaImageToVideoNode2_2" icon: "circle" mode: wide --- + Pika Image to Video 노드는 이미지와 텍스트 프롬프트를 Pika API 버전 2.2로 전송하여 비디오를 생성합니다. 제공된 설명과 설정에 따라 입력 이미지를 비디오 형식으로 변환합니다. 이 노드는 API 통신을 처리하고 생성된 비디오를 출력으로 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/PikaScenesV2_2.mdx b/ko/built-in-nodes/PikaScenesV2_2.mdx index 3cc22e04c..fed7c1c15 100644 --- a/ko/built-in-nodes/PikaScenesV2_2.mdx +++ b/ko/built-in-nodes/PikaScenesV2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaScenesV2_2" icon: "circle" mode: wide --- + PikaScenes v2.2 노드는 여러 이미지를 결합하여 모든 입력 이미지의 객체를 통합한 비디오를 생성합니다. 최대 5개의 서로 다른 이미지를 재료로 업로드하여 이를 매끄럽게 혼합한 고품질 비디오를 생성할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/PikaStartEndFrameNode2_2.mdx b/ko/built-in-nodes/PikaStartEndFrameNode2_2.mdx index fece79be1..68ea6dd51 100644 --- a/ko/built-in-nodes/PikaStartEndFrameNode2_2.mdx +++ b/ko/built-in-nodes/PikaStartEndFrameNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaStartEndFrameNode2_2" icon: "circle" mode: wide --- + PikaFrames v2.2 노드는 첫 번째 프레임과 마지막 프레임을 결합하여 비디오를 생성합니다. 시작점과 끝점을 정의하는 두 개의 이미지를 업로드하면, AI가 두 이미지 사이의 부드러운 전환을 생성하여 완전한 비디오를 만들어냅니다. ## 입력 diff --git a/ko/built-in-nodes/PikaTextToVideoNode2_2.mdx b/ko/built-in-nodes/PikaTextToVideoNode2_2.mdx index 3c93e1abe..38c0ec9ac 100644 --- a/ko/built-in-nodes/PikaTextToVideoNode2_2.mdx +++ b/ko/built-in-nodes/PikaTextToVideoNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaTextToVideoNode2_2" icon: "circle" mode: wide --- + Pika Text2Video v2.2 노드는 Pika API 버전 2.2에 텍스트 프롬프트를 전송하여 비디오를 생성합니다. 텍스트 설명을 Pika의 AI 비디오 생성 서비스를 사용하여 비디오로 변환합니다. 이 노드를 사용하면 화면 비율, 지속 시간, 해상도 등 비디오 생성 과정의 다양한 측면을 사용자 지정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/Pikadditions.mdx b/ko/built-in-nodes/Pikadditions.mdx index 189058710..59f5c74b1 100644 --- a/ko/built-in-nodes/Pikadditions.mdx +++ b/ko/built-in-nodes/Pikadditions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikadditions" icon: "circle" mode: wide --- + Pikadditions 노드를 사용하면 비디오에 원하는 객체나 이미지를 추가할 수 있습니다. 비디오를 업로드하고 추가할 대상을 지정하면 자연스럽게 통합된 결과물이 생성됩니다. 이 노드는 Pika API를 활용하여 이미지를 비디오에 자연스러운 모습으로 삽입합니다. ## 입력 diff --git a/ko/built-in-nodes/Pikaffects.mdx b/ko/built-in-nodes/Pikaffects.mdx index 1c9cd71b1..59c55e1a1 100644 --- a/ko/built-in-nodes/Pikaffects.mdx +++ b/ko/built-in-nodes/Pikaffects.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikaffects" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Pikaffects/en.md) Pikaffects 노드는 입력 이미지에 다양한 시각 효과를 적용하여 비디오를 생성합니다. Pika의 비디오 생성 API를 사용하여 정적 이미지를 녹이기, 폭발, 부양과 같은 특정 효과가 적용된 애니메이션 비디오로 변환합니다. 이 노드는 Pika 서비스에 액세스하기 위해 API 키와 인증 토큰이 필요합니다. diff --git a/ko/built-in-nodes/Pikaswaps.mdx b/ko/built-in-nodes/Pikaswaps.mdx index eb08d90a7..bb87fc3b5 100644 --- a/ko/built-in-nodes/Pikaswaps.mdx +++ b/ko/built-in-nodes/Pikaswaps.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikaswaps" icon: "circle" mode: wide --- + Pika Swaps 노드는 비디오 내의 객체나 영역을 새 이미지로 교체합니다. 마스크를 사용하여 교체할 영역을 정의하면, 노드가 비디오 시퀀스 전체에서 지정된 콘텐츠를 매끄럽게 교체합니다. ## 입력 diff --git a/ko/built-in-nodes/PixverseImageToVideoNode.mdx b/ko/built-in-nodes/PixverseImageToVideoNode.mdx index d114c5e3c..836b94e89 100644 --- a/ko/built-in-nodes/PixverseImageToVideoNode.mdx +++ b/ko/built-in-nodes/PixverseImageToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PixverseImageToVideoNode" icon: "circle" mode: wide --- -# PixverseImageToVideoNode 입력 이미지와 텍스트 프롬프트를 기반으로 비디오를 생성합니다. 이 노드는 이미지를 입력받아 지정된 모션 및 품질 설정을 적용하여 정적 이미지를 움직이는 시퀀스로 변환함으로써 애니메이션 비디오를 생성합니다. diff --git a/ko/built-in-nodes/PixverseTemplateNode.mdx b/ko/built-in-nodes/PixverseTemplateNode.mdx index 9c24e3d6d..1ce786973 100644 --- a/ko/built-in-nodes/PixverseTemplateNode.mdx +++ b/ko/built-in-nodes/PixverseTemplateNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTemplateNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTemplateNode/en.md) PixVerse 템플릿 노드를 사용하면 PixVerse 비디오 생성을 위해 사용 가능한 템플릿 중에서 선택할 수 있습니다. 선택한 템플릿 이름을 PixVerse API가 비디오 생성에 필요한 해당 템플릿 ID로 변환합니다. @@ -19,7 +20,7 @@ PixVerse 템플릿 노드를 사용하면 PixVerse 비디오 생성을 위해 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `pixverse_template` | 선택한 템플릿 이름에 해당하는 템플릿 ID로, 다른 PixVerse 노드에서 비디오 생성에 사용할 수 있습니다. | STRING | +| `pixverse 템플릿` | 선택한 템플릿 이름에 해당하는 템플릿 ID로, 다른 PixVerse 노드에서 비디오 생성에 사용할 수 있습니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTemplateNode/ko.md) diff --git a/ko/built-in-nodes/PixverseTextToVideoNode.mdx b/ko/built-in-nodes/PixverseTextToVideoNode.mdx index 9881ecfae..0415a4083 100644 --- a/ko/built-in-nodes/PixverseTextToVideoNode.mdx +++ b/ko/built-in-nodes/PixverseTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTextToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTextToVideoNode/en.md) 텍스트 프롬프트와 다양한 생성 매개변수를 기반으로 비디오를 생성합니다. 이 노드는 PixVerse API를 사용하여 비디오 콘텐츠를 생성하며, 화면 비율, 품질, 길이, 모션 스타일 등을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/PixverseTransitionVideoNode.mdx b/ko/built-in-nodes/PixverseTransitionVideoNode.mdx index dffa697cc..16b6c6046 100644 --- a/ko/built-in-nodes/PixverseTransitionVideoNode.mdx +++ b/ko/built-in-nodes/PixverseTransitionVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PixverseTransitionVideoNode" icon: "circle" mode: wide --- -# 개요 PixVerse API를 사용하여 두 입력 이미지 간의 전환 비디오를 생성합니다. 시작 이미지와 종료 이미지를 제공하면, 노드가 텍스트 프롬프트와 선택한 설정에 따라 한 이미지에서 다른 이미지로 부드럽게 전환되는 비디오를 생성합니다. diff --git a/ko/built-in-nodes/PolyexponentialScheduler.mdx b/ko/built-in-nodes/PolyexponentialScheduler.mdx index 7102f8167..049af7da7 100644 --- a/ko/built-in-nodes/PolyexponentialScheduler.mdx +++ b/ko/built-in-nodes/PolyexponentialScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PolyexponentialScheduler" icon: "circle" mode: wide --- + PolyexponentialScheduler 노드는 다지수(polyexponential) 노이즈 스케줄을 기반으로 노이즈 수준(sigmas) 시퀀스를 생성하도록 설계되었습니다. 이 스케줄은 시그마 로그값에 대한 다항 함수로서, 확산 과정 전반에 걸쳐 유연하고 사용자 정의 가능한 노이즈 수준 진행을 가능하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/PorterDuffImageComposite.mdx b/ko/built-in-nodes/PorterDuffImageComposite.mdx index f162f97ec..87e8e59b0 100644 --- a/ko/built-in-nodes/PorterDuffImageComposite.mdx +++ b/ko/built-in-nodes/PorterDuffImageComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PorterDuffImageComposite" icon: "circle" mode: wide --- + PorterDuffImageComposite 노드는 Porter-Duff 합성 연산자를 사용하여 이미지 합성을 수행하도록 설계되었습니다. 소스 이미지와 대상 이미지를 다양한 혼합 모드에 따라 결합하여, 이미지 투명도를 조작하고 창의적인 방식으로 이미지를 겹쳐 복잡한 시각 효과를 생성할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/Preview3D.mdx b/ko/built-in-nodes/Preview3D.mdx index 69a7c4a05..77f562073 100644 --- a/ko/built-in-nodes/Preview3D.mdx +++ b/ko/built-in-nodes/Preview3D.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Preview3D" icon: "circle" mode: wide --- -# Preview3D 노드 Preview3D 노드는 주로 3D 모델 출력을 미리 보는 데 사용됩니다. 이 노드는 두 가지 입력을 받습니다. 하나는 Load3D 노드의 `camera_info`이고, 다른 하나는 3D 모델 파일의 경로입니다. 모델 파일 경로는 `ComfyUI/output` 폴더에 위치해야 합니다. diff --git a/ko/built-in-nodes/Preview3DAdvanced.mdx b/ko/built-in-nodes/Preview3DAdvanced.mdx index d8549d3ec..b2bb43918 100644 --- a/ko/built-in-nodes/Preview3DAdvanced.mdx +++ b/ko/built-in-nodes/Preview3DAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Preview3DAdvanced" icon: "circle" mode: wide --- -# Preview 3D (고급) 이 노드는 카메라 및 모델 정보 출력과 함께 고급 3D 모델 미리보기를 제공합니다. 3D 모델을 임시 파일로 저장하여 UI에 표시하며, 모델 데이터, 카메라 정보 및 뷰포트 크기를 다운스트림 처리를 위해 전달합니다. @@ -24,10 +23,10 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | |-------------|-------------|-----------| -| `camera_info` | 입력에서 전달된 3D 모델 파일입니다. | FILE3D | -| `model_3d_info` | 입력 또는 뷰포트 상태에서 가져온 모델 정보 메타데이터입니다. | LOAD3DMODELINFO | -| `width` | 입력 또는 뷰포트 상태에서 가져온 카메라 구성입니다. | LOAD3DCAMERA | -| `height` | 미리보기의 너비(픽셀)입니다. | INT | +| `model_file` | 입력에서 전달된 3D 모델 파일입니다. | FILE3D | +| `camera_info` | 입력 또는 뷰포트 상태에서 가져온 모델 정보 메타데이터입니다. | LOAD3DMODELINFO | +| `model_3d_info` | 입력 또는 뷰포트 상태에서 가져온 카메라 구성입니다. | LOAD3DCAMERA | +| `width` | 미리보기의 너비(픽셀)입니다. | INT | | `height` | 미리보기의 높이(픽셀)입니다. | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Preview3DAdvanced/ko.md) diff --git a/ko/built-in-nodes/Preview3DAnimation.mdx b/ko/built-in-nodes/Preview3DAnimation.mdx index 7b9afe2a6..ff83cf40a 100644 --- a/ko/built-in-nodes/Preview3DAnimation.mdx +++ b/ko/built-in-nodes/Preview3DAnimation.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Preview3DAnimation" icon: "circle" mode: wide --- -# Preview3DAnimation 노드 Preview3DAnimation 노드는 주로 3D 모델 출력을 미리보기 위한 노드입니다. 이 노드는 두 가지 입력을 받습니다: 하나는 Load3D 노드의 `camera_info`이고, 다른 하나는 3D 모델 파일의 경로입니다. 모델 파일 경로는 `ComfyUI/output` 폴더에 위치해야 합니다. diff --git a/ko/built-in-nodes/PreviewAny.mdx b/ko/built-in-nodes/PreviewAny.mdx index ebc71628e..e2f1898a2 100644 --- a/ko/built-in-nodes/PreviewAny.mdx +++ b/ko/built-in-nodes/PreviewAny.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewAny" icon: "circle" mode: wide --- + ## 입력 | 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | diff --git a/ko/built-in-nodes/PreviewAudio.mdx b/ko/built-in-nodes/PreviewAudio.mdx index 3ba462db2..6301ab4cb 100644 --- a/ko/built-in-nodes/PreviewAudio.mdx +++ b/ko/built-in-nodes/PreviewAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewAudio" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAudio/en.md) PreviewAudio 노드는 인터페이스에서 직접 재생할 수 있는 임시 오디오 미리보기를 생성합니다. 오디오 데이터를 입력으로 받아 미리보기 위젯을 생성하며, 사용자가 영구 파일을 저장하지 않고도 오디오 출력을 들을 수 있도록 합니다. @@ -19,7 +20,7 @@ PreviewAudio 노드는 인터페이스에서 직접 재생할 수 있는 임시 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `ui` | 오디오 미리보기를 위해 인터페이스에 오디오 플레이어 위젯을 표시합니다 | UI | +| `audio` | 오디오 미리보기를 위해 인터페이스에 오디오 플레이어 위젯을 표시합니다 | UI | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAudio/ko.md) diff --git a/ko/built-in-nodes/PreviewGaussianSplat.mdx b/ko/built-in-nodes/PreviewGaussianSplat.mdx index cdd6712b9..4bb116bb3 100644 --- a/ko/built-in-nodes/PreviewGaussianSplat.mdx +++ b/ko/built-in-nodes/PreviewGaussianSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PreviewGaussianSplat" icon: "circle" mode: wide --- -# PreviewGaussianSplat PreviewGaussianSplat 노드를 사용하면 ComfyUI 인터페이스 내에서 3D 가우시안 스플랫 파일을 미리 볼 수 있습니다. 다양한 가우시안 스플랫 형식의 3D 모델 파일을 입력받아 3D 미리보기 창에서 렌더링하며, 모델 데이터를 그대로 전달하여 추가 처리가 가능하도록 합니다. diff --git a/ko/built-in-nodes/PreviewImage.mdx b/ko/built-in-nodes/PreviewImage.mdx index 7727700fb..042653a23 100644 --- a/ko/built-in-nodes/PreviewImage.mdx +++ b/ko/built-in-nodes/PreviewImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewImage" icon: "circle" mode: wide --- + PreviewImage 노드는 임시 미리보기 이미지를 생성하기 위해 설계되었습니다. 각 이미지에 대해 고유한 임시 파일 이름을 자동으로 생성하고, 이미지를 지정된 수준으로 압축한 후 임시 디렉터리에 저장합니다. 이 기능은 원본 파일에 영향을 주지 않고 처리 중인 이미지의 미리보기를 생성하는 데 특히 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/PreviewPointCloud.mdx b/ko/built-in-nodes/PreviewPointCloud.mdx index 836b70faa..d64f6b29a 100644 --- a/ko/built-in-nodes/PreviewPointCloud.mdx +++ b/ko/built-in-nodes/PreviewPointCloud.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PreviewPointCloud" icon: "circle" mode: wide --- -# 포인트 클라우드 미리보기 Preview Point Cloud 노드는 ComfyUI 인터페이스 내에서 3D 포인트 클라우드 파일을 볼 수 있도록 합니다. 포인트 클라우드를 임시 파일로 저장하고 3D 미리보기 창에 표시하며, 모델 데이터와 뷰포트 설정을 추가 처리할 수 있도록 전달합니다. diff --git a/ko/built-in-nodes/PrimitiveBoolean.mdx b/ko/built-in-nodes/PrimitiveBoolean.mdx index dca036dee..c7dd0e356 100644 --- a/ko/built-in-nodes/PrimitiveBoolean.mdx +++ b/ko/built-in-nodes/PrimitiveBoolean.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveBoolean" icon: "circle" mode: wide --- + Boolean 노드는 워크플로우에서 부울(true/false) 값을 전달하는 간단한 방법을 제공합니다. 부울 입력값을 받아 변경 없이 동일한 값을 출력함으로써, 다른 노드의 부울 매개변수를 제어할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/PrimitiveBoundingBox.mdx b/ko/built-in-nodes/PrimitiveBoundingBox.mdx index a1db25411..6677ba042 100644 --- a/ko/built-in-nodes/PrimitiveBoundingBox.mdx +++ b/ko/built-in-nodes/PrimitiveBoundingBox.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveBoundingBox" icon: "circle" mode: wide --- + PrimitiveBoundingBox 노드는 위치와 크기로 정의된 단순한 사각형 영역을 생성합니다. 상단-왼쪽 모서리의 X 및 Y 좌표와 너비 및 높이 값을 입력받아, 워크플로우의 다른 노드에서 사용할 수 있는 경계 상자 데이터 구조를 출력합니다. ## 입력 diff --git a/ko/built-in-nodes/PrimitiveFloat.mdx b/ko/built-in-nodes/PrimitiveFloat.mdx index bf7928f5d..6aee227e5 100644 --- a/ko/built-in-nodes/PrimitiveFloat.mdx +++ b/ko/built-in-nodes/PrimitiveFloat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveFloat" icon: "circle" mode: wide --- + PrimitiveFloat 노드는 워크플로우에서 사용할 수 있는 부동소수점 숫자 값을 생성합니다. 단일 숫자 입력을 받아 동일한 값을 출력하므로, ComfyUI 파이프라인의 여러 노드 간에 float 값을 정의하고 전달할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/PrimitiveInt.mdx b/ko/built-in-nodes/PrimitiveInt.mdx index 40c99c8f1..53ab5a50c 100644 --- a/ko/built-in-nodes/PrimitiveInt.mdx +++ b/ko/built-in-nodes/PrimitiveInt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveInt" icon: "circle" mode: wide --- + PrimitiveInt 노드는 워크플로우에서 정수 값을 간편하게 사용할 수 있는 방법을 제공합니다. 정수 입력을 받아 동일한 값을 출력하므로, 노드 간에 정수 매개변수를 전달하거나 다른 작업을 위한 특정 숫자 값을 설정하는 데 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/PrimitiveString.mdx b/ko/built-in-nodes/PrimitiveString.mdx index 7b2db0e8f..531cb81e6 100644 --- a/ko/built-in-nodes/PrimitiveString.mdx +++ b/ko/built-in-nodes/PrimitiveString.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveString" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PrimitiveString/en.md) String 노드는 워크플로우에서 텍스트 데이터를 간편하게 입력하고 전달할 수 있는 방법을 제공합니다. 텍스트 문자열을 입력받아 변경 없이 동일한 문자열을 출력하므로, 문자열 매개변수가 필요한 다른 노드에 텍스트 입력을 제공하는 데 유용합니다. diff --git a/ko/built-in-nodes/PrimitiveStringMultiline.mdx b/ko/built-in-nodes/PrimitiveStringMultiline.mdx index 8bf0de782..1bf8b918e 100644 --- a/ko/built-in-nodes/PrimitiveStringMultiline.mdx +++ b/ko/built-in-nodes/PrimitiveStringMultiline.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveStringMultiline" icon: "circle" mode: wide --- + PrimitiveStringMultiline 노드는 여러 줄의 텍스트 입력 필드를 제공하여 워크플로우에서 문자열 값을 입력하고 전달할 수 있도록 합니다. 이 노드는 여러 줄에 걸친 텍스트 입력을 받아들이고, 동일한 문자열 값을 변경 없이 출력합니다. 긴 텍스트 콘텐츠나 여러 줄로 구성된 서식 있는 텍스트를 입력해야 할 때 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/QuadrupleCLIPLoader.mdx b/ko/built-in-nodes/QuadrupleCLIPLoader.mdx index f618d5a29..065e6ad97 100644 --- a/ko/built-in-nodes/QuadrupleCLIPLoader.mdx +++ b/ko/built-in-nodes/QuadrupleCLIPLoader.mdx @@ -5,7 +5,6 @@ sidebarTitle: "QuadrupleCLIPLoader" icon: "circle" mode: wide --- -# Quadruple CLIP Loader (쿼드러플 CLIP 로더) QuadrupleCLIPLoader는 ComfyUI의 핵심 노드 중 하나로, HiDream I1 버전 모델을 지원하기 위해 처음 추가되었습니다. 이 노드가 누락된 경우 ComfyUI를 최신 버전으로 업데이트하여 노드 지원을 확인하시기 바랍니다. diff --git a/ko/built-in-nodes/QuiverImageToSVGNode.mdx b/ko/built-in-nodes/QuiverImageToSVGNode.mdx index 74209049d..9e5cd9c0a 100644 --- a/ko/built-in-nodes/QuiverImageToSVGNode.mdx +++ b/ko/built-in-nodes/QuiverImageToSVGNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QuiverImageToSVGNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/QuiverImageToSVGNode/en.md) 이 노드는 Quiver AI의 벡터화 모델을 사용하여 래스터 이미지를 확장 가능한 벡터 그래픽(SVG)으로 변환합니다. 이미지를 외부 API로 전송하여 처리한 후 벡터화된 결과를 반환합니다. diff --git a/ko/built-in-nodes/QuiverTextToSVGNode.mdx b/ko/built-in-nodes/QuiverTextToSVGNode.mdx index 1a260573d..b08aece92 100644 --- a/ko/built-in-nodes/QuiverTextToSVGNode.mdx +++ b/ko/built-in-nodes/QuiverTextToSVGNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "QuiverTextToSVGNode" icon: "circle" mode: wide --- -# Quiver Text to SVG 노드 Quiver Text to SVG 노드는 Quiver AI의 모델을 사용하여 텍스트 설명으로부터 확장 가능한 벡터 그래픽(SVG) 이미지를 생성합니다. 필요에 따라 참조 이미지와 스타일 지침을 제공하여 생성 과정을 안내할 수 있습니다. diff --git a/ko/built-in-nodes/QwenImageDiffsynthControlnet.mdx b/ko/built-in-nodes/QwenImageDiffsynthControlnet.mdx index 6133d5fc6..caa16c16c 100644 --- a/ko/built-in-nodes/QwenImageDiffsynthControlnet.mdx +++ b/ko/built-in-nodes/QwenImageDiffsynthControlnet.mdx @@ -5,7 +5,6 @@ sidebarTitle: "QwenImageDiffsynthControlnet" icon: "circle" mode: wide --- -# QwenImageDiffsynthControlnet 노드 QwenImageDiffsynthControlnet 노드는 확산 합성 제어 네트워크 패치를 적용하여 기본 모델의 동작을 수정합니다. 이미지 입력과 선택적 마스크를 사용하여 조정 가능한 강도로 모델의 생성 과정을 안내하며, 제어 네트워크의 영향을 통합한 패치된 모델을 생성하여 보다 제어된 이미지 합성을 가능하게 합니다. diff --git a/ko/built-in-nodes/RTDETR_detect.mdx b/ko/built-in-nodes/RTDETR_detect.mdx index 91462a50e..0a69cb2da 100644 --- a/ko/built-in-nodes/RTDETR_detect.mdx +++ b/ko/built-in-nodes/RTDETR_detect.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RTDETR_detect" icon: "circle" mode: wide --- + RT-DETR 탐지 노드는 RT-DETR 모델을 사용하여 입력 이미지에서 객체 탐지를 수행합니다. 객체를 식별하고, 주변에 경계 상자를 그린 후 COCO 데이터셋 클래스에 따라 레이블을 지정합니다. 신뢰도 점수, 객체 클래스별로 결과를 필터링할 수 있으며, 탐지 결과의 총 개수를 제한할 수도 있습니다. ## 입력 diff --git a/ko/built-in-nodes/RandomCropImages.mdx b/ko/built-in-nodes/RandomCropImages.mdx index 90ebc3fc8..2c7481d23 100644 --- a/ko/built-in-nodes/RandomCropImages.mdx +++ b/ko/built-in-nodes/RandomCropImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RandomCropImages" icon: "circle" mode: wide --- + **Random Crop Images 노드** Random Crop Images 노드는 각 입력 이미지에서 무작위로 직사각형 영역을 선택하여 지정된 너비와 높이로 자릅니다. 이는 주로 데이터 증강을 위해 사용되어 학습 이미지의 변형을 생성합니다. 자르기 위치는 시드 값에 의해 결정되므로 동일한 자르기를 재현할 수 있습니다. @@ -24,7 +25,7 @@ Random Crop Images 노드는 각 입력 이미지에서 무작위로 직사각 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `image` | 무작위 자르기가 적용된 결과 이미지입니다. | IMAGE | +| `images` | 무작위 자르기가 적용된 결과 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RandomCropImages/ko.md) diff --git a/ko/built-in-nodes/RandomNoise.mdx b/ko/built-in-nodes/RandomNoise.mdx index d50d339d6..99deb4e0b 100644 --- a/ko/built-in-nodes/RandomNoise.mdx +++ b/ko/built-in-nodes/RandomNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RandomNoise" icon: "circle" mode: wide --- + RandomNoise 노드는 시드 값을 기반으로 무작위 노이즈 패턴을 생성합니다. 이 노드는 다양한 이미지 처리 및 생성 작업에 사용할 수 있는 재현 가능한 노이즈를 생성합니다. 동일한 시드는 항상 동일한 노이즈 패턴을 생성하므로 여러 번 실행해도 일관된 결과를 얻을 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/RebatchImages.mdx b/ko/built-in-nodes/RebatchImages.mdx index 3d81908a7..02d965a9f 100644 --- a/ko/built-in-nodes/RebatchImages.mdx +++ b/ko/built-in-nodes/RebatchImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RebatchImages" icon: "circle" mode: wide --- + ## 개요 RebatchImages 노드는 이미지 배치를 새로운 배치 구성으로 재구성하여 지정된 배치 크기에 맞게 조정하도록 설계되었습니다. 이 프로세스는 배치 작업에서 이미지 데이터 처리를 관리하고 최적화하는 데 필수적이며, 효율적인 처리를 위해 원하는 배치 크기에 따라 이미지를 그룹화합니다. diff --git a/ko/built-in-nodes/RebatchLatents.mdx b/ko/built-in-nodes/RebatchLatents.mdx index 8029ea859..ebd4389f6 100644 --- a/ko/built-in-nodes/RebatchLatents.mdx +++ b/ko/built-in-nodes/RebatchLatents.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RebatchLatents" icon: "circle" mode: wide --- + ## 개요 RebatchLatents 노드는 지정된 배치 크기에 따라 잠재 표현들의 배치를 새로운 배치 구성으로 재구성합니다. 잠재 샘플들이 적절하게 그룹화되도록 하여 차원과 크기의 변동을 처리하며, 추가 처리나 모델 추론을 용이하게 합니다. diff --git a/ko/built-in-nodes/RecordAudio.mdx b/ko/built-in-nodes/RecordAudio.mdx index a1cc39ed2..f4615ac56 100644 --- a/ko/built-in-nodes/RecordAudio.mdx +++ b/ko/built-in-nodes/RecordAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecordAudio" icon: "circle" mode: wide --- + RecordAudio 노드는 오디오 녹음 인터페이스를 통해 녹음되거나 선택된 오디오 파일을 불러옵니다. 이 노드는 오디오 파일을 처리하여 워크플로우의 다른 오디오 처리 노드에서 사용할 수 있는 파형 형식으로 변환합니다. 샘플 속도를 자동으로 감지하고 추가 조작을 위해 오디오 데이터를 준비합니다. ## 입력 diff --git a/ko/built-in-nodes/RecraftColorRGB.mdx b/ko/built-in-nodes/RecraftColorRGB.mdx index ae083306e..5b8fefeef 100644 --- a/ko/built-in-nodes/RecraftColorRGB.mdx +++ b/ko/built-in-nodes/RecraftColorRGB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftColorRGB" icon: "circle" mode: wide --- + 개별 빨간색, 녹색, 파란색 값을 지정하여 Recraft 색상을 생성합니다. 이 노드는 RGB 정수 값(0-255)을 입력받아 다른 Recraft 작업에서 사용할 수 있는 Recraft 색상 형식으로 변환합니다. 또한 기존 Recraft 색상 체인을 선택적으로 제공하여 새 색상으로 확장할 수도 있습니다. ## 입력 diff --git a/ko/built-in-nodes/RecraftControls.mdx b/ko/built-in-nodes/RecraftControls.mdx index 2129ca93a..3120082fa 100644 --- a/ko/built-in-nodes/RecraftControls.mdx +++ b/ko/built-in-nodes/RecraftControls.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftControls" icon: "circle" mode: wide --- + 다음은 요청하신 번역 결과입니다. --- @@ -24,7 +25,7 @@ Recraft 생성을 사용자 정의하기 위한 Recraft 컨트롤을 생성합 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `recraft_controls` | 색상 설정이 포함된 구성된 Recraft 컨트롤 | CONTROLS | +| `recraft 제어` | 색상 설정이 포함된 구성된 Recraft 컨트롤 | CONTROLS | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftControls/ko.md) diff --git a/ko/built-in-nodes/RecraftCreateStyleNode.mdx b/ko/built-in-nodes/RecraftCreateStyleNode.mdx index bedb69e01..9a7b38889 100644 --- a/ko/built-in-nodes/RecraftCreateStyleNode.mdx +++ b/ko/built-in-nodes/RecraftCreateStyleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCreateStyleNode" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreateStyleNode/en.md) 이 노드는 참조 이미지를 업로드하여 이미지 생성을 위한 사용자 정의 스타일을 생성합니다. 새 스타일을 정의하기 위해 1~5개의 이미지를 업로드할 수 있으며, 노드는 다른 Recraft 노드에서 사용할 수 있는 고유한 스타일 ID를 반환합니다. 업로드된 모든 이미지의 총 파일 크기는 5MB를 초과할 수 없습니다. diff --git a/ko/built-in-nodes/RecraftCreativeUpscaleNode.mdx b/ko/built-in-nodes/RecraftCreativeUpscaleNode.mdx index c497753a3..0018986fb 100644 --- a/ko/built-in-nodes/RecraftCreativeUpscaleNode.mdx +++ b/ko/built-in-nodes/RecraftCreativeUpscaleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCreativeUpscaleNode" icon: "circle" mode: wide --- + Recraft 창의적 업스케일 이미지 노드는 래스터 이미지의 해상도를 높여 향상시킵니다. 이미지 내 작은 세부 사항과 얼굴을 개선하는 데 중점을 둔 "창의적 업스케일" 프로세스를 사용합니다. 이 작업은 외부 API를 통해 동기식으로 수행됩니다. ## 입력 diff --git a/ko/built-in-nodes/RecraftCrispUpscaleNode.mdx b/ko/built-in-nodes/RecraftCrispUpscaleNode.mdx index bb32bd9fb..adefc222d 100644 --- a/ko/built-in-nodes/RecraftCrispUpscaleNode.mdx +++ b/ko/built-in-nodes/RecraftCrispUpscaleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCrispUpscaleNode" icon: "circle" mode: wide --- + 이미지를 동기 방식으로 업스케일합니다. '선명한 업스케일' 도구를 사용하여 제공된 래스터 이미지를 향상시켜 해상도를 높이고 이미지를 더 선명하고 깨끗하게 만듭니다. ## 입력 diff --git a/ko/built-in-nodes/RecraftImageInpaintingNode.mdx b/ko/built-in-nodes/RecraftImageInpaintingNode.mdx index 5f7f74b7d..51dbeedf7 100644 --- a/ko/built-in-nodes/RecraftImageInpaintingNode.mdx +++ b/ko/built-in-nodes/RecraftImageInpaintingNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftImageInpaintingNode" icon: "circle" mode: wide --- + 이 노드는 텍스트 프롬프트와 마스크를 기반으로 이미지의 특정 영역을 수정합니다. Recraft API를 사용하여 마스크된 영역만 지능적으로 편집하고 나머지 이미지는 변경하지 않습니다. ## 입력 diff --git a/ko/built-in-nodes/RecraftImageToImageNode.mdx b/ko/built-in-nodes/RecraftImageToImageNode.mdx index 2747ddff2..6838b0995 100644 --- a/ko/built-in-nodes/RecraftImageToImageNode.mdx +++ b/ko/built-in-nodes/RecraftImageToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftImageToImageNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageToImageNode/en.md) 이 노드는 텍스트 프롬프트와 강도 매개변수를 기반으로 기존 이미지를 수정합니다. Recraft API를 사용하여 제공된 설명에 따라 입력 이미지를 변환하면서, 강도 설정에 따라 원본 이미지와의 일부 유사성을 유지합니다. diff --git a/ko/built-in-nodes/RecraftRemoveBackgroundNode.mdx b/ko/built-in-nodes/RecraftRemoveBackgroundNode.mdx index 2a7a6ec9d..e04271c17 100644 --- a/ko/built-in-nodes/RecraftRemoveBackgroundNode.mdx +++ b/ko/built-in-nodes/RecraftRemoveBackgroundNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftRemoveBackgroundNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftRemoveBackgroundNode/en.md) 이 노드는 Recraft API 서비스를 사용하여 이미지에서 배경을 제거합니다. 입력 배치의 각 이미지를 처리한 후, 투명 배경이 적용된 처리 이미지와 제거된 배경 영역을 나타내는 해당 알파 마스크를 반환합니다. diff --git a/ko/built-in-nodes/RecraftReplaceBackgroundNode.mdx b/ko/built-in-nodes/RecraftReplaceBackgroundNode.mdx index 7e94f29c7..f26b89b70 100644 --- a/ko/built-in-nodes/RecraftReplaceBackgroundNode.mdx +++ b/ko/built-in-nodes/RecraftReplaceBackgroundNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftReplaceBackgroundNode" icon: "circle" mode: wide --- + 제공된 프롬프트를 기반으로 이미지의 배경을 교체합니다. 이 노드는 Recraft API를 사용하여 텍스트 설명에 따라 이미지의 새 배경을 생성하므로, 주요 피사체는 그대로 유지하면서 배경을 완전히 변환할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx b/ko/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx index fa8ecb956..e3c50da4b 100644 --- a/ko/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx +++ b/ko/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3DigitalIllustration" icon: "circle" mode: wide --- + 이 노드는 Recraft API와 함께 사용할 스타일을 구성하며, 특히 "digital_illustration" 스타일을 선택합니다. 생성된 이미지의 예술적 방향을 더욱 세분화하기 위해 선택적 하위 스타일을 지정할 수 있습니다. ## 입력 @@ -17,7 +18,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `recraft_style` | 선택한 "digital_illustration" 스타일과 선택적 하위 스타일이 포함된 구성된 스타일 객체로, 다른 Recraft API 노드에 전달할 준비가 되었습니다. | STYLEV3 | +| `recraft 스타일` | 선택한 "digital_illustration" 스타일과 선택적 하위 스타일이 포함된 구성된 스타일 객체로, 다른 Recraft API 노드에 전달할 준비가 되었습니다. | STYLEV3 | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3DigitalIllustration/ko.md) diff --git a/ko/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx b/ko/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx index d31e8c9b2..e7ea63574 100644 --- a/ko/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx +++ b/ko/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3InfiniteStyleLibrary" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3InfiniteStyleLibrary/en.md) 이 노드는 기존 UUID를 사용하여 Recraft의 Infinite Style Library에서 스타일을 선택할 수 있도록 합니다. 제공된 스타일 식별자를 기반으로 스타일 정보를 검색하고, 이를 다른 Recraft 노드에서 사용할 수 있도록 반환합니다. @@ -21,7 +22,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `recraft_style` | Recraft의 Infinite Style Library에서 선택한 스타일 객체입니다. | STYLEV3 | +| `recraft 스타일` | Recraft의 Infinite Style Library에서 선택한 스타일 객체입니다. | STYLEV3 | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3InfiniteStyleLibrary/ko.md) diff --git a/ko/built-in-nodes/RecraftStyleV3LogoRaster.mdx b/ko/built-in-nodes/RecraftStyleV3LogoRaster.mdx index d5302c5e1..2d7b99413 100644 --- a/ko/built-in-nodes/RecraftStyleV3LogoRaster.mdx +++ b/ko/built-in-nodes/RecraftStyleV3LogoRaster.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3LogoRaster" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3LogoRaster/en.md) 이 노드는 로고 이미지 생성을 위한 로고 래스터 스타일과 선택적 하위 스타일을 선택합니다. 래스터 기반 시각적 처리를 적용한 로고 디자인 제작에 특화되어 있습니다. @@ -19,7 +20,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `recraft_style` | 로고 래스터 스타일과 선택된 하위 스타일을 포함한 선택된 Recraft 스타일 구성입니다. | CUSTOM | +| `recraft 스타일` | 로고 래스터 스타일과 선택된 하위 스타일을 포함한 선택된 Recraft 스타일 구성입니다. | CUSTOM | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3LogoRaster/ko.md) diff --git a/ko/built-in-nodes/RecraftStyleV3RealisticImage.mdx b/ko/built-in-nodes/RecraftStyleV3RealisticImage.mdx index 359728ca9..ecf0bafad 100644 --- a/ko/built-in-nodes/RecraftStyleV3RealisticImage.mdx +++ b/ko/built-in-nodes/RecraftStyleV3RealisticImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3RealisticImage" icon: "circle" mode: wide --- + 이 노드는 Recraft의 API를 사용하여 사실적인 이미지를 생성하기 위한 스타일 구성을 생성합니다. `realistic_image` 스타일을 선택하고, 선택적으로 하위 스타일을 지정하여 출력 결과를 미세 조정할 수 있습니다. ## 입력 @@ -17,7 +18,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `recraft_style` | `realistic_image` 스타일과 선택한 하위 스타일 설정을 포함하는 Recraft 스타일 구성 객체입니다. 이 출력은 스타일 입력을 허용하는 다른 Recraft 노드에 연결할 수 있습니다. | STYLEV3 | +| `recraft 스타일` | `realistic_image` 스타일과 선택한 하위 스타일 설정을 포함하는 Recraft 스타일 구성 객체입니다. 이 출력은 스타일 입력을 허용하는 다른 Recraft 노드에 연결할 수 있습니다. | STYLEV3 | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3RealisticImage/ko.md) diff --git a/ko/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx b/ko/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx index 37ccb04d8..1a4b3d073 100644 --- a/ko/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx +++ b/ko/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3VectorIllustrationNode" icon: "circle" mode: wide --- + 이 노드는 Recraft API에서 사용할 스타일을 구성하며, 특히 `vector_illustration` 스타일을 선택합니다. 해당 카테고리 내에서 더 구체적인 하위 스타일을 선택적으로 지정할 수 있습니다. 이 노드는 다른 Recraft API 노드에 전달할 수 있는 스타일 구성 객체를 출력합니다. ## 입력 diff --git a/ko/built-in-nodes/RecraftTextToImageNode.mdx b/ko/built-in-nodes/RecraftTextToImageNode.mdx index 58c60b8c1..bf17a4a22 100644 --- a/ko/built-in-nodes/RecraftTextToImageNode.mdx +++ b/ko/built-in-nodes/RecraftTextToImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RecraftTextToImageNode" icon: "circle" mode: wide --- -# Recraft 텍스트-이미지 생성 노드 프롬프트와 해상도를 기반으로 이미지를 동기식으로 생성합니다. 이 노드는 Recraft API에 연결하여 지정된 크기와 선택적 스타일 및 제어 매개변수를 사용하여 텍스트 설명으로부터 이미지를 만듭니다. diff --git a/ko/built-in-nodes/RecraftTextToVectorNode.mdx b/ko/built-in-nodes/RecraftTextToVectorNode.mdx index 79912a23d..7f4bd1e2d 100644 --- a/ko/built-in-nodes/RecraftTextToVectorNode.mdx +++ b/ko/built-in-nodes/RecraftTextToVectorNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftTextToVectorNode" icon: "circle" mode: wide --- + 텍스트 프롬프트와 해상도를 기반으로 SVG 벡터 일러스트레이션을 동기식으로 생성합니다. 이 노드는 프롬프트를 Recraft API로 전송하고 생성된 SVG 콘텐츠를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/RecraftV4TextToImageNode.mdx b/ko/built-in-nodes/RecraftV4TextToImageNode.mdx index e59806287..da93a7129 100644 --- a/ko/built-in-nodes/RecraftV4TextToImageNode.mdx +++ b/ko/built-in-nodes/RecraftV4TextToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftV4TextToImageNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하시거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftV4TextToImageNode/en.md) 이 노드는 Recraft V4 또는 V4 Pro AI 모델을 사용하여 텍스트 설명으로부터 이미지를 생성합니다. 프롬프트를 외부 API로 전송하고 생성된 이미지를 반환합니다. 모델, 이미지 크기 및 생성할 이미지 수를 지정하여 출력을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/RecraftV4TextToVectorNode.mdx b/ko/built-in-nodes/RecraftV4TextToVectorNode.mdx index 49d9adbbd..fcd7130d2 100644 --- a/ko/built-in-nodes/RecraftV4TextToVectorNode.mdx +++ b/ko/built-in-nodes/RecraftV4TextToVectorNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RecraftV4TextToVectorNode" icon: "circle" mode: wide --- -# Recraft V4 텍스트-벡터 노드 Recraft V4 텍스트-벡터 노드는 텍스트 설명으로부터 확장 가능한 벡터 그래픽(SVG) 일러스트레이션을 생성합니다. 외부 API에 연결하여 Recraft V4 또는 Recraft V4 Pro 모델을 이미지 생성에 사용합니다. 이 노드는 프롬프트를 기반으로 하나 이상의 SVG 이미지를 출력합니다. diff --git a/ko/built-in-nodes/RecraftVectorizeImageNode.mdx b/ko/built-in-nodes/RecraftVectorizeImageNode.mdx index fef8c7a7e..ee0dd7eb2 100644 --- a/ko/built-in-nodes/RecraftVectorizeImageNode.mdx +++ b/ko/built-in-nodes/RecraftVectorizeImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftVectorizeImageNode" icon: "circle" mode: wide --- + 입력 이미지로부터 SVG를 동기식으로 생성합니다. 이 노드는 입력 배치의 각 이미지를 처리하고 결과를 단일 SVG 출력으로 결합하여 래스터 이미지를 벡터 그래픽 형식으로 변환합니다. ## 입력 diff --git a/ko/built-in-nodes/ReferenceLatent.mdx b/ko/built-in-nodes/ReferenceLatent.mdx index abdfe2b24..08368f748 100644 --- a/ko/built-in-nodes/ReferenceLatent.mdx +++ b/ko/built-in-nodes/ReferenceLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReferenceLatent" icon: "circle" mode: wide --- + 이 노드는 편집 모델의 가이딩 잠재 변수를 설정합니다. 조건화 데이터와 선택적 잠재 변수 입력을 받아 참조 잠재 변수 정보를 포함하도록 조건화를 수정합니다. 모델이 지원하는 경우 여러 개의 ReferenceLatent 노드를 연결하여 여러 참조 이미지를 설정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ReferenceTimbreAudio.mdx b/ko/built-in-nodes/ReferenceTimbreAudio.mdx index 68691f409..44e6b5cf9 100644 --- a/ko/built-in-nodes/ReferenceTimbreAudio.mdx +++ b/ko/built-in-nodes/ReferenceTimbreAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReferenceTimbreAudio" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReferenceTimbreAudio/en.md) 이 노드는 "ace step 1.5" 프로세스에서 사용할 기준 오디오 음색을 설정합니다. 컨디셔닝 입력과 선택적으로 오디오의 잠재 표현을 받아, 해당 잠재 데이터를 컨디셔닝에 첨부하여 워크플로우의 후속 노드에서 사용할 수 있도록 합니다. diff --git a/ko/built-in-nodes/RegexExtract.mdx b/ko/built-in-nodes/RegexExtract.mdx index 06193ad90..dfa8b878c 100644 --- a/ko/built-in-nodes/RegexExtract.mdx +++ b/ko/built-in-nodes/RegexExtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexExtract" icon: "circle" mode: wide --- + 다음은 ComfyUI RegexExtract 노드 문서의 한국어 번역입니다. --- diff --git a/ko/built-in-nodes/RegexMatch.mdx b/ko/built-in-nodes/RegexMatch.mdx index 8f406f375..1f2400ab5 100644 --- a/ko/built-in-nodes/RegexMatch.mdx +++ b/ko/built-in-nodes/RegexMatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexMatch" icon: "circle" mode: wide --- + RegexMatch 노드는 텍스트 문자열에 지정된 정규 표현식 패턴과 일치하는 항목이 있는지 확인합니다. 입력 문자열을 검색하여 패턴이 텍스트 내에서 발견되었는지 여부를 예/아니오 결과로 반환합니다. 대소문자 구분 없음 일치 또는 여러 줄 모드와 같은 옵션을 활성화하여 검색 방식을 조정할 수 있습니다. ## 입력 @@ -21,7 +22,7 @@ RegexMatch 노드는 텍스트 문자열에 지정된 정규 표현식 패턴과 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `matches` | 정규 표현식 패턴이 입력 문자열의 일부와 일치하면 True를 반환하고, 그렇지 않으면 False를 반환합니다 | BOOLEAN | +| `일치 항목` | 정규 표현식 패턴이 입력 문자열의 일부와 일치하면 True를 반환하고, 그렇지 않으면 False를 반환합니다 | BOOLEAN | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexMatch/ko.md) diff --git a/ko/built-in-nodes/RegexReplace.mdx b/ko/built-in-nodes/RegexReplace.mdx index bcc2072e6..277b08939 100644 --- a/ko/built-in-nodes/RegexReplace.mdx +++ b/ko/built-in-nodes/RegexReplace.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RegexReplace" icon: "circle" mode: wide --- -# RegexReplace 노드 RegexReplace 노드는 정규 표현식 패턴을 사용하여 문자열에서 텍스트를 찾고 바꿉니다. 텍스트 패턴을 검색하여 새 텍스트로 바꿀 수 있으며, 대소문자 구분, 여러 줄 일치, 바꾸기 횟수 제한 등 패턴 일치 작동 방식을 제어하는 옵션을 제공합니다. diff --git a/ko/built-in-nodes/RemoveBackground.mdx b/ko/built-in-nodes/RemoveBackground.mdx index ae6f4645f..b7861c1ee 100644 --- a/ko/built-in-nodes/RemoveBackground.mdx +++ b/ko/built-in-nodes/RemoveBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RemoveBackground" icon: "circle" mode: wide --- + ## 개요 Remove Background 노드는 배경 제거 모델을 사용하여 입력 이미지에서 전경 피사체를 배경과 분리하는 마스크를 생성합니다. 이미지와 배경 제거 모델을 입력받아 주요 피사체를 강조하는 마스크를 출력합니다. diff --git a/ko/built-in-nodes/RenderSplat.mdx b/ko/built-in-nodes/RenderSplat.mdx index 54bae1423..e00bf4fc7 100644 --- a/ko/built-in-nodes/RenderSplat.mdx +++ b/ko/built-in-nodes/RenderSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RenderSplat" icon: "circle" mode: wide --- -# Render Splat 비등방성 EWA 래스터라이저를 사용하여 가우시안 스플랫을 이미지로 렌더링합니다. 방향성 타원형 스플랫, 안티앨리어싱 및 깊이 정렬된 전면-후면 렌더링을 지원합니다. 카메라는 `camera_info` 입력에서 가져오거나, 비워두면 스플랫이 자동으로 프레임에 맞춰집니다. 1보다 큰 프레임 값을 설정하면 턴테이블 배치 이미지가 생성되어 Video 노드에 공급할 수 있습니다. @@ -30,7 +29,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | |-----------|------|------------| -| `mask` | 가우시안 스플랫의 렌더링된 이미지 | IMAGE | +| `image` | 가우시안 스플랫의 렌더링된 이미지 | IMAGE | | `mask` | 렌더링된 스플랫의 알파 마스크 | MASK | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RenderSplat/ko.md) diff --git a/ko/built-in-nodes/RenormCFG.mdx b/ko/built-in-nodes/RenormCFG.mdx index 6f44b2d61..a1635d484 100644 --- a/ko/built-in-nodes/RenormCFG.mdx +++ b/ko/built-in-nodes/RenormCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RenormCFG" icon: "circle" mode: wide --- + RenormCFG 노드는 조건부 스케일링과 정규화를 적용하여 확산 모델의 분류기-자유 유도(CFG) 과정을 수정합니다. 이미지 생성 중 조건부 예측과 무조건부 예측 간의 영향을 제어하기 위해 지정된 타임스텝 임계값과 재정규화 계수에 따라 노이즈 제거 과정을 조정합니다. ## 입력 diff --git a/ko/built-in-nodes/RepeatImageBatch.mdx b/ko/built-in-nodes/RepeatImageBatch.mdx index 986aace7d..b8f746c93 100644 --- a/ko/built-in-nodes/RepeatImageBatch.mdx +++ b/ko/built-in-nodes/RepeatImageBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RepeatImageBatch" icon: "circle" mode: wide --- + ## 개요 RepeatImageBatch 노드는 지정된 이미지를 특정 횟수만큼 복제하여 동일한 이미지 배치를 생성하도록 설계되었습니다. 이 기능은 배치 처리나 데이터 증강과 같이 동일한 이미지의 여러 인스턴스가 필요한 작업에 유용합니다. diff --git a/ko/built-in-nodes/RepeatLatentBatch.mdx b/ko/built-in-nodes/RepeatLatentBatch.mdx index 80d4d1e2f..18dfd16a0 100644 --- a/ko/built-in-nodes/RepeatLatentBatch.mdx +++ b/ko/built-in-nodes/RepeatLatentBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RepeatLatentBatch" icon: "circle" mode: wide --- + RepeatLatentBatch 노드는 잠재 표현 배치를 지정된 횟수만큼 복제하는 기능을 수행합니다. 여기에는 노이즈 마스크나 배치 인덱스와 같은 추가 데이터가 포함될 수 있습니다. 이 기능은 데이터 증강이나 특정 생성 작업과 같이 동일한 잠재 데이터의 여러 인스턴스가 필요한 작업에 매우 중요합니다. ## 입력 diff --git a/ko/built-in-nodes/ReplaceText.mdx b/ko/built-in-nodes/ReplaceText.mdx index 92d923196..e6eb7b287 100644 --- a/ko/built-in-nodes/ReplaceText.mdx +++ b/ko/built-in-nodes/ReplaceText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReplaceText" icon: "circle" mode: wide --- + 텍스트 바꾸기(Replace Text) 노드는 간단한 텍스트 치환을 수행합니다. 입력 텍스트 내에서 지정된 텍스트 조각을 검색하여 모든 항목을 새 텍스트로 바꿉니다. 이 작업은 노드에 제공된 모든 텍스트 입력에 적용됩니다. ## 입력 @@ -19,7 +20,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `text` | `find` 텍스트의 모든 항목이 `replace` 텍스트로 바뀐 처리된 텍스트입니다. | STRING | +| `texts` | `find` 텍스트의 모든 항목이 `replace` 텍스트로 바뀐 처리된 텍스트입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReplaceText/ko.md) diff --git a/ko/built-in-nodes/ReplaceVideoLatentFrames.mdx b/ko/built-in-nodes/ReplaceVideoLatentFrames.mdx index 6cc95a12e..34ed9bf63 100644 --- a/ko/built-in-nodes/ReplaceVideoLatentFrames.mdx +++ b/ko/built-in-nodes/ReplaceVideoLatentFrames.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReplaceVideoLatentFrames" icon: "circle" mode: wide --- + ReplaceVideoLatentFrames 노드는 소스 잠재 비디오의 프레임을 대상 잠재 비디오에 삽입하며, 지정된 프레임 인덱스부터 시작합니다. 소스 잠재가 제공되지 않으면 대상 잠재가 변경되지 않은 상태로 반환됩니다. 이 노드는 음수 인덱싱을 처리하며, 소스 프레임이 대상 내에 맞지 않을 경우 경고를 출력합니다. ## 입력 diff --git a/ko/built-in-nodes/Reroute.mdx b/ko/built-in-nodes/Reroute.mdx index 5cf4c87eb..acf938f4d 100644 --- a/ko/built-in-nodes/Reroute.mdx +++ b/ko/built-in-nodes/Reroute.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Reroute" icon: "circle" mode: wide --- + **노드 이름:** 경로 재지정 노드 **노드 목적:** 주로 ComfyUI 워크플로우에서 지나치게 긴 연결선의 로직을 정리하는 데 사용됩니다. diff --git a/ko/built-in-nodes/RescaleCFG.mdx b/ko/built-in-nodes/RescaleCFG.mdx index 16a9b597f..b6a76300a 100644 --- a/ko/built-in-nodes/RescaleCFG.mdx +++ b/ko/built-in-nodes/RescaleCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RescaleCFG" icon: "circle" mode: wide --- + RescaleCFG 노드는 모델 출력의 조건부 및 비조건부 스케일을 지정된 승수에 따라 조정하여 보다 균형 잡히고 통제된 생성 과정을 달성하도록 설계되었습니다. 이 노드는 모델 출력을 재조정하여 조건부 및 비조건부 구성 요소의 영향을 수정함으로써 모델의 성능이나 출력 품질을 향상시킬 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ResizeAndPadImage.mdx b/ko/built-in-nodes/ResizeAndPadImage.mdx index cfe99995c..61734157f 100644 --- a/ko/built-in-nodes/ResizeAndPadImage.mdx +++ b/ko/built-in-nodes/ResizeAndPadImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeAndPadImage" icon: "circle" mode: wide --- + ResizeAndPadImage 노드는 이미지의 원본 비율을 유지하면서 지정된 크기에 맞게 크기를 조정합니다. 대상 너비와 높이에 맞게 이미지를 비례적으로 축소한 후, 남는 공간을 채우기 위해 가장자리에 패딩을 추가합니다. 패딩 색상과 보간 방법을 사용자 지정하여 패딩 영역의 모양과 크기 조정 품질을 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/ResizeImageMaskNode.mdx b/ko/built-in-nodes/ResizeImageMaskNode.mdx index 724b0a7d9..18594d1bf 100644 --- a/ko/built-in-nodes/ResizeImageMaskNode.mdx +++ b/ko/built-in-nodes/ResizeImageMaskNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImageMaskNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImageMaskNode/en.md) 이미지/마스크 크기 조정 노드는 입력 이미지 또는 마스크의 크기를 변경하는 여러 방법을 제공합니다. 배율을 사용하여 크기를 조정하거나, 특정 크기를 설정하거나, 다른 입력의 크기와 일치시키거나, 픽셀 수를 기준으로 조정할 수 있으며, 다양한 보간 방법을 사용하여 품질을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/ResizeImagesByLongerEdge.mdx b/ko/built-in-nodes/ResizeImagesByLongerEdge.mdx index 92de01ecb..028e18d8c 100644 --- a/ko/built-in-nodes/ResizeImagesByLongerEdge.mdx +++ b/ko/built-in-nodes/ResizeImagesByLongerEdge.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ResizeImagesByLongerEdge" icon: "circle" mode: wide --- -# 긴 변 기준 이미지 크기 조정 노드 긴 변 기준 이미지 크기 조정 노드는 하나 이상의 이미지의 가장 긴 변이 지정된 목표 길이와 일치하도록 크기를 조정합니다. 너비와 높이 중 어느 쪽이 더 긴지 자동으로 판단하여 다른 쪽 치수를 비례적으로 조정함으로써 원본 종횡비를 유지합니다. 이는 이미지의 가장 큰 치수를 기준으로 이미지 크기를 표준화할 때 유용합니다. @@ -20,7 +19,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `image` | 크기가 조정된 이미지 또는 이미지 배치입니다. 출력은 입력과 동일한 수의 이미지를 가지며, 각 이미지의 긴 변이 지정된 `longer_edge` 길이와 일치합니다. | IMAGE | +| `images` | 크기가 조정된 이미지 또는 이미지 배치입니다. 출력은 입력과 동일한 수의 이미지를 가지며, 각 이미지의 긴 변이 지정된 `longer_edge` 길이와 일치합니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByLongerEdge/ko.md) diff --git a/ko/built-in-nodes/ResizeImagesByShorterEdge.mdx b/ko/built-in-nodes/ResizeImagesByShorterEdge.mdx index 0ac33b4c8..2c152fffa 100644 --- a/ko/built-in-nodes/ResizeImagesByShorterEdge.mdx +++ b/ko/built-in-nodes/ResizeImagesByShorterEdge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImagesByShorterEdge" icon: "circle" mode: wide --- + 이 노드는 원본 이미지의 가로세로 비율을 유지하면서 짧은 쪽 가장자리가 지정된 길이와 일치하도록 이미지 크기를 조정합니다. 짧은 쪽의 목표 길이를 기준으로 새 치수를 계산하고 크기가 조정된 이미지를 반환합니다. ## 입력 @@ -18,7 +19,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `image` | 짧은 쪽 가장자리가 지정된 목표 길이와 일치하도록 크기가 조정된 이미지입니다. | IMAGE | +| `images` | 짧은 쪽 가장자리가 지정된 목표 길이와 일치하도록 크기가 조정된 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByShorterEdge/ko.md) diff --git a/ko/built-in-nodes/ResolutionBucket.mdx b/ko/built-in-nodes/ResolutionBucket.mdx index 9c7a644e0..0f3ce6231 100644 --- a/ko/built-in-nodes/ResolutionBucket.mdx +++ b/ko/built-in-nodes/ResolutionBucket.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResolutionBucket" icon: "circle" mode: wide --- + 이 노드는 잠재 이미지 목록과 해당 조건화 데이터를 해상도별로 정리합니다. 동일한 높이와 너비를 가진 항목들을 함께 그룹화하여 각 고유 해상도에 대해 별도의 배치를 생성합니다. 이 과정은 모델이 동일한 크기의 여러 항목을 함께 처리할 수 있도록 하여 효율적인 학습을 위한 데이터 준비에 유용합니다. ## 입력 @@ -20,7 +21,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `conditioning` | 해상도 버킷별로 하나씩 배치된 잠재 딕셔너리 목록입니다. | LATENT | +| `latents` | 해상도 버킷별로 하나씩 배치된 잠재 딕셔너리 목록입니다. | LATENT | | `conditioning` | 해상도 버킷별로 하나씩 조건화 목록의 목록입니다. | CONDITIONING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResolutionBucket/ko.md) diff --git a/ko/built-in-nodes/ResolutionSelector.mdx b/ko/built-in-nodes/ResolutionSelector.mdx index 97e7f2d11..83404f40e 100644 --- a/ko/built-in-nodes/ResolutionSelector.mdx +++ b/ko/built-in-nodes/ResolutionSelector.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResolutionSelector" icon: "circle" mode: wide --- + 해상도 선택기 노드는 선택한 종횡비와 목표 총 해상도(메가픽셀 단위)를 기준으로 이미지의 픽셀 너비와 높이를 계산합니다. 이는 빈 잠재 이미지 노드와 같은 다른 노드에 일관된 크기를 생성하는 데 유용합니다. 출력 크기는 항상 8의 가장 가까운 배수로 반올림됩니다. ## 입력 @@ -18,8 +19,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `높이` | 계산된 픽셀 너비로, 8의 배수입니다. | INT | -| `height` | 계산된 픽셀 높이로, 8의 배수입니다. | INT | +| `너비` | 계산된 픽셀 너비로, 8의 배수입니다. | INT | +| `높이` | 계산된 픽셀 높이로, 8의 배수입니다. | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResolutionSelector/ko.md) diff --git a/ko/built-in-nodes/ReveImageCreateNode.mdx b/ko/built-in-nodes/ReveImageCreateNode.mdx index 97b373e5b..f65a4dd3f 100644 --- a/ko/built-in-nodes/ReveImageCreateNode.mdx +++ b/ko/built-in-nodes/ReveImageCreateNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ReveImageCreateNode" icon: "circle" mode: wide --- -# Reve 이미지 생성 노드 Reve 이미지 생성 노드는 Reve AI 모델을 사용하여 텍스트 설명으로부터 이미지를 생성합니다. 텍스트 프롬프트를 Reve API로 전송하고 생성된 이미지를 반환합니다. 이미지의 종횡비를 제어하고 업스케일링과 같은 선택적 후처리 효과를 적용할 수 있습니다. diff --git a/ko/built-in-nodes/ReveImageEditNode.mdx b/ko/built-in-nodes/ReveImageEditNode.mdx index ef9aac3ad..a5afcffcf 100644 --- a/ko/built-in-nodes/ReveImageEditNode.mdx +++ b/ko/built-in-nodes/ReveImageEditNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ReveImageEditNode" icon: "circle" mode: wide --- -# Reve 이미지 편집 노드 Reve 이미지 편집 노드는 텍스트 설명을 기반으로 기존 이미지를 수정할 수 있게 해줍니다. Reve API를 사용하여 사용자의 지침을 해석하고 제공된 이미지에 요청된 변경 사항을 적용합니다. diff --git a/ko/built-in-nodes/ReveImageRemixNode.mdx b/ko/built-in-nodes/ReveImageRemixNode.mdx index 9a39de887..5bbd1d981 100644 --- a/ko/built-in-nodes/ReveImageRemixNode.mdx +++ b/ko/built-in-nodes/ReveImageRemixNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ReveImageRemixNode" icon: "circle" mode: wide --- -# Reve Image Remix 노드 Reve Image Remix 노드는 Reve API를 사용하여 새 이미지를 생성합니다. 하나 이상의 참조 이미지와 텍스트 프롬프트를 결합하여 제공된 설명에 기반한 새로운 리믹스 이미지를 만듭니다. diff --git a/ko/built-in-nodes/Rodin3D_Detail.mdx b/ko/built-in-nodes/Rodin3D_Detail.mdx index 9b1cacba9..b592d6a86 100644 --- a/ko/built-in-nodes/Rodin3D_Detail.mdx +++ b/ko/built-in-nodes/Rodin3D_Detail.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Rodin3D_Detail" icon: "circle" mode: wide --- -# Rodin 3D Detail 노드 Rodin 3D Detail 노드는 Rodin API를 사용하여 상세한 3D 에셋을 생성합니다. 입력 이미지를 받아 Rodin 서비스를 통해 처리하여 정교한 지오메트리와 재질을 갖춘 고품질 3D 모델을 제작합니다. 이 노드는 작업 생성부터 최종 3D 모델 파일 다운로드까지 전체 워크플로우를 처리합니다. @@ -22,7 +21,7 @@ Rodin 3D Detail 노드는 Rodin API를 사용하여 상세한 3D 에셋을 생 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `GLB` | 생성된 3D 모델의 파일 경로입니다 (하위 호환성 전용). | STRING | +| `3D 모델 경로` | 생성된 3D 모델의 파일 경로입니다 (하위 호환성 전용). | STRING | | `GLB` | GLB 형식으로 생성된 3D 모델입니다. | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Detail/ko.md) diff --git a/ko/built-in-nodes/Rodin3D_Gen2.mdx b/ko/built-in-nodes/Rodin3D_Gen2.mdx index 6e8156bb8..6a6eb3efc 100644 --- a/ko/built-in-nodes/Rodin3D_Gen2.mdx +++ b/ko/built-in-nodes/Rodin3D_Gen2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Rodin3D_Gen2" icon: "circle" mode: wide --- -# Rodin3D_Gen2 노드 Rodin3D_Gen2 노드는 Rodin API를 사용하여 3D 에셋을 생성합니다. 입력 이미지를 받아 다양한 재질 유형과 폴리곤 수로 3D 모델로 변환합니다. 이 노드는 작업 생성, 상태 폴링, 파일 다운로드를 포함한 전체 생성 과정을 자동으로 처리합니다. @@ -23,7 +22,7 @@ Rodin3D_Gen2 노드는 Rodin API를 사용하여 3D 에셋을 생성합니다. | 출력 이름 | 설명 | 데이터 유형 | | --- | --- | --- | -| `GLB` | 생성된 3D 모델의 파일 경로 (하위 호환성 유지) | STRING | +| `3D 모델 경로` | 생성된 3D 모델의 파일 경로 (하위 호환성 유지) | STRING | | `GLB` | GLB 형식으로 생성된 3D 모델 | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen2/ko.md) diff --git a/ko/built-in-nodes/Rodin3D_Gen25_Image.mdx b/ko/built-in-nodes/Rodin3D_Gen25_Image.mdx index 87013f425..de205b840 100644 --- a/ko/built-in-nodes/Rodin3D_Gen25_Image.mdx +++ b/ko/built-in-nodes/Rodin3D_Gen25_Image.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Rodin3D_Gen25_Image" icon: "circle" mode: wide --- -# 개요 이 노드는 Rodin Gen-2.5 API를 사용하여 1~5개의 참조 이미지로부터 3D 모델을 생성합니다. 생성 속도와 비용의 균형을 맞추기 위해 빠름(Fast), 보통(Regular), 초고화질(Extreme-High) 모드 중에서 선택할 수 있습니다. diff --git a/ko/built-in-nodes/Rodin3D_Gen25_Text.mdx b/ko/built-in-nodes/Rodin3D_Gen25_Text.mdx index e218c6c27..4f32bb283 100644 --- a/ko/built-in-nodes/Rodin3D_Gen25_Text.mdx +++ b/ko/built-in-nodes/Rodin3D_Gen25_Text.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen25_Text" icon: "circle" mode: wide --- + ## 개요 Rodin Gen-2.5 API를 사용하여 텍스트 프롬프트로 3D 모델을 생성합니다. 생성 속도와 출력 품질의 균형을 위해 다양한 품질 모드(빠름, 일반, 초고화질) 중에서 선택할 수 있습니다. @@ -34,7 +35,7 @@ Rodin Gen-2.5 API를 사용하여 텍스트 프롬프트로 3D 모델을 생성 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `model_file` | 지정된 형식의 생성된 3D 모델 파일입니다. | FILE3DANY | +| `모델 파일` | 지정된 형식의 생성된 3D 모델 파일입니다. | FILE3DANY | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen25_Text/ko.md) diff --git a/ko/built-in-nodes/Rodin3D_Regular.mdx b/ko/built-in-nodes/Rodin3D_Regular.mdx index cc8c06b28..7bb6ac5e0 100644 --- a/ko/built-in-nodes/Rodin3D_Regular.mdx +++ b/ko/built-in-nodes/Rodin3D_Regular.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Rodin3D_Regular" icon: "circle" mode: wide --- -# Rodin 3D Regular 노드 Rodin 3D Regular 노드는 Rodin API를 사용하여 3D 에셋을 생성합니다. 입력 이미지를 받아 Rodin 서비스를 통해 처리하여 3D 모델을 만듭니다. 이 노드는 작업 생성부터 최종 3D 모델 파일 다운로드까지 전체 워크플로를 처리합니다. @@ -22,7 +21,7 @@ Rodin 3D Regular 노드는 Rodin API를 사용하여 3D 에셋을 생성합니 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `GLB` | 생성된 3D 모델의 파일 경로입니다(하위 호환성을 위해 유지됨). | STRING | +| `3D 모델 경로` | 생성된 3D 모델의 파일 경로입니다(하위 호환성을 위해 유지됨). | STRING | | `GLB` | GLB 형식으로 생성된 3D 모델입니다. | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Regular/ko.md) diff --git a/ko/built-in-nodes/Rodin3D_Sketch.mdx b/ko/built-in-nodes/Rodin3D_Sketch.mdx index 0ea29dcb1..bbefe08b0 100644 --- a/ko/built-in-nodes/Rodin3D_Sketch.mdx +++ b/ko/built-in-nodes/Rodin3D_Sketch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Sketch" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Sketch/en.md) 이 노드는 Rodin API를 사용하여 3D 에셋을 생성합니다. 입력 이미지를 받아 외부 서비스를 통해 3D 모델로 변환합니다. 이 노드는 작업 생성부터 최종 3D 모델 파일 다운로드까지 전체 프로세스를 처리합니다. @@ -20,7 +21,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `GLB` | 생성된 3D 모델의 파일 경로입니다(하위 호환성 전용). | STRING | +| `3D 모델 경로` | 생성된 3D 모델의 파일 경로입니다(하위 호환성 전용). | STRING | | `GLB` | GLB 형식으로 생성된 3D 모델입니다. | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Sketch/ko.md) diff --git a/ko/built-in-nodes/Rodin3D_Smooth.mdx b/ko/built-in-nodes/Rodin3D_Smooth.mdx index f00a603a7..4a11b5ea2 100644 --- a/ko/built-in-nodes/Rodin3D_Smooth.mdx +++ b/ko/built-in-nodes/Rodin3D_Smooth.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Smooth" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Smooth/en.md) Rodin 3D Smooth 노드는 Rodin API를 사용하여 입력 이미지를 처리하고 부드러운 3D 모델로 변환함으로써 3D 에셋을 생성합니다. 여러 이미지를 입력으로 받아 다운로드 가능한 3D 모델 파일을 출력합니다. 이 노드는 작업 생성, 상태 폴링, 파일 다운로드를 포함한 전체 생성 과정을 자동으로 처리합니다. @@ -22,7 +23,7 @@ Rodin 3D Smooth 노드는 Rodin API를 사용하여 입력 이미지를 처리 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `GLB` | 다운로드된 3D 모델의 파일 경로입니다(하위 호환성 전용). | STRING | +| `3D 모델 경로` | 다운로드된 3D 모델의 파일 경로입니다(하위 호환성 전용). | STRING | | `GLB` | GLB 형식으로 생성된 3D 모델입니다. | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Smooth/ko.md) diff --git a/ko/built-in-nodes/RunwayAleph2KeyframeNode.mdx b/ko/built-in-nodes/RunwayAleph2KeyframeNode.mdx new file mode 100644 index 000000000..f909d504d --- /dev/null +++ b/ko/built-in-nodes/RunwayAleph2KeyframeNode.mdx @@ -0,0 +1,37 @@ +--- +title: "RunwayAleph2KeyframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2KeyframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2KeyframeNode" +icon: "circle" +mode: wide +--- + +이 노드는 입력 비디오의 특정 시점에 가이던스 이미지를 고정하여, Aleph2 모델이 해당 지점에서 편집을 수행하도록 안내합니다. 이 노드를 Runway Aleph2 비디오 투 비디오 노드의 "keyframes" 입력에 연결하고, 선택적 "keyframes" 입력을 통해 여러 개(최대 5개)를 함께 연결할 수 있습니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `image` | 입력 비디오의 선택된 시점에 적용할 가이던스 이미지입니다. | IMAGE | 예 | - | +| `timing` | 이 이미지를 입력 비디오의 타임라인에 배치하는 방법입니다. | COMBO | 예 | 아래 참조 | +| `keyframes` | 이 키프레임과 함께 연결할 선택적 이전 키프레임입니다. | KEYFRAME | 아니요 | - | + +### Timing 매개변수 옵션 + +`timing` 매개변수는 두 가지 모드가 있습니다: + +| 모드 | 하위 매개변수 | 설명 | 범위 | +|------|--------------|-------------|-------| +| "절대 초" | `seconds` | 이 이미지가 적용되는 입력 비디오 시작부터의 시간(초)입니다(기본값: 0.0) | 0.0 ~ 30.0, 간격 0.1 | +| "길이 분수" | `fraction` | 이 이미지가 적용되는 입력 비디오 내 위치로, 전체 길이에 대한 분수입니다(0.0 = 시작, 1.0 = 끝)(기본값: 0.0) | 0.0 ~ 1.0, 간격 0.01 | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `keyframes` | 현재 키프레임과 이전에 연결된 모든 키프레임을 포함하는 키프레임 체인입니다. | KEYFRAME | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2KeyframeNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `b5ac6553166b7366fd35f97740861be163f91bc2353f5f83bdc2f04bf40f8478` diff --git a/ko/built-in-nodes/RunwayAleph2PromptImageNode.mdx b/ko/built-in-nodes/RunwayAleph2PromptImageNode.mdx new file mode 100644 index 000000000..8fb78f3af --- /dev/null +++ b/ko/built-in-nodes/RunwayAleph2PromptImageNode.mdx @@ -0,0 +1,34 @@ +--- +title: "RunwayAleph2PromptImageNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2PromptImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2PromptImageNode" +icon: "circle" +mode: wide +--- + +이 노드는 가이드 이미지를 출력 비디오의 특정 시점에 고정하여, 해당 지점에서 편집된 비디오의 모습을 제어합니다. 이 노드를 Runway Aleph2 비디오 투 비디오 노드의 `prompt_images` 입력에 연결하고, 선택적 `prompt_images` 입력을 사용하여 여러 개(최대 5개)를 함께 체인으로 연결할 수 있습니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `image` | 출력 비디오의 선택한 시점에 배치할 가이드 이미지입니다. | IMAGE | 예 | - | +| `position` | 출력 비디오 타임라인에 이 이미지를 배치하는 방법입니다. 절대 시간(시작부터 초 단위) 또는 분수 시간(비디오 길이 대비 백분율) 중에서 선택합니다. | COMBO | 예 | `Absolute (seconds)`
`Fraction (0.0 to 1.0)` | +| `prompt_images` | 이 이미지와 함께 체인으로 연결할 선택적 이전 프롬프트 이미지입니다. 다른 Runway Aleph2 프롬프트 이미지 노드의 출력을 여기에 연결하여 최대 5개의 가이드 이미지 체인을 구성합니다. | PROMPT_IMAGE_CHAIN | 아니요 | - | + +**위치 모드 세부 정보:** + +`position`이 `Absolute (seconds)`로 설정된 경우, `seconds` 값을 제공해야 합니다(기본값: 0.0, 범위: 0.0~30.0, 단계: 0.1). 이는 출력 비디오 시작부터 이 이미지가 적용되는 정확한 시간(초)을 지정합니다. + +`position`이 `Fraction (0.0 to 1.0)`으로 설정된 경우, `fraction` 값을 제공해야 합니다(기본값: 0.0, 범위: 0.0~1.0, 단계: 0.01). 이는 출력 비디오 전체 길이 대비 분수 값으로 이 이미지가 적용되는 위치를 지정합니다(0.0 = 시작, 1.0 = 끝). + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `prompt_images` | Runway Aleph2 비디오 투 비디오 노드의 `prompt_images` 입력에 연결할 수 있는 프롬프트 이미지 체인입니다. | PROMPT_IMAGE_CHAIN | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2PromptImageNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `a8b86fb5d73d27cc58aa59c195ca058eec8a5c9433ea09522ff3e905f6b88193` diff --git a/ko/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx b/ko/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx new file mode 100644 index 000000000..4ac202054 --- /dev/null +++ b/ko/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx @@ -0,0 +1,37 @@ +--- +title: "RunwayAleph2VideoToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2VideoToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2VideoToVideoNode" +icon: "circle" +mode: wide +--- + +이 노드는 Runway의 Aleph2 모델을 사용하여 텍스트 프롬프트로 비디오를 편집합니다. 원본 움직임과 타이밍을 유지하면서 영상을 스타일 변경, 조명 변경, 요소 추가 또는 제거, 또는 시점 변경을 통해 변환합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `프롬프트` | 출력 결과에 나타나야 할 내용을 설명합니다(1-1000자). | STRING | 예 | 1-1000자 | +| `비디오` | 편집할 입력 비디오입니다. 30fps 이하에서 2-30초 길이여야 합니다. | VIDEO | 예 | 2-30초 길이, 최대 30fps | +| `시드` | 생성을 위한 랜덤 시드(기본값: 0). | INT | 예 | 0 ~ 4294967295 | +| `공인 임계값` | 식별 가능한 공인에 대한 콘텐츠 검열(기본값: "low"). | COMBO | 예 | "auto"
"low" | +| `키프레임` | Aleph2 키프레임 노드에서 가져온, 입력 비디오에 고정된 가이던스 이미지(최대 5개). 키프레임 또는 프롬프트 이미지 중 하나만 사용하세요. | KEYFRAME | 아니요 | 최대 5개 | +| `프롬프트 이미지` | Aleph2 프롬프트 이미지 노드에서 가져온, 출력 비디오에 고정된 가이던스 이미지(최대 5개). 키프레임 또는 프롬프트 이미지 중 하나만 사용하세요. | PROMPT_IMAGE | 아니요 | 최대 5개 | + +**중요 제약사항:** +- 입력 비디오는 2초에서 30초 사이의 길이여야 하며, 프레임 속도는 30fps 이하여야 합니다. +- 가이던스에는 `keyframes` 또는 `prompt_images` 중 하나만 사용할 수 있으며, 동시에 사용할 수 없습니다. +- 각 가이던스 입력(키프레임 또는 프롬프트 이미지)은 최대 5개까지 지원됩니다. +- 키프레임 타임스탬프와 프롬프트 이미지 타임스탬프는 입력 비디오 길이를 초과할 수 없습니다. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `비디오` | Aleph2 모델이 생성한 편집된 비디오입니다. | VIDEO | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2VideoToVideoNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `bda4d0f49843c1a8f311ddbce5911a2a157cae798a26f7a183b31fe41686d0b7` diff --git a/ko/built-in-nodes/RunwayFirstLastFrameNode.mdx b/ko/built-in-nodes/RunwayFirstLastFrameNode.mdx index 7acc26f4f..c2960ed81 100644 --- a/ko/built-in-nodes/RunwayFirstLastFrameNode.mdx +++ b/ko/built-in-nodes/RunwayFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayFirstLastFrameNode" icon: "circle" mode: wide --- + Runway 첫 번째-마지막 프레임-투-비디오 노드는 첫 번째 및 마지막 키프레임과 텍스트 프롬프트를 업로드하여 비디오를 생성합니다. Runway의 Gen-3 모델을 사용하여 제공된 시작 프레임과 종료 프레임 간의 부드러운 전환을 만듭니다. 이는 종료 프레임이 시작 프레임과 크게 다른 복잡한 전환에 특히 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx b/ko/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx index 144043e09..aa8a28f9f 100644 --- a/ko/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx +++ b/ko/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RunwayImageToVideoNodeGen3a" icon: "circle" mode: wide --- -# Runway 이미지-투-비디오(Gen3a Turbo) 노드 Runway 이미지-투-비디오(Gen3a Turbo) 노드는 Runway의 Gen3a Turbo 모델을 사용하여 단일 시작 프레임에서 비디오를 생성합니다. 텍스트 프롬프트와 초기 이미지 프레임을 입력받아 지정된 지속 시간과 화면 비율에 따라 비디오 시퀀스를 생성합니다. 이 노드는 Runway의 API에 연결하여 원격으로 생성을 처리합니다. diff --git a/ko/built-in-nodes/RunwayImageToVideoNodeGen4.mdx b/ko/built-in-nodes/RunwayImageToVideoNodeGen4.mdx index 07a531074..6d20f1d6c 100644 --- a/ko/built-in-nodes/RunwayImageToVideoNodeGen4.mdx +++ b/ko/built-in-nodes/RunwayImageToVideoNodeGen4.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayImageToVideoNodeGen4" icon: "circle" mode: wide --- + Runway Image to Video (Gen4 Turbo) 노드는 Runway의 Gen4 Turbo 모델을 사용하여 단일 시작 프레임에서 비디오를 생성합니다. 텍스트 프롬프트와 초기 이미지 프레임을 입력받아, 지정된 지속 시간 및 화면 비율 설정에 따라 비디오 시퀀스를 생성합니다. 이 노드는 시작 프레임을 Runway의 API에 업로드하고 생성된 비디오를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/RunwayTextToImageNode.mdx b/ko/built-in-nodes/RunwayTextToImageNode.mdx index a1bd72f12..7eb76cdea 100644 --- a/ko/built-in-nodes/RunwayTextToImageNode.mdx +++ b/ko/built-in-nodes/RunwayTextToImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RunwayTextToImageNode" icon: "circle" mode: wide --- -# Runway 텍스트-이미지 노드 Runway 텍스트-이미지 노드는 Runway의 Gen 4 모델을 사용하여 텍스트 프롬프트로부터 이미지를 생성합니다. 텍스트 설명을 제공하고 선택적으로 참조 이미지를 포함하여 이미지 생성 과정을 안내할 수 있습니다. 이 노드는 API 통신을 처리하고 생성된 이미지를 반환합니다. diff --git a/ko/built-in-nodes/SAM3_Detect.mdx b/ko/built-in-nodes/SAM3_Detect.mdx index 5cd5015dc..f02cece5f 100644 --- a/ko/built-in-nodes/SAM3_Detect.mdx +++ b/ko/built-in-nodes/SAM3_Detect.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SAM3_Detect" icon: "circle" mode: wide --- -# SAM3 Detect 노드 ## 개요 @@ -38,7 +37,7 @@ SAM3 Detect 노드는 텍스트 설명, 경계 상자 또는 포인트 프롬프 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `bboxes` | 분할 마스크. `individual_masks`가 False(기본값)인 경우 프레임당 단일 결합 마스크를 반환합니다. True인 경우 감지된 각 객체에 대한 개별 마스크를 반환합니다 | MASK | +| `masks` | 분할 마스크. `individual_masks`가 False(기본값)인 경우 프레임당 단일 결합 마스크를 반환합니다. True인 경우 감지된 각 객체에 대한 개별 마스크를 반환합니다 | MASK | | `bboxes` | 좌표와 신뢰도 점수가 포함된 감지된 경계 상자. 각 상자에는 `x`, `y`, `width`, `height` 및 `score` 값이 포함됩니다 | BOUNDING_BOX | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SAM3_Detect/ko.md) diff --git a/ko/built-in-nodes/SAM3_TrackPreview.mdx b/ko/built-in-nodes/SAM3_TrackPreview.mdx index c8036b983..71f8225d2 100644 --- a/ko/built-in-nodes/SAM3_TrackPreview.mdx +++ b/ko/built-in-nodes/SAM3_TrackPreview.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SAM3_TrackPreview" icon: "circle" mode: wide --- -# 개요 이 노드는 추적된 객체의 비디오 미리보기를 생성하며, 각 추적된 객체를 고유한 색상 오버레이와 숫자 레이블로 표시합니다. 이미지나 비디오 텐서를 출력하지 않는 대신, 결과 미리보기 비디오를 임시 파일에 직접 저장합니다. diff --git a/ko/built-in-nodes/SAM3_TrackToMask.mdx b/ko/built-in-nodes/SAM3_TrackToMask.mdx index a7a588625..c699e3247 100644 --- a/ko/built-in-nodes/SAM3_TrackToMask.mdx +++ b/ko/built-in-nodes/SAM3_TrackToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_TrackToMask" icon: "circle" mode: wide --- + 다음은 주어진 영어 문서를 한국어로 번역한 결과입니다. --- diff --git a/ko/built-in-nodes/SAM3_VideoTrack.mdx b/ko/built-in-nodes/SAM3_VideoTrack.mdx index c45a93b38..fb04b1fb6 100644 --- a/ko/built-in-nodes/SAM3_VideoTrack.mdx +++ b/ko/built-in-nodes/SAM3_VideoTrack.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SAM3_VideoTrack" icon: "circle" mode: wide --- -# 개요 SAM3의 메모리 기반 추적기를 사용하여 비디오 프레임 간 객체를 추적합니다. 이 노드는 비디오 프레임 시퀀스를 처리하고 프레임 간 객체 식별자를 유지하며, 초기 마스크 또는 텍스트 프롬프트를 사용하여 추적할 대상을 정의합니다. diff --git a/ko/built-in-nodes/SCAIL2ColoredMask.mdx b/ko/built-in-nodes/SCAIL2ColoredMask.mdx new file mode 100644 index 000000000..8ebbd2b8d --- /dev/null +++ b/ko/built-in-nodes/SCAIL2ColoredMask.mdx @@ -0,0 +1,31 @@ +--- +title: "SCAIL2ColoredMask - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the SCAIL2ColoredMask node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "SCAIL2ColoredMask" +icon: "circle" +mode: wide +--- + +이 노드는 SAM3 추적 데이터를 채색된 마스크로 변환하여 WanSCAILToVideo 노드에서 사용할 수 있도록 합니다. 드라이빙 포즈 비디오와 선택적으로 참조 이미지의 추적 데이터를 처리하여, 각 출력에서 추적된 사람들에게 일관된 색상을 할당합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `driving_track_data` | 드라이빙 포즈 비디오의 SAM3 추적 데이터입니다. pose_video_mask 출력으로 렌더링됩니다. | SAM3_TRACK_DATA | 예 | - | +| `ref_track_data` | 참조 이미지의 SAM3 추적 데이터입니다. | SAM3_TRACK_DATA | 아니요 | - | +| `object_indices` | 포함할 사람 인덱스의 쉼표로 구분된 목록입니다(예: '0,2,3'). 참조 및 포즈 비디오 마스크 모두에 적용됩니다. 비워두면 전체가 포함됩니다. | STRING | 예 | - | +| `sort_by` | 추적된 객체에 팔레트 색상이 할당되는 순서입니다(참조 및 포즈 비디오 모두에 적용되어 각 개체가 동일한 색상을 유지합니다). left_to_right = 가장 왼쪽 객체(첫 번째 프레임 중심 기준)가 첫 번째 색상을 받습니다; area = 가장 큰 객체(첫 번째 프레임 마스크 영역 기준)가 첫 번째 색상을 받습니다; none = SAM3의 순서를 유지합니다. (기본값: "left_to_right") | COMBO | 예 | `"none"`
`"left_to_right"`
`"area"` | +| `replacement_mode` | False = 애니메이션 모드(pose_video_mask는 검은색 배경, reference_image_mask는 흰색 배경). True = 대체 모드(pose_video_mask는 흰색 배경, reference_image_mask는 검은색 배경). (기본값: False) | BOOLEAN | 예 | False
True | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `pose_video_mask` | 드라이빙 포즈 비디오 추적 데이터에서 렌더링된 채색 마스크입니다. 배경 색상은 replacement_mode 설정을 따릅니다. | IMAGE | +| `reference_image_mask` | 참조 이미지 추적 데이터에서 렌더링된 채색 마스크입니다. 모델 규칙에 따라 항상 검은색 배경으로 렌더링됩니다. | IMAGE | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SCAIL2ColoredMask/ko.md) + +--- +**Source fingerprint (SHA-256):** `c9f6d87410b8bd4082ffb06ef1cf973829566ed222be643db3528cbc241d3c14` diff --git a/ko/built-in-nodes/SDPoseDrawKeypoints.mdx b/ko/built-in-nodes/SDPoseDrawKeypoints.mdx index acd597921..d5ecd22d2 100644 --- a/ko/built-in-nodes/SDPoseDrawKeypoints.mdx +++ b/ko/built-in-nodes/SDPoseDrawKeypoints.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SDPoseDrawKeypoints" icon: "circle" mode: wide --- -# SDPoseDrawKeypoints 노드 SDPoseDrawKeypoints 노드는 포즈 추정 데이터(키포인트)를 가져와 빈 캔버스에 시각적 골격 형태로 그립니다. 신체, 손, 얼굴, 발 등 포즈의 다양한 부분을 선택적으로 그릴 수 있으며, 선 두께와 점 크기를 사용자 정의할 수 있습니다. 결과 이미지는 시각화 용도로 사용하거나 포즈 이미지가 필요한 다른 노드의 입력으로 사용할 수 있습니다. diff --git a/ko/built-in-nodes/SDPoseFaceBBoxes.mdx b/ko/built-in-nodes/SDPoseFaceBBoxes.mdx index c75cdbe4d..d7f3f6389 100644 --- a/ko/built-in-nodes/SDPoseFaceBBoxes.mdx +++ b/ko/built-in-nodes/SDPoseFaceBBoxes.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SDPoseFaceBBoxes" icon: "circle" mode: wide --- -# SDPoseFaceBBoxes 노드 SDPoseFaceBBoxes 노드는 포즈 키포인트 데이터를 처리하여 사람의 얼굴 주변에 경계 상자를 감지하고 생성합니다. 프레임 내 각 사람의 2D 얼굴 키포인트를 분석하고, 해당 지점을 기반으로 경계 상자를 계산하며, 상자의 크기와 모양을 조정할 수 있습니다. 생성된 경계 상자는 SDPoseKeypointExtractor와 같은 SDPose 워크플로우의 다른 노드와 호환되는 형식으로 제공됩니다. diff --git a/ko/built-in-nodes/SDPoseKeypointExtractor.mdx b/ko/built-in-nodes/SDPoseKeypointExtractor.mdx index 9737095ca..2a0a6034e 100644 --- a/ko/built-in-nodes/SDPoseKeypointExtractor.mdx +++ b/ko/built-in-nodes/SDPoseKeypointExtractor.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SDPoseKeypointExtractor" icon: "circle" mode: wide --- -# SDPoseKeypointExtractor SDPoseKeypointExtractor 노드는 SDPose 모델을 사용하여 입력 이미지에서 사람의 포즈 키포인트를 감지합니다. 전체 이미지 또는 경계 상자로 정의된 특정 영역을 처리할 수 있으며, 각 사람의 좌표와 각 키포인트의 신뢰도 점수를 포함하는 OpenPose 형식으로 감지된 키포인트를 출력합니다. diff --git a/ko/built-in-nodes/SDTurboScheduler.mdx b/ko/built-in-nodes/SDTurboScheduler.mdx index 47f48f6f4..21aade520 100644 --- a/ko/built-in-nodes/SDTurboScheduler.mdx +++ b/ko/built-in-nodes/SDTurboScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDTurboScheduler" icon: "circle" mode: wide --- + SDTurboScheduler는 이미지 샘플링을 위한 시그마 값 시퀀스를 생성하도록 설계되었으며, 지정된 노이즈 제거 수준과 단계 수에 따라 시퀀스를 조정합니다. 특정 모델의 샘플링 기능을 활용하여 이러한 시그마 값을 생성하며, 이 값은 이미지 생성 중 노이즈 제거 과정을 제어하는 데 중요합니다. ## 입력 diff --git a/ko/built-in-nodes/SD_4XUpscale_Conditioning.mdx b/ko/built-in-nodes/SD_4XUpscale_Conditioning.mdx index 7cece3aa6..bf23b9ff1 100644 --- a/ko/built-in-nodes/SD_4XUpscale_Conditioning.mdx +++ b/ko/built-in-nodes/SD_4XUpscale_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SD_4XUpscale_Conditioning" icon: "circle" mode: wide --- + SD_4XUpscale_Conditioning 노드는 확산 모델을 사용하여 이미지를 업스케일링하기 위한 컨디셔닝 데이터를 준비합니다. 입력 이미지와 컨디셔닝 데이터를 받아 스케일링과 노이즈 증강을 적용하여 업스케일링 과정을 안내하는 수정된 컨디셔닝을 생성합니다. 이 노드는 업스케일된 차원에 대한 잠재 표현과 함께 양성 및 음성 컨디셔닝을 모두 출력합니다. ## 입력 @@ -21,9 +22,9 @@ SD_4XUpscale_Conditioning 노드는 확산 모델을 사용하여 이미지를 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 업스케일링 정보가 적용된 수정된 양성 컨디셔닝 | CONDITIONING | -| `잠재 이미지` | 업스케일링 정보가 적용된 수정된 음성 컨디셔닝 | CONDITIONING | -| `latent` | 업스케일된 차원에 맞는 빈 잠재 표현 | LATENT | +| `긍정 조건` | 업스케일링 정보가 적용된 수정된 양성 컨디셔닝 | CONDITIONING | +| `부정 조건` | 업스케일링 정보가 적용된 수정된 음성 컨디셔닝 | CONDITIONING | +| `잠재 이미지` | 업스케일된 차원에 맞는 빈 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SD_4XUpscale_Conditioning/ko.md) diff --git a/ko/built-in-nodes/SUPIRApply.mdx b/ko/built-in-nodes/SUPIRApply.mdx index f71b99358..9307cfb82 100644 --- a/ko/built-in-nodes/SUPIRApply.mdx +++ b/ko/built-in-nodes/SUPIRApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SUPIRApply" icon: "circle" mode: wide --- + SUPIRApply 노드는 확산 모델에 SUPIR 모델 패치를 적용합니다. 이 패치를 사용하여 모델의 동작을 수정함으로써 샘플링 과정에서 입력 이미지의 안내를 통합할 수 있습니다. 또한 시간에 따른 안내 강도를 조정하는 컨트롤과 원본 입력에 대한 충실도를 유지하는 데 도움이 되는 선택적 기능을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/SV3D_Conditioning.mdx b/ko/built-in-nodes/SV3D_Conditioning.mdx index 874089331..b9a820495 100644 --- a/ko/built-in-nodes/SV3D_Conditioning.mdx +++ b/ko/built-in-nodes/SV3D_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SV3D_Conditioning" icon: "circle" mode: wide --- + SV3D_Conditioning 노드는 SV3D 모델을 사용하여 3D 비디오 생성을 위한 컨디셔닝 데이터를 준비합니다. 초기 이미지를 받아 CLIP 비전 및 VAE 인코더를 통해 처리하여 포지티브 및 네거티브 컨디셔닝과 잠재 표현을 생성합니다. 이 노드는 지정된 비디오 프레임 수를 기반으로 다중 프레임 비디오 생성을 위한 카메라 고도 및 방위각 시퀀스를 생성합니다. ## 입력 @@ -23,9 +24,9 @@ SV3D_Conditioning 노드는 SV3D 모델을 사용하여 3D 비디오 생성을 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 이미지 임베딩과 카메라 매개변수를 포함하는 포지티브 컨디셔닝 데이터 (생성용) | CONDITIONING | -| `잠재 데이터` | 대비 생성을 위해 임베딩이 0으로 설정된 네거티브 컨디셔닝 데이터 | CONDITIONING | -| `latent` | 지정된 비디오 프레임 및 해상도와 일치하는 차원을 가진 빈 잠재 텐서 | LATENT | +| `긍정 조건` | 이미지 임베딩과 카메라 매개변수를 포함하는 포지티브 컨디셔닝 데이터 (생성용) | CONDITIONING | +| `부정 조건` | 대비 생성을 위해 임베딩이 0으로 설정된 네거티브 컨디셔닝 데이터 | CONDITIONING | +| `잠재 데이터` | 지정된 비디오 프레임 및 해상도와 일치하는 차원을 가진 빈 잠재 텐서 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SV3D_Conditioning/ko.md) diff --git a/ko/built-in-nodes/SVD_img2vid_Conditioning.mdx b/ko/built-in-nodes/SVD_img2vid_Conditioning.mdx index 89944eb48..b496d5a76 100644 --- a/ko/built-in-nodes/SVD_img2vid_Conditioning.mdx +++ b/ko/built-in-nodes/SVD_img2vid_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SVD_img2vid_Conditioning" icon: "circle" mode: wide --- + SVD_img2vid_Conditioning 노드는 Stable Video Diffusion을 사용한 비디오 생성을 위한 컨디셔닝 데이터를 준비합니다. 초기 이미지를 입력받아 CLIP 비전 및 VAE 인코더를 통해 처리하여 포지티브 및 네거티브 컨디셔닝 쌍과 비디오 생성을 위한 빈 잠재 공간을 생성합니다. 이 노드는 생성된 비디오에서 모션, 프레임 속도 및 증강 수준을 제어하는 데 필요한 매개변수를 설정합니다. ## 입력 @@ -25,9 +26,9 @@ SVD_img2vid_Conditioning 노드는 Stable Video Diffusion을 사용한 비디오 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 이미지 임베딩과 비디오 매개변수를 포함한 포지티브 컨디셔닝 데이터 | CONDITIONING | -| `잠재 비디오` | 0으로 설정된 임베딩과 비디오 매개변수를 포함한 네거티브 컨디셔닝 데이터 | CONDITIONING | -| `latent` | 비디오 생성을 위해 준비된 빈 잠재 공간 텐서 | LATENT | +| `긍정 조건` | 이미지 임베딩과 비디오 매개변수를 포함한 포지티브 컨디셔닝 데이터 | CONDITIONING | +| `부정 조건` | 0으로 설정된 임베딩과 비디오 매개변수를 포함한 네거티브 컨디셔닝 데이터 | CONDITIONING | +| `잠재 비디오` | 비디오 생성을 위해 준비된 빈 잠재 공간 텐서 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SVD_img2vid_Conditioning/ko.md) diff --git a/ko/built-in-nodes/SamplerARVideo.mdx b/ko/built-in-nodes/SamplerARVideo.mdx index 1deb6af91..164818419 100644 --- a/ko/built-in-nodes/SamplerARVideo.mdx +++ b/ko/built-in-nodes/SamplerARVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerARVideo" icon: "circle" mode: wide --- + Sampler AR Video 노드는 Causal Forcing 또는 Self-Forcing 기술을 사용하는 것과 같은 자기회귀 비디오 모델을 위한 특수 샘플링 방법을 제공합니다. 워크플로우 내에서 자기회귀(AR) 루프와 관련된 모든 매개변수를 직접 관리하므로, 모델이 한 번에 한 프레임씩 비디오 프레임을 생성하는 방식을 쉽게 구성할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerCustom.mdx b/ko/built-in-nodes/SamplerCustom.mdx index 585b69e06..4eb08dec9 100644 --- a/ko/built-in-nodes/SamplerCustom.mdx +++ b/ko/built-in-nodes/SamplerCustom.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerCustom" icon: "circle" mode: wide --- + SamplerCustom 노드는 다양한 애플리케이션을 위한 유연하고 사용자 정의 가능한 샘플링 메커니즘을 제공하도록 설계되었습니다. 이를 통해 사용자는 특정 요구에 맞게 다양한 샘플링 전략을 선택하고 구성할 수 있어 샘플링 프로세스의 적응성과 효율성을 향상시킵니다. ## 입력 @@ -25,7 +26,7 @@ SamplerCustom 노드는 다양한 애플리케이션을 위한 유연하고 사 | 매개변수 | 설명 | 데이터 타입 | | --- | --- | --- | -| `디노이즈 출력` | 'output'은 샘플링 과정의 주요 결과를 나타내며, 생성된 샘플을 포함합니다. | `LATENT` | -| `denoised_output` | 'denoised_output'은 노이즈 제거 과정이 적용된 후의 샘플을 나타내며, 생성된 샘플의 선명도와 품질을 향상시킬 수 있습니다. | `LATENT` | +| `출력` | 'output'은 샘플링 과정의 주요 결과를 나타내며, 생성된 샘플을 포함합니다. | `LATENT` | +| `디노이즈 출력` | 'denoised_output'은 노이즈 제거 과정이 적용된 후의 샘플을 나타내며, 생성된 샘플의 선명도와 품질을 향상시킬 수 있습니다. | `LATENT` | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerCustom/ko.md) diff --git a/ko/built-in-nodes/SamplerCustomAdvanced.mdx b/ko/built-in-nodes/SamplerCustomAdvanced.mdx index f7d64178a..98fa1939d 100644 --- a/ko/built-in-nodes/SamplerCustomAdvanced.mdx +++ b/ko/built-in-nodes/SamplerCustomAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerCustomAdvanced" icon: "circle" mode: wide --- + **SamplerCustomAdvanced** 노드는 사용자 정의 노이즈, 가이던스 및 샘플링 구성을 사용하여 고급 잠재 공간 샘플링을 수행합니다. 이 노드는 사용자 정의 가능한 노이즈 생성 및 시그마 일정을 통해 안내된 샘플링 과정으로 잠재 이미지를 처리하여, 최종 샘플링 출력과 사용 가능한 경우 노이즈가 제거된 버전을 모두 생성합니다. ## 입력 @@ -21,8 +22,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `디노이즈 출력` | 샘플링 과정을 완료한 후의 최종 샘플링된 잠재 표현입니다. | LATENT | -| `denoised_output` | 사용 가능한 경우 출력의 노이즈가 제거된 버전이며, 그렇지 않으면 출력과 동일한 값을 반환합니다. | LATENT | +| `출력` | 샘플링 과정을 완료한 후의 최종 샘플링된 잠재 표현입니다. | LATENT | +| `디노이즈 출력` | 사용 가능한 경우 출력의 노이즈가 제거된 버전이며, 그렇지 않으면 출력과 동일한 값을 반환합니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerCustomAdvanced/ko.md) diff --git a/ko/built-in-nodes/SamplerDPMAdaptative.mdx b/ko/built-in-nodes/SamplerDPMAdaptative.mdx index f72a97715..8f9980620 100644 --- a/ko/built-in-nodes/SamplerDPMAdaptative.mdx +++ b/ko/built-in-nodes/SamplerDPMAdaptative.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerDPMAdaptative" icon: "circle" mode: wide --- -# SamplerDPMAdaptative 노드 SamplerDPMAdaptative 노드는 샘플링 과정에서 단계 크기를 자동으로 조정하는 적응형 DPM(확산 확률 모델) 샘플러를 구현합니다. 허용 오차 기반 오류 제어를 사용하여 최적의 단계 크기를 결정함으로써 계산 효율성과 샘플링 정확도의 균형을 유지합니다. 이 적응형 접근 방식은 필요한 단계 수를 줄이면서도 품질을 유지하는 데 도움이 됩니다. diff --git a/ko/built-in-nodes/SamplerDPMPP_2M_SDE.mdx b/ko/built-in-nodes/SamplerDPMPP_2M_SDE.mdx index 004385852..787dff3bd 100644 --- a/ko/built-in-nodes/SamplerDPMPP_2M_SDE.mdx +++ b/ko/built-in-nodes/SamplerDPMPP_2M_SDE.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerDPMPP_2M_SDE" icon: "circle" mode: wide --- -# SamplerDPMPP_2M_SDE SamplerDPMPP_2M_SDE 노드는 확산 모델을 위한 DPM++ 2M SDE 샘플러를 생성합니다. 이 샘플러는 확률적 미분 방정식과 함께 2차 미분 방정식 솔버를 사용하여 샘플을 생성합니다. 다양한 솔버 유형과 노이즈 처리 옵션을 제공하여 샘플링 과정을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx b/ko/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx index ba596e7bf..278cde7cf 100644 --- a/ko/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx +++ b/ko/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerDPMPP_2S_Ancestral" icon: "circle" mode: wide --- -# SamplerDPMPP_2S_Ancestral SamplerDPMPP_2S_Ancestral 노드는 DPM++ 2S Ancestral 샘플링 방식을 사용하여 이미지를 생성하는 샘플러를 생성합니다. 이 샘플러는 결정론적 요소와 확률적 요소를 결합하여 일관성을 유지하면서도 다양한 결과를 생성합니다. 샘플링 과정 중 무작위성과 노이즈 수준을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/SamplerDPMPP_3M_SDE.mdx b/ko/built-in-nodes/SamplerDPMPP_3M_SDE.mdx index f4a5ef956..47c085b91 100644 --- a/ko/built-in-nodes/SamplerDPMPP_3M_SDE.mdx +++ b/ko/built-in-nodes/SamplerDPMPP_3M_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_3M_SDE" icon: "circle" mode: wide --- + SamplerDPMPP_3M_SDE 노드는 샘플링 과정에서 사용할 DPM++ 3M SDE 샘플러를 생성합니다. 이 샘플러는 구성 가능한 노이즈 매개변수를 사용하는 3차 다단계 확률적 미분 방정식 방법을 활용합니다. 노드를 통해 노이즈 계산을 GPU 또는 CPU에서 수행할지 선택할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerDPMPP_SDE.mdx b/ko/built-in-nodes/SamplerDPMPP_SDE.mdx index a99689c27..b3d9e3c1c 100644 --- a/ko/built-in-nodes/SamplerDPMPP_SDE.mdx +++ b/ko/built-in-nodes/SamplerDPMPP_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_SDE" icon: "circle" mode: wide --- + `SamplerDPMPP_SDE` 노드는 샘플링 과정에서 사용할 DPM++ SDE(확률적 미분 방정식) 샘플러를 생성합니다. 이 샘플러는 구성 가능한 노이즈 매개변수와 장치 선택 기능을 갖춘 확률적 샘플링 방법을 제공합니다. 샘플링 파이프라인에서 사용할 수 있는 샘플러 객체를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerDpmpp2mSde.mdx b/ko/built-in-nodes/SamplerDpmpp2mSde.mdx index b271385b0..2bab74b06 100644 --- a/ko/built-in-nodes/SamplerDpmpp2mSde.mdx +++ b/ko/built-in-nodes/SamplerDpmpp2mSde.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDpmpp2mSde" icon: "circle" mode: wide --- + 이 노드는 DPMPP_2M_SDE 모델용 샘플러를 생성하도록 설계되어, 지정된 솔버 유형, 노이즈 수준 및 연산 장치 선호도에 따라 샘플을 생성할 수 있습니다. 샘플러 구성의 복잡성을 추상화하여 맞춤 설정으로 샘플을 생성할 수 있는 간소화된 인터페이스를 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerDpmppSde.mdx b/ko/built-in-nodes/SamplerDpmppSde.mdx index e7421d778..072f8ada7 100644 --- a/ko/built-in-nodes/SamplerDpmppSde.mdx +++ b/ko/built-in-nodes/SamplerDpmppSde.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDpmppSde" icon: "circle" mode: wide --- + 이 노드는 DPM++ SDE(확률적 미분 방정식) 모델용 샘플러를 생성하도록 설계되었습니다. CPU 및 GPU 실행 환경 모두에 적응하며, 사용 가능한 하드웨어에 따라 샘플러 구현을 최적화합니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerER_SDE.mdx b/ko/built-in-nodes/SamplerER_SDE.mdx index 867c6e363..c51595b18 100644 --- a/ko/built-in-nodes/SamplerER_SDE.mdx +++ b/ko/built-in-nodes/SamplerER_SDE.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerER_SDE" icon: "circle" mode: wide --- -# SamplerER_SDE 노드 SamplerER_SDE 노드는 확산 모델을 위한 특화된 샘플링 방법을 제공하며, ER-SDE, 역시간 SDE 및 ODE 접근 방식을 포함한 다양한 솔버 유형을 지원합니다. 이 노드는 샘플링 과정의 확률적 동작과 계산 단계를 제어할 수 있게 해줍니다. 선택된 솔버 유형에 따라 매개변수를 자동으로 조정하여 적절한 기능이 작동하도록 보장합니다. diff --git a/ko/built-in-nodes/SamplerEulerAncestral.mdx b/ko/built-in-nodes/SamplerEulerAncestral.mdx index 10f4a4cfc..8db2f8825 100644 --- a/ko/built-in-nodes/SamplerEulerAncestral.mdx +++ b/ko/built-in-nodes/SamplerEulerAncestral.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerAncestral" icon: "circle" mode: wide --- + SamplerEulerAncestral 노드는 이미지 생성을 위한 오일러 조상 샘플러를 생성합니다. 이 샘플러는 오일러 적분과 조상 샘플링 기법을 결합한 특정 수학적 접근 방식을 사용하여 이미지 변형을 생성합니다. 이 노드는 생성 과정 중 무작위성과 단계 크기를 제어하는 매개변수를 조정하여 샘플링 동작을 구성할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerEulerAncestralCFGPP.mdx b/ko/built-in-nodes/SamplerEulerAncestralCFGPP.mdx index dcc10b0c3..029ad17e6 100644 --- a/ko/built-in-nodes/SamplerEulerAncestralCFGPP.mdx +++ b/ko/built-in-nodes/SamplerEulerAncestralCFGPP.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerAncestralCFGPP" icon: "circle" mode: wide --- + SamplerEulerAncestralCFGPP 노드는 이미지 생성을 위해 분류기 자유도 안내(CFG++)와 함께 오일러 조상(Euler Ancestral) 방법을 사용하는 샘플러를 생성합니다. 이 샘플러는 조상 샘플링 기법과 안내 조건화를 결합하여 다양성을 유지하면서도 일관성 있는 이미지 변형을 생성하며, 노이즈와 스텝 크기 조정을 제어하는 매개변수를 통해 세부 조정이 가능합니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerEulerCFGpp.mdx b/ko/built-in-nodes/SamplerEulerCFGpp.mdx index e84d86f10..d5187a909 100644 --- a/ko/built-in-nodes/SamplerEulerCFGpp.mdx +++ b/ko/built-in-nodes/SamplerEulerCFGpp.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerEulerCFGpp" icon: "circle" mode: wide --- -# SamplerEulerCFGpp 노드 SamplerEulerCFGpp 노드는 출력을 생성하기 위한 Euler CFG++ 샘플링 방법을 제공합니다. 이 노드는 사용자 선호도에 따라 선택할 수 있는 두 가지 서로 다른 구현 버전의 Euler CFG++ 샘플러를 제공합니다. diff --git a/ko/built-in-nodes/SamplerLCM.mdx b/ko/built-in-nodes/SamplerLCM.mdx index f67d298d1..93f6fec1e 100644 --- a/ko/built-in-nodes/SamplerLCM.mdx +++ b/ko/built-in-nodes/SamplerLCM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLCM" icon: "circle" mode: wide --- + SamplerLCM 노드는 단계별 노이즈 매개변수를 조정할 수 있는 LCM(잠재 일관성 모델) 샘플러를 제공합니다. 각 샘플링 단계에서 적용되는 노이즈를 제어하여 샘플링 과정을 세밀하게 조정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerLCMUpscale.mdx b/ko/built-in-nodes/SamplerLCMUpscale.mdx index 0cac37bcf..85b8f35ae 100644 --- a/ko/built-in-nodes/SamplerLCMUpscale.mdx +++ b/ko/built-in-nodes/SamplerLCMUpscale.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerLCMUpscale" icon: "circle" mode: wide --- -# SamplerLCMUpscale SamplerLCMUpscale 노드는 잠재 일관성 모델(LCM) 샘플링과 이미지 업스케일링 기능을 결합한 특수 샘플링 방법을 제공합니다. 다양한 보간 방법을 사용하여 샘플링 과정 중에 이미지를 업스케일링할 수 있으므로, 이미지 품질을 유지하면서 더 높은 해상도의 출력물을 생성하는 데 유용합니다. diff --git a/ko/built-in-nodes/SamplerLMS.mdx b/ko/built-in-nodes/SamplerLMS.mdx index 201e4b764..25fa8c4bc 100644 --- a/ko/built-in-nodes/SamplerLMS.mdx +++ b/ko/built-in-nodes/SamplerLMS.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLMS" icon: "circle" mode: wide --- + SamplerLMS 노드는 확산 모델에서 사용하기 위한 최소 평균 제곱(LMS) 샘플러를 생성합니다. 샘플링 과정에서 사용할 수 있는 샘플러 객체를 생성하며, 수치적 안정성과 정확성을 위해 LMS 알고리즘의 차수를 제어할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/SamplerSASolver.mdx b/ko/built-in-nodes/SamplerSASolver.mdx index 0830c8722..f351e842a 100644 --- a/ko/built-in-nodes/SamplerSASolver.mdx +++ b/ko/built-in-nodes/SamplerSASolver.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerSASolver" icon: "circle" mode: wide --- -# SamplerSASolver 노드 SamplerSASolver 노드는 확산 모델을 위한 사용자 정의 샘플링 알고리즘을 구현합니다. 이 노드는 예측-보정 접근 방식을 사용하며, 설정 가능한 차수 설정과 확률적 미분 방정식(SDE) 매개변수를 통해 입력 모델로부터 샘플을 생성합니다. diff --git a/ko/built-in-nodes/SamplerSEEDS2.mdx b/ko/built-in-nodes/SamplerSEEDS2.mdx index 4e4b2657f..2ef76bff6 100644 --- a/ko/built-in-nodes/SamplerSEEDS2.mdx +++ b/ko/built-in-nodes/SamplerSEEDS2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerSEEDS2" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerSEEDS2/en.md) 이 노드는 이미지 생성을 위한 구성 가능한 샘플러를 제공합니다. 확률적 미분 방정식(SDE) 해석기인 SEEDS-2 알고리즘을 구현합니다. 매개변수를 조정하여 `seeds_2`, `exp_heun_2_x0`, `exp_heun_2_x0_sde`를 포함한 여러 특정 샘플러처럼 동작하도록 구성할 수 있습니다. diff --git a/ko/built-in-nodes/SamplingPercentToSigma.mdx b/ko/built-in-nodes/SamplingPercentToSigma.mdx index a39326523..45c587a7b 100644 --- a/ko/built-in-nodes/SamplingPercentToSigma.mdx +++ b/ko/built-in-nodes/SamplingPercentToSigma.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplingPercentToSigma" icon: "circle" mode: wide --- -# SamplingPercentToSigma (샘플링 백분율-시그마 변환) SamplingPercentToSigma 노드는 샘플링 백분율 값을 모델의 샘플링 매개변수를 사용하여 해당 시그마 값으로 변환합니다. 0.0에서 1.0 사이의 백분율 값을 입력받아 모델의 노이즈 스케줄에서 적절한 시그마 값으로 매핑하며, 경계값에서 계산된 시그마 또는 실제 최대/최소 시그마 값을 반환하는 옵션을 제공합니다. @@ -21,7 +20,7 @@ SamplingPercentToSigma 노드는 샘플링 백분율 값을 모델의 샘플링 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `sigma_value` | 입력 샘플링 백분율에 해당하는 변환된 시그마 값 | FLOAT | +| `시그마 값` | 입력 샘플링 백분율에 해당하는 변환된 시그마 값 | FLOAT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplingPercentToSigma/ko.md) diff --git a/ko/built-in-nodes/SaveAnimatedPNG.mdx b/ko/built-in-nodes/SaveAnimatedPNG.mdx index 4dbe6f72a..ffd123b71 100644 --- a/ko/built-in-nodes/SaveAnimatedPNG.mdx +++ b/ko/built-in-nodes/SaveAnimatedPNG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAnimatedPNG" icon: "circle" mode: wide --- + SaveAnimatedPNG 노드는 프레임 시퀀스로부터 애니메이션 PNG 이미지를 생성하고 저장하도록 설계되었습니다. 개별 이미지 프레임을 하나의 애니메이션으로 조합하여 프레임 지속 시간, 반복 재생 및 메타데이터 포함을 사용자 지정할 수 있습니다. ## 입력 @@ -20,6 +21,6 @@ SaveAnimatedPNG 노드는 프레임 시퀀스로부터 애니메이션 PNG 이 | 필드 | 설명 | 데이터 유형 | | --- | --- | --- | -| `ui` | 생성된 애니메이션 PNG 이미지를 표시하고, 애니메이션이 단일 프레임인지 다중 프레임인지 나타내는 UI 구성 요소를 제공합니다. | 해당 없음 | +| `images` | 생성된 애니메이션 PNG 이미지를 표시하고, 애니메이션이 단일 프레임인지 다중 프레임인지 나타내는 UI 구성 요소를 제공합니다. | 해당 없음 | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAnimatedPNG/ko.md) diff --git a/ko/built-in-nodes/SaveAnimatedWEBP.mdx b/ko/built-in-nodes/SaveAnimatedWEBP.mdx index 1446a91fd..0695df421 100644 --- a/ko/built-in-nodes/SaveAnimatedWEBP.mdx +++ b/ko/built-in-nodes/SaveAnimatedWEBP.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAnimatedWEBP" icon: "circle" mode: wide --- + 이 노드는 일련의 이미지들을 애니메이션 WEBP 파일로 저장하기 위해 설계되었습니다. 개별 프레임을 하나의 애니메이션으로 집계하고, 지정된 메타데이터를 적용하며, 품질 및 압축 설정에 따라 출력물을 최적화하는 기능을 처리합니다. ## 입력 @@ -22,6 +23,6 @@ mode: wide | 필드 | 설명 | 데이터 유형 | | --- | --- | --- | -| `ui` | 저장된 애니메이션 WEBP 이미지와 해당 메타데이터를 표시하고, 애니메이션 활성화 여부를 나타내는 UI 구성 요소를 제공합니다. | 해당 없음 | +| `images` | 저장된 애니메이션 WEBP 이미지와 해당 메타데이터를 표시하고, 애니메이션 활성화 여부를 나타내는 UI 구성 요소를 제공합니다. | 해당 없음 | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAnimatedWEBP/ko.md) diff --git a/ko/built-in-nodes/SaveAudio.mdx b/ko/built-in-nodes/SaveAudio.mdx index 37009b1a3..267771d41 100644 --- a/ko/built-in-nodes/SaveAudio.mdx +++ b/ko/built-in-nodes/SaveAudio.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveAudio" icon: "circle" mode: wide --- -# SaveAudio 노드 SaveAudio 노드는 오디오 데이터를 FLAC 형식의 파일로 저장합니다. 오디오 입력을 받아 지정된 출력 디렉토리에 주어진 파일명 접두사로 저장합니다. 이 노드는 자동으로 파일 이름을 처리하고 오디오가 추후 사용을 위해 적절히 저장되도록 보장합니다. diff --git a/ko/built-in-nodes/SaveAudioAdvanced.mdx b/ko/built-in-nodes/SaveAudioAdvanced.mdx index aea5c5b6f..52e6d8b95 100644 --- a/ko/built-in-nodes/SaveAudioAdvanced.mdx +++ b/ko/built-in-nodes/SaveAudioAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveAudioAdvanced" icon: "circle" mode: wide --- -# 오디오 저장 (고급) 입력된 오디오를 ComfyUI 출력 디렉토리에 저장합니다. 이 노드는 FLAC, MP3, Opus 등 다양한 형식으로 오디오를 내보낼 수 있으며, 품질 설정을 구성할 수 있습니다. @@ -25,7 +24,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | |-----------|------|------------| -| `ui` | 저장된 오디오 파일 정보를 포함하는 UI 출력입니다. | UI | +| `audio` | 저장된 오디오 파일 정보를 포함하는 UI 출력입니다. | UI | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAudioAdvanced/ko.md) diff --git a/ko/built-in-nodes/SaveAudioMP3.mdx b/ko/built-in-nodes/SaveAudioMP3.mdx index cfcf0bc19..8c04c1132 100644 --- a/ko/built-in-nodes/SaveAudioMP3.mdx +++ b/ko/built-in-nodes/SaveAudioMP3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAudioMP3" icon: "circle" mode: wide --- + SaveAudioMP3 노드는 오디오 데이터를 MP3 파일로 저장합니다. 오디오 입력을 받아 사용자 지정 파일 이름과 품질 설정으로 지정된 출력 디렉터리에 내보냅니다. 이 노드는 재생 가능한 MP3 파일을 생성하기 위해 파일 이름 지정과 형식 변환을 자동으로 처리합니다. ## 입력 diff --git a/ko/built-in-nodes/SaveAudioOpus.mdx b/ko/built-in-nodes/SaveAudioOpus.mdx index e3d10ba3d..a18700290 100644 --- a/ko/built-in-nodes/SaveAudioOpus.mdx +++ b/ko/built-in-nodes/SaveAudioOpus.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAudioOpus" icon: "circle" mode: wide --- + SaveAudioOpus 노드는 오디오 데이터를 Opus 형식 파일로 저장합니다. 오디오 입력을 받아 압축된 Opus 파일로 내보내며, 품질 설정을 구성할 수 있습니다. 이 노드는 자동으로 파일 이름을 처리하고 출력을 지정된 출력 디렉터리에 저장합니다. ## 입력 diff --git a/ko/built-in-nodes/SaveGLB.mdx b/ko/built-in-nodes/SaveGLB.mdx index 3203d8f77..759a95cbd 100644 --- a/ko/built-in-nodes/SaveGLB.mdx +++ b/ko/built-in-nodes/SaveGLB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveGLB" icon: "circle" mode: wide --- + SaveGLB 노드는 3D 메시 데이터 또는 3D 파일을 출력 디렉토리에 저장합니다. 메시 데이터 또는 다양한 3D 파일 형식(GLB, GLTF, OBJ, FBX, STL, USDZ)을 입력받아 지정된 파일 이름 접두사로 내보냅니다. 메시 데이터를 저장할 때는 여러 메시를 처리할 수 있으며, 메타데이터가 활성화된 경우 파일에 워크플로우 메타데이터가 자동으로 추가됩니다. ## 입력 diff --git a/ko/built-in-nodes/SaveImage.mdx b/ko/built-in-nodes/SaveImage.mdx index 43bcc1d2a..3c6478b7d 100644 --- a/ko/built-in-nodes/SaveImage.mdx +++ b/ko/built-in-nodes/SaveImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImage" icon: "circle" mode: wide --- + SaveImage 노드는 수신한 이미지를 `ComfyUI/output` 디렉토리에 저장합니다. 각 이미지를 PNG 파일로 저장하며, 향후 참조를 위해 프롬프트와 같은 워크플로우 메타데이터를 저장된 파일에 포함시킬 수 있습니다. ## 입력 @@ -18,7 +19,7 @@ SaveImage 노드는 수신한 이미지를 `ComfyUI/output` 디렉토리에 저 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `ui` | 이 노드는 저장된 이미지의 파일 이름과 하위 폴더 목록을 포함하는 UI 결과를 출력합니다. 다른 노드에 연결하기 위한 데이터는 출력하지 않습니다. | UI_RESULT | +| `images` | 이 노드는 저장된 이미지의 파일 이름과 하위 폴더 목록을 포함하는 UI 결과를 출력합니다. 다른 노드에 연결하기 위한 데이터는 출력하지 않습니다. | UI_RESULT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImage/ko.md) diff --git a/ko/built-in-nodes/SaveImageAdvanced.mdx b/ko/built-in-nodes/SaveImageAdvanced.mdx index 83aba92a4..2bc8b4912 100644 --- a/ko/built-in-nodes/SaveImageAdvanced.mdx +++ b/ko/built-in-nodes/SaveImageAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveImageAdvanced" icon: "circle" mode: wide --- -# SaveImageAdvanced **SaveImageAdvanced** 노드는 파일 형식, 비트 심도 및 색상 공간에 대한 고급 제어 기능을 제공하며 이미지를 ComfyUI 출력 디렉토리에 저장합니다. PNG 또는 EXR 파일로 저장하는 것을 지원하며, 저장된 파일에 워크플로우 메타데이터를 포함할 수 있습니다. diff --git a/ko/built-in-nodes/SaveImageDataSetToFolder.mdx b/ko/built-in-nodes/SaveImageDataSetToFolder.mdx index 9f8cb9c70..f9db603b3 100644 --- a/ko/built-in-nodes/SaveImageDataSetToFolder.mdx +++ b/ko/built-in-nodes/SaveImageDataSetToFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImageDataSetToFolder" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageDataSetToFolder/en.md) 이 노드는 이미지 목록을 ComfyUI 출력 디렉터리 내의 지정된 폴더에 저장합니다. 여러 이미지를 입력으로 받아 사용자 정의 가능한 파일명 접두사를 사용하여 디스크에 기록합니다. diff --git a/ko/built-in-nodes/SaveImageTextDataSetToFolder.mdx b/ko/built-in-nodes/SaveImageTextDataSetToFolder.mdx index a85e27dbb..652e4e5d4 100644 --- a/ko/built-in-nodes/SaveImageTextDataSetToFolder.mdx +++ b/ko/built-in-nodes/SaveImageTextDataSetToFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImageTextDataSetToFolder" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImageTextDataSetToFolder/en.md) 이미지와 텍스트 데이터셋을 폴더에 저장 노드는 이미지 목록과 해당하는 텍스트 캡션을 ComfyUI 출력 디렉터리 내의 지정된 폴더에 저장합니다. 각 이미지가 PNG 파일로 저장될 때, 동일한 기본 이름을 가진 텍스트 파일이 생성되어 해당 캡션을 저장합니다. 이는 생성된 이미지와 해당 설명으로 구성된 체계적인 데이터셋을 만드는 데 유용합니다. diff --git a/ko/built-in-nodes/SaveLatent.mdx b/ko/built-in-nodes/SaveLatent.mdx index c619728d7..7a5e2790f 100644 --- a/ko/built-in-nodes/SaveLatent.mdx +++ b/ko/built-in-nodes/SaveLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLatent" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLatent/en.md) SaveLatent 노드는 잠재 텐서를 디스크에 파일로 저장하여 추후 사용이나 공유가 가능하도록 합니다. 잠재 샘플을 입력받아 프롬프트 정보를 포함한 선택적 메타데이터와 함께 출력 디렉터리에 저장합니다. 이 노드는 잠재 데이터 구조를 유지하면서 파일 이름 지정과 구성을 자동으로 처리합니다. @@ -22,7 +23,7 @@ SaveLatent 노드는 잠재 텐서를 디스크에 파일로 저장하여 추후 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `ui` | ComfyUI 인터페이스에서 저장된 잠재 파일의 위치 정보를 제공합니다 | UI | +| `samples` | ComfyUI 인터페이스에서 저장된 잠재 파일의 위치 정보를 제공합니다 | UI | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLatent/ko.md) diff --git a/ko/built-in-nodes/SaveLoRA.mdx b/ko/built-in-nodes/SaveLoRA.mdx index 9df464bd3..bf5282730 100644 --- a/ko/built-in-nodes/SaveLoRA.mdx +++ b/ko/built-in-nodes/SaveLoRA.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLoRA" icon: "circle" mode: wide --- + SaveLoRA 노드는 LoRA(Low-Rank Adaptation) 모델을 파일로 저장합니다. LoRA 모델을 입력으로 받아 출력 디렉토리에 `.safetensors` 파일로 기록합니다. 최종 파일 이름에 포함될 파일명 접두사와 선택적 단계(step) 수를 지정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/SaveLoRANode.mdx b/ko/built-in-nodes/SaveLoRANode.mdx index 210de08a4..8efbcde34 100644 --- a/ko/built-in-nodes/SaveLoRANode.mdx +++ b/ko/built-in-nodes/SaveLoRANode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLoRANode" icon: "circle" mode: wide --- + SaveLoRA 노드는 LoRA(Low-Rank Adaptation) 모델을 출력 디렉토리에 저장합니다. LoRA 모델을 입력으로 받아 자동 생성된 파일 이름으로 safetensors 파일을 생성합니다. 파일 이름 접두사를 사용자 지정할 수 있으며, 선택적으로 학습 단계 수를 파일 이름에 포함하여 더 체계적으로 관리할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/SaveSVGNode.mdx b/ko/built-in-nodes/SaveSVGNode.mdx index 9ac8f3a84..3b627015f 100644 --- a/ko/built-in-nodes/SaveSVGNode.mdx +++ b/ko/built-in-nodes/SaveSVGNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveSVGNode" icon: "circle" mode: wide --- -# 개요 SVG 파일을 디스크에 저장합니다. 이 노드는 SVG 데이터를 입력으로 받아 선택적 메타데이터를 포함하여 출력 디렉토리에 저장합니다. 노드는 카운터 접미사를 사용하여 파일 이름을 자동으로 처리하며, 워크플로우 프롬프트 정보를 SVG 파일에 직접 포함시킬 수 있습니다. @@ -20,7 +19,7 @@ SVG 파일을 디스크에 저장합니다. 이 노드는 SVG 데이터를 입 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `ui` | ComfyUI 인터페이스에 표시하기 위한 파일 이름, 하위 폴더 및 유형을 포함한 파일 정보를 반환합니다 | DICT | +| `svg` | ComfyUI 인터페이스에 표시하기 위한 파일 이름, 하위 폴더 및 유형을 포함한 파일 정보를 반환합니다 | DICT | **참고:** 이 노드는 사용 가능한 경우 워크플로우 메타데이터(프롬프트 및 추가 PNG 정보)를 SVG 파일에 자동으로 포함시킵니다. 메타데이터는 SVG의 메타데이터 요소 내에 CDATA 섹션으로 삽입됩니다. diff --git a/ko/built-in-nodes/SaveTrainingDataset.mdx b/ko/built-in-nodes/SaveTrainingDataset.mdx index 1051c3af4..34c076e27 100644 --- a/ko/built-in-nodes/SaveTrainingDataset.mdx +++ b/ko/built-in-nodes/SaveTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveTrainingDataset" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveTrainingDataset/en.md) 이 노드는 준비된 학습 데이터셋을 컴퓨터의 하드 드라이브에 저장합니다. 이미지 잠재(latent)와 해당 텍스트 조건(conditioning)을 포함하는 인코딩된 데이터를 받아, 관리가 용이하도록 여러 개의 작은 파일(샤드)로 구성합니다. 노드는 출력 디렉토리에 자동으로 폴더를 생성하고, 데이터 파일과 데이터셋을 설명하는 메타데이터 파일을 저장합니다. diff --git a/ko/built-in-nodes/SaveVideo.mdx b/ko/built-in-nodes/SaveVideo.mdx index 2b3016cd3..1bf2f1da9 100644 --- a/ko/built-in-nodes/SaveVideo.mdx +++ b/ko/built-in-nodes/SaveVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveVideo" icon: "circle" mode: wide --- + SaveVideo 노드는 입력된 비디오 콘텐츠를 ComfyUI 출력 디렉터리에 저장합니다. 저장할 파일의 파일명 접두사, 비디오 형식 및 코덱을 지정할 수 있습니다. 이 노드는 카운터 증가를 통한 파일명 자동 처리 기능을 제공하며, 저장된 비디오에 워크플로우 메타데이터를 포함할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/SaveWEBM.mdx b/ko/built-in-nodes/SaveWEBM.mdx index 8cb3b0ace..d665ca6fc 100644 --- a/ko/built-in-nodes/SaveWEBM.mdx +++ b/ko/built-in-nodes/SaveWEBM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveWEBM" icon: "circle" mode: wide --- + SaveWEBM 노드는 이미지 시퀀스를 WEBM 비디오 파일로 저장합니다. 여러 입력 이미지를 받아 VP9 또는 AV1 코덱을 사용하여 구성 가능한 품질 설정과 프레임 속도로 비디오로 인코딩합니다. 결과 비디오 파일은 프롬프트 정보를 포함한 메타데이터와 함께 출력 디렉토리에 저장됩니다. ## 입력 @@ -21,7 +22,7 @@ SaveWEBM 노드는 이미지 시퀀스를 WEBM 비디오 파일로 저장합니 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `ui` | 저장된 WEBM 파일을 보여주는 비디오 미리보기 | PREVIEW | +| `images` | 저장된 WEBM 파일을 보여주는 비디오 미리보기 | PREVIEW | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveWEBM/ko.md) diff --git a/ko/built-in-nodes/ScaleROPE.mdx b/ko/built-in-nodes/ScaleROPE.mdx index 48d4cae1b..d9ff71a57 100644 --- a/ko/built-in-nodes/ScaleROPE.mdx +++ b/ko/built-in-nodes/ScaleROPE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ScaleROPE" icon: "circle" mode: wide --- + ScaleROPE 노드는 모델의 X, Y, T(시간) 구성 요소에 개별적인 스케일링 및 시프트 계수를 적용하여 ROPE(Rotary Position Embedding)를 수정할 수 있게 해줍니다. 이는 모델의 위치 인코딩 동작을 조정하는 데 사용되는 고급 실험적 노드입니다. ## 입력 diff --git a/ko/built-in-nodes/Sd4xupscaleConditioning.mdx b/ko/built-in-nodes/Sd4xupscaleConditioning.mdx index 6466ebffd..3e97acd9c 100644 --- a/ko/built-in-nodes/Sd4xupscaleConditioning.mdx +++ b/ko/built-in-nodes/Sd4xupscaleConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Sd4xupscaleConditioning" icon: "circle" mode: wide --- + 이 노드는 이미지 해상도를 4배로 향상시키는 업스케일 과정에 특화되어 있으며, 출력 결과를 정교하게 다듬기 위해 컨디셔닝 요소를 통합합니다. 확산 기법을 활용하여 이미지를 업스케일하는 동시에 스케일 비율과 노이즈 증강을 조정하여 향상 과정을 미세 조정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/SeedNode.mdx b/ko/built-in-nodes/SeedNode.mdx new file mode 100644 index 000000000..ec2decb79 --- /dev/null +++ b/ko/built-in-nodes/SeedNode.mdx @@ -0,0 +1,28 @@ +--- +title: "SeedNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the SeedNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "SeedNode" +icon: "circle" +mode: wide +--- + +## 개요 + +Seed 노드는 고정되거나 무작위의 정수 값을 생성합니다. 다른 노드에서 무작위 연산의 재현성을 제어하기 위해 일관된 시작점을 제공하는 데 일반적으로 사용됩니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `시드` | 사용할 시드 값입니다. 생성 후 제어 옵션은 값이 고정된 상태로 유지될지, 아니면 각 생성 후 변경될지를 결정합니다. | INT | 예 | 0 ~ 9223372036854775807 | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `시드` | 생성된 시드 값입니다. | INT | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SeedNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `19f9b22945bb152ff5066195067f1b6b4c006589f26c7533fad905044ac3b7fa` diff --git a/ko/built-in-nodes/SeedVR2Conditioning.mdx b/ko/built-in-nodes/SeedVR2Conditioning.mdx index 75e403626..9db453dc6 100644 --- a/ko/built-in-nodes/SeedVR2Conditioning.mdx +++ b/ko/built-in-nodes/SeedVR2Conditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2Conditioning" icon: "circle" mode: wide --- -# Apply SeedVR2 Conditioning 노드 이 노드는 SeedVR2 모델과 함께 사용하기 위해 VAE 잠재 변수로부터 긍정 및 부정 컨디셔닝을 구축합니다. 이미지 또는 비디오 생성 과정을 안내하는 컨디셔닝 데이터를 준비합니다. diff --git a/ko/built-in-nodes/SeedVR2PostProcessing.mdx b/ko/built-in-nodes/SeedVR2PostProcessing.mdx index 95d810fe0..c36eaef7d 100644 --- a/ko/built-in-nodes/SeedVR2PostProcessing.mdx +++ b/ko/built-in-nodes/SeedVR2PostProcessing.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2PostProcessing" icon: "circle" mode: wide --- -# Post-Process SeedVR2 Output 이 노드는 생성된 이미지를 원본 리사이즈 이미지와 정렬하고 선택적으로 색상 보정을 적용합니다. SeedVR2 업스케일링 프로세스의 출력을 받아 원본 참조 이미지의 색상과 크기에 맞게 조정합니다. diff --git a/ko/built-in-nodes/SeedVR2Preprocess.mdx b/ko/built-in-nodes/SeedVR2Preprocess.mdx index ecfe0ba6c..c108bf574 100644 --- a/ko/built-in-nodes/SeedVR2Preprocess.mdx +++ b/ko/built-in-nodes/SeedVR2Preprocess.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2Preprocess" icon: "circle" mode: wide --- -# Pre-Process SeedVR2 Input 이 노드는 크기가 조정된 이미지에 패딩을 적용하여 SeedVR2 모델에 입력할 준비를 합니다. 처리 과정에서 알파 채널을 제거하며, 이후 함께 제공되는 Post-Process SeedVR2 Output 노드가 원본 크기 조정 이미지를 사용하여 알파 채널을 복원합니다. diff --git a/ko/built-in-nodes/SeedVR2ProgressiveSampler.mdx b/ko/built-in-nodes/SeedVR2ProgressiveSampler.mdx index 95a56a23d..e8c0f5ea2 100644 --- a/ko/built-in-nodes/SeedVR2ProgressiveSampler.mdx +++ b/ko/built-in-nodes/SeedVR2ProgressiveSampler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2ProgressiveSampler" icon: "circle" mode: wide --- -# SeedVR2ProgressiveSampler SeedVR2 네이티브 워크플로우를 위한 순차적 시간 청크 샘플러입니다. 이 노드는 긴 비디오 잠재 변수를 더 작은 시간 청크로 분할하고, 각 청크를 순차적으로 샘플링한 후 결과를 혼합하여 처리합니다. SeedVR2 모델로 작업할 때 메모리 부족 오류가 발생할 수 있는 시퀀스에서 표준 KSampler를 대체하여 사용할 수 있습니다. diff --git a/ko/built-in-nodes/SelectCLIPDevice.mdx b/ko/built-in-nodes/SelectCLIPDevice.mdx index 393ff0648..545451252 100644 --- a/ko/built-in-nodes/SelectCLIPDevice.mdx +++ b/ko/built-in-nodes/SelectCLIPDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectCLIPDevice" icon: "circle" mode: wide --- + ## 개요 Select CLIP Device 노드는 CLIP 텍스트 인코더가 실행될 장치(CPU 또는 특정 GPU)를 선택할 수 있게 해줍니다. 기본적으로 장치는 모델 로더에 의해 할당되지만, CPU나 특정 GPU를 사용하도록 재정의할 수 있습니다. 요청한 장치가 시스템에 존재하지 않는 경우, 노드는 오류를 발생시키는 대신 CLIP을 변경 없이 그대로 전달하고 메시지를 기록합니다. diff --git a/ko/built-in-nodes/SelectModelDevice.mdx b/ko/built-in-nodes/SelectModelDevice.mdx index c13e8e229..516cc8097 100644 --- a/ko/built-in-nodes/SelectModelDevice.mdx +++ b/ko/built-in-nodes/SelectModelDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectModelDevice" icon: "circle" mode: wide --- + ## 개요 SelectModelDevice 노드는 확산 모델이 실행될 장치(CPU 또는 특정 GPU)를 수동으로 선택할 수 있게 해줍니다. 모델을 다른 장치로 이동시킬 수 있으며, 다른 멀티 GPU 노드와의 충돌을 자동으로 처리합니다. diff --git a/ko/built-in-nodes/SelectVAEDevice.mdx b/ko/built-in-nodes/SelectVAEDevice.mdx index 635ab24bb..b7c31c8f8 100644 --- a/ko/built-in-nodes/SelectVAEDevice.mdx +++ b/ko/built-in-nodes/SelectVAEDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectVAEDevice" icon: "circle" mode: wide --- + ## 개요 이 노드는 VAE 모델을 배치할 GPU 장치를 수동으로 선택할 수 있게 해줍니다. 기본적으로 VAE는 모델 로더가 할당한 장치에 배치되지만, 특정 GPU(예: `gpu:0`, `gpu:1`)에 고정할 수 있습니다. 선택한 장치를 사용할 수 없는 경우, 노드는 VAE를 변경 없이 그대로 전달하고 오류 대신 메시지를 기록합니다. diff --git a/ko/built-in-nodes/SelfAttentionGuidance.mdx b/ko/built-in-nodes/SelfAttentionGuidance.mdx index 59cd35ab1..f5433cd53 100644 --- a/ko/built-in-nodes/SelfAttentionGuidance.mdx +++ b/ko/built-in-nodes/SelfAttentionGuidance.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SelfAttentionGuidance" icon: "circle" mode: wide --- -# Self-Attention Guidance (자기 주의 유도) 자기 주의 유도 노드는 샘플링 과정에서 주의 메커니즘을 수정하여 확산 모델에 유도를 적용합니다. 비조건부 잡음 제거 단계에서 주의 점수를 포착하고 이를 사용하여 최종 출력에 영향을 미치는 흐릿한 유도 맵을 생성합니다. 이 기법은 모델 자체의 주의 패턴을 활용하여 생성 과정을 안내하는 데 도움을 줍니다. diff --git a/ko/built-in-nodes/SetClipHooks.mdx b/ko/built-in-nodes/SetClipHooks.mdx index ed5082435..dd69a72f9 100644 --- a/ko/built-in-nodes/SetClipHooks.mdx +++ b/ko/built-in-nodes/SetClipHooks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetClipHooks" icon: "circle" mode: wide --- + SetClipHooks 노드는 CLIP 모델에 사용자 정의 후크를 적용하여 동작을 고급 수준으로 수정할 수 있도록 합니다. 이 노드는 컨디셔닝 출력에 후크를 적용하고 선택적으로 클립 스케줄링 기능을 활성화할 수 있습니다. 지정된 후크 구성이 적용된 입력 CLIP 모델의 복제본을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/SetFirstSigma.mdx b/ko/built-in-nodes/SetFirstSigma.mdx index bfc30f801..02b89fd1e 100644 --- a/ko/built-in-nodes/SetFirstSigma.mdx +++ b/ko/built-in-nodes/SetFirstSigma.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetFirstSigma" icon: "circle" mode: wide --- + SetFirstSigma 노드는 시그마 값 시퀀스의 첫 번째 시그마 값을 사용자 지정 값으로 대체하여 수정합니다. 기존 시그마 시퀀스와 새 시그마 값을 입력으로 받아, 첫 번째 요소만 변경되고 나머지 시그마 값은 그대로 유지된 새 시그마 시퀀스를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/SetHookKeyframes.mdx b/ko/built-in-nodes/SetHookKeyframes.mdx index 98535ac0c..7942b74bd 100644 --- a/ko/built-in-nodes/SetHookKeyframes.mdx +++ b/ko/built-in-nodes/SetHookKeyframes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetHookKeyframes" icon: "circle" mode: wide --- + ## 입력 | 매개변수 | 설명 | 데이터 타입 | 필수 여부 | 범위 | diff --git a/ko/built-in-nodes/SetLatentNoiseMask.mdx b/ko/built-in-nodes/SetLatentNoiseMask.mdx index 4126fab45..54b916bbc 100644 --- a/ko/built-in-nodes/SetLatentNoiseMask.mdx +++ b/ko/built-in-nodes/SetLatentNoiseMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetLatentNoiseMask" icon: "circle" mode: wide --- + 이 노드는 잠재 샘플 세트에 노이즈 마스크를 적용하도록 설계되었습니다. 지정된 마스크를 통합하여 입력 샘플을 수정함으로써 노이즈 특성을 변경합니다. ## 입력 diff --git a/ko/built-in-nodes/SetModelHooksOnCond.mdx b/ko/built-in-nodes/SetModelHooksOnCond.mdx index 99424b678..5577f7409 100644 --- a/ko/built-in-nodes/SetModelHooksOnCond.mdx +++ b/ko/built-in-nodes/SetModelHooksOnCond.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetModelHooksOnCond" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SetModelHooksOnCond/en.md) 이 노드는 조건화 데이터에 사용자 정의 후크를 연결하여 모델 실행 중 조건화 프로세스를 가로채고 수정할 수 있도록 합니다. 후크 집합을 가져와 제공된 조건화 데이터에 적용함으로써 텍스트-이미지 생성 워크플로우의 고급 사용자 정의를 가능하게 합니다. 후크가 연결된 수정된 조건화 데이터는 이후 처리 단계에서 사용하기 위해 반환됩니다. diff --git a/ko/built-in-nodes/SetUnionControlNetType.mdx b/ko/built-in-nodes/SetUnionControlNetType.mdx index c0599eff0..db7f1c605 100644 --- a/ko/built-in-nodes/SetUnionControlNetType.mdx +++ b/ko/built-in-nodes/SetUnionControlNetType.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetUnionControlNetType" icon: "circle" mode: wide --- + SetUnionControlNetType 노드는 컨디셔닝에 사용할 제어 네트워크 유형을 지정할 수 있도록 합니다. 기존 제어 네트워크를 가져와 선택한 유형을 설정하고, 지정된 유형 구성이 적용된 수정된 복사본을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/ShuffleDataset.mdx b/ko/built-in-nodes/ShuffleDataset.mdx index ea0d3a439..66bcc9e16 100644 --- a/ko/built-in-nodes/ShuffleDataset.mdx +++ b/ko/built-in-nodes/ShuffleDataset.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ShuffleDataset" icon: "circle" mode: wide --- -# Shuffle Dataset 노드 Shuffle Dataset 노드는 이미지 목록을 받아 무작위로 순서를 변경합니다. 시드(seed) 값을 사용하여 무작위성을 제어하므로 동일한 셔플 순서를 재현할 수 있습니다. 이는 데이터셋을 처리하기 전에 이미지 순서를 무작위화하는 데 유용합니다. diff --git a/ko/built-in-nodes/ShuffleImageTextDataset.mdx b/ko/built-in-nodes/ShuffleImageTextDataset.mdx index b14a0ac14..781798b38 100644 --- a/ko/built-in-nodes/ShuffleImageTextDataset.mdx +++ b/ko/built-in-nodes/ShuffleImageTextDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ShuffleImageTextDataset" icon: "circle" mode: wide --- + 이 노드는 이미지 목록과 텍스트 목록을 함께 섞어서 각각의 쌍을 유지합니다. 무작위 시드를 사용하여 섞기 순서를 결정하므로, 동일한 입력 목록은 시드가 재사용될 때마다 동일한 방식으로 섞입니다. ## 입력 @@ -21,7 +22,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `texts` | 섞인 이미지 목록입니다. | IMAGE | +| `images` | 섞인 이미지 목록입니다. | IMAGE | | `texts` | 섞인 텍스트 목록으로, 이미지와의 원래 쌍을 유지합니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ShuffleImageTextDataset/ko.md) diff --git a/ko/built-in-nodes/SkipLayerGuidanceDiT.mdx b/ko/built-in-nodes/SkipLayerGuidanceDiT.mdx index e84d52615..c56250057 100644 --- a/ko/built-in-nodes/SkipLayerGuidanceDiT.mdx +++ b/ko/built-in-nodes/SkipLayerGuidanceDiT.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceDiT" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SkipLayerGuidanceDiT/en.md) 레이어를 건너뛴 또 다른 CFG 네거티브 세트를 사용하여 세부 구조에 대한 가이던스를 향상시킵니다. 이 일반화된 버전의 SkipLayerGuidance는 모든 DiT 모델에 사용할 수 있으며, Perturbed Attention Guidance에서 영감을 받았습니다. 원래 실험적 구현은 SD3를 위해 만들어졌습니다. diff --git a/ko/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx b/ko/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx index 6b771d496..9df733050 100644 --- a/ko/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx +++ b/ko/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceDiTSimple" icon: "circle" mode: wide --- + ## 개요 SkipLayerGuidanceDiT 노드의 간소화된 버전으로, 노이즈 제거 과정 중 무조건부 패스(unconditional pass)만 수정합니다. 이 노드는 지정된 타이밍과 레이어 매개변수에 따라 무조건부 패스 중 특정 트랜스포머 레이어를 선택적으로 건너뛰어 DiT(Diffusion Transformer) 모델에 스킵 레이어 가이던스를 적용합니다. diff --git a/ko/built-in-nodes/SkipLayerGuidanceSD3.mdx b/ko/built-in-nodes/SkipLayerGuidanceSD3.mdx index 0e49f501f..07d9afbb7 100644 --- a/ko/built-in-nodes/SkipLayerGuidanceSD3.mdx +++ b/ko/built-in-nodes/SkipLayerGuidanceSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceSD3" icon: "circle" mode: wide --- + SkipLayerGuidanceSD3 노드는 건너뛴 레이어를 사용하여 추가적인 분류기-프리 가이던스를 적용함으로써 세부 구조를 향상시키는 방향으로 가이던스를 강화합니다. 이 실험적 구현은 Perturbed Attention Guidance에서 영감을 받았으며, 부정적 조건화 과정에서 특정 레이어를 선택적으로 우회하여 생성 결과물의 구조적 세부 사항을 개선하는 방식으로 작동합니다. ## 입력 diff --git a/ko/built-in-nodes/SolidMask.mdx b/ko/built-in-nodes/SolidMask.mdx index 322a91877..d0670974b 100644 --- a/ko/built-in-nodes/SolidMask.mdx +++ b/ko/built-in-nodes/SolidMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SolidMask" icon: "circle" mode: wide --- + SolidMask 노드는 전체 영역에 걸쳐 지정된 값을 가진 균일한 마스크를 생성합니다. 특정 크기와 강도의 마스크를 만들기 위해 설계되었으며, 다양한 이미지 처리 및 마스킹 작업에 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/SoniloTextToMusic.mdx b/ko/built-in-nodes/SoniloTextToMusic.mdx index 147a2cff3..e38df1a18 100644 --- a/ko/built-in-nodes/SoniloTextToMusic.mdx +++ b/ko/built-in-nodes/SoniloTextToMusic.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SoniloTextToMusic" icon: "circle" mode: wide --- -# Sonilo 텍스트-음악 변환 노드 Sonilo 텍스트-음악 변환 노드는 Sonilo의 AI 모델을 사용하여 텍스트 설명으로부터 음악을 생성합니다. 원하는 음악을 설명하는 프롬프트를 제공하면, 노드가 Sonilo 서비스에 요청을 보내 오디오 파일을 생성합니다. 대상 재생 시간을 지정하거나 프롬프트를 기반으로 모델이 자동으로 추정하도록 할 수 있습니다. diff --git a/ko/built-in-nodes/SoniloVideoToMusic.mdx b/ko/built-in-nodes/SoniloVideoToMusic.mdx index 49b1d8afe..97b5138ff 100644 --- a/ko/built-in-nodes/SoniloVideoToMusic.mdx +++ b/ko/built-in-nodes/SoniloVideoToMusic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SoniloVideoToMusic" icon: "circle" mode: wide --- + 다음은 ComfyUI 노드 문서의 한국어 번역입니다. 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SoniloVideoToMusic/en.md) diff --git a/ko/built-in-nodes/SplatToFile3D.mdx b/ko/built-in-nodes/SplatToFile3D.mdx index cc4a8ecaf..db2c9bfd5 100644 --- a/ko/built-in-nodes/SplatToFile3D.mdx +++ b/ko/built-in-nodes/SplatToFile3D.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SplatToFile3D" icon: "circle" mode: wide --- -# SplatToFile3D 노드 문서 ## 개요 diff --git a/ko/built-in-nodes/SplatToMesh.mdx b/ko/built-in-nodes/SplatToMesh.mdx index e38fae00b..c9e0d46ec 100644 --- a/ko/built-in-nodes/SplatToMesh.mdx +++ b/ko/built-in-nodes/SplatToMesh.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SplatToMesh" icon: "circle" mode: wide --- -# Splat에서 메시 추출 이 노드는 3D 가우시안 스플랫을 색상이 있는 메시 표면으로 변환합니다. 가우시안을 밀도 그리드에 래스터화하고, 선택한 밀도 수준에서 등위면을 추출한 후, 선택적으로 평활화 및 정리 과정을 적용하여 깨끗하고 색상이 있는 삼각형 메시를 생성하는 방식으로 작동합니다. diff --git a/ko/built-in-nodes/SplitAudioChannels.mdx b/ko/built-in-nodes/SplitAudioChannels.mdx index d0be8bb21..4213997ba 100644 --- a/ko/built-in-nodes/SplitAudioChannels.mdx +++ b/ko/built-in-nodes/SplitAudioChannels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitAudioChannels" icon: "circle" mode: wide --- + SplitAudioChannels 노드는 스테레오 오디오를 개별 좌측 및 우측 채널로 분리합니다. 두 개의 채널로 구성된 스테레오 오디오 입력을 받아 각각 좌측 채널과 우측 채널에 해당하는 두 개의 개별 오디오 스트림을 출력합니다. ## 입력 @@ -19,8 +20,8 @@ SplitAudioChannels 노드는 스테레오 오디오를 개별 좌측 및 우측 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `오른쪽` | 분리된 좌측 채널 오디오 | AUDIO | -| `right` | 분리된 우측 채널 오디오 | AUDIO | +| `왼쪽` | 분리된 좌측 채널 오디오 | AUDIO | +| `오른쪽` | 분리된 우측 채널 오디오 | AUDIO | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitAudioChannels/ko.md) diff --git a/ko/built-in-nodes/SplitImageToTileList.mdx b/ko/built-in-nodes/SplitImageToTileList.mdx index 742083f7c..d8797ebb8 100644 --- a/ko/built-in-nodes/SplitImageToTileList.mdx +++ b/ko/built-in-nodes/SplitImageToTileList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitImageToTileList" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitImageToTileList/en.md) Split Image into List of Tiles 노드는 단일 입력 이미지를 타일이라고 하는 더 작은 겹치는 직사각형 영역의 시리즈로 분할합니다. 이러한 타일들을 배치 목록으로 생성하여 다른 노드에서 개별적으로 처리할 수 있도록 합니다. 각 타일의 크기와 타일 간의 겹침 정도를 지정할 수 있습니다. diff --git a/ko/built-in-nodes/SplitImageWithAlpha.mdx b/ko/built-in-nodes/SplitImageWithAlpha.mdx index 5af055790..ee6a8bd5e 100644 --- a/ko/built-in-nodes/SplitImageWithAlpha.mdx +++ b/ko/built-in-nodes/SplitImageWithAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitImageWithAlpha" icon: "circle" mode: wide --- + `SplitImageWithAlpha` 노드는 이미지의 색상 구성 요소와 알파 구성 요소를 분리하도록 설계되었습니다. 입력 이미지 텐서를 처리하여 RGB 채널을 색상 구성 요소로, 알파 채널을 투명도 구성 요소로 추출함으로써, 이러한 개별 이미지 측면을 조작해야 하는 작업을 용이하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/SplitSigmas.mdx b/ko/built-in-nodes/SplitSigmas.mdx index e1c722c53..fba1d5357 100644 --- a/ko/built-in-nodes/SplitSigmas.mdx +++ b/ko/built-in-nodes/SplitSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitSigmas" icon: "circle" mode: wide --- + SplitSigmas 노드는 시그마 값 시퀀스를 지정된 단계에 따라 두 부분으로 분할하도록 설계되었습니다. 이 기능은 시그마 시퀀스의 초기 부분과 후속 부분에 대해 서로 다른 처리나 가공이 필요한 작업에 필수적이며, 이러한 값들을 보다 유연하고 목적에 맞게 조작할 수 있게 해줍니다. ## 입력 @@ -18,6 +19,6 @@ SplitSigmas 노드는 시그마 값 시퀀스를 지정된 단계에 따라 두 | 매개변수 | 설명 | 데이터 타입 | | --- | --- | --- | -| `로우 시그마` | 노드는 두 개의 시그마 값 시퀀스를 출력하며, 각각은 지정된 단계에서 분할된 원본 시퀀스의 일부를 나타냅니다. 이러한 출력은 시그마 값에 대해 차별화된 처리가 필요한 후속 작업에 중요합니다. | `SIGMAS` | +| `하이 시그마` | 노드는 두 개의 시그마 값 시퀀스를 출력하며, 각각은 지정된 단계에서 분할된 원본 시퀀스의 일부를 나타냅니다. 이러한 출력은 시그마 값에 대해 차별화된 처리가 필요한 후속 작업에 중요합니다. | `SIGMAS` | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitSigmas/ko.md) diff --git a/ko/built-in-nodes/SplitSigmasDenoise.mdx b/ko/built-in-nodes/SplitSigmasDenoise.mdx index 507c9d42f..9b00d6edd 100644 --- a/ko/built-in-nodes/SplitSigmasDenoise.mdx +++ b/ko/built-in-nodes/SplitSigmasDenoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitSigmasDenoise" icon: "circle" mode: wide --- + SplitSigmasDenoise 노드는 디노이징 강도 매개변수를 기준으로 시그마 값 시퀀스를 두 부분으로 분할합니다. 입력 시그마를 높은 시그마 시퀀스와 낮은 시그마 시퀀스로 나누며, 분할 지점은 전체 단계 수에 디노이즈 계수를 곱하여 결정됩니다. 이를 통해 노이즈 스케줄을 서로 다른 강도 범위로 분리하여 특수 처리를 수행할 수 있습니다. ## 입력 @@ -18,8 +19,8 @@ SplitSigmasDenoise 노드는 디노이징 강도 매개변수를 기준으로 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `로우 시그마` | 더 높은 시그마 값을 포함하는 시그마 시퀀스의 첫 번째 부분 | SIGMAS | -| `low_sigmas` | 더 낮은 시그마 값을 포함하는 시그마 시퀀스의 두 번째 부분 | SIGMAS | +| `하이 시그마` | 더 높은 시그마 값을 포함하는 시그마 시퀀스의 첫 번째 부분 | SIGMAS | +| `로우 시그마` | 더 낮은 시그마 값을 포함하는 시그마 시퀀스의 두 번째 부분 | SIGMAS | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitSigmasDenoise/ko.md) diff --git a/ko/built-in-nodes/StabilityAudioInpaint.mdx b/ko/built-in-nodes/StabilityAudioInpaint.mdx index 6ae91e79f..2baa2a995 100644 --- a/ko/built-in-nodes/StabilityAudioInpaint.mdx +++ b/ko/built-in-nodes/StabilityAudioInpaint.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StabilityAudioInpaint" icon: "circle" mode: wide --- -# 개요 텍스트 명령어를 사용하여 기존 오디오 샘플의 일부를 변환합니다. 이 노드를 사용하면 설명 프롬프트를 제공하여 오디오의 특정 구간을 수정할 수 있으며, 나머지 부분은 유지하면서 선택한 부분을 효과적으로 "인페인팅"하거나 재생성합니다. diff --git a/ko/built-in-nodes/StabilityAudioToAudio.mdx b/ko/built-in-nodes/StabilityAudioToAudio.mdx index 5557d795e..ef87c1a46 100644 --- a/ko/built-in-nodes/StabilityAudioToAudio.mdx +++ b/ko/built-in-nodes/StabilityAudioToAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityAudioToAudio" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityAudioToAudio/en.md) 텍스트 명령어를 사용하여 기존 오디오 샘플을 새로운 고품질 작품으로 변환합니다. 이 노드는 입력 오디오 파일을 받아 텍스트 프롬프트를 기반으로 수정하여 새로운 오디오 콘텐츠를 생성합니다. diff --git a/ko/built-in-nodes/StabilityStableImageSD_3_5Node.mdx b/ko/built-in-nodes/StabilityStableImageSD_3_5Node.mdx index 847568673..8ced3f24f 100644 --- a/ko/built-in-nodes/StabilityStableImageSD_3_5Node.mdx +++ b/ko/built-in-nodes/StabilityStableImageSD_3_5Node.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityStableImageSD_3_5Node" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityStableImageSD_3_5Node/en.md) 이 노드는 Stability AI의 Stable Diffusion 3.5 모델을 사용하여 이미지를 동기식으로 생성합니다. 텍스트 프롬프트를 기반으로 이미지를 만들며, 입력으로 제공될 경우 기존 이미지를 수정할 수도 있습니다. 이 노드는 출력을 사용자 지정하기 위해 다양한 종횡비와 스타일 프리셋을 지원합니다. diff --git a/ko/built-in-nodes/StabilityStableImageUltraNode.mdx b/ko/built-in-nodes/StabilityStableImageUltraNode.mdx index 5ef269c2d..7d855d3e5 100644 --- a/ko/built-in-nodes/StabilityStableImageUltraNode.mdx +++ b/ko/built-in-nodes/StabilityStableImageUltraNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StabilityStableImageUltraNode" icon: "circle" mode: wide --- -# Stability Stable Image Ultra 노드 프롬프트와 해상도를 기반으로 이미지를 동기식으로 생성합니다. 이 노드는 Stability AI의 Stable Image Ultra 모델을 사용하여 텍스트 프롬프트를 처리하고 지정된 종횡비와 스타일로 해당 이미지를 생성합니다. diff --git a/ko/built-in-nodes/StabilityTextToAudio.mdx b/ko/built-in-nodes/StabilityTextToAudio.mdx index e6fdd1702..92d0d8c99 100644 --- a/ko/built-in-nodes/StabilityTextToAudio.mdx +++ b/ko/built-in-nodes/StabilityTextToAudio.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StabilityTextToAudio" icon: "circle" mode: wide --- -# 개요 텍스트 설명으로부터 고품질의 음악과 음향 효과를 생성합니다. 이 노드는 Stability AI의 오디오 생성 기술을 사용하여 텍스트 프롬프트를 기반으로 오디오 콘텐츠를 만듭니다. diff --git a/ko/built-in-nodes/StabilityUpscaleConservativeNode.mdx b/ko/built-in-nodes/StabilityUpscaleConservativeNode.mdx index 58edb9c4e..689308ba0 100644 --- a/ko/built-in-nodes/StabilityUpscaleConservativeNode.mdx +++ b/ko/built-in-nodes/StabilityUpscaleConservativeNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StabilityUpscaleConservativeNode" icon: "circle" mode: wide --- -# StabilityUpscaleConservativeNode 원본 이미지를 최소한으로 변경하여 4K 해상도로 업스케일합니다. 이 노드는 Stability AI의 보수적 업스케일링을 사용하여 이미지 해상도를 높이면서 원본 콘텐츠를 보존하고 미묘한 변경만 적용합니다. diff --git a/ko/built-in-nodes/StabilityUpscaleCreativeNode.mdx b/ko/built-in-nodes/StabilityUpscaleCreativeNode.mdx index a1eed11fb..ac006d124 100644 --- a/ko/built-in-nodes/StabilityUpscaleCreativeNode.mdx +++ b/ko/built-in-nodes/StabilityUpscaleCreativeNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StabilityUpscaleCreativeNode" icon: "circle" mode: wide --- -# Stability Upscale Creative 노드 원본 이미지를 최소한으로 변경하여 4K 해상도로 업스케일합니다. 이 노드는 Stability AI의 창의적 업스케일링 기술을 사용하여 원본 콘텐츠를 보존하면서 미묘한 창의적 디테일을 추가하여 이미지 해상도를 향상시킵니다. diff --git a/ko/built-in-nodes/StabilityUpscaleFastNode.mdx b/ko/built-in-nodes/StabilityUpscaleFastNode.mdx index 6992c7211..bc021eeaa 100644 --- a/ko/built-in-nodes/StabilityUpscaleFastNode.mdx +++ b/ko/built-in-nodes/StabilityUpscaleFastNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StabilityUpscaleFastNode" icon: "circle" mode: wide --- -# StabilityUpscaleFastNode Stability API 호출을 통해 이미지를 원본 크기의 4배로 빠르게 업스케일합니다. 이 노드는 저품질 또는 압축된 이미지를 Stability AI의 빠른 업스케일링 서비스로 전송하여 업스케일링하기 위해 특별히 설계되었습니다. diff --git a/ko/built-in-nodes/StableCascade_EmptyLatentImage.mdx b/ko/built-in-nodes/StableCascade_EmptyLatentImage.mdx index c53de6553..addcf9a42 100644 --- a/ko/built-in-nodes/StableCascade_EmptyLatentImage.mdx +++ b/ko/built-in-nodes/StableCascade_EmptyLatentImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StableCascade_EmptyLatentImage" icon: "circle" mode: wide --- -# StableCascade_EmptyLatentImage StableCascade_EmptyLatentImage 노드는 Stable Cascade 모델을 위한 빈 잠재 텐서를 생성합니다. 입력 해상도와 압축 설정에 따라 적절한 차원을 가진 두 개의 개별 잠재 표현(스테이지 C용과 스테이지 B용)을 생성합니다. 이 노드는 Stable Cascade 생성 파이프라인의 시작점을 제공합니다. @@ -22,8 +21,8 @@ StableCascade_EmptyLatentImage 노드는 Stable Cascade 모델을 위한 빈 잠 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `StageB 잠재 이미지` | 차원이 [batch_size, 16, height//compression, width//compression]인 스테이지 C 잠재 텐서 | LATENT | -| `stage_b` | 차원이 [batch_size, 4, height//4, width//4]인 스테이지 B 잠재 텐서 | LATENT | +| `StageC 잠재 이미지` | 차원이 [batch_size, 16, height//compression, width//compression]인 스테이지 C 잠재 텐서 | LATENT | +| `StageB 잠재 이미지` | 차원이 [batch_size, 4, height//4, width//4]인 스테이지 B 잠재 텐서 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_EmptyLatentImage/ko.md) diff --git a/ko/built-in-nodes/StableCascade_StageB_Conditioning.mdx b/ko/built-in-nodes/StableCascade_StageB_Conditioning.mdx index c5b9f436e..87bb58d3b 100644 --- a/ko/built-in-nodes/StableCascade_StageB_Conditioning.mdx +++ b/ko/built-in-nodes/StableCascade_StageB_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_StageB_Conditioning" icon: "circle" mode: wide --- + StableCascade_StageB_Conditioning 노드는 기존 컨디셔닝 정보를 Stage C의 사전 잠재 표현과 결합하여 Stable Cascade Stage B 생성을 위한 컨디셔닝 데이터를 준비합니다. 이 노드는 Stage C의 잠재 샘플을 포함하도록 컨디셔닝 데이터를 수정하여, 생성 과정이 사전 정보를 활용해 더 일관된 결과를 도출할 수 있도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/StableCascade_StageC_VAEEncode.mdx b/ko/built-in-nodes/StableCascade_StageC_VAEEncode.mdx index 47c99a244..05ed8498c 100644 --- a/ko/built-in-nodes/StableCascade_StageC_VAEEncode.mdx +++ b/ko/built-in-nodes/StableCascade_StageC_VAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_StageC_VAEEncode" icon: "circle" mode: wide --- + StableCascade_StageC_VAEEncode 노드는 VAE 인코더를 통해 이미지를 처리하여 Stable Cascade 모델용 잠재 표현을 생성합니다. 입력 이미지를 받아 지정된 VAE 모델을 사용하여 압축한 후, stage C용 잠재 표현과 stage B용 플레이스홀더라는 두 가지 잠재 표현을 출력합니다. 압축 매개변수는 인코딩 전 이미지가 축소되는 정도를 제어합니다. ## 입력 @@ -19,8 +20,8 @@ StableCascade_StageC_VAEEncode 노드는 VAE 인코더를 통해 이미지를 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `StageB 잠재 이미지` | Stable Cascade 모델의 stage C용으로 인코딩된 잠재 표현 | LATENT | -| `stage_b` | stage B용 플레이스홀더 잠재 표현 (현재는 0을 반환) | LATENT | +| `StageC 잠재 이미지` | Stable Cascade 모델의 stage C용으로 인코딩된 잠재 표현 | LATENT | +| `StageB 잠재 이미지` | stage B용 플레이스홀더 잠재 표현 (현재는 0을 반환) | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_StageC_VAEEncode/ko.md) diff --git a/ko/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx b/ko/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx index e508fd3bc..36104113c 100644 --- a/ko/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx +++ b/ko/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_SuperResolutionControlnet" icon: "circle" mode: wide --- + StableCascade_SuperResolutionControlnet 노드는 Stable Cascade 초고해상도 처리를 위한 입력값을 준비합니다. 입력 이미지를 받아 VAE를 사용하여 인코딩함으로써 컨트롤넷 입력을 생성하고, 동시에 Stable Cascade 파이프라인의 스테이지 C와 스테이지 B를 위한 플레이스홀더 잠재 표현을 생성합니다. ## 입력 @@ -18,9 +19,9 @@ StableCascade_SuperResolutionControlnet 노드는 Stable Cascade 초고해상도 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `StageC 잠재 이미지` | 컨트롤넷 입력에 적합하도록 인코딩된 이미지 표현 | IMAGE | -| `StageB 잠재 이미지` | Stable Cascade 처리의 스테이지 C를 위한 플레이스홀더 잠재 표현 | LATENT | -| `stage_b` | Stable Cascade 처리의 스테이지 B를 위한 플레이스홀더 잠재 표현 | LATENT | +| `컨트롤넷 입력` | 컨트롤넷 입력에 적합하도록 인코딩된 이미지 표현 | IMAGE | +| `StageC 잠재 이미지` | Stable Cascade 처리의 스테이지 C를 위한 플레이스홀더 잠재 표현 | LATENT | +| `StageB 잠재 이미지` | Stable Cascade 처리의 스테이지 B를 위한 플레이스홀더 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_SuperResolutionControlnet/ko.md) diff --git a/ko/built-in-nodes/StableZero123_Conditioning.mdx b/ko/built-in-nodes/StableZero123_Conditioning.mdx index 44b5d93b2..f94a076e9 100644 --- a/ko/built-in-nodes/StableZero123_Conditioning.mdx +++ b/ko/built-in-nodes/StableZero123_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableZero123_Conditioning" icon: "circle" mode: wide --- + StableZero123_Conditioning 노드는 입력 이미지와 카메라 각도를 처리하여 3D 모델 생성을 위한 컨디셔닝 데이터와 잠재 표현을 생성합니다. CLIP 비전 모델을 사용하여 이미지 특징을 인코딩하고, 고도 및 방위각을 기반으로 한 카메라 임베딩 정보와 결합하여 양성 및 음성 컨디셔닝과 함께 다운스트림 3D 생성 작업을 위한 잠재 표현을 생성합니다. ## 입력 @@ -26,9 +27,9 @@ StableZero123_Conditioning 노드는 입력 이미지와 카메라 각도를 처 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 이미지 특징과 카메라 임베딩을 결합한 양성 컨디셔닝 데이터 | CONDITIONING | -| `잠재 데이터` | 0으로 초기화된 특징을 가진 음성 컨디셔닝 데이터 | CONDITIONING | -| `latent` | [batch_size, 4, height//8, width//8] 차원의 잠재 표현 | LATENT | +| `긍정 조건` | 이미지 특징과 카메라 임베딩을 결합한 양성 컨디셔닝 데이터 | CONDITIONING | +| `부정 조건` | 0으로 초기화된 특징을 가진 음성 컨디셔닝 데이터 | CONDITIONING | +| `잠재 데이터` | [batch_size, 4, height//8, width//8] 차원의 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning/ko.md) diff --git a/ko/built-in-nodes/StableZero123_Conditioning_Batched.mdx b/ko/built-in-nodes/StableZero123_Conditioning_Batched.mdx index 6a7d4c41e..d33dca067 100644 --- a/ko/built-in-nodes/StableZero123_Conditioning_Batched.mdx +++ b/ko/built-in-nodes/StableZero123_Conditioning_Batched.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StableZero123_Conditioning_Batched" icon: "circle" mode: wide --- -# StableZero123_Conditioning_Batched StableZero123_Conditioning_Batched 노드는 입력 이미지를 처리하여 3D 모델 생성을 위한 컨디셔닝 데이터를 생성합니다. CLIP 비전과 VAE 모델을 사용하여 이미지를 인코딩한 후, 고도(elevation) 및 방위각(azimuth) 각도를 기반으로 카메라 임베딩을 생성하여 배치 처리를 위한 양성 및 음성 컨디셔닝과 잠재 표현을 생성합니다. @@ -30,9 +29,9 @@ StableZero123_Conditioning_Batched 노드는 입력 이미지를 처리하여 3D | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 이미지 임베딩과 카메라 매개변수를 포함하는 양성 컨디셔닝 데이터 | CONDITIONING | -| `잠재 데이터` | 0으로 초기화된 임베딩을 포함하는 음성 컨디셔닝 데이터 | CONDITIONING | -| `latent` | 배치 인덱싱 정보와 함께 처리된 이미지의 잠재 표현 | LATENT | +| `긍정 조건` | 이미지 임베딩과 카메라 매개변수를 포함하는 양성 컨디셔닝 데이터 | CONDITIONING | +| `부정 조건` | 0으로 초기화된 임베딩을 포함하는 음성 컨디셔닝 데이터 | CONDITIONING | +| `잠재 데이터` | 배치 인덱싱 정보와 함께 처리된 이미지의 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning_Batched/ko.md) diff --git a/ko/built-in-nodes/Stablezero123Conditioning.mdx b/ko/built-in-nodes/Stablezero123Conditioning.mdx index 5b11eb377..d1b28f075 100644 --- a/ko/built-in-nodes/Stablezero123Conditioning.mdx +++ b/ko/built-in-nodes/Stablezero123Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Stablezero123Conditioning" icon: "circle" mode: wide --- + 이 노드는 StableZero123 모델에서 사용할 데이터를 처리 및 조건화하여, 해당 모델에 호환되고 최적화된 특정 형식으로 입력을 준비하도록 설계되었습니다. ## 입력 diff --git a/ko/built-in-nodes/Stablezero123ConditioningBatched.mdx b/ko/built-in-nodes/Stablezero123ConditioningBatched.mdx index 179e56b84..22a2a49d6 100644 --- a/ko/built-in-nodes/Stablezero123ConditioningBatched.mdx +++ b/ko/built-in-nodes/Stablezero123ConditioningBatched.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Stablezero123ConditioningBatched" icon: "circle" mode: wide --- + 이 노드는 StableZero123 모델에 특화된 배치 방식으로 컨디셔닝 정보를 처리하도록 설계되었습니다. 여러 컨디셔닝 데이터 세트를 동시에 효율적으로 처리하여 배치 처리가 중요한 워크플로우를 최적화합니다. ## 입력 diff --git a/ko/built-in-nodes/StringCompare.mdx b/ko/built-in-nodes/StringCompare.mdx index fdff7475e..e9977c346 100644 --- a/ko/built-in-nodes/StringCompare.mdx +++ b/ko/built-in-nodes/StringCompare.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringCompare" icon: "circle" mode: wide --- + StringCompare 노드는 다양한 비교 방식을 사용하여 두 개의 텍스트 문자열을 비교합니다. 한 문자열이 다른 문자열로 시작하는지, 끝나는지, 또는 두 문자열이 정확히 동일한지 확인할 수 있습니다. 비교 시 대소문자 구분 여부를 선택할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/StringConcatenate.mdx b/ko/built-in-nodes/StringConcatenate.mdx index 0a1b8d4d9..4e77c2895 100644 --- a/ko/built-in-nodes/StringConcatenate.mdx +++ b/ko/built-in-nodes/StringConcatenate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringConcatenate" icon: "circle" mode: wide --- + StringConcatenate 노드는 두 개의 텍스트 문자열을 지정된 구분자로 결합하여 하나의 문자열로 만듭니다. 두 개의 입력 문자열과 구분자 문자 또는 문자열을 받아, 두 입력 사이에 구분자를 삽입하여 연결된 단일 문자열을 출력합니다. ## 입력 diff --git a/ko/built-in-nodes/StringContains.mdx b/ko/built-in-nodes/StringContains.mdx index a3b39493e..b8868bf48 100644 --- a/ko/built-in-nodes/StringContains.mdx +++ b/ko/built-in-nodes/StringContains.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringContains" icon: "circle" mode: wide --- + StringContains 노드는 주어진 문자열에 특정 하위 문자열이 포함되어 있는지 확인합니다. 대소문자를 구분하거나 구분하지 않고 검색을 수행할 수 있으며, 하위 문자열이 주 문자열 내에서 발견되었는지 여부를 나타내는 부울 결과를 반환합니다. ## 입력 @@ -19,7 +20,7 @@ StringContains 노드는 주어진 문자열에 특정 하위 문자열이 포 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `contains` | 하위 문자열이 문자열에서 발견되면 true를, 그렇지 않으면 false를 반환합니다 | BOOLEAN | +| `포함 여부` | 하위 문자열이 문자열에서 발견되면 true를, 그렇지 않으면 false를 반환합니다 | BOOLEAN | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringContains/ko.md) diff --git a/ko/built-in-nodes/StringFormat.mdx b/ko/built-in-nodes/StringFormat.mdx index f43b9c82d..70d0ca3f8 100644 --- a/ko/built-in-nodes/StringFormat.mdx +++ b/ko/built-in-nodes/StringFormat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringFormat" icon: "circle" mode: wide --- + ## 개요 이 노드는 Python의 문자열 형식화 메서드를 사용하여 텍스트를 포맷합니다. 템플릿처럼 작동하여 자리 표시자가 있는 텍스트 패턴을 정의한 다음, 해당 자리 표시자를 채울 값을 제공합니다. 모든 Python 형식 옵션과 기능을 지원합니다. diff --git a/ko/built-in-nodes/StringLength.mdx b/ko/built-in-nodes/StringLength.mdx index 6ab6b3337..83aef5483 100644 --- a/ko/built-in-nodes/StringLength.mdx +++ b/ko/built-in-nodes/StringLength.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringLength" icon: "circle" mode: wide --- + StringLength 노드는 텍스트 문자열의 문자 수를 계산합니다. 모든 텍스트 입력을 받아 공백과 구두점을 포함한 총 문자 수를 반환합니다. 이는 텍스트 길이를 측정하거나 문자열 크기 요구 사항을 검증하는 데 유용합니다. ## 입력 @@ -17,7 +18,7 @@ StringLength 노드는 텍스트 문자열의 문자 수를 계산합니다. 모 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `length` | 입력 문자열의 총 문자 수로, 공백과 특수 문자를 포함합니다. | INT | +| `길이` | 입력 문자열의 총 문자 수로, 공백과 특수 문자를 포함합니다. | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringLength/ko.md) diff --git a/ko/built-in-nodes/StringReplace.mdx b/ko/built-in-nodes/StringReplace.mdx index 983e4c8af..1a6c44291 100644 --- a/ko/built-in-nodes/StringReplace.mdx +++ b/ko/built-in-nodes/StringReplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringReplace" icon: "circle" mode: wide --- + StringReplace 노드는 입력 문자열에 대해 텍스트 치환 작업을 수행합니다. 입력 텍스트 내에서 지정된 하위 문자열을 검색하고 모든 항목을 다른 하위 문자열로 교체합니다. 이 노드는 모든 치환이 적용된 수정된 문자열을 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/StringSubstring.mdx b/ko/built-in-nodes/StringSubstring.mdx index 136d4c48d..09c1dc9a2 100644 --- a/ko/built-in-nodes/StringSubstring.mdx +++ b/ko/built-in-nodes/StringSubstring.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringSubstring" icon: "circle" mode: wide --- + StringSubstring 노드는 더 큰 문자열에서 텍스트의 일부를 추출합니다. 추출할 부분을 정의하기 위해 시작 위치와 끝 위치를 사용하며, 해당 두 위치 사이의 텍스트를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/StringTrim.mdx b/ko/built-in-nodes/StringTrim.mdx index dbdccb9f3..95a18ade1 100644 --- a/ko/built-in-nodes/StringTrim.mdx +++ b/ko/built-in-nodes/StringTrim.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringTrim" icon: "circle" mode: wide --- + StringTrim 노드는 텍스트 문자열의 시작, 끝 또는 양쪽에서 공백 문자를 제거합니다. 문자열의 왼쪽, 오른쪽 또는 양쪽에서 트리밍 방식을 선택할 수 있습니다. 불필요한 공백, 탭 또는 줄 바꿈 문자를 제거하여 텍스트 입력을 정리하는 데 유용합니다. ## 입력 diff --git a/ko/built-in-nodes/StripWhitespace.mdx b/ko/built-in-nodes/StripWhitespace.mdx index 0e1b4f0cc..88ead3d15 100644 --- a/ko/built-in-nodes/StripWhitespace.mdx +++ b/ko/built-in-nodes/StripWhitespace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StripWhitespace" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StripWhitespace/en.md) 이 노드는 텍스트 문자열의 시작과 끝에서 불필요한 공백, 탭 또는 줄바꿈을 제거합니다. 텍스트 입력을 받아 앞뒤 공백이 제거된 정리된 버전을 반환합니다. @@ -19,7 +20,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `text` | 모든 앞뒤 공백 문자가 제거된 처리된 텍스트입니다. | STRING | +| `texts` | 모든 앞뒤 공백 문자가 제거된 처리된 텍스트입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StripWhitespace/ko.md) diff --git a/ko/built-in-nodes/StyleModelApply.mdx b/ko/built-in-nodes/StyleModelApply.mdx index 1fddbff10..2a60b1397 100644 --- a/ko/built-in-nodes/StyleModelApply.mdx +++ b/ko/built-in-nodes/StyleModelApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StyleModelApply" icon: "circle" mode: wide --- + 이 노드는 스타일 모델을 주어진 컨디셔닝에 적용하여, CLIP 비전 모델의 출력을 기반으로 스타일을 강화하거나 변경합니다. 스타일 모델의 컨디셔닝을 기존 컨디셔닝에 통합하여, 생성 과정에서 스타일이 자연스럽게 혼합되도록 합니다. ## 입력 diff --git a/ko/built-in-nodes/StyleModelLoader.mdx b/ko/built-in-nodes/StyleModelLoader.mdx index 5d3b4932e..e62803e4b 100644 --- a/ko/built-in-nodes/StyleModelLoader.mdx +++ b/ko/built-in-nodes/StyleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StyleModelLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/style_models` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 설정된 추가 경로의 모델도 함께 읽어옵니다. 경우에 따라 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수도 있습니다. StyleModelLoader 노드는 지정된 경로에서 스타일 모델을 로드하도록 설계되었습니다. 이 노드는 특정 예술적 스타일을 이미지에 적용하는 데 사용할 수 있는 스타일 모델을 검색하고 초기화하는 데 중점을 두며, 로드된 스타일 모델을 기반으로 시각적 출력을 사용자 지정할 수 있도록 합니다. diff --git a/ko/built-in-nodes/SvdImg2vidConditioning.mdx b/ko/built-in-nodes/SvdImg2vidConditioning.mdx index 97d7331d4..449cea259 100644 --- a/ko/built-in-nodes/SvdImg2vidConditioning.mdx +++ b/ko/built-in-nodes/SvdImg2vidConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SvdImg2vidConditioning" icon: "circle" mode: wide --- + 이 노드는 비디오 생성 작업을 위한 컨디셔닝 데이터를 생성하도록 설계되었으며, 특히 SVD_img2vid 모델과 함께 사용하기 위해 맞춤화되었습니다. 초기 이미지, 비디오 매개변수 및 VAE 모델을 포함한 다양한 입력을 받아 비디오 프레임 생성을 안내하는 데 사용할 수 있는 컨디셔닝 데이터를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/T5TokenizerOptions.mdx b/ko/built-in-nodes/T5TokenizerOptions.mdx index 8a589b008..44880ec5a 100644 --- a/ko/built-in-nodes/T5TokenizerOptions.mdx +++ b/ko/built-in-nodes/T5TokenizerOptions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "T5TokenizerOptions" icon: "circle" mode: wide --- + T5TokenizerOptions 노드를 사용하면 다양한 T5 모델 유형에 대한 토크나이저 설정을 구성할 수 있습니다. 이 노드는 t5xxl, pile_t5xl, t5base, mt5xl, umt5xxl 등 여러 T5 모델 변형에 대한 최소 패딩 및 최소 길이 매개변수를 설정합니다. CLIP 입력을 받아 지정된 토크나이저 옵션이 적용된 수정된 CLIP을 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/TCFG.mdx b/ko/built-in-nodes/TCFG.mdx index 3def6de8a..ab82d6be5 100644 --- a/ko/built-in-nodes/TCFG.mdx +++ b/ko/built-in-nodes/TCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TCFG" icon: "circle" mode: wide --- + TCFG(접선 감쇠 CFG)는 샘플링 과정에서 조건부(긍정) 예측과 더 잘 일치하도록 무조건부(부정) 예측을 정제합니다. 이 기술은 연구 논문 2503.18137을 기반으로 무조건부 안내에 접선 감쇠를 적용하여 출력 품질을 향상시킵니다. 이 노드는 분류기 자유 안내(classifier-free guidance) 중 무조건부 예측이 처리되는 방식을 조정하여 모델의 샘플링 동작을 수정합니다. ## 입력 @@ -17,7 +18,7 @@ TCFG(접선 감쇠 CFG)는 샘플링 과정에서 조건부(긍정) 예측과 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `patched_model` | 접선 감쇠 CFG가 적용된 수정된 모델 | MODEL | +| `패치된 모델` | 접선 감쇠 CFG가 적용된 수정된 모델 | MODEL | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TCFG/ko.md) diff --git a/ko/built-in-nodes/TemporalScoreRescaling.mdx b/ko/built-in-nodes/TemporalScoreRescaling.mdx index 966ba4db3..f58f66253 100644 --- a/ko/built-in-nodes/TemporalScoreRescaling.mdx +++ b/ko/built-in-nodes/TemporalScoreRescaling.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TemporalScoreRescaling" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TemporalScoreRescaling/en.md) 이 노드는 확산 모델에 시간적 점수 재조정(TSR)을 적용합니다. 노이즈 제거 과정에서 예측된 노이즈 또는 점수를 재조정하여 모델의 샘플링 동작을 수정하며, 이를 통해 생성된 출력의 다양성을 조절할 수 있습니다. 이는 사후 CFG(분류기-비지도 안내) 함수로 구현됩니다. @@ -21,7 +22,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `patched_model` | 샘플링 과정에 시간적 점수 재조정 함수가 적용되어 패치된 입력 모델입니다. | MODEL | +| `패치된 모델` | 샘플링 과정에 시간적 점수 재조정 함수가 적용되어 패치된 입력 모델입니다. | MODEL | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TemporalScoreRescaling/ko.md) diff --git a/ko/built-in-nodes/Tencent3DPartNode.mdx b/ko/built-in-nodes/Tencent3DPartNode.mdx index dbeae9718..2a874d4fb 100644 --- a/ko/built-in-nodes/Tencent3DPartNode.mdx +++ b/ko/built-in-nodes/Tencent3DPartNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Tencent3DPartNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DPartNode/en.md) 이 노드는 Tencent Hunyuan3D API를 사용하여 3D 모델을 자동으로 분석하고, 구조에 따라 구성 요소를 생성하거나 식별합니다. 모델을 처리한 후 새로운 FBX 파일을 반환합니다. diff --git a/ko/built-in-nodes/Tencent3DTextureEditNode.mdx b/ko/built-in-nodes/Tencent3DTextureEditNode.mdx index e404f87c4..a047eea98 100644 --- a/ko/built-in-nodes/Tencent3DTextureEditNode.mdx +++ b/ko/built-in-nodes/Tencent3DTextureEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Tencent3DTextureEditNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하시거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DTextureEditNode/en.md) 이 노드는 Tencent Hunyuan3D API를 사용하여 3D 모델의 텍스처를 편집합니다. 3D 모델과 원하는 변경 사항에 대한 텍스트 설명을 제공하면, 노드가 사용자의 프롬프트에 따라 텍스처가 다시 그려진 새로운 버전의 모델을 반환합니다. @@ -23,8 +24,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `OBJ` | GLB 형식으로 처리된 3D 모델입니다. | FILE3D | -| `texture_image` | OBJ 형식으로 처리된 3D 모델입니다. | FILE3D | +| `GLB` | GLB 형식으로 처리된 3D 모델입니다. | FILE3D | +| `OBJ` | OBJ 형식으로 처리된 3D 모델입니다. | FILE3D | | `texture_image` | 3D 모델에 대해 새로 생성된 텍스처 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DTextureEditNode/ko.md) diff --git a/ko/built-in-nodes/TencentImageToModelNode.mdx b/ko/built-in-nodes/TencentImageToModelNode.mdx index c004ae5d5..39bb6adae 100644 --- a/ko/built-in-nodes/TencentImageToModelNode.mdx +++ b/ko/built-in-nodes/TencentImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentImageToModelNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentImageToModelNode/en.md) 이 노드는 Tencent의 Hunyuan3D Pro API를 사용하여 하나 이상의 입력 이미지로부터 3D 모델을 생성합니다. 이미지를 처리하여 API로 전송한 후, 생성된 3D 모델 파일을 GLB 및 OBJ 형식과 함께 선택적 텍스처 맵으로 반환합니다. @@ -30,12 +31,12 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `GLB` | 이전 버전과의 호환성을 위한 레거시 출력입니다. | STRING | -| `OBJ` | GLB(Binary GL Transmission Format) 파일 형식으로 생성된 3D 모델입니다. | FILE3DGLB | -| `texture_image` | OBJ(Wavefront) 파일 형식으로 생성된 3D 모델입니다. | FILE3DOBJ | -| `optional_metallic` | 생성된 3D 모델의 텍스처 이미지입니다. | IMAGE | -| `optional_normal` | PBR 재질의 메탈릭 맵입니다. 사용할 수 없는 경우 검은색 이미지를 반환합니다. | IMAGE | -| `optional_roughness` | PBR 재질의 노멀 맵입니다. 사용할 수 없는 경우 검은색 이미지를 반환합니다. | IMAGE | +| `모델 파일` | 이전 버전과의 호환성을 위한 레거시 출력입니다. | STRING | +| `GLB` | GLB(Binary GL Transmission Format) 파일 형식으로 생성된 3D 모델입니다. | FILE3DGLB | +| `OBJ` | OBJ(Wavefront) 파일 형식으로 생성된 3D 모델입니다. | FILE3DOBJ | +| `texture_image` | 생성된 3D 모델의 텍스처 이미지입니다. | IMAGE | +| `optional_metallic` | PBR 재질의 메탈릭 맵입니다. 사용할 수 없는 경우 검은색 이미지를 반환합니다. | IMAGE | +| `optional_normal` | PBR 재질의 노멀 맵입니다. 사용할 수 없는 경우 검은색 이미지를 반환합니다. | IMAGE | | `optional_roughness` | PBR 재질의 러프니스 맵입니다. 사용할 수 없는 경우 검은색 이미지를 반환합니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentImageToModelNode/ko.md) diff --git a/ko/built-in-nodes/TencentModelTo3DUVNode.mdx b/ko/built-in-nodes/TencentModelTo3DUVNode.mdx index 52992d31a..8baa11b22 100644 --- a/ko/built-in-nodes/TencentModelTo3DUVNode.mdx +++ b/ko/built-in-nodes/TencentModelTo3DUVNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentModelTo3DUVNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentModelTo3DUVNode/en.md) 이 노드는 Tencent Hunyuan3D API를 사용하여 3D 모델에 UV 전개를 수행합니다. 3D 모델 파일을 입력으로 받아 API로 전송하여 처리한 후, 처리된 모델을 OBJ 및 FBX 형식과 함께 생성된 UV 텍스처 이미지를 반환합니다. 입력 모델의 면 수는 30,000개 미만이어야 합니다. @@ -20,8 +21,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `FBX` | OBJ 형식으로 처리된 3D 모델 파일입니다. | FILE3D | -| `uv_image` | FBX 형식으로 처리된 3D 모델 파일입니다. | FILE3D | +| `OBJ` | OBJ 형식으로 처리된 3D 모델 파일입니다. | FILE3D | +| `FBX` | FBX 형식으로 처리된 3D 모델 파일입니다. | FILE3D | | `uv_image` | 생성된 UV 텍스처 이미지입니다. | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentModelTo3DUVNode/ko.md) diff --git a/ko/built-in-nodes/TencentSmartTopologyNode.mdx b/ko/built-in-nodes/TencentSmartTopologyNode.mdx index 8e7dd7dca..b639d4210 100644 --- a/ko/built-in-nodes/TencentSmartTopologyNode.mdx +++ b/ko/built-in-nodes/TencentSmartTopologyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentSmartTopologyNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentSmartTopologyNode/en.md) 이 노드는 3D 모델에 대해 스마트 리토폴로지를 수행하여 최적화된 폴리곤 수로 새롭고 깔끔한 메시를 자동으로 생성합니다. Tencent Hunyuan 3D API에 연결하여 모델을 처리하며, 최대 200MB까지의 GLB 및 OBJ 파일 형식을 지원합니다. 이 노드는 처리된 모델을 OBJ 파일로 반환합니다. diff --git a/ko/built-in-nodes/TencentTextToModelNode.mdx b/ko/built-in-nodes/TencentTextToModelNode.mdx index 2d4e68bc2..61e67ac94 100644 --- a/ko/built-in-nodes/TencentTextToModelNode.mdx +++ b/ko/built-in-nodes/TencentTextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentTextToModelNode" icon: "circle" mode: wide --- + 이 문서는 AI로 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentTextToModelNode/en.md) 이 노드는 Tencent의 Hunyuan3D Pro API를 사용하여 텍스트 설명으로부터 3D 모델을 생성합니다. 생성 작업 요청을 전송하고, 결과를 폴링하며, 최종 모델 파일을 GLB 및 OBJ 형식으로 다운로드합니다. @@ -27,9 +28,9 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `GLB` | 이전 버전과의 호환성을 위한 레거시 출력입니다. | STRING | -| `OBJ` | GLB 파일 형식으로 생성된 3D 모델입니다. | FILE3DGLB | -| `texture_image` | OBJ 파일 형식으로 생성된 3D 모델입니다. | FILE3DOBJ | +| `모델 파일` | 이전 버전과의 호환성을 위한 레거시 출력입니다. | STRING | +| `GLB` | GLB 파일 형식으로 생성된 3D 모델입니다. | FILE3DGLB | +| `OBJ` | OBJ 파일 형식으로 생성된 3D 모델입니다. | FILE3DOBJ | | `texture_image` | 생성된 OBJ 파일에서 추출한 텍스처 이미지입니다(사용 가능한 경우). | IMAGE | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentTextToModelNode/ko.md) diff --git a/ko/built-in-nodes/TerminalLog.mdx b/ko/built-in-nodes/TerminalLog.mdx index 74603ab56..e1ce2f5fa 100644 --- a/ko/built-in-nodes/TerminalLog.mdx +++ b/ko/built-in-nodes/TerminalLog.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TerminalLog" icon: "circle" mode: wide --- + **터미널 로그 (관리자)** 노드는 주로 ComfyUI 인터페이스 내에서 터미널에 표시되는 ComfyUI의 실행 정보를 표시하는 데 사용됩니다. 사용하려면 `mode`를 **로깅** 모드로 설정해야 합니다. 이렇게 하면 이미지 생성 작업 중에 해당 로그 정보를 기록할 수 있습니다. `mode`가 **중지** 모드로 설정되면 로그 정보를 기록하지 않습니다. 원격 연결이나 근거리 통신망 연결을 통해 ComfyUI에 접속하여 사용할 때, 터미널 로그 (관리자) 노드는 특히 유용합니다. 이 노드를 사용하면 ComfyUI 인터페이스 내에서 CMD의 오류 메시지를 직접 확인할 수 있어 ComfyUI 작동의 현재 상태를 더 쉽게 파악할 수 있습니다. diff --git a/ko/built-in-nodes/TextEncodeAceStepAudio.mdx b/ko/built-in-nodes/TextEncodeAceStepAudio.mdx index bd838b889..668bd9f63 100644 --- a/ko/built-in-nodes/TextEncodeAceStepAudio.mdx +++ b/ko/built-in-nodes/TextEncodeAceStepAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeAceStepAudio" icon: "circle" mode: wide --- + TextEncodeAceStepAudio 노드는 태그와 가사를 토큰으로 결합한 후 조정 가능한 가사 강도로 인코딩하여 오디오 컨디셔닝을 위한 텍스트 입력을 처리합니다. 이 노드는 CLIP 모델과 텍스트 설명 및 가사를 입력받아 함께 토큰화하고, 오디오 생성 작업에 적합한 컨디셔닝 데이터를 생성합니다. 최종 출력에 대한 가사의 영향을 제어하는 강도 매개변수를 통해 가사의 영향력을 미세 조정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/TextEncodeAceStepAudio1.5.mdx b/ko/built-in-nodes/TextEncodeAceStepAudio1.5.mdx index d46157126..89e9f497f 100644 --- a/ko/built-in-nodes/TextEncodeAceStepAudio1.5.mdx +++ b/ko/built-in-nodes/TextEncodeAceStepAudio1.5.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeAceStepAudio1.5" icon: "circle" mode: wide --- + TextEncodeAceStepAudio1.5 노드는 AceStepAudio 1.5 모델과 함께 사용하기 위해 텍스트 및 오디오 관련 메타데이터를 준비합니다. 설명 태그, 가사 및 음악 매개변수를 입력받은 후 CLIP 모델을 사용하여 오디오 생성에 적합한 컨디셔닝 형식으로 변환합니다. ## 입력 diff --git a/ko/built-in-nodes/TextEncodeBooguEdit.mdx b/ko/built-in-nodes/TextEncodeBooguEdit.mdx new file mode 100644 index 000000000..7fe7e3111 --- /dev/null +++ b/ko/built-in-nodes/TextEncodeBooguEdit.mdx @@ -0,0 +1,31 @@ +--- +title: "TextEncodeBooguEdit - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the TextEncodeBooguEdit node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "TextEncodeBooguEdit" +icon: "circle" +mode: wide +--- + +이 노드는 Boogu를 사용한 이미지 편집을 위한 컨디셔닝을 준비합니다. 참조 이미지를 처리하여 긍정 및 부정 컨디셔닝 출력을 모두 생성합니다. 참조 이미지는 두 번 사용됩니다. 이미지의 비전 토큰은 편집 명령을 증폭하기 위해 긍정 컨디셔닝에만 추가되는 반면, VAE 참조 잠재값은 긍정 및 부정 컨디셔닝 모두에 추가되어 CFG 하에서 상쇄되며 원본 이미지의 정체성을 보존합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `clip` | 텍스트 인코딩에 사용되는 CLIP 모델 | CLIP | 예 | | +| `프롬프트` | 원하는 편집을 설명하는 텍스트 프롬프트 | STRING | 예 | | +| `네거티브 프롬프트` | 편집에서 피해야 할 내용을 설명하는 텍스트 프롬프트 | STRING | 아니요 | | +| `vae` | 참조 이미지를 잠재 공간으로 인코딩하는 데 사용되는 VAE 모델 | VAE | 아니요 | | +| `이미지` | 편집할 참조 이미지입니다. Boogu는 샘플당 하나의 참조 이미지에 초점을 맞춥니다. 더 많은 이미지도 허용됩니다. | IMAGE | 아니요 | 최대 16개 이미지 | + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `positive` | 비전 토큰이 포함된 텍스트 프롬프트와 참조 잠재값을 모두 포함하는 컨디셔닝 | CONDITIONING | +| `negative` | 부정 텍스트 프롬프트와 참조 잠재값을 포함하는 컨디셔닝 | CONDITIONING | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeBooguEdit/ko.md) + +--- +**Source fingerprint (SHA-256):** `170979acf5b2e9f25f96231a4b23a4376cfddcd4bda2fdd6e03528417e6931b0` diff --git a/ko/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx b/ko/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx index 0e0864c04..38bed6385 100644 --- a/ko/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx +++ b/ko/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeHunyuanVideo_ImageToVideo" icon: "circle" mode: wide --- + TextEncodeHunyuanVideo_ImageToVideo 노드는 텍스트 프롬프트와 이미지 임베딩을 결합하여 비디오 생성을 위한 컨디셔닝 데이터를 생성합니다. CLIP 모델을 사용하여 텍스트 입력과 CLIP 비전 출력의 시각적 정보를 모두 처리한 후, 지정된 이미지 인터리브 설정에 따라 이 두 소스를 혼합한 토큰을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/TextEncodeQwenImageEdit.mdx b/ko/built-in-nodes/TextEncodeQwenImageEdit.mdx index e39f6419c..270c6c758 100644 --- a/ko/built-in-nodes/TextEncodeQwenImageEdit.mdx +++ b/ko/built-in-nodes/TextEncodeQwenImageEdit.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TextEncodeQwenImageEdit" icon: "circle" mode: wide --- -# TextEncodeQwenImageEdit 노드 TextEncodeQwenImageEdit 노드는 텍스트 프롬프트와 선택적 이미지를 처리하여 이미지 생성 또는 편집을 위한 컨디셔닝 데이터를 생성합니다. CLIP 모델을 사용하여 입력을 토큰화하며, VAE를 사용하여 참조 이미지를 인코딩하여 참조 잠재 변수를 생성할 수 있습니다. 이미지가 제공되면 일관된 처리 차원을 유지하기 위해 자동으로 크기가 조정됩니다. diff --git a/ko/built-in-nodes/TextEncodeQwenImageEditPlus.mdx b/ko/built-in-nodes/TextEncodeQwenImageEditPlus.mdx index b98dacf6c..881676f62 100644 --- a/ko/built-in-nodes/TextEncodeQwenImageEditPlus.mdx +++ b/ko/built-in-nodes/TextEncodeQwenImageEditPlus.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TextEncodeQwenImageEditPlus" icon: "circle" mode: wide --- -# TextEncodeQwenImageEditPlus 노드 TextEncodeQwenImageEditPlus 노드는 텍스트 프롬프트와 선택적 이미지를 처리하여 이미지 생성 또는 편집 작업을 위한 컨디셔닝 데이터를 생성합니다. 이 노드는 특수 템플릿을 사용하여 입력 이미지를 분석하고 텍스트 명령이 이미지를 어떻게 수정해야 하는지 이해한 후, 이 정보를 후속 생성 단계에서 사용할 수 있도록 인코딩합니다. 최대 3개의 입력 이미지를 처리할 수 있으며, VAE가 제공될 경우 선택적으로 참조 잠재값을 생성합니다. diff --git a/ko/built-in-nodes/TextEncodeZImageOmni.mdx b/ko/built-in-nodes/TextEncodeZImageOmni.mdx index 83d4d0489..d570f2f9a 100644 --- a/ko/built-in-nodes/TextEncodeZImageOmni.mdx +++ b/ko/built-in-nodes/TextEncodeZImageOmni.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TextEncodeZImageOmni" icon: "circle" mode: wide --- -# TextEncodeZImageOmni TextEncodeZImageOmni 노드는 텍스트 프롬프트와 선택적 참조 이미지를 이미지 생성 모델에 적합한 컨디셔닝 형식으로 인코딩하는 고급 컨디셔닝 노드입니다. 최대 3개의 이미지를 처리할 수 있으며, 선택적으로 비전 인코더 및/또는 VAE를 사용하여 이미지를 인코딩하여 참조 잠재 표현을 생성하고, 특정 템플릿 구조를 사용하여 이러한 시각적 참조를 텍스트 프롬프트와 통합합니다. diff --git a/ko/built-in-nodes/TextGenerate.mdx b/ko/built-in-nodes/TextGenerate.mdx index 5df85661f..7fbef68fb 100644 --- a/ko/built-in-nodes/TextGenerate.mdx +++ b/ko/built-in-nodes/TextGenerate.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TextGenerate" icon: "circle" mode: wide --- -# TextGenerate 노드 TextGenerate 노드는 CLIP 모델을 사용하여 사용자의 프롬프트를 기반으로 텍스트를 생성합니다. 선택적으로 이미지, 비디오 또는 오디오를 추가 컨텍스트로 사용하여 텍스트 생성을 안내할 수 있습니다. 출력 길이를 제어하고, 지원되는 모델의 경우 사고 모드를 활성화하며, 다양한 설정으로 무작위 샘플링을 사용할지 또는 샘플링 없이 텍스트를 생성할지 선택할 수 있습니다. @@ -36,7 +35,7 @@ TextGenerate 노드는 CLIP 모델을 사용하여 사용자의 프롬프트를 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `generated_text` | 입력 프롬프트와 선택적 이미지, 비디오 또는 오디오를 기반으로 모델이 생성한 텍스트입니다. | STRING | +| `생성된 텍스트` | 입력 프롬프트와 선택적 이미지, 비디오 또는 오디오를 기반으로 모델이 생성한 텍스트입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerate/ko.md) diff --git a/ko/built-in-nodes/TextGenerateLTX2Prompt.mdx b/ko/built-in-nodes/TextGenerateLTX2Prompt.mdx index 87d4d33e6..3e95a3eeb 100644 --- a/ko/built-in-nodes/TextGenerateLTX2Prompt.mdx +++ b/ko/built-in-nodes/TextGenerateLTX2Prompt.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TextGenerateLTX2Prompt" icon: "circle" mode: wide --- -# TextGenerateLTX2Prompt 노드 TextGenerateLTX2Prompt 노드는 텍스트 생성 노드의 특수 버전입니다. 사용자의 텍스트 프롬프트를 받아 특정 시스템 명령어로 자동 서식을 지정한 후 언어 모델로 전송하여 개선 또는 완성합니다. 이 노드는 텍스트 전용 모드와 이미지 참조 모드, 두 가지 방식으로 작동할 수 있으며, 각 경우에 서로 다른 시스템 프롬프트를 사용합니다. @@ -29,7 +28,7 @@ TextGenerateLTX2Prompt 노드는 텍스트 생성 노드의 특수 버전입니 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `output` | 언어 모델이 생성한 개선 또는 완성된 텍스트 문자열입니다. | STRING | +| `생성된 텍스트` | 언어 모델이 생성한 개선 또는 완성된 텍스트 문자열입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerateLTX2Prompt/ko.md) diff --git a/ko/built-in-nodes/TextToLowercase.mdx b/ko/built-in-nodes/TextToLowercase.mdx index 3b8fffb55..cd20d2c8e 100644 --- a/ko/built-in-nodes/TextToLowercase.mdx +++ b/ko/built-in-nodes/TextToLowercase.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextToLowercase" icon: "circle" mode: wide --- + Text to Lowercase 노드는 텍스트 문자열을 입력받아 모든 문자를 소문자로 변환합니다. 텍스트 대소문자를 표준화하는 간단한 유틸리티입니다. ## 입력 @@ -17,7 +18,7 @@ Text to Lowercase 노드는 텍스트 문자열을 입력받아 모든 문자를 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `text` | 모든 문자가 소문자로 변환된 입력 텍스트입니다. | STRING | +| `texts` | 모든 문자가 소문자로 변환된 입력 텍스트입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToLowercase/ko.md) diff --git a/ko/built-in-nodes/TextToUppercase.mdx b/ko/built-in-nodes/TextToUppercase.mdx index 119b6b00f..941af4d63 100644 --- a/ko/built-in-nodes/TextToUppercase.mdx +++ b/ko/built-in-nodes/TextToUppercase.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextToUppercase" icon: "circle" mode: wide --- + Text to Uppercase 노드는 텍스트 입력을 받아 모든 문자를 대문자로 변환합니다. 제공된 문자열의 대소문자를 변경하는 간단한 텍스트 처리 유틸리티입니다. ## 입력 @@ -17,7 +18,7 @@ Text to Uppercase 노드는 텍스트 입력을 받아 모든 문자를 대문 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `text` | 모든 문자가 대문자로 변환된 결과 텍스트입니다. | STRING | +| `texts` | 모든 문자가 대문자로 변환된 결과 텍스트입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToUppercase/ko.md) diff --git a/ko/built-in-nodes/ThresholdMask.mdx b/ko/built-in-nodes/ThresholdMask.mdx index adb0f8883..e1a7f6464 100644 --- a/ko/built-in-nodes/ThresholdMask.mdx +++ b/ko/built-in-nodes/ThresholdMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ThresholdMask" icon: "circle" mode: wide --- + ThresholdMask 노드는 임계값을 적용하여 마스크를 이진 마스크로 변환합니다. 입력 마스크의 각 픽셀을 지정된 임계값과 비교하여, 임계값을 초과하는 픽셀은 1(흰색)이 되고 임계값 이하인 픽셀은 0(검은색)이 되는 새 마스크를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/TomePatchModel.mdx b/ko/built-in-nodes/TomePatchModel.mdx index 8d09554bc..bb065a375 100644 --- a/ko/built-in-nodes/TomePatchModel.mdx +++ b/ko/built-in-nodes/TomePatchModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TomePatchModel" icon: "circle" mode: wide --- + TomePatchModel 노드는 확산 모델에 토큰 병합(ToMe)을 적용하여 추론 중 계산 요구 사항을 줄입니다. 이는 어텐션 메커니즘에서 유사한 토큰을 선택적으로 병합하여 이미지 품질을 유지하면서 모델이 더 적은 토큰을 처리할 수 있도록 합니다. 이 기술은 품질 저하 없이 생성 속도를 높이는 데 도움을 줍니다. ## 입력 diff --git a/ko/built-in-nodes/TopazImageEnhance.mdx b/ko/built-in-nodes/TopazImageEnhance.mdx index 66f5cdbad..c66c8487d 100644 --- a/ko/built-in-nodes/TopazImageEnhance.mdx +++ b/ko/built-in-nodes/TopazImageEnhance.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TopazImageEnhance" icon: "circle" mode: wide --- -# Topaz Image Enhance 노드 Topaz Image Enhance 노드는 업계 표준의 업스케일링 및 이미지 향상 기능을 제공합니다. 클라우드 기반 AI 모델을 사용하여 단일 입력 이미지를 처리하여 품질, 세부 묘사 및 해상도를 개선합니다. 이 노드는 창의적 가이드, 피사체 초점, 얼굴 보존 옵션을 포함하여 향상 과정을 세밀하게 제어할 수 있습니다. diff --git a/ko/built-in-nodes/TopazVideoEnhance.mdx b/ko/built-in-nodes/TopazVideoEnhance.mdx index 1bb0303f0..c42b495c0 100644 --- a/ko/built-in-nodes/TopazVideoEnhance.mdx +++ b/ko/built-in-nodes/TopazVideoEnhance.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TopazVideoEnhance" icon: "circle" mode: wide --- -# Topaz Video Enhance 노드 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazVideoEnhance/en.md) diff --git a/ko/built-in-nodes/TopazVideoEnhanceV2.mdx b/ko/built-in-nodes/TopazVideoEnhanceV2.mdx index 81f595a48..d809b982e 100644 --- a/ko/built-in-nodes/TopazVideoEnhanceV2.mdx +++ b/ko/built-in-nodes/TopazVideoEnhanceV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TopazVideoEnhanceV2" icon: "circle" mode: wide --- -# Topaz Video Enhance V2 **Topaz Video Enhance V2** 노드는 Topaz Labs의 AI 모델을 사용하여 비디오를 업스케일링하고 향상시킬 수 있습니다. 해상도를 높이고, 보간을 통해 프레임 속도를 조정하며, 창의적이거나 사실적인 향상 효과를 적용하여 비디오 영상에 새로운 생명을 불어넣을 수 있습니다. diff --git a/ko/built-in-nodes/TorchCompileModel.mdx b/ko/built-in-nodes/TorchCompileModel.mdx index 54348ccde..126f597db 100644 --- a/ko/built-in-nodes/TorchCompileModel.mdx +++ b/ko/built-in-nodes/TorchCompileModel.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TorchCompileModel" icon: "circle" mode: wide --- -# TorchCompileModel 노드 TorchCompileModel 노드는 PyTorch 컴파일을 모델에 적용하여 성능을 최적화합니다. 입력 모델의 복사본을 생성하고 지정된 백엔드를 사용하여 PyTorch의 컴파일 기능으로 감쌉니다. 이를 통해 추론 중 모델의 실행 속도를 향상시킬 수 있습니다. diff --git a/ko/built-in-nodes/TrainLoraNode.mdx b/ko/built-in-nodes/TrainLoraNode.mdx index 05f33d982..c4b72296c 100644 --- a/ko/built-in-nodes/TrainLoraNode.mdx +++ b/ko/built-in-nodes/TrainLoraNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TrainLoraNode" icon: "circle" mode: wide --- -# TrainLoRA 노드 TrainLoRA 노드는 제공된 잠재 표현(latents)과 컨디셔닝 데이터를 사용하여 확산 모델에 대한 LoRA(저차원 적응) 모델을 생성하고 학습합니다. 사용자 정의 학습 매개변수, 최적화기 및 손실 함수를 사용하여 모델을 미세 조정할 수 있습니다. 이 노드는 학습된 LoRA 가중치, 손실 이력 맵 및 완료된 총 학습 단계 수를 출력합니다. @@ -47,9 +46,9 @@ TrainLoRA 노드는 제공된 잠재 표현(latents)과 컨디셔닝 데이터 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `손실 맵` | 저장하거나 다른 모델에 적용할 수 있는 학습된 LoRA 가중치입니다. | LORA_MODEL | -| `스텝` | 시간에 따른 학습 손실 값을 포함하는 사전입니다. | LOSS_MAP | -| `단계 수` | 완료된 총 학습 단계 수입니다(기존 LoRA의 이전 단계 포함). | INT | +| `lora` | 저장하거나 다른 모델에 적용할 수 있는 학습된 LoRA 가중치입니다. | LORA_MODEL | +| `손실 맵` | 시간에 따른 학습 손실 값을 포함하는 사전입니다. | LOSS_MAP | +| `스텝` | 완료된 총 학습 단계 수입니다(기존 LoRA의 이전 단계 포함). | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrainLoraNode/ko.md) diff --git a/ko/built-in-nodes/TransformSplat.mdx b/ko/built-in-nodes/TransformSplat.mdx index 365f1e5b5..c9187fe13 100644 --- a/ko/built-in-nodes/TransformSplat.mdx +++ b/ko/built-in-nodes/TransformSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TransformSplat" icon: "circle" mode: wide --- -# Transform Splat Transform Splat 노드는 가우시안 스플랫에 이동, 회전 및 크기 조정 변환을 적용합니다. 전체 스플랫을 하나의 객체로 이동, 회전 및 크기 조정하며, 균일하지 않은 크기 조정이 적용될 경우 정확한 결과를 위해 각 개별 가우시안 스플랫의 형태도 함께 변형합니다. diff --git a/ko/built-in-nodes/TrimAudioDuration.mdx b/ko/built-in-nodes/TrimAudioDuration.mdx index af175da32..098ce86c3 100644 --- a/ko/built-in-nodes/TrimAudioDuration.mdx +++ b/ko/built-in-nodes/TrimAudioDuration.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TrimAudioDuration" icon: "circle" mode: wide --- -# TrimAudioDuration (오디오 길이 자르기) TrimAudioDuration 노드를 사용하면 오디오 파일에서 특정 시간 구간을 잘라낼 수 있습니다. 자르기를 시작할 시점과 결과 오디오 클립의 길이를 지정할 수 있습니다. 이 노드는 시간 값을 오디오 프레임 위치로 변환하고 해당 오디오 파형 부분을 추출하는 방식으로 작동합니다. diff --git a/ko/built-in-nodes/TrimVideoLatent.mdx b/ko/built-in-nodes/TrimVideoLatent.mdx index cd68b2be3..fded3bd80 100644 --- a/ko/built-in-nodes/TrimVideoLatent.mdx +++ b/ko/built-in-nodes/TrimVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrimVideoLatent" icon: "circle" mode: wide --- + TrimVideoLatent 노드는 비디오 잠재 표현의 시작 부분에서 프레임을 제거합니다. 잠재 비디오 샘플을 입력받아 지정된 수의 프레임을 앞에서 잘라내고, 남은 비디오 부분을 반환합니다. 이를 통해 초기 프레임을 제거하여 비디오 시퀀스를 단축할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/TripleCLIPLoader.mdx b/ko/built-in-nodes/TripleCLIPLoader.mdx index 67d765579..f2d627213 100644 --- a/ko/built-in-nodes/TripleCLIPLoader.mdx +++ b/ko/built-in-nodes/TripleCLIPLoader.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripleCLIPLoader" icon: "circle" mode: wide --- -# TripleCLIPLoader TripleCLIPLoader 노드는 세 가지 서로 다른 텍스트 인코더 모델을 동시에 로드하여 단일 CLIP 모델로 결합합니다. 이는 SD3 워크플로우에서 clip-l, clip-g, t5 모델을 함께 사용해야 하는 경우와 같이 여러 텍스트 인코더가 필요한 고급 텍스트 인코딩 시나리오에 유용합니다. diff --git a/ko/built-in-nodes/TripoConversionNode.mdx b/ko/built-in-nodes/TripoConversionNode.mdx index 2f2f260de..e2f3f5db5 100644 --- a/ko/built-in-nodes/TripoConversionNode.mdx +++ b/ko/built-in-nodes/TripoConversionNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoConversionNode" icon: "circle" mode: wide --- -# Tripo 변환 노드 TripoConversionNode는 Tripo API를 사용하여 3D 모델을 다양한 파일 형식 간에 변환합니다. 이 노드는 이전 Tripo 작업(모델 생성, 리깅 또는 리타겟팅)의 작업 ID를 받아 결과 모델을 다양한 내보내기 옵션과 함께 원하는 형식으로 변환합니다. diff --git a/ko/built-in-nodes/TripoImageToModelNode.mdx b/ko/built-in-nodes/TripoImageToModelNode.mdx index 9952e1b8a..19fccffe4 100644 --- a/ko/built-in-nodes/TripoImageToModelNode.mdx +++ b/ko/built-in-nodes/TripoImageToModelNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoImageToModelNode" icon: "circle" mode: wide --- -# Tripo 이미지-3D 모델 노드 Tripo의 API를 사용하여 단일 이미지를 기반으로 3D 모델을 동기식으로 생성합니다. 이 노드는 입력 이미지를 받아 텍스처, 품질 및 모델 속성에 대한 다양한 사용자 지정 옵션과 함께 3D 모델로 변환합니다. @@ -33,8 +32,8 @@ Tripo의 API를 사용하여 단일 이미지를 기반으로 3D 모델을 동 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `모델 task_id` | 생성된 3D 모델 파일 (하위 호환성 전용) | STRING | -| `GLB` | 모델 생성 과정 추적을 위한 작업 ID | MODEL_TASK_ID | +| `모델 파일` | 생성된 3D 모델 파일 (하위 호환성 전용) | STRING | +| `모델 task_id` | 모델 생성 과정 추적을 위한 작업 ID | MODEL_TASK_ID | | `GLB` | GLB 형식으로 생성된 3D 모델 | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImageToModelNode/ko.md) diff --git a/ko/built-in-nodes/TripoImportModelNode.mdx b/ko/built-in-nodes/TripoImportModelNode.mdx new file mode 100644 index 000000000..a9f377911 --- /dev/null +++ b/ko/built-in-nodes/TripoImportModelNode.mdx @@ -0,0 +1,28 @@ +--- +title: "TripoImportModelNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the TripoImportModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "TripoImportModelNode" +icon: "circle" +mode: wide +--- + +이 노드는 외부 3D 모델 파일을 Tripo 시스템으로 가져와서 Texture, Rig, Convert와 같은 Tripo 후처리 노드에서 사용할 수 있도록 합니다. 모델을 업로드하고 다른 Tripo 노드에서 가져온 모델을 참조할 수 있는 작업 ID를 반환합니다. + +## 입력 + +| 매개변수 | 설명 | 데이터 타입 | 필수 | 범위 | +|-----------|-------------|-----------|----------|-------| +| `model_3d` | 가져올 3D 모델입니다(GLB / FBX / OBJ / STL, 최대 150MB). OBJ 및 STL 파일에는 텍스처가 포함되어 있지 않습니다. | FILE3D | 예 | GLB
FBX
OBJ
STL
모든 3D 형식 | + +**참고:** 텍스처는 파일에 직접 포함된 경우에만 보존되므로 GLB 형식을 권장합니다. OBJ 및 STL 파일은 포함된 텍스처를 지원하지 않습니다. GLTF(.gltf) 형식은 외부 파일을 참조하므로 지원되지 않습니다. 단일 파일 GLB를 대신 사용하십시오. + +## 출력 + +| 출력 이름 | 설명 | 데이터 타입 | +|-------------|-------------|-----------| +| `model task_id` | Tripo 후처리 노드에서 사용할 수 있도록 가져온 모델을 식별하는 작업 ID입니다. | MODEL_TASK_ID | + +> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImportModelNode/ko.md) + +--- +**Source fingerprint (SHA-256):** `4fa13a108804f2a52190a85b5b5d58ff18190e9d182b556abada444788012fab` diff --git a/ko/built-in-nodes/TripoMultiviewToModelNode.mdx b/ko/built-in-nodes/TripoMultiviewToModelNode.mdx index ecde56a16..99d95d4c3 100644 --- a/ko/built-in-nodes/TripoMultiviewToModelNode.mdx +++ b/ko/built-in-nodes/TripoMultiviewToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoMultiviewToModelNode" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! 이 노드는 Tripo의 API를 사용하여 객체의 여러 뷰를 보여주는 최대 4개의 이미지를 처리하여 3D 모델을 동기식으로 생성합니다. 완전한 3D 모델을 만들기 위해 정면 이미지와 최소 하나의 추가 뷰(왼쪽, 뒤 또는 오른쪽)가 필요하며, 텍스처 및 재질 옵션을 제공합니다. @@ -35,8 +36,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `모델 task_id` | 생성된 3D 모델의 파일 경로 또는 식별자 (하위 호환성 전용) | STRING | -| `GLB` | 모델 생성 과정 추적을 위한 작업 식별자 | MODEL_TASK_ID | +| `모델 파일` | 생성된 3D 모델의 파일 경로 또는 식별자 (하위 호환성 전용) | STRING | +| `모델 task_id` | 모델 생성 과정 추적을 위한 작업 식별자 | MODEL_TASK_ID | | `GLB` | GLB 형식으로 생성된 3D 모델 파일 | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoMultiviewToModelNode/ko.md) diff --git a/ko/built-in-nodes/TripoP1ImageToModelNode.mdx b/ko/built-in-nodes/TripoP1ImageToModelNode.mdx index b92d81939..096fa0d03 100644 --- a/ko/built-in-nodes/TripoP1ImageToModelNode.mdx +++ b/ko/built-in-nodes/TripoP1ImageToModelNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoP1ImageToModelNode" icon: "circle" mode: wide --- -# 개요 이 노드는 Tripo P1 API를 사용하여 단일 2D 이미지를 3D 모델로 변환합니다. 저폴리곤, 게임에 바로 사용할 수 있는 메시를 생성하도록 최적화되어 있습니다. diff --git a/ko/built-in-nodes/TripoP1MultiviewToModelNode.mdx b/ko/built-in-nodes/TripoP1MultiviewToModelNode.mdx index fff9f8f9b..8e0ced17f 100644 --- a/ko/built-in-nodes/TripoP1MultiviewToModelNode.mdx +++ b/ko/built-in-nodes/TripoP1MultiviewToModelNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoP1MultiviewToModelNode" icon: "circle" mode: wide --- -# 개요 이 노드는 객체나 캐릭터의 2~4장의 참조 이미지로부터 3D 모델을 생성합니다. 다양한 각도(정면, 좌측, 후면, 우측)의 이미지를 제공하면 노드가 GLB 형식의 3D 메시를 생성합니다. 정면 뷰는 필수이며, 더 나은 결과를 위해 나머지 세 가지 뷰를 선택적으로 추가할 수 있습니다. diff --git a/ko/built-in-nodes/TripoP1TextToModelNode.mdx b/ko/built-in-nodes/TripoP1TextToModelNode.mdx index fee90291f..e6f4fa1a6 100644 --- a/ko/built-in-nodes/TripoP1TextToModelNode.mdx +++ b/ko/built-in-nodes/TripoP1TextToModelNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoP1TextToModelNode" icon: "circle" mode: wide --- -# 개요 이 노드는 Tripo P1 API를 사용하여 텍스트 설명으로부터 3D 모델을 생성합니다. 안정적인 토폴로지를 가진 로우폴리, 게임에 바로 사용할 수 있는 메시를 생성하도록 최적화되어 있어 실시간 애플리케이션에 적합합니다. diff --git a/ko/built-in-nodes/TripoRefineNode.mdx b/ko/built-in-nodes/TripoRefineNode.mdx index e428e47b9..ecc230252 100644 --- a/ko/built-in-nodes/TripoRefineNode.mdx +++ b/ko/built-in-nodes/TripoRefineNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoRefineNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/en.md) TripoRefineNode는 특히 v1.4 Tripo 모델이 생성한 초안 3D 모델을 정제합니다. 모델 작업 ID를 받아 Tripo API를 통해 처리하여 개선된 버전의 모델을 생성합니다. 이 노드는 Tripo v1.4 모델이 생성한 초안 모델에만 작동하도록 설계되었습니다. @@ -21,8 +22,8 @@ TripoRefineNode는 특히 v1.4 Tripo 모델이 생성한 초안 3D 모델을 정 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `모델 task_id` | 정제된 모델의 파일 경로 또는 참조(하위 호환성 전용) | STRING | -| `GLB` | 정제된 모델 작업의 식별자 | MODEL_TASK_ID | +| `모델 파일` | 정제된 모델의 파일 경로 또는 참조(하위 호환성 전용) | STRING | +| `모델 task_id` | 정제된 모델 작업의 식별자 | MODEL_TASK_ID | | `GLB` | GLB 형식의 정제된 3D 모델 | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/ko.md) diff --git a/ko/built-in-nodes/TripoRetargetNode.mdx b/ko/built-in-nodes/TripoRetargetNode.mdx index bded24c19..d36cd3569 100644 --- a/ko/built-in-nodes/TripoRetargetNode.mdx +++ b/ko/built-in-nodes/TripoRetargetNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoRetargetNode" icon: "circle" mode: wide --- -# TripoRetargetNode TripoRetargetNode는 사전 정의된 애니메이션을 3D 캐릭터 모델에 적용하여 모션 데이터를 리타겟팅합니다. 이 노드는 이전에 리깅된 3D 모델을 입력받아 여러 사전 설정 애니메이션 중 하나를 적용하고, 애니메이션이 적용된 3D 모델 파일을 출력으로 생성합니다. Tripo API와 통신하여 애니메이션 리타겟팅 작업을 처리합니다. @@ -23,8 +22,8 @@ TripoRetargetNode는 사전 정의된 애니메이션을 3D 캐릭터 모델에 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `리타겟 task_id` | 생성된 애니메이션 3D 모델 파일(하위 호환성 전용) | STRING | -| `GLB` | 리타겟팅 작업 추적을 위한 작업 ID | RETARGET_TASK_ID | +| `모델 파일` | 생성된 애니메이션 3D 모델 파일(하위 호환성 전용) | STRING | +| `리타겟 task_id` | 리타겟팅 작업 추적을 위한 작업 ID | RETARGET_TASK_ID | | `GLB` | GLB 형식의 애니메이션 3D 모델 | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRetargetNode/ko.md) diff --git a/ko/built-in-nodes/TripoRigNode.mdx b/ko/built-in-nodes/TripoRigNode.mdx index 42d7db9f7..af5606e80 100644 --- a/ko/built-in-nodes/TripoRigNode.mdx +++ b/ko/built-in-nodes/TripoRigNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoRigNode" icon: "circle" mode: wide --- -# TripoRigNode TripoRigNode는 원본 모델 작업 ID로부터 리깅된 3D 모델을 생성합니다. Tripo API에 요청을 전송하여 Tripo 사양을 사용해 GLB 형식의 애니메이션 리그를 생성한 후, 리그 생성 작업이 완료될 때까지 API를 폴링합니다. @@ -22,8 +21,8 @@ TripoRigNode는 원본 모델 작업 ID로부터 리깅된 3D 모델을 생성 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `리깅 task_id` | 생성된 리깅 3D 모델 파일 (하위 호환성을 위해 유지됨) | STRING | -| `GLB` | 리그 생성 과정 추적을 위한 작업 ID | RIG_TASK_ID | +| `모델 파일` | 생성된 리깅 3D 모델 파일 (하위 호환성을 위해 유지됨) | STRING | +| `리깅 task_id` | 리그 생성 과정 추적을 위한 작업 ID | RIG_TASK_ID | | `GLB` | GLB 형식으로 생성된 리깅 3D 모델 | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRigNode/ko.md) diff --git a/ko/built-in-nodes/TripoSplatConditioning.mdx b/ko/built-in-nodes/TripoSplatConditioning.mdx index c5a0e62e6..973f867cd 100644 --- a/ko/built-in-nodes/TripoSplatConditioning.mdx +++ b/ko/built-in-nodes/TripoSplatConditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatConditioning" icon: "circle" mode: wide --- -# TripoSpat 조건부 설정 이 노드는 DINOv3와 Flux2 VAE를 사용하여 입력 이미지를 인코딩함으로써 TripoSpat 모델을 위한 긍정 및 부정 조건부 데이터를 생성합니다. 또한 KSampler의 시작점 역할을 하는 고정 크기의 노이즈 대상(잠재 변수 및 카메라 데이터)을 생성합니다. @@ -21,8 +20,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | |-------------|-------------|-----------| -| `negative` | DINOv3 특징과 Flux2 VAE 잠재 변수를 포함하는 긍정 조건부 데이터 | CONDITIONING | -| `latent` | 0으로 채워진 DINOv3 특징과 0으로 채워진 Flux2 VAE 잠재 변수를 포함하는 부정 조건부 데이터 | CONDITIONING | +| `positive` | DINOv3 특징과 Flux2 VAE 잠재 변수를 포함하는 긍정 조건부 데이터 | CONDITIONING | +| `negative` | 0으로 채워진 DINOv3 특징과 0으로 채워진 Flux2 VAE 잠재 변수를 포함하는 부정 조건부 데이터 | CONDITIONING | | `latent` | KSampler를 위한 고정 크기 노이즈 대상(잠재 시퀀스 및 카메라 토큰) | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoSplatConditioning/ko.md) diff --git a/ko/built-in-nodes/TripoSplatPreprocessImage.mdx b/ko/built-in-nodes/TripoSplatPreprocessImage.mdx index 232775ffd..8943d7f17 100644 --- a/ko/built-in-nodes/TripoSplatPreprocessImage.mdx +++ b/ko/built-in-nodes/TripoSplatPreprocessImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatPreprocessImage" icon: "circle" mode: wide --- -# TripoSplat 이미지 전처리 이 노드는 각 입력 이미지를 검은색 배경의 중앙 정사각형으로 자른 후, 지정된 출력 크기에 도달하도록 패딩을 추가합니다. 일관된 정사각형 프레임과 테두리 아티팩트 방지를 위한 선택적 알파 매트 침식을 통해 TripoSplat 3D 모델용 이미지를 준비하도록 설계되었습니다. diff --git a/ko/built-in-nodes/TripoSplatSamplingPreview.mdx b/ko/built-in-nodes/TripoSplatSamplingPreview.mdx index 347c2d01f..44608b2cf 100644 --- a/ko/built-in-nodes/TripoSplatSamplingPreview.mdx +++ b/ko/built-in-nodes/TripoSplatSamplingPreview.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatSamplingPreview" icon: "circle" mode: wide --- -# TripoSplat 샘플링 미리보기 이 노드는 TripoSplat 모델을 패치하여 표준 KSampler 노드와 함께 사용할 때 각 샘플링 단계에서 디코딩된 가우시안 스플랫의 실시간 미리보기를 표시합니다. 샘플러의 콜백을 래핑하여 각 단계 후 모델의 출력을 미리보기 이미지로 디코딩하는 방식으로 작동합니다. diff --git a/ko/built-in-nodes/TripoTextToModelNode.mdx b/ko/built-in-nodes/TripoTextToModelNode.mdx index b187901eb..740f4bbe0 100644 --- a/ko/built-in-nodes/TripoTextToModelNode.mdx +++ b/ko/built-in-nodes/TripoTextToModelNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoTextToModelNode" icon: "circle" mode: wide --- -# Tripo 텍스트-3D 모델 노드 Tripo의 API를 사용하여 텍스트 프롬프트를 기반으로 3D 모델을 동기식으로 생성합니다. 이 노드는 텍스트 설명을 받아 선택적 텍스처 및 재질 속성과 함께 3D 모델을 생성합니다. @@ -33,8 +32,8 @@ Tripo의 API를 사용하여 텍스트 프롬프트를 기반으로 3D 모델을 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `모델 task_id` | 생성된 3D 모델 파일 (하위 호환성 전용) | STRING | -| `GLB` | 모델 생성 프로세스의 고유 작업 식별자 | MODEL_TASK_ID | +| `모델 파일` | 생성된 3D 모델 파일 (하위 호환성 전용) | STRING | +| `모델 task_id` | 모델 생성 프로세스의 고유 작업 식별자 | MODEL_TASK_ID | | `GLB` | GLB 형식으로 생성된 3D 모델 | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextToModelNode/ko.md) diff --git a/ko/built-in-nodes/TripoTextureNode.mdx b/ko/built-in-nodes/TripoTextureNode.mdx index dd659b69a..43294e947 100644 --- a/ko/built-in-nodes/TripoTextureNode.mdx +++ b/ko/built-in-nodes/TripoTextureNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoTextureNode" icon: "circle" mode: wide --- -# TripoTextureNode TripoTextureNode는 Tripo API를 사용하여 텍스처가 적용된 3D 모델을 생성합니다. 모델 작업 ID를 입력받아 PBR 재질, 텍스처 품질 설정, 정렬 방법 등 다양한 옵션으로 텍스처 생성을 적용합니다. 이 노드는 Tripo API와 통신하여 텍스처 생성 요청을 처리하고 결과 모델 파일과 작업 ID를 반환합니다. @@ -26,8 +25,8 @@ TripoTextureNode는 Tripo API를 사용하여 텍스처가 적용된 3D 모델 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `모델 task_id` | 텍스처가 적용된 생성된 모델 파일 (하위 호환성 전용) | STRING | -| `GLB` | 텍스처 생성 과정 추적을 위한 작업 ID | MODEL_TASK_ID | +| `모델 파일` | 텍스처가 적용된 생성된 모델 파일 (하위 호환성 전용) | STRING | +| `모델 task_id` | 텍스처 생성 과정 추적을 위한 작업 ID | MODEL_TASK_ID | | `GLB` | 텍스처가 적용된 GLB 형식의 생성된 3D 모델 | FILE3DGLB | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextureNode/ko.md) diff --git a/ko/built-in-nodes/TruncateText.mdx b/ko/built-in-nodes/TruncateText.mdx index 57f3e43c0..63ae756ad 100644 --- a/ko/built-in-nodes/TruncateText.mdx +++ b/ko/built-in-nodes/TruncateText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TruncateText" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TruncateText/en.md) 이 노드는 지정된 최대 길이에서 텍스트를 잘라내어 단축합니다. 입력 텍스트를 받아 설정한 문자 수까지만 첫 부분을 반환합니다. 텍스트가 특정 크기를 초과하지 않도록 하는 간단한 방법입니다. @@ -20,7 +21,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `string` | 잘라낸 텍스트로, 입력에서 처음 `max_length` 문자만 포함합니다. | STRING | +| `texts` | 잘라낸 텍스트로, 입력에서 처음 `max_length` 문자만 포함합니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TruncateText/ko.md) diff --git a/ko/built-in-nodes/UNETLoader.mdx b/ko/built-in-nodes/UNETLoader.mdx index 8feb6d1d3..dad46bcb3 100644 --- a/ko/built-in-nodes/UNETLoader.mdx +++ b/ko/built-in-nodes/UNETLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNETLoader" icon: "circle" mode: wide --- + UNETLoader 노드는 이름으로 U-Net 모델을 로드하도록 설계되어, 시스템 내에서 사전 훈련된 U-Net 아키텍처를 손쉽게 사용할 수 있도록 합니다. 이 노드는 `ComfyUI/models/diffusion_models` 폴더에 위치한 모델을 감지합니다. diff --git a/ko/built-in-nodes/UNetCrossAttentionMultiply.mdx b/ko/built-in-nodes/UNetCrossAttentionMultiply.mdx index c5bc0257f..50d78491a 100644 --- a/ko/built-in-nodes/UNetCrossAttentionMultiply.mdx +++ b/ko/built-in-nodes/UNetCrossAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetCrossAttentionMultiply" icon: "circle" mode: wide --- + UNetCrossAttentionMultiply 노드는 UNet 모델의 교차 주의 메커니즘에 곱셈 계수를 적용합니다. 이를 통해 교차 주의 레이어의 쿼리, 키, 값 및 출력 구성 요소의 크기를 조정하여 다양한 주의 동작과 효과를 실험할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/UNetSelfAttentionMultiply.mdx b/ko/built-in-nodes/UNetSelfAttentionMultiply.mdx index f235f2e72..2924c7f10 100644 --- a/ko/built-in-nodes/UNetSelfAttentionMultiply.mdx +++ b/ko/built-in-nodes/UNetSelfAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetSelfAttentionMultiply" icon: "circle" mode: wide --- + UNetSelfAttentionMultiply 노드는 UNet 모델의 셀프 어텐션 메커니즘에서 쿼리(query), 키(key), 값(value) 및 출력(output) 구성 요소에 곱셈 계수를 적용합니다. 이를 통해 어텐션 계산의 여러 부분을 조정하여 어텐션 가중치가 모델 동작에 미치는 영향을 실험할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/UNetTemporalAttentionMultiply.mdx b/ko/built-in-nodes/UNetTemporalAttentionMultiply.mdx index 48524a56d..6da32878f 100644 --- a/ko/built-in-nodes/UNetTemporalAttentionMultiply.mdx +++ b/ko/built-in-nodes/UNetTemporalAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetTemporalAttentionMultiply" icon: "circle" mode: wide --- + UNetTemporalAttentionMultiply 노드는 시간적 UNet 모델에서 다양한 유형의 어텐션 메커니즘에 곱셈 계수를 적용합니다. 이 노드는 자기 어텐션(self-attention)과 교차 어텐션(cross-attention) 레이어의 가중치를 조정하여 모델을 수정하며, 구조적 구성 요소와 시간적 구성 요소를 구분합니다. 이를 통해 각 어텐션 유형이 모델 출력에 미치는 영향을 세밀하게 조정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/USOStyleReference.mdx b/ko/built-in-nodes/USOStyleReference.mdx index d5e7c9086..d823d96e7 100644 --- a/ko/built-in-nodes/USOStyleReference.mdx +++ b/ko/built-in-nodes/USOStyleReference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "USOStyleReference" icon: "circle" mode: wide --- + USOStyleReference 노드는 CLIP 비전 출력에서 인코딩된 이미지 특징을 사용하여 모델에 스타일 참조 패치를 적용합니다. 시각적 입력에서 추출된 스타일 정보를 통합하여 입력 모델의 수정된 버전을 생성함으로써, 스타일 전이 또는 참조 기반 생성 기능을 가능하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/UpscaleModelLoader.mdx b/ko/built-in-nodes/UpscaleModelLoader.mdx index b2a0a41cc..029ca08a6 100644 --- a/ko/built-in-nodes/UpscaleModelLoader.mdx +++ b/ko/built-in-nodes/UpscaleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UpscaleModelLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/upscale_models` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 구성된 추가 경로의 모델도 읽어옵니다. 때로는 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수도 있습니다. UpscaleModelLoader 노드는 지정된 디렉터리에서 업스케일 모델을 로드하도록 설계되었습니다. 이미지 업스케일 작업을 위해 업스케일 모델을 검색하고 준비하는 과정을 용이하게 하며, 모델이 올바르게 로드되고 평가를 위해 구성되도록 보장합니다. diff --git a/ko/built-in-nodes/VAEDecode.mdx b/ko/built-in-nodes/VAEDecode.mdx index 17e83f8f2..c4d3974d8 100644 --- a/ko/built-in-nodes/VAEDecode.mdx +++ b/ko/built-in-nodes/VAEDecode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecode" icon: "circle" mode: wide --- + VAEDecode 노드는 지정된 Variational Autoencoder(VAE)를 사용하여 잠재 표현을 이미지로 디코딩하도록 설계되었습니다. 이 노드는 압축된 데이터 표현에서 이미지를 생성하고, 잠재 공간 인코딩으로부터 이미지를 재구성하는 역할을 수행합니다. ## 입력 diff --git a/ko/built-in-nodes/VAEDecodeAudio.mdx b/ko/built-in-nodes/VAEDecodeAudio.mdx index 10ed65531..5ac657fdb 100644 --- a/ko/built-in-nodes/VAEDecodeAudio.mdx +++ b/ko/built-in-nodes/VAEDecodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeAudio" icon: "circle" mode: wide --- + VAEDecodeAudio 노드는 변이형 오토인코더(Variational Autoencoder)를 사용하여 잠재 표현을 다시 오디오 파형으로 변환합니다. 인코딩된 오디오 샘플을 입력받아 VAE를 통해 처리하여 원본 오디오를 재구성하며, 일관된 출력 레벨을 보장하기 위해 정규화를 적용합니다. 결과 오디오는 표준 샘플 레이트인 44100Hz로 반환됩니다. ## 입력 diff --git a/ko/built-in-nodes/VAEDecodeAudioTiled.mdx b/ko/built-in-nodes/VAEDecodeAudioTiled.mdx index 8fce8b280..bcfbdf2dc 100644 --- a/ko/built-in-nodes/VAEDecodeAudioTiled.mdx +++ b/ko/built-in-nodes/VAEDecodeAudioTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeAudioTiled" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VAEDecodeAudioTiled/en.md) 이 노드는 Variational Autoencoder(VAE)를 사용하여 압축된 오디오 표현(잠재 샘플)을 다시 오디오 파형으로 변환합니다. 메모리 사용량을 관리하기 위해 데이터를 더 작고 겹치는 섹션(타일)으로 처리하므로, 긴 오디오 시퀀스를 처리하는 데 적합합니다. diff --git a/ko/built-in-nodes/VAEDecodeHunyuan3D.mdx b/ko/built-in-nodes/VAEDecodeHunyuan3D.mdx index 6d1e483a4..3bbc344a1 100644 --- a/ko/built-in-nodes/VAEDecodeHunyuan3D.mdx +++ b/ko/built-in-nodes/VAEDecodeHunyuan3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeHunyuan3D" icon: "circle" mode: wide --- + VAEDecodeHunyuan3D 노드는 VAE 디코더를 사용하여 잠재 표현을 3D 복셀 데이터로 변환합니다. 이 노드는 VAE 모델을 통해 잠재 샘플을 처리하며, 청크 및 해상도 설정을 구성하여 3D 애플리케이션에 적합한 체적 데이터를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/VAEDecodeTiled.mdx b/ko/built-in-nodes/VAEDecodeTiled.mdx index 1ecd82e84..394805def 100644 --- a/ko/built-in-nodes/VAEDecodeTiled.mdx +++ b/ko/built-in-nodes/VAEDecodeTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeTiled" icon: "circle" mode: wide --- + VAEDecodeTiled 노드는 잠재 표현을 이미지로 디코딩할 때 타일 방식을 사용하여 대용량 이미지를 효율적으로 처리합니다. 입력 데이터를 더 작은 타일로 나누어 메모리 사용량을 관리하면서 이미지 품질을 유지합니다. 또한 비디오 VAE를 지원하여 시간적 프레임을 청크 단위로 처리하고 중첩을 통해 부드러운 전환을 구현합니다. ## 입력 diff --git a/ko/built-in-nodes/VAEDecodeTripoSplat.mdx b/ko/built-in-nodes/VAEDecodeTripoSplat.mdx index ba47dd5d8..b7ef1f4f1 100644 --- a/ko/built-in-nodes/VAEDecodeTripoSplat.mdx +++ b/ko/built-in-nodes/VAEDecodeTripoSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VAEDecodeTripoSplat" icon: "circle" mode: wide --- -# VAEDecodeTripoSplat TripoSplat 잠재 표현을 3D 가우시안 스플랫으로 디코딩합니다. 이 노드는 TripoSplat 모델에서 샘플링된 잠재 변수를 가져와 3D 가우시안 집합으로 재구성하며, 생성되는 가우시안 수를 조정하여 밀도를 변경할 수 있습니다. diff --git a/ko/built-in-nodes/VAEEncode.mdx b/ko/built-in-nodes/VAEEncode.mdx index 856cc9734..9033aa8d6 100644 --- a/ko/built-in-nodes/VAEEncode.mdx +++ b/ko/built-in-nodes/VAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncode" icon: "circle" mode: wide --- + 이 노드는 지정된 VAE 모델을 사용하여 이미지를 잠재 공간 표현으로 인코딩하도록 설계되었습니다. 인코딩 프로세스의 복잡성을 추상화하여 이미지를 잠재 표현으로 변환하는 간단한 방법을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/VAEEncodeAudio.mdx b/ko/built-in-nodes/VAEEncodeAudio.mdx index 80319b23b..ec859c6d0 100644 --- a/ko/built-in-nodes/VAEEncodeAudio.mdx +++ b/ko/built-in-nodes/VAEEncodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeAudio" icon: "circle" mode: wide --- + VAEEncodeAudio 노드는 가변 오토인코더(VAE)를 사용하여 오디오 데이터를 잠재 표현으로 변환합니다. 오디오 입력을 받아 VAE를 통해 처리하여 압축된 잠재 샘플을 생성하며, 이는 추가 오디오 생성 또는 조작 작업에 사용할 수 있습니다. 이 노드는 인코딩 전에 필요 시 오디오를 VAE의 예상 샘플 속도에 맞게 자동으로 리샘플링합니다. ## 입력 diff --git a/ko/built-in-nodes/VAEEncodeForInpaint.mdx b/ko/built-in-nodes/VAEEncodeForInpaint.mdx index 8698f2fea..92ad2cb10 100644 --- a/ko/built-in-nodes/VAEEncodeForInpaint.mdx +++ b/ko/built-in-nodes/VAEEncodeForInpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeForInpaint" icon: "circle" mode: wide --- + 이 노드는 인페인팅 작업에 적합한 잠재 표현으로 이미지를 인코딩하기 위해 설계되었으며, VAE 모델이 최적으로 인코딩할 수 있도록 입력 이미지와 마스크를 조정하는 추가 전처리 단계를 포함합니다. ## 입력 diff --git a/ko/built-in-nodes/VAEEncodeTiled.mdx b/ko/built-in-nodes/VAEEncodeTiled.mdx index 2bc665523..9d57aac08 100644 --- a/ko/built-in-nodes/VAEEncodeTiled.mdx +++ b/ko/built-in-nodes/VAEEncodeTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeTiled" icon: "circle" mode: wide --- + VAEEncodeTiled 노드는 이미지를 더 작은 타일로 분할하고 Variational Autoencoder를 사용하여 인코딩합니다. 이 타일 방식은 메모리 제한을 초과할 수 있는 대형 이미지를 처리할 수 있게 해줍니다. 이 노드는 이미지 및 비디오 VAE를 모두 지원하며, 공간 및 시간 차원에 대한 별도의 타일링 제어 기능을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/VAELoader.mdx b/ko/built-in-nodes/VAELoader.mdx index c419fa702..380aa701c 100644 --- a/ko/built-in-nodes/VAELoader.mdx +++ b/ko/built-in-nodes/VAELoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAELoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/vae` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 구성된 추가 경로에서도 모델을 읽어옵니다. 때로는 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수도 있습니다. VAELoader 노드는 변분 오토인코더(VAE) 모델을 로드하기 위해 설계되었으며, 표준 VAE와 근사 VAE를 모두 처리할 수 있도록 특별히 구성되어 있습니다. 이름으로 VAE를 로드하는 기능을 지원하며, 'taesd' 및 'taesdxl' 모델에 대한 특수 처리를 포함하고, VAE의 특정 구성에 따라 동적으로 조정됩니다. diff --git a/ko/built-in-nodes/VAESave.mdx b/ko/built-in-nodes/VAESave.mdx index 5f5b4d7a3..97fc5a1ed 100644 --- a/ko/built-in-nodes/VAESave.mdx +++ b/ko/built-in-nodes/VAESave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAESave" icon: "circle" mode: wide --- + VAESave 노드는 VAE 모델과 해당 메타데이터(프롬프트 및 추가 PNG 정보 포함)를 지정된 출력 디렉토리에 저장하기 위해 설계되었습니다. 이 노드는 모델 상태와 관련 정보를 파일로 직렬화하는 기능을 캡슐화하여, 학습된 모델의 보존과 공유를 용이하게 합니다. ## 입력 diff --git a/ko/built-in-nodes/VOIDInpaintConditioning.mdx b/ko/built-in-nodes/VOIDInpaintConditioning.mdx index 0f395fd35..11527c3ac 100644 --- a/ko/built-in-nodes/VOIDInpaintConditioning.mdx +++ b/ko/built-in-nodes/VOIDInpaintConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDInpaintConditioning" icon: "circle" mode: wide --- + VOIDInpaintConditioning 노드는 CogVideoX 모델의 인페인팅에 필요한 컨디셔닝 데이터를 준비합니다. 소스 비디오와 전처리된 쿼드마스크를 입력받아 VAE를 통해 인코딩한 후, 모델이 마스크 영역을 채우는 데 사용하는 32채널 컨디셔닝 신호로 결합합니다. ## 입력 @@ -25,8 +26,8 @@ VOIDInpaintConditioning 노드는 CogVideoX 모델의 인페인팅에 필요한 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 인페인팅 잠재 정보가 추가된 포지티브 컨디셔닝 | CONDITIONING | -| `latent` | 인페인팅 잠재 정보가 추가된 네거티브 컨디셔닝 | CONDITIONING | +| `positive` | 인페인팅 잠재 정보가 추가된 포지티브 컨디셔닝 | CONDITIONING | +| `negative` | 인페인팅 잠재 정보가 추가된 네거티브 컨디셔닝 | CONDITIONING | | `latent` | 형태가 [batch_size, 16, latent_t, latent_h, latent_w]인 0으로 채워진 노이즈 잠재 텐서 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VOIDInpaintConditioning/ko.md) diff --git a/ko/built-in-nodes/VOIDQuadmaskPreprocess.mdx b/ko/built-in-nodes/VOIDQuadmaskPreprocess.mdx index 3ceded156..5f51dce4f 100644 --- a/ko/built-in-nodes/VOIDQuadmaskPreprocess.mdx +++ b/ko/built-in-nodes/VOIDQuadmaskPreprocess.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDQuadmaskPreprocess" icon: "circle" mode: wide --- + ## 개요 VOIDQuadmaskPreprocess 노드는 마스크를 특수한 4단계 "쿼드마스크"로 변환하여 VOID 인페인팅을 위한 마스크를 준비합니다. 입력 마스크를 받아 선택적으로 주요 영역을 확장한 후, 마스크 값을 서로 다른 의미론적 영역(주요 객체, 중첩 영역, 영향 영역, 배경)을 나타내는 4개의 고유한 수준으로 양자화합니다. 마지막으로 마스크를 반전 및 정규화하여 출력 값이 [0, 1] 범위에 있도록 하며, 1.0은 제거할 영역, 0.0은 유지할 영역을 나타냅니다. diff --git a/ko/built-in-nodes/VOIDSampler.mdx b/ko/built-in-nodes/VOIDSampler.mdx index 66aab1e99..1fd7695cf 100644 --- a/ko/built-in-nodes/VOIDSampler.mdx +++ b/ko/built-in-nodes/VOIDSampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDSampler" icon: "circle" mode: wide --- + ## 개요 VOIDSampler 노드는 VOID 인페인팅 모델을 위해 특별히 설계된 전용 DDIM 샘플링 방식을 제공합니다. 이 노드는 표준 KSampler가 적용하는 노이즈 스케일링 없이, VOID 모델 학습 시 사용된 것과 동일한 잡음 제거 프로세스를 구현합니다. 이 노드는 SamplerCustom 또는 SamplerCustomAdvanced 노드와 함께 사용하도록 설계되었으며, RandomNoise 또는 VOIDWarpedNoiseSource와 함께 사용해야 합니다. diff --git a/ko/built-in-nodes/VOIDWarpedNoise.mdx b/ko/built-in-nodes/VOIDWarpedNoise.mdx index 78ca2d4ab..3c17bd939 100644 --- a/ko/built-in-nodes/VOIDWarpedNoise.mdx +++ b/ko/built-in-nodes/VOIDWarpedNoise.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VOIDWarpedNoise" icon: "circle" mode: wide --- -# 개요 VOID 비디오 개선 프로세스의 두 번째 패스(pass)를 위한 시간적 상관관계가 있는 노이즈를 생성합니다. 패스 1의 출력 비디오를 가져와 광학 흐름 벡터를 따라 가우시안 노이즈를 워핑(warping)하여 비디오 콘텐츠와 일관되게 움직이는 노이즈를 만듭니다. 이 워핑된 노이즈는 패스 2의 시작 잠재 변수(latent)로 사용되어 최종 출력의 시간적 일관성을 향상시킵니다. diff --git a/ko/built-in-nodes/VOIDWarpedNoiseSource.mdx b/ko/built-in-nodes/VOIDWarpedNoiseSource.mdx index 64af958de..239bedcea 100644 --- a/ko/built-in-nodes/VOIDWarpedNoiseSource.mdx +++ b/ko/built-in-nodes/VOIDWarpedNoiseSource.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDWarpedNoiseSource" icon: "circle" mode: wide --- + ## 개요 이 노드는 LATENT(VOIDWarpedNoise 노드의 출력 등)를 NOISE 소스로 변환합니다. 이를 통해 왜곡된 노이즈를 SamplerCustomAdvanced 노드와 함께 사용하여 보다 제어된 이미지 생성을 수행할 수 있습니다. diff --git a/ko/built-in-nodes/VPScheduler.mdx b/ko/built-in-nodes/VPScheduler.mdx index 30bc8824e..ee88cc52f 100644 --- a/ko/built-in-nodes/VPScheduler.mdx +++ b/ko/built-in-nodes/VPScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VPScheduler" icon: "circle" mode: wide --- + VPScheduler 노드는 Variance Preserving(VP) 스케줄링 방식을 기반으로 노이즈 수준(시그마) 시퀀스를 생성하도록 설계되었습니다. 이 시퀀스는 확산 모델의 노이즈 제거 과정을 안내하여 이미지 또는 기타 데이터 유형의 제어된 생성을 가능하게 하는 데 중요합니다. ## 입력 diff --git a/ko/built-in-nodes/Veo3FirstLastFrameNode.mdx b/ko/built-in-nodes/Veo3FirstLastFrameNode.mdx index bca412069..af752d6a5 100644 --- a/ko/built-in-nodes/Veo3FirstLastFrameNode.mdx +++ b/ko/built-in-nodes/Veo3FirstLastFrameNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Veo3FirstLastFrameNode" icon: "circle" mode: wide --- -# Veo3FirstLastFrameNode Veo3FirstLastFrameNode는 Google의 Veo 3 모델을 사용하여 텍스트 프롬프트를 기반으로 비디오를 생성하며, 비디오 시퀀스의 시작과 끝을 정의하는 첫 번째 프레임과 마지막 프레임을 제공합니다. diff --git a/ko/built-in-nodes/Veo3VideoGenerationNode.mdx b/ko/built-in-nodes/Veo3VideoGenerationNode.mdx index 707018a79..f41a607bf 100644 --- a/ko/built-in-nodes/Veo3VideoGenerationNode.mdx +++ b/ko/built-in-nodes/Veo3VideoGenerationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Veo3VideoGenerationNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3VideoGenerationNode/en.md) Google의 Veo 3 API를 사용하여 텍스트 프롬프트에서 비디오를 생성합니다. 이 노드는 빠른 버전과 라이트 버전을 포함한 여러 Veo 3 모델을 지원하며, 비디오 해상도, 길이 및 오디오 생성을 지정할 수 있습니다. diff --git a/ko/built-in-nodes/VeoVideoGenerationNode.mdx b/ko/built-in-nodes/VeoVideoGenerationNode.mdx index 75d7bdc30..0501a947e 100644 --- a/ko/built-in-nodes/VeoVideoGenerationNode.mdx +++ b/ko/built-in-nodes/VeoVideoGenerationNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VeoVideoGenerationNode" icon: "circle" mode: wide --- -# 개요 Google Veo 2 API를 사용하여 텍스트 프롬프트로 비디오를 생성합니다. 이 노드는 텍스트 설명과 선택적 이미지 입력을 바탕으로 비디오를 제작할 수 있으며, 화면 비율, 재생 시간 등의 매개변수를 제어할 수 있습니다. diff --git a/ko/built-in-nodes/Video Slice.mdx b/ko/built-in-nodes/Video Slice.mdx index 1d3f44d3b..09b9036ba 100644 --- a/ko/built-in-nodes/Video Slice.mdx +++ b/ko/built-in-nodes/Video Slice.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Video Slice" icon: "circle" mode: wide --- -# Video Slice Video Slice 노드를 사용하면 비디오에서 특정 구간을 추출할 수 있습니다. 시작 시간과 지속 시간을 정의하여 비디오를 자르거나, 단순히 시작 프레임을 건너뛸 수 있습니다. 요청한 지속 시간이 남은 비디오보다 긴 경우, 노드는 사용 가능한 부분을 반환하거나 오류를 발생시킬 수 있습니다. diff --git a/ko/built-in-nodes/VideoLinearCFGGuidance.mdx b/ko/built-in-nodes/VideoLinearCFGGuidance.mdx index ba6cfc88a..0a50ef68a 100644 --- a/ko/built-in-nodes/VideoLinearCFGGuidance.mdx +++ b/ko/built-in-nodes/VideoLinearCFGGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VideoLinearCFGGuidance" icon: "circle" mode: wide --- + VideoLinearCFGGuidance 노드는 비디오 모델에 선형 조건부 안내 스케일을 적용하여, 지정된 범위 내에서 조건부 및 비조건부 구성 요소의 영향을 조정합니다. 이를 통해 생성 과정을 동적으로 제어할 수 있으며, 원하는 조건화 수준에 따라 모델 출력을 세밀하게 조정할 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/VideoTriangleCFGGuidance.mdx b/ko/built-in-nodes/VideoTriangleCFGGuidance.mdx index d2a7eab4a..8ed5184e3 100644 --- a/ko/built-in-nodes/VideoTriangleCFGGuidance.mdx +++ b/ko/built-in-nodes/VideoTriangleCFGGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VideoTriangleCFGGuidance" icon: "circle" mode: wide --- + VideoTriangleCFGGuidance 노드는 비디오 모델에 삼각형 분류기-프리 가이던스 스케일링 패턴을 적용합니다. 최소 CFG 값과 원래 컨디셔닝 스케일 사이를 진동하는 삼각파 함수를 사용하여 시간에 따라 컨디셔닝 스케일을 수정합니다. 이를 통해 동적인 가이던스 패턴이 생성되어 비디오 생성의 일관성과 품질을 향상시키는 데 도움이 될 수 있습니다. ## 입력 diff --git a/ko/built-in-nodes/Vidu2ImageToVideoNode.mdx b/ko/built-in-nodes/Vidu2ImageToVideoNode.mdx index 7fb147cf7..806e39fef 100644 --- a/ko/built-in-nodes/Vidu2ImageToVideoNode.mdx +++ b/ko/built-in-nodes/Vidu2ImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2ImageToVideoNode" icon: "circle" mode: wide --- + Vidu2 이미지-투-비디오 생성 노드는 단일 입력 이미지로부터 비디오 시퀀스를 생성합니다. 선택적 텍스트 프롬프트를 기반으로 지정된 Vidu2 모델을 사용하여 장면에 애니메이션을 적용하며, 비디오 길이, 해상도 및 움직임 강도를 제어합니다. ## 입력 diff --git a/ko/built-in-nodes/Vidu2ReferenceVideoNode.mdx b/ko/built-in-nodes/Vidu2ReferenceVideoNode.mdx index 19ff8c42b..61e9c3826 100644 --- a/ko/built-in-nodes/Vidu2ReferenceVideoNode.mdx +++ b/ko/built-in-nodes/Vidu2ReferenceVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Vidu2ReferenceVideoNode" icon: "circle" mode: wide --- -# Vidu2 참조-비디오 생성 노드 Vidu2 참조-비디오 생성 노드는 텍스트 프롬프트와 여러 참조 이미지를 기반으로 비디오를 생성합니다. 최대 7개의 주제를 정의할 수 있으며, 각 주제마다 고유한 참조 이미지 세트를 지정할 수 있습니다. 프롬프트에서 `@subject{subject_id}`를 사용하여 주제를 참조할 수 있습니다. 이 노드는 지속 시간, 화면 비율 및 움직임을 구성 가능한 비디오를 생성합니다. diff --git a/ko/built-in-nodes/Vidu2StartEndToVideoNode.mdx b/ko/built-in-nodes/Vidu2StartEndToVideoNode.mdx index c01df8b99..3b8e676ea 100644 --- a/ko/built-in-nodes/Vidu2StartEndToVideoNode.mdx +++ b/ko/built-in-nodes/Vidu2StartEndToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2StartEndToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2StartEndToVideoNode/en.md) 이 노드는 제공된 시작 프레임과 종료 프레임 사이를 보간하여 텍스트 프롬프트에 따라 비디오를 생성합니다. 지정된 Vidu 모델을 사용하여 설정된 시간 동안 두 이미지 간의 부드러운 전환을 만듭니다. diff --git a/ko/built-in-nodes/Vidu2TextToVideoNode.mdx b/ko/built-in-nodes/Vidu2TextToVideoNode.mdx index d24375bd1..1ecf9b3dc 100644 --- a/ko/built-in-nodes/Vidu2TextToVideoNode.mdx +++ b/ko/built-in-nodes/Vidu2TextToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Vidu2TextToVideoNode" icon: "circle" mode: wide --- -# Vidu2 텍스트-비디오 생성 노드 Vidu2 텍스트-비디오 생성 노드는 텍스트 설명을 기반으로 비디오를 생성합니다. 외부 API에 연결하여 프롬프트에 따라 비디오 콘텐츠를 생성하며, 비디오 길이, 시각적 스타일 및 형식을 제어할 수 있습니다. diff --git a/ko/built-in-nodes/Vidu3ImageToVideoNode.mdx b/ko/built-in-nodes/Vidu3ImageToVideoNode.mdx index c6336b1e5..4eb63dbb9 100644 --- a/ko/built-in-nodes/Vidu3ImageToVideoNode.mdx +++ b/ko/built-in-nodes/Vidu3ImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3ImageToVideoNode" icon: "circle" mode: wide --- + Vidu Q3 이미지-투-비디오 생성 노드는 입력 이미지로부터 비디오 시퀀스를 생성합니다. Vidu Q3 모델을 사용하여 이미지에 애니메이션을 적용하며, 선택적으로 텍스트 프롬프트에 의해 안내되어 비디오 파일을 출력합니다. ## 입력 diff --git a/ko/built-in-nodes/Vidu3StartEndToVideoNode.mdx b/ko/built-in-nodes/Vidu3StartEndToVideoNode.mdx index ae18f6ff7..813b63e02 100644 --- a/ko/built-in-nodes/Vidu3StartEndToVideoNode.mdx +++ b/ko/built-in-nodes/Vidu3StartEndToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3StartEndToVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3StartEndToVideoNode/en.md) 이 노드는 제공된 시작 프레임과 종료 프레임 사이를 보간하여 텍스트 프롬프트에 따라 비디오를 생성합니다. Vidu Q3 모델을 사용하여 두 이미지 간의 원활한 전환을 만들고, 지정된 길이와 해상도의 비디오를 출력합니다. diff --git a/ko/built-in-nodes/Vidu3TextToVideoNode.mdx b/ko/built-in-nodes/Vidu3TextToVideoNode.mdx index 34b8aca98..6e5589375 100644 --- a/ko/built-in-nodes/Vidu3TextToVideoNode.mdx +++ b/ko/built-in-nodes/Vidu3TextToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Vidu3TextToVideoNode" icon: "circle" mode: wide --- -# Vidu Q3 텍스트-비디오 생성 노드 Vidu Q3 텍스트-비디오 생성 노드는 텍스트 설명을 기반으로 비디오를 생성합니다. Vidu Q3 Pro 또는 Q3 Turbo 모델을 사용하여 사용자의 프롬프트에 따라 비디오 콘텐츠를 생성하며, 비디오 길이, 해상도, 화면 비율 및 오디오 포함 여부를 제어할 수 있습니다. diff --git a/ko/built-in-nodes/ViduExtendVideoNode.mdx b/ko/built-in-nodes/ViduExtendVideoNode.mdx index 67b5bf31c..fd1370634 100644 --- a/ko/built-in-nodes/ViduExtendVideoNode.mdx +++ b/ko/built-in-nodes/ViduExtendVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ViduExtendVideoNode" icon: "circle" mode: wide --- -# ViduExtendVideoNode ViduExtendVideoNode는 기존 비디오의 길이를 연장하기 위해 추가 프레임을 생성합니다. 지정된 AI 모델을 사용하여 소스 비디오와 선택적 텍스트 프롬프트를 기반으로 자연스러운 연속 영상을 만듭니다. diff --git a/ko/built-in-nodes/ViduImageToVideoNode.mdx b/ko/built-in-nodes/ViduImageToVideoNode.mdx index 92d4085a9..46e1a096e 100644 --- a/ko/built-in-nodes/ViduImageToVideoNode.mdx +++ b/ko/built-in-nodes/ViduImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduImageToVideoNode" icon: "circle" mode: wide --- + Vidu 이미지-투-비디오 생성 노드는 시작 이미지와 선택적 텍스트 설명을 사용하여 짧은 비디오를 생성합니다. 제공된 이미지 프레임에서 이어지는 비디오 콘텐츠를 AI 모델로 생성하며, 결과 비디오를 반환합니다. ## 입력 diff --git a/ko/built-in-nodes/ViduMultiFrameVideoNode.mdx b/ko/built-in-nodes/ViduMultiFrameVideoNode.mdx index 3c719f2c9..dc430d373 100644 --- a/ko/built-in-nodes/ViduMultiFrameVideoNode.mdx +++ b/ko/built-in-nodes/ViduMultiFrameVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduMultiFrameVideoNode" icon: "circle" mode: wide --- + 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduMultiFrameVideoNode/en.md) 이 노드는 여러 키프레임 간의 전환을 생성하여 비디오를 제작합니다. 초기 이미지에서 시작하여 사용자가 정의한 일련의 종료 이미지와 프롬프트를 통해 애니메이션을 적용하며, 최종적으로 단일 비디오 파일을 출력합니다. diff --git a/ko/built-in-nodes/ViduReferenceVideoNode.mdx b/ko/built-in-nodes/ViduReferenceVideoNode.mdx index 761829d55..74eda733c 100644 --- a/ko/built-in-nodes/ViduReferenceVideoNode.mdx +++ b/ko/built-in-nodes/ViduReferenceVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ViduReferenceVideoNode" icon: "circle" mode: wide --- -# Vidu 참조 비디오 노드 Vidu 참조 비디오 노드는 여러 참조 이미지와 텍스트 프롬프트를 기반으로 비디오를 생성합니다. AI 모델을 사용하여 제공된 이미지와 설명에 기반한 일관된 비디오 콘텐츠를 만듭니다. 이 노드는 지속 시간, 화면 비율, 해상도 및 움직임 제어를 포함한 다양한 비디오 설정을 지원합니다. diff --git a/ko/built-in-nodes/ViduStartEndToVideoNode.mdx b/ko/built-in-nodes/ViduStartEndToVideoNode.mdx index f46deb1c9..98fca6ed2 100644 --- a/ko/built-in-nodes/ViduStartEndToVideoNode.mdx +++ b/ko/built-in-nodes/ViduStartEndToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ViduStartEndToVideoNode" icon: "circle" mode: wide --- -# Vidu 시작-종료 프레임 영상 생성 노드 Vidu 시작-종료 프레임 영상 생성 노드는 시작 프레임과 종료 프레임 사이의 프레임을 생성하여 영상을 만듭니다. 텍스트 프롬프트를 사용하여 영상 생성 과정을 안내하며, 다양한 해상도와 움직임 설정을 지원하는 여러 영상 모델을 제공합니다. 이 노드는 처리 전에 시작 프레임과 종료 프레임의 종횡비가 호환되는지 확인합니다. diff --git a/ko/built-in-nodes/ViduTextToVideoNode.mdx b/ko/built-in-nodes/ViduTextToVideoNode.mdx index e423e1f21..60ea72826 100644 --- a/ko/built-in-nodes/ViduTextToVideoNode.mdx +++ b/ko/built-in-nodes/ViduTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduTextToVideoNode" icon: "circle" mode: wide --- + Vidu 텍스트-비디오 생성 노드는 텍스트 설명을 기반으로 비디오를 생성합니다. Vidu 비디오 생성 모델을 사용하여 텍스트 프롬프트를 지속 시간, 화면 비율 및 시각적 스타일에 대한 사용자 정의 설정과 함께 비디오 콘텐츠로 변환합니다. ## 입력 diff --git a/ko/built-in-nodes/VoxelToMesh.mdx b/ko/built-in-nodes/VoxelToMesh.mdx index 07ff5381b..37703d001 100644 --- a/ko/built-in-nodes/VoxelToMesh.mdx +++ b/ko/built-in-nodes/VoxelToMesh.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VoxelToMesh" icon: "circle" mode: wide --- + VoxelToMeshBasic 노드는 지정된 임계값에서 표면을 추출하여 3D 복셀 데이터를 메시 지오메트리로 변환합니다. 입력된 각 복셀 그리드를 처리하여 3D 메시 표현을 구성하는 정점과 면을 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/VoxelToMeshBasic.mdx b/ko/built-in-nodes/VoxelToMeshBasic.mdx index 63bcaab6e..77648f4ca 100644 --- a/ko/built-in-nodes/VoxelToMeshBasic.mdx +++ b/ko/built-in-nodes/VoxelToMeshBasic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VoxelToMeshBasic" icon: "circle" mode: wide --- + VoxelToMeshBasic 노드는 3D 복셀 데이터를 메시 지오메트리로 변환합니다. 임계값을 적용하여 복셀 볼륨 중 어떤 부분이 결과 메시에서 솔리드 표면이 될지를 결정하는 방식으로 복셀 볼륨을 처리합니다. 이 노드는 3D 렌더링 및 모델링에 사용할 수 있는 정점과 면을 포함한 완전한 메시 구조를 출력합니다. ## 입력 diff --git a/ko/built-in-nodes/Wan22FunControlToVideo.mdx b/ko/built-in-nodes/Wan22FunControlToVideo.mdx index 1c627e8cf..0cff3be26 100644 --- a/ko/built-in-nodes/Wan22FunControlToVideo.mdx +++ b/ko/built-in-nodes/Wan22FunControlToVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Wan22FunControlToVideo" icon: "circle" mode: wide --- -# Wan22FunControlToVideo 노드 Wan22FunControlToVideo 노드는 Wan 비디오 모델 아키텍처를 사용하여 비디오 생성을 위한 컨디셔닝 및 잠재 표현을 준비합니다. 이 노드는 양성 및 음성 컨디셔닝 입력과 함께 선택적 참조 이미지 및 제어 비디오를 처리하여 비디오 합성에 필요한 잠재 공간 표현을 생성합니다. 비디오 모델에 적합한 컨디셔닝 데이터를 생성하기 위해 공간적 스케일링과 시간적 차원을 처리합니다. @@ -29,9 +28,9 @@ Wan22FunControlToVideo 노드는 Wan 비디오 모델 아키텍처를 사용하 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 프롬프트` | 연결 잠재, 마스크 및 선택적 참조 잠재를 포함한 비디오별 잠재 데이터가 적용된 수정된 양성 컨디셔닝 | CONDITIONING | -| `잠재 공간` | 연결 잠재, 마스크 및 선택적 참조 잠재를 포함한 비디오별 잠재 데이터가 적용된 수정된 음성 컨디셔닝 | CONDITIONING | -| `latent` | 배치 크기, 잠재 채널 및 공간/시간적 스케일링을 기반으로 비디오 생성에 적합한 차원을 가진 빈 잠재 텐서 | LATENT | +| `긍정 프롬프트` | 연결 잠재, 마스크 및 선택적 참조 잠재를 포함한 비디오별 잠재 데이터가 적용된 수정된 양성 컨디셔닝 | CONDITIONING | +| `부정 프롬프트` | 연결 잠재, 마스크 및 선택적 참조 잠재를 포함한 비디오별 잠재 데이터가 적용된 수정된 음성 컨디셔닝 | CONDITIONING | +| `잠재 공간` | 배치 크기, 잠재 채널 및 공간/시간적 스케일링을 기반으로 비디오 생성에 적합한 차원을 가진 빈 잠재 텐서 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22FunControlToVideo/ko.md) diff --git a/ko/built-in-nodes/Wan22ImageToVideoLatent.mdx b/ko/built-in-nodes/Wan22ImageToVideoLatent.mdx index e783627ba..45ff0f923 100644 --- a/ko/built-in-nodes/Wan22ImageToVideoLatent.mdx +++ b/ko/built-in-nodes/Wan22ImageToVideoLatent.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Wan22ImageToVideoLatent" icon: "circle" mode: wide --- -# Wan22ImageToVideoLatent 노드 Wan22ImageToVideoLatent 노드는 이미지로부터 비디오 잠재 표현을 생성합니다. 지정된 차원으로 빈 비디오 잠재 공간을 생성하고, 선택적으로 시작 이미지 시퀀스를 첫 번째 프레임에 인코딩할 수 있습니다. 시작 이미지가 제공되면 이미지를 잠재 공간으로 인코딩하고 인페인팅된 영역에 대한 해당 노이즈 마스크를 생성합니다. diff --git a/ko/built-in-nodes/Wan2ImageToVideoApi.mdx b/ko/built-in-nodes/Wan2ImageToVideoApi.mdx index 3da2a8e30..e9f8de967 100644 --- a/ko/built-in-nodes/Wan2ImageToVideoApi.mdx +++ b/ko/built-in-nodes/Wan2ImageToVideoApi.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Wan2ImageToVideoApi" icon: "circle" mode: wide --- -# Wan 2.7 이미지-투-비디오 노드 Wan 2.7 이미지-투-비디오 노드는 첫 번째 프레임 이미지를 기준으로 비디오를 생성합니다. 선택적으로 마지막 프레임 이미지를 제공하여 두 이미지 간의 전환을 만들거나, 오디오 파일을 제공하여 비디오의 움직임과 타이밍을 조정할 수 있습니다. 이 노드는 AI 모델을 사용하여 텍스트 설명을 기반으로 장면을 애니메이션화합니다. diff --git a/ko/built-in-nodes/Wan2ReferenceVideoApi.mdx b/ko/built-in-nodes/Wan2ReferenceVideoApi.mdx index 816d365df..8c6f6c77e 100644 --- a/ko/built-in-nodes/Wan2ReferenceVideoApi.mdx +++ b/ko/built-in-nodes/Wan2ReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2ReferenceVideoApi" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan2ReferenceVideoApi/en.md) 이 노드는 제공된 참조 자료를 기반으로 사람이나 사물이 등장하는 비디오를 생성합니다. Wan 2.7 모델을 사용하여 텍스트 프롬프트로부터 비디오를 생성하며, 단일 캐릭터 퍼포먼스와 다중 캐릭터 상호작용을 지원합니다. 생성이 작동하려면 최소한 하나의 참조 비디오 또는 이미지를 제공해야 합니다. diff --git a/ko/built-in-nodes/Wan2TextToVideoApi.mdx b/ko/built-in-nodes/Wan2TextToVideoApi.mdx index 74bfe7cd3..9435d19d2 100644 --- a/ko/built-in-nodes/Wan2TextToVideoApi.mdx +++ b/ko/built-in-nodes/Wan2TextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2TextToVideoApi" icon: "circle" mode: wide --- + 이 문서는 AI가 생성했습니다. 오류를 발견하거나 개선 제안이 있으시면 언제든지 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan2TextToVideoApi/en.md) 이 노드는 Wan 2.7 모델을 사용하여 텍스트 설명으로부터 비디오를 생성합니다. 요청을 외부 API로 전송하며, 해당 API가 프롬프트를 처리하고 비디오 파일을 반환합니다. 선택적으로 오디오 클립을 제공하여 비디오의 움직임과 타이밍에 영향을 줄 수 있습니다. diff --git a/ko/built-in-nodes/Wan2VideoContinuationApi.mdx b/ko/built-in-nodes/Wan2VideoContinuationApi.mdx index 31f92ac04..5c5ac575e 100644 --- a/ko/built-in-nodes/Wan2VideoContinuationApi.mdx +++ b/ko/built-in-nodes/Wan2VideoContinuationApi.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Wan2VideoContinuationApi" icon: "circle" mode: wide --- -# Wan2VideoContinuation 노드 Wan 2.7 비디오 연속 생성 노드는 입력 비디오 클립의 끝부분에서 자연스럽게 이어지는 새로운 비디오 세그먼트를 생성합니다. Wan 2.7 모델을 사용하여 텍스트 프롬프트를 기반으로 연속 영상을 합성하며, 선택적으로 특정 대상 프레임으로 마무리되도록 유도할 수 있습니다. diff --git a/ko/built-in-nodes/Wan2VideoEditApi.mdx b/ko/built-in-nodes/Wan2VideoEditApi.mdx index e6acdd7ab..f09d9e343 100644 --- a/ko/built-in-nodes/Wan2VideoEditApi.mdx +++ b/ko/built-in-nodes/Wan2VideoEditApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2VideoEditApi" icon: "circle" mode: wide --- + Wan2VideoEditApi 노드는 Wan 2.7 모델을 사용하여 텍스트 지침, 참조 이미지 또는 스타일 전송을 기반으로 비디오를 편집합니다. 입력 비디오를 처리하고 해상도, 길이, 화면 비율과 같은 지정된 매개변수에 따라 새 비디오를 생성합니다. ## 입력 diff --git a/ko/built-in-nodes/WanAnimateToVideo.mdx b/ko/built-in-nodes/WanAnimateToVideo.mdx index 2f61afdf1..8b15c454d 100644 --- a/ko/built-in-nodes/WanAnimateToVideo.mdx +++ b/ko/built-in-nodes/WanAnimateToVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanAnimateToVideo" icon: "circle" mode: wide --- -# WanAnimateToVideo 노드 WanAnimateToVideo 노드는 포즈 참조, 표정, 배경 요소를 포함한 여러 조건 입력을 결합하여 비디오 콘텐츠를 생성합니다. 다양한 비디오 입력을 처리하여 일관된 애니메이션 시퀀스를 만들며, 프레임 간 시간적 일관성을 유지합니다. 이 노드는 잠재 공간 연산을 처리하며, 모션 패턴을 지속하여 기존 비디오를 확장할 수 있습니다. @@ -45,11 +44,11 @@ WanAnimateToVideo 노드는 포즈 참조, 표정, 배경 요소를 포함한 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 프롬프트` | CLIP 비전 출력, 포즈 비디오 잠재, 얼굴 비디오 픽셀, 연결된 잠재 이미지 및 연결된 마스크를 포함한 추가 비디오 컨텍스트가 적용된 수정된 긍정 조건 | CONDITIONING | -| `잠재 공간` | CLIP 비전 출력, 포즈 비디오 잠재, 얼굴 비디오 픽셀(반전), 연결된 잠재 이미지 및 연결된 마스크를 포함한 추가 비디오 컨텍스트가 적용된 수정된 부정 조건 | CONDITIONING | -| `잠재 공간 트리밍` | [batch_size, 16, latent_length + trim_latent, latent_height, latent_width] 형태의 잠재 공간 형식으로 생성된 비디오 콘텐츠 | LATENT | -| `이미지 트리밍` | 시작 부분에서 제거할 잠재 프레임 수를 나타내는 잠재 공간 트리밍 정보 (참조 이미지 잠재 프레임에 해당) | INT | -| `비디오 프레임 오프셋` | 참조 모션 프레임에 대한 이미지 공간 트리밍 정보로, 시작 부분에서 제거할 이미지 프레임 수를 나타냅니다 | INT | +| `긍정 프롬프트` | CLIP 비전 출력, 포즈 비디오 잠재, 얼굴 비디오 픽셀, 연결된 잠재 이미지 및 연결된 마스크를 포함한 추가 비디오 컨텍스트가 적용된 수정된 긍정 조건 | CONDITIONING | +| `부정 프롬프트` | CLIP 비전 출력, 포즈 비디오 잠재, 얼굴 비디오 픽셀(반전), 연결된 잠재 이미지 및 연결된 마스크를 포함한 추가 비디오 컨텍스트가 적용된 수정된 부정 조건 | CONDITIONING | +| `잠재 공간` | [batch_size, 16, latent_length + trim_latent, latent_height, latent_width] 형태의 잠재 공간 형식으로 생성된 비디오 콘텐츠 | LATENT | +| `잠재 공간 트리밍` | 시작 부분에서 제거할 잠재 프레임 수를 나타내는 잠재 공간 트리밍 정보 (참조 이미지 잠재 프레임에 해당) | INT | +| `이미지 트리밍` | 참조 모션 프레임에 대한 이미지 공간 트리밍 정보로, 시작 부분에서 제거할 이미지 프레임 수를 나타냅니다 | INT | | `비디오 프레임 오프셋` | 청크 단위로 비디오 생성을 계속하기 위한 업데이트된 프레임 오프셋으로, 이전 오프셋에 생성된 길이를 더하여 계산됩니다 | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanAnimateToVideo/ko.md) diff --git a/ko/built-in-nodes/WanCameraEmbedding.mdx b/ko/built-in-nodes/WanCameraEmbedding.mdx index 46caa6257..ea0fe4e8a 100644 --- a/ko/built-in-nodes/WanCameraEmbedding.mdx +++ b/ko/built-in-nodes/WanCameraEmbedding.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanCameraEmbedding" icon: "circle" mode: wide --- + WanCameraEmbedding 노드는 카메라 모션 매개변수를 기반으로 플뤼커 임베딩(Plücker embedding)을 사용하여 카메라 궤적 임베딩을 생성합니다. 다양한 카메라 움직임을 시뮬레이션하는 일련의 카메라 포즈를 생성하고, 이를 비디오 생성 파이프라인에 적합한 임베딩 텐서로 변환합니다. ## 입력 @@ -25,9 +26,9 @@ WanCameraEmbedding 노드는 카메라 모션 매개변수를 기반으로 플 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `너비` | 궤적 시퀀스를 포함하는 생성된 카메라 임베딩 텐서 | TENSOR | -| `높이` | 처리에 사용된 가로 크기 값 | INT | -| `길이` | 처리에 사용된 세로 크기 값 | INT | +| `카메라 임베딩` | 궤적 시퀀스를 포함하는 생성된 카메라 임베딩 텐서 | TENSOR | +| `너비` | 처리에 사용된 가로 크기 값 | INT | +| `높이` | 처리에 사용된 세로 크기 값 | INT | | `길이` | 처리에 사용된 길이 값 | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraEmbedding/ko.md) diff --git a/ko/built-in-nodes/WanCameraImageToVideo.mdx b/ko/built-in-nodes/WanCameraImageToVideo.mdx index e7a38aac0..67941fa3f 100644 --- a/ko/built-in-nodes/WanCameraImageToVideo.mdx +++ b/ko/built-in-nodes/WanCameraImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanCameraImageToVideo" icon: "circle" mode: wide --- + WanCameraImageToVideo 노드는 이미지를 비디오 시퀀스로 변환하여 비디오 생성을 위한 잠재 표현을 생성합니다. 이 노드는 컨디셔닝 입력과 선택적 시작 이미지를 처리하여 비디오 모델과 함께 사용할 수 있는 비디오 잠재 변수를 생성합니다. 또한 향상된 비디오 생성 제어를 위해 카메라 조건과 CLIP 비전 출력을 지원합니다. ## 입력 @@ -28,9 +29,9 @@ WanCameraImageToVideo 노드는 이미지를 비디오 시퀀스로 변환하여 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 프롬프트` | 카메라 조건 및 CLIP 비전 출력이 적용된 수정된 긍정 컨디셔닝 | CONDITIONING | -| `잠재 공간` | 카메라 조건 및 CLIP 비전 출력이 적용된 수정된 부정 컨디셔닝 | CONDITIONING | -| `latent` | 비디오 모델과 함께 사용하기 위해 생성된 비디오 잠재 표현입니다. 잠재 텐서의 차원은 [batch_size, 16, frames, height/8, width/8]이며, 여기서 frames는 ((length - 1) // 4) + 1로 계산됩니다. | LATENT | +| `긍정 프롬프트` | 카메라 조건 및 CLIP 비전 출력이 적용된 수정된 긍정 컨디셔닝 | CONDITIONING | +| `부정 프롬프트` | 카메라 조건 및 CLIP 비전 출력이 적용된 수정된 부정 컨디셔닝 | CONDITIONING | +| `잠재 공간` | 비디오 모델과 함께 사용하기 위해 생성된 비디오 잠재 표현입니다. 잠재 텐서의 차원은 [batch_size, 16, frames, height/8, width/8]이며, 여기서 frames는 ((length - 1) // 4) + 1로 계산됩니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraImageToVideo/ko.md) diff --git a/ko/built-in-nodes/WanContextWindowsManual.mdx b/ko/built-in-nodes/WanContextWindowsManual.mdx index b22a4185c..67306138a 100644 --- a/ko/built-in-nodes/WanContextWindowsManual.mdx +++ b/ko/built-in-nodes/WanContextWindowsManual.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanContextWindowsManual" icon: "circle" mode: wide --- -# WAN 컨텍스트 윈도우(수동) WAN 컨텍스트 윈도우(수동) 노드는 2차원 처리를 수행하는 WAN 계열 모델의 컨텍스트 윈도우를 수동으로 구성할 수 있게 해줍니다. 윈도우 길이, 중첩, 스케줄링 방식 및 융합 기법을 지정하여 샘플링 중에 사용자 정의 컨텍스트 윈도우 설정을 적용합니다. 이를 통해 모델이 서로 다른 컨텍스트 영역에서 정보를 처리하는 방식을 정밀하게 제어할 수 있습니다. diff --git a/ko/built-in-nodes/WanDancerEncodeAudio.mdx b/ko/built-in-nodes/WanDancerEncodeAudio.mdx index 8b49613c6..40e371200 100644 --- a/ko/built-in-nodes/WanDancerEncodeAudio.mdx +++ b/ko/built-in-nodes/WanDancerEncodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerEncodeAudio" icon: "circle" mode: wide --- + ## 개요 이 노드는 오디오 입력을 처리하여 비디오 생성 모델을 안내하는 데 사용할 수 있는 특징을 추출합니다. 템포, 비트 및 기타 음악적 특성을 감지하기 위해 오디오를 분석한 후, 이 정보를 비디오 모델을 컨디셔닝하는 데 적합한 형식으로 패키징하여 생성된 비디오가 오디오와 동기화될 수 있도록 합니다. @@ -21,7 +22,7 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `fps_string` | 처리된 오디오 특징, 계산된 프레임 속도(fps) 및 오디오 주입 스케일을 포함하는 딕셔너리입니다. 이 출력은 비디오 생성 모델을 컨디셔닝하는 데 사용됩니다. | AUDIO_ENCODER_OUTPUT | +| `audio_encoder_output` | 처리된 오디오 특징, 계산된 프레임 속도(fps) 및 오디오 주입 스케일을 포함하는 딕셔너리입니다. 이 출력은 비디오 생성 모델을 컨디셔닝하는 데 사용됩니다. | AUDIO_ENCODER_OUTPUT | | `fps_string` | 오디오 길이와 비디오 프레임 수를 기반으로 계산된 프레임 속도(fps)를 설명하는 텍스트 문자열입니다. 이 문자열은 비디오 모델의 프롬프트에서 사용하기 위한 것입니다. | STRING | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerEncodeAudio/ko.md) diff --git a/ko/built-in-nodes/WanDancerPadKeyframes.mdx b/ko/built-in-nodes/WanDancerPadKeyframes.mdx index f370f9701..74647621f 100644 --- a/ko/built-in-nodes/WanDancerPadKeyframes.mdx +++ b/ko/built-in-nodes/WanDancerPadKeyframes.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanDancerPadKeyframes" icon: "circle" mode: wide --- -# 개요 이 노드는 긴 비디오 생성 과정의 특정 세그먼트에 대한 키프레임 시퀀스를 준비합니다. 입력 이미지 배치와 오디오 트랙을 받아, 오디오 길이를 기준으로 전체 비디오의 총 프레임 수를 계산한 후, 선택한 세그먼트에 입력 이미지를 키프레임으로 분배하고 나머지는 빈 프레임으로 채웁니다. 또한 해당 세그먼트에 대응하는 오디오 부분을 추출합니다. @@ -22,8 +21,8 @@ mode: wide | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `keyframes_mask` | 지정된 세그먼트에 대한 패딩 처리된 키프레임 시퀀스입니다. | IMAGE | -| `audio_segment` | 유효 프레임을 나타내는 마스크입니다(키프레임 위치는 1, 패딩 위치는 0). | MASK | +| `keyframes_sequence` | 지정된 세그먼트에 대한 패딩 처리된 키프레임 시퀀스입니다. | IMAGE | +| `keyframes_mask` | 유효 프레임을 나타내는 마스크입니다(키프레임 위치는 1, 패딩 위치는 0). | MASK | | `audio_segment` | 이 비디오 세그먼트에 해당하는 오디오 세그먼트입니다. | AUDIO | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerPadKeyframes/ko.md) diff --git a/ko/built-in-nodes/WanDancerPadKeyframesList.mdx b/ko/built-in-nodes/WanDancerPadKeyframesList.mdx index b896eb196..51d0e43dd 100644 --- a/ko/built-in-nodes/WanDancerPadKeyframesList.mdx +++ b/ko/built-in-nodes/WanDancerPadKeyframesList.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanDancerPadKeyframesList" icon: "circle" mode: wide --- -# 개요 이 노드는 이미지 시퀀스와 선택적 오디오 트랙을 입력받아 지정된 개수의 패딩된 세그먼트로 분할합니다. 각 세그먼트가 일관된 길이로 패딩되고 유효한 프레임을 나타내는 마스크가 생성되는 비디오 생성을 위한 키프레임 시퀀스를 준비하도록 설계되었습니다. diff --git a/ko/built-in-nodes/WanDancerVideo.mdx b/ko/built-in-nodes/WanDancerVideo.mdx index 47fd8beae..dfed42998 100644 --- a/ko/built-in-nodes/WanDancerVideo.mdx +++ b/ko/built-in-nodes/WanDancerVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerVideo" icon: "circle" mode: wide --- + WanDancerVideo 노드는 WanDancer 모델을 사용한 비디오 생성에 필요한 조건화 데이터와 빈 잠재 텐서를 준비합니다. 시작 이미지, 마스크, CLIP 비전 임베딩 및 오디오 특징과 같은 선택적 입력과 함께 긍정 및 부정 조건화를 결합하여 생성된 비디오를 제어합니다. ## 입력 @@ -32,8 +33,8 @@ WanDancerVideo 노드는 WanDancer 모델을 사용한 비디오 생성에 필 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 추가 데이터(연결된 잠재 텐서, CLIP 비전, 오디오)가 첨부된 긍정 조건화입니다. | CONDITIONING | -| `latent` | 추가 데이터(연결된 잠재 텐서, CLIP 비전, 오디오)가 첨부된 부정 조건화입니다. | CONDITIONING | +| `positive` | 추가 데이터(연결된 잠재 텐서, CLIP 비전, 오디오)가 첨부된 긍정 조건화입니다. | CONDITIONING | +| `negative` | 추가 데이터(연결된 잠재 텐서, CLIP 비전, 오디오)가 첨부된 부정 조건화입니다. | CONDITIONING | | `latent` | 지정된 비디오 길이, 높이 및 너비와 일치하는 차원의 빈 잠재 텐서입니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerVideo/ko.md) diff --git a/ko/built-in-nodes/WanFirstLastFrameToVideo.mdx b/ko/built-in-nodes/WanFirstLastFrameToVideo.mdx index 5d3434e3c..0025d90eb 100644 --- a/ko/built-in-nodes/WanFirstLastFrameToVideo.mdx +++ b/ko/built-in-nodes/WanFirstLastFrameToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFirstLastFrameToVideo" icon: "circle" mode: wide --- + WanFirstLastFrameToVideo 노드는 시작 프레임과 종료 프레임을 텍스트 프롬프트와 결합하여 비디오 컨디셔닝을 생성합니다. 첫 번째 프레임과 마지막 프레임을 인코딩하고, 생성 과정을 안내하는 마스크를 적용하며, 사용 가능한 경우 CLIP 비전 특징을 통합하여 비디오 생성을 위한 잠재 표현을 생성합니다. 이 노드는 지정된 시작점과 종료점 사이에서 일관된 시퀀스를 생성하기 위해 비디오 모델에 대한 긍정 및 부정 컨디셔닝을 모두 준비합니다. ## 입력 @@ -29,8 +30,8 @@ WanFirstLastFrameToVideo 노드는 시작 프레임과 종료 프레임을 텍 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 비디오 프레임 인코딩 및 CLIP 비전 특징이 적용된 긍정 컨디셔닝 | CONDITIONING | -| `latent` | 비디오 프레임 인코딩 및 CLIP 비전 특징이 적용된 부정 컨디셔닝 | CONDITIONING | +| `긍정 조건` | 비디오 프레임 인코딩 및 CLIP 비전 특징이 적용된 긍정 컨디셔닝 | CONDITIONING | +| `부정 조건` | 비디오 프레임 인코딩 및 CLIP 비전 특징이 적용된 부정 컨디셔닝 | CONDITIONING | | `latent` | 지정된 비디오 매개변수와 일치하는 차원의 빈 잠재 텐서 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFirstLastFrameToVideo/ko.md) diff --git a/ko/built-in-nodes/WanFunControlToVideo.mdx b/ko/built-in-nodes/WanFunControlToVideo.mdx index 763502645..ec79610b3 100644 --- a/ko/built-in-nodes/WanFunControlToVideo.mdx +++ b/ko/built-in-nodes/WanFunControlToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFunControlToVideo" icon: "circle" mode: wide --- + 이 노드는 Alibaba Wan Fun Control 모델을 지원하여 비디오 생성을 돕기 위해 추가되었으며, [이 커밋](https://github.com/comfyanonymous/ComfyUI/commit/3661c833bcc41b788a7c9f0e7bc48524f8ee5f82) 이후에 추가되었습니다. - **목적:** Wan 2.1 Fun Control 모델을 사용하여 비디오 생성에 필요한 컨디셔닝 정보를 준비합니다. diff --git a/ko/built-in-nodes/WanFunInpaintToVideo.mdx b/ko/built-in-nodes/WanFunInpaintToVideo.mdx index 18a3a9f2a..4e0af1a12 100644 --- a/ko/built-in-nodes/WanFunInpaintToVideo.mdx +++ b/ko/built-in-nodes/WanFunInpaintToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFunInpaintToVideo" icon: "circle" mode: wide --- + WanFunInpaintToVideo 노드는 시작 이미지와 종료 이미지 사이를 인페인팅하여 비디오 시퀀스를 생성합니다. 양성 및 음성 컨디셔닝과 선택적 프레임 이미지를 입력받아 비디오 잠재 표현을 생성합니다. 이 노드는 구성 가능한 크기 및 길이 매개변수로 비디오 생성을 처리합니다. ## 입력 @@ -26,8 +27,8 @@ WanFunInpaintToVideo 노드는 시작 이미지와 종료 이미지 사이를 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 처리된 양성 컨디셔닝 출력 | CONDITIONING | -| `latent` | 처리된 음성 컨디셔닝 출력 | CONDITIONING | +| `긍정 조건` | 처리된 양성 컨디셔닝 출력 | CONDITIONING | +| `부정 조건` | 처리된 음성 컨디셔닝 출력 | CONDITIONING | | `latent` | 생성된 비디오 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFunInpaintToVideo/ko.md) diff --git a/ko/built-in-nodes/WanHuMoImageToVideo.mdx b/ko/built-in-nodes/WanHuMoImageToVideo.mdx index 234232c36..bb2763e90 100644 --- a/ko/built-in-nodes/WanHuMoImageToVideo.mdx +++ b/ko/built-in-nodes/WanHuMoImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanHuMoImageToVideo" icon: "circle" mode: wide --- + WanHuMoImageToVideo 노드는 비디오 프레임에 대한 잠재 표현을 생성하여 이미지를 비디오 시퀀스로 변환합니다. 이 노드는 컨디셔닝 입력을 처리하며, 참조 이미지와 오디오 임베딩을 통합하여 비디오 생성에 영향을 줄 수 있습니다. 노드는 수정된 컨디셔닝 데이터와 비디오 합성에 적합한 잠재 표현을 출력합니다. ## 입력 @@ -27,9 +28,9 @@ WanHuMoImageToVideo 노드는 비디오 프레임에 대한 잠재 표현을 생 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 프롬프트` | 참조 이미지 및/또는 오디오 임베딩이 통합된 수정된 긍정 컨디셔닝입니다. | CONDITIONING | -| `잠재 공간` | 참조 이미지 및/또는 오디오 임베딩이 통합된 수정된 부정 컨디셔닝입니다. | CONDITIONING | -| `latent` | 비디오 시퀀스 데이터를 포함하는 생성된 잠재 표현입니다. | LATENT | +| `긍정 프롬프트` | 참조 이미지 및/또는 오디오 임베딩이 통합된 수정된 긍정 컨디셔닝입니다. | CONDITIONING | +| `부정 프롬프트` | 참조 이미지 및/또는 오디오 임베딩이 통합된 수정된 부정 컨디셔닝입니다. | CONDITIONING | +| `잠재 공간` | 비디오 시퀀스 데이터를 포함하는 생성된 잠재 표현입니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanHuMoImageToVideo/ko.md) diff --git a/ko/built-in-nodes/WanImageToImageApi.mdx b/ko/built-in-nodes/WanImageToImageApi.mdx index 8a7835a97..494c75864 100644 --- a/ko/built-in-nodes/WanImageToImageApi.mdx +++ b/ko/built-in-nodes/WanImageToImageApi.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanImageToImageApi" icon: "circle" mode: wide --- -# Wan Image to Image 노드 Wan Image to Image 노드는 하나 또는 두 개의 입력 이미지와 텍스트 프롬프트로부터 이미지를 생성합니다. 사용자가 제공한 설명에 따라 입력 이미지를 변환하여 원본 입력의 종횡비를 유지하는 새 이미지를 만듭니다. 출력 이미지는 입력 크기와 관계없이 160만 화소로 고정됩니다. diff --git a/ko/built-in-nodes/WanImageToVideo.mdx b/ko/built-in-nodes/WanImageToVideo.mdx index a47000a70..d45cc5bee 100644 --- a/ko/built-in-nodes/WanImageToVideo.mdx +++ b/ko/built-in-nodes/WanImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToVideo" icon: "circle" mode: wide --- + WanImageToVideo 노드는 비디오 생성 작업을 위한 컨디셔닝 및 잠재 표현을 준비합니다. 비디오 생성을 위한 빈 잠재 공간을 생성하며, 선택적으로 시작 이미지와 CLIP 비전 출력을 통합하여 비디오 생성 과정을 안내할 수 있습니다. 이 노드는 제공된 이미지와 비전 데이터를 기반으로 양수 및 음수 컨디셔닝 입력을 모두 수정합니다. ## 입력 @@ -27,9 +28,9 @@ WanImageToVideo 노드는 비디오 생성 작업을 위한 컨디셔닝 및 잠 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 이미지 및 비전 데이터가 통합된 수정된 양수 컨디셔닝 | CONDITIONING | -| `잠재 비디오` | 이미지 및 비전 데이터가 통합된 수정된 음수 컨디셔닝 | CONDITIONING | -| `latent` | 비디오 생성을 위해 준비된 빈 잠재 공간 텐서 | LATENT | +| `긍정 조건` | 이미지 및 비전 데이터가 통합된 수정된 양수 컨디셔닝 | CONDITIONING | +| `부정 조건` | 이미지 및 비전 데이터가 통합된 수정된 음수 컨디셔닝 | CONDITIONING | +| `잠재 비디오` | 비디오 생성을 위해 준비된 빈 잠재 공간 텐서 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToVideo/ko.md) diff --git a/ko/built-in-nodes/WanImageToVideoApi.mdx b/ko/built-in-nodes/WanImageToVideoApi.mdx index b785c587e..28de4dceb 100644 --- a/ko/built-in-nodes/WanImageToVideoApi.mdx +++ b/ko/built-in-nodes/WanImageToVideoApi.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanImageToVideoApi" icon: "circle" mode: wide --- -# Wan 이미지-투-비디오 노드 Wan 이미지-투-비디오 노드는 단일 입력 이미지와 텍스트 프롬프트로부터 비디오를 생성합니다. 제공된 이미지를 첫 번째 프레임으로 사용하고 설명에 기반하여 비디오 시퀀스를 생성하며, 해상도, 지속 시간, 오디오 및 기타 고급 설정 옵션을 제공합니다. diff --git a/ko/built-in-nodes/WanInfiniteTalkToVideo.mdx b/ko/built-in-nodes/WanInfiniteTalkToVideo.mdx index ebdb944c7..150721147 100644 --- a/ko/built-in-nodes/WanInfiniteTalkToVideo.mdx +++ b/ko/built-in-nodes/WanInfiniteTalkToVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanInfiniteTalkToVideo" icon: "circle" mode: wide --- -# WanInfiniteTalkToVideo 노드 WanInfiniteTalkToVideo 노드는 오디오 입력으로부터 비디오 시퀀스를 생성합니다. 이 노드는 하나 또는 두 명의 화자로부터 추출된 오디오 특징을 조건으로 하는 비디오 확산 모델을 사용하여 토킹 헤드 비디오의 잠재 표현을 생성합니다. 새로운 시퀀스를 생성하거나 이전 프레임을 모션 컨텍스트로 사용하여 기존 시퀀스를 확장할 수 있습니다. @@ -43,10 +42,10 @@ WanInfiniteTalkToVideo 노드는 오디오 입력으로부터 비디오 시퀀 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `positive` | 오디오 조건이 적용된 패치된 모델입니다. | MODEL | -| `negative` | 추가 컨텍스트(예: 시작 이미지, CLIP 비전)로 수정될 수 있는 긍정 조건입니다. | CONDITIONING | -| `latent` | 추가 컨텍스트로 수정될 수 있는 부정 조건입니다. | CONDITIONING | -| `trim_image` | 잠재 공간에서 생성된 비디오 시퀀스입니다. | LATENT | +| `model` | 오디오 조건이 적용된 패치된 모델입니다. | MODEL | +| `positive` | 추가 컨텍스트(예: 시작 이미지, CLIP 비전)로 수정될 수 있는 긍정 조건입니다. | CONDITIONING | +| `negative` | 추가 컨텍스트로 수정될 수 있는 부정 조건입니다. | CONDITIONING | +| `latent` | 잠재 공간에서 생성된 비디오 시퀀스입니다. | LATENT | | `trim_image` | 시퀀스 확장 시 모션 컨텍스트 시작 부분에서 제거해야 하는 프레임 수입니다. | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanInfiniteTalkToVideo/ko.md) diff --git a/ko/built-in-nodes/WanMoveConcatTrack.mdx b/ko/built-in-nodes/WanMoveConcatTrack.mdx index 75041f9a6..02c2a2c2f 100644 --- a/ko/built-in-nodes/WanMoveConcatTrack.mdx +++ b/ko/built-in-nodes/WanMoveConcatTrack.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveConcatTrack" icon: "circle" mode: wide --- + WanMoveConcatTrack 노드는 두 세트의 모션 트래킹 데이터를 하나의 더 긴 시퀀스로 결합합니다. 이 노드는 입력된 트랙의 경로와 가시성 마스크를 각각의 차원을 따라 연결하여 작동합니다. 하나의 트랙 입력만 제공된 경우, 해당 데이터를 변경 없이 그대로 전달합니다. ## 입력 diff --git a/ko/built-in-nodes/WanMoveTrackToVideo.mdx b/ko/built-in-nodes/WanMoveTrackToVideo.mdx index e3566dfab..6b3192432 100644 --- a/ko/built-in-nodes/WanMoveTrackToVideo.mdx +++ b/ko/built-in-nodes/WanMoveTrackToVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanMoveTrackToVideo" icon: "circle" mode: wide --- -# WanMoveTrackToVideo 노드 WanMoveTrackToVideo 노드는 비디오 생성을 위한 컨디셔닝 및 잠재 공간 데이터를 준비하며, 선택적으로 모션 트래킹 정보를 통합합니다. 시작 이미지 시퀀스를 잠재 표현으로 인코딩하고, 객체 트랙의 위치 데이터를 혼합하여 생성된 비디오의 움직임을 안내할 수 있습니다. 이 노드는 수정된 포지티브 및 네거티브 컨디셔닝과 함께 비디오 모델에 사용할 준비가 된 빈 잠재 텐서를 출력합니다. @@ -31,8 +30,8 @@ WanMoveTrackToVideo 노드는 비디오 생성을 위한 컨디셔닝 및 잠재 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 수정된 포지티브 컨디셔닝으로, `concat_latent_image`, `concat_mask` 및 `clip 비전 출력`을 포함할 수 있습니다. | CONDITIONING | -| `latent` | 수정된 네거티브 컨디셔닝으로, `concat_latent_image`, `concat_mask` 및 `clip 비전 출력`을 포함할 수 있습니다. | CONDITIONING | +| `positive` | 수정된 포지티브 컨디셔닝으로, `concat_latent_image`, `concat_mask` 및 `clip 비전 출력`을 포함할 수 있습니다. | CONDITIONING | +| `negative` | 수정된 네거티브 컨디셔닝으로, `concat_latent_image`, `concat_mask` 및 `clip 비전 출력`을 포함할 수 있습니다. | CONDITIONING | | `latent` | `배치 크기`, `길이`, `높이` 및 `너비` 입력에 의해 차원이 결정된 빈 잠재 텐서입니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTrackToVideo/ko.md) diff --git a/ko/built-in-nodes/WanMoveTracksFromCoords.mdx b/ko/built-in-nodes/WanMoveTracksFromCoords.mdx index 6867ed076..04f6c3675 100644 --- a/ko/built-in-nodes/WanMoveTracksFromCoords.mdx +++ b/ko/built-in-nodes/WanMoveTracksFromCoords.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanMoveTracksFromCoords" icon: "circle" mode: wide --- -# WanMoveTracksFromCoords WanMoveTracksFromCoords 노드는 JSON 형식의 좌표 문자열로부터 모션 트랙을 생성합니다. 좌표 데이터를 다른 비디오 처리 노드에서 사용할 수 있는 텐서 형식으로 변환하며, 선택적으로 마스크를 적용하여 시간에 따른 트랙의 가시성을 제어할 수 있습니다. @@ -23,7 +22,7 @@ WanMoveTracksFromCoords 노드는 JSON 형식의 좌표 문자열로부터 모 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | | `트랙 길이` | 생성된 트랙 데이터로, 각 트랙의 경로 좌표와 가시성 정보를 포함합니다. | TRACKS | -| `track_length` | 생성된 트랙의 총 프레임 수입니다. | INT | +| `트랙 길이` | 생성된 트랙의 총 프레임 수입니다. | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTracksFromCoords/ko.md) diff --git a/ko/built-in-nodes/WanMoveVisualizeTracks.mdx b/ko/built-in-nodes/WanMoveVisualizeTracks.mdx index 091d30ee5..e3cb56738 100644 --- a/ko/built-in-nodes/WanMoveVisualizeTracks.mdx +++ b/ko/built-in-nodes/WanMoveVisualizeTracks.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanMoveVisualizeTracks" icon: "circle" mode: wide --- -# WanMoveVisualizeTracks WanMoveVisualizeTracks 노드는 이미지 시퀀스 또는 비디오 프레임 위에 모션 트래킹 데이터를 오버레이합니다. 트래킹된 포인트의 이동 경로와 현재 위치를 시각적으로 표현하여 모션 데이터를 눈으로 확인하고 분석하기 쉽게 만듭니다. diff --git a/ko/built-in-nodes/WanPhantomSubjectToVideo.mdx b/ko/built-in-nodes/WanPhantomSubjectToVideo.mdx index 3f9a33b5d..34d02a922 100644 --- a/ko/built-in-nodes/WanPhantomSubjectToVideo.mdx +++ b/ko/built-in-nodes/WanPhantomSubjectToVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanPhantomSubjectToVideo" icon: "circle" mode: wide --- -# WanPhantomSubjectToVideo 노드 WanPhantomSubjectToVideo 노드는 컨디셔닝 입력과 선택적 참조 이미지를 처리하여 비디오 콘텐츠를 생성합니다. 비디오 생성에 필요한 잠재 표현을 만들며, 입력 이미지가 제공될 경우 시각적 안내를 통합할 수 있습니다. 이 노드는 비디오 모델을 위한 시간 차원 연결이 적용된 컨디셔닝 데이터를 준비하고, 수정된 컨디셔닝과 함께 생성된 잠재 비디오 데이터를 출력합니다. @@ -28,10 +27,10 @@ WanPhantomSubjectToVideo 노드는 컨디셔닝 입력과 선택적 참조 이 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `네거티브 텍스트` | 이미지 제공 시 시간 차원 연결이 적용된 수정된 긍정 컨디셔닝 | CONDITIONING | -| `네거티브 이미지 텍스트` | 이미지 제공 시 시간 차원 연결이 적용된 수정된 부정 컨디셔닝 | CONDITIONING | -| `잠재` | 이미지 제공 시 시간 차원 연결이 0으로 설정된 부정 컨디셔닝 | CONDITIONING | -| `latent` | 지정된 차원과 길이로 생성된 잠재 비디오 표현 | LATENT | +| `포지티브` | 이미지 제공 시 시간 차원 연결이 적용된 수정된 긍정 컨디셔닝 | CONDITIONING | +| `네거티브 텍스트` | 이미지 제공 시 시간 차원 연결이 적용된 수정된 부정 컨디셔닝 | CONDITIONING | +| `네거티브 이미지 텍스트` | 이미지 제공 시 시간 차원 연결이 0으로 설정된 부정 컨디셔닝 | CONDITIONING | +| `잠재` | 지정된 차원과 길이로 생성된 잠재 비디오 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanPhantomSubjectToVideo/ko.md) diff --git a/ko/built-in-nodes/WanReferenceVideoApi.mdx b/ko/built-in-nodes/WanReferenceVideoApi.mdx index a8f45864c..d6e2b4780 100644 --- a/ko/built-in-nodes/WanReferenceVideoApi.mdx +++ b/ko/built-in-nodes/WanReferenceVideoApi.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanReferenceVideoApi" icon: "circle" mode: wide --- -# Wan 참조 영상 API 노드 Wan 참조 영상(Reference to Video) 노드는 하나 이상의 입력 참조 영상에서 시각적 외형과 음성을 사용하여 텍스트 프롬프트와 함께 새로운 영상을 생성합니다. 사용자의 설명에 기반하여 새로운 콘텐츠를 만들면서 참조 자료의 캐릭터와 일관성을 유지합니다. diff --git a/ko/built-in-nodes/WanSCAILToVideo.mdx b/ko/built-in-nodes/WanSCAILToVideo.mdx index cd6400b86..f04660813 100644 --- a/ko/built-in-nodes/WanSCAILToVideo.mdx +++ b/ko/built-in-nodes/WanSCAILToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSCAILToVideo" icon: "circle" mode: wide --- + WanSCAILToVideo 노드는 비디오 생성을 위한 컨디셔닝과 빈 잠재 공간을 준비합니다. 참조 이미지, 포즈 비디오, CLIP 비전 출력과 같은 선택적 입력을 처리하여 비디오 모델의 포지티브 및 네거티브 컨디셔닝에 임베딩합니다. 이 노드는 수정된 컨디셔닝과 지정된 비디오 크기의 빈 잠재 텐서를 출력합니다. ## 입력 @@ -31,8 +32,8 @@ WanSCAILToVideo 노드는 비디오 생성을 위한 컨디셔닝과 빈 잠재 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `negative` | 수정된 포지티브 컨디셔닝으로, 참조 이미지 잠재, CLIP 비전 출력 또는 포즈 비디오 잠재가 포함될 수 있습니다. | CONDITIONING | -| `latent` | 수정된 네거티브 컨디셔닝으로, 참조 이미지 잠재, CLIP 비전 출력 또는 포즈 비디오 잠재가 포함될 수 있습니다. | CONDITIONING | +| `positive` | 수정된 포지티브 컨디셔닝으로, 참조 이미지 잠재, CLIP 비전 출력 또는 포즈 비디오 잠재가 포함될 수 있습니다. | CONDITIONING | +| `negative` | 수정된 네거티브 컨디셔닝으로, 참조 이미지 잠재, CLIP 비전 출력 또는 포즈 비디오 잠재가 포함될 수 있습니다. | CONDITIONING | | `latent` | `[batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8]` 형태의 빈 잠재 텐서입니다. | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSCAILToVideo/ko.md) diff --git a/ko/built-in-nodes/WanSoundImageToVideo.mdx b/ko/built-in-nodes/WanSoundImageToVideo.mdx index 42fa04a2e..9c9e9b1d3 100644 --- a/ko/built-in-nodes/WanSoundImageToVideo.mdx +++ b/ko/built-in-nodes/WanSoundImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSoundImageToVideo" icon: "circle" mode: wide --- + WanSoundImageToVideo 노드는 오디오 컨디셔닝을 선택적으로 적용하여 이미지로부터 비디오 콘텐츠를 생성합니다. 포지티브 및 네거티브 컨디셔닝 프롬프트와 VAE 모델을 입력받아 비디오 잠재 표현을 생성하며, 참조 이미지, 오디오 인코딩, 제어 비디오 및 모션 참조를 활용하여 비디오 생성 과정을 안내할 수 있습니다. ## 입력 @@ -27,9 +28,9 @@ WanSoundImageToVideo 노드는 오디오 컨디셔닝을 선택적으로 적용 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 프롬프트` | 비디오 생성을 위해 수정된 처리된 포지티브 컨디셔닝입니다 | CONDITIONING | -| `잠재 공간` | 비디오 생성을 위해 수정된 처리된 네거티브 컨디셔닝입니다 | CONDITIONING | -| `latent` | 최종 비디오 프레임으로 디코딩될 수 있는 잠재 공간에서 생성된 비디오 표현입니다 | LATENT | +| `긍정 프롬프트` | 비디오 생성을 위해 수정된 처리된 포지티브 컨디셔닝입니다 | CONDITIONING | +| `부정 프롬프트` | 비디오 생성을 위해 수정된 처리된 네거티브 컨디셔닝입니다 | CONDITIONING | +| `잠재 공간` | 최종 비디오 프레임으로 디코딩될 수 있는 잠재 공간에서 생성된 비디오 표현입니다 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideo/ko.md) diff --git a/ko/built-in-nodes/WanSoundImageToVideoExtend.mdx b/ko/built-in-nodes/WanSoundImageToVideoExtend.mdx index d5e65b2f3..a3ce60e7a 100644 --- a/ko/built-in-nodes/WanSoundImageToVideoExtend.mdx +++ b/ko/built-in-nodes/WanSoundImageToVideoExtend.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanSoundImageToVideoExtend" icon: "circle" mode: wide --- -# WanSoundImageToVideoExtend 노드 WanSoundImageToVideoExtend 노드는 기존 비디오 잠재 표현에 추가 프레임을 생성하여 비디오를 확장합니다. 선택적으로 오디오, 참조 이미지 및 제어 비디오의 안내를 받을 수 있습니다. 시작 비디오 잠재 표현을 입력받아 제공된 조건화 및 오디오 신호를 활용하여 더 긴 비디오 시퀀스를 생성합니다. @@ -26,9 +25,9 @@ WanSoundImageToVideoExtend 노드는 기존 비디오 잠재 표현에 추가 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 프롬프트` | 비디오 컨텍스트가 적용된 처리된 긍정 조건화 | CONDITIONING | -| `잠재 공간` | 비디오 컨텍스트가 적용된 처리된 부정 조건화 | CONDITIONING | -| `latent` | 확장된 비디오 시퀀스를 포함하는 생성된 비디오 잠재 표현 | LATENT | +| `긍정 프롬프트` | 비디오 컨텍스트가 적용된 처리된 긍정 조건화 | CONDITIONING | +| `부정 프롬프트` | 비디오 컨텍스트가 적용된 처리된 부정 조건화 | CONDITIONING | +| `잠재 공간` | 확장된 비디오 시퀀스를 포함하는 생성된 비디오 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideoExtend/ko.md) diff --git a/ko/built-in-nodes/WanTextToImageApi.mdx b/ko/built-in-nodes/WanTextToImageApi.mdx index 1c9a630c5..a32273a4e 100644 --- a/ko/built-in-nodes/WanTextToImageApi.mdx +++ b/ko/built-in-nodes/WanTextToImageApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTextToImageApi" icon: "circle" mode: wide --- + Wan Text to Image 노드는 텍스트 설명을 기반으로 이미지를 생성합니다. AI 모델을 사용하여 작성된 프롬프트로부터 시각적 콘텐츠를 만들며, 영어와 중국어 텍스트 입력을 모두 지원합니다. 이 노드는 출력 이미지의 크기, 품질 및 스타일 선호도를 조정할 수 있는 다양한 제어 기능을 제공합니다. ## 입력 diff --git a/ko/built-in-nodes/WanTextToVideoApi.mdx b/ko/built-in-nodes/WanTextToVideoApi.mdx index 5025b5ee3..fd05a12c6 100644 --- a/ko/built-in-nodes/WanTextToVideoApi.mdx +++ b/ko/built-in-nodes/WanTextToVideoApi.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WanTextToVideoApi" icon: "circle" mode: wide --- -# Wan 텍스트-투-비디오 노드 Wan 텍스트-투-비디오 노드는 텍스트 설명을 기반으로 비디오 콘텐츠를 생성합니다. AI 모델을 사용하여 프롬프트로부터 비디오를 생성하며, 다양한 비디오 크기, 길이 및 선택적 오디오 입력을 지원합니다. 이 노드는 필요 시 오디오를 자동으로 생성할 수 있으며, 프롬프트 향상 및 워터마킹 옵션을 제공합니다. diff --git a/ko/built-in-nodes/WanTrackToVideo.mdx b/ko/built-in-nodes/WanTrackToVideo.mdx index f5ecd5b38..d8850e0ed 100644 --- a/ko/built-in-nodes/WanTrackToVideo.mdx +++ b/ko/built-in-nodes/WanTrackToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTrackToVideo" icon: "circle" mode: wide --- + WanTrackToVideo 노드는 트랙 포인트를 처리하고 해당 비디오 프레임을 생성하여 모션 트래킹 데이터를 비디오 시퀀스로 변환합니다. 트래킹 좌표를 입력으로 받아 비디오 생성에 사용할 수 있는 비디오 컨디셔닝 및 잠재 표현을 생성합니다. 트랙이 제공되지 않으면 표준 이미지-투-비디오 변환으로 대체됩니다. ## 입력 @@ -30,9 +31,9 @@ WanTrackToVideo 노드는 트랙 포인트를 처리하고 해당 비디오 프 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정` | 모션 트랙 정보가 적용된 포지티브 컨디셔닝 | CONDITIONING | -| `잠재` | 모션 트랙 정보가 적용된 네거티브 컨디셔닝 | CONDITIONING | -| `latent` | 생성된 비디오 잠재 표현 | LATENT | +| `긍정` | 모션 트랙 정보가 적용된 포지티브 컨디셔닝 | CONDITIONING | +| `부정` | 모션 트랙 정보가 적용된 네거티브 컨디셔닝 | CONDITIONING | +| `잠재` | 생성된 비디오 잠재 표현 | LATENT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTrackToVideo/ko.md) diff --git a/ko/built-in-nodes/WanVaceToVideo.mdx b/ko/built-in-nodes/WanVaceToVideo.mdx index a982b5fb3..a2a689883 100644 --- a/ko/built-in-nodes/WanVaceToVideo.mdx +++ b/ko/built-in-nodes/WanVaceToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanVaceToVideo" icon: "circle" mode: wide --- + WanVaceToVideo 노드는 비디오 생성 모델을 위한 비디오 컨디셔닝 데이터를 처리합니다. 이 노드는 긍정 및 부정 컨디셔닝 입력과 비디오 제어 데이터를 받아 비디오 생성을 위한 잠재 표현을 준비합니다. 또한 비디오 업스케일링, 마스킹 및 VAE 인코딩을 처리하여 비디오 모델에 적합한 컨디셔닝 구조를 생성합니다. ## 입력 @@ -29,10 +30,10 @@ WanVaceToVideo 노드는 비디오 생성 모델을 위한 비디오 컨디셔 | 출력 이름 | 설명 | 데이터 타입 | | --- | --- | --- | -| `부정 조건` | 비디오 제어 데이터가 적용된 긍정 컨디셔닝 | CONDITIONING | -| `잠재 비디오` | 비디오 제어 데이터가 적용된 부정 컨디셔닝 | CONDITIONING | -| `잘린 잠재 비디오` | 비디오 생성을 위해 준비된 빈 잠재 텐서 | LATENT | -| `trim_latent` | 참조 이미지 사용 시 제거할 잠재 프레임 수 | INT | +| `긍정 조건` | 비디오 제어 데이터가 적용된 긍정 컨디셔닝 | CONDITIONING | +| `부정 조건` | 비디오 제어 데이터가 적용된 부정 컨디셔닝 | CONDITIONING | +| `잠재 비디오` | 비디오 생성을 위해 준비된 빈 잠재 텐서 | LATENT | +| `잘린 잠재 비디오` | 참조 이미지 사용 시 제거할 잠재 프레임 수 | INT | > 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanVaceToVideo/ko.md) diff --git a/ko/built-in-nodes/WavespeedFlashVSRNode.mdx b/ko/built-in-nodes/WavespeedFlashVSRNode.mdx index 73c31e1c2..38cf13fcd 100644 --- a/ko/built-in-nodes/WavespeedFlashVSRNode.mdx +++ b/ko/built-in-nodes/WavespeedFlashVSRNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WavespeedFlashVSRNode" icon: "circle" mode: wide --- + WavespeedFlashVSRNode는 저해상도 또는 흐릿한 영상의 해상도를 높이고 선명도를 복원하는 빠르고 고품질의 비디오 업스케일러입니다. 비디오 입력을 처리하여 사용자가 선택한 더 높은 해상도의 새 비디오를 출력합니다. ## 입력 diff --git a/ko/built-in-nodes/WavespeedImageUpscaleNode.mdx b/ko/built-in-nodes/WavespeedImageUpscaleNode.mdx index 02150269c..b30ee9600 100644 --- a/ko/built-in-nodes/WavespeedImageUpscaleNode.mdx +++ b/ko/built-in-nodes/WavespeedImageUpscaleNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WavespeedImageUpscaleNode" icon: "circle" mode: wide --- -# WaveSpeed 이미지 업스케일 노드 WaveSpeed 이미지 업스케일 노드는 외부 AI 서비스를 사용하여 이미지의 해상도와 품질을 향상시킵니다. 단일 입력 사진을 받아 2K, 4K 또는 8K와 같은 더 높은 목표 해상도로 업스케일하여 더 선명하고 세부적인 결과물을 생성합니다. diff --git a/ko/built-in-nodes/WebcamCapture.mdx b/ko/built-in-nodes/WebcamCapture.mdx index 151bf643f..819b3a9aa 100644 --- a/ko/built-in-nodes/WebcamCapture.mdx +++ b/ko/built-in-nodes/WebcamCapture.mdx @@ -5,7 +5,6 @@ sidebarTitle: "WebcamCapture" icon: "circle" mode: wide --- -# WebcamCapture 노드 WebcamCapture 노드는 웹캠 장치에서 이미지를 캡처하여 ComfyUI 워크플로 내에서 사용할 수 있는 형식으로 변환합니다. 이 노드는 LoadImage 노드를 상속받으며, 캡처 크기와 타이밍을 제어하는 옵션을 제공합니다. 활성화되면 워크플로 큐가 처리될 때마다 새로운 이미지를 캡처할 수 있습니다. diff --git a/ko/built-in-nodes/ZImageFunControlnet.mdx b/ko/built-in-nodes/ZImageFunControlnet.mdx index a1fdc3ced..3c8bf070b 100644 --- a/ko/built-in-nodes/ZImageFunControlnet.mdx +++ b/ko/built-in-nodes/ZImageFunControlnet.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ZImageFunControlnet" icon: "circle" mode: wide --- -# ZImageFunControlnet 노드 ZImageFunControlnet 노드는 특수화된 제어 네트워크를 적용하여 이미지 생성 또는 편집 과정에 영향을 줍니다. 기본 모델, 모델 패치 및 VAE를 사용하며, 제어 효과의 강도를 조정할 수 있습니다. 이 노드는 기본 이미지, 인페인팅 이미지 및 마스크와 함께 작동하여 보다 정밀한 편집이 가능합니다. diff --git a/ko/built-in-nodes/unCLIPCheckpointLoader.mdx b/ko/built-in-nodes/unCLIPCheckpointLoader.mdx index 81f8f4a93..d9e1633d1 100644 --- a/ko/built-in-nodes/unCLIPCheckpointLoader.mdx +++ b/ko/built-in-nodes/unCLIPCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "unCLIPCheckpointLoader" icon: "circle" mode: wide --- + 이 노드는 `ComfyUI/models/checkpoints` 폴더에 있는 모델을 감지하며, extra_model_paths.yaml 파일에 구성된 추가 경로의 모델도 읽어옵니다. 때로는 **ComfyUI 인터페이스를 새로고침**하여 해당 폴더에서 모델 파일을 읽도록 해야 할 수도 있습니다. unCLIPCheckpointLoader 노드는 unCLIP 모델에 특화된 체크포인트를 로드하도록 설계되었습니다. 지정된 체크포인트에서 모델, CLIP 비전 모듈 및 VAE를 검색하고 초기화하는 기능을 제공하여, 추가 작업이나 분석을 위한 설정 과정을 간소화합니다. diff --git a/ko/built-in-nodes/unCLIPConditioning.mdx b/ko/built-in-nodes/unCLIPConditioning.mdx index 50e40c21b..424618ffa 100644 --- a/ko/built-in-nodes/unCLIPConditioning.mdx +++ b/ko/built-in-nodes/unCLIPConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "unCLIPConditioning" icon: "circle" mode: wide --- + 이 노드는 CLIP 비전 출력을 컨디셔닝 과정에 통합하여, 지정된 강도 및 노이즈 증강 매개변수에 따라 이러한 출력의 영향을 조정합니다. 시각적 맥락으로 컨디셔닝을 풍부하게 하여 생성 과정을 향상시킵니다. ## 입력 diff --git a/ko/built-in-nodes/wanBlockSwap.mdx b/ko/built-in-nodes/wanBlockSwap.mdx index 636dff312..2f4807bbb 100644 --- a/ko/built-in-nodes/wanBlockSwap.mdx +++ b/ko/built-in-nodes/wanBlockSwap.mdx @@ -5,6 +5,7 @@ sidebarTitle: "wanBlockSwap" icon: "circle" mode: wide --- + 이 노드는 더 이상 사용되지 않으며 아무 기능도 수행하지 않습니다. 모델을 입력으로 받아 변경 없이 동일한 모델을 반환합니다. "NOP"라는 설명은 아무 작업도 수행하지 않음을 나타냅니다. ## 입력 diff --git a/zh/built-in-nodes/APG.mdx b/zh/built-in-nodes/APG.mdx index f32c349d3..2f67fc9b5 100644 --- a/zh/built-in-nodes/APG.mdx +++ b/zh/built-in-nodes/APG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "APG" icon: "circle" mode: wide --- + APG（自适应投影引导）节点通过调整扩散过程中的引导应用方式来修改采样过程。它将引导向量相对于条件输出分解为平行分量和正交分量，从而实现更可控的图像生成。该节点提供参数来缩放引导、归一化其幅度，并应用动量以实现扩散步骤之间更平滑的过渡。 ## 输入 diff --git a/zh/built-in-nodes/ARVideoI2V.mdx b/zh/built-in-nodes/ARVideoI2V.mdx index def947f0e..b6a1fcff2 100644 --- a/zh/built-in-nodes/ARVideoI2V.mdx +++ b/zh/built-in-nodes/ARVideoI2V.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ARVideoI2V" icon: "circle" mode: wide --- + ## 概述 此节点为 AR（自回归）视频模型准备图像到视频的生成配置。它接收起始图像，使用 VAE 将其编码到潜在空间中，并将编码后的图像存储在模型配置中。这使得视频采样过程能够将该图像用作第一帧，从而在不依赖独立图像到视频模型架构的情况下有效引导生成过程。 diff --git a/zh/built-in-nodes/AddNoise.mdx b/zh/built-in-nodes/AddNoise.mdx index 664d076bf..7b1f2f73b 100644 --- a/zh/built-in-nodes/AddNoise.mdx +++ b/zh/built-in-nodes/AddNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddNoise" icon: "circle" mode: wide --- + 此节点使用指定的噪声生成器和 sigma 值向潜在图像添加受控噪声。它通过模型的采样系统处理输入，以应用适用于给定 sigma 范围的噪声缩放，并返回添加噪声后的新潜在表示。 ## 输入 diff --git a/zh/built-in-nodes/AddTextPrefix.mdx b/zh/built-in-nodes/AddTextPrefix.mdx index 746088b13..70ccc4513 100644 --- a/zh/built-in-nodes/AddTextPrefix.mdx +++ b/zh/built-in-nodes/AddTextPrefix.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddTextPrefix" icon: "circle" mode: wide --- + 添加文本前缀节点通过将指定字符串添加到每个输入文本的开头来修改文本。该节点接收文本和前缀作为输入，然后返回合并后的结果。 ## 输入 @@ -18,7 +19,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `text` | 在前端添加了前缀的结果文本。 | STRING | +| `文本` | 在前端添加了前缀的结果文本。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextPrefix/zh.md) diff --git a/zh/built-in-nodes/AddTextSuffix.mdx b/zh/built-in-nodes/AddTextSuffix.mdx index f94997d75..5bccebb1c 100644 --- a/zh/built-in-nodes/AddTextSuffix.mdx +++ b/zh/built-in-nodes/AddTextSuffix.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AddTextSuffix" icon: "circle" mode: wide --- + 此节点将指定的后缀附加到输入文本字符串的末尾。它接收原始文本和后缀作为输入，然后返回组合后的结果。 ## 输入 @@ -18,7 +19,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `text` | 附加后缀后得到的结果文本。 | STRING | +| `文本` | 附加后缀后得到的结果文本。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AddTextSuffix/zh.md) diff --git a/zh/built-in-nodes/AdjustBrightness.mdx b/zh/built-in-nodes/AdjustBrightness.mdx index 68cdbf252..d76fb5580 100644 --- a/zh/built-in-nodes/AdjustBrightness.mdx +++ b/zh/built-in-nodes/AdjustBrightness.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AdjustBrightness" icon: "circle" mode: wide --- + ## 概述 调整亮度节点用于修改输入图像的亮度。其工作原理是将每个像素的值乘以指定的系数，然后将结果值限制在有效范围内。系数为 1.0 时图像保持不变，低于 1.0 时图像变暗，高于 1.0 时图像变亮。 @@ -20,7 +21,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `image` | 调整亮度后的输出图像。 | IMAGE | +| `图像` | 调整亮度后的输出图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustBrightness/zh.md) diff --git a/zh/built-in-nodes/AdjustContrast.mdx b/zh/built-in-nodes/AdjustContrast.mdx index cac927c66..6bae810f7 100644 --- a/zh/built-in-nodes/AdjustContrast.mdx +++ b/zh/built-in-nodes/AdjustContrast.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AdjustContrast" icon: "circle" mode: wide --- + 调整对比度节点用于修改输入图像的对比度水平。其工作原理是通过调整图像亮部与暗部之间的差异来实现。当因子为 1.0 时图像保持不变，低于 1.0 的值会降低对比度，高于 1.0 的值则会增强对比度。 ## 输入 @@ -18,7 +19,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `image` | 调整对比度后生成的图像。 | IMAGE | +| `图像` | 调整对比度后生成的图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AdjustContrast/zh.md) diff --git a/zh/built-in-nodes/AlignYourStepsScheduler.mdx b/zh/built-in-nodes/AlignYourStepsScheduler.mdx index 90d795ec7..8f0ceb77f 100644 --- a/zh/built-in-nodes/AlignYourStepsScheduler.mdx +++ b/zh/built-in-nodes/AlignYourStepsScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AlignYourStepsScheduler" icon: "circle" mode: wide --- + AlignYourStepsScheduler节点根据不同的模型类型生成去噪过程的sigma值。它会为采样过程的每一步计算合适的噪声水平，并根据去噪参数调整总步数。这有助于将采样步数与不同扩散模型的特定要求对齐。 ## 输入 diff --git a/zh/built-in-nodes/AudioAdjustVolume.mdx b/zh/built-in-nodes/AudioAdjustVolume.mdx index 2e586d0de..3f014b441 100644 --- a/zh/built-in-nodes/AudioAdjustVolume.mdx +++ b/zh/built-in-nodes/AudioAdjustVolume.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioAdjustVolume" icon: "circle" mode: wide --- + AudioAdjustVolume 节点通过以分贝（dB）为单位调整音量来修改音频的响度。它接收音频输入，并根据指定的音量级别应用增益系数，其中正值增加音量，负值降低音量。该节点返回与原始音频采样率相同的修改后音频。 ## 输入 diff --git a/zh/built-in-nodes/AudioConcat.mdx b/zh/built-in-nodes/AudioConcat.mdx index 3723cb452..ee6dd873f 100644 --- a/zh/built-in-nodes/AudioConcat.mdx +++ b/zh/built-in-nodes/AudioConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioConcat" icon: "circle" mode: wide --- + AudioConcat 节点通过拼接两个音频输入来合并它们。该节点接收两个音频输入，并按照您指定的顺序连接它们，可以将第二个音频放置在第一个音频之前或之后。节点会自动处理不同的音频格式，将单声道音频转换为立体声，并匹配两个输入之间的采样率。 ## 输入 diff --git a/zh/built-in-nodes/AudioEncoderEncode.mdx b/zh/built-in-nodes/AudioEncoderEncode.mdx index 07a073623..7eaf269b1 100644 --- a/zh/built-in-nodes/AudioEncoderEncode.mdx +++ b/zh/built-in-nodes/AudioEncoderEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEncoderEncode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AudioEncoderEncode/en.md) AudioEncoderEncode 节点通过使用音频编码器模型对音频数据进行编码处理。它接收音频输入，并将其转换为编码表示形式，以便在 conditioning 流程中进一步处理。此节点将原始音频波形转换为适合基于音频的机器学习应用的格式。 diff --git a/zh/built-in-nodes/AudioEncoderLoader.mdx b/zh/built-in-nodes/AudioEncoderLoader.mdx index db88c2ef8..23364b9c6 100644 --- a/zh/built-in-nodes/AudioEncoderLoader.mdx +++ b/zh/built-in-nodes/AudioEncoderLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEncoderLoader" icon: "circle" mode: wide --- + AudioEncoderLoader 节点用于从音频编码器文件夹中的文件加载音频编码器模型。它接收音频编码器模型的文件名作为输入，并返回加载后的模型，该模型随后可用于工作流中的音频处理任务。 ## 输入 diff --git a/zh/built-in-nodes/AudioEqualizer3Band.mdx b/zh/built-in-nodes/AudioEqualizer3Band.mdx index 2dfbf1377..7b923f4ba 100644 --- a/zh/built-in-nodes/AudioEqualizer3Band.mdx +++ b/zh/built-in-nodes/AudioEqualizer3Band.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioEqualizer3Band" icon: "circle" mode: wide --- + 音频均衡器（3 频段）节点允许您调整音频波形的低频、中频和高频。它应用三个独立的滤波器：用于低频的低架滤波器、用于中频的峰值滤波器和用于高频的高架滤波器。每个频段都可以通过增益、频率和带宽设置独立控制。 ## 输入 diff --git a/zh/built-in-nodes/AudioMerge.mdx b/zh/built-in-nodes/AudioMerge.mdx index 7bd55bdbc..54dc9b6e0 100644 --- a/zh/built-in-nodes/AudioMerge.mdx +++ b/zh/built-in-nodes/AudioMerge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AudioMerge" icon: "circle" mode: wide --- + AudioMerge 节点通过叠加波形来合并两条音轨。它会自动匹配两个音频输入的采样率，并在合并前将它们的长度调整为相等。该节点提供了多种数学方法来组合音频信号，并确保输出保持在可接受的音量范围内。 ## 输入 diff --git a/zh/built-in-nodes/AutogrowNamesTestNode.mdx b/zh/built-in-nodes/AutogrowNamesTestNode.mdx index 9e6d3eb2f..7bd29cd12 100644 --- a/zh/built-in-nodes/AutogrowNamesTestNode.mdx +++ b/zh/built-in-nodes/AutogrowNamesTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AutogrowNamesTestNode" icon: "circle" mode: wide --- + 此节点用于测试自动增长输入功能。它接收动态数量的浮点数输入，每个输入都带有特定名称，并将这些值合并为一个以逗号分隔的字符串。 ## 输入 diff --git a/zh/built-in-nodes/AutogrowPrefixTestNode.mdx b/zh/built-in-nodes/AutogrowPrefixTestNode.mdx index 2a5108f18..ededa1819 100644 --- a/zh/built-in-nodes/AutogrowPrefixTestNode.mdx +++ b/zh/built-in-nodes/AutogrowPrefixTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "AutogrowPrefixTestNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AutogrowPrefixTestNode/en.md) AutogrowPrefixTestNode 是一个逻辑节点，用于测试输入自动增长功能。它接受动态数量的浮点数输入，将其值合并为逗号分隔的字符串，并输出该字符串。 diff --git a/zh/built-in-nodes/BasicGuider.mdx b/zh/built-in-nodes/BasicGuider.mdx index 7e8feb176..1a6aee6ab 100644 --- a/zh/built-in-nodes/BasicGuider.mdx +++ b/zh/built-in-nodes/BasicGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BasicGuider" icon: "circle" mode: wide --- + BasicGuider 节点为采样过程创建了一个简单的引导机制。它接收模型和条件数据作为输入，并生成一个引导器对象，用于在采样过程中引导生成过程。该节点提供了受控生成所需的基础引导功能。 ## 输入 diff --git a/zh/built-in-nodes/BasicScheduler.mdx b/zh/built-in-nodes/BasicScheduler.mdx index c6360932e..4ce6822cd 100644 --- a/zh/built-in-nodes/BasicScheduler.mdx +++ b/zh/built-in-nodes/BasicScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BasicScheduler" icon: "circle" mode: wide --- + `BasicScheduler` 节点旨在根据提供的调度器、模型和去噪参数，为扩散模型计算一系列 sigma 值。它会根据去噪因子动态调整总步数，以微调扩散过程，为需要精细控制的高级采样过程（如多阶段采样）的不同阶段提供精确的“配方”。 ## 输入 diff --git a/zh/built-in-nodes/BatchImagesMasksLatentsNode.mdx b/zh/built-in-nodes/BatchImagesMasksLatentsNode.mdx index 197807375..4c6aa7317 100644 --- a/zh/built-in-nodes/BatchImagesMasksLatentsNode.mdx +++ b/zh/built-in-nodes/BatchImagesMasksLatentsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchImagesMasksLatentsNode" icon: "circle" mode: wide --- + 批量图像/遮罩/潜空间节点将多个相同类型的输入合并为单个批次。它会自动检测输入是图像、遮罩还是潜空间表示，并使用相应的批处理方法。这对于准备多个项目以供接受批量输入的节点处理非常有用。 ## 输入 diff --git a/zh/built-in-nodes/BatchImagesNode.mdx b/zh/built-in-nodes/BatchImagesNode.mdx index 7440daa14..1e63bcd59 100644 --- a/zh/built-in-nodes/BatchImagesNode.mdx +++ b/zh/built-in-nodes/BatchImagesNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchImagesNode" icon: "circle" mode: wide --- + 批量图像节点将多个单独图像合并为单个批次。它接收可变数量的图像输入，并将其输出为一个批处理的图像张量，以便在后续节点中一起处理。 ## 输入 diff --git a/zh/built-in-nodes/BatchLatentsNode.mdx b/zh/built-in-nodes/BatchLatentsNode.mdx index 75e668cc3..6994bed29 100644 --- a/zh/built-in-nodes/BatchLatentsNode.mdx +++ b/zh/built-in-nodes/BatchLatentsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchLatentsNode" icon: "circle" mode: wide --- + 批量潜空间节点将多个潜空间输入合并为单个批次。它接收可变数量的潜空间样本，并沿批次维度将其合并，以便在后续节点中一起处理。这对于在单次操作中生成或处理多张图像非常有用。 ## 输入 diff --git a/zh/built-in-nodes/BatchMasksNode.mdx b/zh/built-in-nodes/BatchMasksNode.mdx index 0ebc99026..9cb2a58ef 100644 --- a/zh/built-in-nodes/BatchMasksNode.mdx +++ b/zh/built-in-nodes/BatchMasksNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BatchMasksNode" icon: "circle" mode: wide --- + 批量遮罩节点将多个单独的遮罩输入合并为一个批次。它接收可变数量的遮罩输入，并将其作为单个批处理遮罩张量输出，从而允许在后续节点中对遮罩进行批量处理。 ## 输入 diff --git a/zh/built-in-nodes/BeebleSwitchXImageEdit.mdx b/zh/built-in-nodes/BeebleSwitchXImageEdit.mdx index ad21bf26a..cd9e0c601 100644 --- a/zh/built-in-nodes/BeebleSwitchXImageEdit.mdx +++ b/zh/built-in-nodes/BeebleSwitchXImageEdit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BeebleSwitchXImageEdit" icon: "circle" mode: wide --- + ## ## 概述 使用 Beeble SwitchX 编辑单张图像。此节点可以切换场景中的任何元素（背景、光照、服装），同时保留原始主体的像素。提供参考图像和/或文本提示来描述新的外观。最大分辨率约为 277 万像素。 diff --git a/zh/built-in-nodes/BeebleSwitchXVideoEdit.mdx b/zh/built-in-nodes/BeebleSwitchXVideoEdit.mdx index 99e111a19..c85327e83 100644 --- a/zh/built-in-nodes/BeebleSwitchXVideoEdit.mdx +++ b/zh/built-in-nodes/BeebleSwitchXVideoEdit.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BeebleSwitchXVideoEdit" icon: "circle" mode: wide --- -# Beeble SwitchX 视频编辑 使用 Beeble SwitchX 编辑视频。此节点可以切换场景中的任何内容（背景、光照、服装），同时保留原始主体的像素和运动。提供参考图像和/或文本提示来描述新的外观。 diff --git a/zh/built-in-nodes/BerniniConditioning.mdx b/zh/built-in-nodes/BerniniConditioning.mdx new file mode 100644 index 000000000..8479f550f --- /dev/null +++ b/zh/built-in-nodes/BerniniConditioning.mdx @@ -0,0 +1,45 @@ +--- +title: "BerniniConditioning - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the BerniniConditioning node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "BerniniConditioning" +icon: "circle" +mode: wide +--- + +BerniniConditioning 节点为 Wan2.2-A14B 模型准备视频和图像条件数据。它使用提供的 VAE 对源视频、参考视频和参考图像进行编码，然后将它们附加到条件数据中，用于上下文生成任务。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `positive` | 正向条件数据 | CONDITIONING | 是 | - | +| `negative` | 负向条件数据 | CONDITIONING | 是 | - | +| `vae` | 用于编码视频和图像输入的 VAE 模型 | VAE | 是 | - | +| `宽度` | 输出潜变量的宽度（默认值：832） | INT | 是 | 16 至 8192（步长：16） | +| `高度` | 输出潜变量的高度（默认值：480） | INT | 是 | 16 至 8192（步长：16） | +| `长度` | 输出潜变量的帧数（默认值：81） | INT | 是 | 1 至 8192（步长：4） | +| `批量大小` | 单批次生成的视频数量（默认值：1） | INT | 是 | 1 至 4096 | +| `源视频` | 要编辑或重新造型的源视频（v2v, rv2v）。会调整至 width/height 尺寸并裁剪至 length 长度。 | IMAGE | 否 | - | +| `参考视频` | 要插入到源视频中的视频（ads2v）。 | IMAGE | 否 | - | +| `参考图像` | 作为上下文令牌注入的参考图像（r2v, rv2v）。最多可提供 8 张图像。 | IMAGE | 否 | 0 至 8 张图像 | +| `参考最大尺寸` | reference_video 和 reference_images 长边的最大尺寸。按比例调整大小并对齐至 16px（默认值：848）。 | INT | 否 | 16 至 8192（步长：16） | + +**注意：** 任务类型根据连接的输入推断： +- 未连接任何输入 → 文本到视频（t2v） +- 仅连接 `source_video` → 视频到视频（v2v） +- 连接 `source_video` + `reference_images` → 参考引导的视频编辑（rv2v） +- 仅连接 `reference_images` → 参考到视频（r2v） +- 连接 `source_video` + `reference_video` → 将图像/视频插入视频（ads2v） + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `positive` | 附加了上下文潜变量的正向条件数据 | CONDITIONING | +| `negative` | 附加了上下文潜变量的负向条件数据 | CONDITIONING | +| `latent` | 维度与指定的宽度、高度、长度和批次大小匹配的空潜变量张量 | LATENT | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BerniniConditioning/zh.md) + +--- +**Source fingerprint (SHA-256):** `3535bbe9a1ae007dc579242b44787ab315479a820eb0da680eab9b870ab60699` diff --git a/zh/built-in-nodes/BetaSamplingScheduler.mdx b/zh/built-in-nodes/BetaSamplingScheduler.mdx index 9af165e8c..a067564d4 100644 --- a/zh/built-in-nodes/BetaSamplingScheduler.mdx +++ b/zh/built-in-nodes/BetaSamplingScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BetaSamplingScheduler" icon: "circle" mode: wide --- + BetaSamplingScheduler 节点使用 beta 调度算法生成采样过程中的噪声水平序列（sigma 值）。它接收一个模型和配置参数，创建自定义的噪声调度方案，用于控制图像生成过程中的去噪进程。通过 alpha 和 beta 参数，该调度器可对降噪轨迹进行精细调整。 ## 输入 diff --git a/zh/built-in-nodes/BriaImageEditNode.mdx b/zh/built-in-nodes/BriaImageEditNode.mdx index c2dcfdc7b..f615d1749 100644 --- a/zh/built-in-nodes/BriaImageEditNode.mdx +++ b/zh/built-in-nodes/BriaImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BriaImageEditNode" icon: "circle" mode: wide --- + Bria FIBO 图像编辑节点允许您通过文本指令修改现有图像。它会将图像和提示词发送至 Bria API，由 Bria API 使用 FIBO 模型根据您的请求生成新的编辑版本。您还可以提供遮罩，将编辑限制在特定区域。 ## 输入 diff --git a/zh/built-in-nodes/BriaRemoveImageBackground.mdx b/zh/built-in-nodes/BriaRemoveImageBackground.mdx index f22f1a91f..dac0d301c 100644 --- a/zh/built-in-nodes/BriaRemoveImageBackground.mdx +++ b/zh/built-in-nodes/BriaRemoveImageBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BriaRemoveImageBackground" icon: "circle" mode: wide --- + 此节点使用 Bria RMBG 2.0 服务从图像中移除背景。它将图像发送到外部 API 进行处理，并返回移除背景后的结果。 ## 输入 diff --git a/zh/built-in-nodes/BriaRemoveVideoBackground.mdx b/zh/built-in-nodes/BriaRemoveVideoBackground.mdx index 6418ace2a..8054db1a5 100644 --- a/zh/built-in-nodes/BriaRemoveVideoBackground.mdx +++ b/zh/built-in-nodes/BriaRemoveVideoBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "BriaRemoveVideoBackground" icon: "circle" mode: wide --- + 此节点使用 Bria AI 服务移除视频背景。它会处理输入视频，并将原始背景替换为您选择的纯色。该操作通过外部 API 执行，结果以新视频文件的形式返回。 ## 输入 diff --git a/zh/built-in-nodes/BriaTransparentVideoBackground.mdx b/zh/built-in-nodes/BriaTransparentVideoBackground.mdx index 7a395a48b..59c4e96fd 100644 --- a/zh/built-in-nodes/BriaTransparentVideoBackground.mdx +++ b/zh/built-in-nodes/BriaTransparentVideoBackground.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaTransparentVideoBackground" icon: "circle" mode: wide --- -# Bria 移除视频背景（透明） 此节点使用 Bria 的 AI 服务移除视频背景，并输出去除背景后的帧画面及对应的 Alpha 遮罩。将两个输出连接到合成节点，或将其输入到保存 WEBM 节点以生成透明视频。 diff --git a/zh/built-in-nodes/BriaVideoGreenScreen.mdx b/zh/built-in-nodes/BriaVideoGreenScreen.mdx index 7344be628..4f0067912 100644 --- a/zh/built-in-nodes/BriaVideoGreenScreen.mdx +++ b/zh/built-in-nodes/BriaVideoGreenScreen.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaVideoGreenScreen" icon: "circle" mode: wide --- -# Bria 视频绿幕 此节点使用 Bria API 将视频背景替换为纯色色度抠像屏幕。它处理输入视频并返回一个新视频，其中原始背景已被移除并替换为统一的绿色或蓝色屏幕颜色。 diff --git a/zh/built-in-nodes/BriaVideoReplaceBackground.mdx b/zh/built-in-nodes/BriaVideoReplaceBackground.mdx index ab651acb3..4f503ec2a 100644 --- a/zh/built-in-nodes/BriaVideoReplaceBackground.mdx +++ b/zh/built-in-nodes/BriaVideoReplaceBackground.mdx @@ -5,7 +5,6 @@ sidebarTitle: "BriaVideoReplaceBackground" icon: "circle" mode: wide --- -# Bria 视频背景替换 此节点使用 Bria 的 API，将视频背景替换为提供的图像或视频。输出内容保持前景视频的分辨率和帧率；若背景素材的宽高比不同，则会被拉伸以适配，因此匹配宽高比可产生无失真的结果。 diff --git a/zh/built-in-nodes/BuildJsonPromptIdeogram.mdx b/zh/built-in-nodes/BuildJsonPromptIdeogram.mdx new file mode 100644 index 000000000..a0e21534e --- /dev/null +++ b/zh/built-in-nodes/BuildJsonPromptIdeogram.mdx @@ -0,0 +1,37 @@ +--- +title: "BuildJsonPromptIdeogram - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the BuildJsonPromptIdeogram node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "BuildJsonPromptIdeogram" +icon: "circle" +mode: wide +--- + +此节点构建一个结构化的 JSON 提示词，专为 Ideogram 4 图像生成模型格式化。它将您的文本指令、风格偏好和调色板组织成模型所需的 JSON 结构。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `元素` | 来自“创建边界框”节点的提示词元素。 | ARRAY | 是 | - | +| `高级描述` | 可选的一两句图像描述。强烈建议填写。（默认：空） | STRING | 否 | - | +| `背景` | 图像背景或环境的必填描述。（默认：空） | STRING | 是 | - | +| `风格` | 生成图像的视觉风格类别。（默认："none"） | COMBO | 是 | `"none"`
`"photo"`
`"art_style"` | +| `photo` | 摄影输出的相机或镜头细节（例如 35mm、f/1.4、散景）。仅在 `风格` 设置为 "photo" 时可用。（默认：空） | STRING | 否 | - | +| `art_style` | 艺术风格描述（例如扁平矢量插画、粗轮廓线）。仅在 `风格` 设置为 "art_style" 时可用。（默认：空） | STRING | 否 | - | +| `美学` | 必填的美学关键词（例如情绪化、电影感、去饱和）。（默认：空） | STRING | 是 | - | +| `光照` | 必填的照明描述（例如黄金时刻、轮廓光、戏剧性阴影）。（默认：空） | STRING | 是 | - | +| `媒介` | 必填的媒介类型（例如照片、插画、3D 渲染、绘画、平面设计）。当 `风格` = photo 时，设置为 photograph。（默认：空） | STRING | 是 | - | +| `色板` | 十六进制颜色代码，用于引导图像的主色调。最多 16 个条目。 | COLORS | 否 | - | + +**注意：** 当 `style` 参数设置为 "photo" 时，`photo` 输入变为可用，并且您应将 `medium` 参数设置为 "photograph"。当 `style` 设置为 "art_style" 时，`art_style` 输入变为可用。 + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `提示` | 一个结构化的 JSON 字典，包含高级描述、风格描述（如适用），以及包含背景和元素的构图解构。 | DICT | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BuildJsonPromptIdeogram/zh.md) + +--- +**Source fingerprint (SHA-256):** `56a045e0c7c19531e6443696c0bdf3946df066d03eea7d2d217b7d92f052592f` diff --git a/zh/built-in-nodes/ByteDance2FirstLastFrameNode.mdx b/zh/built-in-nodes/ByteDance2FirstLastFrameNode.mdx index cac04524f..98fde2409 100644 --- a/zh/built-in-nodes/ByteDance2FirstLastFrameNode.mdx +++ b/zh/built-in-nodes/ByteDance2FirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2FirstLastFrameNode" icon: "circle" mode: wide --- + 此节点使用字节跳动的 Seedance 2.0 模型生成视频。它基于文本提示和必需的首帧图像创建视频。您还可以选择提供末帧图像来引导视频序列的结尾。 ## 输入 diff --git a/zh/built-in-nodes/ByteDance2ReferenceNode.mdx b/zh/built-in-nodes/ByteDance2ReferenceNode.mdx index 17485b238..b2174902b 100644 --- a/zh/built-in-nodes/ByteDance2ReferenceNode.mdx +++ b/zh/built-in-nodes/ByteDance2ReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2ReferenceNode" icon: "circle" mode: wide --- + ByteDance Seedance 2.0 参考视频节点使用 Seedance 2.0 AI 模型，根据您的文本提示和提供的参考素材来创建、编辑或扩展视频。它可以使用图像、视频和音频作为参考来引导生成过程，支持视频编辑和扩展等任务。 ## 输入 diff --git a/zh/built-in-nodes/ByteDance2TextToVideoNode.mdx b/zh/built-in-nodes/ByteDance2TextToVideoNode.mdx index b8e8ff27c..9861b0979 100644 --- a/zh/built-in-nodes/ByteDance2TextToVideoNode.mdx +++ b/zh/built-in-nodes/ByteDance2TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDance2TextToVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDance2TextToVideoNode/en.md) 此节点使用字节跳动的 Seedance 2.0 API 根据文本描述生成视频。它将您的提示词发送至所选模型，等待视频处理完成，并返回最终结果。 diff --git a/zh/built-in-nodes/ByteDanceCreateImageAsset.mdx b/zh/built-in-nodes/ByteDanceCreateImageAsset.mdx index 47ecf1e13..5efdb4f85 100644 --- a/zh/built-in-nodes/ByteDanceCreateImageAsset.mdx +++ b/zh/built-in-nodes/ByteDanceCreateImageAsset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceCreateImageAsset" icon: "circle" mode: wide --- + 此节点为字节跳动的 Seedance 2.0 服务创建个人图像资产。它会上传输入图像并将其注册到指定的资产组中。如果未提供组 ID，则会在浏览器中启动真人验证流程，以创建新组后再添加资产。 ## 输入 @@ -23,7 +24,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `group_id` | 新创建的图像资产的唯一标识符。 | STRING | +| `asset_id` | 新创建的图像资产的唯一标识符。 | STRING | | `group_id` | 资产组的标识符。这将是提供的 `group_id` 或新创建的组 ID。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateImageAsset/zh.md) diff --git a/zh/built-in-nodes/ByteDanceCreateVideoAsset.mdx b/zh/built-in-nodes/ByteDanceCreateVideoAsset.mdx index 7a2038e35..2476f4fa3 100644 --- a/zh/built-in-nodes/ByteDanceCreateVideoAsset.mdx +++ b/zh/built-in-nodes/ByteDanceCreateVideoAsset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceCreateVideoAsset" icon: "circle" mode: wide --- + 此节点用于为 Seedance 2.0 创建个人视频资产。它会上传您的输入视频，并将其注册到指定的资产组中。如果您未提供组 ID，系统将在浏览器中引导您完成真人验证流程，以便首先创建一个新组。 ## 输入 @@ -25,7 +26,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `group_id` | 新创建的视频资产的唯一标识符。 | STRING | +| `asset_id` | 新创建的视频资产的唯一标识符。 | STRING | | `group_id` | 包含新视频的资产组标识符。这将是提供的 `group_id` 或新创建的组 ID。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceCreateVideoAsset/zh.md) diff --git a/zh/built-in-nodes/ByteDanceFirstLastFrameNode.mdx b/zh/built-in-nodes/ByteDanceFirstLastFrameNode.mdx index 882703c8c..ff26737b4 100644 --- a/zh/built-in-nodes/ByteDanceFirstLastFrameNode.mdx +++ b/zh/built-in-nodes/ByteDanceFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceFirstLastFrameNode" icon: "circle" mode: wide --- + 此节点使用文本提示以及首帧和尾帧图像生成视频。它根据您的描述和两个关键帧，创建在这两者之间过渡的完整视频序列。该节点提供多种选项来控制视频的分辨率、宽高比、时长和其他生成参数。 ## 输入 diff --git a/zh/built-in-nodes/ByteDanceImageEditNode.mdx b/zh/built-in-nodes/ByteDanceImageEditNode.mdx index f99caaaa4..3dc8f5a6e 100644 --- a/zh/built-in-nodes/ByteDanceImageEditNode.mdx +++ b/zh/built-in-nodes/ByteDanceImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageEditNode" icon: "circle" mode: wide --- + 字节跳动图像编辑节点允许您通过 API 使用字节跳动的 AI 模型修改图像。您提供输入图像和描述所需更改的文本提示，节点将根据您的指令处理图像。该节点自动处理 API 通信并返回编辑后的图像。 ## 输入 diff --git a/zh/built-in-nodes/ByteDanceImageNode.mdx b/zh/built-in-nodes/ByteDanceImageNode.mdx index 0f7b42c2f..91fab4252 100644 --- a/zh/built-in-nodes/ByteDanceImageNode.mdx +++ b/zh/built-in-nodes/ByteDanceImageNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ByteDanceImageNode" icon: "circle" mode: wide --- -# ByteDance 图像节点 此文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageNode/en.md) diff --git a/zh/built-in-nodes/ByteDanceImageReferenceNode.mdx b/zh/built-in-nodes/ByteDanceImageReferenceNode.mdx index c3a238da5..b90c3d888 100644 --- a/zh/built-in-nodes/ByteDanceImageReferenceNode.mdx +++ b/zh/built-in-nodes/ByteDanceImageReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageReferenceNode" icon: "circle" mode: wide --- + 字节跳动图像参考节点通过文本提示和一到四张参考图像生成视频。它将图像和提示发送到外部 API 服务，该服务在融合参考图像视觉风格和内容的同时，创建与描述匹配的视频。该节点提供多种控制选项，用于设置视频分辨率、宽高比、时长及其他生成参数。 ## 输入 diff --git a/zh/built-in-nodes/ByteDanceImageToVideoNode.mdx b/zh/built-in-nodes/ByteDanceImageToVideoNode.mdx index be7c25964..9dcf3828d 100644 --- a/zh/built-in-nodes/ByteDanceImageToVideoNode.mdx +++ b/zh/built-in-nodes/ByteDanceImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceImageToVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceImageToVideoNode/en.md) ByteDance 图像转视频节点通过 API 使用 ByteDance 模型，基于输入图像和文本提示生成视频。它接收起始图像帧，并创建遵循所提供描述的视频序列。该节点提供多种自定义选项，用于设置视频分辨率、宽高比、时长及其他生成参数。 diff --git a/zh/built-in-nodes/ByteDanceSeedAudio.mdx b/zh/built-in-nodes/ByteDanceSeedAudio.mdx new file mode 100644 index 000000000..c70e34477 --- /dev/null +++ b/zh/built-in-nodes/ByteDanceSeedAudio.mdx @@ -0,0 +1,49 @@ +--- +title: "ByteDanceSeedAudio - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ByteDanceSeedAudio node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ByteDanceSeedAudio" +icon: "circle" +mode: wide +--- + +使用单个提示词，通过字节跳动 Seed Audio 1.0 生成语音、音乐、音效和多说话人对话。在提示词中描述声音、情感、氛围、背景音乐和音效，并包含要朗读的台词。可选择内置预设语音，从最多 3 个参考片段（在提示词中标记为 @Audio1-3）克隆声音，或从角色图像中衍生声音。每次运行最多可生成 2 分钟音频。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `text_prompt` | 描述声音、情感、节奏、氛围、背景音乐和音效，并包含要朗读的台词（对话中可内联标注角色名称）。在“音频参考”模式下，按顺序引用连接的片段为 @Audio1、@Audio2、@Audio3。最多 3000 个字符。 | STRING | 是 | 1 到 3000 个字符 | +| `reference_mode` | 如何控制声音：“仅文本”（在提示词中描述所有内容）、“音频参考”（克隆最多 3 个声音，标记为 @Audio1-3）、“图像参考”（从一张角色图像衍生声音）或“预设语音”（选择一个内置命名语音来朗读提示词）。 | COMBO | 是 | `"text only"`
`"audio reference"`
`"image reference"`
`"preset voice"` | +| `reference_audio_1` | 用于声音克隆的参考片段，在提示词中标记为 @Audio1。最长 30 秒。仅当 `reference_mode` 为“audio reference”时可用。 | AUDIO | 否 | 最长 30 秒 | +| `reference_audio_2` | 在提示词中标记为 @Audio2 的参考片段。最长 30 秒。仅当 `reference_mode` 为“audio reference”时可用。 | AUDIO | 否 | 最长 30 秒 | +| `reference_audio_3` | 在提示词中标记为 @Audio3 的参考片段。最长 30 秒。仅当 `reference_mode` 为“audio reference”时可用。 | AUDIO | 否 | 最长 30 秒 | +| `reference_image` | 一张角色图像；模型从中衍生声音。不能与参考音频结合使用。仅当 `reference_mode` 为“image reference”时可用。 | IMAGE | 否 | - | +| `preset_voice` | 一个内置的 TTS 2.0 语音，用于朗读提示词。无需参考片段，且在此模式下不使用 @AudioN 标签。仅当 `reference_mode` 为“preset voice”时可用。 | COMBO | 否 | 多个选项可用（见描述） | +| `sample_rate` | 输出采样率，单位为 Hz。（默认值："24000"） | COMBO | 是 | `"8000"`
`"16000"`
`"24000"`
`"32000"`
`"44100"`
`"48000"` | +| `speech_rate` | 语速。0 = 正常，100 = 2.0 倍，-50 = 0.5 倍。（默认值：0） | INT | 是 | -50 到 100 | +| `loudness_rate` | 音量。0 = 正常，100 = 2.0 倍，-50 = 0.5 倍。（默认值：0） | INT | 是 | -50 到 100 | +| `pitch_rate` | 音高偏移，单位为半音（-12 到 12）。（默认值：0） | INT | 是 | -12 到 12 | +| `seed` | 种子控制节点是否应重新运行；无论种子如何，结果都是非确定性的。（默认值：42） | INT | 是 | 0 到 2147483647 | + +### 参数约束 + +- **参考模式依赖关系**：`reference_mode` 参数决定了哪些其他输入是必需的： + - **"text only"**：无需额外输入。提示词不得包含 @AudioN 标签。 + - **"audio reference"**：需要至少连接 `reference_audio_1`、`reference_audio_2` 或 `reference_audio_3` 中的一个。参考片段必须按顺序连接，不能有间隔（例如，_1，然后 _2，然后 _3）。每个片段最长 30 秒。提示词必须使用 @Audio1、@Audio2、@Audio3 标签引用连接的片段。 + - **"image reference"**：需要连接 `reference_image`。提示词不得包含 @AudioN 标签。 + - **"preset voice"**：需要选择 `preset_voice`。提示词不得包含 @AudioN 标签（整个提示词将以所选语音朗读）。 + +- **音频参考排序**：使用“audio reference”模式时，参考音频输入必须从 `reference_audio_1` 开始顺序连接，不能有间隔。例如，可以连接 _1 和 _2，但不能在没有 _2 的情况下连接 _1 和 _3。 + +- **最大音频标签数**：在“audio reference”模式下，提示词最多可引用 3 个音频片段（@Audio1、@Audio2、@Audio3）。编号最高的标签不得超过已连接的参考音频输入数量。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `AUDIO` | 字节跳动 Seed Audio 1.0 生成的音频输出，包含提示词中描述的语音、音乐、音效或多说话人对话。 | AUDIO | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedAudio/zh.md) + +--- +**Source fingerprint (SHA-256):** `cefd5fca496b02c35022d25be3d99d3911c1304b6e3a751751b58841d5895ef7` diff --git a/zh/built-in-nodes/ByteDanceSeedNode.mdx b/zh/built-in-nodes/ByteDanceSeedNode.mdx index 75d3f74f6..3418d6fc2 100644 --- a/zh/built-in-nodes/ByteDanceSeedNode.mdx +++ b/zh/built-in-nodes/ByteDanceSeedNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceSeedNode" icon: "circle" mode: wide --- + ## ## 概述 使用字节跳动的 Seed 2.0 模型生成文本回复。提供文本提示，并可选择包含图像或视频以提供多模态上下文。 diff --git a/zh/built-in-nodes/ByteDanceSeedreamNode.mdx b/zh/built-in-nodes/ByteDanceSeedreamNode.mdx index 20b97a8d8..8de2430a1 100644 --- a/zh/built-in-nodes/ByteDanceSeedreamNode.mdx +++ b/zh/built-in-nodes/ByteDanceSeedreamNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceSeedreamNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ByteDanceSeedreamNode/en.md) ByteDance Seedream 4.5 & 5.0 节点提供统一的文本到图像生成功能，并支持高达 4K 分辨率的精确单句编辑能力。它可以根据文本提示创建新图像，或使用文本指令编辑现有图像。该节点支持单张图像生成以及多张相关图像的序列生成。 diff --git a/zh/built-in-nodes/ByteDanceSeedreamNodeV2.mdx b/zh/built-in-nodes/ByteDanceSeedreamNodeV2.mdx index 38b4be1bd..dd29d0a79 100644 --- a/zh/built-in-nodes/ByteDanceSeedreamNodeV2.mdx +++ b/zh/built-in-nodes/ByteDanceSeedreamNodeV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceSeedreamNodeV2" icon: "circle" mode: wide --- + ## 概述 此节点使用字节跳动的 Seedream 模型（版本 4.0、4.5 和 5.0 Lite）生成或编辑图像。它可以根据文本提示创建新图像，或通过提供参考图像编辑现有图像，支持最高 4K 分辨率。 diff --git a/zh/built-in-nodes/ByteDanceTextToVideoNode.mdx b/zh/built-in-nodes/ByteDanceTextToVideoNode.mdx index 686cf228f..a631884a9 100644 --- a/zh/built-in-nodes/ByteDanceTextToVideoNode.mdx +++ b/zh/built-in-nodes/ByteDanceTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ByteDanceTextToVideoNode" icon: "circle" mode: wide --- + 字节跳动文本转视频节点通过 API 使用字节跳动模型，基于文本提示生成视频。它接收文本描述和各种视频设置作为输入，然后创建符合指定规格的视频。该节点处理 API 通信，并将生成的视频作为输出返回。 ## 输入 diff --git a/zh/built-in-nodes/CFGGuider.mdx b/zh/built-in-nodes/CFGGuider.mdx index 997d0b02b..8e407c8ef 100644 --- a/zh/built-in-nodes/CFGGuider.mdx +++ b/zh/built-in-nodes/CFGGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGGuider" icon: "circle" mode: wide --- + CFGGuider 节点创建了一个引导系统，用于控制图像生成中的采样过程。它接收一个模型以及正向和负向条件输入，然后应用无分类器引导尺度，使生成过程趋向期望内容，同时避免不想要的元素。该节点输出一个引导器对象，可供采样节点用于控制图像生成方向。 ## 输入 diff --git a/zh/built-in-nodes/CFGNorm.mdx b/zh/built-in-nodes/CFGNorm.mdx index f9344eec3..11906a177 100644 --- a/zh/built-in-nodes/CFGNorm.mdx +++ b/zh/built-in-nodes/CFGNorm.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGNorm" icon: "circle" mode: wide --- + CFGNorm 节点对扩散模型中的无分类器引导（CFG）过程应用归一化技术。它通过比较条件输出和无条件输出的范数来调整去噪预测的缩放比例，然后应用强度乘数来控制效果。这有助于通过防止引导缩放中的极端值来稳定生成过程。 ## 输入 @@ -18,7 +19,7 @@ CFGNorm 节点对扩散模型中的无分类器引导（CFG）过程应用归一 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `patched_model` | 返回经过修改的模型，其采样过程已应用 CFG 归一化 | MODEL | +| `模型` | 返回经过修改的模型，其采样过程已应用 CFG 归一化 | MODEL | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGNorm/zh.md) diff --git a/zh/built-in-nodes/CFGOverride.mdx b/zh/built-in-nodes/CFGOverride.mdx index d65abedc2..99c65906f 100644 --- a/zh/built-in-nodes/CFGOverride.mdx +++ b/zh/built-in-nodes/CFGOverride.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CFGOverride" icon: "circle" mode: wide --- -# CFG 覆盖 CFG 覆盖节点允许您为采样过程的特定范围（以总步数的百分比定义）设置固定的 CFG（无分类器引导）缩放值。当连接多个 CFG 覆盖节点时，链中离采样器最近的节点将优先处理重叠范围。 diff --git a/zh/built-in-nodes/CFGZeroStar.mdx b/zh/built-in-nodes/CFGZeroStar.mdx index 4d413d4ee..cf37ced41 100644 --- a/zh/built-in-nodes/CFGZeroStar.mdx +++ b/zh/built-in-nodes/CFGZeroStar.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CFGZeroStar" icon: "circle" mode: wide --- + CFGZeroStar 节点对扩散模型应用了一种专门的引导缩放技术。它通过计算基于条件预测与无条件预测之间差异的优化缩放因子，来修改无分类器引导过程。该方法调整最终输出，以在保持模型稳定性的同时，增强对生成过程的控制。 ## 输入 @@ -17,7 +18,7 @@ CFGZeroStar 节点对扩散模型应用了一种专门的引导缩放技术。 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `patched_model` | 已应用 CFGZeroStar 引导缩放的修改后模型 | MODEL | +| `模型` | 已应用 CFGZeroStar 引导缩放的修改后模型 | MODEL | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CFGZeroStar/zh.md) diff --git a/zh/built-in-nodes/CLIPAttentionMultiply.mdx b/zh/built-in-nodes/CLIPAttentionMultiply.mdx index ec47cf169..e9936f06b 100644 --- a/zh/built-in-nodes/CLIPAttentionMultiply.mdx +++ b/zh/built-in-nodes/CLIPAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPAttentionMultiply" icon: "circle" mode: wide --- + CLIPAttentionMultiply节点允许您通过将乘法因子应用于自注意力层的不同组件来调整CLIP模型中的注意力机制。其工作原理是修改CLIP模型注意力机制中的查询、键、值和输出投影的权重与偏置。此实验性节点会创建输入CLIP模型的修改副本，并应用指定的缩放因子。 ## 输入 diff --git a/zh/built-in-nodes/CLIPMergeAdd.mdx b/zh/built-in-nodes/CLIPMergeAdd.mdx index 52569a093..7d28fe1a2 100644 --- a/zh/built-in-nodes/CLIPMergeAdd.mdx +++ b/zh/built-in-nodes/CLIPMergeAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeAdd" icon: "circle" mode: wide --- + CLIPMergeAdd 节点通过将第二个 CLIP 模型的补丁添加到第一个模型来合并两个 CLIP 模型。它会创建第一个 CLIP 模型的副本，并有选择地合并第二个模型的关键补丁，排除位置 ID 和 logit 缩放参数。这允许您在保留基础模型结构的同时合并 CLIP 模型组件。 ## 输入 diff --git a/zh/built-in-nodes/CLIPMergeSubtract.mdx b/zh/built-in-nodes/CLIPMergeSubtract.mdx index 2d2fe6378..731410d10 100644 --- a/zh/built-in-nodes/CLIPMergeSubtract.mdx +++ b/zh/built-in-nodes/CLIPMergeSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeSubtract" icon: "circle" mode: wide --- + CLIPMergeSubtract 节点通过从一个 CLIP 模型中减去另一个模型的权重来执行模型合并。它通过克隆第一个模型，然后减去第二个模型的关键补丁来创建一个新的 CLIP 模型，并使用可调整的乘数来控制减法强度。这使得可以通过从基础模型中移除特定特征来实现精细调整的模型混合。 ## 输入 diff --git a/zh/built-in-nodes/CLIPTextEncodeControlnet.mdx b/zh/built-in-nodes/CLIPTextEncodeControlnet.mdx index 9fa6095e6..b9c1eaed3 100644 --- a/zh/built-in-nodes/CLIPTextEncodeControlnet.mdx +++ b/zh/built-in-nodes/CLIPTextEncodeControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeControlnet" icon: "circle" mode: wide --- + CLIPTextEncodeControlnet 节点使用 CLIP 模型处理文本输入，并将其与现有条件数据结合，为 ControlNet 应用生成增强的条件输出。该节点对输入文本进行分词，通过 CLIP 模型进行编码，并将生成的嵌入向量作为交叉注意力 ControlNet 参数添加到提供的条件数据中。 ## 输入 diff --git a/zh/built-in-nodes/CLIPTextEncodeHiDream.mdx b/zh/built-in-nodes/CLIPTextEncodeHiDream.mdx index 2b2492e58..37c6893cd 100644 --- a/zh/built-in-nodes/CLIPTextEncodeHiDream.mdx +++ b/zh/built-in-nodes/CLIPTextEncodeHiDream.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeHiDream" icon: "circle" mode: wide --- + CLIPTextEncodeHiDream 节点使用不同的语言模型（CLIP-L、CLIP-G、T5-XXL 和 LLaMA）处理四个独立的文本输入，并将它们合并为单个 conditioning 输出。它会使用对应的模型对每个文本输入进行分词，并通过调度编码方法将它们一起编码，从而通过同时利用多个语言模型实现更复杂的文本 conditioning。 ## 输入 diff --git a/zh/built-in-nodes/CLIPTextEncodeKandinsky5.mdx b/zh/built-in-nodes/CLIPTextEncodeKandinsky5.mdx index a6b7d5241..3457f969d 100644 --- a/zh/built-in-nodes/CLIPTextEncodeKandinsky5.mdx +++ b/zh/built-in-nodes/CLIPTextEncodeKandinsky5.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeKandinsky5" icon: "circle" mode: wide --- + CLIPTextEncodeKandinsky5 节点用于准备与 Kandinsky 5 模型配合使用的文本提示。它接收两个独立的文本输入，使用提供的 CLIP 模型对其进行分词处理，并将它们合并为单个 conditioning 输出。该输出用于指导图像生成过程。 ## 输入 diff --git a/zh/built-in-nodes/CLIPTextEncodeLumina2.mdx b/zh/built-in-nodes/CLIPTextEncodeLumina2.mdx index efd5d0a1c..de50446d9 100644 --- a/zh/built-in-nodes/CLIPTextEncodeLumina2.mdx +++ b/zh/built-in-nodes/CLIPTextEncodeLumina2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeLumina2" icon: "circle" mode: wide --- + Lumina2 的 CLIP 文本编码节点使用 CLIP 模型将系统提示词和用户提示词编码为嵌入向量，从而引导扩散模型生成特定图像。该节点将预定义的系统提示词与自定义文本提示词相结合，并通过 CLIP 模型进行处理，最终生成用于图像生成的条件数据。 ## 输入 diff --git a/zh/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx b/zh/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx index eafb1df2d..91c89b4a9 100644 --- a/zh/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx +++ b/zh/built-in-nodes/CLIPTextEncodePixArtAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodePixArtAlpha" icon: "circle" mode: wide --- + 对 PixArt Alpha 进行文本编码并设置分辨率条件。此节点处理文本输入，并添加宽度和高度信息，以创建专门用于 PixArt Alpha 模型的条件数据。不适用于 PixArt Sigma 模型。 ## 输入 diff --git a/zh/built-in-nodes/CLIPTextEncodeSD3.mdx b/zh/built-in-nodes/CLIPTextEncodeSD3.mdx index 63de817f7..1ded6fae3 100644 --- a/zh/built-in-nodes/CLIPTextEncodeSD3.mdx +++ b/zh/built-in-nodes/CLIPTextEncodeSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSD3" icon: "circle" mode: wide --- + CLIPTextEncodeSD3 节点通过使用不同的 CLIP 模型对多个文本提示进行编码，处理 Stable Diffusion 3 模型的文本输入。它管理三个独立的文本输入（`clip_g`、`clip_l` 和 `t5xxl`），并提供管理空文本填充的选项。该节点确保不同文本输入之间的令牌对齐正确，并返回适用于 SD3 生成流程的条件数据。 ## 输入 diff --git a/zh/built-in-nodes/Canny.mdx b/zh/built-in-nodes/Canny.mdx index e65c65876..4d6b7699b 100644 --- a/zh/built-in-nodes/Canny.mdx +++ b/zh/built-in-nodes/Canny.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Canny" icon: "circle" mode: wide --- + 从照片中提取所有边缘线条，就像用笔勾勒照片一样，绘制出物体的轮廓和细节边界。 ## 工作原理 diff --git a/zh/built-in-nodes/CaseConverter.mdx b/zh/built-in-nodes/CaseConverter.mdx index df2016f99..2ba8ea625 100644 --- a/zh/built-in-nodes/CaseConverter.mdx +++ b/zh/built-in-nodes/CaseConverter.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CaseConverter" icon: "circle" mode: wide --- + 大小写转换节点用于将文本字符串转换为不同的大小写格式。它接收一个输入字符串，并根据所选模式进行转换，输出应用了指定大小写格式的字符串。该节点支持四种不同的大小写转换选项，用于修改文本的大小写。 ## 输入 diff --git a/zh/built-in-nodes/CenterCropImages.mdx b/zh/built-in-nodes/CenterCropImages.mdx index 0fca9c4dd..cb06d6805 100644 --- a/zh/built-in-nodes/CenterCropImages.mdx +++ b/zh/built-in-nodes/CenterCropImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CenterCropImages" icon: "circle" mode: wide --- + 中心裁剪图像节点从图像中心裁剪出指定宽度和高度的区域。它会计算输入图像的中心区域，并提取出定义尺寸的矩形区域。如果请求的裁剪尺寸大于图像本身，裁剪将被限制在图像的边界内。 ## 输入 @@ -19,7 +20,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `image` | 中心裁剪操作后生成的图像。 | IMAGE | +| `图像` | 中心裁剪操作后生成的图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CenterCropImages/zh.md) diff --git a/zh/built-in-nodes/CheckpointLoader.mdx b/zh/built-in-nodes/CheckpointLoader.mdx index 2abd677a3..63654a93e 100644 --- a/zh/built-in-nodes/CheckpointLoader.mdx +++ b/zh/built-in-nodes/CheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointLoader" icon: "circle" mode: wide --- + CheckpointLoader 节点用于加载预训练模型检查点及其配置文件。它接收一个配置文件和检查点文件作为输入，并返回加载后的模型组件，包括主模型、CLIP 模型和 VAE 模型，以供工作流使用。 ## 输入 diff --git a/zh/built-in-nodes/CheckpointLoaderSimple.mdx b/zh/built-in-nodes/CheckpointLoaderSimple.mdx index 9dbabfc23..96dae7ee0 100644 --- a/zh/built-in-nodes/CheckpointLoaderSimple.mdx +++ b/zh/built-in-nodes/CheckpointLoaderSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointLoaderSimple" icon: "circle" mode: wide --- + ## 概述 加载扩散模型检查点文件，并将其分解为三个核心组件：用于去噪潜空间的主模型、CLIP 文本编码器以及 VAE 图像编码器/解码器。此节点会自动检测 `ComfyUI/models/checkpoints` 文件夹以及 `extra_model_paths.yaml` 文件中配置的所有其他路径中的模型文件。 diff --git a/zh/built-in-nodes/CheckpointSave.mdx b/zh/built-in-nodes/CheckpointSave.mdx index 69278759d..85861c811 100644 --- a/zh/built-in-nodes/CheckpointSave.mdx +++ b/zh/built-in-nodes/CheckpointSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CheckpointSave" icon: "circle" mode: wide --- + `Save Checkpoint` 节点用于将完整的 Stable Diffusion 模型（包括 UNet、CLIP 和 VAE 组件）保存为 **.safetensors** 格式的检查点文件。 该节点主要用于模型合并工作流。在通过 `ModelMergeSimple`、`ModelMergeBlocks` 等节点创建新的合并模型后，您可以使用此节点将结果保存为可复用的检查点文件。 diff --git a/zh/built-in-nodes/ChromaRadianceOptions.mdx b/zh/built-in-nodes/ChromaRadianceOptions.mdx index d42cb565a..22b9b31a7 100644 --- a/zh/built-in-nodes/ChromaRadianceOptions.mdx +++ b/zh/built-in-nodes/ChromaRadianceOptions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ChromaRadianceOptions" icon: "circle" mode: wide --- + ChromaRadianceOptions 节点允许您为 Chroma Radiance 模型配置高级设置。它会封装现有模型，并根据 sigma 值在去噪过程中应用特定选项，从而实现对 NeRF 瓦片大小及其他辐射相关参数的精细控制。 ## 输入 diff --git a/zh/built-in-nodes/ClaudeNode.mdx b/zh/built-in-nodes/ClaudeNode.mdx index e10a6da02..c0b9ee7a0 100644 --- a/zh/built-in-nodes/ClaudeNode.mdx +++ b/zh/built-in-nodes/ClaudeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ClaudeNode" icon: "circle" mode: wide --- + ## 概述 从 Anthropic Claude 模型生成文本响应。此节点将文本提示和可选图像发送至 Claude 模型，并返回生成的文本响应。 diff --git a/zh/built-in-nodes/ClipLoader.mdx b/zh/built-in-nodes/ClipLoader.mdx index 88f75a902..f4e441890 100644 --- a/zh/built-in-nodes/ClipLoader.mdx +++ b/zh/built-in-nodes/ClipLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPLoader" icon: "circle" mode: wide --- + CLIPLoader 节点用于从文件加载文本编码器模型（CLIP、T5 或类似模型），使其可供其他需要将文本提示转换为数值表示的节点使用。该节点支持多种模型架构，每种架构需要特定的编码器类型。 ## 输入 diff --git a/zh/built-in-nodes/ClipMergeSimple.mdx b/zh/built-in-nodes/ClipMergeSimple.mdx index 511bc1846..7e0cf93b9 100644 --- a/zh/built-in-nodes/ClipMergeSimple.mdx +++ b/zh/built-in-nodes/ClipMergeSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPMergeSimple" icon: "circle" mode: wide --- + `CLIPMergeSimple` 是一个高级模型合并节点，用于根据指定比例合并两个 CLIP 文本编码器模型。 此节点专门根据指定比例合并两个 CLIP 模型，有效融合它们的特性。它选择性地将一个模型的补丁应用到另一个模型（排除位置 ID 和 logit 缩放等特定组件），从而创建一个结合两个源模型特征的混合模型。 diff --git a/zh/built-in-nodes/ClipSave.mdx b/zh/built-in-nodes/ClipSave.mdx index acac2f39d..b0818ab29 100644 --- a/zh/built-in-nodes/ClipSave.mdx +++ b/zh/built-in-nodes/ClipSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPSave" icon: "circle" mode: wide --- + `CLIPSave` 节点将 CLIP 文本编码器模型以 SafeTensors 格式保存到磁盘。该节点专为高级模型合并工作流设计，可根据模型的内部结构自动将 CLIP 模型拆分为其组成部分（如 CLIP-L、CLIP-G 或 T5XXL），并将每个组件保存为单独的文件。 ## 输入 diff --git a/zh/built-in-nodes/ClipSetLastLayer.mdx b/zh/built-in-nodes/ClipSetLastLayer.mdx index efd509332..631f61a06 100644 --- a/zh/built-in-nodes/ClipSetLastLayer.mdx +++ b/zh/built-in-nodes/ClipSetLastLayer.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPSetLastLayer" icon: "circle" mode: wide --- + `CLIP Set Last Layer` 是 ComfyUI 中用于控制 CLIP 模型处理深度的核心节点。它允许用户精确控制 CLIP 文本编码器的停止处理位置，从而影响文本理解的深度和生成图像的风格。 将 CLIP 模型想象成一个 24 层的智能大脑： diff --git a/zh/built-in-nodes/ClipTextEncode.mdx b/zh/built-in-nodes/ClipTextEncode.mdx index e27e37fc5..b74f7b378 100644 --- a/zh/built-in-nodes/ClipTextEncode.mdx +++ b/zh/built-in-nodes/ClipTextEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncode" icon: "circle" mode: wide --- + `CLIP 文本编码 (CLIPTextEncode)` 充当翻译官的角色，将您的文本描述转换为 AI 能够理解的格式。这有助于 AI 解读您的输入并生成所需的图像。 可以将其想象为与一位使用不同语言的艺术家沟通。CLIP 模型经过海量图像-文本对的训练，通过将您的描述转换为 AI 模型可以遵循的"指令"来弥合这一鸿沟。 diff --git a/zh/built-in-nodes/ClipTextEncodeFlux.mdx b/zh/built-in-nodes/ClipTextEncodeFlux.mdx index b90f7c36e..9b82ead98 100644 --- a/zh/built-in-nodes/ClipTextEncodeFlux.mdx +++ b/zh/built-in-nodes/ClipTextEncodeFlux.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeFlux" icon: "circle" mode: wide --- + `CLIPTextEncodeFlux` 是一个为 Flux 架构设计的高级文本编码节点。它通过不同的编码器（CLIP-L 和 T5XXL）处理两个独立的文本输入，并结合引导比例（guidance scale）生成统一的 conditioning 输出，用于图像生成。 ## 输入 diff --git a/zh/built-in-nodes/ClipTextEncodeHunyuanDit.mdx b/zh/built-in-nodes/ClipTextEncodeHunyuanDit.mdx index 75d299fed..aaa79d92f 100644 --- a/zh/built-in-nodes/ClipTextEncodeHunyuanDit.mdx +++ b/zh/built-in-nodes/ClipTextEncodeHunyuanDit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeHunyuanDiT" icon: "circle" mode: wide --- + `CLIPTextEncodeHunyuanDiT` 节点将文本描述转换为 HunyuanDiT 模型可理解的格式。这是一个专为 HunyuanDiT 双文本编码器架构设计的高级条件节点，通过不同的分词器处理两个独立的文本输入。 ## 输入 diff --git a/zh/built-in-nodes/ClipTextEncodeSdxl.mdx b/zh/built-in-nodes/ClipTextEncodeSdxl.mdx index dfbce137b..eb1b84ef5 100644 --- a/zh/built-in-nodes/ClipTextEncodeSdxl.mdx +++ b/zh/built-in-nodes/ClipTextEncodeSdxl.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSDXL" icon: "circle" mode: wide --- + 此节点专门用于通过针对 SDXL 架构定制的 CLIP 模型对文本输入进行编码。它采用双编码器系统（CLIP-L 和 CLIP-G）来处理文本描述，从而生成更精确的图像。 ## 输入 diff --git a/zh/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx b/zh/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx index 702486fe5..924d69bdf 100644 --- a/zh/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx +++ b/zh/built-in-nodes/ClipTextEncodeSdxlRefiner.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPTextEncodeSDXLRefiner" icon: "circle" mode: wide --- + 此节点专为 SDXL Refiner 模型设计，通过引入美学评分和尺寸信息，将文本提示转换为条件信息，以增强生成任务的条件，从而提升最终的细化效果。它就像一位专业的艺术总监，不仅传达您的创作意图，还能为作品注入精确的美学标准与规格要求。 ## 关于 SDXL Refiner diff --git a/zh/built-in-nodes/ClipVisionEncode.mdx b/zh/built-in-nodes/ClipVisionEncode.mdx index c9b26b895..219d3cbf3 100644 --- a/zh/built-in-nodes/ClipVisionEncode.mdx +++ b/zh/built-in-nodes/ClipVisionEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPVisionEncode" icon: "circle" mode: wide --- + `CLIP Vision Encode` 节点是 ComfyUI 中的图像编码节点，用于通过 CLIP Vision 模型将输入图像转换为视觉特征向量。该节点是连接图像与文本理解的重要桥梁，广泛应用于各类 AI 图像生成与处理工作流中。 **节点功能** diff --git a/zh/built-in-nodes/ClipVisionLoader.mdx b/zh/built-in-nodes/ClipVisionLoader.mdx index e6e7252ce..c9829f4f9 100644 --- a/zh/built-in-nodes/ClipVisionLoader.mdx +++ b/zh/built-in-nodes/ClipVisionLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CLIPVisionLoader" icon: "circle" mode: wide --- + 此节点会自动检测位于 `ComfyUI/models/clip_vision` 文件夹中的模型，以及 `extra_model_paths.yaml` 文件中配置的任何额外模型路径。如果在启动 ComfyUI 后添加了模型，请**刷新 ComfyUI 界面**，以确保列出最新的模型文件。 ## 输入 diff --git a/zh/built-in-nodes/ColorToRGBInt.mdx b/zh/built-in-nodes/ColorToRGBInt.mdx index 9695e8c43..1145e6512 100644 --- a/zh/built-in-nodes/ColorToRGBInt.mdx +++ b/zh/built-in-nodes/ColorToRGBInt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ColorToRGBInt" icon: "circle" mode: wide --- + ColorToRGBInt 节点将十六进制格式指定的颜色转换为单个整数值。它接收类似 `#FF5733` 的颜色字符串，并通过组合红色、绿色和蓝色分量来计算对应的 RGB 整数。 ## 输入 @@ -19,7 +20,7 @@ ColorToRGBInt 节点将十六进制格式指定的颜色转换为单个整数值 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `rgb_int` | 计算出的 RGB 整数值。该值通过以下公式得出：`(红色值 * 65536) + (绿色值 * 256) + 蓝色值`。 | INT | +| `rgb整数` | 计算出的 RGB 整数值。该值通过以下公式得出：`(红色值 * 65536) + (绿色值 * 256) + 蓝色值`。 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ColorToRGBInt/zh.md) diff --git a/zh/built-in-nodes/ColorTransfer.mdx b/zh/built-in-nodes/ColorTransfer.mdx index 36ff55025..027ab13b1 100644 --- a/zh/built-in-nodes/ColorTransfer.mdx +++ b/zh/built-in-nodes/ColorTransfer.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ColorTransfer" icon: "circle" mode: wide --- + ColorTransfer 节点用于调整目标图像的调色板，使其与参考图像的颜色相匹配。它采用不同的数学算法，分析并将参考图像的色彩特征（如亮度、对比度和色调分布）迁移至目标图像。此功能有助于在多张图像之间实现视觉一致性，或应用特定的色彩分级效果。 ## 输入 diff --git a/zh/built-in-nodes/CombineHooks.mdx b/zh/built-in-nodes/CombineHooks.mdx index 0a377ec56..4b45b7f4f 100644 --- a/zh/built-in-nodes/CombineHooks.mdx +++ b/zh/built-in-nodes/CombineHooks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooks" icon: "circle" mode: wide --- + 组合钩子 [2] 节点将两个钩子组合合并为一个统一的组合钩子。它接收两个可选的钩子输入，并利用 ComfyUI 的钩子组合功能将其合并。这使您能够整合多个钩子配置，以实现简化的处理流程。 ## 输入 diff --git a/zh/built-in-nodes/CombineHooksEight.mdx b/zh/built-in-nodes/CombineHooksEight.mdx index 8587f19f6..b4e87e8a8 100644 --- a/zh/built-in-nodes/CombineHooksEight.mdx +++ b/zh/built-in-nodes/CombineHooksEight.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooksEight" icon: "circle" mode: wide --- + 组合钩子 [8] 节点将最多八个不同的钩子组合合并为一个统一的组合钩子组合。它接收多个钩子输入，并利用 ComfyUI 的钩子组合功能将其合并。这使得您可以整合多个钩子配置，从而在高级工作流中实现精简处理。 ## 输入 diff --git a/zh/built-in-nodes/CombineHooksFour.mdx b/zh/built-in-nodes/CombineHooksFour.mdx index 2119f568f..9c5090c70 100644 --- a/zh/built-in-nodes/CombineHooksFour.mdx +++ b/zh/built-in-nodes/CombineHooksFour.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CombineHooksFour" icon: "circle" mode: wide --- + 组合钩子 [4] 节点将最多四个独立的钩子组合合并为一个组合钩子组。它接收四个可用钩子输入的任何组合，并使用 ComfyUI 的钩子组合系统进行合并。这使得您可以整合多个钩子配置，以便在高级工作流程中实现流线化处理。 ## 输入 diff --git a/zh/built-in-nodes/ComboOptionTestNode.mdx b/zh/built-in-nodes/ComboOptionTestNode.mdx index aa217745d..b0a34ab20 100644 --- a/zh/built-in-nodes/ComboOptionTestNode.mdx +++ b/zh/built-in-nodes/ComboOptionTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComboOptionTestNode" icon: "circle" mode: wide --- + ComboOptionTestNode 是一个逻辑节点，用于测试和传递组合框选择。它接收两个组合框输入，每个输入包含一组预定义选项，并直接输出所选值，不做任何修改。 ## 输入 diff --git a/zh/built-in-nodes/ComfyAndNode.mdx b/zh/built-in-nodes/ComfyAndNode.mdx index 1e8403a69..50b1406e4 100644 --- a/zh/built-in-nodes/ComfyAndNode.mdx +++ b/zh/built-in-nodes/ComfyAndNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyAndNode" icon: "circle" mode: wide --- + ## ## 概述 And 节点对一组输入值执行逻辑与运算。仅当所有提供的值根据 Python 的真值规则均被视为真值时，才返回 `true`。此节点适用于在继续操作前检查多个条件是否全部满足。 diff --git a/zh/built-in-nodes/ComfyMathExpression.mdx b/zh/built-in-nodes/ComfyMathExpression.mdx index af986e97d..7fb8d1e4a 100644 --- a/zh/built-in-nodes/ComfyMathExpression.mdx +++ b/zh/built-in-nodes/ComfyMathExpression.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyMathExpression" icon: "circle" mode: wide --- + ComfyMathExpression 节点使用一组输入值计算数学公式。您可以编写包含变量名（如 `a`、`b`、`c`）的表达式，节点将计算结果。它支持根据计算需要动态添加任意数量的输入值。 ## 输入 @@ -25,7 +26,7 @@ ComfyMathExpression 节点使用一组输入值计算数学公式。您可以编 | --- | --- | --- | | `FLOAT` | 数学表达式的结果，以浮点数形式返回。 | FLOAT | | `布尔值` | 数学表达式的结果，以整数形式返回。 | INT | -| `BOOL` | 数学表达式的结果，以布尔值形式返回。 | BOOLEAN | +| `布尔值` | 数学表达式的结果，以布尔值形式返回。 | BOOLEAN | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfyMathExpression/zh.md) diff --git a/zh/built-in-nodes/ComfyNotNode.mdx b/zh/built-in-nodes/ComfyNotNode.mdx index 76a1c3f39..9b14456d1 100644 --- a/zh/built-in-nodes/ComfyNotNode.mdx +++ b/zh/built-in-nodes/ComfyNotNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyNotNode" icon: "circle" mode: wide --- + ## ## 概述 Not 节点对任意输入值执行逻辑非运算。如果输入值被视为假值（例如 0、空字符串、None、False），则返回 True；如果输入值为真值，则返回 False。它使用 Python 的标准规则来判断真值性。 diff --git a/zh/built-in-nodes/ComfyNumberConvert.mdx b/zh/built-in-nodes/ComfyNumberConvert.mdx index e651a610b..929ca5b74 100644 --- a/zh/built-in-nodes/ComfyNumberConvert.mdx +++ b/zh/built-in-nodes/ComfyNumberConvert.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfyNumberConvert" icon: "circle" mode: wide --- + 数字转换节点可将多种输入数据类型转换为数值。它接受整数、浮点数、字符串或布尔值类型的单个输入，并产生两个输出：一个浮点数和一个整数。此功能适用于将文本或逻辑值转换为工作流中其他数学或处理节点可用的格式。 ## 输入 diff --git a/zh/built-in-nodes/ComfyOrNode.mdx b/zh/built-in-nodes/ComfyOrNode.mdx index e498ce309..f234ca6a8 100644 --- a/zh/built-in-nodes/ComfyOrNode.mdx +++ b/zh/built-in-nodes/ComfyOrNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ComfyOrNode" icon: "circle" mode: wide --- -# ComfyOrNode ComfyOrNode 对一组输入值执行逻辑或运算。如果根据 Python 的标准真值规则，提供的任意一个值为真，则返回 `true`。 diff --git a/zh/built-in-nodes/ComfySoftSwitchNode.mdx b/zh/built-in-nodes/ComfySoftSwitchNode.mdx index cee7a8c24..137ece73c 100644 --- a/zh/built-in-nodes/ComfySoftSwitchNode.mdx +++ b/zh/built-in-nodes/ComfySoftSwitchNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfySoftSwitchNode" icon: "circle" mode: wide --- + 软开关节点根据布尔条件在两个可能的输入值之间进行选择。当 `switch` 为真时，输出 `on_true` 输入的值；当 `switch` 为假时，输出 `on_false` 输入的值。该节点设计为惰性求值，意味着它仅根据开关状态评估所需的输入。 ## 输入 diff --git a/zh/built-in-nodes/ComfySwitchNode.mdx b/zh/built-in-nodes/ComfySwitchNode.mdx index 2c72a0a71..022240b6a 100644 --- a/zh/built-in-nodes/ComfySwitchNode.mdx +++ b/zh/built-in-nodes/ComfySwitchNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ComfySwitchNode" icon: "circle" mode: wide --- + Switch 节点根据布尔条件在两个可能的输入之间进行选择。当 `switch` 启用时，输出 `on_true` 输入；当 `switch` 禁用时，输出 `on_false` 输入。这使您能够创建工作流中的条件逻辑并选择不同的数据路径。 ## 输入 @@ -21,7 +22,7 @@ Switch 节点根据布尔条件在两个可能的输入之间进行选择。当 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `output` | 选中的数据。如果 `切换` 为 true，则为 `为真时` 输入的值；如果 `切换` 为 false，则为 `为假时` 输入的值。 | MATCH_TYPE | +| `输出` | 选中的数据。如果 `切换` 为 true，则为 `为真时` 输入的值；如果 `切换` 为 false，则为 `为假时` 输入的值。 | MATCH_TYPE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfySwitchNode/zh.md) diff --git a/zh/built-in-nodes/ConditioningAverage.mdx b/zh/built-in-nodes/ConditioningAverage.mdx index 8a904fd23..b6dc6d46b 100644 --- a/zh/built-in-nodes/ConditioningAverage.mdx +++ b/zh/built-in-nodes/ConditioningAverage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningAverage" icon: "circle" mode: wide --- + `ConditioningAverage` 节点用于根据指定权重混合两组不同的条件（如文本提示），生成介于两者之间的新条件向量。通过调整权重参数，您可以灵活控制每组条件对最终结果的影响程度。该功能特别适用于提示插值、风格融合等高级应用场景。 如下图所示，通过调整 `conditioning_to` 的强度，您可以输出介于两个条件之间的结果。 diff --git a/zh/built-in-nodes/ConditioningCombine.mdx b/zh/built-in-nodes/ConditioningCombine.mdx index a8fc1d5ad..d39e79c54 100644 --- a/zh/built-in-nodes/ConditioningCombine.mdx +++ b/zh/built-in-nodes/ConditioningCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningCombine" icon: "circle" mode: wide --- + 此节点将两个条件输入合并为单个输出，有效融合其信息。两个条件通过列表拼接方式进行组合。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningConcat.mdx b/zh/built-in-nodes/ConditioningConcat.mdx index 74dcaa7ed..0cf7c8884 100644 --- a/zh/built-in-nodes/ConditioningConcat.mdx +++ b/zh/built-in-nodes/ConditioningConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningConcat" icon: "circle" mode: wide --- + ConditioningConcat 节点用于拼接条件向量，具体操作是将 'conditioning_from' 向量合并到 'conditioning_to' 向量中。当需要将来自两个来源的条件信息合并为统一的表示时，此操作至关重要。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningMultiply.mdx b/zh/built-in-nodes/ConditioningMultiply.mdx new file mode 100644 index 000000000..d5184dbd7 --- /dev/null +++ b/zh/built-in-nodes/ConditioningMultiply.mdx @@ -0,0 +1,27 @@ +--- +title: "ConditioningMultiply - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConditioningMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConditioningMultiply" +icon: "circle" +mode: wide +--- + +此节点将 conditioning 值乘以指定系数，使您能够缩放 conditioning 对生成过程的影响。其工作原理是将乘数同时应用于主 conditioning 张量和池化输出值。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `conditioning` | 需要缩放的 conditioning 数据 | CONDITIONING | 是 | - | +| `multiplier` | 用于乘以 conditioning 值的系数（默认值：1.0） | FLOAT | 是 | -100.0 至 100.0（步长：0.01） | + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `CONDITIONING` | 经过乘法缩放后的 conditioning 数据 | CONDITIONING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningMultiply/zh.md) + +--- +**Source fingerprint (SHA-256):** `8d241e3d5d91e513c24ade5b4bece4bf879fe093a4be6d53dab11a5a0bf55616` diff --git a/zh/built-in-nodes/ConditioningSetArea.mdx b/zh/built-in-nodes/ConditioningSetArea.mdx index 29795ff56..553a07c00 100644 --- a/zh/built-in-nodes/ConditioningSetArea.mdx +++ b/zh/built-in-nodes/ConditioningSetArea.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetArea" icon: "circle" mode: wide --- + 此节点旨在通过设置条件上下文中的特定区域来修改条件信息。它允许对条件元素进行精确的空间操作，从而基于指定的尺寸和强度实现有针对性的调整和增强。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningSetAreaPercentage.mdx b/zh/built-in-nodes/ConditioningSetAreaPercentage.mdx index b0ac8b0e4..516500ec8 100644 --- a/zh/built-in-nodes/ConditioningSetAreaPercentage.mdx +++ b/zh/built-in-nodes/ConditioningSetAreaPercentage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaPercentage" icon: "circle" mode: wide --- + ConditioningSetAreaPercentage 节点专门用于基于百分比值调整条件元素的区域影响范围。它允许以总图像尺寸的百分比形式指定区域的尺寸和位置，同时通过强度参数调节条件效果的强度。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx b/zh/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx index bd75d6543..ef83d60dc 100644 --- a/zh/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx +++ b/zh/built-in-nodes/ConditioningSetAreaPercentageVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaPercentageVideo" icon: "circle" mode: wide --- + ## 概述 ConditioningSetAreaPercentageVideo 节点通过定义视频生成中的特定空间区域和时间范围来修改 conditioning 数据。您可以使用相对于整体尺寸的百分比值来设置该区域的位置、大小和持续时间。这对于将生成聚焦于视频序列的特定部分非常有用。 diff --git a/zh/built-in-nodes/ConditioningSetAreaStrength.mdx b/zh/built-in-nodes/ConditioningSetAreaStrength.mdx index b5ed3d6ff..fd7247a3d 100644 --- a/zh/built-in-nodes/ConditioningSetAreaStrength.mdx +++ b/zh/built-in-nodes/ConditioningSetAreaStrength.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetAreaStrength" icon: "circle" mode: wide --- + 此节点用于修改给定条件集的强度属性，从而调整条件对生成过程的影响程度或强度。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningSetDefaultAndCombine.mdx b/zh/built-in-nodes/ConditioningSetDefaultAndCombine.mdx index e7823bf00..211a6d8f8 100644 --- a/zh/built-in-nodes/ConditioningSetDefaultAndCombine.mdx +++ b/zh/built-in-nodes/ConditioningSetDefaultAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetDefaultAndCombine" icon: "circle" mode: wide --- + 此节点通过基于钩子的系统，将主要条件输入与默认条件输入相结合。它将两个条件源合并为单一输出，使得当主要条件不完整时，默认条件可作为备用或基础。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningSetMask.mdx b/zh/built-in-nodes/ConditioningSetMask.mdx index 23e030b8f..65182739f 100644 --- a/zh/built-in-nodes/ConditioningSetMask.mdx +++ b/zh/built-in-nodes/ConditioningSetMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetMask" icon: "circle" mode: wide --- + 此节点旨在通过将指定强度的遮罩应用于特定区域来修改生成模型的条件控制。它允许在条件控制中进行针对性调整，从而实现对生成过程更精确的控制。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningSetProperties.mdx b/zh/built-in-nodes/ConditioningSetProperties.mdx index b87705a32..00a8fb371 100644 --- a/zh/built-in-nodes/ConditioningSetProperties.mdx +++ b/zh/built-in-nodes/ConditioningSetProperties.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetProperties" icon: "circle" mode: wide --- + ConditioningSetProperties 节点通过调整强度、区域设置，并应用可选的遮罩、钩子或时间步范围，来修改条件数据（conditioning data）的属性。它允许您通过设置特定参数来控制条件数据在图像生成过程中的应用方式，从而影响生成过程。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx b/zh/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx index e3604eb3c..7a459bddb 100644 --- a/zh/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx +++ b/zh/built-in-nodes/ConditioningSetPropertiesAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetPropertiesAndCombine" icon: "circle" mode: wide --- + ConditioningSetPropertiesAndCombine 节点通过将新条件输入中的属性应用于现有条件输入来修改条件数据。它结合两个条件集，同时控制新条件的强度，并指定条件区域的应用方式。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningSetTimestepRange.mdx b/zh/built-in-nodes/ConditioningSetTimestepRange.mdx index 64a69991c..5ddcaf670 100644 --- a/zh/built-in-nodes/ConditioningSetTimestepRange.mdx +++ b/zh/built-in-nodes/ConditioningSetTimestepRange.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningSetTimestepRange" icon: "circle" mode: wide --- + 此节点旨在通过设置特定的时间步长范围来调整条件作用的时间维度。它允许精确控制条件处理过程的起始点和结束点，从而实现更具针对性和更高效的生成。 ## 输入 diff --git a/zh/built-in-nodes/ConditioningStableAudio.mdx b/zh/built-in-nodes/ConditioningStableAudio.mdx index 97ed0771b..1d49abf1f 100644 --- a/zh/built-in-nodes/ConditioningStableAudio.mdx +++ b/zh/built-in-nodes/ConditioningStableAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningStableAudio" icon: "circle" mode: wide --- + ## 概述 ConditioningStableAudio 节点用于为音频生成的正向和负向条件输入添加时间信息。它设置开始时间和总时长参数，帮助控制音频内容的生成时机和持续时间。此节点通过附加音频特定的时间元数据来修改现有的条件数据。 @@ -22,7 +23,7 @@ ConditioningStableAudio 节点用于为音频生成的正向和负向条件输 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 已应用音频时间信息的修改后正向条件 | CONDITIONING | +| `正面条件` | 已应用音频时间信息的修改后正向条件 | CONDITIONING | | `负面条件` | 已应用音频时间信息的修改后负向条件 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningStableAudio/zh.md) diff --git a/zh/built-in-nodes/ConditioningTimestepsRange.mdx b/zh/built-in-nodes/ConditioningTimestepsRange.mdx index 01e052558..e96d41afb 100644 --- a/zh/built-in-nodes/ConditioningTimestepsRange.mdx +++ b/zh/built-in-nodes/ConditioningTimestepsRange.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningTimestepsRange" icon: "circle" mode: wide --- + ConditioningTimestepsRange 节点会创建三个不同的时间步长范围，用于控制生成过程中条件效果的生效时机。该节点接收起始和结束百分比值，并将整个时间步长范围（0.0 到 1.0）划分为三个区间：指定百分比之间的主范围、起始百分比之前的范围以及结束百分比之后的范围。 ## 输入 @@ -19,8 +20,8 @@ ConditioningTimestepsRange 节点会创建三个不同的时间步长范围， | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `范围前` | 由 start_percent 和 end_percent 定义的主时间步长范围 | TIMESTEPS_RANGE | -| `范围后` | 从 0.0 到 start_percent 的时间步长范围 | TIMESTEPS_RANGE | -| `AFTER_RANGE` | 从 end_percent 到 1.0 的时间步长范围 | TIMESTEPS_RANGE | +| `范围前` | 从 0.0 到 start_percent 的时间步长范围 | TIMESTEPS_RANGE | +| `范围后` | 从 end_percent 到 1.0 的时间步长范围 | TIMESTEPS_RANGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConditioningTimestepsRange/zh.md) diff --git a/zh/built-in-nodes/ConditioningZeroOut.mdx b/zh/built-in-nodes/ConditioningZeroOut.mdx index c91071b2b..36aa4f56d 100644 --- a/zh/built-in-nodes/ConditioningZeroOut.mdx +++ b/zh/built-in-nodes/ConditioningZeroOut.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConditioningZeroOut" icon: "circle" mode: wide --- + 此节点将 conditioning 数据结构中的特定元素归零，从而有效消除它们在后续处理步骤中的影响。它专为高级 conditioning 操作设计，在这些操作中需要直接操控 conditioning 的内部表示。 ## 输入 diff --git a/zh/built-in-nodes/ContextWindowsManual.mdx b/zh/built-in-nodes/ContextWindowsManual.mdx index 908549dc7..13a712adc 100644 --- a/zh/built-in-nodes/ContextWindowsManual.mdx +++ b/zh/built-in-nodes/ContextWindowsManual.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ContextWindowsManual" icon: "circle" mode: wide --- + 上下文窗口（手动）节点允许您在采样期间手动配置模型的上下文窗口。它会创建具有指定长度、重叠和调度模式的上下文片段，以便在处理数据时将其划分为可管理的块，同时保持片段之间的连续性。此节点提供了用于控制上下文窗口应用方式的高级选项，包括噪声混洗、条件保留和因果窗口修复。 ## 输入 diff --git a/zh/built-in-nodes/ControlNetApply.mdx b/zh/built-in-nodes/ControlNetApply.mdx index f57f0dbcf..4b050e72a 100644 --- a/zh/built-in-nodes/ControlNetApply.mdx +++ b/zh/built-in-nodes/ControlNetApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApply" icon: "circle" mode: wide --- + 使用 controlNet 需要对输入图像进行预处理。由于 ComfyUI 初始节点不附带预处理器和 controlNet 模型，请先安装 ControlNet 预处理器 [在此处下载预处理器](https://github.com/Fannovel16/comfy_controlnet_preprocessors) 和相应的 controlNet 模型。 ## 输入 diff --git a/zh/built-in-nodes/ControlNetApplyAdvanced.mdx b/zh/built-in-nodes/ControlNetApplyAdvanced.mdx index 7119ff391..0b2c84f60 100644 --- a/zh/built-in-nodes/ControlNetApplyAdvanced.mdx +++ b/zh/built-in-nodes/ControlNetApplyAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApplyAdvanced" icon: "circle" mode: wide --- + 此节点根据图像和控制网模型，对 conditioning 数据应用高级控制网变换。它允许对控制网对生成内容的影响进行精细调整，从而实现对 conditioning 的更精确和多样化的修改。 ## 输入 @@ -23,7 +24,7 @@ mode: wide | 参数 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 应用控制网变换后的修改版正向 conditioning 数据，反映了基于输入参数所做的增强。 | `CONDITIONING` | +| `正面条件` | 应用控制网变换后的修改版正向 conditioning 数据，反映了基于输入参数所做的增强。 | `CONDITIONING` | | `负面条件` | 应用控制网变换后的修改版负向 conditioning 数据，反映了基于输入参数对特定特征的抑制或移除。 | `CONDITIONING` | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetApplyAdvanced/zh.md) diff --git a/zh/built-in-nodes/ControlNetApplySD3.mdx b/zh/built-in-nodes/ControlNetApplySD3.mdx index 989cd9ca5..93918e324 100644 --- a/zh/built-in-nodes/ControlNetApplySD3.mdx +++ b/zh/built-in-nodes/ControlNetApplySD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetApplySD3" icon: "circle" mode: wide --- + 此节点将 ControlNet 引导应用于 Stable Diffusion 3 的条件控制。它接收正向和负向条件控制输入，以及一个 ControlNet 模型和图像，然后通过可调整的强度和时序参数应用控制引导，以影响生成过程。 **注意：** 此节点已被标记为已弃用，可能在未来的版本中移除。 @@ -26,7 +27,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 应用了 ControlNet 引导后的修改版正向条件控制 | CONDITIONING | +| `正面条件` | 应用了 ControlNet 引导后的修改版正向条件控制 | CONDITIONING | | `负面条件` | 应用了 ControlNet 引导后的修改版负向条件控制 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetApplySD3/zh.md) diff --git a/zh/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx b/zh/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx index f049eaba4..88f10819e 100644 --- a/zh/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx +++ b/zh/built-in-nodes/ControlNetInpaintingAliMamaApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetInpaintingAliMamaApply" icon: "circle" mode: wide --- + ### ControlNetInpaintingAliMamaApply 节点 ControlNetInpaintingAliMamaApply 节点通过将正向和负向条件与控制图像及遮罩相结合，为图像修复任务应用 ControlNet 条件控制。它处理输入图像和遮罩，生成修改后的条件控制，从而引导生成过程，实现对图像修复区域的精确控制。该节点支持强度调整和时序控制，可在生成过程的不同阶段微调 ControlNet 的影响。 @@ -29,7 +30,7 @@ ControlNetInpaintingAliMamaApply 节点通过将正向和负向条件与控制 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 应用 ControlNet 进行图像修复后的修改版正向条件 | CONDITIONING | +| `正面条件` | 应用 ControlNet 进行图像修复后的修改版正向条件 | CONDITIONING | | `负面条件` | 应用 ControlNet 进行图像修复后的修改版负向条件 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ControlNetInpaintingAliMamaApply/zh.md) diff --git a/zh/built-in-nodes/ControlNetLoader.mdx b/zh/built-in-nodes/ControlNetLoader.mdx index 1b4acddd8..51e019a83 100644 --- a/zh/built-in-nodes/ControlNetLoader.mdx +++ b/zh/built-in-nodes/ControlNetLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ControlNetLoader" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/controlnet` 文件夹中的模型，同时也会读取 extra_model_paths.yaml 文件中配置的其他路径中的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够读取相应文件夹中的模型文件。 ControlNetLoader 节点用于从指定路径加载 ControlNet 模型。它在初始化 ControlNet 模型方面发挥着关键作用，这些模型对于对生成内容应用控制机制或基于控制信号修改现有内容至关重要。 diff --git a/zh/built-in-nodes/ConvertArrayToString.mdx b/zh/built-in-nodes/ConvertArrayToString.mdx new file mode 100644 index 000000000..1db3c8b28 --- /dev/null +++ b/zh/built-in-nodes/ConvertArrayToString.mdx @@ -0,0 +1,27 @@ +--- +title: "ConvertArrayToString - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConvertArrayToString node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConvertArrayToString" +icon: "circle" +mode: wide +--- + +将数组转换为字符串节点接收一个项目数组（列表），并将其转换为格式化的 JSON 字符串。当您需要序列化数组数据以便显示、记录或传递给其他期望字符串输入的系统时，此功能非常有用。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 范围 | +|------|------|----------|----------|------| +| `数组` | 要转换为 JSON 字符串的数组 | ARRAY | 是 | - | +| `缩进` | 每级缩进的空格数。0 表示生成紧凑的单行字符串（默认值：2） | INT | 否 | 0 到 8 | + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|----------|------|----------| +| `STRING` | 转换为 JSON 格式字符串的数组 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertArrayToString/zh.md) + +--- +**Source fingerprint (SHA-256):** `ac8397fed0336f546403ee3e1f17d7e8f5973190b102e74943f098bf6905f726` diff --git a/zh/built-in-nodes/ConvertDictionaryToString.mdx b/zh/built-in-nodes/ConvertDictionaryToString.mdx new file mode 100644 index 000000000..8ec520d10 --- /dev/null +++ b/zh/built-in-nodes/ConvertDictionaryToString.mdx @@ -0,0 +1,27 @@ +--- +title: "ConvertDictionaryToString - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ConvertDictionaryToString node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ConvertDictionaryToString" +icon: "circle" +mode: wide +--- + +此节点将字典（键值对集合）转换为文本字符串，通常采用 JSON 格式。您可以控制缩进级别，使输出更易读或更紧凑。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 取值范围 | +|-----------|-------------|-----------|----------|-------| +| `字典` | 要转换为字符串的字典 | DICT | 是 | - | +| `缩进` | 每级缩进的空格数。0 生成紧凑的单行字符串（默认值：2） | INT | 否 | 0 到 8 | + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `STRING` | 转换为 JSON 格式字符串的字典 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ConvertDictionaryToString/zh.md) + +--- +**Source fingerprint (SHA-256):** `ae4e9889d5347acfc69166bac66f2ba63f5cd37dafab25a9e0aff6bfe7381219` diff --git a/zh/built-in-nodes/ConvertStringToComboNode.mdx b/zh/built-in-nodes/ConvertStringToComboNode.mdx index 9c6b65fba..6e4073106 100644 --- a/zh/built-in-nodes/ConvertStringToComboNode.mdx +++ b/zh/built-in-nodes/ConvertStringToComboNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ConvertStringToComboNode" icon: "circle" mode: wide --- + 将字符串转换为组合节点接收一个文本字符串作为输入，并将其转换为组合数据类型。这使您可以将文本值用作需要组合输入的其他节点的选择项。该节点仅将字符串值原样传递，但会更改其数据类型。 ## 输入 diff --git a/zh/built-in-nodes/CosmosImageToVideoLatent.mdx b/zh/built-in-nodes/CosmosImageToVideoLatent.mdx index a880fc8fe..adcd13844 100644 --- a/zh/built-in-nodes/CosmosImageToVideoLatent.mdx +++ b/zh/built-in-nodes/CosmosImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CosmosImageToVideoLatent" icon: "circle" mode: wide --- + CosmosImageToVideoLatent 节点从输入图像创建视频潜在表示。它会生成一个空白视频潜在表示，并可选择将起始和/或结束图像编码到视频序列的起始和/或结束帧中。当提供图像时，它还会创建相应的噪声掩码，以指示在生成过程中应保留潜在表示的哪些部分。 ## 输入 diff --git a/zh/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx b/zh/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx index eae4ed495..4f71eac84 100644 --- a/zh/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx +++ b/zh/built-in-nodes/CosmosPredict2ImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CosmosPredict2ImageToVideoLatent" icon: "circle" mode: wide --- + CosmosPredict2ImageToVideoLatent 节点用于从图像创建视频潜在表示，以进行视频生成。它可以生成空白视频潜在表示，或结合起始图像和结束图像，创建具有指定尺寸和时长的视频序列。该节点负责将图像编码为适合视频处理的潜在空间格式。 ## 输入 diff --git a/zh/built-in-nodes/CreateBoundingBoxes.mdx b/zh/built-in-nodes/CreateBoundingBoxes.mdx new file mode 100644 index 000000000..52ec315d0 --- /dev/null +++ b/zh/built-in-nodes/CreateBoundingBoxes.mdx @@ -0,0 +1,31 @@ +--- +title: "CreateBoundingBoxes - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the CreateBoundingBoxes node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "CreateBoundingBoxes" +icon: "circle" +mode: wide +--- + +此节点提供一个画布界面，用于在图像中的物体或文本区域周围绘制边界框。它输出像素空间中的边界框坐标、与 Ideogram 提示格式兼容的结构化元素数据，以及显示带有标签和调色板的绘制框的预览图像。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `背景` | 可选图像，用作画布和预览中的背景。 | IMAGE | 否 | - | +| `宽度` | 画布及边界框像素网格的宽度（默认值：1024）。 | INT | 是 | 64 至 16384（步长：16） | +| `高度` | 画布及边界框像素网格的高度（默认值：1024）。 | INT | 是 | 64 至 16384（步长：16） | +| `编辑器状态` | 绘制边界框并设置每个框的类型、文本、描述、调色板。先从背景元素开始，最后处理前景元素。 | BOUNDING_BOXES | 是 | - | + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `preview` | 一张 RGB 图像，显示画布上所有已渲染的边界框，包括标签、调色板色样和描述性文本。 | IMAGE | +| `bboxes` | 像素坐标下的边界框列表，每个框包含 x、y、宽度和高度值。 | BOUNDING_BOX | +| `elements` | 元素对象的结构化数组，每个元素包含类型、边界框坐标（归一化 0-1000）、文本（针对文本类型）、描述和调色板。 | ARRAY | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateBoundingBoxes/zh.md) + +--- +**Source fingerprint (SHA-256):** `a63939f13edc6c6507590a390dcd6d0a3321febb5831baab1655d9952228612c` diff --git a/zh/built-in-nodes/CreateCameraInfo.mdx b/zh/built-in-nodes/CreateCameraInfo.mdx index 0e0609b90..3c2dc2955 100644 --- a/zh/built-in-nodes/CreateCameraInfo.mdx +++ b/zh/built-in-nodes/CreateCameraInfo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateCameraInfo" icon: "circle" mode: wide --- -# 创建相机信息 创建相机信息节点用于构建3D渲染所需的相机信息结构。它支持三种相机定义模式：轨道模式（围绕目标点的偏航/俯仰/距离）、注视模式（显式世界坐标）和四元数模式（位置加旋转）。坐标系采用右手坐标系，Y轴为向上轴。 diff --git a/zh/built-in-nodes/CreateHookKeyframe.mdx b/zh/built-in-nodes/CreateHookKeyframe.mdx index fd7c750bb..62ce5267c 100644 --- a/zh/built-in-nodes/CreateHookKeyframe.mdx +++ b/zh/built-in-nodes/CreateHookKeyframe.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframe" icon: "circle" mode: wide --- + 创建钩子关键帧节点允许您在生成过程中定义钩子行为发生变化的特定点。它会创建关键帧，在生成进度的特定百分比处修改钩子的强度，并且这些关键帧可以串联在一起，形成复杂的调度模式。 ## 输入 @@ -19,7 +20,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `HOOK_KF` | 包含新创建关键帧的一组钩子关键帧 | HOOK_KEYFRAMES | +| `约束关键帧` | 包含新创建关键帧的一组钩子关键帧 | HOOK_KEYFRAMES | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframe/zh.md) diff --git a/zh/built-in-nodes/CreateHookKeyframesFromFloats.mdx b/zh/built-in-nodes/CreateHookKeyframesFromFloats.mdx index 4a6eb41d2..5ecfd0353 100644 --- a/zh/built-in-nodes/CreateHookKeyframesFromFloats.mdx +++ b/zh/built-in-nodes/CreateHookKeyframesFromFloats.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframesFromFloats" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesFromFloats/en.md) 此节点根据浮点强度值列表创建钩子关键帧，并将它们均匀分布在指定的起始和结束百分比之间。它会生成一系列关键帧，其中每个强度值被分配到动画时间轴上的特定百分比位置。该节点可以创建新的关键帧组，也可以添加到现有关键帧组中，并提供一个选项来打印生成的关键帧以用于调试。 @@ -25,7 +26,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `HOOK_KF` | 包含新创建关键帧的钩子关键帧组，可以是新组，也可以是追加到输入关键帧组后的结果 | HOOK_KEYFRAMES | +| `约束关键帧` | 包含新创建关键帧的钩子关键帧组，可以是新组，也可以是追加到输入关键帧组后的结果 | HOOK_KEYFRAMES | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesFromFloats/zh.md) diff --git a/zh/built-in-nodes/CreateHookKeyframesInterpolated.mdx b/zh/built-in-nodes/CreateHookKeyframesInterpolated.mdx index 057396f4f..72b64d9d9 100644 --- a/zh/built-in-nodes/CreateHookKeyframesInterpolated.mdx +++ b/zh/built-in-nodes/CreateHookKeyframesInterpolated.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookKeyframesInterpolated" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesInterpolated/en.md) 在起始点和结束点之间创建一系列具有插值强度值的钩子关键帧。该节点会生成多个关键帧，使强度参数在生成过程的指定百分比范围内平滑过渡，并使用多种插值方法来控制过渡曲线。 @@ -26,7 +27,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `HOOK_KF` | 生成的包含插值序列的钩子关键帧组 | HOOK_KEYFRAMES | +| `约束关键帧` | 生成的包含插值序列的钩子关键帧组 | HOOK_KEYFRAMES | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateHookKeyframesInterpolated/zh.md) diff --git a/zh/built-in-nodes/CreateHookLora.mdx b/zh/built-in-nodes/CreateHookLora.mdx index 7d65a1d58..493f16801 100644 --- a/zh/built-in-nodes/CreateHookLora.mdx +++ b/zh/built-in-nodes/CreateHookLora.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateHookLora" icon: "circle" mode: wide --- -# Create Hook LoRA 节点 此节点用于生成钩子对象，以便对模型应用 LoRA（低秩适配）修改。它加载指定的 LoRA 文件，创建可调整模型和 CLIP 强度的钩子，然后将这些钩子与传入的任何现有钩子合并。该节点通过缓存先前加载的 LoRA 文件来避免冗余操作，从而高效管理 LoRA 加载。 diff --git a/zh/built-in-nodes/CreateHookLoraModelOnly.mdx b/zh/built-in-nodes/CreateHookLoraModelOnly.mdx index 58efcabf1..62979cf23 100644 --- a/zh/built-in-nodes/CreateHookLoraModelOnly.mdx +++ b/zh/built-in-nodes/CreateHookLoraModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookLoraModelOnly" icon: "circle" mode: wide --- + 此节点创建一个仅应用于模型组件的 LoRA（低秩适配）钩子，完全保持 CLIP 组件不变。它加载一个 LoRA 文件，并以指定的强度应用于模型，同时将 CLIP 强度设置为零。该节点可与之前的钩子链接，构建复杂的修改流程。 ## 输入 diff --git a/zh/built-in-nodes/CreateHookModelAsLora.mdx b/zh/built-in-nodes/CreateHookModelAsLora.mdx index db865f70f..235c2f80b 100644 --- a/zh/built-in-nodes/CreateHookModelAsLora.mdx +++ b/zh/built-in-nodes/CreateHookModelAsLora.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookModelAsLora" icon: "circle" mode: wide --- + 此节点通过加载检查点权重并对模型和 CLIP 组件应用强度调整，以 LoRA（低秩适应）方式创建钩子模型。它允许您通过基于钩子的方法对现有模型应用 LoRA 风格的修改，从而实现微调和适应，而无需永久更改模型。该节点可以结合之前的钩子，并缓存已加载的权重以提高效率。 ## 输入 diff --git a/zh/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx b/zh/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx index e37f5455d..6bbf0d740 100644 --- a/zh/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx +++ b/zh/built-in-nodes/CreateHookModelAsLoraModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateHookModelAsLoraModelOnly" icon: "circle" mode: wide --- + 此节点创建一个钩子，将 LoRA（低秩适配）模型应用于神经网络，仅修改模型的组件部分。它会加载一个检查点文件，并以指定的强度将其应用于模型，同时保持 CLIP 组件不变。这是一个实验性节点，扩展了基础 CreateHookModelAsLora 类的功能。 ## 输入 diff --git a/zh/built-in-nodes/CreateList.mdx b/zh/built-in-nodes/CreateList.mdx index 723ac32d0..8440e9ae5 100644 --- a/zh/built-in-nodes/CreateList.mdx +++ b/zh/built-in-nodes/CreateList.mdx @@ -5,7 +5,6 @@ sidebarTitle: "CreateList" icon: "circle" mode: wide --- -# 创建列表节点 创建列表节点将多个输入合并为一个有序列表。它接收任意数量的相同数据类型输入，并按照连接顺序将它们连接起来。此节点适用于准备批处理数据（如图像或文本），以便工作流中的其他节点进行处理。 @@ -21,7 +20,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `list` | 包含所有已连接输入项目的单个列表，按提供的顺序连接。输出数据类型与输入数据类型一致。 | 可变 | +| `列表` | 包含所有已连接输入项目的单个列表，按提供的顺序连接。输出数据类型与输入数据类型一致。 | 可变 | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CreateList/zh.md) diff --git a/zh/built-in-nodes/CreateVideo.mdx b/zh/built-in-nodes/CreateVideo.mdx index 0a266fab9..e0f9ec474 100644 --- a/zh/built-in-nodes/CreateVideo.mdx +++ b/zh/built-in-nodes/CreateVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CreateVideo" icon: "circle" mode: wide --- + 创建视频节点可根据图像序列生成视频文件。您可以通过每秒帧数指定播放速度，并可选择为视频添加音频。该节点将图像合成为视频格式，并以指定的帧率进行播放。 ## 输入 diff --git a/zh/built-in-nodes/CropByBBoxes.mdx b/zh/built-in-nodes/CropByBBoxes.mdx index 6ed7410a0..0356c54cc 100644 --- a/zh/built-in-nodes/CropByBBoxes.mdx +++ b/zh/built-in-nodes/CropByBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CropByBBoxes" icon: "circle" mode: wide --- + CropByBBoxes 节点从输入图像批次中提取并调整特定矩形区域的大小。它使用提供的边界框坐标来定义每个图像的裁剪区域。裁剪后的区域会被调整到指定的输出尺寸，并可以选择拉伸裁剪区域或填充以保持其原始宽高比。 ## 输入 diff --git a/zh/built-in-nodes/CropMask.mdx b/zh/built-in-nodes/CropMask.mdx index b0592919d..db5ea31fd 100644 --- a/zh/built-in-nodes/CropMask.mdx +++ b/zh/built-in-nodes/CropMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CropMask" icon: "circle" mode: wide --- + CropMask节点用于从给定的遮罩中裁剪指定区域。它允许用户通过指定坐标和尺寸来定义感兴趣区域，从而有效提取遮罩的一部分以供进一步处理或分析。 ## 输入 diff --git a/zh/built-in-nodes/CurveEditor.mdx b/zh/built-in-nodes/CurveEditor.mdx index f321aac01..604327ccb 100644 --- a/zh/built-in-nodes/CurveEditor.mdx +++ b/zh/built-in-nodes/CurveEditor.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CurveEditor" icon: "circle" mode: wide --- + 曲线编辑器节点提供了一个可视化界面，用于调整和微调曲线。它允许您修改输入曲线的形状，并可选择通过直方图可视化其分布。该节点输出修改后的曲线，供工作流程的其他部分使用。 ## 输入 diff --git a/zh/built-in-nodes/CustomCombo.mdx b/zh/built-in-nodes/CustomCombo.mdx index 798ee4b1a..80cea357b 100644 --- a/zh/built-in-nodes/CustomCombo.mdx +++ b/zh/built-in-nodes/CustomCombo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "CustomCombo" icon: "circle" mode: wide --- + 自定义组合节点允许您创建包含自定义文本选项列表的下拉菜单。这是一个专注于前端的节点，同时提供后端表示以确保在工作流程中的兼容性。当您从下拉菜单中选择一个选项时，该节点会输出该文本作为字符串及其索引位置。 ## 输入 @@ -21,7 +22,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `索引` | 从自定义组合框中选择的选项的文本字符串。 | STRING | -| `INDEX` | 所选选项在下拉列表中的索引位置。 | INT | +| `索引` | 所选选项在下拉列表中的索引位置。 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CustomCombo/zh.md) diff --git a/zh/built-in-nodes/DA3GeometryToMesh.mdx b/zh/built-in-nodes/DA3GeometryToMesh.mdx new file mode 100644 index 000000000..76fc432ad --- /dev/null +++ b/zh/built-in-nodes/DA3GeometryToMesh.mdx @@ -0,0 +1,32 @@ +--- +title: "DA3GeometryToMesh - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3GeometryToMesh node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3GeometryToMesh" +icon: "circle" +mode: wide +--- + +此节点通过反投影深度图并对生成的点云进行三角剖分，将 DA3_GEOMETRY 数据包转换为 3D 网格。它处理批次中的单个图像，并生成适合 3D 渲染的带纹理或不带纹理的网格。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 包含深度图、可选置信度图、可选天空图及源图像的 DA3_GEOMETRY 数据包 | DA3_GEOMETRY | 是 | - | +| `batch_index` | 要转换的批次中的图像索引。每张图像的顶点数量不同，因此批次无法堆叠（默认值：0） | INT | 是 | 0 至 4096 | +| `decimation` | 顶点步长。1 = 全分辨率，2 = 半分辨率，以此类推（默认值：1） | INT | 是 | 1 至 8 | +| `discontinuity_threshold` | 丢弃 3x3 深度跨度超过此比例的三角形。0 = 关闭（默认值：0.04） | FLOAT | 是 | 0.0 至 1.0 | +| `confidence_threshold` | 排除归一化置信度低于此值的像素。0 = 保留所有像素，1 = 仅保留置信度最高的单个像素。当几何体包含置信度图时使用（Small/Base 模型）（默认值：0.1） | FLOAT | 是 | 0.0 至 1.0 | +| `use_sky_mask` | 从网格中排除天空概率像素（天空 >= 0.5）。当几何体包含天空图时使用（Mono/Metric 模型）（默认值：True） | BOOLEAN | 是 | True 或 False | +| `texture` | 使用源图像作为基础颜色纹理（默认值：True） | BOOLEAN | 是 | True 或 False | + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `MESH` | 包含顶点、面、UV 坐标及可选纹理的三角剖分 3D 网格 | MESH | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToMesh/zh.md) + +--- +**Source fingerprint (SHA-256):** `1d311223a8d131030bcd4930d21852a21ac9dd5758e7f8b8d20b1cf68698893b` diff --git a/zh/built-in-nodes/DA3GeometryToPointCloud.mdx b/zh/built-in-nodes/DA3GeometryToPointCloud.mdx new file mode 100644 index 000000000..f8c5e628e --- /dev/null +++ b/zh/built-in-nodes/DA3GeometryToPointCloud.mdx @@ -0,0 +1,30 @@ +--- +title: "DA3GeometryToPointCloud - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3GeometryToPointCloud node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3GeometryToPointCloud" +icon: "circle" +mode: wide +--- + +此节点将 DA3_GEOMETRY 对象中的深度图转换为 3D 点云。它会根据置信度和天空遮罩进行过滤，并将点转换到适用于多视角场景的通用世界坐标系中。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 必填 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 包含深度数据以及可选的图像、置信度和天空图的 DA3_GEOMETRY 对象 | DA3_GEOMETRY | 是 | - | +| `batch_index` | 要转换的批次中的图像索引（默认值：0） | INT | 是 | 0 至 4096 | +| `confidence_threshold` | 排除每张图像归一化置信度低于此值的像素（0 = 保留所有像素）。当几何体包含置信度图时使用（小型/基础模型）。（默认值：0.1） | FLOAT | 是 | 0.0 至 1.0 | +| `use_sky_mask` | 排除天空概率像素（天空概率 >= 0.5）。当几何体包含天空图时使用（单目/度量模型）。（默认值：True） | BOOLEAN | 是 | True 或 False | +| `downsample` | 每第 N 个像素取一个（1 = 全分辨率）。值越大，点越少，处理速度越快。（默认值：1） | INT | 是 | 1 至 16 | + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `point_cloud` | 包含过滤后的 3D 点、可选颜色和可选置信度值的点云对象 | DA3_POINT_CLOUD | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3GeometryToPointCloud/zh.md) + +--- +**Source fingerprint (SHA-256):** `3cf5bdbb8afdfcfc02f9832a8cbc5a3df49da755dea6df01792aa6ef9e5d7287` diff --git a/zh/built-in-nodes/DA3Inference.mdx b/zh/built-in-nodes/DA3Inference.mdx new file mode 100644 index 000000000..e04e00ccd --- /dev/null +++ b/zh/built-in-nodes/DA3Inference.mdx @@ -0,0 +1,38 @@ +--- +title: "DA3Inference - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3Inference node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3Inference" +icon: "circle" +mode: wide +--- + +此节点在图像上运行 Depth Anything 3 模型，以估算深度和几何信息。在多视图模式下，多张图像作为同一场景的不同视图被一起处理，以生成几何一致的深度图和相机位姿。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `da3_model` | 用于推理的 Depth Anything 3 模型 | DA3_MODEL | 是 | - | +| `image` | 要处理的输入图像或图像集 | IMAGE | 是 | - | +| `resolution` | 模型运行的分辨率（最长边，14 的倍数）。数值越低，运行速度越快且显存占用越少。数值越高，生成的细节越丰富。输出结果会上采样回原始尺寸（默认值：504） | INT | 是 | 140 至 2520（步长：14） | +| `resize_method` | upper_bound_resize：缩放使最长边等于分辨率（限制显存，默认值）。lower_bound_resize：缩放使最短边等于分辨率（在长/宽图像上保留更多细节，但占用更多显存） | COMBO | 是 | `"upper_bound_resize"`
`"lower_bound_resize"` | +| `mode` | mono：单视图图像处理（适用于任何模型变体）。multiview：所有图像一起处理，以获得几何一致性和相机位姿估计（仅适用于 Small 和 Base 模型） | COMBO | 是 | `"mono"`
`"multiview"` | +| `ref_view_strategy` | 在多视图模式下，哪个视图作为几何锚点。saddle_balanced：在所有视图中最平均的视图（最佳通用选择）。saddle_sim_range：与其他视图视觉差异最大的视图。first / middle：固定的位置选择 | COMBO | 否（有条件） | `"saddle_balanced"`
`"saddle_sim_range"`
`"first"`
`"middle"` | +| `pose_method` | 相机视场角的估算方式（仅适用于 Small 和 Base 模型）。cam_dec：从图像特征中学习。ray_pose：从模型的 3D 射线输出中几何推导得出。影响 3D 输出的透视正确性 | COMBO | 否（有条件） | `"cam_dec"`
`"ray_pose"` | + +**关于参数约束的说明：** +- `ref_view_strategy` 和 `pose_method` 参数仅在 `mode` 设置为 `"multiview"` 时可用 +- 多视图模式需要 Small 或 Base 模型变体。具有其他头部类型（如 Metric 或 Mono）的模型不支持跨视图注意力或相机位姿估计 +- 当 `pose_method` 设置为 `"cam_dec"` 时，模型必须具有相机解码器。如果设置为 `"ray_pose"`，模型必须具有 DualDPT 头部 +- 如果所选 `pose_method` 与加载的模型不兼容，将引发错误 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `da3_geometry` | 非归一化张量的字典。始终包含键：depth、image、mode。可选键包括：sky（适用于 Mono/Metric 模型）、confidence（适用于 Small/Base 模型）、extrinsics 和 intrinsics（适用于多视图模式） | DA3_GEOMETRY | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3Inference/zh.md) + +--- +**Source fingerprint (SHA-256):** `e91dd47e6a01719cdd6b6ce8a9bcc45933cac72c5e147ac42906d2f83ab7c250` diff --git a/zh/built-in-nodes/DA3Render.mdx b/zh/built-in-nodes/DA3Render.mdx new file mode 100644 index 000000000..8c96f311b --- /dev/null +++ b/zh/built-in-nodes/DA3Render.mdx @@ -0,0 +1,54 @@ +--- +title: "DA3Render - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the DA3Render node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "DA3Render" +icon: "circle" +mode: wide +--- + +此节点用于从 Depth Anything 3 几何数据渲染可视化结果。根据所选输出模式，可输出深度图、置信度图或天空遮罩。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `da3_geometry` | 包含深度数据以及可选的天空和置信度张量的 Depth Anything 3 几何数据包 | DA3_GEOMETRY | 是 | - | +| `output` | 要渲染的可视化类型。选项包括 depth、depth_colored、sky_mask 和 confidence。每个选项都有其各自的子参数。 | COMBO | 是 | `"depth"`
`"depth_colored"`
`"sky_mask"`
`"confidence"` | + +### `output` 选项的子参数 + +当 `output` 设置为 `"depth"` 或 `"depth_colored"` 时： + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `normalization` | 深度归一化方法。v2_style 使用均值/标准差归一化以获得感知上平衡的结果（默认）。min_max 将完整深度范围拉伸至 [0, 1] 以获得最大对比度。raw 保留 Metric 模型的度量单位，不进行缩放。 | COMBO | 是 | `"v2_style"`
`"min_max"`
`"raw"` | +| `apply_sky_clip` | 在归一化前将天空区域深度裁剪至前景深度的第 99 百分位数。需要在 da3_geometry 输入中包含天空键（仅适用于 Mono/Metric 模型）。默认值：False | BOOLEAN | 是 | True
False | + +当 `output` 设置为 `"sky_mask"` 时： + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `colored` | 对天空遮罩应用 Turbo 颜色映射。默认值：False | BOOLEAN | 是 | True
False | + +当 `output` 设置为 `"confidence"` 时： + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `colored` | 对置信度图应用 Turbo 颜色映射。默认值：False | BOOLEAN | 是 | True
False | + +### 参数约束 + +- 当 `apply_sky_clip` 设置为 True 时，`da3_geometry` 输入必须包含天空张量。此功能仅在使用 Mono 或 Metric 模型时可用。如果缺少天空张量，节点将报错。 +- `sky_mask` 输出选项需要在 `da3_geometry` 输入中包含天空张量。此功能仅适用于 Mono 或 Metric 模型。 +- `confidence` 输出选项需要在 `da3_geometry` 输入中包含置信度张量。此功能仅适用于 Small 或 Base 模型。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `IMAGE` | 渲染后的可视化图像张量。对于深度输出，返回灰度或彩色深度图。对于 sky_mask 和 confidence，根据 colored 参数返回灰度或彩色可视化结果。 | IMAGE | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DA3Render/zh.md) + +--- +**Source fingerprint (SHA-256):** `54d4cde95a916cac26c8a2e19c5623e794d46c0d7652f1c8204f9f2a0deabe0c` diff --git a/zh/built-in-nodes/DCTestNode.mdx b/zh/built-in-nodes/DCTestNode.mdx index 1ae4cde29..aea4098f7 100644 --- a/zh/built-in-nodes/DCTestNode.mdx +++ b/zh/built-in-nodes/DCTestNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DCTestNode" icon: "circle" mode: wide --- + DCTestNode 是一个逻辑节点，根据用户从动态组合框中的选择返回不同类型的数据。它充当条件路由器，所选选项决定哪个输入字段处于活动状态以及节点将输出什么类型的值。 ## 输入 diff --git a/zh/built-in-nodes/DeprecatedCheckpointLoader.mdx b/zh/built-in-nodes/DeprecatedCheckpointLoader.mdx index 2c2157203..0fd88c137 100644 --- a/zh/built-in-nodes/DeprecatedCheckpointLoader.mdx +++ b/zh/built-in-nodes/DeprecatedCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DeprecatedCheckpointLoader" icon: "circle" mode: wide --- + CheckpointLoader 节点专为高级加载操作而设计，具体用于加载模型检查点及其配置。它有助于检索初始化和运行生成模型所需的模型组件，包括来自指定目录的配置和检查点。 ## 输入 diff --git a/zh/built-in-nodes/DeprecatedDiffusersLoader.mdx b/zh/built-in-nodes/DeprecatedDiffusersLoader.mdx index f9e9d74c9..fe84e231f 100644 --- a/zh/built-in-nodes/DeprecatedDiffusersLoader.mdx +++ b/zh/built-in-nodes/DeprecatedDiffusersLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DeprecatedDiffusersLoader" icon: "circle" mode: wide --- + DiffusersLoader 节点专为从 diffusers 库加载模型而设计，能够根据提供的模型路径处理 UNet、CLIP 和 VAE 模型的加载。该节点有助于将这些模型集成到 ComfyUI 框架中，从而实现文本到图像生成、图像处理等高级功能。 ## 输入 diff --git a/zh/built-in-nodes/DiffControlNetLoader.mdx b/zh/built-in-nodes/DiffControlNetLoader.mdx index 384bb22e4..4df20279e 100644 --- a/zh/built-in-nodes/DiffControlNetLoader.mdx +++ b/zh/built-in-nodes/DiffControlNetLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DiffControlNetLoader" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/controlnet` 文件夹中的模型，同时也会读取 extra_model_paths.yaml 文件中配置的额外路径中的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够从相应文件夹中读取模型文件。 DiffControlNetLoader 节点专为加载差分控制网络而设计，这类专用模型能够基于控制网络规范修改其他模型的行为。该节点通过应用差分控制网络，实现对模型行为的动态调整，从而帮助创建定制化的模型输出。 diff --git a/zh/built-in-nodes/DifferentialDiffusion.mdx b/zh/built-in-nodes/DifferentialDiffusion.mdx index 3ba0fdecb..1ad2bcbc5 100644 --- a/zh/built-in-nodes/DifferentialDiffusion.mdx +++ b/zh/built-in-nodes/DifferentialDiffusion.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DifferentialDiffusion" icon: "circle" mode: wide --- + 差分扩散节点通过基于时间步长阈值应用二值掩码来修改去噪过程。它创建了一个掩码，该掩码在原始去噪掩码与基于阈值的二值掩码之间进行混合，从而允许对扩散过程的强度进行可控调整。 ## 输入 diff --git a/zh/built-in-nodes/DiffusersLoader.mdx b/zh/built-in-nodes/DiffusersLoader.mdx index bd9aa3519..19da38dd7 100644 --- a/zh/built-in-nodes/DiffusersLoader.mdx +++ b/zh/built-in-nodes/DiffusersLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DiffusersLoader" icon: "circle" mode: wide --- + DiffusersLoader 节点用于加载 diffusers 格式的预训练模型。它会搜索包含 `model_index.json` 文件的有效 diffusers 模型目录，并将其作为 MODEL、CLIP 和 VAE 组件加载到流程中。此节点属于已弃用的加载器类别，提供与 Hugging Face diffusers 模型的兼容性。 ## 输入 diff --git a/zh/built-in-nodes/DisableNoise.mdx b/zh/built-in-nodes/DisableNoise.mdx index b23448276..8818ff7c9 100644 --- a/zh/built-in-nodes/DisableNoise.mdx +++ b/zh/built-in-nodes/DisableNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DisableNoise" icon: "circle" mode: wide --- + DisableNoise 节点提供了一种空噪声配置，可用于在采样过程中禁用噪声生成。它返回一个不包含任何噪声数据的特殊噪声对象，当其他节点连接到该输出时，可以跳过与噪声相关的操作。 ## 输入 diff --git a/zh/built-in-nodes/DrawBBoxes.mdx b/zh/built-in-nodes/DrawBBoxes.mdx index ad20a471f..b1d1f6adf 100644 --- a/zh/built-in-nodes/DrawBBoxes.mdx +++ b/zh/built-in-nodes/DrawBBoxes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DrawBBoxes" icon: "circle" mode: wide --- + DrawBBoxes 节点通过在图像上绘制边界框、标签和置信度分数来可视化目标检测结果。如果未提供输入图像，则会创建一个足够大的空白画布来容纳所有绘制的框。该节点支持批量处理，允许您为多张图像绘制不同的检测结果，或在整批图像中重复相同的检测结果。 ## 输入 @@ -23,7 +24,7 @@ DrawBBoxes 节点通过在图像上绘制边界框、标签和置信度分数来 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `out_image` | 叠加了绘制的边界框、标签和置信度分数的输出图像。 | IMAGE | +| `输出图像` | 叠加了绘制的边界框、标签和置信度分数的输出图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DrawBBoxes/zh.md) diff --git a/zh/built-in-nodes/DualCFGGuider.mdx b/zh/built-in-nodes/DualCFGGuider.mdx index 7dd306a26..f855adec0 100644 --- a/zh/built-in-nodes/DualCFGGuider.mdx +++ b/zh/built-in-nodes/DualCFGGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DualCFGGuider" icon: "circle" mode: wide --- + DualCFGGuider 节点创建了一个用于双无分类器引导采样的引导系统。它将两个正向条件输入与一个负向条件输入相结合，对每个条件对应用不同的引导尺度，以控制每个提示对生成输出的影响。 ## 输入 diff --git a/zh/built-in-nodes/DualCLIPLoader.mdx b/zh/built-in-nodes/DualCLIPLoader.mdx index c0a03f94c..13bf39b85 100644 --- a/zh/built-in-nodes/DualCLIPLoader.mdx +++ b/zh/built-in-nodes/DualCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "DualCLIPLoader" icon: "circle" mode: wide --- + DualCLIPLoader 节点专为同时加载两个 CLIP 模型而设计，便于执行需要整合或比较两个模型特征的操作。 此节点将检测位于 `ComfyUI/models/text_encoders` 文件夹中的模型。 diff --git a/zh/built-in-nodes/DualModelGuider.mdx b/zh/built-in-nodes/DualModelGuider.mdx index bf7668666..d0e2f35d2 100644 --- a/zh/built-in-nodes/DualModelGuider.mdx +++ b/zh/built-in-nodes/DualModelGuider.mdx @@ -5,7 +5,6 @@ sidebarTitle: "DualModelGuider" icon: "circle" mode: wide --- -# 双模型 CFG 引导器 此节点允许您在引导式 CFG 采样过程中使用两个不同的模型：一个模型用于正向（条件）传递，另一个独立的模型用于负向（无条件）传递。当未提供负向模型时，其行为类似于使用单个模型的标准 CFG 引导器。 diff --git a/zh/built-in-nodes/EasyCache.mdx b/zh/built-in-nodes/EasyCache.mdx index 82e301a07..c343dcf25 100644 --- a/zh/built-in-nodes/EasyCache.mdx +++ b/zh/built-in-nodes/EasyCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EasyCache" icon: "circle" mode: wide --- + EasyCache 节点为模型实现了一个原生缓存系统，通过在采样过程中复用先前计算过的步骤来提升性能。它向模型添加了 EasyCache 功能，并支持在采样时间线上配置何时开始和停止使用缓存的可调阈值。 ## 输入 diff --git a/zh/built-in-nodes/ElevenLabsAudioIsolation.mdx b/zh/built-in-nodes/ElevenLabsAudioIsolation.mdx index 3e9f25c79..35717c56b 100644 --- a/zh/built-in-nodes/ElevenLabsAudioIsolation.mdx +++ b/zh/built-in-nodes/ElevenLabsAudioIsolation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsAudioIsolation" icon: "circle" mode: wide --- + ElevenLabs 语音隔离节点可从音频文件中去除背景噪音，分离出人声或语音。它会将音频发送至 ElevenLabs API 进行处理，并返回清理后的音频。 ## 输入 diff --git a/zh/built-in-nodes/ElevenLabsInstantVoiceClone.mdx b/zh/built-in-nodes/ElevenLabsInstantVoiceClone.mdx index b88098e38..511f92100 100644 --- a/zh/built-in-nodes/ElevenLabsInstantVoiceClone.mdx +++ b/zh/built-in-nodes/ElevenLabsInstantVoiceClone.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ElevenLabsInstantVoiceClone" icon: "circle" mode: wide --- -# ElevenLabs 即时语音克隆节点 此节点通过分析1到8段人声音频录音，创建全新的独特语音模型。它将样本发送至ElevenLabs API，由API处理生成可用于文本转语音合成的语音克隆。 @@ -22,7 +21,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `voice` | 新创建的克隆语音模型的唯一标识符。此输出可连接至其他ElevenLabs文本转语音节点。 | ELEVENLABS_VOICE | +| `语音` | 新创建的克隆语音模型的唯一标识符。此输出可连接至其他ElevenLabs文本转语音节点。 | ELEVENLABS_VOICE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsInstantVoiceClone/zh.md) diff --git a/zh/built-in-nodes/ElevenLabsSpeechToSpeech.mdx b/zh/built-in-nodes/ElevenLabsSpeechToSpeech.mdx index 485a99e6d..767fda3b7 100644 --- a/zh/built-in-nodes/ElevenLabsSpeechToSpeech.mdx +++ b/zh/built-in-nodes/ElevenLabsSpeechToSpeech.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsSpeechToSpeech" icon: "circle" mode: wide --- + ### 概述 ElevenLabs 语音转语音节点可将输入音频文件从一种声音转换为另一种声音。它利用 ElevenLabs API 进行语音转换，同时保留原始音频的内容和情感基调。 diff --git a/zh/built-in-nodes/ElevenLabsSpeechToText.mdx b/zh/built-in-nodes/ElevenLabsSpeechToText.mdx index 5fb4e44f4..7a089ed3b 100644 --- a/zh/built-in-nodes/ElevenLabsSpeechToText.mdx +++ b/zh/built-in-nodes/ElevenLabsSpeechToText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsSpeechToText" icon: "circle" mode: wide --- + ElevenLabs语音转文字节点可将音频文件转录为文本。它使用ElevenLabs的API将语音转换为书面文本，支持自动语言检测、识别不同说话者以及标记音乐、笑声等非语音声音。 ## 输入 @@ -28,9 +29,9 @@ ElevenLabs语音转文字节点可将音频文件转录为文本。它使用Elev | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `语言代码` | 音频转录后的文本。 | STRING | -| `单词 JSON` | 检测到的音频语言代码。 | STRING | -| `words_json` | 包含详细单词级别信息的JSON格式字符串，如果启用则包含时间戳和说话者标签。 | STRING | +| `文本` | 音频转录后的文本。 | STRING | +| `语言代码` | 检测到的音频语言代码。 | STRING | +| `单词 JSON` | 包含详细单词级别信息的JSON格式字符串，如果启用则包含时间戳和说话者标签。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ElevenLabsSpeechToText/zh.md) diff --git a/zh/built-in-nodes/ElevenLabsTextToDialogue.mdx b/zh/built-in-nodes/ElevenLabsTextToDialogue.mdx index a59dde5fd..527632553 100644 --- a/zh/built-in-nodes/ElevenLabsTextToDialogue.mdx +++ b/zh/built-in-nodes/ElevenLabsTextToDialogue.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsTextToDialogue" icon: "circle" mode: wide --- + ElevenLabs 文本转对话节点可根据文本生成多说话人音频对话。您可以通过指定不同的文本行和每个参与者的独特声音来创建对话。该节点将对话请求发送至 ElevenLabs API，并返回生成的音频。 ## 输入 diff --git a/zh/built-in-nodes/ElevenLabsTextToSoundEffects.mdx b/zh/built-in-nodes/ElevenLabsTextToSoundEffects.mdx index 07cd4ef95..e1d71ea12 100644 --- a/zh/built-in-nodes/ElevenLabsTextToSoundEffects.mdx +++ b/zh/built-in-nodes/ElevenLabsTextToSoundEffects.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsTextToSoundEffects" icon: "circle" mode: wide --- + ElevenLabs 文本转音效节点可根据文本描述生成音频音效。该节点利用 ElevenLabs API，基于您的提示词创建音效，并允许您控制时长、循环行为以及音效与文本的匹配程度。 ## 输入 diff --git a/zh/built-in-nodes/ElevenLabsTextToSpeech.mdx b/zh/built-in-nodes/ElevenLabsTextToSpeech.mdx index 16975b6c9..655555a36 100644 --- a/zh/built-in-nodes/ElevenLabsTextToSpeech.mdx +++ b/zh/built-in-nodes/ElevenLabsTextToSpeech.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsTextToSpeech" icon: "circle" mode: wide --- + ElevenLabs文本转语音节点使用ElevenLabs API将书面文本转换为语音音频。它允许您选择特定语音并微调稳定性、速度和风格等各种语音特性，以生成自定义音频输出。 ## 输入 diff --git a/zh/built-in-nodes/ElevenLabsVoiceSelector.mdx b/zh/built-in-nodes/ElevenLabsVoiceSelector.mdx index 9b9e54f7c..b1674f417 100644 --- a/zh/built-in-nodes/ElevenLabsVoiceSelector.mdx +++ b/zh/built-in-nodes/ElevenLabsVoiceSelector.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ElevenLabsVoiceSelector" icon: "circle" mode: wide --- + ElevenLabs 语音选择器节点允许您从预定义的 ElevenLabs 文本转语音语音列表中选择特定语音。它接收语音名称作为输入，并输出音频生成所需的对应语音标识符。此节点简化了选择兼容语音以用于其他 ElevenLabs 音频节点的过程。 ## 输入 diff --git a/zh/built-in-nodes/EmptyARVideoLatent.mdx b/zh/built-in-nodes/EmptyARVideoLatent.mdx index a64bff011..a351993f8 100644 --- a/zh/built-in-nodes/EmptyARVideoLatent.mdx +++ b/zh/built-in-nodes/EmptyARVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyARVideoLatent" icon: "circle" mode: wide --- + ## 概述 EmptyARVideoLatent 节点创建一个用于视频生成的空白潜空间表示。它通过提供指定尺寸、宽高比和长度的零张量来初始化视频生成过程。 diff --git a/zh/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx b/zh/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx index 01863547d..62564c268 100644 --- a/zh/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx +++ b/zh/built-in-nodes/EmptyAceStep1.5LatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAceStep1.5LatentAudio" icon: "circle" mode: wide --- + Empty Ace Step 1.5 Latent Audio 节点创建一个专为音频处理设计的空潜在张量。它会生成指定时长和批次大小的静音音频潜在表示，可作为 ComfyUI 中音频生成工作流的起始点。该节点根据输入的秒数和固定采样率计算潜在长度。 ## 输入 diff --git a/zh/built-in-nodes/EmptyAceStepLatentAudio.mdx b/zh/built-in-nodes/EmptyAceStepLatentAudio.mdx index 24cfb9a2a..f82904b1f 100644 --- a/zh/built-in-nodes/EmptyAceStepLatentAudio.mdx +++ b/zh/built-in-nodes/EmptyAceStepLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAceStepLatentAudio" icon: "circle" mode: wide --- + ## 概述 EmptyAceStepLatentAudio 节点用于创建指定时长的空潜空间音频样本。它会生成一批静音音频潜空间数据，其中填充了零值，长度根据输入的秒数和音频处理参数计算得出。此节点适用于需要潜空间表示的音频处理工作流的初始化。 diff --git a/zh/built-in-nodes/EmptyAudio.mdx b/zh/built-in-nodes/EmptyAudio.mdx index 71a76caf2..75609bd4c 100644 --- a/zh/built-in-nodes/EmptyAudio.mdx +++ b/zh/built-in-nodes/EmptyAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyAudio" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EmptyAudio/en.md) EmptyAudio 节点生成一段指定时长、采样率和声道配置的静音音频片段。它创建一个全零波形，在给定时长内产生完全静音。此节点适用于创建占位音频或在音频工作流中生成静音片段。 diff --git a/zh/built-in-nodes/EmptyChromaRadianceLatentImage.mdx b/zh/built-in-nodes/EmptyChromaRadianceLatentImage.mdx index 7ab9258cc..95fb17cc3 100644 --- a/zh/built-in-nodes/EmptyChromaRadianceLatentImage.mdx +++ b/zh/built-in-nodes/EmptyChromaRadianceLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyChromaRadianceLatentImage" icon: "circle" mode: wide --- + EmptyChromaRadianceLatentImage 节点会创建一个指定尺寸的空白潜空间图像，用于色度辐射工作流。它会生成一个填充为零的张量，作为潜空间操作的起点。该节点允许您定义空白潜空间图像的宽度、高度和批次大小。 ## 输入 diff --git a/zh/built-in-nodes/EmptyCosmosLatentVideo.mdx b/zh/built-in-nodes/EmptyCosmosLatentVideo.mdx index 1a8455a98..e116e3998 100644 --- a/zh/built-in-nodes/EmptyCosmosLatentVideo.mdx +++ b/zh/built-in-nodes/EmptyCosmosLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyCosmosLatentVideo" icon: "circle" mode: wide --- + EmptyCosmosLatentVideo 节点用于创建具有指定维度的空潜在视频张量。它会生成一个填充为零的潜在表示，可作为视频生成工作流的起点，并支持可配置的宽度、高度、长度和批次大小参数。 ## 输入 diff --git a/zh/built-in-nodes/EmptyFlux2LatentImage.mdx b/zh/built-in-nodes/EmptyFlux2LatentImage.mdx index 577c7d932..2c2eebf53 100644 --- a/zh/built-in-nodes/EmptyFlux2LatentImage.mdx +++ b/zh/built-in-nodes/EmptyFlux2LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyFlux2LatentImage" icon: "circle" mode: wide --- + EmptyFlux2LatentImage 节点用于创建空白的潜在表示。它会生成一个填充为零的张量，作为 Flux 模型去噪过程的起始点。潜在表示的尺寸由输入的宽度和高度决定，并会按 16 倍比例缩小。 ## 输入 diff --git a/zh/built-in-nodes/EmptyHiDreamO1LatentImage.mdx b/zh/built-in-nodes/EmptyHiDreamO1LatentImage.mdx index 9be47a8f8..2bad9ed50 100644 --- a/zh/built-in-nodes/EmptyHiDreamO1LatentImage.mdx +++ b/zh/built-in-nodes/EmptyHiDreamO1LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHiDreamO1LatentImage" icon: "circle" mode: wide --- + ## ## 概述 此节点在像素空间中创建一个空的潜在图像，专为 HiDream-O1-Image 模型设计。它生成一个由零填充的空白张量，作为图像生成的起点，其尺寸由宽度、高度和批次大小输入定义。 diff --git a/zh/built-in-nodes/EmptyHunyuanImageLatent.mdx b/zh/built-in-nodes/EmptyHunyuanImageLatent.mdx index 544fe4584..07c21db68 100644 --- a/zh/built-in-nodes/EmptyHunyuanImageLatent.mdx +++ b/zh/built-in-nodes/EmptyHunyuanImageLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanImageLatent" icon: "circle" mode: wide --- + EmptyHunyuanImageLatent 节点用于创建一个具有特定维度的空潜空间张量，供 Hunyuan 图像生成模型使用。它会生成一个空白起始点，可通过工作流中的后续节点进行处理。此节点允许您指定潜空间的宽度、高度和批次大小。 ## 输入 diff --git a/zh/built-in-nodes/EmptyHunyuanLatentVideo.mdx b/zh/built-in-nodes/EmptyHunyuanLatentVideo.mdx index db29e9140..3b212d3b7 100644 --- a/zh/built-in-nodes/EmptyHunyuanLatentVideo.mdx +++ b/zh/built-in-nodes/EmptyHunyuanLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanLatentVideo" icon: "circle" mode: wide --- + `EmptyHunyuanLatentVideo` 节点与 `EmptyLatentImage` 节点类似。您可以将其视为用于视频生成的空白画布，其中宽度、高度和长度定义了画布的属性，而批次大小则决定了要创建的画布数量。此节点会创建准备好用于后续视频生成任务的空白画布。 ## 输入 diff --git a/zh/built-in-nodes/EmptyHunyuanVideo15Latent.mdx b/zh/built-in-nodes/EmptyHunyuanVideo15Latent.mdx index bfa2716d3..8d23a2cf8 100644 --- a/zh/built-in-nodes/EmptyHunyuanVideo15Latent.mdx +++ b/zh/built-in-nodes/EmptyHunyuanVideo15Latent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyHunyuanVideo15Latent" icon: "circle" mode: wide --- + 此节点创建一个空的潜在张量，专门用于 HunyuanVideo 1.5 模型。它通过分配一个具有正确通道数和空间维度的零张量，为视频生成生成一个空白起点，该张量符合模型的潜在空间要求。 ## 输入 diff --git a/zh/built-in-nodes/EmptyImage.mdx b/zh/built-in-nodes/EmptyImage.mdx index 25255613c..19f2b55ea 100644 --- a/zh/built-in-nodes/EmptyImage.mdx +++ b/zh/built-in-nodes/EmptyImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyImage" icon: "circle" mode: wide --- + ## 功能描述 EmptyImage 节点用于创建具有指定尺寸和颜色的空白图像。它可以生成纯色背景图像，通常用作图像处理工作流的起点或背景图像。 diff --git a/zh/built-in-nodes/EmptyLTXVLatentVideo.mdx b/zh/built-in-nodes/EmptyLTXVLatentVideo.mdx index f9f883193..3fa953f9a 100644 --- a/zh/built-in-nodes/EmptyLTXVLatentVideo.mdx +++ b/zh/built-in-nodes/EmptyLTXVLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLTXVLatentVideo" icon: "circle" mode: wide --- + EmptyLTXVLatentVideo 节点用于创建用于视频处理的空潜在张量。它会生成一个具有指定维度的空白起始点，可作为视频生成工作流的输入。该节点会生成一个填充为零的潜在表示，包含配置的宽度、高度、长度和批量大小。 ## 输入 diff --git a/zh/built-in-nodes/EmptyLatentAudio.mdx b/zh/built-in-nodes/EmptyLatentAudio.mdx index 276e56ade..50c586a14 100644 --- a/zh/built-in-nodes/EmptyLatentAudio.mdx +++ b/zh/built-in-nodes/EmptyLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentAudio" icon: "circle" mode: wide --- + ## 概述 EmptyLatentAudio 节点用于创建音频处理的空潜在张量。它会生成一个具有指定时长和批次大小的空白音频潜在表示，可作为音频生成或处理工作流的起点。该节点会根据音频时长和采样率自动计算合适的潜在维度。 diff --git a/zh/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx b/zh/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx index 337650fe2..45d150ad8 100644 --- a/zh/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx +++ b/zh/built-in-nodes/EmptyLatentHunyuan3Dv2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentHunyuan3Dv2" icon: "circle" mode: wide --- + EmptyLatentHunyuan3Dv2 节点可创建专为 Hunyuan3Dv2 3D 生成模型格式化的空白潜空间张量。它会生成具有 Hunyuan3Dv2 架构所需正确尺寸和结构的空潜空间，让您能够从零开始启动 3D 生成工作流程。该节点生成填充为零的潜空间张量，作为后续 3D 生成过程的基础。 ## 输入 diff --git a/zh/built-in-nodes/EmptyLatentImage.mdx b/zh/built-in-nodes/EmptyLatentImage.mdx index 7cc7daaa1..9432ac235 100644 --- a/zh/built-in-nodes/EmptyLatentImage.mdx +++ b/zh/built-in-nodes/EmptyLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyLatentImage" icon: "circle" mode: wide --- + `EmptyLatentImage` 节点用于生成具有指定尺寸和批次大小的空白潜空间表示。该节点是在潜空间中生成或操作图像的基础步骤，为后续的图像合成或修改过程提供起点。 ## 输入 diff --git a/zh/built-in-nodes/EmptyMochiLatentVideo.mdx b/zh/built-in-nodes/EmptyMochiLatentVideo.mdx index 2b0e9e4f4..7af817c74 100644 --- a/zh/built-in-nodes/EmptyMochiLatentVideo.mdx +++ b/zh/built-in-nodes/EmptyMochiLatentVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyMochiLatentVideo" icon: "circle" mode: wide --- + EmptyMochiLatentVideo 节点用于创建一个具有指定维度的空潜空间视频张量。它会生成一个填充为零的潜空间表示，可作为视频生成工作流的起始点。该节点允许您定义潜空间视频张量的宽度、高度、长度和批次大小。 ## 输入 diff --git a/zh/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx b/zh/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx index eacfa5403..108eb0271 100644 --- a/zh/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx +++ b/zh/built-in-nodes/EmptyQwenImageLayeredLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptyQwenImageLayeredLatentImage" icon: "circle" mode: wide --- + 空 Qwen 图像分层潜空间节点会创建一个空白的、多层的潜空间表示，用于 Qwen 图像模型。它会生成一个填充为零的张量，其结构包含指定的层数、批次大小和空间维度。此空潜空间可作为后续图像生成或处理工作流的起点。 ## 输入 diff --git a/zh/built-in-nodes/EmptySD3LatentImage.mdx b/zh/built-in-nodes/EmptySD3LatentImage.mdx index 8f6bf0417..39bdd75ca 100644 --- a/zh/built-in-nodes/EmptySD3LatentImage.mdx +++ b/zh/built-in-nodes/EmptySD3LatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "EmptySD3LatentImage" icon: "circle" mode: wide --- + EmptySD3LatentImage 节点创建一个专为 Stable Diffusion 3 模型格式化的空白潜空间图像张量。它生成一个填充为零的张量，具有 SD3 流水线所期望的正确维度和结构。这通常用作图像生成工作流的起点。 ## 输入 diff --git a/zh/built-in-nodes/Epsilon Scaling.mdx b/zh/built-in-nodes/Epsilon Scaling.mdx index bf94f1431..1184212ab 100644 --- a/zh/built-in-nodes/Epsilon Scaling.mdx +++ b/zh/built-in-nodes/Epsilon Scaling.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Epsilon Scaling" icon: "circle" mode: wide --- + 此节点实现了研究论文《Elucidating the Exposure Bias in Diffusion Models》（arxiv.org/abs/2308.15321v6）中提出的 Epsilon Scaling 方法。其工作原理是在采样过程中缩放预测的噪声，以帮助减少曝光偏差，从而提升生成图像的质量。本实现采用了论文推荐的“均匀调度”（uniform schedule），因其兼具实用性和有效性。 ## 输入 diff --git a/zh/built-in-nodes/ExponentialScheduler.mdx b/zh/built-in-nodes/ExponentialScheduler.mdx index 90c5cb7a7..3fd3c4ca9 100644 --- a/zh/built-in-nodes/ExponentialScheduler.mdx +++ b/zh/built-in-nodes/ExponentialScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ExponentialScheduler" icon: "circle" mode: wide --- + `ExponentialScheduler` 节点旨在为扩散采样过程生成遵循指数调度的一系列 sigma 值。它提供了一种可定制的方法来控制扩散过程中每一步应用的噪声水平，从而实现对采样行为的精细调整。 ## 输入 diff --git a/zh/built-in-nodes/ExtendIntermediateSigmas.mdx b/zh/built-in-nodes/ExtendIntermediateSigmas.mdx index 406ba15bf..72b809a28 100644 --- a/zh/built-in-nodes/ExtendIntermediateSigmas.mdx +++ b/zh/built-in-nodes/ExtendIntermediateSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ExtendIntermediateSigmas" icon: "circle" mode: wide --- + ## 概述 ExtendIntermediateSigmas 节点接收现有的 sigma 值序列，并在它们之间插入额外的中间 sigma 值。您可以指定要添加的额外步数、插值的间隔方法，以及可选的起始和结束 sigma 边界，以控制扩展在 sigma 序列中的发生位置。 diff --git a/zh/built-in-nodes/FeatherMask.mdx b/zh/built-in-nodes/FeatherMask.mdx index 9e813b953..90702c907 100644 --- a/zh/built-in-nodes/FeatherMask.mdx +++ b/zh/built-in-nodes/FeatherMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FeatherMask" icon: "circle" mode: wide --- + `FeatherMask` 节点用于对给定蒙版的边缘应用羽化效果，通过根据距各边缘的指定距离调整边缘的不透明度，使蒙版边缘平滑过渡，从而产生更柔和、更自然的边缘效果。 ## 输入 diff --git a/zh/built-in-nodes/File3DToSplat.mdx b/zh/built-in-nodes/File3DToSplat.mdx index c2b44e34c..adb0ce92f 100644 --- a/zh/built-in-nodes/File3DToSplat.mdx +++ b/zh/built-in-nodes/File3DToSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "File3DToSplat" icon: "circle" mode: wide --- -# File3DToSplat 此节点将包含高斯泼溅数据的 3D 文件转换为可在节点图中使用的高斯泼溅格式。它支持 PLY、SPLAT、KSPLAT 和 SPZ 文件格式，文件格式会根据文件内容自动检测。 diff --git a/zh/built-in-nodes/FlipSigmas.mdx b/zh/built-in-nodes/FlipSigmas.mdx index 8e18f4af1..eea1a5ec7 100644 --- a/zh/built-in-nodes/FlipSigmas.mdx +++ b/zh/built-in-nodes/FlipSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FlipSigmas" icon: "circle" mode: wide --- + `FlipSigmas` 节点旨在通过反转扩散模型中使用的 sigma 值序列顺序，并确保如果第一个值原本为零则将其设为非零值，来操控该序列。此操作对于按相反顺序调整噪声水平至关重要，有助于在通过逐步减少数据噪声来运行的模型中进行生成过程。 ## 输入 diff --git a/zh/built-in-nodes/Flux2ImageNode.mdx b/zh/built-in-nodes/Flux2ImageNode.mdx index bf1b13522..8092292f1 100644 --- a/zh/built-in-nodes/Flux2ImageNode.mdx +++ b/zh/built-in-nodes/Flux2ImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Flux2ImageNode" icon: "circle" mode: wide --- + ## 概述 使用 Flux.2 [pro] 或 Flux.2 [max] 模型，根据文本提示和可选的参考图像生成图像。此节点将您的请求发送至 BFL API，轮询结果，并将生成的图像以张量形式返回。 diff --git a/zh/built-in-nodes/Flux2Scheduler.mdx b/zh/built-in-nodes/Flux2Scheduler.mdx index 4eb8c5b3b..521b4624f 100644 --- a/zh/built-in-nodes/Flux2Scheduler.mdx +++ b/zh/built-in-nodes/Flux2Scheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Flux2Scheduler" icon: "circle" mode: wide --- + Flux2Scheduler 节点为去噪过程生成一系列噪声水平值（sigmas），专门针对 Flux 模型定制。它根据去噪步数和目标图像尺寸计算调度方案，从而影响图像生成过程中噪声去除的进程。 ## 输入 diff --git a/zh/built-in-nodes/FluxDisableGuidance.mdx b/zh/built-in-nodes/FluxDisableGuidance.mdx index 44e31f755..bc777598c 100644 --- a/zh/built-in-nodes/FluxDisableGuidance.mdx +++ b/zh/built-in-nodes/FluxDisableGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxDisableGuidance" icon: "circle" mode: wide --- + 此节点完全禁用Flux及类似模型的引导嵌入功能。它接收条件数据作为输入，通过将引导组件设置为None来移除该组件，从而在生成过程中有效关闭基于引导的条件控制。 ## 输入 diff --git a/zh/built-in-nodes/FluxEraseNode.mdx b/zh/built-in-nodes/FluxEraseNode.mdx index 910080009..5835713b4 100644 --- a/zh/built-in-nodes/FluxEraseNode.mdx +++ b/zh/built-in-nodes/FluxEraseNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxEraseNode" icon: "circle" mode: wide --- -# Flux Erase 节点 从图像中移除遮罩对象并重建背景。在要擦除的对象上绘制遮罩，节点会用合理的背景内容填充该区域。 diff --git a/zh/built-in-nodes/FluxGuidance.mdx b/zh/built-in-nodes/FluxGuidance.mdx index 7de7d637e..2f2c78539 100644 --- a/zh/built-in-nodes/FluxGuidance.mdx +++ b/zh/built-in-nodes/FluxGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxGuidance" icon: "circle" mode: wide --- + ## 输入 | 参数 | 描述 | 数据类型 | diff --git a/zh/built-in-nodes/FluxKVCache.mdx b/zh/built-in-nodes/FluxKVCache.mdx index ca71d8cb9..8fcaa6ff1 100644 --- a/zh/built-in-nodes/FluxKVCache.mdx +++ b/zh/built-in-nodes/FluxKVCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKVCache" icon: "circle" mode: wide --- + Flux KV Cache节点为Flux系列模型启用了键值（KV）缓存优化。该优化通过缓存部分计算结果来提升使用参考图像时的性能，从而加速生成过程。 ## 输入 diff --git a/zh/built-in-nodes/FluxKontextImageScale.mdx b/zh/built-in-nodes/FluxKontextImageScale.mdx index e5575f192..359f1a564 100644 --- a/zh/built-in-nodes/FluxKontextImageScale.mdx +++ b/zh/built-in-nodes/FluxKontextImageScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKontextImageScale" icon: "circle" mode: wide --- + 此节点根据输入图像的宽高比，使用 Lanczos 算法将输入图像缩放至 Flux Kontext 模型训练时使用的最佳尺寸。当输入大尺寸图像时，此节点尤为有用，因为过大的输入可能导致模型输出质量下降或出现输出中包含多个主体等问题。 ## 输入 diff --git a/zh/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx b/zh/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx index f2c496e77..c241f329b 100644 --- a/zh/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx +++ b/zh/built-in-nodes/FluxKontextMultiReferenceLatentMethod.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxKontextMultiReferenceLatentMethod" icon: "circle" mode: wide --- + FluxKontextMultiReferenceLatentMethod 节点通过设置特定的参考潜空间方法（reference latents method）来修改条件数据（conditioning data）。它会将所选方法附加到条件输入中，从而影响后续生成步骤中参考潜空间的处理方式。此节点标记为实验性功能，属于 Flux 条件系统的一部分。 ## 输入 diff --git a/zh/built-in-nodes/FluxProCannyNode.mdx b/zh/built-in-nodes/FluxProCannyNode.mdx index b93767030..435230a29 100644 --- a/zh/built-in-nodes/FluxProCannyNode.mdx +++ b/zh/built-in-nodes/FluxProCannyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProCannyNode" icon: "circle" mode: wide --- + 使用控制图像（canny）生成图像。此节点接收一张控制图像，并根据提供的提示词，在遵循控制图像中检测到的边缘结构的同时生成新图像。 ## 输入 diff --git a/zh/built-in-nodes/FluxProDepthNode.mdx b/zh/built-in-nodes/FluxProDepthNode.mdx index dee7cadbe..c07bb45ff 100644 --- a/zh/built-in-nodes/FluxProDepthNode.mdx +++ b/zh/built-in-nodes/FluxProDepthNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProDepthNode" icon: "circle" mode: wide --- + 此节点使用深度控制图像作为引导来生成图像。它接收一张控制图像和一段文本提示，然后创建一张同时遵循控制图像深度信息与提示描述的新图像。该节点通过连接外部 API 执行图像生成过程。 ## 输入 diff --git a/zh/built-in-nodes/FluxProExpandNode.mdx b/zh/built-in-nodes/FluxProExpandNode.mdx index 912f822d8..56d9c927d 100644 --- a/zh/built-in-nodes/FluxProExpandNode.mdx +++ b/zh/built-in-nodes/FluxProExpandNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProExpandNode" icon: "circle" mode: wide --- + 根据提示词生成图像的外延。此节点通过向上、下、左、右四个方向添加像素来扩展图像，同时生成与提供的文本描述相匹配的新内容。 ## 输入 diff --git a/zh/built-in-nodes/FluxProFillNode.mdx b/zh/built-in-nodes/FluxProFillNode.mdx index 7b21a44ce..d61a3d571 100644 --- a/zh/built-in-nodes/FluxProFillNode.mdx +++ b/zh/built-in-nodes/FluxProFillNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProFillNode" icon: "circle" mode: wide --- + 根据遮罩和提示词对图像进行修复。此节点使用 Flux.1 模型，根据提供的文本描述填充图像的遮罩区域，生成与周围图像匹配的新内容。 ## 输入 diff --git a/zh/built-in-nodes/FluxProImageNode.mdx b/zh/built-in-nodes/FluxProImageNode.mdx index d77b2961f..94d502c4e 100644 --- a/zh/built-in-nodes/FluxProImageNode.mdx +++ b/zh/built-in-nodes/FluxProImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProImageNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProImageNode/en.md) 根据提示和分辨率同步生成图像。此节点通过向 API 端点发送请求并等待完整响应，使用 Flux 1.1 Pro 模型创建图像，然后返回生成的图像。 diff --git a/zh/built-in-nodes/FluxProUltraImageNode.mdx b/zh/built-in-nodes/FluxProUltraImageNode.mdx index c07c5e170..56d48853c 100644 --- a/zh/built-in-nodes/FluxProUltraImageNode.mdx +++ b/zh/built-in-nodes/FluxProUltraImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FluxProUltraImageNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/FluxProUltraImageNode/en.md) 根据提示和分辨率，通过 API 使用 Flux Pro 1.1 Ultra 生成图像。此节点连接外部服务，根据您的文本描述和指定尺寸创建图像。 diff --git a/zh/built-in-nodes/FluxVTONode.mdx b/zh/built-in-nodes/FluxVTONode.mdx index f2a97bee7..65e829e79 100644 --- a/zh/built-in-nodes/FluxVTONode.mdx +++ b/zh/built-in-nodes/FluxVTONode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "FluxVTONode" icon: "circle" mode: wide --- -# Flux 虚拟试穿 此节点通过将提供的服装图像穿在人物身上来执行虚拟试穿。它使用 BFL Flux VTO API 生成人物穿着指定服装的真实感图像。 diff --git a/zh/built-in-nodes/FrameInterpolate.mdx b/zh/built-in-nodes/FrameInterpolate.mdx index 7463c9252..b75156df3 100644 --- a/zh/built-in-nodes/FrameInterpolate.mdx +++ b/zh/built-in-nodes/FrameInterpolate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FrameInterpolate" icon: "circle" mode: wide --- + ## 概述 帧插值节点在图像序列的现有帧之间创建新帧，有效提升帧率。它利用 AI 模型预测中间帧的形态，可用于创建流畅的慢动作效果或提升视频的平滑度。 diff --git a/zh/built-in-nodes/FrameInterpolationModelLoader.mdx b/zh/built-in-nodes/FrameInterpolationModelLoader.mdx index 84ee38b3e..d25da2dbb 100644 --- a/zh/built-in-nodes/FrameInterpolationModelLoader.mdx +++ b/zh/built-in-nodes/FrameInterpolationModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FrameInterpolationModelLoader" icon: "circle" mode: wide --- + ## 概述 此节点从文件加载帧插值模型，并为其在工作流中使用做好准备。它会自动检测模型类型（FILM 或 RIFE），并根据硬件配置模型以实现最佳性能。 diff --git a/zh/built-in-nodes/FreSca.mdx b/zh/built-in-nodes/FreSca.mdx index 18bce78e7..246a1a3a6 100644 --- a/zh/built-in-nodes/FreSca.mdx +++ b/zh/built-in-nodes/FreSca.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreSca" icon: "circle" mode: wide --- + FreSca 节点在采样过程中对引导信号应用频率相关的缩放。它通过傅里叶滤波将引导信号分离为低频和高频分量，然后对每个频率范围应用不同的缩放因子，最后重新组合。这使得能够更精细地控制引导对生成输出不同方面的影响。 ## 输入 diff --git a/zh/built-in-nodes/FreeU.mdx b/zh/built-in-nodes/FreeU.mdx index 4ecd550e7..35a320650 100644 --- a/zh/built-in-nodes/FreeU.mdx +++ b/zh/built-in-nodes/FreeU.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreeU" icon: "circle" mode: wide --- + FreeU 节点通过对模型的输出块应用频域修改来提升图像生成质量。其工作原理是对不同通道组进行缩放，并对特定特征图应用傅里叶滤波，从而在生成过程中实现对模型行为的精细控制。 ## 输入 diff --git a/zh/built-in-nodes/FreeU_V2.mdx b/zh/built-in-nodes/FreeU_V2.mdx index 8e71ff562..020da3bb5 100644 --- a/zh/built-in-nodes/FreeU_V2.mdx +++ b/zh/built-in-nodes/FreeU_V2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "FreeU_V2" icon: "circle" mode: wide --- + FreeU_V2 节点通过对扩散模型的 U-Net 架构应用基于频率的修改，提升图像生成质量。它使用可配置的缩放因子调整不同块中的特征通道，无需额外训练即可改善输出效果。 ## 输入 diff --git a/zh/built-in-nodes/GITSScheduler.mdx b/zh/built-in-nodes/GITSScheduler.mdx index c00208367..209fa0c3a 100644 --- a/zh/built-in-nodes/GITSScheduler.mdx +++ b/zh/built-in-nodes/GITSScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GITSScheduler" icon: "circle" mode: wide --- + GITSScheduler 节点为 GITS（生成式迭代时间步长）采样方法生成噪声调度 sigma 值。它根据系数参数和步数计算 sigma 值，并可通过可选的去噪因子减少实际使用的总步数。该节点使用预定义的噪声水平和插值方法创建最终的 sigma 调度。 ## 输入 diff --git a/zh/built-in-nodes/GLIGENLoader.mdx b/zh/built-in-nodes/GLIGENLoader.mdx index 9e3f4884c..01cda33db 100644 --- a/zh/built-in-nodes/GLIGENLoader.mdx +++ b/zh/built-in-nodes/GLIGENLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLIGENLoader" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/gligen` 文件夹中的模型，同时也会读取 extra_model_paths.yaml 文件中配置的其他路径中的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够从相应文件夹中读取模型文件。 `GLIGENLoader` 节点专为加载 GLIGEN 模型而设计，这些模型是专门的生成式模型。它简化了从指定路径检索和初始化这些模型的过程，使其可用于后续的生成任务。 diff --git a/zh/built-in-nodes/GLIGENTextBoxApply.mdx b/zh/built-in-nodes/GLIGENTextBoxApply.mdx index a2f3f3d90..9ca6772fb 100644 --- a/zh/built-in-nodes/GLIGENTextBoxApply.mdx +++ b/zh/built-in-nodes/GLIGENTextBoxApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLIGENTextBoxApply" icon: "circle" mode: wide --- + `GLIGENTextBoxApply` 节点旨在将基于文本的条件信息集成到生成模型的输入中，具体通过应用文本框参数并使用 CLIP 模型对其进行编码。此过程通过空间和文本信息丰富条件信息，从而促进更精确且更具上下文感知能力的生成。 ## 输入 diff --git a/zh/built-in-nodes/GLSLShader.mdx b/zh/built-in-nodes/GLSLShader.mdx index 3d0f4f4b3..89af94e1f 100644 --- a/zh/built-in-nodes/GLSLShader.mdx +++ b/zh/built-in-nodes/GLSLShader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GLSLShader" icon: "circle" mode: wide --- + The **GLSL Shader** node lets you write custom fragment shaders in **GLSL ES 3.00** (WebGL 2.0 compatible) to process images directly on the GPU. You can create image effects like blurs, color grading, film grain, glow, and much more - all running at GPU speed. diff --git a/zh/built-in-nodes/GeminiImage2Node.mdx b/zh/built-in-nodes/GeminiImage2Node.mdx index 7b0f99c50..e07a5cdcd 100644 --- a/zh/built-in-nodes/GeminiImage2Node.mdx +++ b/zh/built-in-nodes/GeminiImage2Node.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiImage2Node" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiImage2Node/en.md) GeminiImage2Node 使用 Google 的 Vertex AI Gemini 模型生成或编辑图像。它向 API 发送文本提示词以及可选的参考图像或文件，并返回生成的图像和/或文本描述。 diff --git a/zh/built-in-nodes/GeminiImageNode.mdx b/zh/built-in-nodes/GeminiImageNode.mdx index 420565e96..d4fec32c3 100644 --- a/zh/built-in-nodes/GeminiImageNode.mdx +++ b/zh/built-in-nodes/GeminiImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiImageNode" icon: "circle" mode: wide --- + GeminiImage 节点通过 Google 的 Gemini AI 模型生成文本和图像响应。它允许您提供多模态输入，包括文本提示、图像和文件，以生成连贯的文本和图像输出。该节点处理与最新 Gemini 模型的所有 API 通信和响应解析。 ## 输入 diff --git a/zh/built-in-nodes/GeminiInputFiles.mdx b/zh/built-in-nodes/GeminiInputFiles.mdx index 3a757e3f2..55633d241 100644 --- a/zh/built-in-nodes/GeminiInputFiles.mdx +++ b/zh/built-in-nodes/GeminiInputFiles.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiInputFiles" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiInputFiles/en.md) 加载输入文件并将其格式化，以便与 Gemini API 配合使用。此节点允许用户将文本（.txt）和 PDF（.pdf）文件作为输入上下文包含到 Gemini 模型中。文件会被转换为 API 所需的格式，并且可以链接在一起，以便在单个请求中包含多个文件。 diff --git a/zh/built-in-nodes/GeminiNanoBanana2.mdx b/zh/built-in-nodes/GeminiNanoBanana2.mdx index 2ab7c0bed..8fd9aeb47 100644 --- a/zh/built-in-nodes/GeminiNanoBanana2.mdx +++ b/zh/built-in-nodes/GeminiNanoBanana2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiNanoBanana2" icon: "circle" mode: wide --- + GeminiNanoBanana2 节点使用 Google 的 Vertex AI Gemini 模型生成或编辑图像。其工作原理是将文本提示以及可选的参考图像或文件发送至 API，并返回生成的图像及任何附带的文本。 ## 输入 diff --git a/zh/built-in-nodes/GeminiNanoBanana2V2.mdx b/zh/built-in-nodes/GeminiNanoBanana2V2.mdx index 6fe51f680..de8186fe6 100644 --- a/zh/built-in-nodes/GeminiNanoBanana2V2.mdx +++ b/zh/built-in-nodes/GeminiNanoBanana2V2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiNanoBanana2V2" icon: "circle" mode: wide --- + ## 概述 此节点通过向 Google 的 Vertex AI API 发送文本提示来生成或编辑图像。它使用特定的 Gemini 模型，根据您的指令创建新图像或修改现有图像。 diff --git a/zh/built-in-nodes/GeminiNode.mdx b/zh/built-in-nodes/GeminiNode.mdx index 6d8882d0b..1ae3e13a3 100644 --- a/zh/built-in-nodes/GeminiNode.mdx +++ b/zh/built-in-nodes/GeminiNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GeminiNode" icon: "circle" mode: wide --- + 此节点允许用户与 Google 的 Gemini AI 模型交互，以生成文本回复。您可以提供多种类型的输入，包括文本、图像、音频、视频和文件，作为模型的上下文，从而生成更相关、更有意义的回复。该节点会自动处理所有 API 通信和响应解析。 ## 输入 diff --git a/zh/built-in-nodes/GeminiNodeV2.mdx b/zh/built-in-nodes/GeminiNodeV2.mdx index 505181103..b3b419b33 100644 --- a/zh/built-in-nodes/GeminiNodeV2.mdx +++ b/zh/built-in-nodes/GeminiNodeV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GeminiNodeV2" icon: "circle" mode: wide --- -# Google Gemini 使用 Google 的 Gemini 模型生成文本回复。提供文本提示，并可选择性地提供一个或多个图像、音频片段、视频或文件作为多模态上下文。 diff --git a/zh/built-in-nodes/GeminiVideoOmni.mdx b/zh/built-in-nodes/GeminiVideoOmni.mdx new file mode 100644 index 000000000..a2895b2cf --- /dev/null +++ b/zh/built-in-nodes/GeminiVideoOmni.mdx @@ -0,0 +1,33 @@ +--- +title: "GeminiVideoOmni - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the GeminiVideoOmni node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "GeminiVideoOmni" +icon: "circle" +mode: wide +--- + +使用 Google 的 Gemini Omni Flash 模型，根据文本提示生成带音频的视频。可选择提供参考图像和/或视频来引导或编辑生成结果。请在提示中直接描述所需的时长（3-10 秒）和宽高比（16:9 或 9:16）。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `model` | 用于生成视频的 Gemini 视频模型。 | MODEL | 是 | "Omni Flash" | +| `seed` | 种子控制节点是否应重新运行；无论种子如何，结果均非确定性（默认值：42）。 | INT | 是 | 0 至 2147483647 | +| `prompt` | 描述要生成视频的文本提示。 | STRING | 是 | 去除首尾空格后至少 1 个字符 | +| `images` | 可选参考图像，用于引导视频生成。最多 14 张图像。 | IMAGE | 否 | 允许多张图像（最多 14 张） | +| `videos` | 可选参考视频，用于引导或编辑视频生成。最多 3 个视频，每个最长 10 秒。 | VIDEO | 否 | 允许多个视频（最多 3 个，每个最长 10 秒） | +| `temperature` | 控制生成过程中的随机性（默认值：1.0）。 | FLOAT | 否 | 0.0 至 2.0 | +| `top_p` | 核采样参数（默认值：0.95）。 | FLOAT | 否 | 0.0 至 1.0 | + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `VIDEO` | 由 Gemini 模型生成的带音频的视频。 | VIDEO | +| `STRING` | 模型的任何文本响应，例如推理过程或解释。 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GeminiVideoOmni/zh.md) + +--- +**Source fingerprint (SHA-256):** `046842b7ec736283bba355aaa038b02fcf2416020f5f7aee7b0150d2a05bcbe6` diff --git a/zh/built-in-nodes/GenerateTracks.mdx b/zh/built-in-nodes/GenerateTracks.mdx index 09d02e2c4..c5c3846e3 100644 --- a/zh/built-in-nodes/GenerateTracks.mdx +++ b/zh/built-in-nodes/GenerateTracks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GenerateTracks" icon: "circle" mode: wide --- + `GenerateTracks` 节点用于为视频生成创建多条平行运动路径。它定义一条从起点到终点的主路径，然后生成一组与该路径平行且等距分布的轨道。您可以控制路径的形状（直线或贝塞尔曲线）、沿路径移动的速度以及轨道可见的帧范围。 ## 输入 @@ -33,7 +34,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `轨迹长度` | 一个轨道对象，包含所有帧中所有轨道的生成路径坐标和可见性信息。 | TRACKS | -| `track_length` | 生成轨道的帧数，与输入的 `帧数` 一致。 | INT | +| `轨迹长度` | 生成轨道的帧数，与输入的 `帧数` 一致。 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GenerateTracks/zh.md) diff --git a/zh/built-in-nodes/GetICLoRAParameters.mdx b/zh/built-in-nodes/GetICLoRAParameters.mdx index 356c309b2..f01842884 100644 --- a/zh/built-in-nodes/GetICLoRAParameters.mdx +++ b/zh/built-in-nodes/GetICLoRAParameters.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetICLoRAParameters" icon: "circle" mode: wide --- + ## ## 概述 此节点从已加载 LoRA 模型的元数据中提取 IC-LoRA 参数。它会读取 safetensors 元数据以查找参考降采样因子等值，并将它们输出为结构化的参数对象，该对象可连接到 LTXVAddGuide 节点以进行特殊引导处理。 diff --git a/zh/built-in-nodes/GetImageSize.mdx b/zh/built-in-nodes/GetImageSize.mdx index 4f9cb5e83..0667130d2 100644 --- a/zh/built-in-nodes/GetImageSize.mdx +++ b/zh/built-in-nodes/GetImageSize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetImageSize" icon: "circle" mode: wide --- + GetImageSize 节点从输入图像中提取尺寸和批次信息。它返回图像的宽度、高度和批次大小，同时将这些信息作为进度文本显示在节点界面上。原始图像数据会原样通过。 ## 输入 @@ -17,9 +18,9 @@ GetImageSize 节点从输入图像中提取尺寸和批次信息。它返回图 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `高度` | 输入图像的宽度（像素） | INT | -| `批处理大小` | 输入图像的高度（像素） | INT | -| `batch_size` | 批次中的图像数量 | INT | +| `宽度` | 输入图像的宽度（像素） | INT | +| `高度` | 输入图像的高度（像素） | INT | +| `批处理大小` | 批次中的图像数量 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetImageSize/zh.md) diff --git a/zh/built-in-nodes/GetSplatCount.mdx b/zh/built-in-nodes/GetSplatCount.mdx index 3422a156f..9b3170ea4 100644 --- a/zh/built-in-nodes/GetSplatCount.mdx +++ b/zh/built-in-nodes/GetSplatCount.mdx @@ -5,7 +5,6 @@ sidebarTitle: "GetSplatCount" icon: "circle" mode: wide --- -# 获取 Splat 计数 获取 Splat 计数节点返回 splat 批次中的 splat（高斯点）总数，该计数是对批次中所有项目求和得出的。它会在提供 splat 数量的同时，将原始 splat 数据原样传递出去。 diff --git a/zh/built-in-nodes/GetVideoComponents.mdx b/zh/built-in-nodes/GetVideoComponents.mdx index 6498d18de..7e873faef 100644 --- a/zh/built-in-nodes/GetVideoComponents.mdx +++ b/zh/built-in-nodes/GetVideoComponents.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GetVideoComponents" icon: "circle" mode: wide --- + 获取视频组件节点可从视频文件中提取所有主要元素。它将视频分离为单独的帧，提取音频轨道，并提供视频的帧率信息。这样您就可以独立处理每个组件，以便进行进一步处理或分析。 ## 输入 @@ -17,9 +18,9 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `音频` | 从视频中提取的单独帧，作为独立图像。 | IMAGE | -| `帧率` | 从视频中提取的音频轨道。 | AUDIO | -| `fps` | 视频的帧率，以每秒帧数为单位。 | FLOAT | +| `图像` | 从视频中提取的单独帧，作为独立图像。 | IMAGE | +| `音频` | 从视频中提取的音频轨道。 | AUDIO | +| `帧率` | 视频的帧率，以每秒帧数为单位。 | FLOAT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetVideoComponents/zh.md) diff --git a/zh/built-in-nodes/GrokImageEditNode.mdx b/zh/built-in-nodes/GrokImageEditNode.mdx index 81dc25905..710134e72 100644 --- a/zh/built-in-nodes/GrokImageEditNode.mdx +++ b/zh/built-in-nodes/GrokImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokImageEditNode" icon: "circle" mode: wide --- + Grok 图像编辑节点根据文本提示修改现有图像。它使用 Grok API 生成一个或多个基于输入图像变体的新图像，并由您的描述进行引导。 ## 输入 diff --git a/zh/built-in-nodes/GrokImageEditNodeV2.mdx b/zh/built-in-nodes/GrokImageEditNodeV2.mdx index 811ffa81a..24f71211c 100644 --- a/zh/built-in-nodes/GrokImageEditNodeV2.mdx +++ b/zh/built-in-nodes/GrokImageEditNodeV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokImageEditNodeV2" icon: "circle" mode: wide --- + ## 概述 根据文本提示修改现有图像。此节点将您的图像和文本描述发送至 Grok API，该 API 会根据您的指令编辑图像并返回结果。 diff --git a/zh/built-in-nodes/GrokImageNode.mdx b/zh/built-in-nodes/GrokImageNode.mdx index 1b8ad7e62..95237fd54 100644 --- a/zh/built-in-nodes/GrokImageNode.mdx +++ b/zh/built-in-nodes/GrokImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokImageNode" icon: "circle" mode: wide --- + Grok Image 节点使用 Grok AI 模型，基于文本描述生成一张或多张图像。它会将您的提示词发送至外部服务，并将生成的图像以张量形式返回，供您在工作流中使用。 ## 输入 diff --git a/zh/built-in-nodes/GrokVideoEditNode.mdx b/zh/built-in-nodes/GrokVideoEditNode.mdx index 64e7e6d6c..91df24ee9 100644 --- a/zh/built-in-nodes/GrokVideoEditNode.mdx +++ b/zh/built-in-nodes/GrokVideoEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoEditNode" icon: "circle" mode: wide --- + 此节点使用 Grok API 基于文本提示编辑现有视频。它会上传您的视频，向 AI 模型发送请求以根据您的描述进行修改，并返回新生成的视频。 ## 输入 diff --git a/zh/built-in-nodes/GrokVideoExtendNode.mdx b/zh/built-in-nodes/GrokVideoExtendNode.mdx index 9af21d5f7..ba07ee357 100644 --- a/zh/built-in-nodes/GrokVideoExtendNode.mdx +++ b/zh/built-in-nodes/GrokVideoExtendNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoExtendNode" icon: "circle" mode: wide --- + ## 概述 Grok 视频扩展节点使用 AI 模型为现有视频创建无缝延续。您提供一段短视频和描述接下来应发生什么的文本提示，该节点将生成一段接续原视频的新视频片段。 diff --git a/zh/built-in-nodes/GrokVideoNode.mdx b/zh/built-in-nodes/GrokVideoNode.mdx index 1609d698c..888d0ab64 100644 --- a/zh/built-in-nodes/GrokVideoNode.mdx +++ b/zh/built-in-nodes/GrokVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoNode" icon: "circle" mode: wide --- + Grok Video 节点可根据文本描述生成短视频。它可以通过提示词从零创建视频，或基于提示词对单张输入图像进行动画处理。该节点向外部 API 发送请求并返回生成的视频。 ## 输入 diff --git a/zh/built-in-nodes/GrokVideoReferenceNode.mdx b/zh/built-in-nodes/GrokVideoReferenceNode.mdx index 6a2e5f7c5..a9f0e00b7 100644 --- a/zh/built-in-nodes/GrokVideoReferenceNode.mdx +++ b/zh/built-in-nodes/GrokVideoReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrokVideoReferenceNode" icon: "circle" mode: wide --- + Grok 参考转视频节点根据文本提示生成视频，并使用最多七张参考图像来引导输出的风格和内容。该节点连接外部 API 创建视频，随后下载并返回结果。 ## 输入 diff --git a/zh/built-in-nodes/GrowMask.mdx b/zh/built-in-nodes/GrowMask.mdx index 4f5fa23dd..524a731a9 100644 --- a/zh/built-in-nodes/GrowMask.mdx +++ b/zh/built-in-nodes/GrowMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "GrowMask" icon: "circle" mode: wide --- + `GrowMask` 节点用于修改给定遮罩的尺寸，可将其扩大或收缩，同时可选择对边角应用渐变效果。此功能对于在图像处理任务中动态调整遮罩边界至关重要，可更灵活、更精确地控制感兴趣区域。 ## 输入 diff --git a/zh/built-in-nodes/HappyHorseImageToVideoApi.mdx b/zh/built-in-nodes/HappyHorseImageToVideoApi.mdx index 3c7d4883c..bb1707b49 100644 --- a/zh/built-in-nodes/HappyHorseImageToVideoApi.mdx +++ b/zh/built-in-nodes/HappyHorseImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseImageToVideoApi" icon: "circle" mode: wide --- + ## 概述 此节点使用 HappyHorse 模型从单张起始图像生成短视频。您需要提供首帧图像以及描述所需运动和场景的文本提示，节点将基于该图像创建一段延续的视频。 diff --git a/zh/built-in-nodes/HappyHorseReferenceVideoApi.mdx b/zh/built-in-nodes/HappyHorseReferenceVideoApi.mdx index b33316df2..5843f2338 100644 --- a/zh/built-in-nodes/HappyHorseReferenceVideoApi.mdx +++ b/zh/built-in-nodes/HappyHorseReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseReferenceVideoApi" icon: "circle" mode: wide --- + ### 概述 此节点基于参考图像，使用 HappyHorse 模型生成以人物或物体为特色的视频。它支持创建包含单个角色或多个角色互动的视频。 diff --git a/zh/built-in-nodes/HappyHorseTextToVideoApi.mdx b/zh/built-in-nodes/HappyHorseTextToVideoApi.mdx index addc5120e..32332af73 100644 --- a/zh/built-in-nodes/HappyHorseTextToVideoApi.mdx +++ b/zh/built-in-nodes/HappyHorseTextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseTextToVideoApi" icon: "circle" mode: wide --- + ## 概述 使用 HappyHorse 模型根据文本提示生成视频。此节点将您的提示词和设置发送到 HappyHorse API，等待视频生成完成，然后下载结果。 diff --git a/zh/built-in-nodes/HappyHorseVideoEditApi.mdx b/zh/built-in-nodes/HappyHorseVideoEditApi.mdx index 190f9189d..9267b1a1b 100644 --- a/zh/built-in-nodes/HappyHorseVideoEditApi.mdx +++ b/zh/built-in-nodes/HappyHorseVideoEditApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HappyHorseVideoEditApi" icon: "circle" mode: wide --- + ## 概述 使用 HappyHorse 模型，通过文本指令或参考图像编辑视频。输出时长为 3-15 秒，与输入视频匹配；超过 15 秒的输入将被截断。 diff --git a/zh/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx b/zh/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx index 2a2e51bc8..734237afd 100644 --- a/zh/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx +++ b/zh/built-in-nodes/HiDreamO1PatchSeamSmoothing.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HiDreamO1PatchSeamSmoothing" icon: "circle" mode: wide --- + ## ## 概述 此节点通过在采样过程后期对 HiDream-O1 模型在多个偏移的块网格位置上的输出进行平均，来减少该模型生成图像中的可见接缝。其工作原理是使用略微不同的图像对齐方式多次运行模型，并将结果混合在一起，从而消除块边界处可能出现的网格状伪影。 diff --git a/zh/built-in-nodes/HiDreamO1ReferenceImages.mdx b/zh/built-in-nodes/HiDreamO1ReferenceImages.mdx index 68b84500d..22e330887 100644 --- a/zh/built-in-nodes/HiDreamO1ReferenceImages.mdx +++ b/zh/built-in-nodes/HiDreamO1ReferenceImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HiDreamO1ReferenceImages" icon: "circle" mode: wide --- + ## ## 概述 将参考图像附加到正向和负向条件化中。此节点允许您提供一个或多个参考图像，用于指导图像生成过程，无论是基于指令进行编辑，还是进行主体驱动的个性化生成。 diff --git a/zh/built-in-nodes/HitPawGeneralImageEnhance.mdx b/zh/built-in-nodes/HitPawGeneralImageEnhance.mdx index a2da2b25f..e10e0408e 100644 --- a/zh/built-in-nodes/HitPawGeneralImageEnhance.mdx +++ b/zh/built-in-nodes/HitPawGeneralImageEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HitPawGeneralImageEnhance" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HitPawGeneralImageEnhance/en.md) 此节点通过将低分辨率图像放大至超分辨率，并去除伪影和噪点来增强图像质量。它使用外部 API 处理图像，并可自动调整输入尺寸以保持在处理限制范围内。允许的最大输出尺寸为 4 百万像素。 diff --git a/zh/built-in-nodes/HitPawVideoEnhance.mdx b/zh/built-in-nodes/HitPawVideoEnhance.mdx index e9d237526..3942b40e3 100644 --- a/zh/built-in-nodes/HitPawVideoEnhance.mdx +++ b/zh/built-in-nodes/HitPawVideoEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HitPawVideoEnhance" icon: "circle" mode: wide --- + HitPaw视频增强节点使用外部API来提升视频质量。它可将低分辨率视频放大到更高分辨率，去除视觉伪影并降低噪点。处理费用按输入视频的每秒时长计算。 ## 输入 diff --git a/zh/built-in-nodes/Hunyuan3Dv2Conditioning.mdx b/zh/built-in-nodes/Hunyuan3Dv2Conditioning.mdx index 5e9299275..2b7f495cc 100644 --- a/zh/built-in-nodes/Hunyuan3Dv2Conditioning.mdx +++ b/zh/built-in-nodes/Hunyuan3Dv2Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Hunyuan3Dv2Conditioning" icon: "circle" mode: wide --- + Hunyuan3Dv2Conditioning 节点处理 CLIP 视觉输出，为 3D 模型生成条件数据。它从视觉输出中提取最后的隐藏状态嵌入，并创建正负条件对。正条件使用实际的嵌入，而负条件使用形状相同的零值嵌入。 ## 输入 @@ -17,8 +18,8 @@ Hunyuan3Dv2Conditioning 节点处理 CLIP 视觉输出，为 3D 模型生成条 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `反向` | 包含 CLIP 视觉嵌入的正条件数据 | CONDITIONING | -| `negative` | 包含与正条件嵌入形状匹配的零值嵌入的负条件数据 | CONDITIONING | +| `正向` | 包含 CLIP 视觉嵌入的正条件数据 | CONDITIONING | +| `反向` | 包含与正条件嵌入形状匹配的零值嵌入的负条件数据 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2Conditioning/zh.md) diff --git a/zh/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx b/zh/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx index 2a7f50eb7..e2aef8ad7 100644 --- a/zh/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx +++ b/zh/built-in-nodes/Hunyuan3Dv2ConditioningMultiView.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Hunyuan3Dv2ConditioningMultiView" icon: "circle" mode: wide --- + Hunyuan3Dv2ConditioningMultiView 节点处理用于 3D 视频生成的多视角 CLIP 视觉嵌入。它接收可选的正面、左侧、背面和右侧视角嵌入，并将其与位置编码相结合，为视频模型创建条件数据。该节点输出包含组合嵌入的正向条件数据，以及值为零的负向条件数据。 ## 输入 @@ -22,8 +23,8 @@ Hunyuan3Dv2ConditioningMultiView 节点处理用于 3D 视频生成的多视角 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `反向` | 包含组合后的多视角嵌入及位置编码的正向条件数据 | CONDITIONING | -| `negative` | 用于对比学习的、值为零的负向条件数据 | CONDITIONING | +| `正向` | 包含组合后的多视角嵌入及位置编码的正向条件数据 | CONDITIONING | +| `反向` | 用于对比学习的、值为零的负向条件数据 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Hunyuan3Dv2ConditioningMultiView/zh.md) diff --git a/zh/built-in-nodes/HunyuanImageToVideo.mdx b/zh/built-in-nodes/HunyuanImageToVideo.mdx index 778117508..c9ec4b4bf 100644 --- a/zh/built-in-nodes/HunyuanImageToVideo.mdx +++ b/zh/built-in-nodes/HunyuanImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanImageToVideo" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanImageToVideo/en.md) HunyuanImageToVideo 节点使用 Hunyuan 视频模型将图像转换为视频潜在表示。它接收条件化输入和可选的起始图像，生成可供视频生成模型进一步处理的视频潜在变量。该节点支持不同的引导类型，用于控制起始图像对视频生成过程的影响。 @@ -32,8 +33,8 @@ HunyuanImageToVideo 节点使用 Hunyuan 视频模型将图像转换为视频潜 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `Latent` | 当提供 start_image 时，应用了图像引导的修改后正面条件化输入 | CONDITIONING | -| `latent` | 可供视频生成模型进一步处理的视频潜在表示 | LATENT | +| `正向` | 当提供 start_image 时，应用了图像引导的修改后正面条件化输入 | CONDITIONING | +| `Latent` | 可供视频生成模型进一步处理的视频潜在表示 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanImageToVideo/zh.md) diff --git a/zh/built-in-nodes/HunyuanRefinerLatent.mdx b/zh/built-in-nodes/HunyuanRefinerLatent.mdx index c51169e52..19d010713 100644 --- a/zh/built-in-nodes/HunyuanRefinerLatent.mdx +++ b/zh/built-in-nodes/HunyuanRefinerLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanRefinerLatent" icon: "circle" mode: wide --- + HunyuanRefinerLatent 节点处理用于精炼操作的 conditioning 和 latent 输入。它对正向和负向 conditioning 应用噪声增强，同时结合潜在图像数据，并生成具有特定维度的新 latent 输出以供进一步处理。 ## 输入 @@ -20,9 +21,9 @@ HunyuanRefinerLatent 节点处理用于精炼操作的 conditioning 和 latent | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面` | 经过噪声增强和潜在图像拼接处理后的正向 conditioning | CONDITIONING | -| `潜在` | 经过噪声增强和潜在图像拼接处理后的负向 conditioning | CONDITIONING | -| `Latent` | 维度为 [batch_size, 32, height, width, channels] 的新 latent 输出 | LATENT | +| `正面` | 经过噪声增强和潜在图像拼接处理后的正向 conditioning | CONDITIONING | +| `负面` | 经过噪声增强和潜在图像拼接处理后的负向 conditioning | CONDITIONING | +| `潜在` | 维度为 [batch_size, 32, height, width, channels] 的新 latent 输出 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanRefinerLatent/zh.md) diff --git a/zh/built-in-nodes/HunyuanVideo15ImageToVideo.mdx b/zh/built-in-nodes/HunyuanVideo15ImageToVideo.mdx index 5f9ad6f74..2859f9b06 100644 --- a/zh/built-in-nodes/HunyuanVideo15ImageToVideo.mdx +++ b/zh/built-in-nodes/HunyuanVideo15ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15ImageToVideo" icon: "circle" mode: wide --- + HunyuanVideo15ImageToVideo 节点基于 HunyuanVideo 1.5 模型，为视频生成准备条件嵌入和潜在空间数据。它会为视频序列创建一个初始潜在表示，并可选择性地集成起始图像或 CLIP 视觉输出，以引导生成过程。 ## 输入 @@ -27,8 +28,8 @@ HunyuanVideo15ImageToVideo 节点基于 HunyuanVideo 1.5 模型，为视频生 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 修改后的正向条件，现在可能包含编码后的起始图像或 CLIP 视觉输出。 | CONDITIONING | -| `latent` | 修改后的负向条件，现在可能包含编码后的起始图像或 CLIP 视觉输出。 | CONDITIONING | +| `正面条件` | 修改后的正向条件，现在可能包含编码后的起始图像或 CLIP 视觉输出。 | CONDITIONING | +| `负面条件` | 修改后的负向条件，现在可能包含编码后的起始图像或 CLIP 视觉输出。 | CONDITIONING | | `latent` | 一个空的潜在张量，其维度已根据指定的批次大小、视频长度、宽度和高度进行配置。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15ImageToVideo/zh.md) diff --git a/zh/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx b/zh/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx index a13edeb62..1b0a9ff59 100644 --- a/zh/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx +++ b/zh/built-in-nodes/HunyuanVideo15LatentUpscaleWithModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15LatentUpscaleWithModel" icon: "circle" mode: wide --- + ### 概述 Hunyuan Video 15 潜空间放大（使用模型）节点用于提升潜空间图像表示的分辨率。该节点首先通过选定的插值方法将潜空间样本放大至指定尺寸，随后利用专门的 Hunyuan Video 1.5 放大模型对放大结果进行优化，以提升画质。 diff --git a/zh/built-in-nodes/HunyuanVideo15SuperResolution.mdx b/zh/built-in-nodes/HunyuanVideo15SuperResolution.mdx index 746390466..588bec4cf 100644 --- a/zh/built-in-nodes/HunyuanVideo15SuperResolution.mdx +++ b/zh/built-in-nodes/HunyuanVideo15SuperResolution.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HunyuanVideo15SuperResolution" icon: "circle" mode: wide --- + HunyuanVideo15SuperResolution 节点为视频超分辨率过程准备条件数据。它接收视频的潜在表示，并可选择接收起始图像，将这些数据与噪声增强和 CLIP 视觉数据打包成模型可用于生成更高分辨率输出的格式。 ## 输入 @@ -25,9 +26,9 @@ HunyuanVideo15SuperResolution 节点为视频超分辨率过程准备条件数 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 修改后的正向条件数据，现在包含拼接后的潜在数据、噪声增强以及可选的 CLIP 视觉数据。 | CONDITIONING | -| `Latent` | 修改后的负向条件数据，现在包含拼接后的潜在数据、噪声增强以及可选的 CLIP 视觉数据。 | CONDITIONING | -| `latent` | 输入的潜在数据保持不变地传递。 | LATENT | +| `正面条件` | 修改后的正向条件数据，现在包含拼接后的潜在数据、噪声增强以及可选的 CLIP 视觉数据。 | CONDITIONING | +| `负面条件` | 修改后的负向条件数据，现在包含拼接后的潜在数据、噪声增强以及可选的 CLIP 视觉数据。 | CONDITIONING | +| `Latent` | 输入的潜在数据保持不变地传递。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HunyuanVideo15SuperResolution/zh.md) diff --git a/zh/built-in-nodes/HyperTile.mdx b/zh/built-in-nodes/HyperTile.mdx index ace8ef9b1..5b6c92617 100644 --- a/zh/built-in-nodes/HyperTile.mdx +++ b/zh/built-in-nodes/HyperTile.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HyperTile" icon: "circle" mode: wide --- + HyperTile 节点对扩散模型中的注意力机制应用分块技术，以优化图像生成过程中的内存使用。它将潜在空间划分为更小的图块并分别处理，然后重新组合结果。这使得在内存不足的情况下也能处理更大的图像尺寸。 ## 输入 diff --git a/zh/built-in-nodes/HypernetworkLoader.mdx b/zh/built-in-nodes/HypernetworkLoader.mdx index 32d221050..b65e50c4f 100644 --- a/zh/built-in-nodes/HypernetworkLoader.mdx +++ b/zh/built-in-nodes/HypernetworkLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "HypernetworkLoader" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/hypernetworks` 文件夹中的模型，同时也会读取 extra_model_paths.yaml 文件中配置的额外路径中的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够从相应文件夹中读取模型文件。 HypernetworkLoader 节点旨在通过应用超网络来增强或修改给定模型的能力。它加载指定的超网络并将其应用于模型，根据强度参数可能改变模型的行为或性能。此过程允许对模型架构或参数进行动态调整，从而实现更灵活、更具适应性的 AI 系统。 diff --git a/zh/built-in-nodes/Ideogram4Scheduler.mdx b/zh/built-in-nodes/Ideogram4Scheduler.mdx index da998a063..04dc37865 100644 --- a/zh/built-in-nodes/Ideogram4Scheduler.mdx +++ b/zh/built-in-nodes/Ideogram4Scheduler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Ideogram4Scheduler" icon: "circle" mode: wide --- -# Ideogram 4 调度器 Ideogram 4 调度器节点基于 Ideogram 4 参考调度表生成扩散采样过程中的 sigma 值序列（噪声水平）。它会创建一个自定义噪声调度表，该表会根据图像尺寸进行调整，并允许通过统计参数进行微调。 diff --git a/zh/built-in-nodes/IdeogramV1.mdx b/zh/built-in-nodes/IdeogramV1.mdx index c1ae4c994..9fb68a8c3 100644 --- a/zh/built-in-nodes/IdeogramV1.mdx +++ b/zh/built-in-nodes/IdeogramV1.mdx @@ -5,7 +5,6 @@ sidebarTitle: "IdeogramV1" icon: "circle" mode: wide --- -# ## 概述 IdeogramV1 节点通过 API 使用 Ideogram V1 模型生成图像。它接收文本提示词和各种生成设置，根据您的输入创建一张或多张图像。该节点支持不同的宽高比和生成模式，以自定义输出效果。 diff --git a/zh/built-in-nodes/IdeogramV2.mdx b/zh/built-in-nodes/IdeogramV2.mdx index 40323bec9..ab5011406 100644 --- a/zh/built-in-nodes/IdeogramV2.mdx +++ b/zh/built-in-nodes/IdeogramV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "IdeogramV2" icon: "circle" mode: wide --- + Ideogram V2 节点使用 Ideogram V2 AI 模型生成图像。它接收文本提示词和各种生成设置，通过 API 服务创建图像。该节点支持不同的宽高比、分辨率和风格选项，以自定义输出图像。 ## 输入 diff --git a/zh/built-in-nodes/IdeogramV3.mdx b/zh/built-in-nodes/IdeogramV3.mdx index cfbcbb37a..08674b749 100644 --- a/zh/built-in-nodes/IdeogramV3.mdx +++ b/zh/built-in-nodes/IdeogramV3.mdx @@ -5,7 +5,6 @@ sidebarTitle: "IdeogramV3" icon: "circle" mode: wide --- -# Ideogram V3 节点 此节点使用 Ideogram V3 模型生成图像。它支持从文本提示进行常规图像生成，以及在同时提供图像和遮罩时进行图像编辑。该节点提供多种控制选项，包括宽高比、分辨率、生成速度以及可选的参考人物图像。 diff --git a/zh/built-in-nodes/IdeogramV4.mdx b/zh/built-in-nodes/IdeogramV4.mdx index 9e3af0752..190e5bd3a 100644 --- a/zh/built-in-nodes/IdeogramV4.mdx +++ b/zh/built-in-nodes/IdeogramV4.mdx @@ -5,7 +5,6 @@ sidebarTitle: "IdeogramV4" icon: "circle" mode: wide --- -# Ideogram V4 根据文本提示，使用 Ideogram 4.0 模型生成图像。此节点将您的文本描述发送至 Ideogram API，并将生成的图像作为输出张量返回。 diff --git a/zh/built-in-nodes/ImageAddNoise.mdx b/zh/built-in-nodes/ImageAddNoise.mdx index a47e4563a..d57c73997 100644 --- a/zh/built-in-nodes/ImageAddNoise.mdx +++ b/zh/built-in-nodes/ImageAddNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageAddNoise" icon: "circle" mode: wide --- + ImageAddNoise 节点用于向输入图像添加随机噪声。它使用指定的随机种子生成一致的噪声模式，并允许控制噪声效果的强度。输出图像保持与输入图像相同的尺寸，但增加了视觉纹理。 ## 输入 diff --git a/zh/built-in-nodes/ImageBatch.mdx b/zh/built-in-nodes/ImageBatch.mdx index dd66839dd..9f4aab380 100644 --- a/zh/built-in-nodes/ImageBatch.mdx +++ b/zh/built-in-nodes/ImageBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBatch" icon: "circle" mode: wide --- + `ImageBatch` 节点用于将两张图像合并为一个批次。如果图像的尺寸不匹配，它会自动将第二张图像重新缩放以匹配第一张图像的尺寸，然后再进行合并。 ## 输入 diff --git a/zh/built-in-nodes/ImageBlend.mdx b/zh/built-in-nodes/ImageBlend.mdx index 4165b233d..5586a32ab 100644 --- a/zh/built-in-nodes/ImageBlend.mdx +++ b/zh/built-in-nodes/ImageBlend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBlend" icon: "circle" mode: wide --- + `ImageBlend` 节点用于根据指定的混合模式和混合因子将两张图像混合在一起。它支持多种混合模式，例如正常、正片叠底、滤色、叠加、柔光和差值，可实现多样化的图像处理与合成技术。此节点通过调整两个图像层之间的视觉交互，是创建合成图像的核心工具。 ## 输入 diff --git a/zh/built-in-nodes/ImageBlur.mdx b/zh/built-in-nodes/ImageBlur.mdx index 9f95fa132..2e0470dad 100644 --- a/zh/built-in-nodes/ImageBlur.mdx +++ b/zh/built-in-nodes/ImageBlur.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageBlur" icon: "circle" mode: wide --- + `ImageBlur` 节点对图像应用高斯模糊，可柔化边缘、减少细节和噪点。通过参数可控制模糊的强度和扩散范围。 ## 输入 diff --git a/zh/built-in-nodes/ImageColorToMask.mdx b/zh/built-in-nodes/ImageColorToMask.mdx index e47183690..87b5f7450 100644 --- a/zh/built-in-nodes/ImageColorToMask.mdx +++ b/zh/built-in-nodes/ImageColorToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageColorToMask" icon: "circle" mode: wide --- + `ImageColorToMask` 节点旨在将图像中的指定颜色转换为遮罩。它处理一张图像和一个目标颜色，生成一个突出显示该指定颜色的遮罩，便于执行基于颜色的分割或对象隔离等操作。 ## 输入 diff --git a/zh/built-in-nodes/ImageCompare.mdx b/zh/built-in-nodes/ImageCompare.mdx index 3fef56750..aa67342e4 100644 --- a/zh/built-in-nodes/ImageCompare.mdx +++ b/zh/built-in-nodes/ImageCompare.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCompare" icon: "circle" mode: wide --- + 图像比较节点提供一个可视化界面，通过可拖动的滑块并排比较两张图像。它被设计为输出节点，意味着它不会将数据传递给其他节点，而是直接在用户界面中显示图像以供检查。 ## 输入 diff --git a/zh/built-in-nodes/ImageCompositeMasked.mdx b/zh/built-in-nodes/ImageCompositeMasked.mdx index 75fc4d98f..9a61e114f 100644 --- a/zh/built-in-nodes/ImageCompositeMasked.mdx +++ b/zh/built-in-nodes/ImageCompositeMasked.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCompositeMasked" icon: "circle" mode: wide --- + `ImageCompositeMasked` 节点专为图像合成而设计，支持将源图像叠加到目标图像的指定坐标位置，并可选择调整大小和遮罩。 ## 输入 diff --git a/zh/built-in-nodes/ImageCrop.mdx b/zh/built-in-nodes/ImageCrop.mdx index 7e82147bc..f704f4a45 100644 --- a/zh/built-in-nodes/ImageCrop.mdx +++ b/zh/built-in-nodes/ImageCrop.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCrop" icon: "circle" mode: wide --- + `ImageCrop` 节点用于将图像从指定的 x 和 y 坐标开始裁剪为指定的宽度和高度。此功能对于聚焦图像的特定区域或调整图像大小以满足特定要求至关重要。 ## 输入 diff --git a/zh/built-in-nodes/ImageCropV2.mdx b/zh/built-in-nodes/ImageCropV2.mdx index d76384499..bd9e8a118 100644 --- a/zh/built-in-nodes/ImageCropV2.mdx +++ b/zh/built-in-nodes/ImageCropV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageCropV2" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageCropV2/en.md) 图像裁剪节点从输入图像中提取一个矩形区域。您可以通过指定其左上角坐标以及宽度和高度来定义要保留的区域。该节点随后返回原始图像的裁剪部分。 diff --git a/zh/built-in-nodes/ImageDeduplication.mdx b/zh/built-in-nodes/ImageDeduplication.mdx index eb4b4d2ac..780fc07a0 100644 --- a/zh/built-in-nodes/ImageDeduplication.mdx +++ b/zh/built-in-nodes/ImageDeduplication.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageDeduplication" icon: "circle" mode: wide --- + 此节点用于从一批图像中移除重复或高度相似的图像。其工作原理是为每张图像创建感知哈希——一种基于视觉内容的简单数值指纹——然后进行比较。哈希值相似度超过设定阈值的图像将被视为重复项并过滤掉。 ## 输入 diff --git a/zh/built-in-nodes/ImageFlip.mdx b/zh/built-in-nodes/ImageFlip.mdx index 872e2d2f3..0ecdad178 100644 --- a/zh/built-in-nodes/ImageFlip.mdx +++ b/zh/built-in-nodes/ImageFlip.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageFlip" icon: "circle" mode: wide --- + ImageFlip 节点可沿不同轴翻转图像。它能够沿 x 轴垂直翻转图像，或沿 y 轴水平翻转图像。该节点基于所选方法，使用 `torch.flip` 操作执行翻转。 ## 输入 diff --git a/zh/built-in-nodes/ImageFromBatch.mdx b/zh/built-in-nodes/ImageFromBatch.mdx index b53729001..0eec5f1c4 100644 --- a/zh/built-in-nodes/ImageFromBatch.mdx +++ b/zh/built-in-nodes/ImageFromBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageFromBatch" icon: "circle" mode: wide --- + `ImageFromBatch` 节点用于根据指定的索引和长度从批次中提取特定图像片段。它允许对批次图像进行更精细的控制，从而能够对较大批次中的单个或子集图像执行操作。 ## 输入 diff --git a/zh/built-in-nodes/ImageGrid.mdx b/zh/built-in-nodes/ImageGrid.mdx index aa66e8283..d5e2dc609 100644 --- a/zh/built-in-nodes/ImageGrid.mdx +++ b/zh/built-in-nodes/ImageGrid.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageGrid" icon: "circle" mode: wide --- + 图像网格节点将多张图像合并为一张排列有序的网格或拼贴图。它接收图像列表，将其排列成指定列数，将每张图像调整至设定的单元格尺寸，并在图像之间添加可选间距。最终输出一张包含所有输入图像的新图像，以网格布局呈现。 ## 输入 @@ -21,7 +22,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `image` | 包含所有输入图像按网格排列的单张输出图像。 | IMAGE | +| `图像` | 包含所有输入图像按网格排列的单张输出图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageGrid/zh.md) diff --git a/zh/built-in-nodes/ImageHistogram.mdx b/zh/built-in-nodes/ImageHistogram.mdx index 82abf31dd..98714c48f 100644 --- a/zh/built-in-nodes/ImageHistogram.mdx +++ b/zh/built-in-nodes/ImageHistogram.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageHistogram" icon: "circle" mode: wide --- + ImageHistogram 节点用于分析输入图像的颜色分布。它会计算并输出多个直方图，这些图表展示了图像中每个可能强度值对应的像素数量。该节点会分别生成红色、绿色和蓝色通道的直方图，一个复合 RGB 直方图，以及基于标准亮度公式计算的亮度直方图。 ## 输入 @@ -17,11 +18,11 @@ ImageHistogram 节点用于分析输入图像的颜色分布。它会计算并 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `亮度` | 一个复合直方图，表示红色、绿色和蓝色通道的平均像素强度。 | HISTOGRAM | -| `红色` | 图像感知亮度的直方图，使用 ITU-R BT.709 标准亮度公式计算。 | HISTOGRAM | -| `绿色` | 显示红色通道中像素强度分布的直方图。 | HISTOGRAM | -| `蓝色` | 显示绿色通道中像素强度分布的直方图。 | HISTOGRAM | -| `blue` | 显示蓝色通道中像素强度分布的直方图。 | HISTOGRAM | +| `RGB` | 一个复合直方图，表示红色、绿色和蓝色通道的平均像素强度。 | HISTOGRAM | +| `亮度` | 图像感知亮度的直方图，使用 ITU-R BT.709 标准亮度公式计算。 | HISTOGRAM | +| `红色` | 显示红色通道中像素强度分布的直方图。 | HISTOGRAM | +| `绿色` | 显示绿色通道中像素强度分布的直方图。 | HISTOGRAM | +| `蓝色` | 显示蓝色通道中像素强度分布的直方图。 | HISTOGRAM | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageHistogram/zh.md) diff --git a/zh/built-in-nodes/ImageInvert.mdx b/zh/built-in-nodes/ImageInvert.mdx index 93c88a1a5..3a4c25935 100644 --- a/zh/built-in-nodes/ImageInvert.mdx +++ b/zh/built-in-nodes/ImageInvert.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageInvert" icon: "circle" mode: wide --- + `ImageInvert` 节点用于反转图像的颜色，将每个像素的颜色值转换为其在色轮上的互补色。此操作适用于创建负片图像或需要颜色反转的视觉效果。 ## 输入 diff --git a/zh/built-in-nodes/ImageMergeTileList.mdx b/zh/built-in-nodes/ImageMergeTileList.mdx index bb59fecc5..5a75efc6e 100644 --- a/zh/built-in-nodes/ImageMergeTileList.mdx +++ b/zh/built-in-nodes/ImageMergeTileList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageMergeTileList" icon: "circle" mode: wide --- + 此节点接收一个图像瓦片列表，并将其合并回一张更大的完整图像。它旨在重建之前被分割成重叠瓦片网格的图像，通过加权混合技术实现无缝的最终效果。 ## 输入 diff --git a/zh/built-in-nodes/ImageOnlyCheckpointLoader.mdx b/zh/built-in-nodes/ImageOnlyCheckpointLoader.mdx index 6991de240..dfff5fa7b 100644 --- a/zh/built-in-nodes/ImageOnlyCheckpointLoader.mdx +++ b/zh/built-in-nodes/ImageOnlyCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageOnlyCheckpointLoader" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/checkpoints` 文件夹中的模型，同时也会读取 extra_model_paths.yaml 文件中配置的额外路径中的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够从相应文件夹中读取模型文件。 该节点专门用于在视频生成工作流中加载基于图像的模型检查点。它能高效地从给定检查点中检索并配置必要组件，重点关注模型的图像相关部分。 diff --git a/zh/built-in-nodes/ImageOnlyCheckpointSave.mdx b/zh/built-in-nodes/ImageOnlyCheckpointSave.mdx index ab389efc0..29dd62422 100644 --- a/zh/built-in-nodes/ImageOnlyCheckpointSave.mdx +++ b/zh/built-in-nodes/ImageOnlyCheckpointSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageOnlyCheckpointSave" icon: "circle" mode: wide --- + ImageOnlyCheckpointSave 节点用于保存包含模型、CLIP 视觉编码器和 VAE 的检查点文件。它会创建一个带有指定文件名前缀的 safetensors 文件，并将其存储在输出目录中。此节点专为将图像相关模型组件一起保存到单个检查点文件而设计。 ## 输入 diff --git a/zh/built-in-nodes/ImagePadForOutpaint.mdx b/zh/built-in-nodes/ImagePadForOutpaint.mdx index 38e323a1d..527289c45 100644 --- a/zh/built-in-nodes/ImagePadForOutpaint.mdx +++ b/zh/built-in-nodes/ImagePadForOutpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImagePadForOutpaint" icon: "circle" mode: wide --- + 此节点专为外绘（outpainting）流程准备图像而设计，通过在图像周围添加填充区域来调整图像尺寸，确保与外绘算法兼容，从而便于在原始边界之外生成扩展的图像区域。 ## 输入 diff --git a/zh/built-in-nodes/ImageQuantize.mdx b/zh/built-in-nodes/ImageQuantize.mdx index 8b7a10479..ec1d9cd4f 100644 --- a/zh/built-in-nodes/ImageQuantize.mdx +++ b/zh/built-in-nodes/ImageQuantize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageQuantize" icon: "circle" mode: wide --- + ImageQuantize 节点旨在将图像中的颜色数量减少到指定数目，并可选择应用抖动技术以保持视觉质量。此过程对于创建基于调色板的图像或降低某些应用场景中的颜色复杂度非常有用。 ## 输入 diff --git a/zh/built-in-nodes/ImageRGBToYUV.mdx b/zh/built-in-nodes/ImageRGBToYUV.mdx index d9db5ffa6..1b636baac 100644 --- a/zh/built-in-nodes/ImageRGBToYUV.mdx +++ b/zh/built-in-nodes/ImageRGBToYUV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageRGBToYUV" icon: "circle" mode: wide --- + ImageRGBToYUV 节点用于将 RGB 彩色图像转换为 YUV 色彩空间。它接收一张 RGB 图像作为输入，并将其分离为三个独立的通道：Y（亮度）、U（蓝色投影）和 V（红色投影）。每个输出通道都以单独的灰度图像形式返回，代表对应的 YUV 分量。 ## 输入 @@ -17,8 +18,8 @@ ImageRGBToYUV 节点用于将 RGB 彩色图像转换为 YUV 色彩空间。它 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `U` | YUV 色彩空间的亮度（明度）分量 | IMAGE | -| `V` | YUV 色彩空间的蓝色投影分量 | IMAGE | +| `Y` | YUV 色彩空间的亮度（明度）分量 | IMAGE | +| `U` | YUV 色彩空间的蓝色投影分量 | IMAGE | | `V` | YUV 色彩空间的红色投影分量 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageRGBToYUV/zh.md) diff --git a/zh/built-in-nodes/ImageRotate.mdx b/zh/built-in-nodes/ImageRotate.mdx index cbd511981..452261b87 100644 --- a/zh/built-in-nodes/ImageRotate.mdx +++ b/zh/built-in-nodes/ImageRotate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageRotate" icon: "circle" mode: wide --- + ImageRotate 节点可按指定角度旋转输入图像。它支持四种旋转选项：不旋转、顺时针旋转 90 度、旋转 180 度以及顺时针旋转 270 度。旋转操作通过高效的张量运算完成，可保持图像数据的完整性。 ## 输入 diff --git a/zh/built-in-nodes/ImageScale.mdx b/zh/built-in-nodes/ImageScale.mdx index 867fa2082..b15372597 100644 --- a/zh/built-in-nodes/ImageScale.mdx +++ b/zh/built-in-nodes/ImageScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScale" icon: "circle" mode: wide --- + ImageScale 节点专为将图像调整至特定尺寸而设计，提供多种放大方法选择以及裁剪调整后图像的功能。它抽象了图像放大与裁剪的复杂性，通过用户自定义参数提供直观的界面来修改图像尺寸。 ## 输入 diff --git a/zh/built-in-nodes/ImageScaleBy.mdx b/zh/built-in-nodes/ImageScaleBy.mdx index 303b7f97c..f7f962730 100644 --- a/zh/built-in-nodes/ImageScaleBy.mdx +++ b/zh/built-in-nodes/ImageScaleBy.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleBy" icon: "circle" mode: wide --- + ImageScaleBy 节点旨在通过指定的缩放因子，使用多种插值方法对图像进行放大。它能够灵活调整图像尺寸，满足不同的放大需求。 ## 输入 diff --git a/zh/built-in-nodes/ImageScaleToMaxDimension.mdx b/zh/built-in-nodes/ImageScaleToMaxDimension.mdx index 807f55931..d1e66c7bd 100644 --- a/zh/built-in-nodes/ImageScaleToMaxDimension.mdx +++ b/zh/built-in-nodes/ImageScaleToMaxDimension.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleToMaxDimension" icon: "circle" mode: wide --- + ImageScaleToMaxDimension 节点用于将图像调整至指定的最大尺寸范围内，同时保持原始宽高比。它会判断图像是竖屏还是横屏方向，然后将较大的尺寸缩放至目标大小，并按比例调整较小的尺寸。该节点支持多种放大方法，以满足不同的质量和性能需求。 ## 输入 diff --git a/zh/built-in-nodes/ImageScaleToTotalPixels.mdx b/zh/built-in-nodes/ImageScaleToTotalPixels.mdx index 3d5fe92bb..cbc92f2f7 100644 --- a/zh/built-in-nodes/ImageScaleToTotalPixels.mdx +++ b/zh/built-in-nodes/ImageScaleToTotalPixels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageScaleToTotalPixels" icon: "circle" mode: wide --- + ImageScaleToTotalPixels 节点用于将图像调整至指定的总像素数，同时保持原始宽高比。它提供了多种放大方法，以实现所需的像素数量。 ## 输入 diff --git a/zh/built-in-nodes/ImageSharpen.mdx b/zh/built-in-nodes/ImageSharpen.mdx index d5a1032c4..e291eee0c 100644 --- a/zh/built-in-nodes/ImageSharpen.mdx +++ b/zh/built-in-nodes/ImageSharpen.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageSharpen" icon: "circle" mode: wide --- + ImageSharpen 节点通过突出图像的边缘和细节来增强其清晰度。它对图像应用锐化滤镜，可调节强度和半径，从而使图像看起来更清晰、更鲜明。 ## 输入 diff --git a/zh/built-in-nodes/ImageStitch.mdx b/zh/built-in-nodes/ImageStitch.mdx index 840a87197..4c0931cbc 100644 --- a/zh/built-in-nodes/ImageStitch.mdx +++ b/zh/built-in-nodes/ImageStitch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageStitch" icon: "circle" mode: wide --- + 此节点允许您将两张图像沿指定方向（上、下、左、右）拼接在一起，并支持尺寸匹配和图像间距设置。 ## 输入 diff --git a/zh/built-in-nodes/ImageToMask.mdx b/zh/built-in-nodes/ImageToMask.mdx index 1738e2d16..8940ff19e 100644 --- a/zh/built-in-nodes/ImageToMask.mdx +++ b/zh/built-in-nodes/ImageToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageToMask" icon: "circle" mode: wide --- + ImageToMask 节点旨在根据指定的颜色通道将图像转换为遮罩。它允许提取图像中对应红色、绿色、蓝色或 Alpha 通道的遮罩层，便于执行需要特定通道遮罩或处理的操作。 ## 输入 diff --git a/zh/built-in-nodes/ImageUpscaleWithModel.mdx b/zh/built-in-nodes/ImageUpscaleWithModel.mdx index 5b102afb0..0fe894bbf 100644 --- a/zh/built-in-nodes/ImageUpscaleWithModel.mdx +++ b/zh/built-in-nodes/ImageUpscaleWithModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageUpscaleWithModel" icon: "circle" mode: wide --- + 此节点专为使用指定的放大模型对图像进行放大而设计。它通过将图像调整至合适设备、优化内存使用，并以分块方式应用放大模型来高效管理放大过程，从而防止潜在的内存溢出错误。 ## 输入 diff --git a/zh/built-in-nodes/ImageYUVToRGB.mdx b/zh/built-in-nodes/ImageYUVToRGB.mdx index bc8520f40..3034f0b4f 100644 --- a/zh/built-in-nodes/ImageYUVToRGB.mdx +++ b/zh/built-in-nodes/ImageYUVToRGB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ImageYUVToRGB" icon: "circle" mode: wide --- + ImageYUVToRGB 节点将 YUV 色彩空间的图像转换为 RGB 色彩空间。它接收三个独立的输入图像，分别代表 Y（亮度）、U（蓝色投影）和 V（红色投影）通道，并通过色彩空间转换将它们合并为单个 RGB 图像。 ## 输入 diff --git a/zh/built-in-nodes/InpaintModelConditioning.mdx b/zh/built-in-nodes/InpaintModelConditioning.mdx index 67dd5630d..4fe279f98 100644 --- a/zh/built-in-nodes/InpaintModelConditioning.mdx +++ b/zh/built-in-nodes/InpaintModelConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InpaintModelConditioning" icon: "circle" mode: wide --- + InpaintModelConditioning 节点旨在简化修复模型的条件处理流程，支持集成和操作多种条件输入以定制修复输出。它涵盖从加载特定模型检查点、应用样式或控制网络模型，到编码和组合条件元素等广泛功能，是自定义修复任务的综合工具。 ## 输入 @@ -21,8 +22,8 @@ InpaintModelConditioning 节点旨在简化修复模型的条件处理流程， | 参数 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 处理后的修改版正面条件信息，可应用于修复模型。此输出对于根据指定的正面条件引导修复过程至关重要。 | `CONDITIONING` | -| `Latent` | 处理后的修改版负面条件信息，可应用于修复模型。此输出对于根据指定的负面条件引导修复过程至关重要。 | `CONDITIONING` | -| `latent` | 从条件处理过程中推导出的潜在表示。此输出对于理解被修复图像的底层特征和属性至关重要。 | `LATENT` | +| `正面条件` | 处理后的修改版正面条件信息，可应用于修复模型。此输出对于根据指定的正面条件引导修复过程至关重要。 | `CONDITIONING` | +| `负面条件` | 处理后的修改版负面条件信息，可应用于修复模型。此输出对于根据指定的负面条件引导修复过程至关重要。 | `CONDITIONING` | +| `Latent` | 从条件处理过程中推导出的潜在表示。此输出对于理解被修复图像的底层特征和属性至关重要。 | `LATENT` | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InpaintModelConditioning/zh.md) diff --git a/zh/built-in-nodes/InstructPixToPixConditioning.mdx b/zh/built-in-nodes/InstructPixToPixConditioning.mdx index 25b67a396..9f107968c 100644 --- a/zh/built-in-nodes/InstructPixToPixConditioning.mdx +++ b/zh/built-in-nodes/InstructPixToPixConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InstructPixToPixConditioning" icon: "circle" mode: wide --- + InstructPixToPixConditioning 节点通过将正向和负向文本提示与图像数据结合，为 InstructPix2Pix 图像编辑准备条件数据。它通过 VAE 编码器处理输入图像以创建潜在表示，并将这些潜在数据附加到正向和负向条件数据中。该节点会自动处理图像尺寸，将其裁剪为 8 像素的倍数，以确保与 VAE 编码过程兼容。 ## 输入 @@ -22,9 +23,9 @@ InstructPixToPixConditioning 节点通过将正向和负向文本提示与图像 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 附加了潜在图像表示的正向条件数据 | CONDITIONING | -| `Latent` | 附加了潜在图像表示的负向条件数据 | CONDITIONING | -| `latent` | 与编码图像尺寸相同的空潜在张量 | LATENT | +| `正面条件` | 附加了潜在图像表示的正向条件数据 | CONDITIONING | +| `负面条件` | 附加了潜在图像表示的负向条件数据 | CONDITIONING | +| `Latent` | 与编码图像尺寸相同的空潜在张量 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/InstructPixToPixConditioning/zh.md) diff --git a/zh/built-in-nodes/InvertBooleanNode.mdx b/zh/built-in-nodes/InvertBooleanNode.mdx index c41100d5b..36859d3c3 100644 --- a/zh/built-in-nodes/InvertBooleanNode.mdx +++ b/zh/built-in-nodes/InvertBooleanNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InvertBooleanNode" icon: "circle" mode: wide --- + 此节点接收单个布尔值（true/false）输入，并输出相反的值。它执行逻辑非运算，将 `true` 转换为 `false`，将 `false` 转换为 `true`。 ## 输入 diff --git a/zh/built-in-nodes/InvertMask.mdx b/zh/built-in-nodes/InvertMask.mdx index d0d3bde38..aabb7a661 100644 --- a/zh/built-in-nodes/InvertMask.mdx +++ b/zh/built-in-nodes/InvertMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "InvertMask" icon: "circle" mode: wide --- + InvertMask 节点用于反转给定蒙版的值，有效交换蒙版区域与非蒙版区域。此操作在需要切换前景与背景关注焦点的图像处理任务中至关重要。 ## 输入 diff --git a/zh/built-in-nodes/JoinAudioChannels.mdx b/zh/built-in-nodes/JoinAudioChannels.mdx index 4394bee4c..825e50322 100644 --- a/zh/built-in-nodes/JoinAudioChannels.mdx +++ b/zh/built-in-nodes/JoinAudioChannels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JoinAudioChannels" icon: "circle" mode: wide --- + 合并音频通道节点将两个独立的单声道音频输入合并为单个立体声音频输出。它接收左声道和右声道，确保它们具有兼容的采样率和长度，然后将它们合并为双声道音频波形。 ## 输入 diff --git a/zh/built-in-nodes/JoinImageWithAlpha.mdx b/zh/built-in-nodes/JoinImageWithAlpha.mdx index 2de268954..39e6cc101 100644 --- a/zh/built-in-nodes/JoinImageWithAlpha.mdx +++ b/zh/built-in-nodes/JoinImageWithAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JoinImageWithAlpha" icon: "circle" mode: wide --- + 此节点专为合成操作设计，具体用于将图像与其对应的 Alpha 蒙版合并，生成单一输出图像。它能够有效结合视觉内容与透明度信息，从而创建出某些区域为透明或半透明的图像。 ## 输入 diff --git a/zh/built-in-nodes/JsonExtractString.mdx b/zh/built-in-nodes/JsonExtractString.mdx index c6cd1eebf..7855dcf15 100644 --- a/zh/built-in-nodes/JsonExtractString.mdx +++ b/zh/built-in-nodes/JsonExtractString.mdx @@ -5,6 +5,7 @@ sidebarTitle: "JsonExtractString" icon: "circle" mode: wide --- + ## 概述 JsonExtractString 节点用于读取包含 JSON 数据的文本字符串，并提取与特定键关联的值。它会将提取的值转换为字符串。如果 JSON 无效、未找到该键或值为 null，节点将返回空字符串。 diff --git a/zh/built-in-nodes/KSampler.mdx b/zh/built-in-nodes/KSampler.mdx index e0eb510ec..4bc4dbe25 100644 --- a/zh/built-in-nodes/KSampler.mdx +++ b/zh/built-in-nodes/KSampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSampler" icon: "circle" mode: wide --- + KSampler 的工作原理如下：它根据特定模型以及正向和负向条件，修改所提供的原始潜空间图像信息。 首先，根据设定的 **seed**（种子）和 **denoise**（去噪强度），向原始图像数据添加噪声，然后将预设的 **Model**（模型）与 **positive**（正向）和 **negative**（负向）引导条件结合，输入以生成图像。 diff --git a/zh/built-in-nodes/KSamplerAdvanced.mdx b/zh/built-in-nodes/KSamplerAdvanced.mdx index c845ca62c..70549d872 100644 --- a/zh/built-in-nodes/KSamplerAdvanced.mdx +++ b/zh/built-in-nodes/KSamplerAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSamplerAdvanced" icon: "circle" mode: wide --- + KSamplerAdvanced 节点旨在通过提供高级配置和技术来增强采样过程。它旨在为从模型生成样本提供更复杂的选项，从而改进基础 KSampler 的功能。 ## 输入 diff --git a/zh/built-in-nodes/KSamplerSelect.mdx b/zh/built-in-nodes/KSamplerSelect.mdx index 924bba255..2661acff1 100644 --- a/zh/built-in-nodes/KSamplerSelect.mdx +++ b/zh/built-in-nodes/KSamplerSelect.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KSamplerSelect" icon: "circle" mode: wide --- + KSamplerSelect 节点旨在根据提供的采样器名称选择特定的采样器。它抽象了采样器选择的复杂性，使用户能够轻松地在不同采样策略之间切换以完成任务。 ## 输入 diff --git a/zh/built-in-nodes/Kandinsky5ImageToVideo.mdx b/zh/built-in-nodes/Kandinsky5ImageToVideo.mdx index 6bd0ecd3b..12095fba6 100644 --- a/zh/built-in-nodes/Kandinsky5ImageToVideo.mdx +++ b/zh/built-in-nodes/Kandinsky5ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Kandinsky5ImageToVideo" icon: "circle" mode: wide --- + Kandinsky5ImageToVideo 节点用于准备 Kandinsky 模型视频生成所需的 conditioning 和潜在空间数据。它会创建一个空的视频潜在张量，并可选择对起始图像进行编码，以引导生成视频的初始帧，同时相应地修改正向和负向 conditioning。 ## 输入 @@ -26,10 +27,10 @@ Kandinsky5ImageToVideo 节点用于准备 Kandinsky 模型视频生成所需的 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 修改后的正向 conditioning，可能已更新编码后的起始图像数据。 | CONDITIONING | -| `Latent` | 修改后的负向 conditioning，可能已更新编码后的起始图像数据。 | CONDITIONING | -| `条件Latent` | 一个填充为零的空视频潜在张量，其形状符合指定的尺寸。 | LATENT | -| `cond_latent` | 所提供的起始图像的干净、编码后的潜在表示。内部使用此数据来替换生成视频潜在变量中带噪声的起始部分。 | LATENT | +| `正面条件` | 修改后的正向 conditioning，可能已更新编码后的起始图像数据。 | CONDITIONING | +| `负面条件` | 修改后的负向 conditioning，可能已更新编码后的起始图像数据。 | CONDITIONING | +| `Latent` | 一个填充为零的空视频潜在张量，其形状符合指定的尺寸。 | LATENT | +| `条件Latent` | 所提供的起始图像的干净、编码后的潜在表示。内部使用此数据来替换生成视频潜在变量中带噪声的起始部分。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Kandinsky5ImageToVideo/zh.md) diff --git a/zh/built-in-nodes/KarrasScheduler.mdx b/zh/built-in-nodes/KarrasScheduler.mdx index e5d949252..11a7e9c03 100644 --- a/zh/built-in-nodes/KarrasScheduler.mdx +++ b/zh/built-in-nodes/KarrasScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KarrasScheduler" icon: "circle" mode: wide --- + KarrasScheduler 节点用于根据 Karras 等人（2022）提出的噪声调度生成一系列噪声水平（sigma）。该调度器有助于控制生成模型中的扩散过程，允许对生成过程中每一步应用的噪声水平进行精细调整。 ## 输入 diff --git a/zh/built-in-nodes/KlingAvatarNode.mdx b/zh/built-in-nodes/KlingAvatarNode.mdx index ec136b377..f97918d4e 100644 --- a/zh/built-in-nodes/KlingAvatarNode.mdx +++ b/zh/built-in-nodes/KlingAvatarNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingAvatarNode" icon: "circle" mode: wide --- + ## 概述 Kling Avatar 2.0 节点可根据单张参考照片和音频文件生成广播级数字人视频。该节点能创建说话头像视频，并支持通过可选文本提示定义数字人的动作、表情及镜头运动。 diff --git a/zh/built-in-nodes/KlingCameraControlI2VNode.mdx b/zh/built-in-nodes/KlingCameraControlI2VNode.mdx index 93721dcc4..fc4c1031b 100644 --- a/zh/built-in-nodes/KlingCameraControlI2VNode.mdx +++ b/zh/built-in-nodes/KlingCameraControlI2VNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingCameraControlI2VNode" icon: "circle" mode: wide --- -# Kling 图像转视频摄像机控制节点 此节点可将静态图像转换为具有专业摄像机运镜的电影级视频。这款专门的图像转视频节点允许您控制虚拟摄像机动作，包括变焦、旋转、平移、俯仰和第一人称视角，同时保持对原始图像的关注。摄像机控制目前仅在专业模式下支持，使用 kling-v1-5 模型，时长为5秒。 @@ -25,8 +24,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `视频ID` | 生成的视频输出 | VIDEO | -| `时长` | 生成视频的唯一标识符 | STRING | -| `duration` | 生成视频的时长 | STRING | +| `视频ID` | 生成视频的唯一标识符 | STRING | +| `时长` | 生成视频的时长 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControlI2VNode/zh.md) diff --git a/zh/built-in-nodes/KlingCameraControlT2VNode.mdx b/zh/built-in-nodes/KlingCameraControlT2VNode.mdx index 00c805fd4..8453070a7 100644 --- a/zh/built-in-nodes/KlingCameraControlT2VNode.mdx +++ b/zh/built-in-nodes/KlingCameraControlT2VNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingCameraControlT2VNode" icon: "circle" mode: wide --- + ### 概述 Kling 文本到视频摄像机控制节点可将文本转换为具有专业摄像机运动的电影级视频，模拟真实世界中的电影摄影技术。此节点支持控制虚拟摄像机动作，包括变焦、旋转、平移、倾斜和第一人称视角，同时保持对原始文本的关注。时长、模式和模型名称是硬编码的，因为摄像机控制仅在专业模式下支持，使用 kling-v1-5 模型，时长为 5 秒。 diff --git a/zh/built-in-nodes/KlingCameraControls.mdx b/zh/built-in-nodes/KlingCameraControls.mdx index 52b35f081..5872b7ee2 100644 --- a/zh/built-in-nodes/KlingCameraControls.mdx +++ b/zh/built-in-nodes/KlingCameraControls.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingCameraControls" icon: "circle" mode: wide --- + Kling 摄像机控制节点允许您配置各种摄像机移动和旋转参数，以便在视频生成中创建运动控制效果。它提供了摄像机定位、旋转和变焦的控制，用于模拟不同的摄像机运动。 ## 输入 @@ -25,7 +26,7 @@ Kling 摄像机控制节点允许您配置各种摄像机移动和旋转参数 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `camera_control` | 返回配置好的摄像机控制设置，用于视频生成 | CAMERA_CONTROL | +| `镜头控制` | 返回配置好的摄像机控制设置，用于视频生成 | CAMERA_CONTROL | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingCameraControls/zh.md) diff --git a/zh/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx b/zh/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx index ece7ee2b4..23bd1c484 100644 --- a/zh/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx +++ b/zh/built-in-nodes/KlingDualCharacterVideoEffectNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingDualCharacterVideoEffectNode" icon: "circle" mode: wide --- + ### 概述 Kling 双角色视频特效节点可根据所选场景生成带有特效的视频。该节点接收两张图像，将第一张图像放置在合成视频的左侧，第二张图像放置在右侧。根据所选的特效场景，会应用不同的视觉效果。 diff --git a/zh/built-in-nodes/KlingFirstLastFrameNode.mdx b/zh/built-in-nodes/KlingFirstLastFrameNode.mdx index 065216ad3..d3c4d290a 100644 --- a/zh/built-in-nodes/KlingFirstLastFrameNode.mdx +++ b/zh/built-in-nodes/KlingFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingFirstLastFrameNode" icon: "circle" mode: wide --- + 此节点使用 Kling 3.0 模型生成视频。它基于文本提示、指定时长以及两个提供的图像（起始帧和结束帧）来创建视频。该节点还可以为视频生成配套音频。 ## 输入 diff --git a/zh/built-in-nodes/KlingImage2VideoNode.mdx b/zh/built-in-nodes/KlingImage2VideoNode.mdx index df106b1e1..513177716 100644 --- a/zh/built-in-nodes/KlingImage2VideoNode.mdx +++ b/zh/built-in-nodes/KlingImage2VideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingImage2VideoNode" icon: "circle" mode: wide --- + ### 概述 Kling 图生视频节点使用文本提示从起始参考图像生成视频。它接收一张图像作为第一帧，并根据正面和负面文本描述创建视频序列，支持模型、时长、宽高比和生成模式等可配置选项。 @@ -27,7 +28,7 @@ Kling 图生视频节点使用文本提示从起始参考图像生成视频。 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `视频ID` | 生成的视频输出。 | VIDEO | -| `时长` | 生成视频的唯一标识符。 | STRING | +| `视频ID` | 生成视频的唯一标识符。 | STRING | | `时长` | 生成视频的时长信息。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImage2VideoNode/zh.md) diff --git a/zh/built-in-nodes/KlingImageGenerationNode.mdx b/zh/built-in-nodes/KlingImageGenerationNode.mdx index dabb49a45..8d7f91c72 100644 --- a/zh/built-in-nodes/KlingImageGenerationNode.mdx +++ b/zh/built-in-nodes/KlingImageGenerationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingImageGenerationNode" icon: "circle" mode: wide --- + Kling 图像生成节点可根据文本提示生成图像，并支持使用参考图像进行引导。该节点基于文本描述和参考设置创建一张或多张图像，然后将生成的图像作为输出返回。 ## 输入 diff --git a/zh/built-in-nodes/KlingImageToVideoWithAudio.mdx b/zh/built-in-nodes/KlingImageToVideoWithAudio.mdx index 8971ea0f8..c9000964e 100644 --- a/zh/built-in-nodes/KlingImageToVideoWithAudio.mdx +++ b/zh/built-in-nodes/KlingImageToVideoWithAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingImageToVideoWithAudio" icon: "circle" mode: wide --- + 此文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingImageToVideoWithAudio/en.md) Kling 图像（首帧）转视频并添加音频节点使用 Kling AI 模型，从单张起始图像和文本提示生成短视频。它会创建一个以提供的图像为起始帧的视频序列，并可选择性地包含 AI 生成的音频来配合画面。 diff --git a/zh/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx b/zh/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx index f3c5d1ac9..b1e10efcc 100644 --- a/zh/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx +++ b/zh/built-in-nodes/KlingLipSyncAudioToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingLipSyncAudioToVideoNode" icon: "circle" mode: wide --- -# Kling 唇形同步音频转视频节点 此节点可将视频文件中的嘴部动作与音频文件中的音频内容同步。该节点会分析音频中的语音模式，并调整视频中的面部动作，以创建逼真的唇形同步效果。此过程需要包含清晰面部的视频以及包含清晰可辨语音的音频文件。 @@ -31,8 +30,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `视频ID` | 经过唇形同步嘴部动作处理后的视频 | VIDEO | -| `时长` | 处理后的视频的唯一标识符 | STRING | -| `duration` | 处理后的视频时长 | STRING | +| `视频ID` | 处理后的视频的唯一标识符 | STRING | +| `时长` | 处理后的视频时长 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncAudioToVideoNode/zh.md) diff --git a/zh/built-in-nodes/KlingLipSyncTextToVideoNode.mdx b/zh/built-in-nodes/KlingLipSyncTextToVideoNode.mdx index 0955b4cc6..87941049a 100644 --- a/zh/built-in-nodes/KlingLipSyncTextToVideoNode.mdx +++ b/zh/built-in-nodes/KlingLipSyncTextToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingLipSyncTextToVideoNode" icon: "circle" mode: wide --- -# Kling 唇形同步文本转视频节点 此节点可将视频文件中的人物口型与文本提示进行同步。它接收输入视频，生成角色唇部动作与提供文本相匹配的新视频。该节点使用语音合成技术实现自然的语音同步效果。 @@ -29,8 +28,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `视频ID` | 生成的唇形同步音频视频 | VIDEO | -| `时长` | 生成视频的唯一标识符 | STRING | -| `duration` | 生成视频的时长信息 | STRING | +| `视频ID` | 生成视频的唯一标识符 | STRING | +| `时长` | 生成视频的时长信息 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingLipSyncTextToVideoNode/zh.md) diff --git a/zh/built-in-nodes/KlingMotionControl.mdx b/zh/built-in-nodes/KlingMotionControl.mdx index 4109e4966..654ed15c9 100644 --- a/zh/built-in-nodes/KlingMotionControl.mdx +++ b/zh/built-in-nodes/KlingMotionControl.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingMotionControl" icon: "circle" mode: wide --- + ### 概述 Kling 运动控制节点通过将参考视频中的动作、表情和镜头运动应用于由参考图像和文本提示定义的角色来生成视频。它允许您控制角色的最终朝向是来自参考视频还是参考图像。 diff --git a/zh/built-in-nodes/KlingOmniProEditVideoNode.mdx b/zh/built-in-nodes/KlingOmniProEditVideoNode.mdx index e0ed255fe..f7c4379ed 100644 --- a/zh/built-in-nodes/KlingOmniProEditVideoNode.mdx +++ b/zh/built-in-nodes/KlingOmniProEditVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProEditVideoNode" icon: "circle" mode: wide --- + Kling Omni 编辑视频（专业版）节点使用 AI 模型，根据文本描述编辑现有视频。您提供源视频和提示词，节点将生成相同长度但包含所需更改的新视频。它可以选择使用参考图像来引导风格，并保留源视频的原始音频。 ## 输入 diff --git a/zh/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx b/zh/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx index 922bcb370..ff419f9a0 100644 --- a/zh/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx +++ b/zh/built-in-nodes/KlingOmniProFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProFirstLastFrameNode" icon: "circle" mode: wide --- + 此节点使用最新的 Kling AI 模型，根据起始帧、可选的结束帧或参考图像生成视频。它可以创建单个视频，也可以创建包含多个片段（每个片段有独立提示词和时长）的多镜头故事板。该节点处理这些输入，生成指定时长和分辨率的视频，并可选择生成音频。 ## 输入 diff --git a/zh/built-in-nodes/KlingOmniProImageNode.mdx b/zh/built-in-nodes/KlingOmniProImageNode.mdx index 134b46340..91e564d08 100644 --- a/zh/built-in-nodes/KlingOmniProImageNode.mdx +++ b/zh/built-in-nodes/KlingOmniProImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProImageNode" icon: "circle" mode: wide --- + Kling Omni Image (Pro) 节点使用最新的 Kling AI 模型创建或编辑图像。它基于文本描述生成图像，并可选择使用参考图像来引导风格或内容。该节点向外部 API 发送请求，由 API 处理任务并返回最终图像。 ## 输入 diff --git a/zh/built-in-nodes/KlingOmniProImageToVideoNode.mdx b/zh/built-in-nodes/KlingOmniProImageToVideoNode.mdx index 5d1a1f30a..c2e950604 100644 --- a/zh/built-in-nodes/KlingOmniProImageToVideoNode.mdx +++ b/zh/built-in-nodes/KlingOmniProImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProImageToVideoNode" icon: "circle" mode: wide --- + 此节点使用 Kling AI 模型，基于文本提示和最多七张参考图像生成视频。您可以控制视频的宽高比、时长、分辨率，并可选择使用故事板或生成音频。该节点将请求发送至外部 API 并返回生成的视频。 ## 输入 diff --git a/zh/built-in-nodes/KlingOmniProTextToVideoNode.mdx b/zh/built-in-nodes/KlingOmniProTextToVideoNode.mdx index fc1915bea..e0f9f9f1f 100644 --- a/zh/built-in-nodes/KlingOmniProTextToVideoNode.mdx +++ b/zh/built-in-nodes/KlingOmniProTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProTextToVideoNode" icon: "circle" mode: wide --- + 此节点使用最新的 Kling AI 模型，根据文本描述生成视频。它会将你的提示词发送到远程 API，并返回生成的视频。该节点允许你控制视频的长度、画幅、质量，甚至创建多镜头故事板。 ## 输入 diff --git a/zh/built-in-nodes/KlingOmniProVideoToVideoNode.mdx b/zh/built-in-nodes/KlingOmniProVideoToVideoNode.mdx index 3023114a1..ed8360f51 100644 --- a/zh/built-in-nodes/KlingOmniProVideoToVideoNode.mdx +++ b/zh/built-in-nodes/KlingOmniProVideoToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingOmniProVideoToVideoNode" icon: "circle" mode: wide --- + 此节点使用 Kling AI 模型，基于输入视频和可选的参考图像生成新视频。您提供描述所需内容的文本提示，节点会根据参考视频进行转换。它还可以融合最多四张额外的参考图像，以指导输出的风格和内容。 ## 输入 diff --git a/zh/built-in-nodes/KlingSingleImageVideoEffectNode.mdx b/zh/built-in-nodes/KlingSingleImageVideoEffectNode.mdx index a1c737026..5a206127a 100644 --- a/zh/built-in-nodes/KlingSingleImageVideoEffectNode.mdx +++ b/zh/built-in-nodes/KlingSingleImageVideoEffectNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "KlingSingleImageVideoEffectNode" icon: "circle" mode: wide --- -# Kling 单图视频特效节点 Kling 单图视频特效节点基于单张参考图像创建带有不同特效的视频。它应用各种视觉效果和场景，将静态图像转化为动态视频内容。该节点支持不同的特效场景、模型选项和视频时长，以实现所需的视觉效果。 @@ -25,7 +24,7 @@ Kling 单图视频特效节点基于单张参考图像创建带有不同特效 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `视频ID` | 应用特效后生成的视频 | VIDEO | -| `时长` | 生成视频的唯一标识符 | STRING | +| `视频ID` | 生成视频的唯一标识符 | STRING | | `时长` | 生成视频的时长 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingSingleImageVideoEffectNode/zh.md) diff --git a/zh/built-in-nodes/KlingStartEndFrameNode.mdx b/zh/built-in-nodes/KlingStartEndFrameNode.mdx index 2a9737009..395a11c9e 100644 --- a/zh/built-in-nodes/KlingStartEndFrameNode.mdx +++ b/zh/built-in-nodes/KlingStartEndFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingStartEndFrameNode" icon: "circle" mode: wide --- + Kling 起始-结束帧转视频节点可创建一段视频序列，在您提供的起始图像和结束图像之间进行过渡。它会生成中间的所有帧，从而产生从第一帧到最后一帧的平滑变换。此节点调用图像到视频 API，但仅支持与 `image_tail` 请求字段配合使用的输入选项。 ## 输入 @@ -31,8 +32,8 @@ Kling 起始-结束帧转视频节点可创建一段视频序列，在您提供 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `视频ID` | 生成的视频序列 | VIDEO | -| `时长` | 生成视频的唯一标识符 | STRING | -| `duration` | 生成视频的时长 | STRING | +| `视频ID` | 生成视频的唯一标识符 | STRING | +| `时长` | 生成视频的时长 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingStartEndFrameNode/zh.md) diff --git a/zh/built-in-nodes/KlingTextToVideoNode.mdx b/zh/built-in-nodes/KlingTextToVideoNode.mdx index 66d4aad3e..462954260 100644 --- a/zh/built-in-nodes/KlingTextToVideoNode.mdx +++ b/zh/built-in-nodes/KlingTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingTextToVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoNode/en.md) Kling 文本转视频节点可将文本描述转换为视频内容。它接收文本提示词，并根据指定的配置设置生成相应的视频序列。该节点支持不同的宽高比和生成模式，以生成不同时长和质量的视频。 @@ -24,8 +25,8 @@ Kling 文本转视频节点可将文本描述转换为视频内容。它接收 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `视频ID` | 生成的视频输出 | VIDEO | -| `时长` | 生成视频的唯一标识符 | STRING | -| `duration` | 生成视频的时长信息 | STRING | +| `视频ID` | 生成视频的唯一标识符 | STRING | +| `时长` | 生成视频的时长信息 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingTextToVideoNode/zh.md) diff --git a/zh/built-in-nodes/KlingTextToVideoWithAudio.mdx b/zh/built-in-nodes/KlingTextToVideoWithAudio.mdx index 44dea0fd7..5478cda47 100644 --- a/zh/built-in-nodes/KlingTextToVideoWithAudio.mdx +++ b/zh/built-in-nodes/KlingTextToVideoWithAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingTextToVideoWithAudio" icon: "circle" mode: wide --- + Kling 文本转视频（含音频）节点可根据文本描述生成短视频。该节点向 Kling AI 服务发送请求，由服务处理提示词并返回视频文件。节点还可根据文本为视频生成配套音频。 ## 输入 diff --git a/zh/built-in-nodes/KlingVideoExtendNode.mdx b/zh/built-in-nodes/KlingVideoExtendNode.mdx index 339a0bc40..de8b34491 100644 --- a/zh/built-in-nodes/KlingVideoExtendNode.mdx +++ b/zh/built-in-nodes/KlingVideoExtendNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingVideoExtendNode" icon: "circle" mode: wide --- + Kling 视频扩展节点允许您扩展由其他 Kling 节点生成的视频。它接收一个由视频 ID 标识的现有视频，并根据您的文本提示生成额外内容。该节点通过将扩展请求发送至 Kling API，并返回扩展后的视频及其新 ID 和时长。 ## 输入 @@ -23,8 +24,8 @@ Kling 视频扩展节点允许您扩展由其他 Kling 节点生成的视频。 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `视频ID` | 由 Kling API 生成的扩展视频 | VIDEO | -| `时长` | 扩展视频的唯一标识符 | STRING | -| `duration` | 扩展视频的时长 | STRING | +| `视频ID` | 扩展视频的唯一标识符 | STRING | +| `时长` | 扩展视频的时长 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/KlingVideoExtendNode/zh.md) diff --git a/zh/built-in-nodes/KlingVideoNode.mdx b/zh/built-in-nodes/KlingVideoNode.mdx index edeff6550..bbab968aa 100644 --- a/zh/built-in-nodes/KlingVideoNode.mdx +++ b/zh/built-in-nodes/KlingVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingVideoNode" icon: "circle" mode: wide --- + 此节点使用 Kling V3 模型生成视频。它支持两种主要模式：文本转视频（根据文本描述创建视频）和图像转视频（对现有图像进行动画处理）。它还提供高级功能，例如为每个部分（分镜）使用不同提示创建多段视频，以及可选地生成配套音频。 ## 输入 diff --git a/zh/built-in-nodes/KlingVirtualTryOnNode.mdx b/zh/built-in-nodes/KlingVirtualTryOnNode.mdx index a42e53600..d0fc13e5d 100644 --- a/zh/built-in-nodes/KlingVirtualTryOnNode.mdx +++ b/zh/built-in-nodes/KlingVirtualTryOnNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "KlingVirtualTryOnNode" icon: "circle" mode: wide --- + Kling 虚拟试穿节点。输入一张人物图像和一张服装图像，即可在人物身上试穿该服装。您可以将多张服装图片合并为一张白色背景的图像。 ## 输入 diff --git a/zh/built-in-nodes/Krea2ImageNode.mdx b/zh/built-in-nodes/Krea2ImageNode.mdx index 9c1599357..a73cc2473 100644 --- a/zh/built-in-nodes/Krea2ImageNode.mdx +++ b/zh/built-in-nodes/Krea2ImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Krea2ImageNode" icon: "circle" mode: wide --- + ## ## 概述 Krea 2 图像节点使用 Krea 2 AI 模型生成图像。它支持两种模型变体：Medium 适用于表现力丰富的插画，Large 适用于表现力丰富的写实风格。您可以选择性地包含情绪板（moodboard）和最多 10 个图像风格参考，以影响生成的图像。 diff --git a/zh/built-in-nodes/Krea2StyleReferenceNode.mdx b/zh/built-in-nodes/Krea2StyleReferenceNode.mdx index 94b40cca7..f8aed40a3 100644 --- a/zh/built-in-nodes/Krea2StyleReferenceNode.mdx +++ b/zh/built-in-nodes/Krea2StyleReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Krea2StyleReferenceNode" icon: "circle" mode: wide --- + ### 概述 Krea 2 风格参考节点允许您添加一张参考图片来影响 Krea 2 图像生成的风格。您可以串联多个风格参考（最多 10 个），并将合并后的结果输入到 Krea 2 图像节点。您提供的每张图片都会上传到 ComfyAPI 存储，并以 URL 形式传递。 diff --git a/zh/built-in-nodes/LTXAVTextEncoderLoader.mdx b/zh/built-in-nodes/LTXAVTextEncoderLoader.mdx index e451e047f..d1a6e3c3c 100644 --- a/zh/built-in-nodes/LTXAVTextEncoderLoader.mdx +++ b/zh/built-in-nodes/LTXAVTextEncoderLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXAVTextEncoderLoader" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXAVTextEncoderLoader/en.md) 此节点加载用于 LTXV 音频模型的专用文本编码器。它将特定的文本编码器文件与检查点文件结合，创建一个可用于音频相关文本条件任务的 CLIP 模型。 diff --git a/zh/built-in-nodes/LTXVAddGuide.mdx b/zh/built-in-nodes/LTXVAddGuide.mdx index e72405766..880e89987 100644 --- a/zh/built-in-nodes/LTXVAddGuide.mdx +++ b/zh/built-in-nodes/LTXVAddGuide.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAddGuide" icon: "circle" mode: wide --- + LTXVAddGuide 节点通过编码输入图像或视频，并将其作为关键帧融入条件数据，为潜在序列添加视频条件引导。该节点通过 VAE 编码器处理输入，将生成的潜在表示策略性地放置在指定的帧位置，同时使用关键帧信息更新正向和负向条件。节点处理帧对齐约束，并允许控制条件影响的强度。 ## 输入 @@ -25,8 +26,8 @@ LTXVAddGuide 节点通过编码输入图像或视频，并将其作为关键帧 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向` | 已使用关键帧引导信息更新的正向条件 | CONDITIONING | -| `潜在空间` | 已使用关键帧引导信息更新的负向条件 | CONDITIONING | +| `正向` | 已使用关键帧引导信息更新的正向条件 | CONDITIONING | +| `负向` | 已使用关键帧引导信息更新的负向条件 | CONDITIONING | | `潜在空间` | 已融入条件帧并更新噪声掩码的潜在序列 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAddGuide/zh.md) diff --git a/zh/built-in-nodes/LTXVAudioVAEDecode.mdx b/zh/built-in-nodes/LTXVAudioVAEDecode.mdx index 62d49c524..5e11a5241 100644 --- a/zh/built-in-nodes/LTXVAudioVAEDecode.mdx +++ b/zh/built-in-nodes/LTXVAudioVAEDecode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAEDecode" icon: "circle" mode: wide --- + LTXV 音频 VAE 解码节点用于将音频的潜在表示转换回音频波形。它使用专门的音频 VAE 模型执行此解码过程，生成具有特定采样率的音频输出。 ## 输入 @@ -20,7 +21,7 @@ LTXV 音频 VAE 解码节点用于将音频的潜在表示转换回音频波形 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `Audio` | 解码后的音频波形及其关联的采样率。波形是一个张量，被移动到与输入潜在表示相同的设备上，采样率由音频 VAE 模型决定。 | AUDIO | +| `音频` | 解码后的音频波形及其关联的采样率。波形是一个张量，被移动到与输入潜在表示相同的设备上，采样率由音频 VAE 模型决定。 | AUDIO | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAEDecode/zh.md) diff --git a/zh/built-in-nodes/LTXVAudioVAEEncode.mdx b/zh/built-in-nodes/LTXVAudioVAEEncode.mdx index c9e720bb0..972ff5b19 100644 --- a/zh/built-in-nodes/LTXVAudioVAEEncode.mdx +++ b/zh/built-in-nodes/LTXVAudioVAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAEEncode" icon: "circle" mode: wide --- + LTXV 音频 VAE 编码节点接收音频输入，并使用指定的音频 VAE 模型将其压缩为更小的潜在表示。此过程对于在潜在空间工作流中生成或操作音频至关重要，因为它将原始音频数据转换为管道中其他节点能够理解和处理的格式。 ## 输入 diff --git a/zh/built-in-nodes/LTXVAudioVAELoader.mdx b/zh/built-in-nodes/LTXVAudioVAELoader.mdx index d35501180..8e8cdfb7b 100644 --- a/zh/built-in-nodes/LTXVAudioVAELoader.mdx +++ b/zh/built-in-nodes/LTXVAudioVAELoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVAudioVAELoader" icon: "circle" mode: wide --- + LTXV 音频 VAE 加载器节点用于从检查点文件加载预训练的音频变分自编码器（VAE）模型。它会读取指定的检查点，加载其权重和元数据，并将模型准备好，以便在 ComfyUI 中的音频生成或处理工作流中使用。 ## 输入 @@ -17,7 +18,7 @@ LTXV 音频 VAE 加载器节点用于从检查点文件加载预训练的音频 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `Audio VAE` | 已加载的音频变分自编码器模型，可连接到其他音频处理节点。 | VAE | +| `音频VAE` | 已加载的音频变分自编码器模型，可连接到其他音频处理节点。 | VAE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVAudioVAELoader/zh.md) diff --git a/zh/built-in-nodes/LTXVConcatAVLatent.mdx b/zh/built-in-nodes/LTXVConcatAVLatent.mdx index 5ddd2bf58..3ec5f41d0 100644 --- a/zh/built-in-nodes/LTXVConcatAVLatent.mdx +++ b/zh/built-in-nodes/LTXVConcatAVLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVConcatAVLatent" icon: "circle" mode: wide --- + LTXVConcatAVLatent 节点将视频潜在表示和音频潜在表示合并为单个拼接后的潜在输出。它会合并两个输入的 `samples` 张量，如果存在 `noise_mask` 张量也会一并合并，为视频生成流程中的后续处理做好准备。 ## 输入 diff --git a/zh/built-in-nodes/LTXVConditioning.mdx b/zh/built-in-nodes/LTXVConditioning.mdx index 094d50ebd..286ba4627 100644 --- a/zh/built-in-nodes/LTXVConditioning.mdx +++ b/zh/built-in-nodes/LTXVConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVConditioning" icon: "circle" mode: wide --- + LTXVConditioning 节点用于为视频生成模型的正向和负向条件输入添加帧率信息。它接收现有的条件数据，并将指定的帧率值应用于两个条件集，使其适用于视频模型处理。 ## 输入 @@ -19,7 +20,7 @@ LTXVConditioning 节点用于为视频生成模型的正向和负向条件输入 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 已应用帧率信息的正向条件 | CONDITIONING | +| `正面条件` | 已应用帧率信息的正向条件 | CONDITIONING | | `负面条件` | 已应用帧率信息的负向条件 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVConditioning/zh.md) diff --git a/zh/built-in-nodes/LTXVContextWindows.mdx b/zh/built-in-nodes/LTXVContextWindows.mdx new file mode 100644 index 000000000..2caddf6c2 --- /dev/null +++ b/zh/built-in-nodes/LTXVContextWindows.mdx @@ -0,0 +1,37 @@ +--- +title: "LTXVContextWindows - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LTXVContextWindows node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LTXVContextWindows" +icon: "circle" +mode: wide +--- + +此节点在采样过程中为 LTXV 类模型设置上下文窗口。它将视频生成过程划分为重叠窗口，以管理内存使用并改善时间连贯性。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 必填 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `model` | 采样时应用上下文窗口的模型。 | MODEL | 是 | - | +| `context_length` | 上下文窗口的实际帧长度。必须为 8*n + 1。（默认值：145） | INT | 是 | 最小值：1
最大值：nodes.MAX_RESOLUTION
步长：8 | +| `context_overlap` | 上下文窗口的实际帧重叠长度。（默认值：40） | INT | 是 | 最小值：0
步长：8 | +| `context_schedule` | 上下文窗口的步进依赖调度算法。（默认值：UNIFORM_STANDARD） | COMBO | 是 | `STATIC_STANDARD`
`UNIFORM_STANDARD`
`UNIFORM_LOOPED`
`BATCHED` | +| `context_stride` | 上下文窗口的步幅；仅适用于均匀调度。（默认值：1） | INT | 否 | 最小值：1 | +| `closed_loop` | 是否闭合上下文窗口循环；仅适用于循环调度。（默认值：False） | BOOLEAN | 否 | True
False | +| `fuse_method` | 用于融合上下文窗口的方法。（默认值：PYRAMID） | COMBO | 是 | 选项来自 comfy.context_windows.ContextFuseMethods.LIST_STATIC | +| `freenoise` | 是否应用 FreeNoise 噪声混洗，可改善窗口融合效果。（默认值：True） | BOOLEAN | 否 | True
False | +| `retain_first_frame` | 在每个上下文窗口中保留第一个潜在帧（可能有助于保留初始参考）。（默认值：False） | BOOLEAN | 否 | True
False | +| `split_conds_to_windows` | 是否根据区域索引将由 ConditionCombine 创建的多个条件分割到每个窗口。（默认值：False） | BOOLEAN | 否 | True
False | + +**注意：** `context_length` 参数必须遵循公式 8*n + 1，其中 n 为正整数。节点通过将实际帧转换为潜在帧来自动调整该值以满足此要求。`context_overlap` 也会从实际帧转换为潜在帧（除以 8）。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `MODEL` | 已应用上下文窗口用于采样的模型。 | MODEL | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVContextWindows/zh.md) + +--- +**Source fingerprint (SHA-256):** `ad0b8c54acaab1853f6fe98dbad675478f033caf867df954b40b7db5208f5ae4` diff --git a/zh/built-in-nodes/LTXVCropGuides.mdx b/zh/built-in-nodes/LTXVCropGuides.mdx index 5482b3b74..94ece28c8 100644 --- a/zh/built-in-nodes/LTXVCropGuides.mdx +++ b/zh/built-in-nodes/LTXVCropGuides.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVCropGuides" icon: "circle" mode: wide --- + LTXVCropGuides 节点通过移除关键帧信息并调整潜在维度，处理用于视频生成的 conditioning 和 latent 输入。它会裁剪潜在图像和噪声掩码以排除关键帧部分，同时清除正向和负向 conditioning 输入中的关键帧索引。此操作用于准备无需关键帧引导的视频生成工作流数据。 ## 输入 @@ -19,8 +20,8 @@ LTXVCropGuides 节点通过移除关键帧信息并调整潜在维度，处理 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向` | 已处理的正向 conditioning，关键帧索引和引导注意力条目已被清除 | CONDITIONING | -| `潜在空间` | 已处理的负向 conditioning，关键帧索引和引导注意力条目已被清除 | CONDITIONING | +| `正向` | 已处理的正向 conditioning，关键帧索引和引导注意力条目已被清除 | CONDITIONING | +| `负向` | 已处理的负向 conditioning，关键帧索引和引导注意力条目已被清除 | CONDITIONING | | `潜在空间` | 裁剪后的潜在表示，包含调整后的样本和噪声掩码，关键帧部分已被移除 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVCropGuides/zh.md) diff --git a/zh/built-in-nodes/LTXVEmptyLatentAudio.mdx b/zh/built-in-nodes/LTXVEmptyLatentAudio.mdx index 482fa14c8..2df7bce99 100644 --- a/zh/built-in-nodes/LTXVEmptyLatentAudio.mdx +++ b/zh/built-in-nodes/LTXVEmptyLatentAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVEmptyLatentAudio" icon: "circle" mode: wide --- + LTXV 空潜变量音频节点用于创建一批空（零填充）潜变量音频张量。它通过提供的音频 VAE 模型配置来确定潜变量空间的正确维度，例如通道数和频率区间数。该空潜变量可作为 ComfyUI 中音频生成或处理工作流的起点。 ## 输入 @@ -22,7 +23,7 @@ LTXV 空潜变量音频节点用于创建一批空（零填充）潜变量音频 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `Latent` | 一个空的潜变量音频张量，其结构为 (batch_size, z_channels, num_audio_latents, audio_freq)，配置为与输入的音频 VAE 匹配。输出还包含一个设置为 "audio" 的 `type` 字段。 | LATENT | +| `潜空间` | 一个空的潜变量音频张量，其结构为 (batch_size, z_channels, num_audio_latents, audio_freq)，配置为与输入的音频 VAE 匹配。输出还包含一个设置为 "audio" 的 `type` 字段。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVEmptyLatentAudio/zh.md) diff --git a/zh/built-in-nodes/LTXVImgToVideo.mdx b/zh/built-in-nodes/LTXVImgToVideo.mdx index 6570240bc..a218c2186 100644 --- a/zh/built-in-nodes/LTXVImgToVideo.mdx +++ b/zh/built-in-nodes/LTXVImgToVideo.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LTXVImgToVideo" icon: "circle" mode: wide --- -# LTXVImgToVideo 节点 LTXVImgToVideo 节点将输入图像转换为视频生成模型所需的视频潜在表示。它接收单张图像，使用 VAE 编码器将其扩展为帧序列，然后通过强度控制应用条件处理，以确定视频生成过程中原始图像内容被保留或修改的程度。 @@ -27,9 +26,9 @@ LTXVImgToVideo 节点将输入图像转换为视频生成模型所需的视频 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 已应用视频帧遮罩处理后的正面条件 | CONDITIONING | -| `Latent` | 已应用视频帧遮罩处理后的负面条件 | CONDITIONING | -| `latent` | 包含编码帧和噪声遮罩的视频潜在表示，用于视频生成 | LATENT | +| `正面条件` | 已应用视频帧遮罩处理后的正面条件 | CONDITIONING | +| `负面条件` | 已应用视频帧遮罩处理后的负面条件 | CONDITIONING | +| `Latent` | 包含编码帧和噪声遮罩的视频潜在表示，用于视频生成 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVImgToVideo/zh.md) diff --git a/zh/built-in-nodes/LTXVImgToVideoInplace.mdx b/zh/built-in-nodes/LTXVImgToVideoInplace.mdx index db085d1a6..59cd66efe 100644 --- a/zh/built-in-nodes/LTXVImgToVideoInplace.mdx +++ b/zh/built-in-nodes/LTXVImgToVideoInplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVImgToVideoInplace" icon: "circle" mode: wide --- + LTXVImgToVideoInplace 节点通过将输入图像编码到视频潜空间的初始帧中，对视频潜空间表示进行条件化处理。其工作原理是使用 VAE 将图像编码到潜空间，然后根据指定的强度将其与现有潜空间样本进行混合。这使得图像能够作为视频生成的起始点或条件信号。 ## 输入 diff --git a/zh/built-in-nodes/LTXVLatentUpsampler.mdx b/zh/built-in-nodes/LTXVLatentUpsampler.mdx index a96980e2b..dc9342994 100644 --- a/zh/built-in-nodes/LTXVLatentUpsampler.mdx +++ b/zh/built-in-nodes/LTXVLatentUpsampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVLatentUpsampler" icon: "circle" mode: wide --- + LTXVLatentUpsampler节点可将视频潜在表示的空间分辨率提升两倍。它使用专门的上采样模型处理潜在数据，该数据首先经过反归一化处理，然后利用提供的VAE通道统计信息重新归一化。此节点专为潜在空间内的视频工作流设计。 ## 输入 diff --git a/zh/built-in-nodes/LTXVPreprocess.mdx b/zh/built-in-nodes/LTXVPreprocess.mdx index aadee19d4..286b21fff 100644 --- a/zh/built-in-nodes/LTXVPreprocess.mdx +++ b/zh/built-in-nodes/LTXVPreprocess.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVPreprocess" icon: "circle" mode: wide --- + LTXVPreprocess 节点对图像应用压缩预处理。它接收输入图像，并使用指定的压缩级别进行处理，输出应用了压缩设置的已处理图像。 ## 输入 @@ -18,7 +19,7 @@ LTXVPreprocess 节点对图像应用压缩预处理。它接收输入图像， | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `output_image` | 应用压缩后的已处理输出图像 | IMAGE | +| `输出图像` | 应用压缩后的已处理输出图像 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVPreprocess/zh.md) diff --git a/zh/built-in-nodes/LTXVReferenceAudio.mdx b/zh/built-in-nodes/LTXVReferenceAudio.mdx index ba08ef9ae..d4c393f03 100644 --- a/zh/built-in-nodes/LTXVReferenceAudio.mdx +++ b/zh/built-in-nodes/LTXVReferenceAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVReferenceAudio" icon: "circle" mode: wide --- + ## 概述 LTXV 参考音频节点用于音频生成中的说话人身份迁移。它将参考音频片段编码为模型的条件输入，使生成的音频能够继承说话人的声音特征。该节点还可应用身份引导，通过额外的处理步骤来增强说话人身份效果。 @@ -27,7 +28,7 @@ LTXV 参考音频节点用于音频生成中的说话人身份迁移。它将参 | 输出名称 | 说明 | 数据类型 | | --- | --- | --- | | `positive` | 已应用身份引导函数的模型。 | MODEL | -| `negative` | 正向条件，现包含编码后的参考音频数据。 | CONDITIONING | +| `positive` | 正向条件，现包含编码后的参考音频数据。 | CONDITIONING | | `negative` | 负向条件，现包含编码后的参考音频数据。 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVReferenceAudio/zh.md) diff --git a/zh/built-in-nodes/LTXVScheduler.mdx b/zh/built-in-nodes/LTXVScheduler.mdx index 533e82455..890828172 100644 --- a/zh/built-in-nodes/LTXVScheduler.mdx +++ b/zh/built-in-nodes/LTXVScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVScheduler" icon: "circle" mode: wide --- + LTXVScheduler 节点用于生成自定义采样过程中的 sigma 值。它根据输入潜变量中的 token 数量计算噪声调度参数，并应用 sigmoid 变换来创建采样调度。该节点可以选择性地拉伸生成的 sigma 值，使其匹配指定的终止值。 ## 输入 diff --git a/zh/built-in-nodes/LTXVSeparateAVLatent.mdx b/zh/built-in-nodes/LTXVSeparateAVLatent.mdx index ebde30b68..3944870c7 100644 --- a/zh/built-in-nodes/LTXVSeparateAVLatent.mdx +++ b/zh/built-in-nodes/LTXVSeparateAVLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LTXVSeparateAVLatent" icon: "circle" mode: wide --- + LTXVSeparateAVLatent 节点接收一个组合的音频-视频潜在表示，并将其拆分为两个独立的部分：一个用于视频，一个用于音频。它会分离样本，如果存在噪声掩码，也会从输入潜在表示中分离出来，从而创建两个新的潜在对象。 ## 输入 @@ -19,7 +20,7 @@ LTXVSeparateAVLatent 节点接收一个组合的音频-视频潜在表示，并 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `audio_latent` | 包含分离后视频数据的潜在表示。 | LATENT | +| `video_latent` | 包含分离后视频数据的潜在表示。 | LATENT | | `audio_latent` | 包含分离后音频数据的潜在表示。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVSeparateAVLatent/zh.md) diff --git a/zh/built-in-nodes/LaplaceScheduler.mdx b/zh/built-in-nodes/LaplaceScheduler.mdx index 15b7cfd45..1170d8de7 100644 --- a/zh/built-in-nodes/LaplaceScheduler.mdx +++ b/zh/built-in-nodes/LaplaceScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LaplaceScheduler" icon: "circle" mode: wide --- + LaplaceScheduler 节点会生成遵循拉普拉斯分布的 sigma 值序列，用于扩散采样过程。它创建了一个从最大值逐渐减小到最小值的噪声水平调度，并使用拉普拉斯分布参数来控制其进程。该调度器常用于自定义采样工作流中，为扩散模型定义噪声调度。 ## 输入 diff --git a/zh/built-in-nodes/LatentAdd.mdx b/zh/built-in-nodes/LatentAdd.mdx index 6dad30ee9..8e3978b75 100644 --- a/zh/built-in-nodes/LatentAdd.mdx +++ b/zh/built-in-nodes/LatentAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentAdd" icon: "circle" mode: wide --- + LatentAdd 节点用于对两个潜在表示进行加法运算。它通过逐元素相加的方式，将这两个表示中编码的特征或属性进行组合。 ## 输入 diff --git a/zh/built-in-nodes/LatentApplyOperation.mdx b/zh/built-in-nodes/LatentApplyOperation.mdx index e6c76eccb..61143e981 100644 --- a/zh/built-in-nodes/LatentApplyOperation.mdx +++ b/zh/built-in-nodes/LatentApplyOperation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentApplyOperation" icon: "circle" mode: wide --- + LatentApplyOperation 节点对潜在样本应用指定操作。它接收潜在数据和操作作为输入，使用提供的操作处理潜在样本，并返回修改后的潜在数据。此节点允许您在工作流中转换或操作潜在表示。 ## 输入 diff --git a/zh/built-in-nodes/LatentApplyOperationCFG.mdx b/zh/built-in-nodes/LatentApplyOperationCFG.mdx index 256fd1e82..1e43cd17b 100644 --- a/zh/built-in-nodes/LatentApplyOperationCFG.mdx +++ b/zh/built-in-nodes/LatentApplyOperationCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentApplyOperationCFG" icon: "circle" mode: wide --- + LatentApplyOperationCFG 节点应用潜在操作来修改模型中的条件引导过程。其工作原理是在无分类器引导（CFG）采样过程中拦截条件输出，并在潜在表示用于生成之前对其应用指定操作。 ## 输入 diff --git a/zh/built-in-nodes/LatentBatch.mdx b/zh/built-in-nodes/LatentBatch.mdx index b4727bbc1..5e767391c 100644 --- a/zh/built-in-nodes/LatentBatch.mdx +++ b/zh/built-in-nodes/LatentBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBatch" icon: "circle" mode: wide --- + LatentBatch 节点旨在将两组潜在样本合并为单个批次，在拼接前可能会调整其中一组样本的尺寸以匹配另一组。此操作有助于将不同的潜在表示组合起来，用于后续处理或生成任务。 ## 输入 diff --git a/zh/built-in-nodes/LatentBatchSeedBehavior.mdx b/zh/built-in-nodes/LatentBatchSeedBehavior.mdx index 22b913146..fbd3fd70f 100644 --- a/zh/built-in-nodes/LatentBatchSeedBehavior.mdx +++ b/zh/built-in-nodes/LatentBatchSeedBehavior.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBatchSeedBehavior" icon: "circle" mode: wide --- + LatentBatchSeedBehavior 节点用于修改一批潜在样本的种子行为。它允许在整个批次中随机化或固定种子，从而通过引入变异性或保持生成输出的一致性来影响生成过程。 ## 输入 diff --git a/zh/built-in-nodes/LatentBlend.mdx b/zh/built-in-nodes/LatentBlend.mdx index a5922c749..1f4c5a075 100644 --- a/zh/built-in-nodes/LatentBlend.mdx +++ b/zh/built-in-nodes/LatentBlend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentBlend" icon: "circle" mode: wide --- + LatentBlend 节点通过使用指定的混合因子将两个潜在样本混合在一起。它接收两个潜在输入，并创建一个新的输出，其中第一个样本按混合因子加权，第二个样本按逆因子加权。如果输入样本具有不同的形状，第二个样本会自动调整大小以匹配第一个样本的尺寸。 ## 输入 diff --git a/zh/built-in-nodes/LatentComposite.mdx b/zh/built-in-nodes/LatentComposite.mdx index b5b1b2445..e08388bf3 100644 --- a/zh/built-in-nodes/LatentComposite.mdx +++ b/zh/built-in-nodes/LatentComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentComposite" icon: "circle" mode: wide --- + LatentComposite 节点旨在将两个潜在表示混合或合并为单个输出。此过程通过以受控方式结合输入潜在特征，对于创建复合图像或特征至关重要。 ## 输入 diff --git a/zh/built-in-nodes/LatentCompositeMasked.mdx b/zh/built-in-nodes/LatentCompositeMasked.mdx index e05ed2777..5281bfae9 100644 --- a/zh/built-in-nodes/LatentCompositeMasked.mdx +++ b/zh/built-in-nodes/LatentCompositeMasked.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCompositeMasked" icon: "circle" mode: wide --- + LatentCompositeMasked 节点用于在指定坐标处将两个潜在表示混合在一起，并可选择使用遮罩进行更可控的合成。该节点通过将一幅图像的部分叠加到另一幅图像上，并能够调整源图像大小以实现完美匹配，从而创建复杂的潜在图像。 ## 输入 diff --git a/zh/built-in-nodes/LatentConcat.mdx b/zh/built-in-nodes/LatentConcat.mdx index acb2a657b..0e192e2e0 100644 --- a/zh/built-in-nodes/LatentConcat.mdx +++ b/zh/built-in-nodes/LatentConcat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentConcat" icon: "circle" mode: wide --- + LatentConcat 节点通过沿选定维度拼接两个潜在样本来将其合并。该节点接收两个潜在输入，并沿 x、y 或 t 轴进行拼接，同时提供控制哪个样本排在前面的选项。在执行拼接前，节点会自动调整第二个输入的批次大小以匹配第一个输入。 ## 输入 diff --git a/zh/built-in-nodes/LatentCrop.mdx b/zh/built-in-nodes/LatentCrop.mdx index 1526b0cef..6312eda0c 100644 --- a/zh/built-in-nodes/LatentCrop.mdx +++ b/zh/built-in-nodes/LatentCrop.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCrop" icon: "circle" mode: wide --- + LatentCrop 节点用于对图像的潜在表示执行裁剪操作。它允许指定裁剪的尺寸和位置，从而实现对潜在空间的目标性修改。 ## 输入 diff --git a/zh/built-in-nodes/LatentCut.mdx b/zh/built-in-nodes/LatentCut.mdx index e874cb3c3..6fc753323 100644 --- a/zh/built-in-nodes/LatentCut.mdx +++ b/zh/built-in-nodes/LatentCut.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCut" icon: "circle" mode: wide --- + LatentCut 节点用于从潜在样本中沿指定维度提取特定部分。通过指定维度（x、y 或 t）、起始位置和提取数量，您可以裁剪出潜在表示的一部分。该节点支持正负索引，并会自动调整提取数量，确保其不超过可用范围。 ## 输入 diff --git a/zh/built-in-nodes/LatentCutToBatch.mdx b/zh/built-in-nodes/LatentCutToBatch.mdx index 2862dadac..59ff99dae 100644 --- a/zh/built-in-nodes/LatentCutToBatch.mdx +++ b/zh/built-in-nodes/LatentCutToBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentCutToBatch" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentCutToBatch/en.md) LatentCutToBatch 节点沿选定维度将潜在表示分割成多个切片，并将它们堆叠成一个新的批次。这使您可以独立处理潜在样本的不同部分。 diff --git a/zh/built-in-nodes/LatentFlip.mdx b/zh/built-in-nodes/LatentFlip.mdx index 50328824d..8ba9e1c12 100644 --- a/zh/built-in-nodes/LatentFlip.mdx +++ b/zh/built-in-nodes/LatentFlip.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentFlip" icon: "circle" mode: wide --- + ## 概述 LatentFlip 节点用于通过垂直或水平翻转来操控潜在表示。此操作可对潜在空间进行变换，从而在数据中发掘新的变体或视角。 diff --git a/zh/built-in-nodes/LatentFromBatch.mdx b/zh/built-in-nodes/LatentFromBatch.mdx index b56d67615..cf845ec98 100644 --- a/zh/built-in-nodes/LatentFromBatch.mdx +++ b/zh/built-in-nodes/LatentFromBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentFromBatch" icon: "circle" mode: wide --- + 此节点用于根据指定的批次索引和长度，从给定批次中提取特定的潜在样本子集。它允许对潜在样本进行选择性处理，便于对批次中的较小片段进行操作，以提高效率或实现针对性处理。 ## 输入 diff --git a/zh/built-in-nodes/LatentInterpolate.mdx b/zh/built-in-nodes/LatentInterpolate.mdx index 0a0768b73..7673f27c2 100644 --- a/zh/built-in-nodes/LatentInterpolate.mdx +++ b/zh/built-in-nodes/LatentInterpolate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentInterpolate" icon: "circle" mode: wide --- + LatentInterpolate 节点旨在根据指定比例对两组潜在样本进行插值，融合两组样本的特征，生成一组新的中间潜在样本。 ## 输入 diff --git a/zh/built-in-nodes/LatentMultiply.mdx b/zh/built-in-nodes/LatentMultiply.mdx index b80a6d899..7fd9c6620 100644 --- a/zh/built-in-nodes/LatentMultiply.mdx +++ b/zh/built-in-nodes/LatentMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentMultiply" icon: "circle" mode: wide --- + LatentMultiply 节点旨在通过指定的乘数缩放样本的潜在表示。此操作允许调整潜在空间内特征的强度或幅度，从而实现对生成内容的微调，或探索给定潜在方向上的变化。 ## 输入 diff --git a/zh/built-in-nodes/LatentOperationSharpen.mdx b/zh/built-in-nodes/LatentOperationSharpen.mdx index bcaaa0268..3a156345c 100644 --- a/zh/built-in-nodes/LatentOperationSharpen.mdx +++ b/zh/built-in-nodes/LatentOperationSharpen.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentOperationSharpen" icon: "circle" mode: wide --- + LatentOperationSharpen 节点使用高斯核对潜在表示应用锐化效果。其工作原理是对潜在数据进行归一化，使用自定义锐化核进行卷积，然后恢复原始亮度。这增强了潜在空间表示中的细节和边缘。 ## 输入 diff --git a/zh/built-in-nodes/LatentOperationTonemapReinhard.mdx b/zh/built-in-nodes/LatentOperationTonemapReinhard.mdx index e38c984ee..e5b887625 100644 --- a/zh/built-in-nodes/LatentOperationTonemapReinhard.mdx +++ b/zh/built-in-nodes/LatentOperationTonemapReinhard.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentOperationTonemapReinhard" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentOperationTonemapReinhard/en.md) LatentOperationTonemapReinhard 节点对潜在向量应用 Reinhard 色调映射。该技术通过基于均值和标准差的统计方法对潜在向量进行归一化并调整其幅度，其强度由乘数参数控制。 diff --git a/zh/built-in-nodes/LatentRotate.mdx b/zh/built-in-nodes/LatentRotate.mdx index 7698eb1da..6ede7a69b 100644 --- a/zh/built-in-nodes/LatentRotate.mdx +++ b/zh/built-in-nodes/LatentRotate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentRotate" icon: "circle" mode: wide --- + LatentRotate 节点旨在按指定角度旋转图像的潜在表示。它抽象了在潜在空间中实现旋转效果的复杂性，使用户能够轻松地在生成模型的潜在空间中变换图像。 ## 输入 diff --git a/zh/built-in-nodes/LatentSubtract.mdx b/zh/built-in-nodes/LatentSubtract.mdx index 6d679477b..faafc905d 100644 --- a/zh/built-in-nodes/LatentSubtract.mdx +++ b/zh/built-in-nodes/LatentSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentSubtract" icon: "circle" mode: wide --- + LatentSubtract 节点用于从一个潜在表示中减去另一个潜在表示。此操作可通过有效移除一个潜在空间中的特征或属性来操控或修改生成模型的输出特性。 ## 输入 diff --git a/zh/built-in-nodes/LatentUpscale.mdx b/zh/built-in-nodes/LatentUpscale.mdx index 122c973f4..e32a5da34 100644 --- a/zh/built-in-nodes/LatentUpscale.mdx +++ b/zh/built-in-nodes/LatentUpscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscale" icon: "circle" mode: wide --- + LatentUpscale 节点用于对图像的潜在表示进行放大。它允许调整输出图像的尺寸和放大方法，为提升潜在图像的分辨率提供了灵活性。 ## 输入 diff --git a/zh/built-in-nodes/LatentUpscaleBy.mdx b/zh/built-in-nodes/LatentUpscaleBy.mdx index 40abd1659..ae95b5f19 100644 --- a/zh/built-in-nodes/LatentUpscaleBy.mdx +++ b/zh/built-in-nodes/LatentUpscaleBy.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscaleBy" icon: "circle" mode: wide --- + LatentUpscaleBy 节点用于对图像的潜在表示进行放大。它允许调整缩放因子和放大方法，从而灵活提升潜在样本的分辨率。 ## 输入 diff --git a/zh/built-in-nodes/LatentUpscaleModelLoader.mdx b/zh/built-in-nodes/LatentUpscaleModelLoader.mdx index 3746039f3..5af14ca84 100644 --- a/zh/built-in-nodes/LatentUpscaleModelLoader.mdx +++ b/zh/built-in-nodes/LatentUpscaleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LatentUpscaleModelLoader" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LatentUpscaleModelLoader/en.md) LatentUpscaleModelLoader 节点用于加载专为放大潜在表示而设计的专用模型。它从系统指定文件夹中读取模型文件，并自动检测其类型（720p、1080p 或其他），以实例化并配置正确的内部模型架构。加载后的模型即可供其他节点用于潜在空间超分辨率任务。 diff --git a/zh/built-in-nodes/LazyCache.mdx b/zh/built-in-nodes/LazyCache.mdx index 7132b7930..b1fc879c3 100644 --- a/zh/built-in-nodes/LazyCache.mdx +++ b/zh/built-in-nodes/LazyCache.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LazyCache" icon: "circle" mode: wide --- + LazyCache 是 EasyCache 的自制版本，提供了更简单的实现方式。它可与 ComfyUI 中的任何模型配合使用，通过添加缓存功能来减少采样过程中的计算量。虽然其整体性能通常不如 EasyCache，但在某些罕见情况下可能更有效，并且具有通用兼容性。 ## 输入 diff --git a/zh/built-in-nodes/Load3D.mdx b/zh/built-in-nodes/Load3D.mdx index a3ce94326..00953ec34 100644 --- a/zh/built-in-nodes/Load3D.mdx +++ b/zh/built-in-nodes/Load3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Load3D" icon: "circle" mode: wide --- + 以下是您要求的 ComfyUI 节点文档的简体中文翻译： Load3D 节点是用于加载和处理 3D 模型文件的核心节点。加载节点时，它会自动从 `ComfyUI/input/3d/` 目录中检索可用的 3D 资源。您也可以使用上传功能上传支持的 3D 文件进行预览。 @@ -31,13 +32,13 @@ Load3D 节点是用于加载和处理 3D 模型文件的核心节点。加载节 | 参数名 | 描述 | 数据类型 | | --- | --- | --- | -| `mask` | 画布渲染图像 | IMAGE | -| `网格路径` | 包含当前模型位置的遮罩 | MASK | -| `法线` | 模型文件路径 | STRING | -| `相机信息` | 法线贴图 | IMAGE | -| `录制视频` | 线稿图像输出，对应的 `edge_threshold` 可在画布模型菜单中调整 | IMAGE | -| `model_3d` | 相机信息 | LOAD3D_CAMERA | -| `model_3d_info` | 录制的视频（仅在存在录制时） | VIDEO | +| `图像` | 画布渲染图像 | IMAGE | +| `mask` | 包含当前模型位置的遮罩 | MASK | +| `网格路径` | 模型文件路径 | STRING | +| `法线` | 法线贴图 | IMAGE | +| `相机信息` | 线稿图像输出，对应的 `edge_threshold` 可在画布模型菜单中调整 | IMAGE | +| `录制视频` | 相机信息 | LOAD3D_CAMERA | +| `model_3d` | 录制的视频（仅在存在录制时） | VIDEO | 所有输出预览： ![查看操作演示](/images/built-in-nodes/Load3D/load3d_outputs.webp) diff --git a/zh/built-in-nodes/Load3DAdvanced.mdx b/zh/built-in-nodes/Load3DAdvanced.mdx new file mode 100644 index 000000000..ec382df41 --- /dev/null +++ b/zh/built-in-nodes/Load3DAdvanced.mdx @@ -0,0 +1,38 @@ +--- +title: "Load3DAdvanced - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the Load3DAdvanced node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "Load3DAdvanced" +icon: "circle" +mode: wide +--- + +此节点从您的 ComfyUI 输入目录加载 3D 模型文件，并提供模型数据以及相机和视口信息。它支持常见的 3D 文件格式，并允许您指定渲染输出的图像尺寸。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `model_file` | 要加载的 3D 模型文件。选择 "none" 可跳过加载模型。 | STRING | 是 | `"none"`
input/3d 目录中可用的 3D 文件列表 | +| `viewport_state` | 当前视口状态，包含来自 3D 查看器的相机和模型信息。 | LOAD3D | 是 | - | +| `width` | 输出图像的宽度（像素），默认值：1024 | INT | 是 | 最小值：1
最大值：4096
步长：1 | +| `height` | 输出图像的高度（像素），默认值：1024 | INT | 是 | 最小值：1
最大值：4096
步长：1 | + +**参数说明：** +- `model_file` 参数仅显示以下扩展名的文件：.gltf、.glb、.obj、.fbx、.stl +- 文件必须放置在 ComfyUI 安装目录的 `input/3d` 文件夹中 +- 如果 `model_file` 设置为 "none"，则不会加载任何 3D 模型数据（输出 `model_3d` 将为空） + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `model_3d` | 已加载的 3D 模型数据，如果未选择模型文件则为空 | FILE3DANY | +| `model_3d_info` | 来自视口状态的已加载 3D 模型信息 | LOAD3DMODELINFO | +| `camera_info` | 来自视口状态的相机信息 | LOAD3DCAMERA | +| `width` | 指定的输出图像宽度 | INT | +| `height` | 指定的输出图像高度 | INT | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Load3DAdvanced/zh.md) + +--- +**Source fingerprint (SHA-256):** `fdacea8abf627621150e1196743e36f61534333837c33cc9a7416a6d11700c4d` diff --git a/zh/built-in-nodes/Load3DAnimation.mdx b/zh/built-in-nodes/Load3DAnimation.mdx index d996a4705..4f66f6c66 100644 --- a/zh/built-in-nodes/Load3DAnimation.mdx +++ b/zh/built-in-nodes/Load3DAnimation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Load3DAnimation" icon: "circle" mode: wide --- + ```markdown # Load3DAnimation 节点文档 diff --git a/zh/built-in-nodes/LoadAudio.mdx b/zh/built-in-nodes/LoadAudio.mdx index 431827998..1e7b41427 100644 --- a/zh/built-in-nodes/LoadAudio.mdx +++ b/zh/built-in-nodes/LoadAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadAudio" icon: "circle" mode: wide --- + LoadAudio 节点从输入目录加载音频文件，并将其转换为 ComfyUI 中其他音频节点可处理的格式。它会读取音频文件，提取波形数据和采样率，供下游音频处理任务使用。 ## 输入 diff --git a/zh/built-in-nodes/LoadBackgroundRemovalModel.mdx b/zh/built-in-nodes/LoadBackgroundRemovalModel.mdx index b6da1082a..60b6e29ff 100644 --- a/zh/built-in-nodes/LoadBackgroundRemovalModel.mdx +++ b/zh/built-in-nodes/LoadBackgroundRemovalModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadBackgroundRemovalModel" icon: "circle" mode: wide --- + ## 概述 从文件中加载背景移除模型。此节点准备模型，用于从图像中移除背景。 diff --git a/zh/built-in-nodes/LoadDA3Model.mdx b/zh/built-in-nodes/LoadDA3Model.mdx new file mode 100644 index 000000000..21c075a91 --- /dev/null +++ b/zh/built-in-nodes/LoadDA3Model.mdx @@ -0,0 +1,27 @@ +--- +title: "LoadDA3Model - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LoadDA3Model node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LoadDA3Model" +icon: "circle" +mode: wide +--- + +此节点从文件加载 Depth Anything 3 模型，为深度估计任务做好准备。它允许您选择模型文件，并可选择指定模型权重的数值精度（数据类型）。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `model_name` | 要加载的 Depth Anything 3 模型文件名。 | STRING | 是 | `geometry_estimation` 文件夹中可用的模型文件列表 | +| `weight_dtype` | 模型权重的数值精度（数据类型）。"default" 选项使用模型的原始精度。（默认值："default"） | STRING | 否 | `"default"`
`"fp16"`
`"bf16"`
`"fp32"` | + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `DA3_MODEL` | 加载后的 Depth Anything 3 模型，可用于深度估计工作流程。 | DA3_MODEL | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadDA3Model/zh.md) + +--- +**Source fingerprint (SHA-256):** `b1b3f4075cd9172bc1f274848b9300bca20d3cbd53b23d3c4a9f0986b36e409e` diff --git a/zh/built-in-nodes/LoadImage.mdx b/zh/built-in-nodes/LoadImage.mdx index b5911b2a5..7eaec8764 100644 --- a/zh/built-in-nodes/LoadImage.mdx +++ b/zh/built-in-nodes/LoadImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImage" icon: "circle" mode: wide --- + LoadImage 节点用于从指定路径加载并预处理图像。它处理包含多帧的图像格式，根据 EXIF 数据应用必要的变换（如旋转），归一化像素值，并可选择为包含 Alpha 通道的图像生成遮罩。该节点是准备图像以供后续处理或分析的关键组件。 ## 输入 diff --git a/zh/built-in-nodes/LoadImageDataSetFromFolder.mdx b/zh/built-in-nodes/LoadImageDataSetFromFolder.mdx index c0fd8bb34..7aee45a14 100644 --- a/zh/built-in-nodes/LoadImageDataSetFromFolder.mdx +++ b/zh/built-in-nodes/LoadImageDataSetFromFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageDataSetFromFolder" icon: "circle" mode: wide --- + 此节点从 ComfyUI 输入目录中的指定子文件夹加载多张图像。它会扫描所选文件夹中常见的图像文件类型，并将其作为列表返回，便于批量处理或数据集准备。 ## 输入 @@ -17,7 +18,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `images` | 已加载图像的列表。该节点会加载所选文件夹中找到的所有有效图像文件（PNG、JPG、JPEG、WEBP）。 | IMAGE | +| `图像` | 已加载图像的列表。该节点会加载所选文件夹中找到的所有有效图像文件（PNG、JPG、JPEG、WEBP）。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageDataSetFromFolder/zh.md) diff --git a/zh/built-in-nodes/LoadImageMask.mdx b/zh/built-in-nodes/LoadImageMask.mdx index 547526128..61ed2b0f5 100644 --- a/zh/built-in-nodes/LoadImageMask.mdx +++ b/zh/built-in-nodes/LoadImageMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageMask" icon: "circle" mode: wide --- + LoadImageMask 节点用于从指定路径加载图像及其关联的遮罩，并对其进行处理，以确保与后续图像处理或分析任务的兼容性。该节点专注于处理各种图像格式和条件（例如遮罩的 Alpha 通道是否存在），并通过将图像和遮罩转换为标准化格式，为下游处理做好准备。 ## 输入 diff --git a/zh/built-in-nodes/LoadImageOutput.mdx b/zh/built-in-nodes/LoadImageOutput.mdx index d11f273c9..2444ed2c8 100644 --- a/zh/built-in-nodes/LoadImageOutput.mdx +++ b/zh/built-in-nodes/LoadImageOutput.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageOutput" icon: "circle" mode: wide --- + LoadImageOutput 节点用于从输出文件夹加载图像。当您点击刷新按钮时，它会更新可用图像列表并自动选择第一张图像，方便您快速浏览生成的图像。 ## 输入 diff --git a/zh/built-in-nodes/LoadImageSetFromFolderNode.mdx b/zh/built-in-nodes/LoadImageSetFromFolderNode.mdx index 694148e5e..85aed115b 100644 --- a/zh/built-in-nodes/LoadImageSetFromFolderNode.mdx +++ b/zh/built-in-nodes/LoadImageSetFromFolderNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageSetFromFolderNode" icon: "circle" mode: wide --- + LoadImageSetFromFolderNode 从指定文件夹目录加载多张图像用于训练目的。它会自动检测常见图像格式，并可选地使用不同方法调整图像大小，然后以批次形式返回。 ## 输入 diff --git a/zh/built-in-nodes/LoadImageSetNode.mdx b/zh/built-in-nodes/LoadImageSetNode.mdx index 2be60bf02..729b76bc6 100644 --- a/zh/built-in-nodes/LoadImageSetNode.mdx +++ b/zh/built-in-nodes/LoadImageSetNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageSetNode" icon: "circle" mode: wide --- + LoadImageSetNode 从输入目录加载多张图像，用于批量处理与训练目的。它支持多种图像格式，并可通过不同方法对图像进行可选缩放。此节点将所有选定图像作为批次处理，并以单个张量形式返回。 ## 输入 diff --git a/zh/built-in-nodes/LoadImageTextDataSetFromFolder.mdx b/zh/built-in-nodes/LoadImageTextDataSetFromFolder.mdx index 25d6c400e..354e641f6 100644 --- a/zh/built-in-nodes/LoadImageTextDataSetFromFolder.mdx +++ b/zh/built-in-nodes/LoadImageTextDataSetFromFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageTextDataSetFromFolder" icon: "circle" mode: wide --- + 此节点从指定文件夹加载图像数据集及其对应的文本描述。它会搜索图像文件，并自动查找同名的 `.txt` 文件作为描述文本。该节点还支持特定的文件夹结构，其中子文件夹可以带有数字前缀（例如 `10_folder_name`），表示该文件夹中的图像在输出中应重复多次。 ## 输入 @@ -19,8 +20,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `文本` | 加载的图像张量列表。 | IMAGE | -| `texts` | 与每张加载图像对应的文本描述列表。 | STRING | +| `图像` | 加载的图像张量列表。 | IMAGE | +| `文本` | 与每张加载图像对应的文本描述列表。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadImageTextDataSetFromFolder/zh.md) diff --git a/zh/built-in-nodes/LoadImageTextSetFromFolderNode.mdx b/zh/built-in-nodes/LoadImageTextSetFromFolderNode.mdx index 042819a23..d97ee923d 100644 --- a/zh/built-in-nodes/LoadImageTextSetFromFolderNode.mdx +++ b/zh/built-in-nodes/LoadImageTextSetFromFolderNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadImageTextSetFromFolderNode" icon: "circle" mode: wide --- + 从指定目录加载一批图像及其对应的文本描述，用于训练目的。该节点会自动搜索图像文件及其关联的描述文本文件，根据指定的缩放设置处理图像，并使用提供的 CLIP 模型对描述进行编码。 ## 输入 diff --git a/zh/built-in-nodes/LoadLatent.mdx b/zh/built-in-nodes/LoadLatent.mdx index 955d95e66..3bf949f1d 100644 --- a/zh/built-in-nodes/LoadLatent.mdx +++ b/zh/built-in-nodes/LoadLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadLatent" icon: "circle" mode: wide --- + LoadLatent 节点用于从输入目录中的 .latent 文件加载先前保存的潜在表示。它会从文件中读取潜在张量数据，并应用必要的缩放调整，然后将潜在数据返回以供其他节点使用。 ## 输入 diff --git a/zh/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx b/zh/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx index 90c5fb8d4..64f0ce170 100644 --- a/zh/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx +++ b/zh/built-in-nodes/LoadMediaPipeFaceLandmarker.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadMediaPipeFaceLandmarker" icon: "circle" mode: wide --- + ## ## 概述 此节点加载一个 MediaPipe 面部特征点检测器 v2 模型，该模型可检测图像中的人脸及面部特征点（如眼睛、鼻子和嘴巴）。它包含两种检测变体（短距离和全距离），以及用于面部分析的共享网格数据、混合变形和标准几何体。 diff --git a/zh/built-in-nodes/LoadMoGeModel.mdx b/zh/built-in-nodes/LoadMoGeModel.mdx index b95bc59dd..b6f119ff1 100644 --- a/zh/built-in-nodes/LoadMoGeModel.mdx +++ b/zh/built-in-nodes/LoadMoGeModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadMoGeModel" icon: "circle" mode: wide --- + ## ## 概述 从文件加载 MoGe（单目几何）模型，并准备用于几何估计任务。此节点从 `geometry_estimation` 文件夹读取模型文件，并使用其训练权重初始化 MoGe 模型。 diff --git a/zh/built-in-nodes/LoadTrainingDataset.mdx b/zh/built-in-nodes/LoadTrainingDataset.mdx index 6605215b4..84c7d25b2 100644 --- a/zh/built-in-nodes/LoadTrainingDataset.mdx +++ b/zh/built-in-nodes/LoadTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadTrainingDataset" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadTrainingDataset/en.md) 此节点加载先前保存到磁盘的编码训练数据集。它会在 ComfyUI 输出目录中搜索并读取指定文件夹内的所有数据分片文件，然后返回合并后的潜在向量和条件数据，以供训练工作流使用。 @@ -19,8 +20,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `条件` | 潜在字典列表，每个字典包含一个键为 `"samples"` 的张量。 | LATENT | -| `conditioning` | 条件列表的列表，其中每个内部列表包含对应样本的条件数据。 | CONDITIONING | +| `Latent` | 潜在字典列表，每个字典包含一个键为 `"samples"` 的张量。 | LATENT | +| `条件` | 条件列表的列表，其中每个内部列表包含对应样本的条件数据。 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadTrainingDataset/zh.md) diff --git a/zh/built-in-nodes/LoadVideo.mdx b/zh/built-in-nodes/LoadVideo.mdx index c2608f77a..917c4c977 100644 --- a/zh/built-in-nodes/LoadVideo.mdx +++ b/zh/built-in-nodes/LoadVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoadVideo" icon: "circle" mode: wide --- + 加载视频节点用于从输入目录加载视频文件，使其可在工作流中处理。该节点从指定输入文件夹读取视频文件，并将其输出为可连接至其他视频处理节点的视频数据。 ## 输入 diff --git a/zh/built-in-nodes/LoraLoader.mdx b/zh/built-in-nodes/LoraLoader.mdx index ffd5d88ee..c0e05edc7 100644 --- a/zh/built-in-nodes/LoraLoader.mdx +++ b/zh/built-in-nodes/LoraLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoader" icon: "circle" mode: wide --- + 此节点会自动检测 LoRA 文件夹（包括子文件夹）中的模型，对应的模型路径为 `ComfyUI\models\loras`。更多信息请参考《安装 LoRA 模型》。 LoRA 加载器节点主要用于加载 LoRA 模型。你可以将 LoRA 模型视为滤镜，能够为图像赋予特定的风格、内容和细节： diff --git a/zh/built-in-nodes/LoraLoaderBypass.mdx b/zh/built-in-nodes/LoraLoaderBypass.mdx index 37900b37d..d752d9925 100644 --- a/zh/built-in-nodes/LoraLoaderBypass.mdx +++ b/zh/built-in-nodes/LoraLoaderBypass.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderBypass" icon: "circle" mode: wide --- + LoraLoaderBypass 节点以特殊的"旁路"模式将 LoRA（低秩适配）应用于扩散模型和 CLIP 模型。与标准 LoRA 加载器不同，此方法不会永久修改基础模型的权重。相反，它通过将 LoRA 的效果添加到模型的正常前向传播中来计算输出，这在训练或处理已卸载权重的模型时非常有用。 ## 输入 diff --git a/zh/built-in-nodes/LoraLoaderBypassModelOnly.mdx b/zh/built-in-nodes/LoraLoaderBypassModelOnly.mdx index 1645e8db0..0a121d460 100644 --- a/zh/built-in-nodes/LoraLoaderBypassModelOnly.mdx +++ b/zh/built-in-nodes/LoraLoaderBypassModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderBypassModelOnly" icon: "circle" mode: wide --- + 此节点对模型应用 LoRA（低秩适配）以修改其行为，但仅影响模型组件本身。它会加载指定的 LoRA 文件，并按给定强度调整模型权重，而 CLIP 文本编码器等其他组件保持不变。 ## 输入 diff --git a/zh/built-in-nodes/LoraLoaderModelOnly.mdx b/zh/built-in-nodes/LoraLoaderModelOnly.mdx index 9b474c5f6..d68a3c839 100644 --- a/zh/built-in-nodes/LoraLoaderModelOnly.mdx +++ b/zh/built-in-nodes/LoraLoaderModelOnly.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraLoaderModelOnly" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/loras` 文件夹中的模型，同时也会读取在 extra_model_paths.yaml 文件中配置的其他路径中的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够从相应文件夹中读取模型文件。 该节点专门用于加载无需 CLIP 模型的 LoRA 模型，专注于根据 LoRA 参数增强或修改给定的模型。它允许通过 LoRA 参数动态调整模型的强度，从而实现对模型行为的精细控制。 diff --git a/zh/built-in-nodes/LoraModelLoader.mdx b/zh/built-in-nodes/LoraModelLoader.mdx index 3c2688ad4..e31b87efb 100644 --- a/zh/built-in-nodes/LoraModelLoader.mdx +++ b/zh/built-in-nodes/LoraModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LoraModelLoader" icon: "circle" mode: wide --- + LoraModelLoader 节点将训练好的 LoRA（低秩适配）权重应用于扩散模型。它通过加载训练好的 LoRA 模型中的 LoRA 权重并调整其影响强度来修改基础模型。这使得您能够自定义扩散模型的行为，而无需从头重新训练。 ## 输入 diff --git a/zh/built-in-nodes/LoraSave.mdx b/zh/built-in-nodes/LoraSave.mdx index 1cbc9c02c..67b5b6e8c 100644 --- a/zh/built-in-nodes/LoraSave.mdx +++ b/zh/built-in-nodes/LoraSave.mdx @@ -5,7 +5,6 @@ sidebarTitle: "LoraSave" icon: "circle" mode: wide --- -# 概述 LoraSave 节点可从模型差异中提取并保存 LoRA（低秩适应）文件。它可以处理扩散模型差异、文本编码器差异或两者同时处理，将其转换为指定秩和类型的 LoRA 格式。生成的 LoRA 文件将保存到输出目录中供后续使用。 diff --git a/zh/built-in-nodes/LossGraphNode.mdx b/zh/built-in-nodes/LossGraphNode.mdx index b48e0f98b..a2a87592f 100644 --- a/zh/built-in-nodes/LossGraphNode.mdx +++ b/zh/built-in-nodes/LossGraphNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LossGraphNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LossGraphNode/en.md) LossGraphNode 会创建训练损失值随时间变化的可视化图表，并将其显示为预览图像。它从训练过程中获取损失数据，生成折线图，展示损失值随训练步骤的变化趋势。生成的图表包含坐标轴标签以及最小/最大损失值。 diff --git a/zh/built-in-nodes/LotusConditioning.mdx b/zh/built-in-nodes/LotusConditioning.mdx index 881e0e9b7..7c0a57116 100644 --- a/zh/built-in-nodes/LotusConditioning.mdx +++ b/zh/built-in-nodes/LotusConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LotusConditioning" icon: "circle" mode: wide --- + LotusConditioning 节点为 Lotus 模型提供预计算的条件嵌入。它使用带有空条件（null conditioning）的冻结编码器，并返回硬编码的提示嵌入，以实现与参考实现的一致性，无需推理或加载大型张量文件。该节点输出一个固定的条件张量，可直接用于生成流程。 ## 输入 @@ -17,7 +18,7 @@ LotusConditioning 节点为 Lotus 模型提供预计算的条件嵌入。它使 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `conditioning` | Lotus 模型的预计算条件嵌入，包含固定的提示嵌入和一个空字典。 | CONDITIONING | +| `条件` | Lotus 模型的预计算条件嵌入，包含固定的提示嵌入和一个空字典。 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LotusConditioning/zh.md) diff --git a/zh/built-in-nodes/LtxvApiImageToVideo.mdx b/zh/built-in-nodes/LtxvApiImageToVideo.mdx index c4c88ac7c..4c6310424 100644 --- a/zh/built-in-nodes/LtxvApiImageToVideo.mdx +++ b/zh/built-in-nodes/LtxvApiImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LtxvApiImageToVideo" icon: "circle" mode: wide --- + ## 概述 LTXV 图像转视频节点可从单张起始图像生成专业品质的视频。它使用外部 API，根据您的文本提示创建视频序列，让您能够自定义时长、分辨率和帧率。 diff --git a/zh/built-in-nodes/LtxvApiTextToVideo.mdx b/zh/built-in-nodes/LtxvApiTextToVideo.mdx index 0413fad83..3d549a328 100644 --- a/zh/built-in-nodes/LtxvApiTextToVideo.mdx +++ b/zh/built-in-nodes/LtxvApiTextToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LtxvApiTextToVideo" icon: "circle" mode: wide --- + LTXV 文本转视频节点可根据文本描述生成专业质量的视频。它通过连接外部 API 创建视频，支持自定义时长、分辨率和帧率。您还可以选择为视频添加 AI 生成的音频。 ## 输入 diff --git a/zh/built-in-nodes/LumaConceptsNode.mdx b/zh/built-in-nodes/LumaConceptsNode.mdx index 97d88376b..0517a9c51 100644 --- a/zh/built-in-nodes/LumaConceptsNode.mdx +++ b/zh/built-in-nodes/LumaConceptsNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaConceptsNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaConceptsNode/en.md) 保存一个或多个相机概念，用于 Luma 文本转视频和 Luma 图像转视频节点。此节点允许您选择最多四个相机概念，并可选择将其与现有概念链组合。 diff --git a/zh/built-in-nodes/LumaImageEditNode2.mdx b/zh/built-in-nodes/LumaImageEditNode2.mdx index 6cb62eb38..c10318995 100644 --- a/zh/built-in-nodes/LumaImageEditNode2.mdx +++ b/zh/built-in-nodes/LumaImageEditNode2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageEditNode2" icon: "circle" mode: wide --- + ## 概述 此节点使用文本提示对现有图像进行编辑，由 Luma UNI-1 模型驱动。它接收源图像和所需更改的描述，然后生成编辑后的新版本图像。 diff --git a/zh/built-in-nodes/LumaImageModifyNode.mdx b/zh/built-in-nodes/LumaImageModifyNode.mdx index c552497bc..be400fc09 100644 --- a/zh/built-in-nodes/LumaImageModifyNode.mdx +++ b/zh/built-in-nodes/LumaImageModifyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageModifyNode" icon: "circle" mode: wide --- + 根据文本提示和原始图像的宽高比同步修改图像。此节点接收输入图像，并根据提供的提示对其进行变换，使用可配置的图像权重来控制原始图像的修改程度。 ## 输入 diff --git a/zh/built-in-nodes/LumaImageNode.mdx b/zh/built-in-nodes/LumaImageNode.mdx index f47af8b16..6633a2a0b 100644 --- a/zh/built-in-nodes/LumaImageNode.mdx +++ b/zh/built-in-nodes/LumaImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaImageNode/en.md) 根据文本提示和宽高比同步生成图像。此节点使用文本描述创建图像，并允许您通过多种参考输入（包括角色图像和风格图像）控制图像尺寸和风格。 diff --git a/zh/built-in-nodes/LumaImageNode2.mdx b/zh/built-in-nodes/LumaImageNode2.mdx index 55c91e87f..d8f40f17d 100644 --- a/zh/built-in-nodes/LumaImageNode2.mdx +++ b/zh/built-in-nodes/LumaImageNode2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageNode2" icon: "circle" mode: wide --- + ## 概述 此节点使用 Luma UNI-1 模型根据文本描述生成图像。它接收文本提示以及宽高比和风格等可选设置，然后将请求发送至 Luma API 以创建图像。 diff --git a/zh/built-in-nodes/LumaImageToVideoNode.mdx b/zh/built-in-nodes/LumaImageToVideoNode.mdx index 48adb3648..34bb8e7a5 100644 --- a/zh/built-in-nodes/LumaImageToVideoNode.mdx +++ b/zh/built-in-nodes/LumaImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaImageToVideoNode" icon: "circle" mode: wide --- + 根据文本提示和可选的起始/结束图像同步生成视频。此节点使用 Luma API 创建视频，允许您通过提示定义视频内容，并可选择指定首帧和/或末帧来控制视频结构。 ## 输入 diff --git a/zh/built-in-nodes/LumaRay32ExtendVideoNode.mdx b/zh/built-in-nodes/LumaRay32ExtendVideoNode.mdx new file mode 100644 index 000000000..0844cf9bc --- /dev/null +++ b/zh/built-in-nodes/LumaRay32ExtendVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32ExtendVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32ExtendVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32ExtendVideoNode" +icon: "circle" +mode: wide +--- + +此节点通过在前一个 Luma Ray 3.2 视频生成结果之后（正向扩展）或之前（反向扩展）添加新内容来扩展视频。连接先前 Luma Ray 3.2 节点的生成 ID 输出，即可创建无缝衔接的 5 秒视频扩展。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 取值范围 | +|------|------|----------|----------|----------| +| `source_generation_id` | 待扩展的先前 Ray 3.2 视频的生成 ID。连接另一个 Luma Ray 3.2 节点的 generation_id 输出。 | STRING | 是 | - | +| `direction` | 正向表示在先前片段之后继续；反向表示在先前片段之前添加。选择"正向（之后继续）"时，可选择启用循环模式。 | COMBO | 是 | "正向（之后继续）"
"反向（之前插入）" | +| `loop` | 使扩展后的视频无缝循环（仅限正向扩展）。 | BOOLEAN | 否 | True
False | +| `prompt` | 描述要生成的新内容的文本提示。 | STRING | 是 | - | +| `resolution` | 扩展视频片段的输出分辨率。 | COMBO | 是 | "540p"
"720p"
"1080p" | +| `seed` | 用于可重复生成结果的随机种子。 | INT | 是 | - | + +**注意：** `loop` 参数仅在 `direction` 设置为"正向（之后继续）"时可用。使用"反向（之前插入）"时，循环选项不可用。`prompt` 的长度必须在 1 到 6000 个字符之间。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|----------|------|----------| +| `VIDEO` | 生成的 5 秒扩展视频片段。 | VIDEO | +| `generation_id` | 本次生成的唯一标识符，可连接到另一个 Luma Ray 3.2 扩展视频节点以进行进一步扩展。 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32ExtendVideoNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `a67ca53d4bcb9f3fd82bc0482b579f5f7fe4bf866f8d83cb922e1082ad320057` diff --git a/zh/built-in-nodes/LumaRay32ImageToVideoNode.mdx b/zh/built-in-nodes/LumaRay32ImageToVideoNode.mdx new file mode 100644 index 000000000..b175921de --- /dev/null +++ b/zh/built-in-nodes/LumaRay32ImageToVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32ImageToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32ImageToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32ImageToVideoNode" +icon: "circle" +mode: wide +--- + +使用 Luma 的 Ray 3.2 模型，根据起始帧和/或结束帧生成视频。基于图像锚定的生成时长固定为 5 秒。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `prompt` | 视频生成的文本提示词。 | STRING | 是 | 1 至 6000 个字符 | +| `resolution` | 生成视频的输出分辨率（默认值："720p"）。 | COMBO | 是 | "360p"
"540p"
"720p"
"1080p" | +| `循环` | 使视频无缝循环播放。当设置了结束帧时不可用。 | BOOLEAN | 是 | True
False | +| `seed` | 用于可重复生成的随机种子值。 | INT | 是 | 0 至 2147483647 | +| `start_frame` | 生成视频的第一帧。 | IMAGE | 否 | - | +| `end_frame` | 生成视频的最后一帧。 | IMAGE | 否 | - | + +**注意：** 必须至少提供 `start_frame` 或 `end_frame` 中的一个。如果同时提供了两者，生成的视频将从起始帧过渡到结束帧。当设置了 `end_frame` 时，无法启用 `loop` 选项。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `video` | 生成的视频输出。 | VIDEO | +| `generation_id` | 生成请求的唯一标识符。 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32ImageToVideoNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `ff479c196f10153ffa09af6acfb4e286d1934aa28a5e9b413613097a2cfb5f2a` diff --git a/zh/built-in-nodes/LumaRay32KeyframeNode.mdx b/zh/built-in-nodes/LumaRay32KeyframeNode.mdx new file mode 100644 index 000000000..54bf0b303 --- /dev/null +++ b/zh/built-in-nodes/LumaRay32KeyframeNode.mdx @@ -0,0 +1,32 @@ +--- +title: "LumaRay32KeyframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32KeyframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32KeyframeNode" +icon: "circle" +mode: wide +--- + +此节点将引导图像锚定到 Luma Ray 3.2 输出视频时间轴上的特定位置。将此节点连接到 Luma Ray 3.2 关键帧转视频节点的"keyframes"输入，并通过连接可选的"keyframes"输入将多个关键帧串联在一起。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `image` | 放置在输出视频选定时刻的引导图像。 | IMAGE | 是 | - | +| `position` | 将此图像放置在输出视频时间轴上的方式。 | COMBO | 是 | "Fraction of duration (0.0-1.0)"
"Absolute time (seconds)" | +| `keyframes` | 可选的前置关键帧，用于与此关键帧串联。 | LUMA_RAY32_KEYFRAME | 否 | - | + +当为`position`参数选择"Fraction of duration (0.0-1.0)"时，您可以指定一个`fraction`值（默认值：0.0，范围：0.0 至 1.0，步长：0.01），该值决定此图像在输出视频中的应用位置（0.0 = 开始，1.0 = 结束）。 + +当为`position`参数选择"Absolute time (seconds)"时，您可以指定一个`seconds`值（默认值：0.0，范围：0.0 至 10.0，步长：0.1），该值决定此图像在输出视频中从开始算起的时间（以秒为单位）。 + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `keyframes` | 包含新关键帧与任何可选前置关键帧组合的关键帧链。 | LUMA_RAY32_KEYFRAME | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32KeyframeNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `b49d879888e6e83d6937068e799ea583ed5c90284e829ac496821eea330fe9c7` diff --git a/zh/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx b/zh/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx new file mode 100644 index 000000000..5c3bf0fa7 --- /dev/null +++ b/zh/built-in-nodes/LumaRay32KeyframesToVideoNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32KeyframesToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32KeyframesToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32KeyframesToVideoNode" +icon: "circle" +mode: wide +--- + +此节点使用 Luma Ray 3.2 生成一段视频，该视频在引导图像序列之间进行插值，每张图像锚定在时间轴上的特定位置。请使用 Luma Ray 3.2 关键帧节点构建关键帧序列，并连接至少 2 个关键帧以定义动画。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 取值范围 | +|-----------|-------------|-----------|----------|-------| +| `提示词` | 视频生成的文本提示。 | STRING | 是 | 1 到 6000 个字符 | +| `分辨率` | 生成视频的输出分辨率（默认值："720p"）。 | COMBO | 是 | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `时长` | 生成视频的时长（默认值："5s"）。 | COMBO | 是 | `"5s"`
`"10s"` | +| `种子` | 用于控制可复现性的随机数生成种子。 | INT | 是 | 0 到 4294967295 | +| `关键帧` | 来自 Luma Ray 3.2 关键帧节点的关键帧序列（至少 2 个）。 | LUMA_RAY32_KEYFRAME | 是 | 2 到 64 个关键帧 | + +**注意：** 关键帧序列必须包含至少 2 个关键帧，且最多 64 个关键帧。每个关键帧在时间轴上必须具有不同的位置。关键帧位置将根据所选时长（5 秒对应 120 帧，10 秒对应 240 帧）解析为输出帧索引。秒模式下的关键帧位置不得超过视频总时长。 + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `generation_id` | 生成的视频输出。 | VIDEO | +| `generation_id` | 生成请求的唯一标识符。 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32KeyframesToVideoNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `28099e5990942860a20e23cfd5c71a36b23a6264b44097ca617f8bdd06e7857a` diff --git a/zh/built-in-nodes/LumaRay32TextToVideoNode.mdx b/zh/built-in-nodes/LumaRay32TextToVideoNode.mdx new file mode 100644 index 000000000..c72014ea8 --- /dev/null +++ b/zh/built-in-nodes/LumaRay32TextToVideoNode.mdx @@ -0,0 +1,34 @@ +--- +title: "LumaRay32TextToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32TextToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32TextToVideoNode" +icon: "circle" +mode: wide +--- + +此节点使用 Luma 的 Ray 3.2 模型，根据文本提示生成视频。它会将您的提示和视频设置发送至 Luma API，并返回生成的视频及其生成 ID。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 取值范围 | +|-----------|-------------|-----------|----------|-------| +| `提示词` | 用于视频生成的文本提示。 | STRING | 是 | 1-6000 个字符 | +| `宽高比` | 生成视频的宽高比。 | STRING | 是 | `"16:9"`
`"9:16"`
`"1:1"`
`"4:3"`
`"3:4"`
`"21:9"` | +| `分辨率` | 视频的输出分辨率（默认值："720p"）。 | STRING | 是 | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `时长` | 生成视频的时长。 | STRING | 是 | `"5s"`
`"10s"` | +| `循环` | 使视频无缝循环播放。仅当时长为 5s 时可用。 | BOOLEAN | 否 | True/False（默认值：False） | +| `种子` | 用于可复现生成的随机种子。 | INT | 否 | 0 至 2147483647 | + +**注意：** `loop` 参数仅在 `duration` 设置为 "5s" 时可用。若选择 "10s" 时长并启用循环，节点将返回错误。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `VIDEO` | 生成的视频文件。 | VIDEO | +| `generation_id` | 视频生成请求的唯一标识符。 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32TextToVideoNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `04358a872530e5a2622bf0f148a694f2c707ce8535586d8f860bdf9911e1fa6a` diff --git a/zh/built-in-nodes/LumaRay32VideoEditNode.mdx b/zh/built-in-nodes/LumaRay32VideoEditNode.mdx new file mode 100644 index 000000000..b77afcb1d --- /dev/null +++ b/zh/built-in-nodes/LumaRay32VideoEditNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32VideoEditNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32VideoEditNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32VideoEditNode" +icon: "circle" +mode: wide +--- + +此节点使用 Luma Ray 3.2 根据新提示重新渲染现有视频，允许您在保持原始运动的同时重新设计风格、重新打光、添加或移除元素。源视频最长可达 18 秒，编辑后的视频保留源视频的原始长度。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 取值范围 | +|-----------|-------------|-----------|----------|-------| +| `视频` | 要编辑的源视频，最长 18 秒。 | VIDEO | 是 | - | +| `提示词` | 描述所需的编辑效果。 | STRING | 是 | - | +| `分辨率` | 编辑后视频的输出分辨率。 | COMBO | 是 | `"360p"`
`"540p"`
`"720p"`
`"1080p"` | +| `强度` | 保留源内容与重新想象源内容之间的强度。"auto" 让 Ray 3.2 自动选择；adhere_* 最大程度保留原内容，flex_* 较为平衡，reimagine_* 变化最大。（默认值："auto"） | COMBO | 是 | `"auto"`
`"adhere_1"`
`"adhere_2"`
`"adhere_3"`
`"flex_1"`
`"flex_2"`
`"flex_3"`
`"reimagine_1"`
`"reimagine_2"`
`"reimagine_3"` | +| `种子` | 用于结果可复现的随机种子。 | INT | 是 | - | + +**注意：** `prompt` 的长度必须在 1 到 6000 个字符之间。源视频的时长不得超过 18 秒。 + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `generation_id` | 编辑后的视频输出。 | VIDEO | +| `generation_id` | 生成请求的唯一标识符。 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32VideoEditNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `936d9d7da3fdee9b0b468781fd470751db01f772f3c5c20582da7fb1ff85e6e6` diff --git a/zh/built-in-nodes/LumaRay32VideoReframeNode.mdx b/zh/built-in-nodes/LumaRay32VideoReframeNode.mdx new file mode 100644 index 000000000..d88f20e1b --- /dev/null +++ b/zh/built-in-nodes/LumaRay32VideoReframeNode.mdx @@ -0,0 +1,33 @@ +--- +title: "LumaRay32VideoReframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the LumaRay32VideoReframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "LumaRay32VideoReframeNode" +icon: "circle" +mode: wide +--- + +此节点使用 Luma Ray 3.2 更改现有视频的宽高比，通过生成内容填充新暴露的画布区域。源视频最长可达 30 秒，计费按输出视频的每秒时长计算。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `video` | 需要重新构图的源视频，最长 30 秒。 | VIDEO | 是 | - | +| `prompt` | 描述新暴露的画布区域应如何填充。 | STRING | 是 | - | +| `aspect_ratio` | 重新构图后的目标宽高比（默认值："16:9"）。 | STRING | 是 | "16:9"
"9:16"
"1:1"
"4:3"
"3:4"
"21:9" | +| `resolution` | 重新构图后的输出分辨率（默认值："720p"）。 | STRING | 是 | "360p"
"540p"
"720p"
"1080p" | +| `seed` | 用于可复现生成的随机种子。 | INT | 是 | - | + +**注意：** 重新构图时，垂直宽高比（`9:16` 和 `3:4`）不支持 `1080p` 分辨率。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `video` | 具有新宽高比且画布区域已填充的重新构图视频。 | VIDEO | +| `generation_id` | 生成请求的唯一标识符。 | STRING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LumaRay32VideoReframeNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `d35ff5b63a850e4e44a40857188918ab5cde00b9159e3720a189a81807cfa7cb` diff --git a/zh/built-in-nodes/LumaReferenceNode.mdx b/zh/built-in-nodes/LumaReferenceNode.mdx index 626322b36..d55ab9d2d 100644 --- a/zh/built-in-nodes/LumaReferenceNode.mdx +++ b/zh/built-in-nodes/LumaReferenceNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaReferenceNode" icon: "circle" mode: wide --- + 此节点用于保存图像及其权重值，供 Luma 生成图像节点使用。它会创建一个参考链，可传递给其他 Luma 节点以影响图像生成。该节点可以启动新的参考链，也可以将内容添加到现有参考链中。 ## 输入 diff --git a/zh/built-in-nodes/LumaVideoNode.mdx b/zh/built-in-nodes/LumaVideoNode.mdx index f3b7041b5..57d081a27 100644 --- a/zh/built-in-nodes/LumaVideoNode.mdx +++ b/zh/built-in-nodes/LumaVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "LumaVideoNode" icon: "circle" mode: wide --- + 根据文本提示和输出设置同步生成视频。此节点使用文本描述和各种生成参数创建视频内容，并在生成过程完成后输出最终视频。 ## 输入 diff --git a/zh/built-in-nodes/MagnificImageRelightNode.mdx b/zh/built-in-nodes/MagnificImageRelightNode.mdx index b57d08ec5..fa7cb783b 100644 --- a/zh/built-in-nodes/MagnificImageRelightNode.mdx +++ b/zh/built-in-nodes/MagnificImageRelightNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MagnificImageRelightNode" icon: "circle" mode: wide --- -# Magnific Image Relight 节点 Magnific Image Relight 节点用于调整输入图像的照明效果。它可以根据文本提示应用风格化照明，或从可选的参考图像中迁移照明特征。该节点提供多种控制选项，用于微调最终输出的亮度、对比度和整体氛围。 diff --git a/zh/built-in-nodes/MagnificImageSkinEnhancerNode.mdx b/zh/built-in-nodes/MagnificImageSkinEnhancerNode.mdx index 9372f47b4..da8d22de1 100644 --- a/zh/built-in-nodes/MagnificImageSkinEnhancerNode.mdx +++ b/zh/built-in-nodes/MagnificImageSkinEnhancerNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageSkinEnhancerNode" icon: "circle" mode: wide --- + Magnific 图像皮肤增强节点对肖像图像应用专门的 AI 处理，以改善皮肤外观。它提供三种不同的模式以实现不同的增强目标：创意模式用于艺术效果，忠实模式用于保留原始外观，灵活模式用于针对性的改进（如光照或真实感）。该节点将图像上传到外部 API 进行处理，并返回增强后的结果。 ## 输入 diff --git a/zh/built-in-nodes/MagnificImageStyleTransferNode.mdx b/zh/built-in-nodes/MagnificImageStyleTransferNode.mdx index 662f64a8d..5a333c33a 100644 --- a/zh/built-in-nodes/MagnificImageStyleTransferNode.mdx +++ b/zh/built-in-nodes/MagnificImageStyleTransferNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageStyleTransferNode" icon: "circle" mode: wide --- + 此节点将参考图像的视觉风格应用于您的输入图像。它使用外部 AI 服务处理图像，让您能够控制风格迁移的强度以及原始图像结构的保留程度。 ## 输入 diff --git a/zh/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx b/zh/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx index bc76213c3..c54005127 100644 --- a/zh/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx +++ b/zh/built-in-nodes/MagnificImageUpscalerCreativeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageUpscalerCreativeNode" icon: "circle" mode: wide --- + 此节点使用 Magnific AI 服务对图像进行放大和创意增强。它允许您通过文本提示引导增强过程，选择特定风格进行优化，并控制创意过程中的各个方面，如细节、与原图的相似度以及风格化强度。该节点以您选择的倍数（2x、4x、8x 或 16x）输出放大后的图像，最大输出尺寸为 25.3 百万像素。 ## 输入 diff --git a/zh/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx b/zh/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx index 80655bf23..66497dc1f 100644 --- a/zh/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx +++ b/zh/built-in-nodes/MagnificImageUpscalerPreciseV2Node.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MagnificImageUpscalerPreciseV2Node" icon: "circle" mode: wide --- + Magnific 图像放大（精确 V2）节点可执行高保真图像放大，并精确控制锐度、颗粒感和细节增强。它通过外部 API 处理图像，支持最高 10060×10060 像素的输出分辨率。该节点提供不同的处理风格，如果请求的输出尺寸超过最大允许值，可自动对输入图像进行降采样。 ## 输入 diff --git a/zh/built-in-nodes/Mahiro.mdx b/zh/built-in-nodes/Mahiro.mdx index fcbcaa1f3..aec690a4b 100644 --- a/zh/built-in-nodes/Mahiro.mdx +++ b/zh/built-in-nodes/Mahiro.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Mahiro" icon: "circle" mode: wide --- + Mahiro 节点修改了引导函数，使其更侧重于正向提示的方向，而非正向与负向提示之间的差异。该节点创建了一个修补后的模型，通过计算归一化条件与非条件去噪输出之间的余弦相似度，应用自定义引导缩放方法。此实验性节点有助于更强烈地将生成结果导向正向提示的预期方向。 ## 输入 @@ -17,7 +18,7 @@ Mahiro 节点修改了引导函数，使其更侧重于正向提示的方向， | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `patched_model` | 应用了 Mahiro 引导函数的修改后模型 | MODEL | +| `修补后的模型` | 应用了 Mahiro 引导函数的修改后模型 | MODEL | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Mahiro/zh.md) diff --git a/zh/built-in-nodes/MakeTrainingDataset.mdx b/zh/built-in-nodes/MakeTrainingDataset.mdx index 85937b3d8..b4aeb6f73 100644 --- a/zh/built-in-nodes/MakeTrainingDataset.mdx +++ b/zh/built-in-nodes/MakeTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MakeTrainingDataset" icon: "circle" mode: wide --- + 此节点通过编码图像和文本来准备训练数据。它接收图像列表及对应的文本描述列表，然后使用 VAE 模型将图像转换为潜在表示，并使用 CLIP 模型将文本转换为条件数据。生成的成对潜在表示和条件数据以列表形式输出，可直接用于训练流程。 ## 输入 @@ -24,8 +25,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `条件` | 潜在字典列表。 | LATENT | -| `conditioning` | 条件列表的列表。 | CONDITIONING | +| `Latent` | 潜在字典列表。 | LATENT | +| `条件` | 条件列表的列表。 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MakeTrainingDataset/zh.md) diff --git a/zh/built-in-nodes/ManualSigmas.mdx b/zh/built-in-nodes/ManualSigmas.mdx index b52a8e8d2..d553b1758 100644 --- a/zh/built-in-nodes/ManualSigmas.mdx +++ b/zh/built-in-nodes/ManualSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ManualSigmas" icon: "circle" mode: wide --- + ManualSigmas 节点允许您手动定义采样过程中使用的自定义噪声水平序列（sigmas）。您以字符串形式输入一组数字，节点会将其转换为可供其他采样节点使用的张量。这对于测试或创建特定的噪声调度非常有用。 ## 输入 diff --git a/zh/built-in-nodes/MarkdownNote.mdx b/zh/built-in-nodes/MarkdownNote.mdx index 2a39d0acb..bf4502ad2 100644 --- a/zh/built-in-nodes/MarkdownNote.mdx +++ b/zh/built-in-nodes/MarkdownNote.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MarkdownNote" icon: "circle" mode: wide --- + 节点用于向工作流添加注释。它支持使用 Markdown 语法进行文本格式化。 ## 输入 diff --git a/zh/built-in-nodes/MaskComposite.mdx b/zh/built-in-nodes/MaskComposite.mdx index ba3264201..0b2486305 100644 --- a/zh/built-in-nodes/MaskComposite.mdx +++ b/zh/built-in-nodes/MaskComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskComposite" icon: "circle" mode: wide --- + 此节点专门用于通过加法、减法及逻辑运算等多种操作，将两个遮罩输入合并，生成新的修改后遮罩。它抽象地处理遮罩数据的操作，以实现复杂的遮罩效果，是基于遮罩的图像编辑与处理工作流程中的关键组件。 ## 输入 diff --git a/zh/built-in-nodes/MaskPreview.mdx b/zh/built-in-nodes/MaskPreview.mdx index 2a44c9f18..04e045fb9 100644 --- a/zh/built-in-nodes/MaskPreview.mdx +++ b/zh/built-in-nodes/MaskPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskPreview" icon: "circle" mode: wide --- + MaskPreview 节点可将蒙版数据作为预览图像保存到 ComfyUI 输出目录，方便您在工作流执行期间直观检查蒙版数据。该节点会将输入蒙版转换为适合图像显示的格式，并使用可配置的文件名前缀进行保存。 ## 输入 diff --git a/zh/built-in-nodes/MaskToImage.mdx b/zh/built-in-nodes/MaskToImage.mdx index 46e26881b..dee0cc764 100644 --- a/zh/built-in-nodes/MaskToImage.mdx +++ b/zh/built-in-nodes/MaskToImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MaskToImage" icon: "circle" mode: wide --- + `MaskToImage` 节点旨在将遮罩转换为图像格式。此转换允许将遮罩可视化为图像并进行进一步处理，从而在基于遮罩的操作与基于图像的应用之间建立桥梁。 ## 输入 diff --git a/zh/built-in-nodes/MediaPipeFaceLandmarker.mdx b/zh/built-in-nodes/MediaPipeFaceLandmarker.mdx index 1c58438eb..48fc0b190 100644 --- a/zh/built-in-nodes/MediaPipeFaceLandmarker.mdx +++ b/zh/built-in-nodes/MediaPipeFaceLandmarker.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceLandmarker" icon: "circle" mode: wide --- + ## 概述 使用 MediaPipe 的 BlazeFace 和 FaceMesh 模型检测图像中的人脸，并识别每张人脸上的 468 个面部特征点（关键点）。该节点还计算用于面部表情分析的 ARKit-52 混合变形系数。节点可批量处理多张图像，并输出每张检测到的人脸的特征点数据和边界框。 @@ -24,7 +25,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `bboxes` | 包含每帧人脸检测结果的结构化输出，包括 468 个面部特征点、ARKit-52 混合变形系数、变换矩阵以及用于网格可视化的连接集。 | FACE_LANDMARKS | +| `face_landmarks` | 包含每帧人脸检测结果的结构化输出，包括 468 个面部特征点、ARKit-52 混合变形系数、变换矩阵以及用于网格可视化的连接集。 | FACE_LANDMARKS | | `bboxes` | 每张检测到的人脸的边界框列表，包含坐标 (x, y, width, height)、标签 "face" 和置信度分数。每个输入帧对应一个列表。 | BOUNDING_BOX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MediaPipeFaceLandmarker/zh.md) diff --git a/zh/built-in-nodes/MediaPipeFaceMask.mdx b/zh/built-in-nodes/MediaPipeFaceMask.mdx index 08654a92a..392021feb 100644 --- a/zh/built-in-nodes/MediaPipeFaceMask.mdx +++ b/zh/built-in-nodes/MediaPipeFaceMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceMask" icon: "circle" mode: wide --- + ## ## 概述 此节点基于 MediaPipe 检测到的面部特征点创建二值掩码（黑白图像）。它会为每个检测到的面部区域绘制填充多边形，在批次中为每一帧生成一个掩码。当同一帧中检测到多张人脸时，这些掩码会被合并为单个掩码。 diff --git a/zh/built-in-nodes/MediaPipeFaceMeshVisualize.mdx b/zh/built-in-nodes/MediaPipeFaceMeshVisualize.mdx index 35f376241..ef8afe440 100644 --- a/zh/built-in-nodes/MediaPipeFaceMeshVisualize.mdx +++ b/zh/built-in-nodes/MediaPipeFaceMeshVisualize.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MediaPipeFaceMeshVisualize" icon: "circle" mode: wide --- + ## 概述 在输入图像上绘制面部特征点及连接线（即面部网格）。此节点利用面部检测节点生成的特征点数据，将检测到的面部特征（如眼睛、鼻子、嘴巴和面部轮廓）可视化呈现。 diff --git a/zh/built-in-nodes/MergeImageLists.mdx b/zh/built-in-nodes/MergeImageLists.mdx index cb28f4594..728abc756 100644 --- a/zh/built-in-nodes/MergeImageLists.mdx +++ b/zh/built-in-nodes/MergeImageLists.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MergeImageLists" icon: "circle" mode: wide --- + 合并图像列表节点将多个独立的图像列表合并为一个连续的列表。其工作原理是获取每个已连接输入中的所有图像，并按照接收顺序将它们依次拼接在一起。这对于整理或批量处理来自不同来源的图像以进行后续处理非常有用。 ## 输入 diff --git a/zh/built-in-nodes/MergeSplat.mdx b/zh/built-in-nodes/MergeSplat.mdx index 12d0b4810..40baf4a4b 100644 --- a/zh/built-in-nodes/MergeSplat.mdx +++ b/zh/built-in-nodes/MergeSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MergeSplat" icon: "circle" mode: wide --- -# 合并高斯泼溅 合并高斯泼溅节点通过连接多个高斯泼溅模型的数据，将其合并为单个泼溅。这对于合并使用不同种子生成的同一潜变量的多个解码结果非常有用，可以在创建3D网格时增加表面密度并提高质量。 diff --git a/zh/built-in-nodes/MergeTextLists.mdx b/zh/built-in-nodes/MergeTextLists.mdx index cbbd189a9..aec6f0b7d 100644 --- a/zh/built-in-nodes/MergeTextLists.mdx +++ b/zh/built-in-nodes/MergeTextLists.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MergeTextLists" icon: "circle" mode: wide --- + 此节点将多个文本列表合并为一个组合列表。它设计用于接收列表形式的文本输入，并将其拼接在一起。节点会记录合并后列表中的文本总数。 ## 输入 diff --git a/zh/built-in-nodes/MeshyAnimateModelNode.mdx b/zh/built-in-nodes/MeshyAnimateModelNode.mdx index b906779a8..46f714cee 100644 --- a/zh/built-in-nodes/MeshyAnimateModelNode.mdx +++ b/zh/built-in-nodes/MeshyAnimateModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyAnimateModelNode" icon: "circle" mode: wide --- + 此节点对已通过 Meshy 服务绑定骨骼的 3D 角色模型应用特定动画。它接收先前绑定操作的任务 ID 和用于从动画库中选择所需动画的动作 ID。节点处理请求后，以 GLB 和 FBX 两种文件格式返回动画模型。 ## 输入 @@ -18,8 +19,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `GLB` | 动画模型的字符串标识符。此输出仅用于向后兼容。 | STRING | -| `FBX` | GLB 格式的动画 3D 模型文件。 | FILE3DGLB | +| `模型文件` | 动画模型的字符串标识符。此输出仅用于向后兼容。 | STRING | +| `GLB` | GLB 格式的动画 3D 模型文件。 | FILE3DGLB | | `FBX` | FBX 格式的动画 3D 模型文件。 | FILE3DFBX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyAnimateModelNode/zh.md) diff --git a/zh/built-in-nodes/MeshyImageToModelNode.mdx b/zh/built-in-nodes/MeshyImageToModelNode.mdx index 7450d6af9..486011b96 100644 --- a/zh/built-in-nodes/MeshyImageToModelNode.mdx +++ b/zh/built-in-nodes/MeshyImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyImageToModelNode" icon: "circle" mode: wide --- + Meshy：图像转模型节点使用 Meshy API 从单张输入图像生成 3D 模型。它会上传您的图像、提交处理任务，并返回生成的 3D 模型文件（GLB 和 FBX）以及用于参考的任务 ID。 ## 输入 @@ -34,9 +35,9 @@ Meshy：图像转模型节点使用 Meshy API 从单张输入图像生成 3D 模 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `meshy_task_id` | 生成的 GLB 模型的文件名。（为保持向后兼容性而保留）。 | STRING | -| `GLB` | Meshy API 任务的唯一标识符，可用于参考或故障排除。 | MESHY_TASK_ID | -| `FBX` | 以 GLB 文件格式生成的 3D 模型。 | FILE3DGLB | +| `模型文件` | 生成的 GLB 模型的文件名。（为保持向后兼容性而保留）。 | STRING | +| `meshy_task_id` | Meshy API 任务的唯一标识符，可用于参考或故障排除。 | MESHY_TASK_ID | +| `GLB` | 以 GLB 文件格式生成的 3D 模型。 | FILE3DGLB | | `FBX` | 以 FBX 文件格式生成的 3D 模型。 | FILE3DFBX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyImageToModelNode/zh.md) diff --git a/zh/built-in-nodes/MeshyMultiImageToModelNode.mdx b/zh/built-in-nodes/MeshyMultiImageToModelNode.mdx index 05b21416f..50daa684c 100644 --- a/zh/built-in-nodes/MeshyMultiImageToModelNode.mdx +++ b/zh/built-in-nodes/MeshyMultiImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyMultiImageToModelNode" icon: "circle" mode: wide --- + 此节点使用 Meshy API 从多张输入图像生成 3D 模型。它会上传提供的图像，提交处理任务，并返回生成的 3D 模型文件（GLB 和 FBX）以及用于参考的任务 ID。 ## 输入 @@ -35,9 +36,9 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `meshy_task_id` | 生成的 GLB 模型的文件名。此输出提供用于向后兼容。 | STRING | -| `GLB` | Meshy API 任务的唯一标识符。 | MESHY_TASK_ID | -| `FBX` | 以 GLB 格式生成的 3D 模型。 | FILE3DGLB | +| `模型文件` | 生成的 GLB 模型的文件名。此输出提供用于向后兼容。 | STRING | +| `meshy_task_id` | Meshy API 任务的唯一标识符。 | MESHY_TASK_ID | +| `GLB` | 以 GLB 格式生成的 3D 模型。 | FILE3DGLB | | `FBX` | 以 FBX 格式生成的 3D 模型。 | FILE3DFBX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyMultiImageToModelNode/zh.md) diff --git a/zh/built-in-nodes/MeshyRefineNode.mdx b/zh/built-in-nodes/MeshyRefineNode.mdx index b774dd4d9..ed54e84b6 100644 --- a/zh/built-in-nodes/MeshyRefineNode.mdx +++ b/zh/built-in-nodes/MeshyRefineNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyRefineNode" icon: "circle" mode: wide --- + Meshy：细化草稿模型节点接收先前生成的 3D 草稿模型，提升其质量，并可选择添加纹理。该节点向 Meshy API 提交细化任务，并在处理完成后返回最终的 3D 模型文件。 ## 输入 @@ -23,9 +24,9 @@ Meshy：细化草稿模型节点接收先前生成的 3D 草稿模型，提升 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `meshy_task_id` | 生成的 GLB 模型文件名。（仅用于向后兼容） | STRING | -| `GLB` | 提交的细化作业的唯一任务 ID。 | MESHY_TASK_ID | -| `FBX` | 最终细化的 3D 模型，格式为 GLB。 | FILE3DGLB | +| `模型文件` | 生成的 GLB 模型文件名。（仅用于向后兼容） | STRING | +| `meshy_task_id` | 提交的细化作业的唯一任务 ID。 | MESHY_TASK_ID | +| `GLB` | 最终细化的 3D 模型，格式为 GLB。 | FILE3DGLB | | `FBX` | 最终细化的 3D 模型，格式为 FBX。 | FILE3DFBX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRefineNode/zh.md) diff --git a/zh/built-in-nodes/MeshyRigModelNode.mdx b/zh/built-in-nodes/MeshyRigModelNode.mdx index 8aabe21b3..dbbb7143f 100644 --- a/zh/built-in-nodes/MeshyRigModelNode.mdx +++ b/zh/built-in-nodes/MeshyRigModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyRigModelNode" icon: "circle" mode: wide --- + Meshy: 骨骼绑定模型节点接收来自先前 Meshy 任务的 3D 模型，并自动为其创建骨骼，生成一个可摆姿势和动画的绑定角色。该节点以 GLB 和 FBX 两种文件格式输出绑定后的模型。 ## 输入 @@ -21,9 +22,9 @@ Meshy: 骨骼绑定模型节点接收来自先前 Meshy 任务的 3D 模型， | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `rig_task_id` | 用于向后兼容的旧版输出，包含 GLB 模型的文件名。 | STRING | -| `GLB` | 此骨骼绑定操作的唯一任务 ID，可用于引用结果。 | STRING | -| `FBX` | 以 GLB 文件格式保存的已绑定 3D 角色模型。 | FILE3DGLB | +| `模型文件` | 用于向后兼容的旧版输出，包含 GLB 模型的文件名。 | STRING | +| `rig_task_id` | 此骨骼绑定操作的唯一任务 ID，可用于引用结果。 | STRING | +| `GLB` | 以 GLB 文件格式保存的已绑定 3D 角色模型。 | FILE3DGLB | | `FBX` | 以 FBX 文件格式保存的已绑定 3D 角色模型。 | FILE3DFBX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyRigModelNode/zh.md) diff --git a/zh/built-in-nodes/MeshyTextToModelNode.mdx b/zh/built-in-nodes/MeshyTextToModelNode.mdx index 71ecc8b62..b2e6050b5 100644 --- a/zh/built-in-nodes/MeshyTextToModelNode.mdx +++ b/zh/built-in-nodes/MeshyTextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyTextToModelNode" icon: "circle" mode: wide --- + ### 概述 Meshy：文本转模型节点使用 Meshy API 根据文本描述生成 3D 模型。它会向 API 发送包含提示词和设置的请求，然后等待生成完成并下载生成的模型文件。 diff --git a/zh/built-in-nodes/MeshyTextureNode.mdx b/zh/built-in-nodes/MeshyTextureNode.mdx index c63e81454..4ab342b5d 100644 --- a/zh/built-in-nodes/MeshyTextureNode.mdx +++ b/zh/built-in-nodes/MeshyTextureNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MeshyTextureNode" icon: "circle" mode: wide --- + Meshy：纹理节点将 AI 生成的纹理应用于 3D 模型。它接收来自先前 Meshy 3D 生成或转换节点的任务 ID，并使用文本描述或参考图像为模型创建新纹理。该节点以 GLB 和 FBX 文件格式输出带纹理的模型。 ## 输入 @@ -27,9 +28,9 @@ Meshy：纹理节点将 AI 生成的纹理应用于 3D 模型。它接收来自 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `meshy_task_id` | 生成的 GLB 模型的文件名。此输出为向后兼容性而提供。 | STRING | -| `GLB` | 此纹理处理任务的唯一任务标识符，可用于引用结果。 | MODEL_TASK_ID | -| `FBX` | 以 GLB 文件格式保存的带纹理 3D 模型。 | FILE3DGLB | +| `模型文件` | 生成的 GLB 模型的文件名。此输出为向后兼容性而提供。 | STRING | +| `meshy_task_id` | 此纹理处理任务的唯一任务标识符，可用于引用结果。 | MODEL_TASK_ID | +| `GLB` | 以 GLB 文件格式保存的带纹理 3D 模型。 | FILE3DGLB | | `FBX` | 以 FBX 文件格式保存的带纹理 3D 模型。 | FILE3DFBX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MeshyTextureNode/zh.md) diff --git a/zh/built-in-nodes/MinimaxHailuoVideoNode.mdx b/zh/built-in-nodes/MinimaxHailuoVideoNode.mdx index 741ccf941..64b6b9c1f 100644 --- a/zh/built-in-nodes/MinimaxHailuoVideoNode.mdx +++ b/zh/built-in-nodes/MinimaxHailuoVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxHailuoVideoNode" icon: "circle" mode: wide --- + 使用 MiniMax Hailuo-02 模型根据文本提示生成视频。您可以选择提供一张起始图像作为第一帧，从而生成从该图像延续的视频。 ## 输入 diff --git a/zh/built-in-nodes/MinimaxImageToVideoNode.mdx b/zh/built-in-nodes/MinimaxImageToVideoNode.mdx index a29dcacb6..a379718c0 100644 --- a/zh/built-in-nodes/MinimaxImageToVideoNode.mdx +++ b/zh/built-in-nodes/MinimaxImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxImageToVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxImageToVideoNode/en.md) 基于图像、提示词及可选参数，通过 MiniMax 的 API 同步生成视频。此节点接收输入图像和文本描述，创建视频序列，并提供多种模型选项和配置设置。 diff --git a/zh/built-in-nodes/MinimaxSubjectToVideoNode.mdx b/zh/built-in-nodes/MinimaxSubjectToVideoNode.mdx index ce51d8f30..2ccef6ef6 100644 --- a/zh/built-in-nodes/MinimaxSubjectToVideoNode.mdx +++ b/zh/built-in-nodes/MinimaxSubjectToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxSubjectToVideoNode" icon: "circle" mode: wide --- + 使用 MiniMax API，基于主体图像和文本提示同步生成视频。此节点接收主体图像和描述，根据提示创建动画或展示该主体的视频。 ## 输入 diff --git a/zh/built-in-nodes/MinimaxTextToVideoNode.mdx b/zh/built-in-nodes/MinimaxTextToVideoNode.mdx index 838d138ab..5716c8cd7 100644 --- a/zh/built-in-nodes/MinimaxTextToVideoNode.mdx +++ b/zh/built-in-nodes/MinimaxTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MinimaxTextToVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MinimaxTextToVideoNode/en.md) 根据提示和可选参数，通过 MiniMax 的 API 同步生成视频。此节点通过连接到 MiniMax 的文本转视频服务，从文本描述创建视频内容。 diff --git a/zh/built-in-nodes/MoGeInference.mdx b/zh/built-in-nodes/MoGeInference.mdx index 027bd8c8d..72836f417 100644 --- a/zh/built-in-nodes/MoGeInference.mdx +++ b/zh/built-in-nodes/MoGeInference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGeInference" icon: "circle" mode: wide --- + ## ## 概述 对单张图像运行 MoGe 模型以估计深度和几何结构。此节点通过 MoGe 模型处理输入图像，生成 3D 点云、深度图、相机内参、遮罩以及表面法线。 diff --git a/zh/built-in-nodes/MoGePanoramaInference.mdx b/zh/built-in-nodes/MoGePanoramaInference.mdx index 8dae10543..6ffd13540 100644 --- a/zh/built-in-nodes/MoGePanoramaInference.mdx +++ b/zh/built-in-nodes/MoGePanoramaInference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGePanoramaInference" icon: "circle" mode: wide --- + ## ## 概述 此节点对等距柱状投影全景图像执行深度估计。其工作原理是将全景图分割为 12 个透视视图，对每个视图运行 MoGe 深度估计模型，然后将结果合并回原始全景图的单一完整深度图。 diff --git a/zh/built-in-nodes/MoGePointMapToMesh.mdx b/zh/built-in-nodes/MoGePointMapToMesh.mdx index 50f1e8ba7..61f9326b3 100644 --- a/zh/built-in-nodes/MoGePointMapToMesh.mdx +++ b/zh/built-in-nodes/MoGePointMapToMesh.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MoGePointMapToMesh" icon: "circle" mode: wide --- + ## 概述 此节点将 MoGe 点图转换为 3D 网格。它接收 MoGe 深度估计节点生成的几何数据，并将其三角化为带有 UV 坐标和可选纹理的网格。 diff --git a/zh/built-in-nodes/MoGeRender.mdx b/zh/built-in-nodes/MoGeRender.mdx index 33738c6bb..a5386a953 100644 --- a/zh/built-in-nodes/MoGeRender.mdx +++ b/zh/built-in-nodes/MoGeRender.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoGeRender" icon: "circle" mode: wide --- -# 概述 此节点接收一个 MOGE_GEOMETRY 数据包（由 MoGe 深度/法线估计节点生成），并将其渲染为标准图像格式。您可以选择输出深度图、彩色深度图、法线图或遮罩。 diff --git a/zh/built-in-nodes/ModelComputeDtype.mdx b/zh/built-in-nodes/ModelComputeDtype.mdx index 4424054bf..7d57ad729 100644 --- a/zh/built-in-nodes/ModelComputeDtype.mdx +++ b/zh/built-in-nodes/ModelComputeDtype.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelComputeDtype" icon: "circle" mode: wide --- + ## 概述 ModelComputeDtype 节点用于更改模型在处理过程中的计算数据类型（精度）。它会创建输入模型的副本，并应用所选的精度设置，这有助于根据硬件情况优化内存使用和性能。该节点对于调试和测试不同精度配置非常有用。 diff --git a/zh/built-in-nodes/ModelMergeAdd.mdx b/zh/built-in-nodes/ModelMergeAdd.mdx index 4d67187ad..34b7be942 100644 --- a/zh/built-in-nodes/ModelMergeAdd.mdx +++ b/zh/built-in-nodes/ModelMergeAdd.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeAdd" icon: "circle" mode: wide --- + ModelMergeAdd 节点用于通过将一个模型的关键补丁添加到另一个模型来合并两个模型。此过程涉及克隆第一个模型，然后应用第二个模型的补丁，从而能够组合两个模型的特征或行为。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeAuraflow.mdx b/zh/built-in-nodes/ModelMergeAuraflow.mdx index 2f95659fa..99d485b94 100644 --- a/zh/built-in-nodes/ModelMergeAuraflow.mdx +++ b/zh/built-in-nodes/ModelMergeAuraflow.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeAuraflow" icon: "circle" mode: wide --- + ModelMergeAuraflow 节点允许您通过调整各个模型组件的特定混合权重，将两个不同的模型融合在一起。它提供了从初始层到最终输出的精细控制，让您能够精确地决定模型不同部分的合并方式。此节点特别适用于创建自定义模型组合，并对合并过程进行精确控制。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeBlocks.mdx b/zh/built-in-nodes/ModelMergeBlocks.mdx index ebbc8536a..fee45268e 100644 --- a/zh/built-in-nodes/ModelMergeBlocks.mdx +++ b/zh/built-in-nodes/ModelMergeBlocks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeBlocks" icon: "circle" mode: wide --- + ModelMergeBlocks 专为高级模型合并操作而设计，允许将两个模型进行整合，并可针对模型的不同部分自定义混合比例。此节点通过根据指定参数有选择地合并两个源模型的组件，从而便于创建混合模型。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeCosmos14B.mdx b/zh/built-in-nodes/ModelMergeCosmos14B.mdx index e7687c748..f62f99c61 100644 --- a/zh/built-in-nodes/ModelMergeCosmos14B.mdx +++ b/zh/built-in-nodes/ModelMergeCosmos14B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmos14B" icon: "circle" mode: wide --- + **ModelMergeCosmos14B** 节点采用基于块的方法，专门为 Cosmos 14B 模型架构设计，用于合并两个 AI 模型。它允许您通过调整每个模型块和嵌入层的权重值（范围在 0.0 到 1.0 之间）来混合模型的不同组件。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeCosmos7B.mdx b/zh/built-in-nodes/ModelMergeCosmos7B.mdx index 39d26b7eb..6d14a0729 100644 --- a/zh/built-in-nodes/ModelMergeCosmos7B.mdx +++ b/zh/built-in-nodes/ModelMergeCosmos7B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmos7B" icon: "circle" mode: wide --- + ModelMergeCosmos7B 节点通过加权混合特定组件的方式，将两个 AI 模型合并在一起。它允许通过调整位置嵌入、Transformer 模块和最终层的各个权重，对模型不同部分的组合方式进行精细控制。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx b/zh/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx index c70fb0ac1..57e90be35 100644 --- a/zh/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx +++ b/zh/built-in-nodes/ModelMergeCosmosPredict2_14B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmosPredict2_14B" icon: "circle" mode: wide --- + ModelMergeCosmosPredict2_14B 节点通过混合两个 AI 模型的内部组件来合并它们。它允许您使用针对特定层和组件的可调权重值，精确控制第二个模型的每个部分对最终合并结果的影响程度。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx b/zh/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx index f857417b3..311d7a20d 100644 --- a/zh/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx +++ b/zh/built-in-nodes/ModelMergeCosmosPredict2_2B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeCosmosPredict2_2B" icon: "circle" mode: wide --- + ## 概述 ModelMergeCosmosPredict2_2B 节点采用基于块（block-based）的方法合并两个扩散模型，可对模型的不同组件进行精细控制。通过调整位置嵌入器、时间嵌入器、Transformer 块和最终层的插值权重，您可以混合两个模型的特定部分，从而精确控制每个模型的不同架构组件对最终合并结果的贡献。 diff --git a/zh/built-in-nodes/ModelMergeFlux1.mdx b/zh/built-in-nodes/ModelMergeFlux1.mdx index d8257af51..e7c0010d0 100644 --- a/zh/built-in-nodes/ModelMergeFlux1.mdx +++ b/zh/built-in-nodes/ModelMergeFlux1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeFlux1" icon: "circle" mode: wide --- + ModelMergeFlux1 节点通过加权插值混合两个扩散模型的组件，从而实现模型合并。它允许对模型不同部分的组合方式进行精细控制，包括图像处理模块、时间嵌入层、引导机制、向量输入、文本编码器以及各种变换器模块。这使得能够从两个源模型创建具有自定义特征的混合模型。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeKrea2.mdx b/zh/built-in-nodes/ModelMergeKrea2.mdx new file mode 100644 index 000000000..34ba7f71d --- /dev/null +++ b/zh/built-in-nodes/ModelMergeKrea2.mdx @@ -0,0 +1,40 @@ +--- +title: "ModelMergeKrea2 - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the ModelMergeKrea2 node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "ModelMergeKrea2" +icon: "circle" +mode: wide +--- + +此节点通过在细粒度级别混合两个模型的内部组件来合并它们，使您能够控制每个模型特定部分对最终结果的影响程度。其工作原理是接收两个输入模型，并对它们架构的不同部分应用独立的混合比例。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `model1` | 要合并的第一个模型 | MODEL | 是 | - | +| `model2` | 要合并的第二个模型 | MODEL | 是 | - | +| `first.` | 第一个层块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `tmlp.` | 时间 MLP 块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `txtmlp.` | 文本 MLP 块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `tproj.` | 时间投影块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `txtfusion.layerwise_blocks.0.` | 第一个文本融合逐层块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `txtfusion.layerwise_blocks.1.` | 第二个文本融合逐层块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `txtfusion.projector.` | 文本融合投影器块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `txtfusion.refiner_blocks.0.` | 第一个文本融合精炼块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `txtfusion.refiner_blocks.1.` | 第二个文本融合精炼块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `blocks.0.` 至 `blocks.27.` | 28 个主块中每个块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | +| `last.` | 最后一个块的混合比例（默认值：1.0） | FLOAT | 是 | 0.0 至 1.0（步长：0.01） | + +每个混合比例控制该特定组件使用 `model2` 的程度，其中 0.0 表示仅使用 `model1`，1.0 表示仅使用 `model2`，中间值则创建加权混合。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `MODEL` | 根据指定比例混合两个输入模型后得到的合并模型 | MODEL | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelMergeKrea2/zh.md) + +--- +**Source fingerprint (SHA-256):** `ece35524f77fd906dc3109a0818d4d7d3986ec9debb518fd04893048843d7e88` diff --git a/zh/built-in-nodes/ModelMergeLTXV.mdx b/zh/built-in-nodes/ModelMergeLTXV.mdx index ba3072f2d..a179c30e9 100644 --- a/zh/built-in-nodes/ModelMergeLTXV.mdx +++ b/zh/built-in-nodes/ModelMergeLTXV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeLTXV" icon: "circle" mode: wide --- + ModelMergeLTXV 节点执行专为 LTXV 模型架构设计的高级模型合并操作。它允许您通过调整各种模型组件（包括 Transformer 块、投影层和其他专用模块）的插值权重，将两个不同的模型混合在一起。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeMochiPreview.mdx b/zh/built-in-nodes/ModelMergeMochiPreview.mdx index efdc67de8..4cb1db1e6 100644 --- a/zh/built-in-nodes/ModelMergeMochiPreview.mdx +++ b/zh/built-in-nodes/ModelMergeMochiPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeMochiPreview" icon: "circle" mode: wide --- + 此节点采用基于块的方法合并两个 AI 模型，并可对不同的模型组件进行精细控制。它允许您通过调整特定部分的插值权重来混合模型，这些部分包括位置频率、嵌入层和各个 Transformer 块。合并过程会根据指定的权重值，将两个输入模型的架构和参数融合在一起。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeQwenImage.mdx b/zh/built-in-nodes/ModelMergeQwenImage.mdx index dbbc99998..6e9b0391f 100644 --- a/zh/built-in-nodes/ModelMergeQwenImage.mdx +++ b/zh/built-in-nodes/ModelMergeQwenImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeQwenImage" icon: "circle" mode: wide --- + ModelMergeQwenImage 节点通过以可调节权重合并两个模型的组件，将两个 AI 模型融合。它允许您混合 Qwen 图像模型的特定部分，包括 Transformer 块、位置嵌入和文本处理组件。您可以控制每个模型对合并结果不同部分的影响程度。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeSD1.mdx b/zh/built-in-nodes/ModelMergeSD1.mdx index 5503a0530..ebf0cead3 100644 --- a/zh/built-in-nodes/ModelMergeSD1.mdx +++ b/zh/built-in-nodes/ModelMergeSD1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD1" icon: "circle" mode: wide --- + ModelMergeSD1 节点允许您通过调整不同模型组件的影响力，将两个 Stable Diffusion 1.x 模型融合在一起。它提供了对时间嵌入、标签嵌入以及所有输入块、中间块和输出块的独立控制，从而能够针对特定用例进行精细化的模型合并。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeSD35_Large.mdx b/zh/built-in-nodes/ModelMergeSD35_Large.mdx index 0b58740c0..7f310f346 100644 --- a/zh/built-in-nodes/ModelMergeSD35_Large.mdx +++ b/zh/built-in-nodes/ModelMergeSD35_Large.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD35_Large" icon: "circle" mode: wide --- + ModelMergeSD35_Large 节点允许您通过调整不同模型组件的影响力，将两个 Stable Diffusion 3.5 Large 模型融合在一起。它提供了精确的控制，让您能够决定第二个模型的每个部分（从嵌入层到联合块和最终层）对最终合并模型贡献多少。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeSD3_2B.mdx b/zh/built-in-nodes/ModelMergeSD3_2B.mdx index 396890af1..0ce94c52b 100644 --- a/zh/built-in-nodes/ModelMergeSD3_2B.mdx +++ b/zh/built-in-nodes/ModelMergeSD3_2B.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSD3_2B" icon: "circle" mode: wide --- + ModelMergeSD3_2B 节点允许您通过以可调整的权重混合两个 Stable Diffusion 3 2B 模型的组件来合并它们。它提供对嵌入层和 Transformer 模块的单独控制，从而能够为专门的生成任务进行精细调整的模型组合。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeSDXL.mdx b/zh/built-in-nodes/ModelMergeSDXL.mdx index a743d9f5e..12d213349 100644 --- a/zh/built-in-nodes/ModelMergeSDXL.mdx +++ b/zh/built-in-nodes/ModelMergeSDXL.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSDXL" icon: "circle" mode: wide --- + ModelMergeSDXL 节点允许您通过调整两个模型对架构不同部分的影响力，将两个 SDXL 模型混合在一起。您可以控制每个模型对时间嵌入、标签嵌入以及模型结构中各个块的贡献程度。这会创建一个结合了两个输入模型特征的混合模型。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeSimple.mdx b/zh/built-in-nodes/ModelMergeSimple.mdx index 55fa9a2a2..7afd17ae0 100644 --- a/zh/built-in-nodes/ModelMergeSimple.mdx +++ b/zh/built-in-nodes/ModelMergeSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSimple" icon: "circle" mode: wide --- + ModelMergeSimple 节点用于通过按指定比例混合两个模型的参数来合并它们。此节点有助于创建融合两个输入模型优势或特性的混合模型。 `ratio` 参数决定两个模型之间的混合比例。当此值为 1 时，输出模型为 100% 的 `model1`；当此值为 0 时，输出模型为 100% 的 `model2`。 diff --git a/zh/built-in-nodes/ModelMergeSubtract.mdx b/zh/built-in-nodes/ModelMergeSubtract.mdx index ca276bee1..53ad0da9b 100644 --- a/zh/built-in-nodes/ModelMergeSubtract.mdx +++ b/zh/built-in-nodes/ModelMergeSubtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeSubtract" icon: "circle" mode: wide --- + 此节点专为高级模型合并操作而设计，具体用于根据指定的乘数将一个模型的参数从另一个模型中减去。它通过调整一个模型参数对另一个模型的影响程度，实现模型行为的定制化，从而促进新型混合模型的创建。 ## 输入 diff --git a/zh/built-in-nodes/ModelMergeWAN2_1.mdx b/zh/built-in-nodes/ModelMergeWAN2_1.mdx index aa7064c8f..7c4be6c46 100644 --- a/zh/built-in-nodes/ModelMergeWAN2_1.mdx +++ b/zh/built-in-nodes/ModelMergeWAN2_1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelMergeWAN2_1" icon: "circle" mode: wide --- + ModelMergeWAN2_1 节点通过加权平均混合两个 WAN2.1 模型的组件来实现模型合并。它支持不同规模的模型，包括 30 个块的 1.3B 模型和 40 个块的 14B 模型，并针对包含额外图像嵌入组件的图像到视频模型进行了特殊处理。模型的每个组件都可以单独设置权重，以控制两个输入模型之间的混合比例。 ## 输入 diff --git a/zh/built-in-nodes/ModelNoiseScale.mdx b/zh/built-in-nodes/ModelNoiseScale.mdx index d4e09a2c1..760fc207b 100644 --- a/zh/built-in-nodes/ModelNoiseScale.mdx +++ b/zh/built-in-nodes/ModelNoiseScale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelNoiseScale" icon: "circle" mode: wide --- + ## ## 概述 此节点用于调整模型采样过程中使用的噪声尺度。它允许您设置特定的噪声尺度值，从而控制应用于模型采样过程的噪声量。 diff --git a/zh/built-in-nodes/ModelPatchLoader.mdx b/zh/built-in-nodes/ModelPatchLoader.mdx index 5e446cd9d..7f5bd6fe7 100644 --- a/zh/built-in-nodes/ModelPatchLoader.mdx +++ b/zh/built-in-nodes/ModelPatchLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelPatchLoader" icon: "circle" mode: wide --- + ModelPatchLoader 节点从 model_patches 文件夹加载专门的模型补丁。它会自动检测补丁文件的类型，加载相应的模型架构，然后将其封装在 ModelPatcher 中，以便在工作流中使用。此节点支持不同的补丁类型，包括 controlnet 块、特征嵌入模型以及其他专门架构。 ## 输入 diff --git a/zh/built-in-nodes/ModelSamplingAuraFlow.mdx b/zh/built-in-nodes/ModelSamplingAuraFlow.mdx index b106d5f6b..cf9894d9c 100644 --- a/zh/built-in-nodes/ModelSamplingAuraFlow.mdx +++ b/zh/built-in-nodes/ModelSamplingAuraFlow.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingAuraFlow" icon: "circle" mode: wide --- + ModelSamplingAuraFlow 节点为扩散模型应用专门的采样配置，专为 AuraFlow 模型架构设计。它通过应用一个调整采样分布的 shift 参数来修改模型的采样行为。此节点继承自 SD3 模型采样框架，并提供对采样过程的精细控制。 ## 输入 diff --git a/zh/built-in-nodes/ModelSamplingContinuousEDM.mdx b/zh/built-in-nodes/ModelSamplingContinuousEDM.mdx index 45ad3f6ed..67ed4f8e2 100644 --- a/zh/built-in-nodes/ModelSamplingContinuousEDM.mdx +++ b/zh/built-in-nodes/ModelSamplingContinuousEDM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingContinuousEDM" icon: "circle" mode: wide --- + 此节点通过集成连续 EDM（基于能量的扩散模型）采样技术，增强模型的采样能力。它允许在模型采样过程中动态调整噪声水平，从而对生成质量和多样性实现更精细的控制。 ## 输入 diff --git a/zh/built-in-nodes/ModelSamplingContinuousV.mdx b/zh/built-in-nodes/ModelSamplingContinuousV.mdx index 2f0479aac..8ad419c03 100644 --- a/zh/built-in-nodes/ModelSamplingContinuousV.mdx +++ b/zh/built-in-nodes/ModelSamplingContinuousV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingContinuousV" icon: "circle" mode: wide --- + ## 概述 ModelSamplingContinuousV 节点通过应用连续 V 预测采样参数来修改模型的采样行为。它会创建输入模型的克隆，并使用自定义 sigma 范围设置进行配置，以实现高级采样控制。这允许用户使用特定的最小和最大 sigma 值来微调采样过程。 diff --git a/zh/built-in-nodes/ModelSamplingDiscrete.mdx b/zh/built-in-nodes/ModelSamplingDiscrete.mdx index b4892da98..d568a18bf 100644 --- a/zh/built-in-nodes/ModelSamplingDiscrete.mdx +++ b/zh/built-in-nodes/ModelSamplingDiscrete.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingDiscrete" icon: "circle" mode: wide --- + 此节点旨在通过应用离散采样策略来修改模型的采样行为。它允许选择不同的采样方法，例如 epsilon、v_prediction、lcm 或 x0，并可选择根据零样本噪声比（zsnr）设置调整模型的降噪策略。 ## 输入 diff --git a/zh/built-in-nodes/ModelSamplingFlux.mdx b/zh/built-in-nodes/ModelSamplingFlux.mdx index da09c9de8..2edffda22 100644 --- a/zh/built-in-nodes/ModelSamplingFlux.mdx +++ b/zh/built-in-nodes/ModelSamplingFlux.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingFlux" icon: "circle" mode: wide --- + ModelSamplingFlux 节点通过根据图像尺寸计算偏移参数，将 Flux 模型采样应用于给定模型。它会创建一个专门的采样配置，根据指定的宽度、高度和偏移参数调整模型行为，然后返回应用了新采样设置的修改后模型。 ## 输入 diff --git a/zh/built-in-nodes/ModelSamplingLTXV.mdx b/zh/built-in-nodes/ModelSamplingLTXV.mdx index 46dfeda86..72fadd819 100644 --- a/zh/built-in-nodes/ModelSamplingLTXV.mdx +++ b/zh/built-in-nodes/ModelSamplingLTXV.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingLTXV" icon: "circle" mode: wide --- + ModelSamplingLTXV节点根据令牌数量对模型应用高级采样参数。它通过基础偏移值和最大偏移值之间的线性插值计算偏移值，该计算取决于输入潜在变量中的令牌数量。随后，该节点创建专门的模型采样配置，并将其应用于输入模型。 ## 输入 diff --git a/zh/built-in-nodes/ModelSamplingSD3.mdx b/zh/built-in-nodes/ModelSamplingSD3.mdx index cba5d4588..2547f3191 100644 --- a/zh/built-in-nodes/ModelSamplingSD3.mdx +++ b/zh/built-in-nodes/ModelSamplingSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingSD3" icon: "circle" mode: wide --- + ModelSamplingSD3 节点将 Stable Diffusion 3 采样参数应用于模型。它通过调整 shift 参数来修改模型的采样行为，该参数控制采样分布特征。此节点会创建输入模型的修改副本，并应用指定的采样配置。 ## 输入 diff --git a/zh/built-in-nodes/ModelSamplingStableCascade.mdx b/zh/built-in-nodes/ModelSamplingStableCascade.mdx index 124c3d6ab..314085eec 100644 --- a/zh/built-in-nodes/ModelSamplingStableCascade.mdx +++ b/zh/built-in-nodes/ModelSamplingStableCascade.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSamplingStableCascade" icon: "circle" mode: wide --- + ModelSamplingStableCascade 节点通过使用偏移值调整采样参数，对模型应用稳定级联采样。它会创建一个输入模型的修改版本，并配置自定义采样参数，用于稳定级联生成。 ## 输入 diff --git a/zh/built-in-nodes/ModelSave.mdx b/zh/built-in-nodes/ModelSave.mdx index f207cb466..4791c380a 100644 --- a/zh/built-in-nodes/ModelSave.mdx +++ b/zh/built-in-nodes/ModelSave.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ModelSave" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ModelSave/en.md) ModelSave 节点将训练或修改后的模型保存到计算机存储中。它接收一个模型作为输入，并将其写入指定文件名的文件中。这使您可以保留工作成果，并在未来项目中重复使用模型。 diff --git a/zh/built-in-nodes/MoonvalleyImg2VideoNode.mdx b/zh/built-in-nodes/MoonvalleyImg2VideoNode.mdx index bd8832e2b..c53e271e5 100644 --- a/zh/built-in-nodes/MoonvalleyImg2VideoNode.mdx +++ b/zh/built-in-nodes/MoonvalleyImg2VideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoonvalleyImg2VideoNode" icon: "circle" mode: wide --- -# Moonvalley Marey 图像转视频节点 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MoonvalleyImg2VideoNode/en.md) diff --git a/zh/built-in-nodes/MoonvalleyTxt2VideoNode.mdx b/zh/built-in-nodes/MoonvalleyTxt2VideoNode.mdx index 42b465037..9499f2c46 100644 --- a/zh/built-in-nodes/MoonvalleyTxt2VideoNode.mdx +++ b/zh/built-in-nodes/MoonvalleyTxt2VideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoonvalleyTxt2VideoNode" icon: "circle" mode: wide --- -# Moonvalley Marey 文本转视频节点 此文档由AI生成。如发现任何错误或有改进建议，欢迎贡献！[在GitHub上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MoonvalleyTxt2VideoNode/en.md) diff --git a/zh/built-in-nodes/MoonvalleyVideo2VideoNode.mdx b/zh/built-in-nodes/MoonvalleyVideo2VideoNode.mdx index 2ac28e375..3df0a88ab 100644 --- a/zh/built-in-nodes/MoonvalleyVideo2VideoNode.mdx +++ b/zh/built-in-nodes/MoonvalleyVideo2VideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "MoonvalleyVideo2VideoNode" icon: "circle" mode: wide --- -# Moonvalley Marey 视频到视频节点 此节点基于文本描述，将输入视频转换为新视频。它使用 Moonvalley API 生成与提示词匹配的视频，同时保留原始视频的运动或姿态特征。您可以通过文本提示词和各种生成参数来控制输出视频的风格和内容。 diff --git a/zh/built-in-nodes/Morphology.mdx b/zh/built-in-nodes/Morphology.mdx index a78103c10..61b978731 100644 --- a/zh/built-in-nodes/Morphology.mdx +++ b/zh/built-in-nodes/Morphology.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Morphology" icon: "circle" mode: wide --- + 形态学节点对图像应用各种形态学运算，这些运算是一种用于处理和分析图像中形状的数学方法。该节点可执行腐蚀、膨胀、开运算、闭运算等操作，并通过可自定义的内核大小来控制效果强度。 ## 输入 diff --git a/zh/built-in-nodes/MultiGPU_Options.mdx b/zh/built-in-nodes/MultiGPU_Options.mdx index fa1a1803e..3dc5832bb 100644 --- a/zh/built-in-nodes/MultiGPU_Options.mdx +++ b/zh/built-in-nodes/MultiGPU_Options.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MultiGPU_Options" icon: "circle" mode: wide --- + ## ## 概述 此节点允许您在使用不同速度的多张显卡时，指定每张 GPU 的相对性能。它会创建一个 GPU 选项组，用于在设备间分配工作负载，不过当前版本尚未实现基于速度的实际工作负载分配功能。 diff --git a/zh/built-in-nodes/MultiGPU_WorkUnits.mdx b/zh/built-in-nodes/MultiGPU_WorkUnits.mdx index 1df98a4b0..3bb703fb1 100644 --- a/zh/built-in-nodes/MultiGPU_WorkUnits.mdx +++ b/zh/built-in-nodes/MultiGPU_WorkUnits.mdx @@ -5,6 +5,7 @@ sidebarTitle: "MultiGPU_WorkUnits" icon: "circle" mode: wide --- + ## 概述 MultiGPU CFG Split 节点可以让同一台电脑中的多张 GPU 一起参与扩散采样。实际提速会因工作流而不同，但在常见工作流中，已经测到最高约 1.95 倍的加速效果。 diff --git a/zh/built-in-nodes/NAGuidance.mdx b/zh/built-in-nodes/NAGuidance.mdx index 16ef24c65..4ff945100 100644 --- a/zh/built-in-nodes/NAGuidance.mdx +++ b/zh/built-in-nodes/NAGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NAGuidance" icon: "circle" mode: wide --- + ## 概述 NAGuidance 节点将归一化注意力引导（Normalized Attention Guidance）应用于模型。该技术通过在采样过程中修改模型的注意力机制，使蒸馏或快速模型能够使用负面提示，从而引导生成结果远离不期望的概念。 diff --git a/zh/built-in-nodes/NormalizeImages.mdx b/zh/built-in-nodes/NormalizeImages.mdx index 8d9ea0cdf..91ee03f8e 100644 --- a/zh/built-in-nodes/NormalizeImages.mdx +++ b/zh/built-in-nodes/NormalizeImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NormalizeImages" icon: "circle" mode: wide --- + 此节点通过数学归一化过程调整输入图像的像素值。它会从每个像素中减去指定的均值，然后将结果除以指定的标准差。这是一种常见的预处理步骤，用于为其他机器学习模型准备图像数据。 ## 输入 @@ -19,7 +20,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `image` | 经过归一化处理后的结果图像。 | IMAGE | +| `图像` | 经过归一化处理后的结果图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeImages/zh.md) diff --git a/zh/built-in-nodes/NormalizeVideoLatentStart.mdx b/zh/built-in-nodes/NormalizeVideoLatentStart.mdx index 162e68a11..1b84bacf8 100644 --- a/zh/built-in-nodes/NormalizeVideoLatentStart.mdx +++ b/zh/built-in-nodes/NormalizeVideoLatentStart.mdx @@ -5,6 +5,7 @@ sidebarTitle: "NormalizeVideoLatentStart" icon: "circle" mode: wide --- + 此节点调整视频潜空间的前几帧，使其看起来更像后续帧。它会从视频较后位置的一组参考帧中计算平均值和变化量，并将这些特征应用于起始帧。这有助于在视频开头创建更平滑、更一致的视觉过渡。 ## 输入 @@ -21,7 +22,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `Latent` | 处理后的视频潜空间，起始帧已归一化。 | LATENT | +| `latent` | 处理后的视频潜空间，起始帧已归一化。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/NormalizeVideoLatentStart/zh.md) diff --git a/zh/built-in-nodes/Note.mdx b/zh/built-in-nodes/Note.mdx index b8c8912fb..3f8529f43 100644 --- a/zh/built-in-nodes/Note.mdx +++ b/zh/built-in-nodes/Note.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Note" icon: "circle" mode: wide --- + 用于向工作流添加注释的节点。 ## 输入 diff --git a/zh/built-in-nodes/OpenAIChatConfig.mdx b/zh/built-in-nodes/OpenAIChatConfig.mdx index 04bd3c76c..99d2fd647 100644 --- a/zh/built-in-nodes/OpenAIChatConfig.mdx +++ b/zh/built-in-nodes/OpenAIChatConfig.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIChatConfig" icon: "circle" mode: wide --- + OpenAIChatConfig 节点允许为 OpenAI 聊天节点设置额外的配置选项。它提供了控制模型生成响应方式的高级设置，包括截断行为、输出长度限制和自定义指令。 ## 输入 diff --git a/zh/built-in-nodes/OpenAIChatNode.mdx b/zh/built-in-nodes/OpenAIChatNode.mdx index 3c57e3546..1aab25330 100644 --- a/zh/built-in-nodes/OpenAIChatNode.mdx +++ b/zh/built-in-nodes/OpenAIChatNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIChatNode" icon: "circle" mode: wide --- + 此节点从 OpenAI 模型生成文本回复。它将您的文本提示（以及可选的图像或文件）发送到 OpenAI 模型，并返回生成的文本回复。 ## 输入 diff --git a/zh/built-in-nodes/OpenAIDalle2.mdx b/zh/built-in-nodes/OpenAIDalle2.mdx index bea544ed3..c52831196 100644 --- a/zh/built-in-nodes/OpenAIDalle2.mdx +++ b/zh/built-in-nodes/OpenAIDalle2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "OpenAIDalle2" icon: "circle" mode: wide --- -# OpenAIDalle2 通过 OpenAI 的 DALL·E 2 端点同步生成图像。 diff --git a/zh/built-in-nodes/OpenAIDalle3.mdx b/zh/built-in-nodes/OpenAIDalle3.mdx index 7eeff9853..06f7a3171 100644 --- a/zh/built-in-nodes/OpenAIDalle3.mdx +++ b/zh/built-in-nodes/OpenAIDalle3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIDalle3" icon: "circle" mode: wide --- + 通过 OpenAI 的 DALL·E 3 端点同步生成图像。此节点接收文本提示，并使用 OpenAI 的 DALL·E 3 模型创建相应图像，允许您指定图像质量、风格和尺寸。 ## 输入 diff --git a/zh/built-in-nodes/OpenAIGPTImage1.mdx b/zh/built-in-nodes/OpenAIGPTImage1.mdx index 5543edc24..8444bda2e 100644 --- a/zh/built-in-nodes/OpenAIGPTImage1.mdx +++ b/zh/built-in-nodes/OpenAIGPTImage1.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIGPTImage1" icon: "circle" mode: wide --- + 通过 OpenAI 的 GPT 图像端点同步生成图像。此节点可以根据文本提示创建新图像，或在提供输入图像和可选遮罩时编辑现有图像。它支持多种 GPT 图像模型，包括 gpt-image-1、gpt-image-1.5 和 gpt-image-2。 ## 输入 diff --git a/zh/built-in-nodes/OpenAIGPTImageNodeV2.mdx b/zh/built-in-nodes/OpenAIGPTImageNodeV2.mdx index d7497d7e1..91511b98f 100644 --- a/zh/built-in-nodes/OpenAIGPTImageNodeV2.mdx +++ b/zh/built-in-nodes/OpenAIGPTImageNodeV2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIGPTImageNodeV2" icon: "circle" mode: wide --- + ## 概述 此节点使用 OpenAI 的 GPT 图像 API 生成图像。它支持多种模型，允许您提供输入图像进行编辑，并可使用遮罩指定要修改的图像区域。 diff --git a/zh/built-in-nodes/OpenAIInputFiles.mdx b/zh/built-in-nodes/OpenAIInputFiles.mdx index cc026e11c..14dfddc39 100644 --- a/zh/built-in-nodes/OpenAIInputFiles.mdx +++ b/zh/built-in-nodes/OpenAIInputFiles.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIInputFiles" icon: "circle" mode: wide --- + 加载并格式化 OpenAI API 的输入文件。此节点准备文本（.txt）和 PDF（.pdf）文件，作为 OpenAI 聊天节点的上下文输入。在生成响应时，OpenAI 模型将读取这些文件。多个 OpenAI 输入文件节点可以链接在一起，以便在单条消息中包含多个文件。 ## 输入 diff --git a/zh/built-in-nodes/OpenAIVideoSora2.mdx b/zh/built-in-nodes/OpenAIVideoSora2.mdx index 3c705e630..73b22f3f1 100644 --- a/zh/built-in-nodes/OpenAIVideoSora2.mdx +++ b/zh/built-in-nodes/OpenAIVideoSora2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenAIVideoSora2" icon: "circle" mode: wide --- + OpenAIVideoSora2 节点使用 OpenAI 的 Sora 模型生成视频。它根据文本提示和可选的输入图像创建视频内容，然后返回生成的视频输出。该节点支持不同的视频时长和分辨率，具体取决于所选模型。 **弃用通知：** OpenAI 将于 2026 年 9 月停止提供 Sora v2 API。届时，此节点将从 ComfyUI 中移除。 diff --git a/zh/built-in-nodes/OpenRouterLLMNode.mdx b/zh/built-in-nodes/OpenRouterLLMNode.mdx index 4bb3a952c..884707e30 100644 --- a/zh/built-in-nodes/OpenRouterLLMNode.mdx +++ b/zh/built-in-nodes/OpenRouterLLMNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpenRouterLLMNode" icon: "circle" mode: wide --- + ## 概述 OpenRouter LLM 节点将文本提示发送至 OpenRouter 服务提供的一组精选流行语言模型，并返回生成的文本响应。它支持来自 xAI、DeepSeek、Qwen、Mistral、Z.AI (GLM)、Moonshot (Kimi) 和 Perplexity Sonar 等提供商的模型，并且可以选择在请求中包含图像或视频。 diff --git a/zh/built-in-nodes/OpticalFlowLoader.mdx b/zh/built-in-nodes/OpticalFlowLoader.mdx index 0c7c6ab03..002c12bb8 100644 --- a/zh/built-in-nodes/OpticalFlowLoader.mdx +++ b/zh/built-in-nodes/OpticalFlowLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "OpticalFlowLoader" icon: "circle" mode: wide --- + ## 概述 从 `models/optical_flow/` 文件夹中加载光流模型。目前仅支持 torchvision 的 RAFT-large 格式，这也是 VOIDWarpedNoise 节点所使用的模型。ComfyUI 不会自动下载光流权重文件，您需要手动将检查点文件放置在 `models/optical_flow/` 目录中。 diff --git a/zh/built-in-nodes/OptimalStepsScheduler.mdx b/zh/built-in-nodes/OptimalStepsScheduler.mdx index e8064183a..e11e69f7e 100644 --- a/zh/built-in-nodes/OptimalStepsScheduler.mdx +++ b/zh/built-in-nodes/OptimalStepsScheduler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "OptimalStepsScheduler" icon: "circle" mode: wide --- -# OptimalStepsScheduler 节点 此节点根据所选模型类型和步数配置，计算扩散模型的噪声调度 sigma 值。它会根据去噪参数调整总步数，并插值噪声水平以匹配请求的步数。该节点返回一系列 sigma 值，用于确定扩散采样过程中使用的噪声水平。 diff --git a/zh/built-in-nodes/Painter.mdx b/zh/built-in-nodes/Painter.mdx index a82ba1ff3..606b2bbcd 100644 --- a/zh/built-in-nodes/Painter.mdx +++ b/zh/built-in-nodes/Painter.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Painter" icon: "circle" mode: wide --- + Painter 节点提供了一个交互式画布，用于直接在 ComfyUI 中创建或编辑图像和遮罩。它允许您从空白画布或现有图像开始，使用画笔工具进行绘制，并输出最终图像和相应的 Alpha 遮罩。遮罩定义了绘制区域，这些区域随后会合成到基础图像或背景颜色之上。 ## 输入 diff --git a/zh/built-in-nodes/PairConditioningCombine.mdx b/zh/built-in-nodes/PairConditioningCombine.mdx index 7c753668a..02052df7e 100644 --- a/zh/built-in-nodes/PairConditioningCombine.mdx +++ b/zh/built-in-nodes/PairConditioningCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningCombine" icon: "circle" mode: wide --- + PairConditioningCombine 节点将两组独立的条件配对（每组包含一个正向条件和一个负向条件）合并为一组组合配对。它从两个不同来源获取正向和负向条件，并使用 ComfyUI 的内部逻辑进行组合，最终输出一个正向条件和一个负向条件。此节点为实验性功能，专为高级条件操控工作流设计。 ## 输入 @@ -20,8 +21,8 @@ PairConditioningCombine 节点将两组独立的条件配对（每组包含一 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 组合后的正向条件输出 | CONDITIONING | -| `negative` | 组合后的负向条件输出 | CONDITIONING | +| `正面条件` | 组合后的正向条件输出 | CONDITIONING | +| `负面条件` | 组合后的负向条件输出 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningCombine/zh.md) diff --git a/zh/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx b/zh/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx index da2d0dd29..28ddfcaa2 100644 --- a/zh/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx +++ b/zh/built-in-nodes/PairConditioningSetDefaultAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetDefaultAndCombine" icon: "circle" mode: wide --- + **PairConditioningSetDefaultAndCombine** 节点用于设置默认条件值，并将其与输入的条件数据结合。它接收正向和负向条件输入及其对应的默认值，然后通过 ComfyUI 的钩子系统进行处理，最终输出包含默认值的条件结果。 ## 输入 diff --git a/zh/built-in-nodes/PairConditioningSetProperties.mdx b/zh/built-in-nodes/PairConditioningSetProperties.mdx index 2835309d6..2ad960630 100644 --- a/zh/built-in-nodes/PairConditioningSetProperties.mdx +++ b/zh/built-in-nodes/PairConditioningSetProperties.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetProperties" icon: "circle" mode: wide --- + ### 概述 **PairConditioningSetProperties** 节点允许您同时修改正向和负向条件对（conditioning pairs）的属性。它对两个条件输入应用强度调整、条件区域设置以及可选的遮罩或时序控制，并返回修改后的正向和负向条件数据。 diff --git a/zh/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx b/zh/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx index a051d3a13..956fb0647 100644 --- a/zh/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx +++ b/zh/built-in-nodes/PairConditioningSetPropertiesAndCombine.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PairConditioningSetPropertiesAndCombine" icon: "circle" mode: wide --- + PairConditioningSetPropertiesAndCombine 节点通过将新的条件数据应用于现有的正面和负面条件输入，来修改和组合条件对。它允许您调整所应用条件的强度，并控制条件区域的设置方式。此节点特别适用于需要将多个条件源混合在一起的进阶条件处理工作流程。 ## 输入 @@ -25,7 +26,7 @@ PairConditioningSetPropertiesAndCombine 节点通过将新的条件数据应用 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 组合后的正面条件输出 | CONDITIONING | +| `正面条件` | 组合后的正面条件输出 | CONDITIONING | | `负面条件` | 组合后的负面条件输出 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PairConditioningSetPropertiesAndCombine/zh.md) diff --git a/zh/built-in-nodes/PatchModelAddDownscale.mdx b/zh/built-in-nodes/PatchModelAddDownscale.mdx index d30017376..ce2867444 100644 --- a/zh/built-in-nodes/PatchModelAddDownscale.mdx +++ b/zh/built-in-nodes/PatchModelAddDownscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PatchModelAddDownscale" icon: "circle" mode: wide --- + PatchModelAddDownscale 节点通过将下采样和上采样操作应用于模型中的特定块，实现了 Kohya Deep Shrink 功能。该节点在处理过程中降低中间特征的分辨率，然后将其恢复至原始大小，从而在保持质量的同时提升性能。该节点允许精确控制这些缩放操作在模型执行过程中的时机和方式。 ## 输入 diff --git a/zh/built-in-nodes/PerpNeg.mdx b/zh/built-in-nodes/PerpNeg.mdx index c06f0c377..24c848714 100644 --- a/zh/built-in-nodes/PerpNeg.mdx +++ b/zh/built-in-nodes/PerpNeg.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerpNeg" icon: "circle" mode: wide --- + PerpNeg 节点对模型的采样过程应用垂直负向引导。该节点修改模型的配置函数，使用负向条件和缩放因子调整噪声预测。此节点已弃用，由 PerpNegGuider 节点替代以提供更完善的功能。 ## 输入 diff --git a/zh/built-in-nodes/PerpNegGuider.mdx b/zh/built-in-nodes/PerpNegGuider.mdx index 35c2aaf03..89b1dace7 100644 --- a/zh/built-in-nodes/PerpNegGuider.mdx +++ b/zh/built-in-nodes/PerpNegGuider.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerpNegGuider" icon: "circle" mode: wide --- + PerpNegGuider 节点创建了一个引导系统，用于通过垂直负向条件控制图像生成。它接收正向、负向和空条件输入，并应用专门的引导算法来引导生成过程。此节点专为实验测试而设计，可精细控制引导强度和负向缩放。 ## 输入 diff --git a/zh/built-in-nodes/PerturbedAttentionGuidance.mdx b/zh/built-in-nodes/PerturbedAttentionGuidance.mdx index a654e3025..c6c36cc77 100644 --- a/zh/built-in-nodes/PerturbedAttentionGuidance.mdx +++ b/zh/built-in-nodes/PerturbedAttentionGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PerturbedAttentionGuidance" icon: "circle" mode: wide --- + PerturbedAttentionGuidance 节点对扩散模型应用扰动注意力引导，以提升生成质量。该节点在采样过程中通过将模型的自注意力机制替换为专注于值投影的简化版本，从而修改该机制。此技术通过调整条件去噪过程，有助于改善生成图像的连贯性和质量。 ## 输入 diff --git a/zh/built-in-nodes/PhotoMakerEncode.mdx b/zh/built-in-nodes/PhotoMakerEncode.mdx index 973305cd4..9e4f3bec5 100644 --- a/zh/built-in-nodes/PhotoMakerEncode.mdx +++ b/zh/built-in-nodes/PhotoMakerEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PhotoMakerEncode" icon: "circle" mode: wide --- + PhotoMakerEncode 节点处理图像和文本，为 AI 图像生成生成条件数据。它接收参考图像和文本提示，然后创建嵌入，用于根据参考图像的视觉特征引导图像生成。该节点会特别查找文本中的 "photomaker" 标记，以确定在何处应用基于图像的条件控制。 ## 输入 diff --git a/zh/built-in-nodes/PhotoMakerLoader.mdx b/zh/built-in-nodes/PhotoMakerLoader.mdx index d1fa370d5..d41a6b6ad 100644 --- a/zh/built-in-nodes/PhotoMakerLoader.mdx +++ b/zh/built-in-nodes/PhotoMakerLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PhotoMakerLoader" icon: "circle" mode: wide --- + PhotoMakerLoader 节点从可用的模型文件中加载 PhotoMaker 模型。它会读取指定的模型文件，并准备 PhotoMaker ID 编码器，用于基于身份的图像生成任务。此节点标记为实验性，仅供测试使用。 ## 输入 diff --git a/zh/built-in-nodes/PiDConditioning.mdx b/zh/built-in-nodes/PiDConditioning.mdx index 5ebf289c8..b9b7c6a0b 100644 --- a/zh/built-in-nodes/PiDConditioning.mdx +++ b/zh/built-in-nodes/PiDConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PiDConditioning" icon: "circle" mode: wide --- + ## 概述 将潜在图像和退化 sigma 值附加到 CONDITIONING 数据中。此节点用于 PiD（像素级细节）解码或放大，允许您控制潜在图像在处理前的退化程度。 diff --git a/zh/built-in-nodes/PikaImageToVideoNode2_2.mdx b/zh/built-in-nodes/PikaImageToVideoNode2_2.mdx index f6f776550..f984381cc 100644 --- a/zh/built-in-nodes/PikaImageToVideoNode2_2.mdx +++ b/zh/built-in-nodes/PikaImageToVideoNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaImageToVideoNode2_2" icon: "circle" mode: wide --- + Pika 图像转视频节点将图像和文本提示发送至 Pika API 2.2 版本以生成视频。该节点根据提供的描述和设置，将输入图像转换为视频格式，并处理 API 通信，最终返回生成的视频作为输出。 ## 输入 diff --git a/zh/built-in-nodes/PikaScenesV2_2.mdx b/zh/built-in-nodes/PikaScenesV2_2.mdx index 852e3ba80..47b242488 100644 --- a/zh/built-in-nodes/PikaScenesV2_2.mdx +++ b/zh/built-in-nodes/PikaScenesV2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaScenesV2_2" icon: "circle" mode: wide --- + PikaScenes v2.2 节点可组合多张图像，生成一段融合所有输入图像中物体的视频。您最多可上传五张不同的图像作为素材，并生成一段高质量、无缝融合的视频。 ## 输入 diff --git a/zh/built-in-nodes/PikaStartEndFrameNode2_2.mdx b/zh/built-in-nodes/PikaStartEndFrameNode2_2.mdx index a25d9e179..2affcc444 100644 --- a/zh/built-in-nodes/PikaStartEndFrameNode2_2.mdx +++ b/zh/built-in-nodes/PikaStartEndFrameNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaStartEndFrameNode2_2" icon: "circle" mode: wide --- + PikaFrames v2.2 节点通过组合首帧和尾帧来生成视频。您上传两张图片分别定义起始点和结束点，AI 会在两者之间创建平滑过渡，从而生成完整的视频。 ## 输入 diff --git a/zh/built-in-nodes/PikaTextToVideoNode2_2.mdx b/zh/built-in-nodes/PikaTextToVideoNode2_2.mdx index 5183c2fd8..b70906037 100644 --- a/zh/built-in-nodes/PikaTextToVideoNode2_2.mdx +++ b/zh/built-in-nodes/PikaTextToVideoNode2_2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PikaTextToVideoNode2_2" icon: "circle" mode: wide --- + Pika Text2Video v2.2 节点将文本提示发送至 Pika API 2.2 版本以生成视频。它利用 Pika 的 AI 视频生成服务，将您的文本描述转换为视频。该节点允许您自定义视频生成过程中的多个方面，包括宽高比、时长和分辨率。 ## 输入 diff --git a/zh/built-in-nodes/Pikadditions.mdx b/zh/built-in-nodes/Pikadditions.mdx index b952ca011..6edbba940 100644 --- a/zh/built-in-nodes/Pikadditions.mdx +++ b/zh/built-in-nodes/Pikadditions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikadditions" icon: "circle" mode: wide --- + Pikadditions 节点允许您将任意物体或图像添加到视频中。您上传视频并指定要添加的内容，即可创建无缝融合的结果。该节点使用 Pika API 将图像以自然的方式插入视频。 ## 输入 diff --git a/zh/built-in-nodes/Pikaffects.mdx b/zh/built-in-nodes/Pikaffects.mdx index 6c8b8868c..9f1c548e2 100644 --- a/zh/built-in-nodes/Pikaffects.mdx +++ b/zh/built-in-nodes/Pikaffects.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikaffects" icon: "circle" mode: wide --- + ### 概述 Pikaffects 节点可对输入图像应用多种视觉效果生成视频。它利用 Pika 的视频生成 API，将静态图像转换为具有特定效果（如融化、爆炸或悬浮）的动画视频。该节点需要 API 密钥和身份验证令牌才能访问 Pika 服务。 diff --git a/zh/built-in-nodes/Pikaswaps.mdx b/zh/built-in-nodes/Pikaswaps.mdx index 3156c1d5d..8b9516d06 100644 --- a/zh/built-in-nodes/Pikaswaps.mdx +++ b/zh/built-in-nodes/Pikaswaps.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Pikaswaps" icon: "circle" mode: wide --- + Pika Swaps 节点可将视频中的物体或区域替换为新图像。您可以使用遮罩定义需要替换的区域，该节点会在整个视频序列中无缝替换指定内容。 ## 输入 diff --git a/zh/built-in-nodes/PixverseImageToVideoNode.mdx b/zh/built-in-nodes/PixverseImageToVideoNode.mdx index 53a721b9e..7ef455b81 100644 --- a/zh/built-in-nodes/PixverseImageToVideoNode.mdx +++ b/zh/built-in-nodes/PixverseImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseImageToVideoNode" icon: "circle" mode: wide --- + 根据输入图像和文本提示生成视频。此节点接收一张图像，通过应用指定的运动和质量设置，将静态图像转换为动态序列，从而创建动画视频。 ## 输入 diff --git a/zh/built-in-nodes/PixverseTemplateNode.mdx b/zh/built-in-nodes/PixverseTemplateNode.mdx index 00d1264e1..4c822f79a 100644 --- a/zh/built-in-nodes/PixverseTemplateNode.mdx +++ b/zh/built-in-nodes/PixverseTemplateNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTemplateNode" icon: "circle" mode: wide --- + PixVerse 模板节点允许您从可用的模板中选择用于 PixVerse 视频生成的模板。它会将您选择的模板名称转换为 PixVerse API 创建视频所需的对应模板 ID。 ## 输入 @@ -17,7 +18,7 @@ PixVerse 模板节点允许您从可用的模板中选择用于 PixVerse 视频 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `pixverse_template` | 与所选模板名称对应的模板 ID，可供其他 PixVerse 节点用于视频生成。 | STRING | +| `Pixverse模板` | 与所选模板名称对应的模板 ID，可供其他 PixVerse 节点用于视频生成。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTemplateNode/zh.md) diff --git a/zh/built-in-nodes/PixverseTextToVideoNode.mdx b/zh/built-in-nodes/PixverseTextToVideoNode.mdx index 67f312577..b40262d3c 100644 --- a/zh/built-in-nodes/PixverseTextToVideoNode.mdx +++ b/zh/built-in-nodes/PixverseTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTextToVideoNode" icon: "circle" mode: wide --- + 根据文本提示和多种生成参数生成视频。此节点通过 PixVerse API 创建视频内容，支持控制宽高比、质量、时长、运动风格等。 ## 输入 diff --git a/zh/built-in-nodes/PixverseTransitionVideoNode.mdx b/zh/built-in-nodes/PixverseTransitionVideoNode.mdx index ed478236f..465acbc8e 100644 --- a/zh/built-in-nodes/PixverseTransitionVideoNode.mdx +++ b/zh/built-in-nodes/PixverseTransitionVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PixverseTransitionVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PixverseTransitionVideoNode/en.md) 使用 PixVerse API 在两幅输入图像之间生成过渡视频。您提供起始图像和结束图像，该节点会根据您的文本提示和所选设置，创建一段从一幅图像平滑过渡到另一幅图像的流畅视频。 diff --git a/zh/built-in-nodes/PolyexponentialScheduler.mdx b/zh/built-in-nodes/PolyexponentialScheduler.mdx index 97edfafb3..a51a77073 100644 --- a/zh/built-in-nodes/PolyexponentialScheduler.mdx +++ b/zh/built-in-nodes/PolyexponentialScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PolyexponentialScheduler" icon: "circle" mode: wide --- + PolyexponentialScheduler 节点旨在基于多指数噪声调度生成一系列噪声水平（sigma）。该调度是 sigma 对数的多项式函数，允许在扩散过程中灵活且可自定义地调整噪声水平的进展。 ## 输入 diff --git a/zh/built-in-nodes/PorterDuffImageComposite.mdx b/zh/built-in-nodes/PorterDuffImageComposite.mdx index ed5de39f9..93517c424 100644 --- a/zh/built-in-nodes/PorterDuffImageComposite.mdx +++ b/zh/built-in-nodes/PorterDuffImageComposite.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PorterDuffImageComposite" icon: "circle" mode: wide --- + PorterDuffImageComposite 节点旨在使用 Porter-Duff 合成运算符执行图像合成。它允许根据多种混合模式组合源图像和目标图像，通过操控图像透明度并以创意方式叠加图像，实现复杂的视觉效果。 ## 输入 diff --git a/zh/built-in-nodes/Preview3D.mdx b/zh/built-in-nodes/Preview3D.mdx index f3af12929..3b788fb0b 100644 --- a/zh/built-in-nodes/Preview3D.mdx +++ b/zh/built-in-nodes/Preview3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Preview3D" icon: "circle" mode: wide --- + Preview3D 节点主要用于预览 3D 模型输出。此节点接受两个输入：一个来自 Load3D 节点的 `camera_info`，另一个是 3D 模型文件的路径。模型文件路径必须位于 `ComfyUI/output` 文件夹中。 **支持的格式** diff --git a/zh/built-in-nodes/Preview3DAdvanced.mdx b/zh/built-in-nodes/Preview3DAdvanced.mdx index 2eb435044..fa1998ec0 100644 --- a/zh/built-in-nodes/Preview3DAdvanced.mdx +++ b/zh/built-in-nodes/Preview3DAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Preview3DAdvanced" icon: "circle" mode: wide --- -# 预览 3D（高级） 此节点提供高级 3D 模型预览功能，并输出相机和模型信息。它会将 3D 模型保存到临时文件并在界面中显示，同时将模型数据、相机信息和视口尺寸传递到下游进行进一步处理。 diff --git a/zh/built-in-nodes/Preview3DAnimation.mdx b/zh/built-in-nodes/Preview3DAnimation.mdx index b341b1149..5807c6129 100644 --- a/zh/built-in-nodes/Preview3DAnimation.mdx +++ b/zh/built-in-nodes/Preview3DAnimation.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Preview3DAnimation" icon: "circle" mode: wide --- + Preview3DAnimation 节点主要用于预览 3D 模型输出。此节点接受两个输入：一个来自 Load3D 节点的 `camera_info`，另一个是 3D 模型文件的路径。模型文件路径必须位于 `ComfyUI/output` 文件夹中。 **支持的格式** diff --git a/zh/built-in-nodes/PreviewAny.mdx b/zh/built-in-nodes/PreviewAny.mdx index 3c6107038..353c2de74 100644 --- a/zh/built-in-nodes/PreviewAny.mdx +++ b/zh/built-in-nodes/PreviewAny.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewAny" icon: "circle" mode: wide --- + PreviewAny 节点以文本格式显示任意输入数据类型的预览。它接受任何数据类型作为输入，并将其转换为可读的字符串表示形式以供查看。该节点会自动处理包括字符串、数字、布尔值和复杂对象在内的不同数据类型，尝试将其序列化为 JSON 格式。 ## 输入 diff --git a/zh/built-in-nodes/PreviewAudio.mdx b/zh/built-in-nodes/PreviewAudio.mdx index 993959814..b77453246 100644 --- a/zh/built-in-nodes/PreviewAudio.mdx +++ b/zh/built-in-nodes/PreviewAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewAudio" icon: "circle" mode: wide --- + PreviewAudio 节点会创建一个临时音频预览，可直接在界面中播放。它接收音频数据作为输入，并生成预览控件，使用户无需保存永久文件即可试听音频输出。 ## 输入 @@ -17,7 +18,7 @@ PreviewAudio 节点会创建一个临时音频预览，可直接在界面中播 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `ui` | 在界面中显示音频播放器控件，用于预览音频 | UI | +| `audio` | 在界面中显示音频播放器控件，用于预览音频 | UI | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/PreviewAudio/zh.md) diff --git a/zh/built-in-nodes/PreviewGaussianSplat.mdx b/zh/built-in-nodes/PreviewGaussianSplat.mdx index 51ce5b797..62cc0d58d 100644 --- a/zh/built-in-nodes/PreviewGaussianSplat.mdx +++ b/zh/built-in-nodes/PreviewGaussianSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PreviewGaussianSplat" icon: "circle" mode: wide --- -# PreviewGaussianSplat PreviewGaussianSplat 节点允许您在 ComfyUI 界面中预览 3D 高斯泼溅文件。它接受多种高斯泼溅格式的 3D 模型文件，并在 3D 预览窗口中渲染，同时将模型数据传递以供进一步处理。 diff --git a/zh/built-in-nodes/PreviewImage.mdx b/zh/built-in-nodes/PreviewImage.mdx index 7d14c47ba..d2c086e8e 100644 --- a/zh/built-in-nodes/PreviewImage.mdx +++ b/zh/built-in-nodes/PreviewImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PreviewImage" icon: "circle" mode: wide --- + PreviewImage 节点用于创建临时预览图像。它会自动为每张图像生成唯一的临时文件名，将图像压缩到指定级别，并保存到临时目录中。此功能特别适用于在处理过程中生成图像预览，而不会影响原始文件。 ## 输入 diff --git a/zh/built-in-nodes/PreviewPointCloud.mdx b/zh/built-in-nodes/PreviewPointCloud.mdx index 87da1153f..370c86399 100644 --- a/zh/built-in-nodes/PreviewPointCloud.mdx +++ b/zh/built-in-nodes/PreviewPointCloud.mdx @@ -5,7 +5,6 @@ sidebarTitle: "PreviewPointCloud" icon: "circle" mode: wide --- -# 预览点云 预览点云节点允许您在 ComfyUI 界面中查看 3D 点云文件。该节点将点云保存到临时文件，并在 3D 预览窗口中显示，同时传递模型数据和视口设置以供进一步处理。 diff --git a/zh/built-in-nodes/PrimitiveBoolean.mdx b/zh/built-in-nodes/PrimitiveBoolean.mdx index 734d3e22b..77b63fbf5 100644 --- a/zh/built-in-nodes/PrimitiveBoolean.mdx +++ b/zh/built-in-nodes/PrimitiveBoolean.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveBoolean" icon: "circle" mode: wide --- + 布尔节点提供了一种简单的方式，用于在工作流中传递布尔值（true/false）。它接收一个布尔输入值，并原样输出该值，使您能够控制其他节点中的布尔参数。 ## 输入 diff --git a/zh/built-in-nodes/PrimitiveBoundingBox.mdx b/zh/built-in-nodes/PrimitiveBoundingBox.mdx index 8ab28b227..3a9bc4c5d 100644 --- a/zh/built-in-nodes/PrimitiveBoundingBox.mdx +++ b/zh/built-in-nodes/PrimitiveBoundingBox.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveBoundingBox" icon: "circle" mode: wide --- + PrimitiveBoundingBox 节点创建一个由位置和大小定义的简单矩形区域。它接收左上角的 X 和 Y 坐标，以及宽度和高度值，并输出一个可供工作流中其他节点使用的边界框数据结构。 ## 输入 diff --git a/zh/built-in-nodes/PrimitiveFloat.mdx b/zh/built-in-nodes/PrimitiveFloat.mdx index c934bb9c4..c13a19ffa 100644 --- a/zh/built-in-nodes/PrimitiveFloat.mdx +++ b/zh/built-in-nodes/PrimitiveFloat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveFloat" icon: "circle" mode: wide --- + ## 概述 PrimitiveFloat 节点用于创建一个可在工作流中使用的浮点数值。它接收单个数值输入并输出相同的值，使您能够在 ComfyUI 流程中的不同节点之间定义和传递浮点数值。 diff --git a/zh/built-in-nodes/PrimitiveInt.mdx b/zh/built-in-nodes/PrimitiveInt.mdx index 10777108a..bc5f8fcdb 100644 --- a/zh/built-in-nodes/PrimitiveInt.mdx +++ b/zh/built-in-nodes/PrimitiveInt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveInt" icon: "circle" mode: wide --- + PrimitiveInt 节点提供了一种在工作流中处理整数值的简便方式。它接收一个整数输入并输出相同的值，便于在节点之间传递整数参数，或为其他操作设置特定的数值。 ## 输入 diff --git a/zh/built-in-nodes/PrimitiveString.mdx b/zh/built-in-nodes/PrimitiveString.mdx index 0a94774be..fffea16f7 100644 --- a/zh/built-in-nodes/PrimitiveString.mdx +++ b/zh/built-in-nodes/PrimitiveString.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveString" icon: "circle" mode: wide --- + 字符串节点提供了一种简单的方式，用于在工作流中输入和传递文本数据。它接收文本字符串作为输入，并原样输出相同的字符串，这对于向需要字符串参数的其他节点提供文本输入非常有用。 ## 输入 diff --git a/zh/built-in-nodes/PrimitiveStringMultiline.mdx b/zh/built-in-nodes/PrimitiveStringMultiline.mdx index 110090a51..744e22273 100644 --- a/zh/built-in-nodes/PrimitiveStringMultiline.mdx +++ b/zh/built-in-nodes/PrimitiveStringMultiline.mdx @@ -5,6 +5,7 @@ sidebarTitle: "PrimitiveStringMultiline" icon: "circle" mode: wide --- + PrimitiveStringMultiline 节点提供一个多行文本输入字段，用于在工作流中输入和传递字符串值。它接受支持多行的文本输入，并原样输出相同的字符串值。当您需要输入较长的文本内容或跨多行的格式化文本时，此节点非常有用。 ## 输入 diff --git a/zh/built-in-nodes/QuadrupleCLIPLoader.mdx b/zh/built-in-nodes/QuadrupleCLIPLoader.mdx index 512da9667..77a1f3dd7 100644 --- a/zh/built-in-nodes/QuadrupleCLIPLoader.mdx +++ b/zh/built-in-nodes/QuadrupleCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QuadrupleCLIPLoader" icon: "circle" mode: wide --- + ## 概述 四重 CLIP 加载器（QuadrupleCLIPLoader）是 ComfyUI 的核心节点之一，最初为支持 HiDream I1 版本模型而添加。如果发现此节点缺失，请尝试将 ComfyUI 更新至最新版本以确保节点支持。 diff --git a/zh/built-in-nodes/QuiverImageToSVGNode.mdx b/zh/built-in-nodes/QuiverImageToSVGNode.mdx index c25a933ad..8ef2940bc 100644 --- a/zh/built-in-nodes/QuiverImageToSVGNode.mdx +++ b/zh/built-in-nodes/QuiverImageToSVGNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QuiverImageToSVGNode" icon: "circle" mode: wide --- + 此节点使用 Quiver AI 的矢量化模型，将光栅图像转换为可缩放矢量图形（SVG）。它会将图像发送到外部 API，由该 API 处理并返回矢量化结果。 ## 输入 diff --git a/zh/built-in-nodes/QuiverTextToSVGNode.mdx b/zh/built-in-nodes/QuiverTextToSVGNode.mdx index fbfb2a03d..42b0fa795 100644 --- a/zh/built-in-nodes/QuiverTextToSVGNode.mdx +++ b/zh/built-in-nodes/QuiverTextToSVGNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "QuiverTextToSVGNode" icon: "circle" mode: wide --- -# Quiver 文本转 SVG 节点 此节点使用 Quiver AI 的模型，根据文本描述生成可缩放矢量图形（SVG）图像。您可以选择提供参考图像和样式指令来指导生成过程。 diff --git a/zh/built-in-nodes/QwenImageDiffsynthControlnet.mdx b/zh/built-in-nodes/QwenImageDiffsynthControlnet.mdx index 2892ddda5..67b22ea62 100644 --- a/zh/built-in-nodes/QwenImageDiffsynthControlnet.mdx +++ b/zh/built-in-nodes/QwenImageDiffsynthControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "QwenImageDiffsynthControlnet" icon: "circle" mode: wide --- + QwenImageDiffsynthControlnet 节点应用扩散合成控制网络补丁来修改基础模型的行为。它使用图像输入和可选的遮罩，以可调节的强度引导模型的生成过程，创建一个融合了控制网络影响的补丁模型，从而实现更可控的图像合成。 ## 输入 diff --git a/zh/built-in-nodes/RTDETR_detect.mdx b/zh/built-in-nodes/RTDETR_detect.mdx index 8c3598505..49105dcb0 100644 --- a/zh/built-in-nodes/RTDETR_detect.mdx +++ b/zh/built-in-nodes/RTDETR_detect.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RTDETR_detect" icon: "circle" mode: wide --- + RT-DETR 检测节点使用 RT-DETR 模型对输入图像执行目标检测。它能识别物体、绘制边界框，并根据 COCO 数据集类别进行标注。您可以根据置信度分数、目标类别进行过滤，并限制检测总数。 ## 输入 @@ -21,7 +22,7 @@ RT-DETR 检测节点使用 RT-DETR 模型对输入图像执行目标检测。它 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `bboxes` | 每个输入图像的边界框列表。每个框包含坐标 (x, y, 宽度, 高度)、类别标签和置信度分数。 | BOUNDINGBOX | +| `边界框` | 每个输入图像的边界框列表。每个框包含坐标 (x, y, 宽度, 高度)、类别标签和置信度分数。 | BOUNDINGBOX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RTDETR_detect/zh.md) diff --git a/zh/built-in-nodes/RandomCropImages.mdx b/zh/built-in-nodes/RandomCropImages.mdx index 244cd6385..7be2f0323 100644 --- a/zh/built-in-nodes/RandomCropImages.mdx +++ b/zh/built-in-nodes/RandomCropImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RandomCropImages" icon: "circle" mode: wide --- + 随机裁剪图像节点从每张输入图像中随机选取一个矩形区域，并将其裁剪为指定的宽度和高度。该操作常用于数据增强，以生成训练图像的变体。裁剪的随机位置由种子值决定，确保相同的裁剪结果可以复现。 ## 输入 @@ -22,7 +23,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `image` | 应用随机裁剪后得到的图像。 | IMAGE | +| `图像` | 应用随机裁剪后得到的图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RandomCropImages/zh.md) diff --git a/zh/built-in-nodes/RandomNoise.mdx b/zh/built-in-nodes/RandomNoise.mdx index afce07551..369d7c972 100644 --- a/zh/built-in-nodes/RandomNoise.mdx +++ b/zh/built-in-nodes/RandomNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RandomNoise" icon: "circle" mode: wide --- + RandomNoise节点根据种子值生成随机噪声模式。它创建可复现的噪声，可用于各种图像处理和生成任务。相同的种子将始终产生相同的噪声模式，确保多次运行结果一致。 ## 输入 diff --git a/zh/built-in-nodes/RebatchImages.mdx b/zh/built-in-nodes/RebatchImages.mdx index 115fc8249..162fb7a7d 100644 --- a/zh/built-in-nodes/RebatchImages.mdx +++ b/zh/built-in-nodes/RebatchImages.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RebatchImages" icon: "circle" mode: wide --- + RebatchImages 节点旨在将一批图像重新组织为新的批次配置，并按指定调整批次大小。此过程对于管理和优化批量操作中的图像数据处理至关重要，可确保图像根据所需的批次大小进行分组，从而实现高效处理。 ## 输入 diff --git a/zh/built-in-nodes/RebatchLatents.mdx b/zh/built-in-nodes/RebatchLatents.mdx index 382068a70..03f836249 100644 --- a/zh/built-in-nodes/RebatchLatents.mdx +++ b/zh/built-in-nodes/RebatchLatents.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RebatchLatents" icon: "circle" mode: wide --- + RebatchLatents 节点旨在根据指定的批次大小，将一批潜在表示重新组织为新的批次配置。该节点确保潜在样本被适当分组，并处理维度与尺寸的变化，以支持后续处理或模型推理。 ## 输入 diff --git a/zh/built-in-nodes/RecordAudio.mdx b/zh/built-in-nodes/RecordAudio.mdx index c9e81f8f5..8cdfe7d59 100644 --- a/zh/built-in-nodes/RecordAudio.mdx +++ b/zh/built-in-nodes/RecordAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecordAudio" icon: "circle" mode: wide --- + RecordAudio 节点用于加载通过音频录制界面录制或选择的音频文件。它会处理音频文件，并将其转换为工作流中其他音频处理节点可用的波形格式。该节点会自动检测采样率，并准备好音频数据以供进一步处理。 ## 输入 diff --git a/zh/built-in-nodes/RecraftColorRGB.mdx b/zh/built-in-nodes/RecraftColorRGB.mdx index 3c0fb62a6..2097a8b1b 100644 --- a/zh/built-in-nodes/RecraftColorRGB.mdx +++ b/zh/built-in-nodes/RecraftColorRGB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftColorRGB" icon: "circle" mode: wide --- + 通过指定独立的红、绿、蓝数值创建 Recraft 颜色。此节点接收 RGB 整数值（0-255），并将其转换为可在其他 Recraft 操作中使用的 Recraft 颜色格式。您还可以选择提供现有的 Recraft 颜色链，以将新颜色扩展至其中。 ## 输入 diff --git a/zh/built-in-nodes/RecraftControls.mdx b/zh/built-in-nodes/RecraftControls.mdx index 346b7089c..99fe10520 100644 --- a/zh/built-in-nodes/RecraftControls.mdx +++ b/zh/built-in-nodes/RecraftControls.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftControls" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftControls/en.md) 创建用于自定义 Recraft 生成的 Recraft 控件。此节点允许您配置将在 Recraft 图像生成过程中使用的颜色设置。 @@ -20,7 +21,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `recraft_controls` | 包含颜色设置的已配置 Recraft 控件 | CONTROLS | +| `Recraft控制` | 包含颜色设置的已配置 Recraft 控件 | CONTROLS | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftControls/zh.md) diff --git a/zh/built-in-nodes/RecraftCreateStyleNode.mdx b/zh/built-in-nodes/RecraftCreateStyleNode.mdx index 89431a045..11e143df4 100644 --- a/zh/built-in-nodes/RecraftCreateStyleNode.mdx +++ b/zh/built-in-nodes/RecraftCreateStyleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCreateStyleNode" icon: "circle" mode: wide --- + 此节点通过上传参考图像创建用于图像生成的定制风格。您可以上传1到5张图像来定义新风格，节点将返回一个唯一的风格ID，该ID可与其他Recraft节点配合使用。所有上传图像的总文件大小不得超过5 MB。 ## 输入 @@ -20,7 +21,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `style_id` | 新创建的定制风格的唯一标识符。 | STRING | +| `风格ID` | 新创建的定制风格的唯一标识符。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreateStyleNode/zh.md) diff --git a/zh/built-in-nodes/RecraftCreativeUpscaleNode.mdx b/zh/built-in-nodes/RecraftCreativeUpscaleNode.mdx index 0bcc72dce..a2b2dbe25 100644 --- a/zh/built-in-nodes/RecraftCreativeUpscaleNode.mdx +++ b/zh/built-in-nodes/RecraftCreativeUpscaleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCreativeUpscaleNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCreativeUpscaleNode/en.md) Recraft 创意放大节点通过提高分辨率来增强光栅图像。它采用"创意放大"流程，专注于改善图像中的微小细节和面部特征。此操作通过外部 API 同步执行。 diff --git a/zh/built-in-nodes/RecraftCrispUpscaleNode.mdx b/zh/built-in-nodes/RecraftCrispUpscaleNode.mdx index 9fc513c47..fb88b6dc2 100644 --- a/zh/built-in-nodes/RecraftCrispUpscaleNode.mdx +++ b/zh/built-in-nodes/RecraftCrispUpscaleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftCrispUpscaleNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftCrispUpscaleNode/en.md) 同步放大图像。使用“清晰放大”工具增强给定的光栅图像，提高图像分辨率，使图像更清晰、更干净。 diff --git a/zh/built-in-nodes/RecraftImageInpaintingNode.mdx b/zh/built-in-nodes/RecraftImageInpaintingNode.mdx index 0ae12b0c9..9bca5db32 100644 --- a/zh/built-in-nodes/RecraftImageInpaintingNode.mdx +++ b/zh/built-in-nodes/RecraftImageInpaintingNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftImageInpaintingNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftImageInpaintingNode/en.md) 此节点根据文本提示和遮罩修改图像的特定区域。它使用 Recraft API 智能编辑仅遮罩区域，同时保持图像其余部分不变。 diff --git a/zh/built-in-nodes/RecraftImageToImageNode.mdx b/zh/built-in-nodes/RecraftImageToImageNode.mdx index 480cfe9d6..b3e9e8e9d 100644 --- a/zh/built-in-nodes/RecraftImageToImageNode.mdx +++ b/zh/built-in-nodes/RecraftImageToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftImageToImageNode" icon: "circle" mode: wide --- + 此节点根据文本提示和强度参数修改现有图像。它使用 Recraft API 根据提供的描述转换输入图像，同时根据强度设置保持与原始图像的一定相似度。 ## 输入 diff --git a/zh/built-in-nodes/RecraftRemoveBackgroundNode.mdx b/zh/built-in-nodes/RecraftRemoveBackgroundNode.mdx index 83b19e113..bd8d971d1 100644 --- a/zh/built-in-nodes/RecraftRemoveBackgroundNode.mdx +++ b/zh/built-in-nodes/RecraftRemoveBackgroundNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftRemoveBackgroundNode" icon: "circle" mode: wide --- + 此节点使用 Recraft API 服务移除图像背景。它会处理输入批次中的每张图像，并返回带有透明背景的处理后图像，以及指示已移除背景区域的对应 Alpha 遮罩。 ## 输入 diff --git a/zh/built-in-nodes/RecraftReplaceBackgroundNode.mdx b/zh/built-in-nodes/RecraftReplaceBackgroundNode.mdx index 316f72667..3c53d27b3 100644 --- a/zh/built-in-nodes/RecraftReplaceBackgroundNode.mdx +++ b/zh/built-in-nodes/RecraftReplaceBackgroundNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftReplaceBackgroundNode" icon: "circle" mode: wide --- + 根据提供的提示词替换图像背景。此节点使用 Recraft API 根据您的文本描述为图像生成新背景，让您能够在保持主体不变的同时彻底改变背景。 ## 输入 diff --git a/zh/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx b/zh/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx index 499053f68..304e1a345 100644 --- a/zh/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx +++ b/zh/built-in-nodes/RecraftStyleV3DigitalIllustration.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3DigitalIllustration" icon: "circle" mode: wide --- + 此节点用于配置 Recraft API 使用的样式，专门选择"数字插画"风格。您可以选择一个可选的子风格，进一步细化生成图像的艺术方向。 ## 输入 @@ -17,7 +18,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `recraft_style` | 一个配置好的样式对象，包含所选的"digital_illustration"风格和可选的子风格，可传递给其他 Recraft API 节点使用。 | STYLEV3 | +| `Recraft风格` | 一个配置好的样式对象，包含所选的"digital_illustration"风格和可选的子风格，可传递给其他 Recraft API 节点使用。 | STYLEV3 | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3DigitalIllustration/zh.md) diff --git a/zh/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx b/zh/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx index 1d4259794..056c848e9 100644 --- a/zh/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx +++ b/zh/built-in-nodes/RecraftStyleV3InfiniteStyleLibrary.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3InfiniteStyleLibrary" icon: "circle" mode: wide --- + 此节点允许您使用已有的 UUID 从 Recraft 的无限样式库中选择一种样式。它根据提供的样式标识符检索样式信息，并将其返回以供其他 Recraft 节点使用。 ## 输入 @@ -19,7 +20,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `recraft_style` | 从 Recraft 无限样式库中选择的样式对象 | STYLEV3 | +| `Recraft风格` | 从 Recraft 无限样式库中选择的样式对象 | STYLEV3 | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3InfiniteStyleLibrary/zh.md) diff --git a/zh/built-in-nodes/RecraftStyleV3LogoRaster.mdx b/zh/built-in-nodes/RecraftStyleV3LogoRaster.mdx index d125bf3cf..537a3f6f0 100644 --- a/zh/built-in-nodes/RecraftStyleV3LogoRaster.mdx +++ b/zh/built-in-nodes/RecraftStyleV3LogoRaster.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3LogoRaster" icon: "circle" mode: wide --- + 此节点用于选择标志光栅样式及可选子样式，以生成标志图像。它专注于通过基于光栅的视觉处理方式创建标志设计。 ## 输入 @@ -17,7 +18,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `recraft_style` | 所选的 Recraft 样式配置，包含标志光栅样式及选定的子样式 | CUSTOM | +| `Recraft风格` | 所选的 Recraft 样式配置，包含标志光栅样式及选定的子样式 | CUSTOM | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3LogoRaster/zh.md) diff --git a/zh/built-in-nodes/RecraftStyleV3RealisticImage.mdx b/zh/built-in-nodes/RecraftStyleV3RealisticImage.mdx index 3cf1eb2cb..67b45ae05 100644 --- a/zh/built-in-nodes/RecraftStyleV3RealisticImage.mdx +++ b/zh/built-in-nodes/RecraftStyleV3RealisticImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3RealisticImage" icon: "circle" mode: wide --- + 此节点用于创建生成逼真图像的样式配置，通过 Recraft 的 API 实现。它选择 `realistic_image` 样式，并允许您选择可选的子样式来微调输出外观。 ## 输入 @@ -17,7 +18,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `recraft_style` | 一个 Recraft 样式配置对象，包含 `realistic_image` 样式和所选子样式设置。此输出可连接到其他接受样式输入的 Recraft 节点。 | STYLEV3 | +| `Recraft风格` | 一个 Recraft 样式配置对象，包含 `realistic_image` 样式和所选子样式设置。此输出可连接到其他接受样式输入的 Recraft 节点。 | STYLEV3 | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RecraftStyleV3RealisticImage/zh.md) diff --git a/zh/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx b/zh/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx index c25e60855..92e968529 100644 --- a/zh/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx +++ b/zh/built-in-nodes/RecraftStyleV3VectorIllustrationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftStyleV3VectorIllustrationNode" icon: "circle" mode: wide --- + 此节点用于配置 Recraft API 使用的样式，专门选择 `vector_illustration` 风格。您可以选择性地在该类别中指定更具体的子风格。节点输出一个样式配置对象，可传递给其他 Recraft API 节点。 ## 输入 diff --git a/zh/built-in-nodes/RecraftTextToImageNode.mdx b/zh/built-in-nodes/RecraftTextToImageNode.mdx index 72044ca66..28f8955a6 100644 --- a/zh/built-in-nodes/RecraftTextToImageNode.mdx +++ b/zh/built-in-nodes/RecraftTextToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftTextToImageNode" icon: "circle" mode: wide --- + 根据提示和分辨率同步生成图像。此节点连接到 Recraft API，根据文本描述创建图像，并支持指定尺寸以及可选的样式和控制参数。 ## 输入 diff --git a/zh/built-in-nodes/RecraftTextToVectorNode.mdx b/zh/built-in-nodes/RecraftTextToVectorNode.mdx index 2e391a993..db66bcd2c 100644 --- a/zh/built-in-nodes/RecraftTextToVectorNode.mdx +++ b/zh/built-in-nodes/RecraftTextToVectorNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftTextToVectorNode" icon: "circle" mode: wide --- + 此节点根据文本提示和分辨率同步生成 SVG 矢量插图。它会将您的提示发送到 Recraft API，并返回生成的 SVG 内容。 ## 输入 diff --git a/zh/built-in-nodes/RecraftV4TextToImageNode.mdx b/zh/built-in-nodes/RecraftV4TextToImageNode.mdx index 32f3554c1..f9b588928 100644 --- a/zh/built-in-nodes/RecraftV4TextToImageNode.mdx +++ b/zh/built-in-nodes/RecraftV4TextToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftV4TextToImageNode" icon: "circle" mode: wide --- + 此节点使用 Recraft V4 或 V4 Pro AI 模型，根据文本描述生成图像。它会将您的提示词发送至外部 API，并返回生成的图像。您可以通过指定模型、图像尺寸和生成数量来控制输出。 ## 输入 diff --git a/zh/built-in-nodes/RecraftV4TextToVectorNode.mdx b/zh/built-in-nodes/RecraftV4TextToVectorNode.mdx index be82819aa..f357c578e 100644 --- a/zh/built-in-nodes/RecraftV4TextToVectorNode.mdx +++ b/zh/built-in-nodes/RecraftV4TextToVectorNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftV4TextToVectorNode" icon: "circle" mode: wide --- + Recraft V4 文本转矢量节点可根据文本描述生成可缩放矢量图形（SVG）插图。该节点连接外部 API，使用 Recraft V4 或 Recraft V4 Pro 模型进行图像生成。节点根据您的提示词输出一个或多个 SVG 图像。 ## 输入 diff --git a/zh/built-in-nodes/RecraftVectorizeImageNode.mdx b/zh/built-in-nodes/RecraftVectorizeImageNode.mdx index ae7ae8ba2..beca41b14 100644 --- a/zh/built-in-nodes/RecraftVectorizeImageNode.mdx +++ b/zh/built-in-nodes/RecraftVectorizeImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RecraftVectorizeImageNode" icon: "circle" mode: wide --- + 从输入图像同步生成 SVG。此节点通过处理输入批次中的每张图像，并将结果合并为单个 SVG 输出来将光栅图像转换为矢量图形格式。 ## 输入 diff --git a/zh/built-in-nodes/ReferenceLatent.mdx b/zh/built-in-nodes/ReferenceLatent.mdx index 5ebd37403..778af987b 100644 --- a/zh/built-in-nodes/ReferenceLatent.mdx +++ b/zh/built-in-nodes/ReferenceLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReferenceLatent" icon: "circle" mode: wide --- + 此节点为编辑模型设置引导潜空间。它接收条件化数据和可选的潜空间输入，然后修改条件化数据以包含参考潜空间信息。如果模型支持，您可以串联多个 ReferenceLatent 节点来设置多个参考图像。 ## 输入 diff --git a/zh/built-in-nodes/ReferenceTimbreAudio.mdx b/zh/built-in-nodes/ReferenceTimbreAudio.mdx index d34b83e71..953e78b09 100644 --- a/zh/built-in-nodes/ReferenceTimbreAudio.mdx +++ b/zh/built-in-nodes/ReferenceTimbreAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReferenceTimbreAudio" icon: "circle" mode: wide --- + 此节点设置参考音频音色，用于"ace step 1.5"流程。它通过接收 conditioning 输入和可选的音频潜在表示，将该潜在数据附加到 conditioning 中，供工作流中的后续节点使用。 ## 输入 diff --git a/zh/built-in-nodes/RegexExtract.mdx b/zh/built-in-nodes/RegexExtract.mdx index c8153dc9d..d1bf073af 100644 --- a/zh/built-in-nodes/RegexExtract.mdx +++ b/zh/built-in-nodes/RegexExtract.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexExtract" icon: "circle" mode: wide --- + RegexExtract 节点使用正则表达式在文本中搜索模式。它可以查找第一个匹配项、所有匹配项、匹配项中的特定分组，或跨多个匹配项的所有分组。该节点支持多种正则表达式标志，用于控制大小写敏感性、多行匹配和点号匹配换行符的行为。 ## 输入 diff --git a/zh/built-in-nodes/RegexMatch.mdx b/zh/built-in-nodes/RegexMatch.mdx index acc363fcc..84ab997f0 100644 --- a/zh/built-in-nodes/RegexMatch.mdx +++ b/zh/built-in-nodes/RegexMatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexMatch" icon: "circle" mode: wide --- + RegexMatch 节点用于检查文本字符串是否包含与给定正则表达式模式匹配的内容。它会搜索输入字符串，并返回一个简单的"是/否"结果，指示该模式是否在文本中的任何位置被找到。您可以通过启用不区分大小写匹配或多行模式等选项来调整搜索方式。 ## 输入 @@ -21,7 +22,7 @@ RegexMatch 节点用于检查文本字符串是否包含与给定正则表达式 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `matches` | 如果正则表达式模式匹配输入字符串的任何部分，则返回 True，否则返回 False | BOOLEAN | +| `匹配结果` | 如果正则表达式模式匹配输入字符串的任何部分，则返回 True，否则返回 False | BOOLEAN | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RegexMatch/zh.md) diff --git a/zh/built-in-nodes/RegexReplace.mdx b/zh/built-in-nodes/RegexReplace.mdx index d2afc9a01..7b2d9c48e 100644 --- a/zh/built-in-nodes/RegexReplace.mdx +++ b/zh/built-in-nodes/RegexReplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RegexReplace" icon: "circle" mode: wide --- + RegexReplace 节点使用正则表达式模式在字符串中查找和替换文本。它允许您搜索文本模式并将其替换为新文本，并提供选项来控制模式匹配的工作方式，包括大小写敏感性、多行匹配以及限制替换次数。 ## 输入 diff --git a/zh/built-in-nodes/RemoveBackground.mdx b/zh/built-in-nodes/RemoveBackground.mdx index 587513722..c1076f5a5 100644 --- a/zh/built-in-nodes/RemoveBackground.mdx +++ b/zh/built-in-nodes/RemoveBackground.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RemoveBackground" icon: "circle" mode: wide --- + ## 概述 移除背景节点使用背景移除模型生成遮罩，将输入图像中的前景主体与背景分离。该节点接收一张图像和一个背景移除模型，然后生成突出显示主要主体的遮罩。 diff --git a/zh/built-in-nodes/RenderSplat.mdx b/zh/built-in-nodes/RenderSplat.mdx index 54d153034..c96169f1f 100644 --- a/zh/built-in-nodes/RenderSplat.mdx +++ b/zh/built-in-nodes/RenderSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "RenderSplat" icon: "circle" mode: wide --- -# 渲染高斯泼溅 使用各向异性EWA光栅化器将高斯泼溅渲染为图像，该光栅化器采用定向椭圆泼溅、抗锯齿和从前到后的深度排序渲染。相机来自 `camera_info` 输入，或者您可以将其留空以自动框选泼溅。将帧数设置为大于1，可生成用于输入视频节点的转盘批量图像。 @@ -30,7 +29,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | |-------------|-------------|-----------| -| `mask` | 高斯泼溅的渲染图像 | IMAGE | +| `图像` | 高斯泼溅的渲染图像 | IMAGE | | `mask` | 渲染泼溅的 Alpha 遮罩 | MASK | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RenderSplat/zh.md) diff --git a/zh/built-in-nodes/RenormCFG.mdx b/zh/built-in-nodes/RenormCFG.mdx index c8472947d..9b2617199 100644 --- a/zh/built-in-nodes/RenormCFG.mdx +++ b/zh/built-in-nodes/RenormCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RenormCFG" icon: "circle" mode: wide --- + RenormCFG 节点通过应用条件缩放和归一化，修改扩散模型中的无分类器引导（CFG）过程。它根据指定的时间步长阈值和重归一化因子调整去噪过程，从而在图像生成过程中控制条件预测与无条件预测的影响。 ## 输入 diff --git a/zh/built-in-nodes/RepeatImageBatch.mdx b/zh/built-in-nodes/RepeatImageBatch.mdx index 4168bb3f7..54834b1b5 100644 --- a/zh/built-in-nodes/RepeatImageBatch.mdx +++ b/zh/built-in-nodes/RepeatImageBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RepeatImageBatch" icon: "circle" mode: wide --- + RepeatImageBatch 节点旨在将指定图像复制指定次数，从而创建一批相同的图像。此功能适用于需要同一图像多个实例的操作，例如批量处理或数据增强。 ## 输入 diff --git a/zh/built-in-nodes/RepeatLatentBatch.mdx b/zh/built-in-nodes/RepeatLatentBatch.mdx index 83e366d8a..a18959d67 100644 --- a/zh/built-in-nodes/RepeatLatentBatch.mdx +++ b/zh/built-in-nodes/RepeatLatentBatch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RepeatLatentBatch" icon: "circle" mode: wide --- + RepeatLatentBatch 节点用于将给定的潜在表示批次按指定次数复制，并可包含噪声掩码和批次索引等附加数据。此功能对于需要同一潜在数据多个实例的操作（如数据增强或特定生成任务）至关重要。 ## 输入 diff --git a/zh/built-in-nodes/ReplaceText.mdx b/zh/built-in-nodes/ReplaceText.mdx index 162735be2..5170c38aa 100644 --- a/zh/built-in-nodes/ReplaceText.mdx +++ b/zh/built-in-nodes/ReplaceText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReplaceText" icon: "circle" mode: wide --- + 替换文本节点执行简单的文本替换操作。它会在输入文本中搜索指定的文本片段，并将每次出现的内容替换为新的文本片段。该操作将应用于提供给节点的所有文本输入。 ## 输入 @@ -19,7 +20,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `text` | 处理后的文本，其中所有 `搜索` 文本的出现位置均被替换为 `替换` 文本。 | STRING | +| `文本` | 处理后的文本，其中所有 `搜索` 文本的出现位置均被替换为 `替换` 文本。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ReplaceText/zh.md) diff --git a/zh/built-in-nodes/ReplaceVideoLatentFrames.mdx b/zh/built-in-nodes/ReplaceVideoLatentFrames.mdx index 6c0fd472c..4e366bb53 100644 --- a/zh/built-in-nodes/ReplaceVideoLatentFrames.mdx +++ b/zh/built-in-nodes/ReplaceVideoLatentFrames.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReplaceVideoLatentFrames" icon: "circle" mode: wide --- + ReplaceVideoLatentFrames 节点可将源潜在视频中的帧插入到目标潜在视频中，从指定的帧索引开始。如果未提供源潜在视频，则直接返回未修改的目标潜在视频。该节点支持负索引，并在源帧无法完全放入目标视频时发出警告。 ## 输入 diff --git a/zh/built-in-nodes/Reroute.mdx b/zh/built-in-nodes/Reroute.mdx index 038dab162..eaef09fc1 100644 --- a/zh/built-in-nodes/Reroute.mdx +++ b/zh/built-in-nodes/Reroute.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Reroute" icon: "circle" mode: wide --- + 节点名称：Reroute 节点 节点用途：主要用于整理 ComfyUI 工作流中过长的连接线逻辑。 diff --git a/zh/built-in-nodes/RescaleCFG.mdx b/zh/built-in-nodes/RescaleCFG.mdx index 73740fda8..07dd59564 100644 --- a/zh/built-in-nodes/RescaleCFG.mdx +++ b/zh/built-in-nodes/RescaleCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RescaleCFG" icon: "circle" mode: wide --- + RescaleCFG 节点旨在根据指定的乘数调整模型输出的条件与非条件缩放比例，以实现更平衡且可控的生成过程。其工作原理是对模型输出进行重新缩放，以修改条件与非条件分量的影响，从而可能提升模型的性能或输出质量。 ## 输入 diff --git a/zh/built-in-nodes/ResizeAndPadImage.mdx b/zh/built-in-nodes/ResizeAndPadImage.mdx index 3269a7da4..88127a1ee 100644 --- a/zh/built-in-nodes/ResizeAndPadImage.mdx +++ b/zh/built-in-nodes/ResizeAndPadImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeAndPadImage" icon: "circle" mode: wide --- + ResizeAndPadImage 节点用于将图像调整至指定尺寸范围内，同时保持原始宽高比。它会按比例缩小图像以适配目标宽度和高度，然后在边缘添加填充以填补剩余空间。填充颜色和插值方法可自定义，以控制填充区域的外观和缩放质量。 ## 输入 diff --git a/zh/built-in-nodes/ResizeImageMaskNode.mdx b/zh/built-in-nodes/ResizeImageMaskNode.mdx index fdd93bc29..dc9e9b478 100644 --- a/zh/built-in-nodes/ResizeImageMaskNode.mdx +++ b/zh/built-in-nodes/ResizeImageMaskNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImageMaskNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImageMaskNode/en.md) 调整图像/遮罩节点提供了多种方法来更改输入图像或遮罩的尺寸。它可以通过倍数缩放、设置特定尺寸、匹配另一个输入的尺寸，或根据像素数量进行调整，并使用多种插值方法来保证质量。 @@ -31,7 +32,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `resized` | 调整大小后的图像或遮罩，与输入的数据类型一致。 | IMAGE 或 MASK | +| `已调整大小` | 调整大小后的图像或遮罩，与输入的数据类型一致。 | IMAGE 或 MASK | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImageMaskNode/zh.md) diff --git a/zh/built-in-nodes/ResizeImagesByLongerEdge.mdx b/zh/built-in-nodes/ResizeImagesByLongerEdge.mdx index e8a699386..c0b3ce9d7 100644 --- a/zh/built-in-nodes/ResizeImagesByLongerEdge.mdx +++ b/zh/built-in-nodes/ResizeImagesByLongerEdge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImagesByLongerEdge" icon: "circle" mode: wide --- + 按较长边调整图像大小节点可调整一个或多个图像的尺寸，使其最长边与指定的目标长度匹配。它会自动判断宽度或高度中哪一边更长，并按比例缩放另一边，以保持原始宽高比。这对于根据图像的最大维度标准化图像尺寸非常有用。 ## 输入 @@ -18,7 +19,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `image` | 调整大小后的图像或图像批次。输出图像数量与输入相同，每张图像的较长边均与指定的 `长边` 长度匹配。 | IMAGE | +| `图像` | 调整大小后的图像或图像批次。输出图像数量与输入相同，每张图像的较长边均与指定的 `长边` 长度匹配。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByLongerEdge/zh.md) diff --git a/zh/built-in-nodes/ResizeImagesByShorterEdge.mdx b/zh/built-in-nodes/ResizeImagesByShorterEdge.mdx index e717815bc..82a482b1f 100644 --- a/zh/built-in-nodes/ResizeImagesByShorterEdge.mdx +++ b/zh/built-in-nodes/ResizeImagesByShorterEdge.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResizeImagesByShorterEdge" icon: "circle" mode: wide --- + 此节点用于调整图像大小，使较短边匹配指定长度，同时保持原始宽高比。它根据较短边的目标长度计算新尺寸，并返回调整后的图像。 ## 输入 @@ -18,7 +19,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `image` | 调整大小后的图像，其较短边与指定的目标长度匹配。 | IMAGE | +| `图像` | 调整大小后的图像，其较短边与指定的目标长度匹配。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResizeImagesByShorterEdge/zh.md) diff --git a/zh/built-in-nodes/ResolutionBucket.mdx b/zh/built-in-nodes/ResolutionBucket.mdx index 61c486621..dfe5da32d 100644 --- a/zh/built-in-nodes/ResolutionBucket.mdx +++ b/zh/built-in-nodes/ResolutionBucket.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResolutionBucket" icon: "circle" mode: wide --- + 此节点根据分辨率整理潜在图像列表及其对应的条件数据。它将具有相同高度和宽度的项目分组，为每个独特分辨率创建独立的批次。此过程有助于为高效训练准备数据，使模型能够同时处理多个相同尺寸的项目。 ## 输入 @@ -20,7 +21,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `条件` | 按分辨率分桶后的批处理潜在字典列表，每个分辨率桶对应一个。 | LATENT | +| `Latent` | 按分辨率分桶后的批处理潜在字典列表，每个分辨率桶对应一个。 | LATENT | | `条件` | 条件列表的列表，每个分辨率桶对应一个。 | CONDITIONING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResolutionBucket/zh.md) diff --git a/zh/built-in-nodes/ResolutionSelector.mdx b/zh/built-in-nodes/ResolutionSelector.mdx index 2432c684d..a2f4698b9 100644 --- a/zh/built-in-nodes/ResolutionSelector.mdx +++ b/zh/built-in-nodes/ResolutionSelector.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ResolutionSelector" icon: "circle" mode: wide --- + 分辨率选择器节点根据选定的宽高比和目标总分辨率（以百万像素为单位）计算图像的像素宽度和高度。它有助于为其他节点（如空潜像节点）生成一致的尺寸。输出尺寸始终四舍五入到最接近的8的倍数。 ## 输入 @@ -18,8 +19,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `高度` | 计算出的像素宽度，为8的倍数。 | INT | -| `height` | 计算出的像素高度，为8的倍数。 | INT | +| `宽度` | 计算出的像素宽度，为8的倍数。 | INT | +| `高度` | 计算出的像素高度，为8的倍数。 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ResolutionSelector/zh.md) diff --git a/zh/built-in-nodes/ReveImageCreateNode.mdx b/zh/built-in-nodes/ReveImageCreateNode.mdx index 2665a47c1..0096e0f81 100644 --- a/zh/built-in-nodes/ReveImageCreateNode.mdx +++ b/zh/built-in-nodes/ReveImageCreateNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReveImageCreateNode" icon: "circle" mode: wide --- + Reve Image Create 节点使用 Reve AI 模型根据文本描述生成图像。它将文本提示发送到 Reve API，并返回生成的图像。您可以控制图像的宽高比，并应用可选的后期处理效果（如放大）。 ## 输入 diff --git a/zh/built-in-nodes/ReveImageEditNode.mdx b/zh/built-in-nodes/ReveImageEditNode.mdx index 687148cad..16fcf893e 100644 --- a/zh/built-in-nodes/ReveImageEditNode.mdx +++ b/zh/built-in-nodes/ReveImageEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReveImageEditNode" icon: "circle" mode: wide --- + Reve 图像编辑节点允许您根据文本描述修改现有图像。它使用 Reve API 来解读您的指令，并对您提供的图像应用所请求的更改。 ## 输入 diff --git a/zh/built-in-nodes/ReveImageRemixNode.mdx b/zh/built-in-nodes/ReveImageRemixNode.mdx index c3e663519..5cfa2632d 100644 --- a/zh/built-in-nodes/ReveImageRemixNode.mdx +++ b/zh/built-in-nodes/ReveImageRemixNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ReveImageRemixNode" icon: "circle" mode: wide --- + Reve Image Remix 节点使用 Reve API 生成新图像。它结合一张或多张参考图像与文本提示，根据提供的描述创建新的混搭图像。 ## 输入 diff --git a/zh/built-in-nodes/Rodin3D_Detail.mdx b/zh/built-in-nodes/Rodin3D_Detail.mdx index c283dcfe1..42e570744 100644 --- a/zh/built-in-nodes/Rodin3D_Detail.mdx +++ b/zh/built-in-nodes/Rodin3D_Detail.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Detail" icon: "circle" mode: wide --- + Rodin 3D 细节生成节点通过 Rodin API 生成高细节的 3D 资产。它接收输入图像，并通过 Rodin 服务进行处理，以创建具有精细几何结构和材质的高质量 3D 模型。该节点处理从任务创建到下载最终 3D 模型文件的完整工作流程。 ## 输入 diff --git a/zh/built-in-nodes/Rodin3D_Gen2.mdx b/zh/built-in-nodes/Rodin3D_Gen2.mdx index ef8b91a28..be7ba5efd 100644 --- a/zh/built-in-nodes/Rodin3D_Gen2.mdx +++ b/zh/built-in-nodes/Rodin3D_Gen2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen2" icon: "circle" mode: wide --- + Rodin3D_Gen2 节点使用 Rodin API 生成 3D 资产。它接收输入图像，并将其转换为具有不同材质类型和多边形数量的 3D 模型。该节点自动处理整个生成过程，包括任务创建、状态轮询和文件下载。 ## 输入 @@ -21,7 +22,7 @@ Rodin3D_Gen2 节点使用 Rodin API 生成 3D 资产。它接收输入图像， | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `GLB` | 生成的 3D 模型文件路径（用于向后兼容） | STRING | +| `3D模型路径` | 生成的 3D 模型文件路径（用于向后兼容） | STRING | | `GLB` | 以 GLB 格式生成的 3D 模型 | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen2/zh.md) diff --git a/zh/built-in-nodes/Rodin3D_Gen25_Image.mdx b/zh/built-in-nodes/Rodin3D_Gen25_Image.mdx index 9629e7253..8b5878db4 100644 --- a/zh/built-in-nodes/Rodin3D_Gen25_Image.mdx +++ b/zh/built-in-nodes/Rodin3D_Gen25_Image.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen25_Image" icon: "circle" mode: wide --- + ## ## 概述 此节点使用 Rodin Gen-2.5 API 从一到五张参考图像生成 3D 模型。您可以在快速、常规或极致高质量模式之间进行选择，以平衡生成速度与成本。 diff --git a/zh/built-in-nodes/Rodin3D_Gen25_Text.mdx b/zh/built-in-nodes/Rodin3D_Gen25_Text.mdx index d69fa57f3..065fc0d0a 100644 --- a/zh/built-in-nodes/Rodin3D_Gen25_Text.mdx +++ b/zh/built-in-nodes/Rodin3D_Gen25_Text.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Gen25_Text" icon: "circle" mode: wide --- + ## 概述 使用 Rodin Gen-2.5 API 从文本提示生成 3D 模型。您可以在不同的质量模式（快速、常规或极致高清）之间进行选择，以平衡生成速度和输出质量。 @@ -34,7 +35,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `model_file` | 以指定格式生成的 3D 模型文件。 | FILE3DANY | +| `模型文件` | 以指定格式生成的 3D 模型文件。 | FILE3DANY | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Gen25_Text/zh.md) diff --git a/zh/built-in-nodes/Rodin3D_Regular.mdx b/zh/built-in-nodes/Rodin3D_Regular.mdx index 72cee82fc..b82eb0823 100644 --- a/zh/built-in-nodes/Rodin3D_Regular.mdx +++ b/zh/built-in-nodes/Rodin3D_Regular.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Regular" icon: "circle" mode: wide --- + ### 概述 Rodin 3D Regular 节点使用 Rodin API 生成 3D 资产。它接收输入图像，并通过 Rodin 服务进行处理，以创建 3D 模型。该节点处理从任务创建到下载最终 3D 模型文件的整个工作流程。 diff --git a/zh/built-in-nodes/Rodin3D_Sketch.mdx b/zh/built-in-nodes/Rodin3D_Sketch.mdx index fc321af85..050cede3a 100644 --- a/zh/built-in-nodes/Rodin3D_Sketch.mdx +++ b/zh/built-in-nodes/Rodin3D_Sketch.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Sketch" icon: "circle" mode: wide --- + 此节点使用 Rodin API 生成 3D 资产。它接收输入图像，并通过外部服务将其转换为 3D 模型。该节点处理从任务创建到下载最终 3D 模型文件的整个过程。 ## 输入 @@ -18,7 +19,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `GLB` | 生成的 3D 模型文件路径（仅用于向后兼容） | STRING | +| `3D模型路径` | 生成的 3D 模型文件路径（仅用于向后兼容） | STRING | | `GLB` | 以 GLB 格式生成的 3D 模型 | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Rodin3D_Sketch/zh.md) diff --git a/zh/built-in-nodes/Rodin3D_Smooth.mdx b/zh/built-in-nodes/Rodin3D_Smooth.mdx index 614e6fc43..75845f58b 100644 --- a/zh/built-in-nodes/Rodin3D_Smooth.mdx +++ b/zh/built-in-nodes/Rodin3D_Smooth.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Rodin3D_Smooth" icon: "circle" mode: wide --- + ### 概述 Rodin 3D Smooth 节点通过 Rodin API 处理输入图像并将其转换为平滑的 3D 模型，从而生成 3D 资产。该节点接收多张图像作为输入，并生成可下载的 3D 模型文件。它会自动处理整个生成过程，包括任务创建、状态轮询和文件下载。 diff --git a/zh/built-in-nodes/RunwayAleph2KeyframeNode.mdx b/zh/built-in-nodes/RunwayAleph2KeyframeNode.mdx new file mode 100644 index 000000000..8e874d00e --- /dev/null +++ b/zh/built-in-nodes/RunwayAleph2KeyframeNode.mdx @@ -0,0 +1,37 @@ +--- +title: "RunwayAleph2KeyframeNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2KeyframeNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2KeyframeNode" +icon: "circle" +mode: wide +--- + +此节点将引导图像锚定到输入视频的特定时刻，使 Aleph2 模型在视频的该点引导编辑效果。将此节点连接到 Runway Aleph2 视频到视频节点的"keyframes"输入，并通过可选的"keyframes"输入将多个节点（最多 5 个）串联在一起。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `image` | 在输入视频的选定时刻应用的引导图像。 | IMAGE | 是 | - | +| `timing` | 如何将此图像放置在输入视频的时间线上。 | COMBO | 是 | 见下文 | +| `keyframes` | 可选的先前关键帧，用于与此关键帧串联。 | KEYFRAME | 否 | - | + +### 时序参数选项 + +`timing` 参数有两种模式： + +| 模式 | 子参数 | 描述 | 范围 | +|------|--------------|-------------|-------| +| "绝对秒数" | `seconds` | 从输入视频开始到此图像应用的时间（秒）（默认值：0.0） | 0.0 到 30.0，步长 0.1 | +| "时长比例" | `fraction` | 此图像在输入视频中应用的位置，以其时长的比例表示（0.0 = 开始，1.0 = 结束）（默认值：0.0） | 0.0 到 1.0，步长 0.01 | + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `keyframes` | 包含此关键帧及任何先前连接的关键帧的关键帧链。 | KEYFRAME | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2KeyframeNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `b5ac6553166b7366fd35f97740861be163f91bc2353f5f83bdc2f04bf40f8478` diff --git a/zh/built-in-nodes/RunwayAleph2PromptImageNode.mdx b/zh/built-in-nodes/RunwayAleph2PromptImageNode.mdx new file mode 100644 index 000000000..1b55b3975 --- /dev/null +++ b/zh/built-in-nodes/RunwayAleph2PromptImageNode.mdx @@ -0,0 +1,34 @@ +--- +title: "RunwayAleph2PromptImageNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2PromptImageNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2PromptImageNode" +icon: "circle" +mode: wide +--- + +此节点将引导图像锚定到输出视频中的特定时刻，控制编辑后的视频在该点的外观。将此节点连接到 Runway Aleph2 视频到视频节点的 `prompt_images` 输入，并使用可选的 `prompt_images` 输入将多个节点串联在一起（最多 5 个）。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `image` | 要放置在输出视频选定时刻的引导图像。 | IMAGE | 是 | - | +| `position` | 如何将此图像放置在输出视频的时间线上。可选择绝对时间（从开始算起的秒数）或分数时间（视频时长的百分比）。 | COMBO | 是 | `Absolute (seconds)`
`Fraction (0.0 to 1.0)` | +| `prompt_images` | 可选的早期提示图像，用于与此图像串联。在此处连接另一个 Runway Aleph2 提示图像节点的输出，以构建最多 5 个引导图像的链条。 | PROMPT_IMAGE_CHAIN | 否 | - | + +**位置模式详情：** + +当 `position` 设置为 `Absolute (seconds)` 时，必须提供 `seconds` 值（默认值：0.0，范围：0.0 至 30.0，步长：0.1）。这指定了从输出视频开始到应用此图像的精确时间（以秒为单位）。 + +当 `position` 设置为 `Fraction (0.0 to 1.0)` 时，必须提供 `fraction` 值（默认值：0.0，范围：0.0 至 1.0，步长：0.01）。这指定了此图像在输出视频中应用的位置，作为其总时长的分数（0.0 = 开始，1.0 = 结束）。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `prompt_images` | 提示图像链条，可连接到 Runway Aleph2 视频到视频节点的 `prompt_images` 输入。 | PROMPT_IMAGE_CHAIN | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2PromptImageNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `a8b86fb5d73d27cc58aa59c195ca058eec8a5c9433ea09522ff3e905f6b88193` diff --git a/zh/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx b/zh/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx new file mode 100644 index 000000000..d25290d6b --- /dev/null +++ b/zh/built-in-nodes/RunwayAleph2VideoToVideoNode.mdx @@ -0,0 +1,37 @@ +--- +title: "RunwayAleph2VideoToVideoNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the RunwayAleph2VideoToVideoNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "RunwayAleph2VideoToVideoNode" +icon: "circle" +mode: wide +--- + +此节点使用 Runway 的 Aleph2 模型，通过文本提示编辑视频。它能够对您的素材进行风格重绘、重新照明、添加或移除元素，或改变视角，同时保留原始的运动和时间节奏。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `提示词` | 描述输出中应出现的内容（1-1000 个字符）。 | STRING | 是 | 1-1000 个字符 | +| `视频` | 要编辑的输入视频。必须为 2-30 秒，帧率不超过 30 fps。 | VIDEO | 是 | 时长 2-30 秒，最大 30 fps | +| `随机种子` | 生成用的随机种子（默认值：0）。 | INT | 是 | 0 到 4294967295 | +| `公众人物阈值` | 针对可识别公众人物的内容审核（默认值："low"）。 | COMBO | 是 | "auto"
"low" | +| `关键帧` | 锚定到输入视频的引导图像，来自 Aleph2 关键帧节点（最多 5 个）。使用关键帧或提示图像，不可同时使用两者。 | KEYFRAME | 否 | 最多 5 项 | +| `提示图像` | 锚定到输出视频的引导图像，来自 Aleph2 提示图像节点（最多 5 个）。使用关键帧或提示图像，不可同时使用两者。 | PROMPT_IMAGE | 否 | 最多 5 项 | + +**重要限制：** +- 输入视频时长必须在 2 到 30 秒之间，帧率不超过 30 fps。 +- 您只能使用 `keyframes` 或 `prompt_images` 其中之一进行引导，不可同时使用两者。 +- 每个引导输入（关键帧或提示图像）最多支持 5 项。 +- 关键帧时间戳和提示图像时间戳不得超过输入视频的时长。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `视频` | 由 Aleph2 模型生成的编辑后视频。 | VIDEO | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/RunwayAleph2VideoToVideoNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `bda4d0f49843c1a8f311ddbce5911a2a157cae798a26f7a183b31fe41686d0b7` diff --git a/zh/built-in-nodes/RunwayFirstLastFrameNode.mdx b/zh/built-in-nodes/RunwayFirstLastFrameNode.mdx index b7f8829ef..fce13e32a 100644 --- a/zh/built-in-nodes/RunwayFirstLastFrameNode.mdx +++ b/zh/built-in-nodes/RunwayFirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayFirstLastFrameNode" icon: "circle" mode: wide --- + Runway 首尾帧生成视频节点通过上传首帧、尾帧及文本提示词来生成视频。该节点利用 Runway 的 Gen-3 模型，在提供的起始帧与结束帧之间创建平滑过渡。当结束帧与起始帧差异显著时，此功能尤其适用于复杂转场场景。 ## 输入 diff --git a/zh/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx b/zh/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx index 6c701088a..816c11381 100644 --- a/zh/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx +++ b/zh/built-in-nodes/RunwayImageToVideoNodeGen3a.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayImageToVideoNodeGen3a" icon: "circle" mode: wide --- + Runway 图像转视频（Gen3a Turbo）节点使用 Runway 的 Gen3a Turbo 模型，从单个起始帧生成视频。它接收文本提示和初始图像帧，然后根据指定的时长和宽高比创建视频序列。此节点连接到 Runway 的 API 以远程处理生成过程。 ## 输入 diff --git a/zh/built-in-nodes/RunwayImageToVideoNodeGen4.mdx b/zh/built-in-nodes/RunwayImageToVideoNodeGen4.mdx index dd5b03068..b8e968ba0 100644 --- a/zh/built-in-nodes/RunwayImageToVideoNodeGen4.mdx +++ b/zh/built-in-nodes/RunwayImageToVideoNodeGen4.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayImageToVideoNodeGen4" icon: "circle" mode: wide --- + Runway 图像转视频（Gen4 Turbo）节点使用 Runway 的 Gen4 Turbo 模型，从单个起始帧生成视频。它接受文本提示和初始图像帧，然后根据提供的时长和宽高比设置创建视频序列。该节点负责将起始帧上传到 Runway 的 API，并返回生成的视频。 ## 输入 diff --git a/zh/built-in-nodes/RunwayTextToImageNode.mdx b/zh/built-in-nodes/RunwayTextToImageNode.mdx index 2bdf7d454..8f71ed8cc 100644 --- a/zh/built-in-nodes/RunwayTextToImageNode.mdx +++ b/zh/built-in-nodes/RunwayTextToImageNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "RunwayTextToImageNode" icon: "circle" mode: wide --- + Runway 文本转图像节点使用 Runway 的 Gen 4 模型，根据文本提示生成图像。您可以提供文本描述，并可选择包含参考图像来引导图像生成过程。该节点负责处理 API 通信并返回生成的图像。 ## 输入 diff --git a/zh/built-in-nodes/SAM3_Detect.mdx b/zh/built-in-nodes/SAM3_Detect.mdx index d1649546c..834a1d7d7 100644 --- a/zh/built-in-nodes/SAM3_Detect.mdx +++ b/zh/built-in-nodes/SAM3_Detect.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SAM3_Detect" icon: "circle" mode: wide --- -# SAM3 检测节点 ## 概述 @@ -38,7 +37,7 @@ SAM3 检测节点使用文本描述、边界框或点提示执行开放词汇检 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `边界框` | 分割遮罩。当 `单独 mask` 为 False（默认值）时，返回每个帧的单个合并遮罩。当为 True 时，返回每个检测到的对象的单独遮罩 | MASK | +| `mask` | 分割遮罩。当 `单独 mask` 为 False（默认值）时，返回每个帧的单个合并遮罩。当为 True 时，返回每个检测到的对象的单独遮罩 | MASK | | `边界框` | 检测到的边界框，包含坐标和置信度得分。每个框包括 `x`、`y`、`width`、`height` 和 `score` 值 | BOUNDING_BOX | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SAM3_Detect/zh.md) diff --git a/zh/built-in-nodes/SAM3_TrackPreview.mdx b/zh/built-in-nodes/SAM3_TrackPreview.mdx index 50fc8946a..befd853cb 100644 --- a/zh/built-in-nodes/SAM3_TrackPreview.mdx +++ b/zh/built-in-nodes/SAM3_TrackPreview.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_TrackPreview" icon: "circle" mode: wide --- + ## 概述 此节点创建跟踪对象的视频预览，为每个跟踪对象绘制不同颜色的叠加层和数字标签。它不输出任何图像或视频张量，而是将生成的预览视频直接保存到临时文件中。 diff --git a/zh/built-in-nodes/SAM3_TrackToMask.mdx b/zh/built-in-nodes/SAM3_TrackToMask.mdx index 845cb431f..8b88616e0 100644 --- a/zh/built-in-nodes/SAM3_TrackToMask.mdx +++ b/zh/built-in-nodes/SAM3_TrackToMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_TrackToMask" icon: "circle" mode: wide --- + ## 概述 通过索引编号从 SAM3 跟踪会话中选择特定的跟踪对象，并将其合并为单个输出遮罩。这使您能够从跟踪结果中选择要保留的对象，并忽略不需要的对象。 @@ -20,7 +21,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `masks` | 每帧的单个二进制遮罩，其中选定的对象合并为一个遮罩。如果未选择任何对象或不存在跟踪数据，则返回零遮罩。 | MASK | +| `mask` | 每帧的单个二进制遮罩，其中选定的对象合并为一个遮罩。如果未选择任何对象或不存在跟踪数据，则返回零遮罩。 | MASK | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SAM3_TrackToMask/zh.md) diff --git a/zh/built-in-nodes/SAM3_VideoTrack.mdx b/zh/built-in-nodes/SAM3_VideoTrack.mdx index 9ead1df37..e09827a61 100644 --- a/zh/built-in-nodes/SAM3_VideoTrack.mdx +++ b/zh/built-in-nodes/SAM3_VideoTrack.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SAM3_VideoTrack" icon: "circle" mode: wide --- + ## 概述 使用 SAM3 的基于记忆的跟踪器在视频帧间跟踪对象。此节点处理一系列视频帧，并跨帧维护对象身份，通过初始遮罩或文本提示来定义要跟踪的内容。 @@ -27,7 +28,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `track_data` | 包含所有视频帧中对象遮罩和元数据的跟踪数据 | SAM3TrackData | +| `跟踪数据` | 包含所有视频帧中对象遮罩和元数据的跟踪数据 | SAM3TrackData | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SAM3_VideoTrack/zh.md) diff --git a/zh/built-in-nodes/SCAIL2ColoredMask.mdx b/zh/built-in-nodes/SCAIL2ColoredMask.mdx new file mode 100644 index 000000000..a80f72a99 --- /dev/null +++ b/zh/built-in-nodes/SCAIL2ColoredMask.mdx @@ -0,0 +1,31 @@ +--- +title: "SCAIL2ColoredMask - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the SCAIL2ColoredMask node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "SCAIL2ColoredMask" +icon: "circle" +mode: wide +--- + +此节点将 SAM3 跟踪数据渲染为彩色遮罩，供 WanSCAILToVideo 节点使用。它处理来自驱动姿态视频以及可选的参考图像的跟踪数据，为两个输出中的每个被跟踪人物分配一致的颜色。 + +## 输入 + +| 参数 | 描述 | 数据类型 | 是否必需 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `驱动轨迹数据` | 驱动姿态视频的 SAM3 跟踪数据。将被渲染到 pose_video_mask 输出中。 | SAM3_TRACK_DATA | 是 | - | +| `参考轨迹数据` | 参考图像的 SAM3 跟踪数据。 | SAM3_TRACK_DATA | 否 | - | +| `对象索引` | 要包含的人物索引列表，以逗号分隔（例如 '0,2,3'）。同时应用于参考遮罩和姿态视频遮罩。留空表示全部包含。 | STRING | 是 | - | +| `排序方式` | 调色板颜色分配给被跟踪对象的顺序（同时应用于参考遮罩和姿态视频，以确保每个身份保持相同颜色）。left_to_right = 最左侧对象（按首帧质心）获得第一种颜色；area = 最大对象（按首帧遮罩面积）获得第一种颜色；none = 保持 SAM3 的顺序。（默认值："left_to_right"） | COMBO | 是 | `"none"`
`"left_to_right"`
`"area"` | +| `替换模式` | False = 动画模式（pose_video_mask 背景为黑色，reference_image_mask 背景为白色）。True = 替换模式（pose_video_mask 背景为白色，reference_image_mask 背景为黑色）。（默认值：False） | BOOLEAN | 是 | False
True | + +## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `姿态视频掩码` | 从驱动姿态视频跟踪数据渲染的彩色遮罩。背景颜色遵循 replacement_mode 设置。 | IMAGE | +| `参考图像掩码` | 从参考图像跟踪数据渲染的彩色遮罩。根据模型惯例，始终以黑色背景渲染。 | IMAGE | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SCAIL2ColoredMask/zh.md) + +--- +**Source fingerprint (SHA-256):** `c9f6d87410b8bd4082ffb06ef1cf973829566ed222be643db3528cbc241d3c14` diff --git a/zh/built-in-nodes/SDPoseDrawKeypoints.mdx b/zh/built-in-nodes/SDPoseDrawKeypoints.mdx index e44e0cae2..ff9915ab5 100644 --- a/zh/built-in-nodes/SDPoseDrawKeypoints.mdx +++ b/zh/built-in-nodes/SDPoseDrawKeypoints.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDPoseDrawKeypoints" icon: "circle" mode: wide --- + SDPoseDrawKeypoints 节点接收姿态估计数据（关键点），并将其作为视觉骨架绘制在空白画布上。您可以选择性地绘制姿态的不同部分，例如身体、手部、面部和脚部，并可自定义线条宽度和点的大小。生成的图像可用于可视化，或作为需要姿态图像的其他节点的输入。 ## 输入 diff --git a/zh/built-in-nodes/SDPoseFaceBBoxes.mdx b/zh/built-in-nodes/SDPoseFaceBBoxes.mdx index 0e4cce3bc..439ee5993 100644 --- a/zh/built-in-nodes/SDPoseFaceBBoxes.mdx +++ b/zh/built-in-nodes/SDPoseFaceBBoxes.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SDPoseFaceBBoxes" icon: "circle" mode: wide --- -# SDPoseFaceBBoxes 节点 SDPoseFaceBBoxes 节点处理姿态关键点数据，用于检测并生成人脸周围的边界框。它会分析每一帧中每个人的二维面部关键点，基于这些点计算边界框，并可调整框的大小和形状。生成的边界框格式与 SDPose 工作流中的其他节点（如 SDPoseKeypointExtractor）兼容。 diff --git a/zh/built-in-nodes/SDPoseKeypointExtractor.mdx b/zh/built-in-nodes/SDPoseKeypointExtractor.mdx index aa35a2845..ff5a034b3 100644 --- a/zh/built-in-nodes/SDPoseKeypointExtractor.mdx +++ b/zh/built-in-nodes/SDPoseKeypointExtractor.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SDPoseKeypointExtractor" icon: "circle" mode: wide --- -# SDPose关键点提取器节点 此节点使用SDPose模型从输入图像中检测人体姿态关键点。它可以处理完整图像或由边界框定义的特定区域，并以OpenPose格式输出检测到的关键点，其中包含每个人的坐标以及每个关键点的置信度分数。 diff --git a/zh/built-in-nodes/SDTurboScheduler.mdx b/zh/built-in-nodes/SDTurboScheduler.mdx index 1f9fd9595..3a69cde31 100644 --- a/zh/built-in-nodes/SDTurboScheduler.mdx +++ b/zh/built-in-nodes/SDTurboScheduler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SDTurboScheduler" icon: "circle" mode: wide --- + SDTurboScheduler 专为生成图像采样所需的 sigma 值序列而设计，可根据去噪程度和指定的步数调整序列。它利用特定模型的采样能力生成这些 sigma 值，这些值对于控制图像生成过程中的去噪过程至关重要。 ## 输入 diff --git a/zh/built-in-nodes/SD_4XUpscale_Conditioning.mdx b/zh/built-in-nodes/SD_4XUpscale_Conditioning.mdx index 4d17e62ad..0507544be 100644 --- a/zh/built-in-nodes/SD_4XUpscale_Conditioning.mdx +++ b/zh/built-in-nodes/SD_4XUpscale_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SD_4XUpscale_Conditioning" icon: "circle" mode: wide --- + SD_4XUpscale_Conditioning 节点用于准备扩散模型放大图像所需的 conditioning 数据。该节点接收输入图像和 conditioning 数据，然后应用缩放和噪声增强，生成修改后的 conditioning 以指导放大过程。节点输出正向和负向 conditioning，以及对应放大尺寸的潜空间表示。 ## 输入 @@ -21,9 +22,9 @@ SD_4XUpscale_Conditioning 节点用于准备扩散模型放大图像所需的 co | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 应用放大信息后的修改版正向 conditioning | CONDITIONING | -| `Latent` | 应用放大信息后的修改版负向 conditioning | CONDITIONING | -| `latent` | 与放大后尺寸匹配的空潜空间表示 | LATENT | +| `正面条件` | 应用放大信息后的修改版正向 conditioning | CONDITIONING | +| `负面条件` | 应用放大信息后的修改版负向 conditioning | CONDITIONING | +| `Latent` | 与放大后尺寸匹配的空潜空间表示 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SD_4XUpscale_Conditioning/zh.md) diff --git a/zh/built-in-nodes/SUPIRApply.mdx b/zh/built-in-nodes/SUPIRApply.mdx index 65d508284..0833a2c0a 100644 --- a/zh/built-in-nodes/SUPIRApply.mdx +++ b/zh/built-in-nodes/SUPIRApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SUPIRApply" icon: "circle" mode: wide --- + SUPIRApply 节点用于将 SUPIR 模型补丁应用于扩散模型。它利用该补丁修改模型的行为，使其能够在采样过程中融入输入图像的引导信息。该节点还提供了随时间调整引导强度的控制功能，并包含一项可选特性，有助于保持对原始输入的保真度。 ## 输入 diff --git a/zh/built-in-nodes/SV3D_Conditioning.mdx b/zh/built-in-nodes/SV3D_Conditioning.mdx index fb5e221ae..7013d1e89 100644 --- a/zh/built-in-nodes/SV3D_Conditioning.mdx +++ b/zh/built-in-nodes/SV3D_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SV3D_Conditioning" icon: "circle" mode: wide --- + SV3D_Conditioning 节点使用 SV3D 模型为 3D 视频生成准备条件数据。它接收初始图像，通过 CLIP 视觉编码器和 VAE 编码器进行处理，生成正向和负向条件数据以及潜在表示。该节点根据指定的视频帧数生成相机仰角和方位角序列，用于多帧视频生成。 ## 输入 @@ -23,9 +24,9 @@ SV3D_Conditioning 节点使用 SV3D 模型为 3D 视频生成准备条件数据 | 输出名称 | 说明 | 数据类型 | | --- | --- | --- | -| `负面条件` | 包含图像嵌入和相机参数的正向条件数据，用于生成过程 | CONDITIONING | -| `Latent` | 嵌入值归零的负向条件数据，用于对比生成 | CONDITIONING | -| `latent` | 维度与指定视频帧数和分辨率匹配的空潜在张量 | LATENT | +| `正面条件` | 包含图像嵌入和相机参数的正向条件数据，用于生成过程 | CONDITIONING | +| `负面条件` | 嵌入值归零的负向条件数据，用于对比生成 | CONDITIONING | +| `Latent` | 维度与指定视频帧数和分辨率匹配的空潜在张量 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SV3D_Conditioning/zh.md) diff --git a/zh/built-in-nodes/SVD_img2vid_Conditioning.mdx b/zh/built-in-nodes/SVD_img2vid_Conditioning.mdx index 764ccc465..fa9773b8c 100644 --- a/zh/built-in-nodes/SVD_img2vid_Conditioning.mdx +++ b/zh/built-in-nodes/SVD_img2vid_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SVD_img2vid_Conditioning" icon: "circle" mode: wide --- + SVD_img2vid_Conditioning 节点用于准备基于 Stable Video Diffusion 的视频生成条件数据。它接收初始图像，通过 CLIP 视觉编码器和 VAE 编码器进行处理，生成正负条件对，以及用于视频生成的空潜在空间。该节点设置了控制生成视频中运动量、帧率和增强级别的必要参数。 ## 输入 @@ -25,9 +26,9 @@ SVD_img2vid_Conditioning 节点用于准备基于 Stable Video Diffusion 的视 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 包含图像嵌入和视频参数的正条件数据 | CONDITIONING | -| `Latent` | 嵌入和视频参数归零后的负条件数据 | CONDITIONING | -| `latent` | 准备用于视频生成的空潜在空间张量 | LATENT | +| `正面条件` | 包含图像嵌入和视频参数的正条件数据 | CONDITIONING | +| `负面条件` | 嵌入和视频参数归零后的负条件数据 | CONDITIONING | +| `Latent` | 准备用于视频生成的空潜在空间张量 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SVD_img2vid_Conditioning/zh.md) diff --git a/zh/built-in-nodes/SamplerARVideo.mdx b/zh/built-in-nodes/SamplerARVideo.mdx index 76303fe83..b8141ada8 100644 --- a/zh/built-in-nodes/SamplerARVideo.mdx +++ b/zh/built-in-nodes/SamplerARVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerARVideo" icon: "circle" mode: wide --- + Sampler AR Video 节点为自回归视频模型（例如使用因果强制或自强制技术的模型）提供了一种专门的采样方法。它直接在工作流中管理与自回归（AR）循环相关的所有参数，使配置模型如何逐步生成视频帧变得简单。 ## 输入 diff --git a/zh/built-in-nodes/SamplerCustom.mdx b/zh/built-in-nodes/SamplerCustom.mdx index 7103270ee..3f18d1fad 100644 --- a/zh/built-in-nodes/SamplerCustom.mdx +++ b/zh/built-in-nodes/SamplerCustom.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerCustom" icon: "circle" mode: wide --- + SamplerCustom 节点旨在为各种应用提供灵活且可定制的采样机制。它使用户能够根据自身特定需求选择和配置不同的采样策略，从而增强采样过程的适应性和效率。 ## 输入 @@ -25,7 +26,7 @@ SamplerCustom 节点旨在为各种应用提供灵活且可定制的采样机制 | 参数 | 描述 | 数据类型 | | --- | --- | --- | -| `降噪Latent` | 'output' 代表采样过程的主要结果，包含生成的样本。 | `LATENT` | -| `denoised_output` | 'denoised_output' 代表经过降噪处理后的样本，可能提升了生成样本的清晰度和质量。 | `LATENT` | +| `Latent` | 'output' 代表采样过程的主要结果，包含生成的样本。 | `LATENT` | +| `降噪Latent` | 'denoised_output' 代表经过降噪处理后的样本，可能提升了生成样本的清晰度和质量。 | `LATENT` | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerCustom/zh.md) diff --git a/zh/built-in-nodes/SamplerCustomAdvanced.mdx b/zh/built-in-nodes/SamplerCustomAdvanced.mdx index 2ab6bc663..da6e92612 100644 --- a/zh/built-in-nodes/SamplerCustomAdvanced.mdx +++ b/zh/built-in-nodes/SamplerCustomAdvanced.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerCustomAdvanced" icon: "circle" mode: wide --- + SamplerCustomAdvanced 节点使用自定义噪声、引导和采样配置执行高级潜在空间采样。它通过引导采样过程处理潜在图像，支持自定义噪声生成和 sigma 调度，最终输出采样结果及可用的去噪版本。 ## 输入 @@ -21,8 +22,8 @@ SamplerCustomAdvanced 节点使用自定义噪声、引导和采样配置执行 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `降噪Latent` | 完成采样过程后的最终潜在表示 | LATENT | -| `denoised_output` | 输出的去噪版本（可用时），否则返回与输出相同的结果 | LATENT | +| `Latent` | 完成采样过程后的最终潜在表示 | LATENT | +| `降噪Latent` | 输出的去噪版本（可用时），否则返回与输出相同的结果 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplerCustomAdvanced/zh.md) diff --git a/zh/built-in-nodes/SamplerDPMAdaptative.mdx b/zh/built-in-nodes/SamplerDPMAdaptative.mdx index 69d59b2a9..6c1e2de52 100644 --- a/zh/built-in-nodes/SamplerDPMAdaptative.mdx +++ b/zh/built-in-nodes/SamplerDPMAdaptative.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMAdaptative" icon: "circle" mode: wide --- + SamplerDPMAdaptative 节点实现了一种自适应 DPM（扩散概率模型）采样器，可在采样过程中自动调整步长。它使用基于容差的误差控制来确定最优步长，从而在计算效率与采样精度之间取得平衡。这种自适应方法有助于在保持质量的同时，可能减少所需的步数。 ## 输入 diff --git a/zh/built-in-nodes/SamplerDPMPP_2M_SDE.mdx b/zh/built-in-nodes/SamplerDPMPP_2M_SDE.mdx index ecbcf1593..929d082bd 100644 --- a/zh/built-in-nodes/SamplerDPMPP_2M_SDE.mdx +++ b/zh/built-in-nodes/SamplerDPMPP_2M_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_2M_SDE" icon: "circle" mode: wide --- + SamplerDPMPP_2M_SDE 节点为扩散模型创建了一个 DPM++ 2M SDE 采样器。该采样器使用二阶微分方程求解器结合随机微分方程来生成样本。它提供了不同的求解器类型和噪声处理选项，以控制采样过程。 ## 输入 diff --git a/zh/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx b/zh/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx index 98cd0979a..2ccf37098 100644 --- a/zh/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx +++ b/zh/built-in-nodes/SamplerDPMPP_2S_Ancestral.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_2S_Ancestral" icon: "circle" mode: wide --- + SamplerDPMPP_2S_Ancestral 节点创建了一个使用 DPM++ 2S Ancestral 采样方法生成图像的采样器。该采样器结合了确定性和随机性元素，在保持一定一致性的同时产生多样化的结果。它允许您在采样过程中控制随机性和噪声水平。 ## 输入 diff --git a/zh/built-in-nodes/SamplerDPMPP_3M_SDE.mdx b/zh/built-in-nodes/SamplerDPMPP_3M_SDE.mdx index 788f9ef81..721d04a66 100644 --- a/zh/built-in-nodes/SamplerDPMPP_3M_SDE.mdx +++ b/zh/built-in-nodes/SamplerDPMPP_3M_SDE.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerDPMPP_3M_SDE" icon: "circle" mode: wide --- -# SamplerDPMPP_3M_SDE 节点 SamplerDPMPP_3M_SDE 节点创建一个用于采样过程的 DPM++ 3M SDE 采样器。该采样器采用三阶多步随机微分方程方法，并具有可配置的噪声参数。此节点允许您选择在 GPU 还是 CPU 上执行噪声计算。 diff --git a/zh/built-in-nodes/SamplerDPMPP_SDE.mdx b/zh/built-in-nodes/SamplerDPMPP_SDE.mdx index 872f16ad4..0095ba14e 100644 --- a/zh/built-in-nodes/SamplerDPMPP_SDE.mdx +++ b/zh/built-in-nodes/SamplerDPMPP_SDE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDPMPP_SDE" icon: "circle" mode: wide --- + SamplerDPMPP_SDE 节点创建一个 DPM++ SDE（随机微分方程）采样器，用于采样过程。该采样器提供一种随机采样方法，具有可配置的噪声参数和设备选择功能。它返回一个可在采样流程中使用的采样器对象。 ## 输入 diff --git a/zh/built-in-nodes/SamplerDpmpp2mSde.mdx b/zh/built-in-nodes/SamplerDpmpp2mSde.mdx index c58bfa966..c8d38b1e7 100644 --- a/zh/built-in-nodes/SamplerDpmpp2mSde.mdx +++ b/zh/built-in-nodes/SamplerDpmpp2mSde.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDpmpp2mSde" icon: "circle" mode: wide --- + 此节点旨在为 DPMPP_2M_SDE 模型生成采样器，支持根据指定的求解器类型、噪声水平和计算设备偏好创建样本。它抽象了采样器配置的复杂性，为使用自定义设置生成样本提供了简化的接口。 ## 输入 diff --git a/zh/built-in-nodes/SamplerDpmppSde.mdx b/zh/built-in-nodes/SamplerDpmppSde.mdx index 215caf1df..2f9085d02 100644 --- a/zh/built-in-nodes/SamplerDpmppSde.mdx +++ b/zh/built-in-nodes/SamplerDpmppSde.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerDpmppSde" icon: "circle" mode: wide --- + 此节点用于为 DPM++ SDE（随机微分方程）模型生成采样器。它能够适配 CPU 和 GPU 执行环境，并根据可用硬件优化采样器的实现。 ## 输入 diff --git a/zh/built-in-nodes/SamplerER_SDE.mdx b/zh/built-in-nodes/SamplerER_SDE.mdx index 64e1c12e8..620c10f7a 100644 --- a/zh/built-in-nodes/SamplerER_SDE.mdx +++ b/zh/built-in-nodes/SamplerER_SDE.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SamplerER_SDE" icon: "circle" mode: wide --- -# SamplerER_SDE 节点 SamplerER_SDE 节点为扩散模型提供专门的采样方法，提供包括 ER-SDE、反向时间 SDE 和 ODE 在内的不同求解器类型。它允许控制采样过程中的随机行为和计算阶段。该节点会根据所选求解器类型自动调整参数，以确保功能正常。 diff --git a/zh/built-in-nodes/SamplerEulerAncestral.mdx b/zh/built-in-nodes/SamplerEulerAncestral.mdx index 6fae870e9..53b3965d9 100644 --- a/zh/built-in-nodes/SamplerEulerAncestral.mdx +++ b/zh/built-in-nodes/SamplerEulerAncestral.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerAncestral" icon: "circle" mode: wide --- + SamplerEulerAncestral 节点用于创建欧拉祖先采样器以生成图像。该采样器采用特定的数学方法，将欧拉积分与祖先采样技术相结合，从而生成图像变体。您可以通过调整控制生成过程中随机性和步长的参数来配置采样行为。 ## 输入 diff --git a/zh/built-in-nodes/SamplerEulerAncestralCFGPP.mdx b/zh/built-in-nodes/SamplerEulerAncestralCFGPP.mdx index 56b2f0df2..eb55de581 100644 --- a/zh/built-in-nodes/SamplerEulerAncestralCFGPP.mdx +++ b/zh/built-in-nodes/SamplerEulerAncestralCFGPP.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerAncestralCFGPP" icon: "circle" mode: wide --- + SamplerEulerAncestralCFGPP 节点创建一个使用欧拉祖先方法（Euler Ancestral）结合无分类器引导（CFG++）的采样器，用于图像生成。该采样器将祖先采样技术与引导条件相结合，在保持图像连贯性的同时生成多样化的图像变体，并允许通过参数微调来控制噪声和步长调整。 ## 输入 diff --git a/zh/built-in-nodes/SamplerEulerCFGpp.mdx b/zh/built-in-nodes/SamplerEulerCFGpp.mdx index abae7e62d..8b6b84dc3 100644 --- a/zh/built-in-nodes/SamplerEulerCFGpp.mdx +++ b/zh/built-in-nodes/SamplerEulerCFGpp.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerEulerCFGpp" icon: "circle" mode: wide --- + SamplerEulerCFGpp 节点提供了一种用于生成输出的 Euler CFG++ 采样方法。该节点提供了两种不同版本的 Euler CFG++ 采样器实现，可根据用户偏好进行选择。 ## 输入 diff --git a/zh/built-in-nodes/SamplerLCM.mdx b/zh/built-in-nodes/SamplerLCM.mdx index bc1d953fc..57b6bb935 100644 --- a/zh/built-in-nodes/SamplerLCM.mdx +++ b/zh/built-in-nodes/SamplerLCM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLCM" icon: "circle" mode: wide --- + SamplerLCM 节点提供了一个带有可调每步噪声参数的 LCM（潜在一致性模型）采样器。它允许您控制每个采样步骤中应用的噪声，从而实现对采样过程的精细调整。 ## ## 输入 diff --git a/zh/built-in-nodes/SamplerLCMUpscale.mdx b/zh/built-in-nodes/SamplerLCMUpscale.mdx index d5ec66043..5b6732afc 100644 --- a/zh/built-in-nodes/SamplerLCMUpscale.mdx +++ b/zh/built-in-nodes/SamplerLCMUpscale.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLCMUpscale" icon: "circle" mode: wide --- + SamplerLCMUpscale 节点提供了一种专门的采样方法，结合了潜在一致性模型（LCM）采样与图像放大功能。它允许您在采样过程中使用多种插值方法放大图像，从而在保持图像质量的同时生成更高分辨率的输出。 ## 输入 diff --git a/zh/built-in-nodes/SamplerLMS.mdx b/zh/built-in-nodes/SamplerLMS.mdx index 1c0cf4e45..6163ea78c 100644 --- a/zh/built-in-nodes/SamplerLMS.mdx +++ b/zh/built-in-nodes/SamplerLMS.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerLMS" icon: "circle" mode: wide --- + SamplerLMS 节点创建一个用于扩散模型的最小均方（LMS）采样器。它会生成一个可在采样过程中使用的采样器对象，允许您控制 LMS 算法的阶数，以实现数值稳定性和准确性。 ## 输入 diff --git a/zh/built-in-nodes/SamplerSASolver.mdx b/zh/built-in-nodes/SamplerSASolver.mdx index dc45c7f75..a7c1c902b 100644 --- a/zh/built-in-nodes/SamplerSASolver.mdx +++ b/zh/built-in-nodes/SamplerSASolver.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerSASolver" icon: "circle" mode: wide --- + SamplerSASolver 节点为扩散模型实现了一种自定义采样算法。它采用预测-校正方法，具有可配置的阶数设置和随机微分方程（SDE）参数，用于从输入模型生成样本。 ## 输入 diff --git a/zh/built-in-nodes/SamplerSEEDS2.mdx b/zh/built-in-nodes/SamplerSEEDS2.mdx index 01f2ee8ca..6cb873bc0 100644 --- a/zh/built-in-nodes/SamplerSEEDS2.mdx +++ b/zh/built-in-nodes/SamplerSEEDS2.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplerSEEDS2" icon: "circle" mode: wide --- + 此节点提供了一个可配置的采样器，用于生成图像。它实现了 SEEDS-2 算法，这是一种随机微分方程（SDE）求解器。通过调整其参数，您可以将其配置为类似多种特定采样器的行为，包括 `seeds_2`、`exp_heun_2_x0` 和 `exp_heun_2_x0_sde`。 ## 输入 diff --git a/zh/built-in-nodes/SamplingPercentToSigma.mdx b/zh/built-in-nodes/SamplingPercentToSigma.mdx index e85fa9605..e8eb5d386 100644 --- a/zh/built-in-nodes/SamplingPercentToSigma.mdx +++ b/zh/built-in-nodes/SamplingPercentToSigma.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SamplingPercentToSigma" icon: "circle" mode: wide --- + ## 概述 SamplingPercentToSigma 节点使用模型的采样参数，将采样百分比值转换为对应的 sigma 值。它接收介于 0.0 到 1.0 之间的百分比值，并将其映射到模型噪声调度中的相应 sigma 值，同时提供选项以返回计算出的 sigma 值或边界处的实际最大/最小 sigma 值。 @@ -21,7 +22,7 @@ SamplingPercentToSigma 节点使用模型的采样参数，将采样百分比值 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `sigma_value` | 与输入采样百分比对应的转换后 sigma 值 | FLOAT | +| `sigma 值` | 与输入采样百分比对应的转换后 sigma 值 | FLOAT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SamplingPercentToSigma/zh.md) diff --git a/zh/built-in-nodes/SaveAnimatedPNG.mdx b/zh/built-in-nodes/SaveAnimatedPNG.mdx index 6f20ad093..68dadab72 100644 --- a/zh/built-in-nodes/SaveAnimatedPNG.mdx +++ b/zh/built-in-nodes/SaveAnimatedPNG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAnimatedPNG" icon: "circle" mode: wide --- + SaveAnimatedPNG 节点用于从一系列帧创建并保存动画 PNG 图像。它负责将单个图像帧组合成一个连贯的动画，并支持自定义帧持续时间、循环播放以及元数据包含。 ## 输入 @@ -20,6 +21,6 @@ SaveAnimatedPNG 节点用于从一系列帧创建并保存动画 PNG 图像。 | 字段 | 描述 | 数据类型 | | --- | --- | --- | -| `ui` | 提供一个 UI 组件，用于显示生成的动画 PNG 图像，并指示动画是单帧还是多帧。 | 无 | +| `images` | 提供一个 UI 组件，用于显示生成的动画 PNG 图像，并指示动画是单帧还是多帧。 | 无 | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAnimatedPNG/zh.md) diff --git a/zh/built-in-nodes/SaveAnimatedWEBP.mdx b/zh/built-in-nodes/SaveAnimatedWEBP.mdx index 723d8cc54..2501c21ea 100644 --- a/zh/built-in-nodes/SaveAnimatedWEBP.mdx +++ b/zh/built-in-nodes/SaveAnimatedWEBP.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAnimatedWEBP" icon: "circle" mode: wide --- + 此节点用于将一系列图像保存为动画 WEBP 文件。它负责将单个帧合并为连贯的动画，应用指定的元数据，并根据质量和压缩设置优化输出。 ## 输入 @@ -22,6 +23,6 @@ mode: wide | 字段 | 描述 | 数据类型 | | --- | --- | --- | -| `ui` | 提供一个 UI 组件，显示保存的动画 WEBP 图像及其元数据，并指示动画是否已启用。 | N/A | +| `images` | 提供一个 UI 组件，显示保存的动画 WEBP 图像及其元数据，并指示动画是否已启用。 | N/A | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveAnimatedWEBP/zh.md) diff --git a/zh/built-in-nodes/SaveAudio.mdx b/zh/built-in-nodes/SaveAudio.mdx index 744102c5e..65ce03047 100644 --- a/zh/built-in-nodes/SaveAudio.mdx +++ b/zh/built-in-nodes/SaveAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAudio" icon: "circle" mode: wide --- + SaveAudio 节点将音频数据以 FLAC 格式保存到文件。它接收音频输入，并将其写入指定输出目录，使用给定的文件名前缀。该节点自动处理文件命名，确保音频被正确保存以供后续使用。 ## 输入 diff --git a/zh/built-in-nodes/SaveAudioAdvanced.mdx b/zh/built-in-nodes/SaveAudioAdvanced.mdx index 7ffb3a858..fd2b5228e 100644 --- a/zh/built-in-nodes/SaveAudioAdvanced.mdx +++ b/zh/built-in-nodes/SaveAudioAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveAudioAdvanced" icon: "circle" mode: wide --- -# 保存音频（高级） 将输入的音频保存到您的 ComfyUI 输出目录。此节点支持以多种格式导出音频，包括 FLAC、MP3 和 Opus，并具有可配置的质量设置。 diff --git a/zh/built-in-nodes/SaveAudioMP3.mdx b/zh/built-in-nodes/SaveAudioMP3.mdx index b80db1306..cf7c023a7 100644 --- a/zh/built-in-nodes/SaveAudioMP3.mdx +++ b/zh/built-in-nodes/SaveAudioMP3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAudioMP3" icon: "circle" mode: wide --- + SaveAudioMP3 节点将音频数据保存为 MP3 文件。它接收音频输入，并将其导出到指定的输出目录，支持自定义文件名和质量设置。该节点自动处理文件命名和格式转换，以生成可播放的 MP3 文件。 ## 输入 diff --git a/zh/built-in-nodes/SaveAudioOpus.mdx b/zh/built-in-nodes/SaveAudioOpus.mdx index 835e1046c..f27372e6e 100644 --- a/zh/built-in-nodes/SaveAudioOpus.mdx +++ b/zh/built-in-nodes/SaveAudioOpus.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveAudioOpus" icon: "circle" mode: wide --- + SaveAudioOpus 节点将音频数据保存为 Opus 格式文件。它接收音频输入，并将其导出为具有可配置质量设置的压缩 Opus 文件。该节点会自动处理文件命名，并将输出保存到指定的输出目录。 ## 输入 diff --git a/zh/built-in-nodes/SaveGLB.mdx b/zh/built-in-nodes/SaveGLB.mdx index 49c6df311..c4d07ca9d 100644 --- a/zh/built-in-nodes/SaveGLB.mdx +++ b/zh/built-in-nodes/SaveGLB.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveGLB" icon: "circle" mode: wide --- + SaveGLB 节点用于将 3D 网格数据或 3D 文件保存到输出目录。它接受网格数据或多种 3D 文件格式（GLB、GLTF、OBJ、FBX、STL、USDZ），并使用指定的文件名前缀进行导出。在保存网格数据时，它可以处理多个网格，并在启用元数据时自动将工作流元数据添加到文件中。 ## 输入 diff --git a/zh/built-in-nodes/SaveImage.mdx b/zh/built-in-nodes/SaveImage.mdx index 9d8b7738b..65892edd8 100644 --- a/zh/built-in-nodes/SaveImage.mdx +++ b/zh/built-in-nodes/SaveImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImage" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImage/en.md) SaveImage 节点将接收到的图像保存到您的 `ComfyUI/output` 目录中。它会将每张图像保存为 PNG 文件，并可嵌入工作流元数据（如提示词）到保存的文件中，以便日后参考。 @@ -20,7 +21,7 @@ SaveImage 节点将接收到的图像保存到您的 `ComfyUI/output` 目录中 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `ui` | 此节点输出一个 UI 结果，其中包含已保存图像的列表及其文件名和子文件夹。它不输出用于连接其他节点的数据。 | UI_RESULT | +| `images` | 此节点输出一个 UI 结果，其中包含已保存图像的列表及其文件名和子文件夹。它不输出用于连接其他节点的数据。 | UI_RESULT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveImage/zh.md) diff --git a/zh/built-in-nodes/SaveImageAdvanced.mdx b/zh/built-in-nodes/SaveImageAdvanced.mdx index de3dee4ed..9217aa833 100644 --- a/zh/built-in-nodes/SaveImageAdvanced.mdx +++ b/zh/built-in-nodes/SaveImageAdvanced.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveImageAdvanced" icon: "circle" mode: wide --- -# SaveImageAdvanced **SaveImageAdvanced** 节点可将图像保存到 ComfyUI 输出目录，并提供对文件格式、位深度和色彩空间的进阶控制。支持保存为 PNG 或 EXR 文件，并能将工作流元数据嵌入到保存的文件中。 diff --git a/zh/built-in-nodes/SaveImageDataSetToFolder.mdx b/zh/built-in-nodes/SaveImageDataSetToFolder.mdx index dd87bc1ff..b78b52106 100644 --- a/zh/built-in-nodes/SaveImageDataSetToFolder.mdx +++ b/zh/built-in-nodes/SaveImageDataSetToFolder.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveImageDataSetToFolder" icon: "circle" mode: wide --- + 此节点将图像列表保存到 ComfyUI 输出目录中的指定文件夹。它接收多张图像作为输入，并使用可自定义的文件名前缀将其写入磁盘。 ## 输入 diff --git a/zh/built-in-nodes/SaveImageTextDataSetToFolder.mdx b/zh/built-in-nodes/SaveImageTextDataSetToFolder.mdx index 042b9732f..c73614580 100644 --- a/zh/built-in-nodes/SaveImageTextDataSetToFolder.mdx +++ b/zh/built-in-nodes/SaveImageTextDataSetToFolder.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SaveImageTextDataSetToFolder" icon: "circle" mode: wide --- -# 将图像和文本数据集保存到文件夹 此节点将图像列表及其对应的文本标题保存到 ComfyUI 输出目录中的指定文件夹。每张图像保存为 PNG 文件时，会创建一个同名的文本文件来存储其标题。这对于创建生成图像及其描述的有组织数据集非常有用。 diff --git a/zh/built-in-nodes/SaveLatent.mdx b/zh/built-in-nodes/SaveLatent.mdx index c36961f6b..86e3bc6c2 100644 --- a/zh/built-in-nodes/SaveLatent.mdx +++ b/zh/built-in-nodes/SaveLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLatent" icon: "circle" mode: wide --- + SaveLatent 节点用于将潜在张量保存为磁盘上的文件，以便后续使用或共享。该节点接收潜在样本，并将其保存到输出目录中，可附带包含提示信息的元数据。节点会自动处理文件命名与组织，同时保留潜在数据的结构。 ## 输入 @@ -20,7 +21,7 @@ SaveLatent 节点用于将潜在张量保存为磁盘上的文件，以便后续 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `ui` | 在 ComfyUI 界面中提供已保存潜在文件的存储位置信息 | UI | +| `samples` | 在 ComfyUI 界面中提供已保存潜在文件的存储位置信息 | UI | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveLatent/zh.md) diff --git a/zh/built-in-nodes/SaveLoRA.mdx b/zh/built-in-nodes/SaveLoRA.mdx index 52d8659c1..f1c766067 100644 --- a/zh/built-in-nodes/SaveLoRA.mdx +++ b/zh/built-in-nodes/SaveLoRA.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLoRA" icon: "circle" mode: wide --- + SaveLoRA 节点用于将 LoRA（低秩适配）模型保存到文件。它接收一个 LoRA 模型作为输入，并将其写入输出目录中的 `.safetensors` 文件。您可以指定文件名前缀以及可选的步数，这些信息将包含在最终文件名中。 ## 输入 diff --git a/zh/built-in-nodes/SaveLoRANode.mdx b/zh/built-in-nodes/SaveLoRANode.mdx index 69abd63f3..6a3197e21 100644 --- a/zh/built-in-nodes/SaveLoRANode.mdx +++ b/zh/built-in-nodes/SaveLoRANode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveLoRANode" icon: "circle" mode: wide --- + SaveLoRA 节点将 LoRA（低秩适配）模型保存到您的输出目录。它接收一个 LoRA 模型作为输入，并创建一个带有自动生成文件名的 safetensors 文件。您可以自定义文件名前缀，并可选择在文件名中包含训练步数，以便更好地组织文件。 ## 输入 diff --git a/zh/built-in-nodes/SaveSVGNode.mdx b/zh/built-in-nodes/SaveSVGNode.mdx index 72b6536e0..8b4f0f975 100644 --- a/zh/built-in-nodes/SaveSVGNode.mdx +++ b/zh/built-in-nodes/SaveSVGNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveSVGNode" icon: "circle" mode: wide --- + 将 SVG 文件保存到磁盘。此节点接收 SVG 数据作为输入，并将其保存到输出目录，同时可嵌入元数据。节点会自动处理带计数器后缀的文件命名，并可将工作流提示信息直接嵌入 SVG 文件中。 ## 输入 @@ -18,7 +19,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `ui` | 返回文件信息，包括文件名、子文件夹和类型，用于在 ComfyUI 界面中显示 | DICT | +| `svg` | 返回文件信息，包括文件名、子文件夹和类型，用于在 ComfyUI 界面中显示 | DICT | **注意：** 此节点会在可用时自动将工作流元数据（提示信息和额外 PNG 信息）嵌入 SVG 文件中。元数据以 CDATA 段的形式插入 SVG 的 metadata 元素内。 diff --git a/zh/built-in-nodes/SaveTrainingDataset.mdx b/zh/built-in-nodes/SaveTrainingDataset.mdx index cc1ee647e..eef9ea1c1 100644 --- a/zh/built-in-nodes/SaveTrainingDataset.mdx +++ b/zh/built-in-nodes/SaveTrainingDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveTrainingDataset" icon: "circle" mode: wide --- + 此节点将准备好的训练数据集保存到计算机硬盘中。它接收编码后的数据（包括图像潜在表示及其对应的文本条件），并将它们组织成多个称为分片的小文件，以便于管理。节点会自动在输出目录中创建一个文件夹，并保存数据文件以及描述数据集的元数据文件。 ## 输入 diff --git a/zh/built-in-nodes/SaveVideo.mdx b/zh/built-in-nodes/SaveVideo.mdx index 7430abf9a..e73597b62 100644 --- a/zh/built-in-nodes/SaveVideo.mdx +++ b/zh/built-in-nodes/SaveVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveVideo" icon: "circle" mode: wide --- + SaveVideo 节点将输入的视频内容保存到您的 ComfyUI 输出目录中。您可以指定保存文件的文件名前缀、视频格式和编解码器。该节点会自动处理带计数器递增的文件命名，并可在保存的视频中包含工作流元数据。 ## 输入 diff --git a/zh/built-in-nodes/SaveWEBM.mdx b/zh/built-in-nodes/SaveWEBM.mdx index e483c1df1..55c70edb1 100644 --- a/zh/built-in-nodes/SaveWEBM.mdx +++ b/zh/built-in-nodes/SaveWEBM.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SaveWEBM" icon: "circle" mode: wide --- + SaveWEBM 节点将图像序列保存为 WEBM 视频文件。该节点接收多张输入图像，并使用 VP9 或 AV1 编码器将其编码为视频，支持可配置的质量设置和帧率。生成的视频文件将保存到输出目录，并包含提示信息等元数据。 ## 输入 @@ -21,7 +22,7 @@ SaveWEBM 节点将图像序列保存为 WEBM 视频文件。该节点接收多 | 输出名称 | 说明 | 数据类型 | | --- | --- | --- | -| `ui` | 显示已保存 WEBM 文件的视频预览 | PREVIEW | +| `images` | 显示已保存 WEBM 文件的视频预览 | PREVIEW | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SaveWEBM/zh.md) diff --git a/zh/built-in-nodes/ScaleROPE.mdx b/zh/built-in-nodes/ScaleROPE.mdx index c015f63ca..fd3451d23 100644 --- a/zh/built-in-nodes/ScaleROPE.mdx +++ b/zh/built-in-nodes/ScaleROPE.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ScaleROPE" icon: "circle" mode: wide --- + ScaleROPE 节点允许您通过对其 X、Y 和 T（时间）分量分别应用缩放和偏移因子，来修改模型的旋转位置编码（ROPE）。这是一个高级实验性节点，用于调整模型的位置编码行为。 ## 输入 diff --git a/zh/built-in-nodes/Sd4xupscaleConditioning.mdx b/zh/built-in-nodes/Sd4xupscaleConditioning.mdx index df8202360..bfa66b422 100644 --- a/zh/built-in-nodes/Sd4xupscaleConditioning.mdx +++ b/zh/built-in-nodes/Sd4xupscaleConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Sd4xupscaleConditioning" icon: "circle" mode: wide --- + 此节点专注于通过 4 倍放大过程提升图像分辨率，并结合调节元素来优化输出。它利用扩散技术进行图像放大，同时允许调整缩放比例和噪声增强，以微调增强过程。 ## 输入 diff --git a/zh/built-in-nodes/SeedNode.mdx b/zh/built-in-nodes/SeedNode.mdx new file mode 100644 index 000000000..179393d92 --- /dev/null +++ b/zh/built-in-nodes/SeedNode.mdx @@ -0,0 +1,26 @@ +--- +title: "SeedNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the SeedNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "SeedNode" +icon: "circle" +mode: wide +--- + +Seed 节点用于生成固定或随机的整数值。它通常通过为其他节点的随机数生成提供一致的起始点，来控制这些节点中随机操作的可复现性。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `种子` | 要使用的种子值。生成后控制选项决定该值在每次生成后保持固定还是发生变化。 | INT | 是 | 0 到 9223372036854775807 | + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `种子` | 生成的种子值。 | INT | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SeedNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `19f9b22945bb152ff5066195067f1b6b4c006589f26c7533fad905044ac3b7fa` diff --git a/zh/built-in-nodes/SeedVR2Conditioning.mdx b/zh/built-in-nodes/SeedVR2Conditioning.mdx index 142245cfb..95bf87ff7 100644 --- a/zh/built-in-nodes/SeedVR2Conditioning.mdx +++ b/zh/built-in-nodes/SeedVR2Conditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2Conditioning" icon: "circle" mode: wide --- -# 应用 SeedVR2 条件设置 此节点从 VAE 潜变量构建正向和负向条件设置，用于 SeedVR2 模型。它准备用于指导图像或视频生成过程的条件数据。 diff --git a/zh/built-in-nodes/SeedVR2PostProcessing.mdx b/zh/built-in-nodes/SeedVR2PostProcessing.mdx index e6c8c0c3b..9a6a13e5b 100644 --- a/zh/built-in-nodes/SeedVR2PostProcessing.mdx +++ b/zh/built-in-nodes/SeedVR2PostProcessing.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2PostProcessing" icon: "circle" mode: wide --- -# 后处理 SeedVR2 输出 此节点将生成的图像与原始调整大小后的图像对齐，并应用可选的色彩校正。它接收 SeedVR2 放大过程的输出，并调整其颜色和尺寸以匹配原始参考图像。 diff --git a/zh/built-in-nodes/SeedVR2Preprocess.mdx b/zh/built-in-nodes/SeedVR2Preprocess.mdx index fcbeaf219..6cf51f89f 100644 --- a/zh/built-in-nodes/SeedVR2Preprocess.mdx +++ b/zh/built-in-nodes/SeedVR2Preprocess.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2Preprocess" icon: "circle" mode: wide --- -# 预处理 SeedVR2 输入 此节点对调整大小后的图像进行填充，以准备用于 SeedVR2 模型。在处理过程中会移除 Alpha 通道，随后由配套的"后处理 SeedVR2 输出"节点使用原始调整大小后的图像恢复该通道。 diff --git a/zh/built-in-nodes/SeedVR2ProgressiveSampler.mdx b/zh/built-in-nodes/SeedVR2ProgressiveSampler.mdx index 0520e9989..341d73fa2 100644 --- a/zh/built-in-nodes/SeedVR2ProgressiveSampler.mdx +++ b/zh/built-in-nodes/SeedVR2ProgressiveSampler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SeedVR2ProgressiveSampler" icon: "circle" mode: wide --- -# SeedVR2ProgressiveSampler 用于 SeedVR2 原生工作流的顺序时间分块采样器。此节点通过将长视频潜变量拆分为更小的时间块，依次对每个块进行采样，并将结果混合在一起。当使用 SeedVR2 模型处理会导致内存溢出的序列时，它可作为标准 KSampler 的直接替代品。 diff --git a/zh/built-in-nodes/SelectCLIPDevice.mdx b/zh/built-in-nodes/SelectCLIPDevice.mdx index c6137e55d..bda5e8fb6 100644 --- a/zh/built-in-nodes/SelectCLIPDevice.mdx +++ b/zh/built-in-nodes/SelectCLIPDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectCLIPDevice" icon: "circle" mode: wide --- + ## 概述 选择 CLIP 设备节点允许您指定 CLIP 文本编码器运行的设备（CPU 或特定 GPU）。默认情况下，设备由模型加载器分配，但您可以覆盖此设置，改为使用 CPU 或特定 GPU。如果请求的设备在您的机器上不存在，该节点会直接原样传递 CLIP 而不做更改，并记录一条消息，而不会引发错误。 diff --git a/zh/built-in-nodes/SelectModelDevice.mdx b/zh/built-in-nodes/SelectModelDevice.mdx index d3679263b..a7c7f3ffb 100644 --- a/zh/built-in-nodes/SelectModelDevice.mdx +++ b/zh/built-in-nodes/SelectModelDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectModelDevice" icon: "circle" mode: wide --- + ## 概述 SelectModelDevice节点允许您手动选择扩散模型运行的设备（CPU或特定GPU）。它可以将模型移动到不同设备，并自动处理与其他多GPU节点的冲突。 diff --git a/zh/built-in-nodes/SelectVAEDevice.mdx b/zh/built-in-nodes/SelectVAEDevice.mdx index 99ddae2ce..ae589b7a3 100644 --- a/zh/built-in-nodes/SelectVAEDevice.mdx +++ b/zh/built-in-nodes/SelectVAEDevice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelectVAEDevice" icon: "circle" mode: wide --- + ## 概述 此节点允许您手动选择 VAE 模型应放置的 GPU 设备。默认情况下，VAE 会放置在模型加载器分配的设备上，但您可以将其固定到特定的 GPU（例如 `gpu:0`、`gpu:1`）。如果所选设备在您的机器上不可用，该节点将直接传递 VAE 而不做任何更改，并记录一条消息，而不是导致失败。 diff --git a/zh/built-in-nodes/SelfAttentionGuidance.mdx b/zh/built-in-nodes/SelfAttentionGuidance.mdx index d1f5a90e0..1472bef14 100644 --- a/zh/built-in-nodes/SelfAttentionGuidance.mdx +++ b/zh/built-in-nodes/SelfAttentionGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SelfAttentionGuidance" icon: "circle" mode: wide --- + ### 概述 自注意力引导节点通过在采样过程中修改注意力机制，对扩散模型施加引导。它会捕获无条件去噪步骤中的注意力分数，并利用这些分数创建模糊引导图，从而影响最终输出。该技术通过利用模型自身的注意力模式来引导生成过程。 diff --git a/zh/built-in-nodes/SetClipHooks.mdx b/zh/built-in-nodes/SetClipHooks.mdx index abf52c3c4..6144d94f3 100644 --- a/zh/built-in-nodes/SetClipHooks.mdx +++ b/zh/built-in-nodes/SetClipHooks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetClipHooks" icon: "circle" mode: wide --- + SetClipHooks 节点允许您对 CLIP 模型应用自定义钩子，从而对其行为进行高级修改。该节点可将钩子应用于条件化输出，并可选择启用 CLIP 调度功能。此节点会创建输入 CLIP 模型的克隆副本，并应用指定的钩子配置。 ## 输入 diff --git a/zh/built-in-nodes/SetFirstSigma.mdx b/zh/built-in-nodes/SetFirstSigma.mdx index d389c23de..5d03304b5 100644 --- a/zh/built-in-nodes/SetFirstSigma.mdx +++ b/zh/built-in-nodes/SetFirstSigma.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetFirstSigma" icon: "circle" mode: wide --- + SetFirstSigma 节点通过将序列中的第一个 sigma 值替换为自定义值来修改 sigma 值序列。它接收一个现有的 sigma 序列和一个新的 sigma 值作为输入，然后返回一个新的 sigma 序列，其中仅第一个元素被更改，而所有其他 sigma 值保持不变。 ## 输入 diff --git a/zh/built-in-nodes/SetHookKeyframes.mdx b/zh/built-in-nodes/SetHookKeyframes.mdx index f6a5ec9f3..adda70103 100644 --- a/zh/built-in-nodes/SetHookKeyframes.mdx +++ b/zh/built-in-nodes/SetHookKeyframes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetHookKeyframes" icon: "circle" mode: wide --- + 设置钩子关键帧节点允许您对现有钩子组应用关键帧调度。它接收一个钩子组，并可选择应用关键帧时间信息，以控制生成过程中不同钩子的执行时机。当提供关键帧时，该节点会克隆钩子组，并为组内的所有钩子设置关键帧时间。 ## 输入 diff --git a/zh/built-in-nodes/SetLatentNoiseMask.mdx b/zh/built-in-nodes/SetLatentNoiseMask.mdx index 733b5e5be..d290a02aa 100644 --- a/zh/built-in-nodes/SetLatentNoiseMask.mdx +++ b/zh/built-in-nodes/SetLatentNoiseMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetLatentNoiseMask" icon: "circle" mode: wide --- + 此节点用于对一组潜在样本应用噪声掩码。它通过整合指定的掩码来修改输入样本，从而改变其噪声特性。 ## 输入 diff --git a/zh/built-in-nodes/SetModelHooksOnCond.mdx b/zh/built-in-nodes/SetModelHooksOnCond.mdx index 38cddb7d2..5644ce10f 100644 --- a/zh/built-in-nodes/SetModelHooksOnCond.mdx +++ b/zh/built-in-nodes/SetModelHooksOnCond.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetModelHooksOnCond" icon: "circle" mode: wide --- + 此节点将自定义钩子附加到条件数据上，允许您在模型执行期间拦截并修改条件处理过程。它接收一组钩子并将其应用于提供的条件数据，从而实现对文本到图像生成工作流的高级定制。附加了钩子的修改后条件数据将被返回，以供后续处理步骤使用。 ## 输入 diff --git a/zh/built-in-nodes/SetUnionControlNetType.mdx b/zh/built-in-nodes/SetUnionControlNetType.mdx index 621daedfb..1d3835c0f 100644 --- a/zh/built-in-nodes/SetUnionControlNetType.mdx +++ b/zh/built-in-nodes/SetUnionControlNetType.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SetUnionControlNetType" icon: "circle" mode: wide --- + SetUnionControlNetType 节点允许您指定用于条件控制的网络类型。它接收一个现有的控制网络，并根据您的选择设置其控制类型，从而创建一个具有指定类型配置的修改副本。 ## 输入 diff --git a/zh/built-in-nodes/ShuffleDataset.mdx b/zh/built-in-nodes/ShuffleDataset.mdx index 1af5585b7..a8257389c 100644 --- a/zh/built-in-nodes/ShuffleDataset.mdx +++ b/zh/built-in-nodes/ShuffleDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ShuffleDataset" icon: "circle" mode: wide --- + Shuffle Dataset（数据集打乱）节点接收一个图像列表并随机改变其顺序。它使用种子值来控制随机性，确保可以重现相同的打乱顺序。这在处理数据集前随机化图像序列时非常有用。 ## 输入 diff --git a/zh/built-in-nodes/ShuffleImageTextDataset.mdx b/zh/built-in-nodes/ShuffleImageTextDataset.mdx index 6b90867d2..2ad26dc5f 100644 --- a/zh/built-in-nodes/ShuffleImageTextDataset.mdx +++ b/zh/built-in-nodes/ShuffleImageTextDataset.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ShuffleImageTextDataset" icon: "circle" mode: wide --- + 此节点将图像列表和文本列表一起打乱，保持它们的配对关系不变。它使用随机种子来确定打乱顺序，确保相同的输入列表在重复使用相同种子时以相同方式打乱。 ## 输入 @@ -21,7 +22,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `文本` | 打乱后的图像列表。 | IMAGE | +| `图像` | 打乱后的图像列表。 | IMAGE | | `文本` | 打乱后的文本列表，保持与图像的原始配对关系。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ShuffleImageTextDataset/zh.md) diff --git a/zh/built-in-nodes/SkipLayerGuidanceDiT.mdx b/zh/built-in-nodes/SkipLayerGuidanceDiT.mdx index 75135a247..45df5a544 100644 --- a/zh/built-in-nodes/SkipLayerGuidanceDiT.mdx +++ b/zh/built-in-nodes/SkipLayerGuidanceDiT.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceDiT" icon: "circle" mode: wide --- + 通过使用另一组带有跳过层的 CFG 负向引导，增强对详细结构的引导。此通用版本的 SkipLayerGuidance 可用于所有 DiT 模型，其灵感来源于扰动注意力引导（Perturbed Attention Guidance）。最初的实验性实现是为 SD3 创建的。 ## 输入 diff --git a/zh/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx b/zh/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx index abcaf0682..dfb4c1d0e 100644 --- a/zh/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx +++ b/zh/built-in-nodes/SkipLayerGuidanceDiTSimple.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceDiTSimple" icon: "circle" mode: wide --- + SkipLayerGuidanceDiT 节点的简化版本，仅在去噪过程中修改无条件传递。此节点通过根据指定的时间和层参数，在无条件传递期间有选择地跳过 DiT（扩散变换器）模型中的特定变换器层，从而应用跳层引导。 ## 输入 diff --git a/zh/built-in-nodes/SkipLayerGuidanceSD3.mdx b/zh/built-in-nodes/SkipLayerGuidanceSD3.mdx index 558b5dec5..1995d8498 100644 --- a/zh/built-in-nodes/SkipLayerGuidanceSD3.mdx +++ b/zh/built-in-nodes/SkipLayerGuidanceSD3.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SkipLayerGuidanceSD3" icon: "circle" mode: wide --- + SkipLayerGuidanceSD3 节点通过应用一组带有跳过层的额外无分类器引导，增强对详细结构的引导。此实验性实现受扰动注意力引导启发，通过在负条件处理过程中选择性绕过某些层来改善生成输出的结构细节。 ## 输入 diff --git a/zh/built-in-nodes/SolidMask.mdx b/zh/built-in-nodes/SolidMask.mdx index 1deb442e4..55554baf4 100644 --- a/zh/built-in-nodes/SolidMask.mdx +++ b/zh/built-in-nodes/SolidMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SolidMask" icon: "circle" mode: wide --- + SolidMask 节点用于生成一个在整个区域内具有指定值的均匀遮罩。它旨在创建具有特定尺寸和强度的遮罩，适用于各种图像处理和遮罩任务。 ## 输入 diff --git a/zh/built-in-nodes/SoniloTextToMusic.mdx b/zh/built-in-nodes/SoniloTextToMusic.mdx index 6cc4c5ab3..82dd53612 100644 --- a/zh/built-in-nodes/SoniloTextToMusic.mdx +++ b/zh/built-in-nodes/SoniloTextToMusic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SoniloTextToMusic" icon: "circle" mode: wide --- + Sonilo 文本转音乐节点使用 Sonilo 的 AI 模型，根据文本描述生成音乐。您提供描述所需音乐的提示词，节点会向 Sonilo 服务发送请求以创建音频文件。您可以指定目标时长，或让模型根据提示词自行推断。 ## 输入 diff --git a/zh/built-in-nodes/SoniloVideoToMusic.mdx b/zh/built-in-nodes/SoniloVideoToMusic.mdx index a9d965526..041cb198a 100644 --- a/zh/built-in-nodes/SoniloVideoToMusic.mdx +++ b/zh/built-in-nodes/SoniloVideoToMusic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SoniloVideoToMusic" icon: "circle" mode: wide --- + 使用 Sonilo 的 AI 模型从视频生成音乐。此节点分析输入视频的内容，并创作一段与之匹配的音乐。它利用外部 AI 服务处理视频并生成音频。 ## 输入 diff --git a/zh/built-in-nodes/SplatToFile3D.mdx b/zh/built-in-nodes/SplatToFile3D.mdx index 55b8609b9..6b9ceba09 100644 --- a/zh/built-in-nodes/SplatToFile3D.mdx +++ b/zh/built-in-nodes/SplatToFile3D.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SplatToFile3D" icon: "circle" mode: wide --- -# SplatToFile3D 节点文档 ## ## 概述 diff --git a/zh/built-in-nodes/SplatToMesh.mdx b/zh/built-in-nodes/SplatToMesh.mdx index c013a91f6..c0d40cc51 100644 --- a/zh/built-in-nodes/SplatToMesh.mdx +++ b/zh/built-in-nodes/SplatToMesh.mdx @@ -5,7 +5,6 @@ sidebarTitle: "SplatToMesh" icon: "circle" mode: wide --- -# 从 Splat 提取网格 此节点将 3D 高斯泼溅转换为彩色网格表面。其工作原理是将高斯体光栅化到密度网格上，在选定的密度水平提取等值面，然后应用可选的平滑和清理操作，生成干净的彩色三角网格。 @@ -26,7 +25,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | |-------------|-------------|-----------| -| `mesh` | 提取的彩色网格，采用无光照渲染（类似自发光）以匹配泼溅外观 | MESH | +| `网格` | 提取的彩色网格，采用无光照渲染（类似自发光）以匹配泼溅外观 | MESH | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplatToMesh/zh.md) diff --git a/zh/built-in-nodes/SplitAudioChannels.mdx b/zh/built-in-nodes/SplitAudioChannels.mdx index 3883dcdbc..5e894dd5a 100644 --- a/zh/built-in-nodes/SplitAudioChannels.mdx +++ b/zh/built-in-nodes/SplitAudioChannels.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitAudioChannels" icon: "circle" mode: wide --- + SplitAudioChannels 节点可将立体声音频分离为独立的左声道和右声道。它接收包含两个声道的立体声音频输入，并输出两个独立的音频流，分别对应左声道和右声道。 ## 输入 @@ -19,8 +20,8 @@ SplitAudioChannels 节点可将立体声音频分离为独立的左声道和右 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `右声道` | 分离后的左声道音频 | AUDIO | -| `right` | 分离后的右声道音频 | AUDIO | +| `左声道` | 分离后的左声道音频 | AUDIO | +| `右声道` | 分离后的右声道音频 | AUDIO | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitAudioChannels/zh.md) diff --git a/zh/built-in-nodes/SplitImageToTileList.mdx b/zh/built-in-nodes/SplitImageToTileList.mdx index a0843d8df..1ca0e319b 100644 --- a/zh/built-in-nodes/SplitImageToTileList.mdx +++ b/zh/built-in-nodes/SplitImageToTileList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitImageToTileList" icon: "circle" mode: wide --- + 将图像分割为图块列表节点可将单个输入图像划分为一系列较小的、重叠的矩形区域（称为图块）。它会创建这些图块的批处理列表，以便其他节点单独处理。可以指定每个图块的大小以及它们之间的重叠量。 ## 输入 diff --git a/zh/built-in-nodes/SplitImageWithAlpha.mdx b/zh/built-in-nodes/SplitImageWithAlpha.mdx index 50f3e272b..6d9b49a2a 100644 --- a/zh/built-in-nodes/SplitImageWithAlpha.mdx +++ b/zh/built-in-nodes/SplitImageWithAlpha.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitImageWithAlpha" icon: "circle" mode: wide --- + SplitImageWithAlpha 节点旨在分离图像的色彩和 Alpha 分量。它处理输入图像张量，提取 RGB 通道作为色彩分量，Alpha 通道作为透明度分量，从而方便需要对这些不同图像方面进行操作的任务。 ## 输入 diff --git a/zh/built-in-nodes/SplitSigmas.mdx b/zh/built-in-nodes/SplitSigmas.mdx index c8af85bec..4efdb08cf 100644 --- a/zh/built-in-nodes/SplitSigmas.mdx +++ b/zh/built-in-nodes/SplitSigmas.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitSigmas" icon: "circle" mode: wide --- + SplitSigmas 节点用于根据指定步长将 sigma 值序列分割为两部分。此功能对于需要对 sigma 序列的初始部分和后续部分进行不同处理或操作的场景至关重要，能够更灵活、更有针对性地操控这些值。 ## 输入 @@ -18,6 +19,6 @@ SplitSigmas 节点用于根据指定步长将 sigma 值序列分割为两部分 | 参数 | 描述 | 数据类型 | | --- | --- | --- | -| `低方差` | 节点输出两个 sigma 值序列，每个序列代表原始序列在指定步长处分割后的部分。这些输出对于后续需要对 sigma 值进行差异化处理的操作至关重要。 | `SIGMAS` | +| `高方差` | 节点输出两个 sigma 值序列，每个序列代表原始序列在指定步长处分割后的部分。这些输出对于后续需要对 sigma 值进行差异化处理的操作至关重要。 | `SIGMAS` | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitSigmas/zh.md) diff --git a/zh/built-in-nodes/SplitSigmasDenoise.mdx b/zh/built-in-nodes/SplitSigmasDenoise.mdx index 200ec1914..0ee988fee 100644 --- a/zh/built-in-nodes/SplitSigmasDenoise.mdx +++ b/zh/built-in-nodes/SplitSigmasDenoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SplitSigmasDenoise" icon: "circle" mode: wide --- + SplitSigmasDenoise 节点根据去噪强度参数将 sigma 值序列分为两部分。它将输入的 sigmas 分割为高 sigma 序列和低 sigma 序列，分割点由总步数乘以去噪因子决定。这使得噪声调度能够被分离到不同的强度范围，以便进行专门处理。 ## 输入 @@ -18,8 +19,8 @@ SplitSigmasDenoise 节点根据去噪强度参数将 sigma 值序列分为两部 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `低方差` | 包含较高 sigma 值的 sigma 序列的第一部分 | SIGMAS | -| `low_sigmas` | 包含较低 sigma 值的 sigma 序列的第二部分 | SIGMAS | +| `高方差` | 包含较高 sigma 值的 sigma 序列的第一部分 | SIGMAS | +| `低方差` | 包含较低 sigma 值的 sigma 序列的第二部分 | SIGMAS | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/SplitSigmasDenoise/zh.md) diff --git a/zh/built-in-nodes/StabilityAudioInpaint.mdx b/zh/built-in-nodes/StabilityAudioInpaint.mdx index 58b38bfd7..980acfbf3 100644 --- a/zh/built-in-nodes/StabilityAudioInpaint.mdx +++ b/zh/built-in-nodes/StabilityAudioInpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityAudioInpaint" icon: "circle" mode: wide --- + 根据文本指令转换现有音频样本的一部分。此节点允许您通过提供描述性提示来修改音频的特定部分，有效地“修复”或重新生成选定部分，同时保留音频的其余部分。 ## 输入 diff --git a/zh/built-in-nodes/StabilityAudioToAudio.mdx b/zh/built-in-nodes/StabilityAudioToAudio.mdx index 162ad604d..1c4cfb693 100644 --- a/zh/built-in-nodes/StabilityAudioToAudio.mdx +++ b/zh/built-in-nodes/StabilityAudioToAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityAudioToAudio" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityAudioToAudio/en.md) 根据文本指令将现有音频样本转换为新的高质量作品。此节点接收输入音频文件，并基于您的文本提示对其进行修改，以创建新的音频内容。 diff --git a/zh/built-in-nodes/StabilityStableImageSD_3_5Node.mdx b/zh/built-in-nodes/StabilityStableImageSD_3_5Node.mdx index 477d61b8c..71bd768be 100644 --- a/zh/built-in-nodes/StabilityStableImageSD_3_5Node.mdx +++ b/zh/built-in-nodes/StabilityStableImageSD_3_5Node.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityStableImageSD_3_5Node" icon: "circle" mode: wide --- + 此节点使用 Stability AI 的 Stable Diffusion 3.5 模型同步生成图像。它根据文本提示创建图像，并在提供输入图像时修改现有图像。该节点支持多种宽高比和风格预设，以自定义输出结果。 ## 输入 diff --git a/zh/built-in-nodes/StabilityStableImageUltraNode.mdx b/zh/built-in-nodes/StabilityStableImageUltraNode.mdx index f57db1732..72bec41c2 100644 --- a/zh/built-in-nodes/StabilityStableImageUltraNode.mdx +++ b/zh/built-in-nodes/StabilityStableImageUltraNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityStableImageUltraNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StabilityStableImageUltraNode/en.md) 根据提示和分辨率同步生成图像。此节点使用 Stability AI 的 Stable Image Ultra 模型，处理您的文本提示，并生成具有指定宽高比和风格的对应图像。 diff --git a/zh/built-in-nodes/StabilityTextToAudio.mdx b/zh/built-in-nodes/StabilityTextToAudio.mdx index 278c19996..9e748f5ac 100644 --- a/zh/built-in-nodes/StabilityTextToAudio.mdx +++ b/zh/built-in-nodes/StabilityTextToAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityTextToAudio" icon: "circle" mode: wide --- + 根据文本描述生成高质量的音乐和音效。此节点使用 Stability AI 的音频生成技术，根据您的文本提示创建音频内容。 ## 输入 diff --git a/zh/built-in-nodes/StabilityUpscaleConservativeNode.mdx b/zh/built-in-nodes/StabilityUpscaleConservativeNode.mdx index c72aa3a7f..cc8a69f2b 100644 --- a/zh/built-in-nodes/StabilityUpscaleConservativeNode.mdx +++ b/zh/built-in-nodes/StabilityUpscaleConservativeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityUpscaleConservativeNode" icon: "circle" mode: wide --- + 以最小改动将图像放大至 4K 分辨率。此节点使用 Stability AI 的保守放大技术，在保留原始内容的同时仅进行细微调整，从而提升图像分辨率。 ## 输入 diff --git a/zh/built-in-nodes/StabilityUpscaleCreativeNode.mdx b/zh/built-in-nodes/StabilityUpscaleCreativeNode.mdx index 0f9c40b08..fb945a902 100644 --- a/zh/built-in-nodes/StabilityUpscaleCreativeNode.mdx +++ b/zh/built-in-nodes/StabilityUpscaleCreativeNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityUpscaleCreativeNode" icon: "circle" mode: wide --- + 以最小改动将图像放大至 4K 分辨率。此节点使用 Stability AI 的创意放大技术，在保留原始内容的同时提升图像分辨率，并添加微妙的创意细节。 ## 输入 diff --git a/zh/built-in-nodes/StabilityUpscaleFastNode.mdx b/zh/built-in-nodes/StabilityUpscaleFastNode.mdx index 165527fde..75d3e9877 100644 --- a/zh/built-in-nodes/StabilityUpscaleFastNode.mdx +++ b/zh/built-in-nodes/StabilityUpscaleFastNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StabilityUpscaleFastNode" icon: "circle" mode: wide --- + 通过 Stability API 调用，将图像快速放大至原始尺寸的 4 倍。此节点专门用于将低质量或压缩图像发送至 Stability AI 的快速放大服务进行放大。 ## 输入 diff --git a/zh/built-in-nodes/StableCascade_EmptyLatentImage.mdx b/zh/built-in-nodes/StableCascade_EmptyLatentImage.mdx index 533dc73d2..42cc07d30 100644 --- a/zh/built-in-nodes/StableCascade_EmptyLatentImage.mdx +++ b/zh/built-in-nodes/StableCascade_EmptyLatentImage.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_EmptyLatentImage" icon: "circle" mode: wide --- + StableCascade_EmptyLatentImage 节点用于为 Stable Cascade 模型创建空的潜空间张量。它会生成两个独立的潜空间表示——一个用于阶段 C，另一个用于阶段 B——并根据输入分辨率和压缩设置调整其维度。该节点为 Stable Cascade 生成流程提供起始点。 ## 输入 @@ -20,8 +21,8 @@ StableCascade_EmptyLatentImage 节点用于为 Stable Cascade 模型创建空的 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `阶段B` | 阶段 C 的潜空间张量，维度为 [batch_size, 16, height//compression, width//compression] | LATENT | -| `stage_b` | 阶段 B 的潜空间张量，维度为 [batch_size, 4, height//4, width//4] | LATENT | +| `阶段C` | 阶段 C 的潜空间张量，维度为 [batch_size, 16, height//compression, width//compression] | LATENT | +| `阶段B` | 阶段 B 的潜空间张量，维度为 [batch_size, 4, height//4, width//4] | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_EmptyLatentImage/zh.md) diff --git a/zh/built-in-nodes/StableCascade_StageB_Conditioning.mdx b/zh/built-in-nodes/StableCascade_StageB_Conditioning.mdx index c986da7d8..21629d304 100644 --- a/zh/built-in-nodes/StableCascade_StageB_Conditioning.mdx +++ b/zh/built-in-nodes/StableCascade_StageB_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_StageB_Conditioning" icon: "circle" mode: wide --- + StableCascade_StageB_Conditioning 节点通过将现有的条件信息与 Stage C 的潜在先验表示相结合，为 Stable Cascade Stage B 生成准备条件数据。它会修改条件数据，使其包含来自 Stage C 的潜在样本，从而使生成过程能够利用先验信息生成更连贯的输出。 ## 输入 diff --git a/zh/built-in-nodes/StableCascade_StageC_VAEEncode.mdx b/zh/built-in-nodes/StableCascade_StageC_VAEEncode.mdx index cee054a49..1d1a94293 100644 --- a/zh/built-in-nodes/StableCascade_StageC_VAEEncode.mdx +++ b/zh/built-in-nodes/StableCascade_StageC_VAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_StageC_VAEEncode" icon: "circle" mode: wide --- + StableCascade_StageC_VAEEncode 节点通过 VAE 编码器处理图像，为 Stable Cascade 模型生成潜在表示。它接收输入图像，使用指定的 VAE 模型进行压缩，然后输出两个潜在表示：一个用于阶段 C，另一个作为阶段 B 的占位符。压缩参数控制编码前图像缩小的程度。 ## 输入 @@ -19,8 +20,8 @@ StableCascade_StageC_VAEEncode 节点通过 VAE 编码器处理图像，为 Stab | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `阶段B` | Stable Cascade 模型阶段 C 的编码潜在表示 | LATENT | -| `stage_b` | 阶段 B 的占位潜在表示（当前返回零值） | LATENT | +| `阶段C` | Stable Cascade 模型阶段 C 的编码潜在表示 | LATENT | +| `阶段B` | 阶段 B 的占位潜在表示（当前返回零值） | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_StageC_VAEEncode/zh.md) diff --git a/zh/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx b/zh/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx index eb993a610..1b0117c8f 100644 --- a/zh/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx +++ b/zh/built-in-nodes/StableCascade_SuperResolutionControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableCascade_SuperResolutionControlnet" icon: "circle" mode: wide --- + StableCascade_SuperResolutionControlnet 节点用于准备 Stable Cascade 超分辨率处理的输入。它接收输入图像，使用 VAE 对其进行编码以生成 controlnet 输入，同时为 Stable Cascade 管道的阶段 C 和阶段 B 生成占位潜空间表示。 ## 输入 @@ -18,9 +19,9 @@ StableCascade_SuperResolutionControlnet 节点用于准备 Stable Cascade 超分 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `阶段C` | 适用于 controlnet 输入的编码图像表示 | IMAGE | -| `阶段B` | Stable Cascade 处理阶段 C 的占位潜空间表示 | LATENT | -| `stage_b` | Stable Cascade 处理阶段 B 的占位潜空间表示 | LATENT | +| `ControlNet` | 适用于 controlnet 输入的编码图像表示 | IMAGE | +| `阶段C` | Stable Cascade 处理阶段 C 的占位潜空间表示 | LATENT | +| `阶段B` | Stable Cascade 处理阶段 B 的占位潜空间表示 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableCascade_SuperResolutionControlnet/zh.md) diff --git a/zh/built-in-nodes/StableZero123_Conditioning.mdx b/zh/built-in-nodes/StableZero123_Conditioning.mdx index 950281d1b..e02605490 100644 --- a/zh/built-in-nodes/StableZero123_Conditioning.mdx +++ b/zh/built-in-nodes/StableZero123_Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StableZero123_Conditioning" icon: "circle" mode: wide --- + StableZero123_Conditioning 节点处理输入图像和相机角度，为 3D 模型生成生成条件数据和潜在表示。它使用 CLIP 视觉模型编码图像特征，根据仰角和方位角将图像特征与相机嵌入信息相结合，并生成正向和负向条件数据以及用于下游 3D 生成任务的潜在表示。 ## 输入 @@ -26,9 +27,9 @@ StableZero123_Conditioning 节点处理输入图像和相机角度，为 3D 模 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 结合图像特征和相机嵌入的正向条件数据 | CONDITIONING | -| `Latent` | 使用零初始化特征的负向条件数据 | CONDITIONING | -| `latent` | 维度为 [batch_size, 4, height//8, width//8] 的潜在表示 | LATENT | +| `正面条件` | 结合图像特征和相机嵌入的正向条件数据 | CONDITIONING | +| `负面条件` | 使用零初始化特征的负向条件数据 | CONDITIONING | +| `Latent` | 维度为 [batch_size, 4, height//8, width//8] 的潜在表示 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning/zh.md) diff --git a/zh/built-in-nodes/StableZero123_Conditioning_Batched.mdx b/zh/built-in-nodes/StableZero123_Conditioning_Batched.mdx index 7c7cc2dcd..280736a32 100644 --- a/zh/built-in-nodes/StableZero123_Conditioning_Batched.mdx +++ b/zh/built-in-nodes/StableZero123_Conditioning_Batched.mdx @@ -5,7 +5,6 @@ sidebarTitle: "StableZero123_Conditioning_Batched" icon: "circle" mode: wide --- -# 概述 StableZero123_Conditioning_Batched 节点处理输入图像，并生成用于 3D 模型生成的条件数据。它使用 CLIP 视觉模型和 VAE 模型对图像进行编码，然后根据仰角和方位角创建相机嵌入，以生成正向和负向条件数据以及用于批量处理的潜在表示。 @@ -30,9 +29,9 @@ StableZero123_Conditioning_Batched 节点处理输入图像，并生成用于 3D | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 包含图像嵌入和相机参数的正向条件数据 | CONDITIONING | -| `Latent` | 嵌入初始化为零的负向条件数据 | CONDITIONING | -| `latent` | 包含批次索引信息的处理后图像潜在表示 | LATENT | +| `正面条件` | 包含图像嵌入和相机参数的正向条件数据 | CONDITIONING | +| `负面条件` | 嵌入初始化为零的负向条件数据 | CONDITIONING | +| `Latent` | 包含批次索引信息的处理后图像潜在表示 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StableZero123_Conditioning_Batched/zh.md) diff --git a/zh/built-in-nodes/Stablezero123Conditioning.mdx b/zh/built-in-nodes/Stablezero123Conditioning.mdx index d59a8b21f..0a51e2c37 100644 --- a/zh/built-in-nodes/Stablezero123Conditioning.mdx +++ b/zh/built-in-nodes/Stablezero123Conditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Stablezero123Conditioning" icon: "circle" mode: wide --- + 此节点专为处理 StableZero123 模型的数据并准备条件输入而设计，重点是将输入格式化为兼容且优化的特定格式，以满足这些模型的需求。 ## 输入 diff --git a/zh/built-in-nodes/Stablezero123ConditioningBatched.mdx b/zh/built-in-nodes/Stablezero123ConditioningBatched.mdx index b08650dd8..0619ce982 100644 --- a/zh/built-in-nodes/Stablezero123ConditioningBatched.mdx +++ b/zh/built-in-nodes/Stablezero123ConditioningBatched.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Stablezero123ConditioningBatched" icon: "circle" mode: wide --- + 此节点专为 StableZero123 模型设计，以批处理方式处理条件信息。它专注于同时高效处理多组条件数据，优化批处理至关重要的场景下的工作流程。 ## 输入 diff --git a/zh/built-in-nodes/StringCompare.mdx b/zh/built-in-nodes/StringCompare.mdx index 351344088..58ff4cb74 100644 --- a/zh/built-in-nodes/StringCompare.mdx +++ b/zh/built-in-nodes/StringCompare.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringCompare" icon: "circle" mode: wide --- + ## 概述 StringCompare节点使用不同的比较方法来比较两个文本字符串。它可以检查一个字符串是否以另一个字符串开头、结尾，或者两个字符串是否完全相等。比较时可以区分或忽略字母大小写。 diff --git a/zh/built-in-nodes/StringConcatenate.mdx b/zh/built-in-nodes/StringConcatenate.mdx index f651a35ca..3a51b0350 100644 --- a/zh/built-in-nodes/StringConcatenate.mdx +++ b/zh/built-in-nodes/StringConcatenate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringConcatenate" icon: "circle" mode: wide --- + StringConcatenate 节点通过指定的分隔符将两个文本字符串合并为一个。它接收两个输入字符串和一个分隔符字符或字符串，然后输出一个单一的字符串，其中两个输入通过分隔符连接在一起。 ## 输入 diff --git a/zh/built-in-nodes/StringContains.mdx b/zh/built-in-nodes/StringContains.mdx index 580424df3..07176bccd 100644 --- a/zh/built-in-nodes/StringContains.mdx +++ b/zh/built-in-nodes/StringContains.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringContains" icon: "circle" mode: wide --- + StringContains 节点用于检查给定字符串是否包含指定的子字符串。它可以通过区分大小写或不区分大小写的匹配方式执行此检查，并返回一个布尔值结果，指示在主字符串中是否找到了该子字符串。 ## 输入 @@ -19,7 +20,7 @@ StringContains 节点用于检查给定字符串是否包含指定的子字符 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `contains` | 如果在字符串中找到子字符串则返回 true，否则返回 false | BOOLEAN | +| `包含` | 如果在字符串中找到子字符串则返回 true，否则返回 false | BOOLEAN | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringContains/zh.md) diff --git a/zh/built-in-nodes/StringFormat.mdx b/zh/built-in-nodes/StringFormat.mdx index a2181521e..aaf3ec14e 100644 --- a/zh/built-in-nodes/StringFormat.mdx +++ b/zh/built-in-nodes/StringFormat.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringFormat" icon: "circle" mode: wide --- + ## 概述 此节点使用 Python 的字符串格式化方法对文本进行格式化。它类似于一个模板，您可以定义一个包含占位符的文本模式，然后提供值来填充这些占位符。它支持 Python 的所有格式化选项和功能。 diff --git a/zh/built-in-nodes/StringLength.mdx b/zh/built-in-nodes/StringLength.mdx index 681930fab..dcb5333db 100644 --- a/zh/built-in-nodes/StringLength.mdx +++ b/zh/built-in-nodes/StringLength.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringLength" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringLength/en.md) StringLength 节点用于计算文本字符串中的字符数。它接受任意文本输入，并返回字符总数，包括空格和标点符号。这对于测量文本长度或验证字符串大小要求非常有用。 @@ -19,7 +20,7 @@ StringLength 节点用于计算文本字符串中的字符数。它接受任意 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `length` | 输入字符串中的字符总数，包括空格和特殊字符。 | INT | +| `长度` | 输入字符串中的字符总数，包括空格和特殊字符。 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StringLength/zh.md) diff --git a/zh/built-in-nodes/StringReplace.mdx b/zh/built-in-nodes/StringReplace.mdx index 3f9763876..5012d2b3b 100644 --- a/zh/built-in-nodes/StringReplace.mdx +++ b/zh/built-in-nodes/StringReplace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringReplace" icon: "circle" mode: wide --- + StringReplace 节点对输入字符串执行文本替换操作。它会在输入文本中搜索指定的子字符串，并将所有匹配项替换为另一个子字符串。此节点返回完成所有替换后的修改字符串。 ## 输入 diff --git a/zh/built-in-nodes/StringSubstring.mdx b/zh/built-in-nodes/StringSubstring.mdx index 8d13cc24c..8f45d81ec 100644 --- a/zh/built-in-nodes/StringSubstring.mdx +++ b/zh/built-in-nodes/StringSubstring.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringSubstring" icon: "circle" mode: wide --- + StringSubstring 节点用于从较长的字符串中提取一部分文本。它通过指定起始位置和结束位置来定义要提取的区间，并返回这两个位置之间的文本。 ## 输入 diff --git a/zh/built-in-nodes/StringTrim.mdx b/zh/built-in-nodes/StringTrim.mdx index 5c874f06e..d30deb529 100644 --- a/zh/built-in-nodes/StringTrim.mdx +++ b/zh/built-in-nodes/StringTrim.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StringTrim" icon: "circle" mode: wide --- + StringTrim 节点用于移除文本字符串开头、结尾或两端的空白字符。您可以选择从字符串的左侧、右侧或两侧进行修剪。此功能有助于清理文本输入，去除多余的空格、制表符或换行符。 ## 输入 diff --git a/zh/built-in-nodes/StripWhitespace.mdx b/zh/built-in-nodes/StripWhitespace.mdx index 24665e40c..e3a00ee5b 100644 --- a/zh/built-in-nodes/StripWhitespace.mdx +++ b/zh/built-in-nodes/StripWhitespace.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StripWhitespace" icon: "circle" mode: wide --- + 此节点用于移除文本字符串开头和结尾的所有多余空格、制表符或换行符。它接收文本输入，并返回经过清理、去除首尾空白字符的版本。 ## 输入 @@ -17,7 +18,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `text` | 已移除所有首尾空白字符的已处理文本。 | STRING | +| `文本` | 已移除所有首尾空白字符的已处理文本。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/StripWhitespace/zh.md) diff --git a/zh/built-in-nodes/StyleModelApply.mdx b/zh/built-in-nodes/StyleModelApply.mdx index fca2928f3..aadf9bfcf 100644 --- a/zh/built-in-nodes/StyleModelApply.mdx +++ b/zh/built-in-nodes/StyleModelApply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StyleModelApply" icon: "circle" mode: wide --- + 此节点将样式模型应用于给定的 conditioning，基于 CLIP 视觉模型的输出增强或改变其样式。它将样式模型的 conditioning 整合到现有的 conditioning 中，从而在生成过程中实现样式的无缝融合。 ## 输入 diff --git a/zh/built-in-nodes/StyleModelLoader.mdx b/zh/built-in-nodes/StyleModelLoader.mdx index 9b187b850..cc12dec62 100644 --- a/zh/built-in-nodes/StyleModelLoader.mdx +++ b/zh/built-in-nodes/StyleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "StyleModelLoader" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/style_models` 文件夹中的模型，同时也会读取 extra_model_paths.yaml 文件中配置的其他路径下的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够从相应文件夹中读取模型文件。 StyleModelLoader 节点设计用于从指定路径加载风格模型。其核心功能是检索并初始化风格模型，这些模型可用于为图像应用特定的艺术风格，从而根据加载的风格模型实现视觉输出的定制化。 diff --git a/zh/built-in-nodes/SvdImg2vidConditioning.mdx b/zh/built-in-nodes/SvdImg2vidConditioning.mdx index 7daca6241..ab10aade8 100644 --- a/zh/built-in-nodes/SvdImg2vidConditioning.mdx +++ b/zh/built-in-nodes/SvdImg2vidConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "SvdImg2vidConditioning" icon: "circle" mode: wide --- + 此节点专为视频生成任务的条件数据生成而设计，特别适用于 SVD_img2vid 模型。它接收包括初始图像、视频参数和 VAE 模型在内的多种输入，生成可用于指导视频帧生成的条件数据。 ## 输入 diff --git a/zh/built-in-nodes/T5TokenizerOptions.mdx b/zh/built-in-nodes/T5TokenizerOptions.mdx index de78ce6a5..f5f1a8b13 100644 --- a/zh/built-in-nodes/T5TokenizerOptions.mdx +++ b/zh/built-in-nodes/T5TokenizerOptions.mdx @@ -5,6 +5,7 @@ sidebarTitle: "T5TokenizerOptions" icon: "circle" mode: wide --- + T5TokenizerOptions 节点允许您为多种 T5 模型类型配置分词器设置。它会为包括 t5xxl、pile_t5xl、t5base、mt5xl 和 umt5xxl 在内的多种 T5 模型变体设置最小填充和最小长度参数。该节点接收一个 CLIP 输入，并返回一个应用了指定分词器选项的修改后 CLIP。 ## 输入 diff --git a/zh/built-in-nodes/TCFG.mdx b/zh/built-in-nodes/TCFG.mdx index 04aa1d272..68f7b2e9c 100644 --- a/zh/built-in-nodes/TCFG.mdx +++ b/zh/built-in-nodes/TCFG.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TCFG" icon: "circle" mode: wide --- + TCFG（切向阻尼 CFG）在采样过程中优化无条件（负向）预测，使其更好地与条件（正向）预测对齐。该技术基于研究论文 2503.18137，通过对无条件引导应用切向阻尼来提升输出质量。此节点通过调整无分类器引导过程中无条件预测的处理方式，修改模型的采样行为。 ## 输入 @@ -17,7 +18,7 @@ TCFG（切向阻尼 CFG）在采样过程中优化无条件（负向）预测， | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `patched_model` | 应用切向阻尼 CFG 后的修改模型 | MODEL | +| `模型` | 应用切向阻尼 CFG 后的修改模型 | MODEL | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TCFG/zh.md) diff --git a/zh/built-in-nodes/TemporalScoreRescaling.mdx b/zh/built-in-nodes/TemporalScoreRescaling.mdx index f8a9bdb4e..6b9107f48 100644 --- a/zh/built-in-nodes/TemporalScoreRescaling.mdx +++ b/zh/built-in-nodes/TemporalScoreRescaling.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TemporalScoreRescaling" icon: "circle" mode: wide --- + 此节点对扩散模型应用时间分数重缩放（Temporal Score Rescaling, TSR）。它通过在去噪过程中重新缩放预测的噪声或分数来修改模型的采样行为，从而引导生成输出的多样性。该功能作为后CFG（无分类器引导）函数实现。 ## 输入 @@ -19,7 +20,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `patched_model` | 输入模型，现已在其采样过程中应用了时间分数重缩放函数进行修补。 | MODEL | +| `模型` | 输入模型，现已在其采样过程中应用了时间分数重缩放函数进行修补。 | MODEL | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TemporalScoreRescaling/zh.md) diff --git a/zh/built-in-nodes/Tencent3DPartNode.mdx b/zh/built-in-nodes/Tencent3DPartNode.mdx index 6c679dd15..b020f5f50 100644 --- a/zh/built-in-nodes/Tencent3DPartNode.mdx +++ b/zh/built-in-nodes/Tencent3DPartNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Tencent3DPartNode" icon: "circle" mode: wide --- + 此节点使用腾讯混元3D API自动分析3D模型，并根据其结构生成或识别组件。它处理模型后返回一个新的FBX文件。 ## 输入 diff --git a/zh/built-in-nodes/Tencent3DTextureEditNode.mdx b/zh/built-in-nodes/Tencent3DTextureEditNode.mdx index caa66af1b..c46c3b5d9 100644 --- a/zh/built-in-nodes/Tencent3DTextureEditNode.mdx +++ b/zh/built-in-nodes/Tencent3DTextureEditNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Tencent3DTextureEditNode" icon: "circle" mode: wide --- + 此节点使用腾讯 Hunyuan3D API 编辑 3D 模型的纹理。您需要提供一个 3D 模型以及所需更改的文本描述，节点将根据您的提示返回一个纹理已重新绘制的新版本模型。 ## 输入 @@ -21,8 +22,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `OBJ` | 处理后的 GLB 格式 3D 模型。 | FILE3D | -| `texture_image` | 处理后的 OBJ 格式 3D 模型。 | FILE3D | +| `GLB` | 处理后的 GLB 格式 3D 模型。 | FILE3D | +| `OBJ` | 处理后的 OBJ 格式 3D 模型。 | FILE3D | | `texture_image` | 为 3D 模型新生成的纹理图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Tencent3DTextureEditNode/zh.md) diff --git a/zh/built-in-nodes/TencentImageToModelNode.mdx b/zh/built-in-nodes/TencentImageToModelNode.mdx index 9354c2f2a..3adf10abe 100644 --- a/zh/built-in-nodes/TencentImageToModelNode.mdx +++ b/zh/built-in-nodes/TencentImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentImageToModelNode" icon: "circle" mode: wide --- + 此节点使用腾讯混元3D Pro API，根据一张或多张输入图像生成3D模型。它会处理图像、发送至API，并返回生成的GLB和OBJ格式3D模型文件，以及可选的纹理贴图。 ## 输入 @@ -28,12 +29,12 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `GLB` | 用于向后兼容的旧版输出。 | STRING | -| `OBJ` | 以GLB（二进制GL传输格式）文件格式生成的3D模型。 | FILE3DGLB | -| `texture_image` | 以OBJ（Wavefront）文件格式生成的3D模型。 | FILE3DOBJ | -| `optional_metallic` | 生成3D模型的纹理图像。 | IMAGE | -| `optional_normal` | PBR材质的金属度贴图。若不可用则返回黑色图像。 | IMAGE | -| `optional_roughness` | PBR材质的法线贴图。若不可用则返回黑色图像。 | IMAGE | +| `模型文件` | 用于向后兼容的旧版输出。 | STRING | +| `GLB` | 以GLB（二进制GL传输格式）文件格式生成的3D模型。 | FILE3DGLB | +| `OBJ` | 以OBJ（Wavefront）文件格式生成的3D模型。 | FILE3DOBJ | +| `texture_image` | 生成3D模型的纹理图像。 | IMAGE | +| `optional_metallic` | PBR材质的金属度贴图。若不可用则返回黑色图像。 | IMAGE | +| `optional_normal` | PBR材质的法线贴图。若不可用则返回黑色图像。 | IMAGE | | `optional_roughness` | PBR材质的粗糙度贴图。若不可用则返回黑色图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentImageToModelNode/zh.md) diff --git a/zh/built-in-nodes/TencentModelTo3DUVNode.mdx b/zh/built-in-nodes/TencentModelTo3DUVNode.mdx index 4e49936c6..bc74acaa8 100644 --- a/zh/built-in-nodes/TencentModelTo3DUVNode.mdx +++ b/zh/built-in-nodes/TencentModelTo3DUVNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentModelTo3DUVNode" icon: "circle" mode: wide --- + 此节点使用腾讯混元3D API对3D模型执行UV展开操作。它接收一个3D模型文件作为输入，将其发送至API进行处理，并以OBJ和FBX格式返回处理后的模型，同时附带生成的UV纹理图像。输入模型的面数必须少于30,000个。 ## 输入 @@ -18,8 +19,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `FBX` | 处理后的3D模型文件（OBJ格式）。 | FILE3D | -| `uv_image` | 处理后的3D模型文件（FBX格式）。 | FILE3D | +| `OBJ` | 处理后的3D模型文件（OBJ格式）。 | FILE3D | +| `FBX` | 处理后的3D模型文件（FBX格式）。 | FILE3D | | `uv_image` | 生成的UV纹理图像。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentModelTo3DUVNode/zh.md) diff --git a/zh/built-in-nodes/TencentSmartTopologyNode.mdx b/zh/built-in-nodes/TencentSmartTopologyNode.mdx index 7c5004d18..d0ba3f045 100644 --- a/zh/built-in-nodes/TencentSmartTopologyNode.mdx +++ b/zh/built-in-nodes/TencentSmartTopologyNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentSmartTopologyNode" icon: "circle" mode: wide --- + 此节点对 3D 模型执行智能重拓扑，自动创建具有优化多边形数量的全新、更干净的网格。它连接到腾讯混元 3D API 来处理模型，支持最大 200MB 的 GLB 和 OBJ 文件格式。该节点以 OBJ 文件形式返回处理后的模型。 ## 输入 diff --git a/zh/built-in-nodes/TencentTextToModelNode.mdx b/zh/built-in-nodes/TencentTextToModelNode.mdx index 84716620f..db19cfcd8 100644 --- a/zh/built-in-nodes/TencentTextToModelNode.mdx +++ b/zh/built-in-nodes/TencentTextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TencentTextToModelNode" icon: "circle" mode: wide --- + 此节点使用腾讯 Hunyuan3D Pro API 从文本描述生成 3D 模型。它会发送请求创建生成任务，轮询结果，并下载最终的 GLB 和 OBJ 格式模型文件。 ## 输入 @@ -25,9 +26,9 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `GLB` | 用于向后兼容的旧版输出。 | STRING | -| `OBJ` | 以 GLB 文件格式生成的 3D 模型。 | FILE3DGLB | -| `texture_image` | 以 OBJ 文件格式生成的 3D 模型。 | FILE3DOBJ | +| `模型文件` | 用于向后兼容的旧版输出。 | STRING | +| `GLB` | 以 GLB 文件格式生成的 3D 模型。 | FILE3DGLB | +| `OBJ` | 以 OBJ 文件格式生成的 3D 模型。 | FILE3DOBJ | | `texture_image` | 从生成的 OBJ 文件中提取的纹理图像（如有）。 | IMAGE | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TencentTextToModelNode/zh.md) diff --git a/zh/built-in-nodes/TerminalLog.mdx b/zh/built-in-nodes/TerminalLog.mdx index 3054a3542..e516a0d58 100644 --- a/zh/built-in-nodes/TerminalLog.mdx +++ b/zh/built-in-nodes/TerminalLog.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TerminalLog" icon: "circle" mode: wide --- + 终端日志（管理）节点主要用于在 ComfyUI 界面中显示终端内 ComfyUI 的运行信息。要使用它，您需要将 `mode` 设置为 **logging** 模式。这将使其在图像生成任务期间记录相应的日志信息。如果 `mode` 设置为 **stop** 模式，则不会记录日志信息。 当您通过远程连接或局域网连接访问和使用 ComfyUI 时，终端日志（管理）节点会变得特别有用。它允许您直接在 ComfyUI 界面中查看来自 CMD 的错误消息，从而更轻松地了解 ComfyUI 的当前运行状态。 diff --git a/zh/built-in-nodes/TextEncodeAceStepAudio.mdx b/zh/built-in-nodes/TextEncodeAceStepAudio.mdx index c80e014eb..27a9999bc 100644 --- a/zh/built-in-nodes/TextEncodeAceStepAudio.mdx +++ b/zh/built-in-nodes/TextEncodeAceStepAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeAceStepAudio" icon: "circle" mode: wide --- + TextEncodeAceStepAudio 节点通过将标签和歌词合并为词元（tokens）来处理音频条件化的文本输入，然后使用可调节的歌词强度进行编码。该节点接收一个 CLIP 模型以及文本描述和歌词，将它们一起词元化，并生成适用于音频生成任务的条件化数据。该节点通过一个强度参数来控制歌词对最终输出的影响，从而实现对歌词影响力的精细调节。 ## 输入 diff --git a/zh/built-in-nodes/TextEncodeAceStepAudio1.5.mdx b/zh/built-in-nodes/TextEncodeAceStepAudio1.5.mdx index 068a2461e..3486ad445 100644 --- a/zh/built-in-nodes/TextEncodeAceStepAudio1.5.mdx +++ b/zh/built-in-nodes/TextEncodeAceStepAudio1.5.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeAceStepAudio1.5" icon: "circle" mode: wide --- + TextEncodeAceStepAudio1.5 节点用于准备文本和音频相关元数据，以供 AceStepAudio 1.5 模型使用。它接收描述性标签、歌词和音乐参数，然后利用 CLIP 模型将其转换为适用于音频生成的 conditioning 格式。 ## 输入 diff --git a/zh/built-in-nodes/TextEncodeBooguEdit.mdx b/zh/built-in-nodes/TextEncodeBooguEdit.mdx new file mode 100644 index 000000000..fd9906b67 --- /dev/null +++ b/zh/built-in-nodes/TextEncodeBooguEdit.mdx @@ -0,0 +1,31 @@ +--- +title: "TextEncodeBooguEdit - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the TextEncodeBooguEdit node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "TextEncodeBooguEdit" +icon: "circle" +mode: wide +--- + +此节点为使用 Boogu 进行图像编辑准备 conditioning。它处理参考图像以生成正向和负向 conditioning 输出。参考图像被使用两次：来自图像的视觉 tokens 仅添加到正向 conditioning 中以增强编辑指令，而 VAE 参考潜空间则同时添加到正向和负向 conditioning 中，从而在 CFG 下相互抵消，保留原始图像特征。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `clip` | 用于文本编码的 CLIP 模型 | CLIP | 是 | | +| `prompt` | 描述所需编辑的文本提示 | STRING | 是 | | +| `negative_prompt` | 描述编辑中需避免内容的文本提示 | STRING | 否 | | +| `vae` | 用于将参考图像编码为潜空间的 VAE 模型 | VAE | 否 | | +| `images` | 待编辑的参考图像。Boogu 每个样本聚焦于一个参考图像；允许多个。 | IMAGE | 否 | 最多 16 张图像 | + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `positive` | 包含文本提示（含视觉 tokens）和参考潜空间的 conditioning | CONDITIONING | +| `negative` | 包含负向文本提示和参考潜空间的 conditioning | CONDITIONING | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextEncodeBooguEdit/zh.md) + +--- +**Source fingerprint (SHA-256):** `170979acf5b2e9f25f96231a4b23a4376cfddcd4bda2fdd6e03528417e6931b0` diff --git a/zh/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx b/zh/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx index 1fd248a99..f1fc38583 100644 --- a/zh/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx +++ b/zh/built-in-nodes/TextEncodeHunyuanVideo_ImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeHunyuanVideo_ImageToVideo" icon: "circle" mode: wide --- + TextEncodeHunyuanVideo_ImageToVideo 节点通过将文本提示与图像嵌入相结合，为视频生成创建条件数据。它使用 CLIP 模型处理文本输入和来自 CLIP 视觉输出的视觉信息，然后根据指定的图像交错设置生成融合这两种来源的令牌。 ## 输入 diff --git a/zh/built-in-nodes/TextEncodeQwenImageEdit.mdx b/zh/built-in-nodes/TextEncodeQwenImageEdit.mdx index d85fa6819..561bf590b 100644 --- a/zh/built-in-nodes/TextEncodeQwenImageEdit.mdx +++ b/zh/built-in-nodes/TextEncodeQwenImageEdit.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeQwenImageEdit" icon: "circle" mode: wide --- + TextEncodeQwenImageEdit 节点处理文本提示和可选图像，以生成用于图像生成或编辑的条件数据。它使用 CLIP 模型对输入进行分词，并可选择使用 VAE 对参考图像进行编码以生成参考潜变量。当提供图像时，它会自动调整图像大小以保持一致的处理尺寸。 ## 输入 diff --git a/zh/built-in-nodes/TextEncodeQwenImageEditPlus.mdx b/zh/built-in-nodes/TextEncodeQwenImageEditPlus.mdx index a514da663..14eaf9ce9 100644 --- a/zh/built-in-nodes/TextEncodeQwenImageEditPlus.mdx +++ b/zh/built-in-nodes/TextEncodeQwenImageEditPlus.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeQwenImageEditPlus" icon: "circle" mode: wide --- + TextEncodeQwenImageEditPlus 节点处理文本提示和可选图像，为图像生成或编辑任务生成条件数据。它使用专门的模板分析输入图像，理解文本指令应如何修改图像，然后将此信息编码，供后续生成步骤使用。该节点最多可处理三张输入图像，并在提供 VAE 时可选地生成参考潜空间。 ## 输入 diff --git a/zh/built-in-nodes/TextEncodeZImageOmni.mdx b/zh/built-in-nodes/TextEncodeZImageOmni.mdx index 49f58bbfa..659a4182f 100644 --- a/zh/built-in-nodes/TextEncodeZImageOmni.mdx +++ b/zh/built-in-nodes/TextEncodeZImageOmni.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextEncodeZImageOmni" icon: "circle" mode: wide --- + TextEncodeZImageOmni 节点是一个高级条件节点，它将文本提示以及可选的参考图像编码为适用于图像生成模型的条件格式。该节点最多可处理三张图像，可选择使用视觉编码器和/或 VAE 对其进行编码以生成参考潜变量，并通过特定的模板结构将这些视觉参考与文本提示整合在一起。 ## 输入 diff --git a/zh/built-in-nodes/TextGenerate.mdx b/zh/built-in-nodes/TextGenerate.mdx index bc1581c5d..9d649b866 100644 --- a/zh/built-in-nodes/TextGenerate.mdx +++ b/zh/built-in-nodes/TextGenerate.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextGenerate" icon: "circle" mode: wide --- + TextGenerate 节点使用 CLIP 模型根据用户提示生成文本。它可以选择性地使用图像、视频或音频作为额外上下文来指导文本生成。您可以控制输出长度，为支持的模型启用思考模式，并选择是否使用各种设置的随机采样或直接生成文本而不进行采样。 ## 输入 @@ -34,7 +35,7 @@ TextGenerate 节点使用 CLIP 模型根据用户提示生成文本。它可以 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `generated_text` | 模型根据输入提示和可选的图像、视频或音频生成的文本。 | STRING | +| `生成文本` | 模型根据输入提示和可选的图像、视频或音频生成的文本。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerate/zh.md) diff --git a/zh/built-in-nodes/TextGenerateLTX2Prompt.mdx b/zh/built-in-nodes/TextGenerateLTX2Prompt.mdx index 98f4ce4d6..ecab9c4f5 100644 --- a/zh/built-in-nodes/TextGenerateLTX2Prompt.mdx +++ b/zh/built-in-nodes/TextGenerateLTX2Prompt.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextGenerateLTX2Prompt" icon: "circle" mode: wide --- + TextGenerateLTX2Prompt 节点是文本生成节点的一个专用版本。它接收用户的文本提示，自动使用特定的系统指令进行格式化，然后发送给语言模型进行增强或补全。该节点支持两种运行模式：纯文本模式或附带图像参考模式，每种模式使用不同的系统提示。 ## 输入 @@ -27,7 +28,7 @@ TextGenerateLTX2Prompt 节点是文本生成节点的一个专用版本。它接 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `output` | 由语言模型生成的增强或补全后的文本字符串。 | STRING | +| `生成文本` | 由语言模型生成的增强或补全后的文本字符串。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextGenerateLTX2Prompt/zh.md) diff --git a/zh/built-in-nodes/TextToLowercase.mdx b/zh/built-in-nodes/TextToLowercase.mdx index 1c1bab37f..6445afe44 100644 --- a/zh/built-in-nodes/TextToLowercase.mdx +++ b/zh/built-in-nodes/TextToLowercase.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextToLowercase" icon: "circle" mode: wide --- + 文本转小写节点接收一个文本字符串作为输入，并将其所有字符转换为小写。这是一个用于标准化文本大小写的简单工具。 ## 输入 @@ -17,7 +18,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `text` | 输入文本中所有字符均已转换为小写的结果。 | STRING | +| `文本` | 输入文本中所有字符均已转换为小写的结果。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToLowercase/zh.md) diff --git a/zh/built-in-nodes/TextToUppercase.mdx b/zh/built-in-nodes/TextToUppercase.mdx index 92723d299..523d20040 100644 --- a/zh/built-in-nodes/TextToUppercase.mdx +++ b/zh/built-in-nodes/TextToUppercase.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TextToUppercase" icon: "circle" mode: wide --- + 文本转大写节点接收文本输入，并将其所有字符转换为大写。这是一个简单的文本处理工具，用于修改所提供字符串的大小写。 ## 输入 @@ -17,7 +18,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `text` | 所有字符均已转换为大写的结果文本。 | STRING | +| `文本` | 所有字符均已转换为大写的结果文本。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TextToUppercase/zh.md) diff --git a/zh/built-in-nodes/ThresholdMask.mdx b/zh/built-in-nodes/ThresholdMask.mdx index 7f8910172..cbe9646e8 100644 --- a/zh/built-in-nodes/ThresholdMask.mdx +++ b/zh/built-in-nodes/ThresholdMask.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ThresholdMask" icon: "circle" mode: wide --- + ThresholdMask 节点通过应用阈值将掩码转换为二值掩码。它将输入掩码中的每个像素与指定的阈值进行比较，并创建一个新掩码，其中高于阈值的像素变为 1（白色），低于或等于阈值的像素变为 0（黑色）。 ## 输入 diff --git a/zh/built-in-nodes/TomePatchModel.mdx b/zh/built-in-nodes/TomePatchModel.mdx index 187446b4c..1dbaea7d9 100644 --- a/zh/built-in-nodes/TomePatchModel.mdx +++ b/zh/built-in-nodes/TomePatchModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TomePatchModel" icon: "circle" mode: wide --- + TomePatchModel 节点对扩散模型应用令牌合并（ToMe），以减少推理过程中的计算需求。其工作原理是在注意力机制中选择性地合并相似令牌，使模型能够处理更少的令牌，同时保持图像质量。该技术有助于在无明显质量损失的情况下加速生成。 ## 输入 diff --git a/zh/built-in-nodes/TopazImageEnhance.mdx b/zh/built-in-nodes/TopazImageEnhance.mdx index 79835328c..7b8d994f0 100644 --- a/zh/built-in-nodes/TopazImageEnhance.mdx +++ b/zh/built-in-nodes/TopazImageEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TopazImageEnhance" icon: "circle" mode: wide --- + Topaz Image Enhance 节点提供行业标准的图像放大和增强功能。它通过基于云的AI模型处理单张输入图像，以提升画质、细节和分辨率。该节点提供对增强过程的精细控制，包括创意引导、主体聚焦和人脸保留等选项。 ## 输入 diff --git a/zh/built-in-nodes/TopazVideoEnhance.mdx b/zh/built-in-nodes/TopazVideoEnhance.mdx index 4edbdaceb..2e00c1a14 100644 --- a/zh/built-in-nodes/TopazVideoEnhance.mdx +++ b/zh/built-in-nodes/TopazVideoEnhance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TopazVideoEnhance" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TopazVideoEnhance/en.md) Topaz Video Enhance 节点使用外部 API 来提升视频质量。它可以对视频进行分辨率放大、通过插值提高帧率以及应用压缩。该节点处理输入的 MP4 视频，并根据所选设置返回增强后的版本。 diff --git a/zh/built-in-nodes/TopazVideoEnhanceV2.mdx b/zh/built-in-nodes/TopazVideoEnhanceV2.mdx index 7d7748ce0..73b56d6a6 100644 --- a/zh/built-in-nodes/TopazVideoEnhanceV2.mdx +++ b/zh/built-in-nodes/TopazVideoEnhanceV2.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TopazVideoEnhanceV2" icon: "circle" mode: wide --- -# Topaz Video Enhance V2 **Topaz Video Enhance V2** 节点允许您使用 Topaz Labs 的 AI 模型对视频进行放大和增强。它可以提高分辨率、通过插值调整帧率，并应用创意或写实增强效果，为您的视频素材注入新的活力。 diff --git a/zh/built-in-nodes/TorchCompileModel.mdx b/zh/built-in-nodes/TorchCompileModel.mdx index 15cf44b44..e452b9356 100644 --- a/zh/built-in-nodes/TorchCompileModel.mdx +++ b/zh/built-in-nodes/TorchCompileModel.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TorchCompileModel" icon: "circle" mode: wide --- + TorchCompileModel 节点对模型应用 PyTorch 编译以优化其性能。它会创建输入模型的副本，并使用指定的后端将其包装为 PyTorch 的编译功能。这可以提高模型在推理过程中的执行速度。 ## 输入 diff --git a/zh/built-in-nodes/TrainLoraNode.mdx b/zh/built-in-nodes/TrainLoraNode.mdx index 308caa5e4..6d9875d67 100644 --- a/zh/built-in-nodes/TrainLoraNode.mdx +++ b/zh/built-in-nodes/TrainLoraNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrainLoraNode" icon: "circle" mode: wide --- + TrainLoraNode 使用提供的潜空间数据和条件数据，在扩散模型上创建并训练一个 LoRA（低秩适配）模型。它允许您使用自定义训练参数、优化器和损失函数对模型进行微调。该节点输出训练好的 LoRA 权重、损失历史记录图以及完成的总训练步数。 ## 输入 @@ -45,9 +46,9 @@ TrainLoraNode 使用提供的潜空间数据和条件数据，在扩散模型上 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `LoRA` | 训练好的 LoRA 权重，可以保存或应用于其他模型。 | LORA_MODEL | -| `损失` | 一个包含随时间变化的训练损失值的字典。 | LOSS_MAP | -| `步数` | 完成的总训练步数（包括来自现有 LoRA 的任何先前步数）。 | INT | +| `带LoRA的模型` | 训练好的 LoRA 权重，可以保存或应用于其他模型。 | LORA_MODEL | +| `LoRA` | 一个包含随时间变化的训练损失值的字典。 | LOSS_MAP | +| `损失` | 完成的总训练步数（包括来自现有 LoRA 的任何先前步数）。 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrainLoraNode/zh.md) diff --git a/zh/built-in-nodes/TransformSplat.mdx b/zh/built-in-nodes/TransformSplat.mdx index 953a3b3be..a4ada7868 100644 --- a/zh/built-in-nodes/TransformSplat.mdx +++ b/zh/built-in-nodes/TransformSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TransformSplat" icon: "circle" mode: wide --- -# Transform Splat Transform Splat 节点可对高斯泼溅（gaussian splat）应用平移、旋转和缩放变换。该节点将整个泼溅作为一个整体进行移动、旋转和缩放，当应用非均匀缩放时，还会对每个高斯泼溅进行重塑以获得精确结果。 diff --git a/zh/built-in-nodes/TrimAudioDuration.mdx b/zh/built-in-nodes/TrimAudioDuration.mdx index c5058e9be..5686ca659 100644 --- a/zh/built-in-nodes/TrimAudioDuration.mdx +++ b/zh/built-in-nodes/TrimAudioDuration.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrimAudioDuration" icon: "circle" mode: wide --- + 此文档由 AI 生成。若发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TrimAudioDuration/en.md) TrimAudioDuration 节点允许您从音频文件中裁剪出特定的时间段。您可以指定裁剪的起始时间以及生成的音频片段的时长。该节点通过将时间值转换为音频帧位置，并提取音频波形中的相应部分来实现此功能。 diff --git a/zh/built-in-nodes/TrimVideoLatent.mdx b/zh/built-in-nodes/TrimVideoLatent.mdx index 497bf157a..c68ab805f 100644 --- a/zh/built-in-nodes/TrimVideoLatent.mdx +++ b/zh/built-in-nodes/TrimVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TrimVideoLatent" icon: "circle" mode: wide --- + TrimVideoLatent 节点用于从视频潜在表示的开头移除帧。它接收一个潜在视频样本，并从起始位置裁剪掉指定数量的帧，返回视频的剩余部分。通过移除初始帧，您可以缩短视频序列。 ## 输入 diff --git a/zh/built-in-nodes/TripleCLIPLoader.mdx b/zh/built-in-nodes/TripleCLIPLoader.mdx index fde0f1999..2babf33a2 100644 --- a/zh/built-in-nodes/TripleCLIPLoader.mdx +++ b/zh/built-in-nodes/TripleCLIPLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripleCLIPLoader" icon: "circle" mode: wide --- + TripleCLIPLoader 节点可同时加载三个不同的文本编码器模型，并将它们合并为一个统一的 CLIP 模型。这在需要多个文本编码器的进阶文本编码场景中非常有用，例如在需要 clip-l、clip-g 和 t5 模型协同工作的 SD3 工作流中。 ## 输入 diff --git a/zh/built-in-nodes/TripoConversionNode.mdx b/zh/built-in-nodes/TripoConversionNode.mdx index a02f3a87c..311cb11db 100644 --- a/zh/built-in-nodes/TripoConversionNode.mdx +++ b/zh/built-in-nodes/TripoConversionNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoConversionNode" icon: "circle" mode: wide --- + TripoConversionNode 使用 Tripo API 在不同文件格式之间转换 3D 模型。它接收来自先前 Tripo 操作（模型生成、骨骼绑定或重定向）的任务 ID，并将生成的模型转换为所需格式，并提供多种导出选项。 ## 输入 diff --git a/zh/built-in-nodes/TripoImageToModelNode.mdx b/zh/built-in-nodes/TripoImageToModelNode.mdx index 26d88d71e..d474f93a6 100644 --- a/zh/built-in-nodes/TripoImageToModelNode.mdx +++ b/zh/built-in-nodes/TripoImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoImageToModelNode" icon: "circle" mode: wide --- + 基于单张图像，使用 Tripo 的 API 同步生成 3D 模型。此节点接收输入图像，并通过多种自定义选项（纹理、质量、模型属性）将其转换为 3D 模型。 ## 输入 @@ -31,8 +32,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `模型任务ID` | 生成的 3D 模型文件（仅用于向后兼容） | STRING | -| `GLB` | 用于追踪模型生成过程的任务 ID | MODEL_TASK_ID | +| `模型文件` | 生成的 3D 模型文件（仅用于向后兼容） | STRING | +| `模型任务ID` | 用于追踪模型生成过程的任务 ID | MODEL_TASK_ID | | `GLB` | 以 GLB 格式生成的 3D 模型 | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImageToModelNode/zh.md) diff --git a/zh/built-in-nodes/TripoImportModelNode.mdx b/zh/built-in-nodes/TripoImportModelNode.mdx new file mode 100644 index 000000000..67a8d4b12 --- /dev/null +++ b/zh/built-in-nodes/TripoImportModelNode.mdx @@ -0,0 +1,28 @@ +--- +title: "TripoImportModelNode - ComfyUI Built-in Node Documentation" +description: "Complete documentation for the TripoImportModelNode node in ComfyUI. Learn its inputs, outputs, parameters and usage." +sidebarTitle: "TripoImportModelNode" +icon: "circle" +mode: wide +--- + +此节点将外部 3D 模型文件导入 Tripo 系统，以便您将其与 Tripo 的后处理节点（如 Texture、Rig 和 Convert）配合使用。它会上传您的模型并返回一个任务 ID，其他 Tripo 节点可使用该 ID 引用已导入的模型。 + +## ## 输入 + +| 参数 | 描述 | 数据类型 | 是否必填 | 范围 | +|-----------|-------------|-----------|----------|-------| +| `model_3d` | 要导入的 3D 模型（GLB / FBX / OBJ / STL，最大 150 MB）。OBJ 和 STL 文件不包含嵌入纹理。 | FILE3D | 是 | GLB
FBX
OBJ
STL
任意 3D 格式 | + +**注意：** 建议使用 GLB 格式，因为只有直接嵌入文件中的纹理才能被保留。OBJ 和 STL 文件不支持嵌入纹理。不支持 GLTF（.gltf）格式，因为它会引用外部文件；请改用单文件 GLB。 + +## ## 输出 + +| 输出名称 | 描述 | 数据类型 | +|-------------|-------------|-----------| +| `model task_id` | 标识已导入模型的任务 ID，用于与 Tripo 后处理节点配合使用 | MODEL_TASK_ID | + +> 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoImportModelNode/zh.md) + +--- +**Source fingerprint (SHA-256):** `4fa13a108804f2a52190a85b5b5d58ff18190e9d182b556abada444788012fab` diff --git a/zh/built-in-nodes/TripoMultiviewToModelNode.mdx b/zh/built-in-nodes/TripoMultiviewToModelNode.mdx index 9ae9a72c2..a5b8503f2 100644 --- a/zh/built-in-nodes/TripoMultiviewToModelNode.mdx +++ b/zh/built-in-nodes/TripoMultiviewToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoMultiviewToModelNode" icon: "circle" mode: wide --- + 此节点通过处理最多四张展示物体不同视角的图像，使用 Tripo API 同步生成 3D 模型。它需要一张正面图像以及至少一个额外视角（左、后或右），以创建带有纹理和材质选项的完整 3D 模型。 ## 输入 @@ -33,8 +34,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `模型任务ID` | 生成的 3D 模型的文件路径或标识符（仅用于向后兼容） | STRING | -| `GLB` | 用于跟踪模型生成过程的任务标识符 | MODEL_TASK_ID | +| `模型文件` | 生成的 3D 模型的文件路径或标识符（仅用于向后兼容） | STRING | +| `模型任务ID` | 用于跟踪模型生成过程的任务标识符 | MODEL_TASK_ID | | `GLB` | 以 GLB 格式生成的 3D 模型文件 | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoMultiviewToModelNode/zh.md) diff --git a/zh/built-in-nodes/TripoP1ImageToModelNode.mdx b/zh/built-in-nodes/TripoP1ImageToModelNode.mdx index f7742f115..11268a41b 100644 --- a/zh/built-in-nodes/TripoP1ImageToModelNode.mdx +++ b/zh/built-in-nodes/TripoP1ImageToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoP1ImageToModelNode" icon: "circle" mode: wide --- + ### ## 概述 此节点使用 Tripo P1 API 将单张 2D 图像转换为 3D 模型。它针对生成低多边形、可直接用于游戏的网格进行了优化。 diff --git a/zh/built-in-nodes/TripoP1MultiviewToModelNode.mdx b/zh/built-in-nodes/TripoP1MultiviewToModelNode.mdx index 719e3afbc..973b9f031 100644 --- a/zh/built-in-nodes/TripoP1MultiviewToModelNode.mdx +++ b/zh/built-in-nodes/TripoP1MultiviewToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoP1MultiviewToModelNode" icon: "circle" mode: wide --- + ## ## 概述 此节点根据物体或角色的 2 到 4 张参考图像生成 3D 模型。您提供不同角度（正面、左侧、背面、右侧）的图像，节点将创建 GLB 格式的 3D 网格。正面视图为必填项，您可以选择添加其他三个视图的任意组合以获得更好的效果。 diff --git a/zh/built-in-nodes/TripoP1TextToModelNode.mdx b/zh/built-in-nodes/TripoP1TextToModelNode.mdx index 53c0c8248..be6b5061b 100644 --- a/zh/built-in-nodes/TripoP1TextToModelNode.mdx +++ b/zh/built-in-nodes/TripoP1TextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoP1TextToModelNode" icon: "circle" mode: wide --- + ## ## 概述 此节点使用 Tripo P1 API 根据文本描述生成 3D 模型。它针对创建低多边形、可直接用于游戏的网格进行了优化，具有稳定的拓扑结构，适用于实时应用。 diff --git a/zh/built-in-nodes/TripoRefineNode.mdx b/zh/built-in-nodes/TripoRefineNode.mdx index df8323e77..12b40b59d 100644 --- a/zh/built-in-nodes/TripoRefineNode.mdx +++ b/zh/built-in-nodes/TripoRefineNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoRefineNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/en.md) TripoRefineNode 用于优化由 Tripo v1.4 模型专门生成的 3D 草稿模型。它接收一个模型任务 ID，并通过 Tripo API 进行处理，生成该模型的改进版本。此节点仅适用于 Tripo v1.4 模型生成的草稿模型。 @@ -21,8 +22,8 @@ TripoRefineNode 用于优化由 Tripo v1.4 模型专门生成的 3D 草稿模型 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `模型任务ID` | 优化后模型的文件路径或引用（仅用于向后兼容） | STRING | -| `GLB` | 优化模型操作的任务标识符 | MODEL_TASK_ID | +| `模型文件` | 优化后模型的文件路径或引用（仅用于向后兼容） | STRING | +| `模型任务ID` | 优化模型操作的任务标识符 | MODEL_TASK_ID | | `GLB` | 优化后的 3D 模型，格式为 GLB | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRefineNode/zh.md) diff --git a/zh/built-in-nodes/TripoRetargetNode.mdx b/zh/built-in-nodes/TripoRetargetNode.mdx index a7e0f98a8..5ab964d53 100644 --- a/zh/built-in-nodes/TripoRetargetNode.mdx +++ b/zh/built-in-nodes/TripoRetargetNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoRetargetNode" icon: "circle" mode: wide --- + TripoRetargetNode 通过重定向运动数据，将预设动画应用于 3D 角色模型。它接收一个先前已绑定骨骼的 3D 模型，并应用多种预设动画之一，生成动画 3D 模型文件作为输出。该节点与 Tripo API 通信以处理动画重定向操作。 ## 输入 @@ -21,8 +22,8 @@ TripoRetargetNode 通过重定向运动数据，将预设动画应用于 3D 角 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `重定向任务ID` | 生成的动画 3D 模型文件（仅用于向后兼容） | STRING | -| `GLB` | 用于跟踪重定向操作的任务 ID | RETARGET_TASK_ID | +| `模型文件` | 生成的动画 3D 模型文件（仅用于向后兼容） | STRING | +| `重定向任务ID` | 用于跟踪重定向操作的任务 ID | RETARGET_TASK_ID | | `GLB` | GLB 格式的动画 3D 模型 | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRetargetNode/zh.md) diff --git a/zh/built-in-nodes/TripoRigNode.mdx b/zh/built-in-nodes/TripoRigNode.mdx index f40706682..cb24c7440 100644 --- a/zh/built-in-nodes/TripoRigNode.mdx +++ b/zh/built-in-nodes/TripoRigNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoRigNode" icon: "circle" mode: wide --- + TripoRigNode 根据原始模型任务 ID 生成一个带有骨骼绑定的 3D 模型。它会向 Tripo API 发送请求，使用 Tripo 规范创建 GLB 格式的动画骨骼，然后轮询 API 直至骨骼生成任务完成。 ## 输入 @@ -20,8 +21,8 @@ TripoRigNode 根据原始模型任务 ID 生成一个带有骨骼绑定的 3D | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `绑定任务ID` | 生成的带骨骼绑定的 3D 模型文件（为保持向后兼容性而保留） | STRING | -| `GLB` | 用于跟踪骨骼生成过程的任务 ID | RIG_TASK_ID | +| `模型文件` | 生成的带骨骼绑定的 3D 模型文件（为保持向后兼容性而保留） | STRING | +| `绑定任务ID` | 用于跟踪骨骼生成过程的任务 ID | RIG_TASK_ID | | `GLB` | 以 GLB 格式生成的带骨骼绑定的 3D 模型 | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoRigNode/zh.md) diff --git a/zh/built-in-nodes/TripoSplatConditioning.mdx b/zh/built-in-nodes/TripoSplatConditioning.mdx index cdbc34a99..d3436b2de 100644 --- a/zh/built-in-nodes/TripoSplatConditioning.mdx +++ b/zh/built-in-nodes/TripoSplatConditioning.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatConditioning" icon: "circle" mode: wide --- -# TripoSplat 条件控制 此节点使用 DINOv3 和 Flux2 VAE 对输入图像进行编码，为 TripoSplat 模型生成正向和负向条件控制数据。同时生成一个固定尺寸的噪声目标（潜空间数据加相机数据），作为 KSampler 的起始点。 diff --git a/zh/built-in-nodes/TripoSplatPreprocessImage.mdx b/zh/built-in-nodes/TripoSplatPreprocessImage.mdx index 060b26287..a64631017 100644 --- a/zh/built-in-nodes/TripoSplatPreprocessImage.mdx +++ b/zh/built-in-nodes/TripoSplatPreprocessImage.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatPreprocessImage" icon: "circle" mode: wide --- -# TripoSplat 图像预处理节点 此节点将每张输入图像裁剪为黑色背景上的居中正方形，然后添加填充以达到指定的输出尺寸。它旨在通过确保一致的方形构图和可选的 Alpha 遮罩腐蚀来防止边框伪影，从而为 TripoSplat 3D 模型准备图像。 diff --git a/zh/built-in-nodes/TripoSplatSamplingPreview.mdx b/zh/built-in-nodes/TripoSplatSamplingPreview.mdx index b17b73cc7..cc60d5c87 100644 --- a/zh/built-in-nodes/TripoSplatSamplingPreview.mdx +++ b/zh/built-in-nodes/TripoSplatSamplingPreview.mdx @@ -5,7 +5,6 @@ sidebarTitle: "TripoSplatSamplingPreview" icon: "circle" mode: wide --- -# TripoSplat 采样预览 此节点用于修补 TripoSplat 模型，使其在与标准 KSampler 节点配合使用时，能在每个采样步骤显示解码后的高斯泼溅实时预览。其工作原理是封装采样器的回调函数，在每一步之后将模型输出解码为预览图像。 diff --git a/zh/built-in-nodes/TripoTextToModelNode.mdx b/zh/built-in-nodes/TripoTextToModelNode.mdx index 2c1ce3d20..28510b859 100644 --- a/zh/built-in-nodes/TripoTextToModelNode.mdx +++ b/zh/built-in-nodes/TripoTextToModelNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoTextToModelNode" icon: "circle" mode: wide --- + 根据文本描述，使用 Tripo 的 API 同步生成 3D 模型。此节点接收文本描述，并创建具有可选纹理和材质属性的 3D 模型。 ## 输入 @@ -31,8 +32,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `模型任务ID` | 生成的 3D 模型文件（仅用于向后兼容） | STRING | -| `GLB` | 模型生成过程的唯一任务标识符 | MODEL_TASK_ID | +| `模型文件` | 生成的 3D 模型文件（仅用于向后兼容） | STRING | +| `模型任务ID` | 模型生成过程的唯一任务标识符 | MODEL_TASK_ID | | `GLB` | 以 GLB 格式生成的 3D 模型 | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextToModelNode/zh.md) diff --git a/zh/built-in-nodes/TripoTextureNode.mdx b/zh/built-in-nodes/TripoTextureNode.mdx index a142fad37..dc06a5d08 100644 --- a/zh/built-in-nodes/TripoTextureNode.mdx +++ b/zh/built-in-nodes/TripoTextureNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TripoTextureNode" icon: "circle" mode: wide --- + TripoTextureNode 使用 Tripo API 生成带纹理的 3D 模型。它接收一个模型任务 ID，并通过多种选项（包括 PBR 材质、纹理质量设置和对齐方法）应用纹理生成。该节点与 Tripo API 通信以处理纹理生成请求，并返回生成的模型文件和任务 ID。 ## 输入 @@ -24,8 +25,8 @@ TripoTextureNode 使用 Tripo API 生成带纹理的 3D 模型。它接收一个 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `模型任务ID` | 已应用纹理的生成模型文件（仅用于向后兼容） | STRING | -| `GLB` | 用于跟踪纹理生成过程的任务 ID | MODEL_TASK_ID | +| `模型文件` | 已应用纹理的生成模型文件（仅用于向后兼容） | STRING | +| `模型任务ID` | 用于跟踪纹理生成过程的任务 ID | MODEL_TASK_ID | | `GLB` | 已应用纹理的 GLB 格式 3D 模型 | FILE3DGLB | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TripoTextureNode/zh.md) diff --git a/zh/built-in-nodes/TruncateText.mdx b/zh/built-in-nodes/TruncateText.mdx index e654697ea..45a9cbdf0 100644 --- a/zh/built-in-nodes/TruncateText.mdx +++ b/zh/built-in-nodes/TruncateText.mdx @@ -5,6 +5,7 @@ sidebarTitle: "TruncateText" icon: "circle" mode: wide --- + 此节点通过在指定最大长度处截断文本来缩短文本。它接收任意输入文本，仅返回从开头到您设置的字符数部分。这是一种确保文本不超过特定大小的简单方法。 ## 输入 @@ -18,7 +19,7 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `string` | 截断后的文本，仅包含输入文本的前 `长度上限` 个字符。 | STRING | +| `文本` | 截断后的文本，仅包含输入文本的前 `长度上限` 个字符。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/TruncateText/zh.md) diff --git a/zh/built-in-nodes/UNETLoader.mdx b/zh/built-in-nodes/UNETLoader.mdx index a1202be14..394cc0a58 100644 --- a/zh/built-in-nodes/UNETLoader.mdx +++ b/zh/built-in-nodes/UNETLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNETLoader" icon: "circle" mode: wide --- + UNETLoader 节点用于按名称加载 U-Net 模型，便于在系统中使用预训练的 U-Net 架构。 此节点将检测位于 `ComfyUI/models/diffusion_models` 文件夹中的模型。 diff --git a/zh/built-in-nodes/UNetCrossAttentionMultiply.mdx b/zh/built-in-nodes/UNetCrossAttentionMultiply.mdx index c6ae76440..ee41fd119 100644 --- a/zh/built-in-nodes/UNetCrossAttentionMultiply.mdx +++ b/zh/built-in-nodes/UNetCrossAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetCrossAttentionMultiply" icon: "circle" mode: wide --- + UNetCrossAttentionMultiply 节点对 UNet 模型中的交叉注意力机制应用乘法因子。它允许您缩放交叉注意力层的查询、键、值和输出分量，以试验不同的注意力行为和效果。 ## 输入 diff --git a/zh/built-in-nodes/UNetSelfAttentionMultiply.mdx b/zh/built-in-nodes/UNetSelfAttentionMultiply.mdx index e6151d20e..671fc327e 100644 --- a/zh/built-in-nodes/UNetSelfAttentionMultiply.mdx +++ b/zh/built-in-nodes/UNetSelfAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetSelfAttentionMultiply" icon: "circle" mode: wide --- + UNetSelfAttentionMultiply 节点对 UNet 模型中的自注意力机制的查询、键、值和输出分量应用乘法因子。它允许您缩放注意力计算的不同部分，以试验注意力权重如何影响模型的行为。 ## 输入 diff --git a/zh/built-in-nodes/UNetTemporalAttentionMultiply.mdx b/zh/built-in-nodes/UNetTemporalAttentionMultiply.mdx index c0743a545..236e3dd95 100644 --- a/zh/built-in-nodes/UNetTemporalAttentionMultiply.mdx +++ b/zh/built-in-nodes/UNetTemporalAttentionMultiply.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UNetTemporalAttentionMultiply" icon: "circle" mode: wide --- + UNetTemporalAttentionMultiply 节点对时序 UNet 模型中的不同注意力机制应用乘法因子。它通过调整自注意力和交叉注意力层的权重来修改模型，并区分结构组件和时序组件。这使得可以精细调整每种注意力类型对模型输出的影响程度。 ## 输入 diff --git a/zh/built-in-nodes/USOStyleReference.mdx b/zh/built-in-nodes/USOStyleReference.mdx index 0e2a8350a..5cb8cd95a 100644 --- a/zh/built-in-nodes/USOStyleReference.mdx +++ b/zh/built-in-nodes/USOStyleReference.mdx @@ -5,6 +5,7 @@ sidebarTitle: "USOStyleReference" icon: "circle" mode: wide --- + USOStyleReference 节点使用来自 CLIP 视觉输出的编码图像特征，将样式参考补丁应用于模型。它通过整合从视觉输入中提取的样式信息，创建输入模型的修改版本，从而实现样式迁移或基于参考的生成能力。 ## 输入 diff --git a/zh/built-in-nodes/UpscaleModelLoader.mdx b/zh/built-in-nodes/UpscaleModelLoader.mdx index ab63a6cd3..7c07e8843 100644 --- a/zh/built-in-nodes/UpscaleModelLoader.mdx +++ b/zh/built-in-nodes/UpscaleModelLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "UpscaleModelLoader" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/upscale_models` 文件夹中的模型，同时也会读取在 extra_model_paths.yaml 文件中配置的其他路径中的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够读取相应文件夹中的模型文件。 UpscaleModelLoader 节点用于从指定目录加载放大模型。它有助于检索和准备用于图像放大任务的放大模型，确保模型被正确加载并配置为评估状态。 diff --git a/zh/built-in-nodes/VAEDecode.mdx b/zh/built-in-nodes/VAEDecode.mdx index dec884b8a..1eec51f03 100644 --- a/zh/built-in-nodes/VAEDecode.mdx +++ b/zh/built-in-nodes/VAEDecode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecode" icon: "circle" mode: wide --- + VAEDecode 节点专用于使用指定的变分自编码器（VAE）将潜在表示解码为图像。其目的是从压缩数据表示中生成图像，促进从潜在空间编码中重建图像。 ## 输入 diff --git a/zh/built-in-nodes/VAEDecodeAudio.mdx b/zh/built-in-nodes/VAEDecodeAudio.mdx index bc3488930..6869ed2e8 100644 --- a/zh/built-in-nodes/VAEDecodeAudio.mdx +++ b/zh/built-in-nodes/VAEDecodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeAudio" icon: "circle" mode: wide --- + VAEDecodeAudio 节点使用变分自编码器将潜在表示转换回音频波形。它接收编码后的音频样本，通过 VAE 进行处理以重建原始音频，并应用归一化确保输出电平一致。最终输出的音频采用 44100 Hz 标准采样率。 ## 输入 diff --git a/zh/built-in-nodes/VAEDecodeAudioTiled.mdx b/zh/built-in-nodes/VAEDecodeAudioTiled.mdx index 3f94164e6..beb426e5a 100644 --- a/zh/built-in-nodes/VAEDecodeAudioTiled.mdx +++ b/zh/built-in-nodes/VAEDecodeAudioTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeAudioTiled" icon: "circle" mode: wide --- + 此节点使用变分自编码器（VAE）将压缩的音频表示（潜在样本）转换回音频波形。它通过将数据分割成较小的重叠区块（tiles）进行处理，以管理内存使用，从而适用于处理较长的音频序列。 ## 输入 diff --git a/zh/built-in-nodes/VAEDecodeHunyuan3D.mdx b/zh/built-in-nodes/VAEDecodeHunyuan3D.mdx index 4c2829fc6..99639f854 100644 --- a/zh/built-in-nodes/VAEDecodeHunyuan3D.mdx +++ b/zh/built-in-nodes/VAEDecodeHunyuan3D.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeHunyuan3D" icon: "circle" mode: wide --- + VAEDecodeHunyuan3D 节点使用 VAE 解码器将潜在表示转换为 3D 体素数据。它通过可配置的分块和分辨率设置，利用 VAE 模型处理潜在样本，生成适用于 3D 应用的体积数据。 ## 输入 diff --git a/zh/built-in-nodes/VAEDecodeTiled.mdx b/zh/built-in-nodes/VAEDecodeTiled.mdx index 808f74375..a14b652a9 100644 --- a/zh/built-in-nodes/VAEDecodeTiled.mdx +++ b/zh/built-in-nodes/VAEDecodeTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEDecodeTiled" icon: "circle" mode: wide --- + VAEDecodeTiled 节点采用分块处理方法，将潜在表示高效解码为图像，以应对大尺寸图像的处理需求。它通过将输入分割为较小的图块进行处理，在保持图像质量的同时有效管理内存使用。该节点还支持视频 VAE，通过分块处理时间帧并设置重叠区域以实现平滑过渡。 ## 输入 diff --git a/zh/built-in-nodes/VAEDecodeTripoSplat.mdx b/zh/built-in-nodes/VAEDecodeTripoSplat.mdx index a4c06cfb0..4981c2fc3 100644 --- a/zh/built-in-nodes/VAEDecodeTripoSplat.mdx +++ b/zh/built-in-nodes/VAEDecodeTripoSplat.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VAEDecodeTripoSplat" icon: "circle" mode: wide --- -# VAEDecodeTripoSplat 将 TripoSplat 潜在表示解码为 3D 高斯泼溅。此节点接收从 TripoSplat 模型采样的潜在变量，并将其重建为一组 3D 高斯体，可通过修改生成的高斯体数量来调整密度。 diff --git a/zh/built-in-nodes/VAEEncode.mdx b/zh/built-in-nodes/VAEEncode.mdx index 1af847a80..936b51b78 100644 --- a/zh/built-in-nodes/VAEEncode.mdx +++ b/zh/built-in-nodes/VAEEncode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncode" icon: "circle" mode: wide --- + 此节点用于使用指定的 VAE 模型将图像编码为潜在空间表示。它抽象了编码过程的复杂性，提供了一种将图像转换为其潜在表示的直观方法。 ## 输入 diff --git a/zh/built-in-nodes/VAEEncodeAudio.mdx b/zh/built-in-nodes/VAEEncodeAudio.mdx index 8667fd333..5443d4467 100644 --- a/zh/built-in-nodes/VAEEncodeAudio.mdx +++ b/zh/built-in-nodes/VAEEncodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeAudio" icon: "circle" mode: wide --- + VAEEncodeAudio 节点使用变分自编码器（VAE）将音频数据转换为潜在表示。它接收音频输入，并通过 VAE 进行处理，生成压缩的潜在样本，可用于后续的音频生成或处理任务。在编码前，如有必要，节点会自动对音频进行重采样，以匹配 VAE 预期的采样率。 ## 输入 diff --git a/zh/built-in-nodes/VAEEncodeForInpaint.mdx b/zh/built-in-nodes/VAEEncodeForInpaint.mdx index e6271ae3d..c5e65f9dd 100644 --- a/zh/built-in-nodes/VAEEncodeForInpaint.mdx +++ b/zh/built-in-nodes/VAEEncodeForInpaint.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeForInpaint" icon: "circle" mode: wide --- + 此节点专为将图像编码为适用于修复任务的潜在表示而设计，并包含额外的预处理步骤，以调整输入图像和遮罩，确保 VAE 模型能够进行最佳编码。 ## 输入 diff --git a/zh/built-in-nodes/VAEEncodeTiled.mdx b/zh/built-in-nodes/VAEEncodeTiled.mdx index 618e6698c..884e8bbb6 100644 --- a/zh/built-in-nodes/VAEEncodeTiled.mdx +++ b/zh/built-in-nodes/VAEEncodeTiled.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAEEncodeTiled" icon: "circle" mode: wide --- + ## 概述 VAEEncodeTiled 节点通过将图像分割成较小的图块，并使用变分自编码器对其进行编码来处理图像。这种分块处理方法能够处理可能超出内存限制的大型图像。该节点支持图像和视频 VAE，并针对空间和时间维度提供了独立的图块控制。 diff --git a/zh/built-in-nodes/VAELoader.mdx b/zh/built-in-nodes/VAELoader.mdx index 53e697605..0d352c3f9 100644 --- a/zh/built-in-nodes/VAELoader.mdx +++ b/zh/built-in-nodes/VAELoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VAELoader" icon: "circle" mode: wide --- + 此节点会检测位于 `ComfyUI/models/vae` 文件夹中的模型，同时也会读取 extra_model_paths.yaml 文件中配置的其他路径下的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它能够读取相应文件夹中的模型文件。 VAELoader 节点专为加载变分自编码器（VAE）模型而设计，特别适用于处理标准 VAE 和近似 VAE。它支持按名称加载 VAE，包括对 'taesd' 和 'taesdxl' 模型的特殊处理，并能根据 VAE 的具体配置动态调整。 diff --git a/zh/built-in-nodes/VAESave.mdx b/zh/built-in-nodes/VAESave.mdx index ef36c4e8e..e308ff7f8 100644 --- a/zh/built-in-nodes/VAESave.mdx +++ b/zh/built-in-nodes/VAESave.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VAESave" icon: "circle" mode: wide --- -# 概述 VAESave 节点用于将 VAE 模型及其元数据（包括提示词和额外的 PNG 信息）保存到指定的输出目录。它封装了将模型状态和相关关联信息序列化到文件中的功能，便于保存和共享训练好的模型。 diff --git a/zh/built-in-nodes/VOIDInpaintConditioning.mdx b/zh/built-in-nodes/VOIDInpaintConditioning.mdx index 9c08f56b6..63eaa125f 100644 --- a/zh/built-in-nodes/VOIDInpaintConditioning.mdx +++ b/zh/built-in-nodes/VOIDInpaintConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDInpaintConditioning" icon: "circle" mode: wide --- + VOIDInpaintConditioning 节点用于准备 CogVideoX 模型进行修复所需的 conditioning 数据。它接收源视频和预处理后的四重遮罩（quadmask），通过 VAE 对其进行编码，并将其组合成一个 32 通道的 conditioning 信号，供模型用于填充遮罩区域。 ## 输入 @@ -25,8 +26,8 @@ VOIDInpaintConditioning 节点用于准备 CogVideoX 模型进行修复所需的 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `negative` | 已添加修复潜在信息的正向 conditioning | CONDITIONING | -| `latent` | 已添加修复潜在信息的负向 conditioning | CONDITIONING | +| `positive` | 已添加修复潜在信息的正向 conditioning | CONDITIONING | +| `negative` | 已添加修复潜在信息的负向 conditioning | CONDITIONING | | `latent` | 形状为 [batch_size, 16, latent_t, latent_h, latent_w] 的零填充噪声潜在张量 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/VOIDInpaintConditioning/zh.md) diff --git a/zh/built-in-nodes/VOIDQuadmaskPreprocess.mdx b/zh/built-in-nodes/VOIDQuadmaskPreprocess.mdx index 6626bf96c..aac3e25ac 100644 --- a/zh/built-in-nodes/VOIDQuadmaskPreprocess.mdx +++ b/zh/built-in-nodes/VOIDQuadmaskPreprocess.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDQuadmaskPreprocess" icon: "circle" mode: wide --- + ## 概述 VOIDQuadmaskPreprocess 节点通过将遮罩转换为特殊的四层级“四重遮罩”，为 VOID 修复任务准备遮罩。它接收输入遮罩，可选择性地对主要区域进行膨胀处理，然后将遮罩值量化为四个不同层级，分别代表不同的语义区域（主要物体、重叠区域、受影响区域和背景）。最后，它会对遮罩进行反转和归一化，使输出值落在 [0, 1] 范围内，其中 1.0 表示要移除的区域，0.0 表示要保留的区域。 diff --git a/zh/built-in-nodes/VOIDSampler.mdx b/zh/built-in-nodes/VOIDSampler.mdx index 93e76e4e8..8615878eb 100644 --- a/zh/built-in-nodes/VOIDSampler.mdx +++ b/zh/built-in-nodes/VOIDSampler.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDSampler" icon: "circle" mode: wide --- + ## 概述 VOIDSampler 节点提供了一种专门为 VOID 修复模型设计的 DDIM 采样方法。它实现了 VOID 模型训练过程中使用的相同去噪流程，但未应用标准 KSampler 所采用的噪声缩放。此节点旨在与 SamplerCustom 或 SamplerCustomAdvanced 节点配合使用，并应与 RandomNoise 或 VOIDWarpedNoiseSource 配对。 diff --git a/zh/built-in-nodes/VOIDWarpedNoise.mdx b/zh/built-in-nodes/VOIDWarpedNoise.mdx index 64e39adc8..0fa645e0e 100644 --- a/zh/built-in-nodes/VOIDWarpedNoise.mdx +++ b/zh/built-in-nodes/VOIDWarpedNoise.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDWarpedNoise" icon: "circle" mode: wide --- + ## 概述 为 VOID 视频优化流程的第二遍生成时间相关的噪声。它接收第一遍输出的视频，并沿着光流矢量扭曲高斯噪声，生成与视频内容一致运动的噪声。该扭曲噪声用作第二遍的初始潜在表示，从而改善最终输出的时间一致性。 diff --git a/zh/built-in-nodes/VOIDWarpedNoiseSource.mdx b/zh/built-in-nodes/VOIDWarpedNoiseSource.mdx index 5ad831882..5d8af35c1 100644 --- a/zh/built-in-nodes/VOIDWarpedNoiseSource.mdx +++ b/zh/built-in-nodes/VOIDWarpedNoiseSource.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VOIDWarpedNoiseSource" icon: "circle" mode: wide --- + ## 概述 此节点将 LATENT（例如 VOIDWarpedNoise 节点的输出）转换为 NOISE 源。这样，您就可以将扭曲后的噪声与 SamplerCustomAdvanced 节点配合使用，实现更可控的图像生成。 diff --git a/zh/built-in-nodes/VPScheduler.mdx b/zh/built-in-nodes/VPScheduler.mdx index 5d24c6158..44b811d19 100644 --- a/zh/built-in-nodes/VPScheduler.mdx +++ b/zh/built-in-nodes/VPScheduler.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VPScheduler" icon: "circle" mode: wide --- -# ## 概述 VPScheduler 节点旨在基于方差保持（VP）调度方法生成一系列噪声水平（sigma 值）。该序列对于指导扩散模型中的去噪过程至关重要，可实现图像或其他数据类型的受控生成。 diff --git a/zh/built-in-nodes/Veo3FirstLastFrameNode.mdx b/zh/built-in-nodes/Veo3FirstLastFrameNode.mdx index e349e5f33..8c56b7444 100644 --- a/zh/built-in-nodes/Veo3FirstLastFrameNode.mdx +++ b/zh/built-in-nodes/Veo3FirstLastFrameNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Veo3FirstLastFrameNode" icon: "circle" mode: wide --- + Veo3FirstLastFrameNode 使用 Google 的 Veo 3 模型，根据文本提示生成视频，并提供定义视频序列起始和结束的首帧与末帧。 ## 输入 diff --git a/zh/built-in-nodes/Veo3VideoGenerationNode.mdx b/zh/built-in-nodes/Veo3VideoGenerationNode.mdx index ee439d140..941e4c255 100644 --- a/zh/built-in-nodes/Veo3VideoGenerationNode.mdx +++ b/zh/built-in-nodes/Veo3VideoGenerationNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Veo3VideoGenerationNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Veo3VideoGenerationNode/en.md) 使用 Google 的 Veo 3 API 根据文本提示生成视频。此节点支持多种 Veo 3 模型，包括快速版和精简版，并允许您指定视频分辨率、时长和音频生成。 diff --git a/zh/built-in-nodes/VeoVideoGenerationNode.mdx b/zh/built-in-nodes/VeoVideoGenerationNode.mdx index 4572ee3be..a32f81c7e 100644 --- a/zh/built-in-nodes/VeoVideoGenerationNode.mdx +++ b/zh/built-in-nodes/VeoVideoGenerationNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "VeoVideoGenerationNode" icon: "circle" mode: wide --- -# ## 概述 此节点使用 Google 的 Veo 2 API 根据文本提示生成视频。该节点可以根据文本描述和可选的图像输入创建视频，并可控制宽高比、时长等参数。 diff --git a/zh/built-in-nodes/Video Slice.mdx b/zh/built-in-nodes/Video Slice.mdx index b344abecf..29d7c76bc 100644 --- a/zh/built-in-nodes/Video Slice.mdx +++ b/zh/built-in-nodes/Video Slice.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Video Slice" icon: "circle" mode: wide --- + 视频切片节点允许您从视频中提取特定片段。您可以定义开始时间和持续时间来裁剪视频，或直接跳过开头帧。如果请求的持续时间超过剩余视频长度，该节点可以返回可用部分或引发错误。 ## 输入 diff --git a/zh/built-in-nodes/VideoLinearCFGGuidance.mdx b/zh/built-in-nodes/VideoLinearCFGGuidance.mdx index d4f3d7504..afd0528b4 100644 --- a/zh/built-in-nodes/VideoLinearCFGGuidance.mdx +++ b/zh/built-in-nodes/VideoLinearCFGGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VideoLinearCFGGuidance" icon: "circle" mode: wide --- + VideoLinearCFGGuidance 节点对视频模型应用线性条件引导缩放，在指定范围内调整条件与非条件成分的影响程度。这实现了对生成过程的动态控制，允许根据所需条件水平对模型输出进行精细调节。 ## 输入 diff --git a/zh/built-in-nodes/VideoTriangleCFGGuidance.mdx b/zh/built-in-nodes/VideoTriangleCFGGuidance.mdx index 0998e4fd4..64c552f38 100644 --- a/zh/built-in-nodes/VideoTriangleCFGGuidance.mdx +++ b/zh/built-in-nodes/VideoTriangleCFGGuidance.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VideoTriangleCFGGuidance" icon: "circle" mode: wide --- + VideoTriangleCFGGuidance 节点对视频模型应用三角形无分类器引导缩放模式。它使用三角波函数随时间调整条件缩放比例，该函数在最小 CFG 值与原始条件缩放比例之间振荡。这会创建一种动态引导模式，有助于提高视频生成的一致性和质量。 ## 输入 diff --git a/zh/built-in-nodes/Vidu2ImageToVideoNode.mdx b/zh/built-in-nodes/Vidu2ImageToVideoNode.mdx index 45ff165d9..8b5752cbb 100644 --- a/zh/built-in-nodes/Vidu2ImageToVideoNode.mdx +++ b/zh/built-in-nodes/Vidu2ImageToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "Vidu2ImageToVideoNode" icon: "circle" mode: wide --- -# Vidu2 图像转视频节点 Vidu2 图像转视频节点可从单张输入图像创建视频序列。它使用指定的 Vidu2 模型，基于可选的文本提示为场景添加动画效果，并控制视频长度、分辨率和运动强度。 diff --git a/zh/built-in-nodes/Vidu2ReferenceVideoNode.mdx b/zh/built-in-nodes/Vidu2ReferenceVideoNode.mdx index 1b22d0581..06cc6fd22 100644 --- a/zh/built-in-nodes/Vidu2ReferenceVideoNode.mdx +++ b/zh/built-in-nodes/Vidu2ReferenceVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2ReferenceVideoNode" icon: "circle" mode: wide --- + Vidu2 参考图生成视频节点可根据文本提示和多张参考图像创建视频。您可以定义最多七个主体，每个主体拥有独立的参考图像集，并在提示中使用 `@subject{subject_id}` 引用它们。该节点可生成具有可配置时长、宽高比和运动幅度的视频。 ## 输入 diff --git a/zh/built-in-nodes/Vidu2StartEndToVideoNode.mdx b/zh/built-in-nodes/Vidu2StartEndToVideoNode.mdx index 287019f22..da3d099d3 100644 --- a/zh/built-in-nodes/Vidu2StartEndToVideoNode.mdx +++ b/zh/built-in-nodes/Vidu2StartEndToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2StartEndToVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu2StartEndToVideoNode/en.md) 此节点通过在提供的起始帧和结束帧之间进行插值，并在文本提示的引导下生成视频。它使用指定的 Vidu 模型，在设定的时长内创建两幅图像之间的平滑过渡。 diff --git a/zh/built-in-nodes/Vidu2TextToVideoNode.mdx b/zh/built-in-nodes/Vidu2TextToVideoNode.mdx index a957a094e..7689de1e4 100644 --- a/zh/built-in-nodes/Vidu2TextToVideoNode.mdx +++ b/zh/built-in-nodes/Vidu2TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu2TextToVideoNode" icon: "circle" mode: wide --- + Vidu2 文本转视频生成节点可根据文本描述创建视频。该节点通过连接外部 API，基于您的提示词生成视频内容，并允许您控制视频长度、视觉风格和格式。 ## 输入 diff --git a/zh/built-in-nodes/Vidu3ImageToVideoNode.mdx b/zh/built-in-nodes/Vidu3ImageToVideoNode.mdx index 01758970c..5f2d97966 100644 --- a/zh/built-in-nodes/Vidu3ImageToVideoNode.mdx +++ b/zh/built-in-nodes/Vidu3ImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3ImageToVideoNode" icon: "circle" mode: wide --- + Vidu Q3 图像转视频生成节点可根据输入图像创建视频序列。它使用 Vidu Q3 模型对图像进行动画处理，可选择通过文本提示进行引导，并输出视频文件。 ## 输入 diff --git a/zh/built-in-nodes/Vidu3StartEndToVideoNode.mdx b/zh/built-in-nodes/Vidu3StartEndToVideoNode.mdx index 9ab945a35..39ef8acae 100644 --- a/zh/built-in-nodes/Vidu3StartEndToVideoNode.mdx +++ b/zh/built-in-nodes/Vidu3StartEndToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3StartEndToVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Vidu3StartEndToVideoNode/en.md) 此节点通过在提供的起始帧和结束帧之间进行插值，并在文本提示的引导下生成视频。它使用 Vidu Q3 模型在两幅图像之间创建无缝过渡，生成指定时长和分辨率的视频。 diff --git a/zh/built-in-nodes/Vidu3TextToVideoNode.mdx b/zh/built-in-nodes/Vidu3TextToVideoNode.mdx index f7aa25df2..d064680ee 100644 --- a/zh/built-in-nodes/Vidu3TextToVideoNode.mdx +++ b/zh/built-in-nodes/Vidu3TextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Vidu3TextToVideoNode" icon: "circle" mode: wide --- + Vidu Q3 文本转视频生成节点可根据文本描述创建视频。它使用 Vidu Q3 Pro 或 Q3 Turbo 模型，基于您的提示词生成视频内容，并允许您控制视频长度、分辨率、宽高比以及是否包含音频。 ## 输入 diff --git a/zh/built-in-nodes/ViduExtendVideoNode.mdx b/zh/built-in-nodes/ViduExtendVideoNode.mdx index 6c26b2da6..b0904adcd 100644 --- a/zh/built-in-nodes/ViduExtendVideoNode.mdx +++ b/zh/built-in-nodes/ViduExtendVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduExtendVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduExtendVideoNode/en.md) ViduExtendVideoNode 节点用于生成额外帧，以延长现有视频的长度。它基于源视频和可选文本提示，使用指定的 AI 模型创建无缝衔接的延续内容。 diff --git a/zh/built-in-nodes/ViduImageToVideoNode.mdx b/zh/built-in-nodes/ViduImageToVideoNode.mdx index 3c51eb22f..33c58f7fa 100644 --- a/zh/built-in-nodes/ViduImageToVideoNode.mdx +++ b/zh/built-in-nodes/ViduImageToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduImageToVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduImageToVideoNode/en.md) Vidu 图像转视频生成节点可根据起始图像和可选的文本描述创建短视频。它使用 AI 模型从提供的图像帧开始生成视频内容，并返回生成的视频。 diff --git a/zh/built-in-nodes/ViduMultiFrameVideoNode.mdx b/zh/built-in-nodes/ViduMultiFrameVideoNode.mdx index 3e0b71e14..e654da39a 100644 --- a/zh/built-in-nodes/ViduMultiFrameVideoNode.mdx +++ b/zh/built-in-nodes/ViduMultiFrameVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduMultiFrameVideoNode" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ViduMultiFrameVideoNode/en.md) 此节点通过在多个关键帧之间创建过渡来生成视频。它从初始图像开始，通过一系列用户定义的结束图像和提示进行动画处理，最终输出一个视频文件。 diff --git a/zh/built-in-nodes/ViduReferenceVideoNode.mdx b/zh/built-in-nodes/ViduReferenceVideoNode.mdx index 192494c50..f45b8d252 100644 --- a/zh/built-in-nodes/ViduReferenceVideoNode.mdx +++ b/zh/built-in-nodes/ViduReferenceVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduReferenceVideoNode" icon: "circle" mode: wide --- + Vidu 参考视频节点可根据多张参考图像和文本提示生成视频。它利用 AI 模型，基于提供的图像和描述创建内容一致的视频。该节点支持多种视频设置，包括时长、宽高比、分辨率和运动控制。 ## 输入 diff --git a/zh/built-in-nodes/ViduStartEndToVideoNode.mdx b/zh/built-in-nodes/ViduStartEndToVideoNode.mdx index 4462cb767..b70771055 100644 --- a/zh/built-in-nodes/ViduStartEndToVideoNode.mdx +++ b/zh/built-in-nodes/ViduStartEndToVideoNode.mdx @@ -5,7 +5,6 @@ sidebarTitle: "ViduStartEndToVideoNode" icon: "circle" mode: wide --- -# Vidu 起始帧到结束帧视频生成节点 Vidu 起始帧到结束帧视频生成节点通过在起始帧和结束帧之间生成帧来创建视频。它使用文本提示来引导视频生成过程，并支持具有不同分辨率和运动设置的各种视频模型。该节点在处理前会验证起始帧和结束帧具有兼容的宽高比。 diff --git a/zh/built-in-nodes/ViduTextToVideoNode.mdx b/zh/built-in-nodes/ViduTextToVideoNode.mdx index edccc0f4d..b5bd1efb3 100644 --- a/zh/built-in-nodes/ViduTextToVideoNode.mdx +++ b/zh/built-in-nodes/ViduTextToVideoNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ViduTextToVideoNode" icon: "circle" mode: wide --- + ## 概述 Vidu 文本转视频生成节点可根据文本描述创建视频。它利用 Vidu 视频生成模型，将您的文本提示转换为视频内容，并支持自定义时长、宽高比和视觉风格等设置。 diff --git a/zh/built-in-nodes/VoxelToMesh.mdx b/zh/built-in-nodes/VoxelToMesh.mdx index 7d410994a..c4ab3b07f 100644 --- a/zh/built-in-nodes/VoxelToMesh.mdx +++ b/zh/built-in-nodes/VoxelToMesh.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VoxelToMesh" icon: "circle" mode: wide --- + VoxelToMeshBasic 节点通过提取指定阈值处的表面，将 3D 体素数据转换为网格几何体。它会处理输入中的每个体素网格，并生成构成 3D 网格表示的顶点和面。 ## 输入 diff --git a/zh/built-in-nodes/VoxelToMeshBasic.mdx b/zh/built-in-nodes/VoxelToMeshBasic.mdx index c08197ef6..6d1e0b007 100644 --- a/zh/built-in-nodes/VoxelToMeshBasic.mdx +++ b/zh/built-in-nodes/VoxelToMeshBasic.mdx @@ -5,6 +5,7 @@ sidebarTitle: "VoxelToMeshBasic" icon: "circle" mode: wide --- + VoxelToMeshBasic 节点将 3D 体素数据转换为网格几何体。它通过应用阈值来处理体素体积，以确定体积的哪些部分会成为生成网格中的实体表面。该节点输出包含顶点和面的完整网格结构，可用于 3D 渲染和建模。 ## 输入 diff --git a/zh/built-in-nodes/Wan22FunControlToVideo.mdx b/zh/built-in-nodes/Wan22FunControlToVideo.mdx index ed38af80e..6d84da98a 100644 --- a/zh/built-in-nodes/Wan22FunControlToVideo.mdx +++ b/zh/built-in-nodes/Wan22FunControlToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan22FunControlToVideo" icon: "circle" mode: wide --- + Wan22FunControlToVideo 节点使用 Wan 视频模型架构，为视频生成准备条件化（conditioning）和潜在空间（latent）表示。该节点处理正向和负向条件化输入，以及可选的参考图像和控制视频，为视频合成创建必要的潜在空间表示。节点处理空间缩放和时间维度，以生成适用于视频模型的条件化数据。 ## 输入 @@ -27,9 +28,9 @@ Wan22FunControlToVideo 节点使用 Wan 视频模型架构，为视频生成准 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向提示` | 修改后的正向条件化，包含视频特定的潜在数据，包括拼接潜在变量、遮罩和可选的参考潜在变量 | CONDITIONING | -| `潜变量` | 修改后的负向条件化，包含视频特定的潜在数据，包括拼接潜在变量、遮罩和可选的参考潜在变量 | CONDITIONING | -| `latent` | 空的潜在张量，具有适合视频生成的适当维度，基于批次大小、潜在通道数以及空间/时间缩放 | LATENT | +| `正向提示` | 修改后的正向条件化，包含视频特定的潜在数据，包括拼接潜在变量、遮罩和可选的参考潜在变量 | CONDITIONING | +| `负向提示` | 修改后的负向条件化，包含视频特定的潜在数据，包括拼接潜在变量、遮罩和可选的参考潜在变量 | CONDITIONING | +| `潜变量` | 空的潜在张量，具有适合视频生成的适当维度，基于批次大小、潜在通道数以及空间/时间缩放 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Wan22FunControlToVideo/zh.md) diff --git a/zh/built-in-nodes/Wan22ImageToVideoLatent.mdx b/zh/built-in-nodes/Wan22ImageToVideoLatent.mdx index cbc0f241a..f1247a017 100644 --- a/zh/built-in-nodes/Wan22ImageToVideoLatent.mdx +++ b/zh/built-in-nodes/Wan22ImageToVideoLatent.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan22ImageToVideoLatent" icon: "circle" mode: wide --- + Wan22ImageToVideoLatent 节点可从图像创建视频潜在表示。它会生成具有指定维度的空白视频潜在空间，并可选择将起始图像序列编码到初始帧中。当提供起始图像时，该节点会将图像编码到潜在空间，并为修复区域生成相应的噪声遮罩。 ## 输入 diff --git a/zh/built-in-nodes/Wan2ImageToVideoApi.mdx b/zh/built-in-nodes/Wan2ImageToVideoApi.mdx index 122c19c1d..e860e0c7a 100644 --- a/zh/built-in-nodes/Wan2ImageToVideoApi.mdx +++ b/zh/built-in-nodes/Wan2ImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2ImageToVideoApi" icon: "circle" mode: wide --- + Wan 2.7 图像转视频节点可根据首帧图像生成视频。您可以选择提供末帧图像来创建两者之间的过渡，或提供音频文件来引导视频的运动和节奏。该节点使用 AI 模型根据您的文本描述对场景进行动画处理。 ## 输入 diff --git a/zh/built-in-nodes/Wan2ReferenceVideoApi.mdx b/zh/built-in-nodes/Wan2ReferenceVideoApi.mdx index c1df91f56..780a5a36d 100644 --- a/zh/built-in-nodes/Wan2ReferenceVideoApi.mdx +++ b/zh/built-in-nodes/Wan2ReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2ReferenceVideoApi" icon: "circle" mode: wide --- + 此节点根据提供的参考素材生成包含人物或对象的视频。它使用 Wan 2.7 模型根据文本提示创建视频，支持单人表演和多人互动。您必须至少提供一个参考视频或图像才能进行生成。 ## 输入 diff --git a/zh/built-in-nodes/Wan2TextToVideoApi.mdx b/zh/built-in-nodes/Wan2TextToVideoApi.mdx index 1e454e2a8..f1d96971b 100644 --- a/zh/built-in-nodes/Wan2TextToVideoApi.mdx +++ b/zh/built-in-nodes/Wan2TextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2TextToVideoApi" icon: "circle" mode: wide --- + 此节点使用 Wan 2.7 模型根据文本描述生成视频。它会将您的请求发送到外部 API，由该 API 处理提示词并返回视频文件。您可以选择提供音频片段来影响视频的运动和节奏。 ## 输入 diff --git a/zh/built-in-nodes/Wan2VideoContinuationApi.mdx b/zh/built-in-nodes/Wan2VideoContinuationApi.mdx index d0cb73d15..708b785a6 100644 --- a/zh/built-in-nodes/Wan2VideoContinuationApi.mdx +++ b/zh/built-in-nodes/Wan2VideoContinuationApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2VideoContinuationApi" icon: "circle" mode: wide --- + ## 概述 Wan 2.7 视频续接节点用于生成一段新的视频片段，该片段能够从输入视频片段的结尾无缝衔接。它利用 Wan 2.7 模型，根据文本提示合成续接内容，并可选择性地引导结尾朝向特定的目标帧。 diff --git a/zh/built-in-nodes/Wan2VideoEditApi.mdx b/zh/built-in-nodes/Wan2VideoEditApi.mdx index 0035f9c1d..254e6adbb 100644 --- a/zh/built-in-nodes/Wan2VideoEditApi.mdx +++ b/zh/built-in-nodes/Wan2VideoEditApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "Wan2VideoEditApi" icon: "circle" mode: wide --- + Wan2VideoEditApi 节点使用 Wan 2.7 模型，根据文本指令、参考图像或风格迁移来编辑视频。它会处理输入视频，并根据指定的参数（如分辨率、时长和宽高比）生成新视频。 ## 输入 diff --git a/zh/built-in-nodes/WanAnimateToVideo.mdx b/zh/built-in-nodes/WanAnimateToVideo.mdx index 832078f8d..e1b41d47c 100644 --- a/zh/built-in-nodes/WanAnimateToVideo.mdx +++ b/zh/built-in-nodes/WanAnimateToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanAnimateToVideo" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanAnimateToVideo/en.md) WanAnimateToVideo 节点通过组合多个条件输入（包括姿态参考、面部表情和背景元素）来生成视频内容。它处理各种视频输入，以创建连贯的动画序列，同时保持帧间的时间一致性。该节点处理潜在空间操作，并可通过延续运动模式来扩展现有视频。 @@ -45,11 +46,11 @@ WanAnimateToVideo 节点通过组合多个条件输入（包括姿态参考、 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向提示` | 修改后的正向条件，包含额外的视频上下文，包括 CLIP 视觉输出、姿态视频潜在表示、面部视频像素、拼接后的潜在图像和拼接后的遮罩 | CONDITIONING | -| `潜变量` | 修改后的负向条件，包含额外的视频上下文，包括 CLIP 视觉输出、姿态视频潜在表示、面部视频像素（反转）、拼接后的潜在图像和拼接后的遮罩 | CONDITIONING | -| `修剪潜变量` | 以潜在空间格式生成的视频内容，形状为 [batch_size, 16, latent_length + trim_latent, latent_height, latent_width] | LATENT | -| `修剪图像` | 潜在空间修剪信息，指示要从开头修剪的潜在帧数（对应于参考图像的潜在帧） | INT | -| `视频帧偏移` | 参考运动帧的图像空间修剪信息，指示要从开头修剪的图像帧数 | INT | +| `正向提示` | 修改后的正向条件，包含额外的视频上下文，包括 CLIP 视觉输出、姿态视频潜在表示、面部视频像素、拼接后的潜在图像和拼接后的遮罩 | CONDITIONING | +| `负向提示` | 修改后的负向条件，包含额外的视频上下文，包括 CLIP 视觉输出、姿态视频潜在表示、面部视频像素（反转）、拼接后的潜在图像和拼接后的遮罩 | CONDITIONING | +| `潜变量` | 以潜在空间格式生成的视频内容，形状为 [batch_size, 16, latent_length + trim_latent, latent_height, latent_width] | LATENT | +| `修剪潜变量` | 潜在空间修剪信息，指示要从开头修剪的潜在帧数（对应于参考图像的潜在帧） | INT | +| `修剪图像` | 参考运动帧的图像空间修剪信息，指示要从开头修剪的图像帧数 | INT | | `视频帧偏移` | 用于按块继续视频生成的更新帧偏移量，计算方式为先前偏移量加上生成的长度 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanAnimateToVideo/zh.md) diff --git a/zh/built-in-nodes/WanCameraEmbedding.mdx b/zh/built-in-nodes/WanCameraEmbedding.mdx index c782f5c90..9c35bcbe9 100644 --- a/zh/built-in-nodes/WanCameraEmbedding.mdx +++ b/zh/built-in-nodes/WanCameraEmbedding.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanCameraEmbedding" icon: "circle" mode: wide --- + WanCameraEmbedding 节点基于相机运动参数，使用普吕克嵌入（Plücker embeddings）生成相机轨迹嵌入。它会创建一系列模拟不同相机运动的相机姿态，并将其转换为适用于视频生成管线的嵌入张量。 ## 输入 @@ -25,9 +26,9 @@ WanCameraEmbedding 节点基于相机运动参数，使用普吕克嵌入（Plü | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `宽度` | 生成的相机嵌入张量，包含轨迹序列 | TENSOR | -| `高度` | 用于处理的宽度值 | INT | -| `长度` | 用于处理的高度值 | INT | +| `相机嵌入` | 生成的相机嵌入张量，包含轨迹序列 | TENSOR | +| `宽度` | 用于处理的宽度值 | INT | +| `高度` | 用于处理的高度值 | INT | | `长度` | 用于处理的长度值 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraEmbedding/zh.md) diff --git a/zh/built-in-nodes/WanCameraImageToVideo.mdx b/zh/built-in-nodes/WanCameraImageToVideo.mdx index ace1bcbf1..216e8879a 100644 --- a/zh/built-in-nodes/WanCameraImageToVideo.mdx +++ b/zh/built-in-nodes/WanCameraImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanCameraImageToVideo" icon: "circle" mode: wide --- + WanCameraImageToVideo 节点通过生成用于视频生成的潜在表示，将图像转换为视频序列。它处理条件化输入和可选的起始图像，以创建可用于视频模型的视频潜在表示。该节点支持相机条件和剪辑视觉输出，以增强视频生成控制。 ## 输入 @@ -28,9 +29,9 @@ WanCameraImageToVideo 节点通过生成用于视频生成的潜在表示，将 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面提示词` | 应用了相机条件和剪辑视觉输出后的修改版正面条件化 | CONDITIONING | -| `潜空间` | 应用了相机条件和剪辑视觉输出后的修改版负面条件化 | CONDITIONING | -| `latent` | 生成的视频潜在表示，用于视频模型。潜在张量的维度为 [batch_size, 16, frames, height/8, width/8]，其中 frames 的计算方式为 ((length - 1) // 4) + 1。 | LATENT | +| `正面提示词` | 应用了相机条件和剪辑视觉输出后的修改版正面条件化 | CONDITIONING | +| `负面提示词` | 应用了相机条件和剪辑视觉输出后的修改版负面条件化 | CONDITIONING | +| `潜空间` | 生成的视频潜在表示，用于视频模型。潜在张量的维度为 [batch_size, 16, frames, height/8, width/8]，其中 frames 的计算方式为 ((length - 1) // 4) + 1。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanCameraImageToVideo/zh.md) diff --git a/zh/built-in-nodes/WanContextWindowsManual.mdx b/zh/built-in-nodes/WanContextWindowsManual.mdx index ac3b63375..f15a35f62 100644 --- a/zh/built-in-nodes/WanContextWindowsManual.mdx +++ b/zh/built-in-nodes/WanContextWindowsManual.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanContextWindowsManual" icon: "circle" mode: wide --- + WAN上下文窗口（手动）节点允许您为具有二维处理的WAN类模型手动配置上下文窗口。它通过在采样过程中指定窗口长度、重叠、调度方法和融合技术来应用自定义上下文窗口设置。这使您能够精确控制模型在不同上下文区域间的信息处理方式。 ## 输入 diff --git a/zh/built-in-nodes/WanDancerEncodeAudio.mdx b/zh/built-in-nodes/WanDancerEncodeAudio.mdx index 4b6dc0aa6..cfbdc130d 100644 --- a/zh/built-in-nodes/WanDancerEncodeAudio.mdx +++ b/zh/built-in-nodes/WanDancerEncodeAudio.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerEncodeAudio" icon: "circle" mode: wide --- + ## 概述 此节点处理音频输入以提取可用于指导视频生成模型的特征。它分析音频以检测节奏、节拍及其他音乐特征，然后将这些信息打包成适合调节视频模型的格式，从而使生成的视频能够与音频同步。 @@ -21,8 +22,8 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `fps字符串` | 一个字典，包含处理后的音频特征、计算出的帧率（fps）以及音频注入缩放比例。此输出用于调节视频生成模型。 | AUDIO_ENCODER_OUTPUT | -| `fps_string` | 基于音频长度和视频帧数计算出的帧率（fps）的文本描述。此字符串旨在用于视频模型的提示词中。 | STRING | +| `音频编码器输出` | 一个字典，包含处理后的音频特征、计算出的帧率（fps）以及音频注入缩放比例。此输出用于调节视频生成模型。 | AUDIO_ENCODER_OUTPUT | +| `fps字符串` | 基于音频长度和视频帧数计算出的帧率（fps）的文本描述。此字符串旨在用于视频模型的提示词中。 | STRING | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerEncodeAudio/zh.md) diff --git a/zh/built-in-nodes/WanDancerPadKeyframes.mdx b/zh/built-in-nodes/WanDancerPadKeyframes.mdx index 3a950f924..4217f3fed 100644 --- a/zh/built-in-nodes/WanDancerPadKeyframes.mdx +++ b/zh/built-in-nodes/WanDancerPadKeyframes.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerPadKeyframes" icon: "circle" mode: wide --- + ## 概述 此节点为较长视频生成过程中的特定片段准备关键帧序列。它接收一批输入图像和一条音频轨道，根据音频时长计算完整视频应包含的总帧数，然后将输入图像作为关键帧分布到所选片段中，其余位置用空白帧填充。同时，它还会提取该片段对应的音频部分。 @@ -22,9 +23,9 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `关键帧掩码` | 指定片段的填充后关键帧序列。 | IMAGE | -| `音频片段` | 指示有效帧的遮罩（关键帧位置为 1，填充位置为 0）。 | MASK | -| `audio_segment` | 此视频片段对应的音频片段。 | AUDIO | +| `关键帧序列` | 指定片段的填充后关键帧序列。 | IMAGE | +| `关键帧掩码` | 指示有效帧的遮罩（关键帧位置为 1，填充位置为 0）。 | MASK | +| `音频片段` | 此视频片段对应的音频片段。 | AUDIO | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerPadKeyframes/zh.md) diff --git a/zh/built-in-nodes/WanDancerPadKeyframesList.mdx b/zh/built-in-nodes/WanDancerPadKeyframesList.mdx index c63858750..6669dd816 100644 --- a/zh/built-in-nodes/WanDancerPadKeyframesList.mdx +++ b/zh/built-in-nodes/WanDancerPadKeyframesList.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerPadKeyframesList" icon: "circle" mode: wide --- + ## 概述 此节点接收一个图像序列和可选的音轨，并将其分割成指定数量的填充片段。它旨在为视频生成准备关键帧序列，其中每个片段都被填充为一致的长度，并创建相应的遮罩来指示哪些帧是有效的。 @@ -22,9 +23,9 @@ mode: wide | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `关键帧掩码` | 填充后的关键帧序列列表，每个片段对应一个序列。 | IMAGE | -| `音频片段` | 指示每个片段有效帧的遮罩列表。 | MASK | -| `audio_segment` | 音频片段列表，每个视频片段对应一个音频片段。 | AUDIO | +| `关键帧序列` | 填充后的关键帧序列列表，每个片段对应一个序列。 | IMAGE | +| `关键帧掩码` | 指示每个片段有效帧的遮罩列表。 | MASK | +| `音频片段` | 音频片段列表，每个视频片段对应一个音频片段。 | AUDIO | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerPadKeyframesList/zh.md) diff --git a/zh/built-in-nodes/WanDancerVideo.mdx b/zh/built-in-nodes/WanDancerVideo.mdx index 9e8834d3a..9462e72fe 100644 --- a/zh/built-in-nodes/WanDancerVideo.mdx +++ b/zh/built-in-nodes/WanDancerVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanDancerVideo" icon: "circle" mode: wide --- + WanDancerVideo 节点用于为 WanDancer 模型的视频生成准备 conditioning 数据和空的潜空间张量。它结合了正向和负向 conditioning，并支持起始图像、遮罩、CLIP 视觉嵌入和音频特征等可选输入，以控制生成的视频。 ## 输入 @@ -32,8 +33,8 @@ WanDancerVideo 节点用于为 WanDancer 模型的视频生成准备 conditionin | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向` | 附加了额外数据（拼接潜空间、CLIP 视觉、音频）的正向 conditioning。 | CONDITIONING | -| `latent` | 附加了额外数据（拼接潜空间、CLIP 视觉、音频）的负向 conditioning。 | CONDITIONING | +| `正向` | 附加了额外数据（拼接潜空间、CLIP 视觉、音频）的正向 conditioning。 | CONDITIONING | +| `负向` | 附加了额外数据（拼接潜空间、CLIP 视觉、音频）的负向 conditioning。 | CONDITIONING | | `latent` | 维度与指定的视频长度、高度和宽度匹配的空潜空间张量。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanDancerVideo/zh.md) diff --git a/zh/built-in-nodes/WanFirstLastFrameToVideo.mdx b/zh/built-in-nodes/WanFirstLastFrameToVideo.mdx index 680a4b25c..8fc609444 100644 --- a/zh/built-in-nodes/WanFirstLastFrameToVideo.mdx +++ b/zh/built-in-nodes/WanFirstLastFrameToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFirstLastFrameToVideo" icon: "circle" mode: wide --- + WanFirstLastFrameToVideo 节点通过结合起始帧、结束帧与文本提示来创建视频条件。它通过编码首帧和末帧、应用遮罩引导生成过程，并在可用时融入 CLIP 视觉特征，为视频生成生成潜在表示。此节点为视频模型准备正面和负面条件，以在指定的起点和终点之间生成连贯的序列。 ## 输入 @@ -29,8 +30,8 @@ WanFirstLastFrameToVideo 节点通过结合起始帧、结束帧与文本提示 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向` | 应用了视频帧编码和 CLIP 视觉特征的正面条件 | CONDITIONING | -| `latent` | 应用了视频帧编码和 CLIP 视觉特征的负面条件 | CONDITIONING | +| `正向` | 应用了视频帧编码和 CLIP 视觉特征的正面条件 | CONDITIONING | +| `负向` | 应用了视频帧编码和 CLIP 视觉特征的负面条件 | CONDITIONING | | `latent` | 空潜在张量，其维度与指定的视频参数匹配 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFirstLastFrameToVideo/zh.md) diff --git a/zh/built-in-nodes/WanFunControlToVideo.mdx b/zh/built-in-nodes/WanFunControlToVideo.mdx index de6bfe573..b5141e584 100644 --- a/zh/built-in-nodes/WanFunControlToVideo.mdx +++ b/zh/built-in-nodes/WanFunControlToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFunControlToVideo" icon: "circle" mode: wide --- + 此节点用于支持阿里巴巴万Fun Control视频生成模型，在[此提交](https://github.com/comfyanonymous/ComfyUI/commit/3661c833bcc41b788a7c9f0e7bc48524f8ee5f82)之后添加。 - **目的：** 使用Wan 2.1 Fun Control模型准备视频生成所需的调节信息。 @@ -34,8 +35,8 @@ WanFunControlToVideo节点是ComfyUI的一个扩展，旨在支持Wan Fun Contro | 参数名 | 描述 | 数据类型 | | --- | --- | --- | -| `负向` | 提供增强后的正向调节数据，包含编码后的start_image和control_video。 | CONDITIONING | -| `latent` | 提供同样经过增强的负向调节数据，包含相同的concat_latent_image。 | CONDITIONING | +| `正向` | 提供增强后的正向调节数据，包含编码后的start_image和control_video。 | CONDITIONING | +| `负向` | 提供同样经过增强的负向调节数据，包含相同的concat_latent_image。 | CONDITIONING | | `latent` | 一个包含空潜在张量的字典，键为"samples"。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFunControlToVideo/zh.md) diff --git a/zh/built-in-nodes/WanFunInpaintToVideo.mdx b/zh/built-in-nodes/WanFunInpaintToVideo.mdx index c0316bceb..be462e89e 100644 --- a/zh/built-in-nodes/WanFunInpaintToVideo.mdx +++ b/zh/built-in-nodes/WanFunInpaintToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanFunInpaintToVideo" icon: "circle" mode: wide --- + WanFunInpaintToVideo 节点通过在起始图像和结束图像之间进行修补来创建视频序列。它接收正向和负向条件输入，以及可选的帧图像，以生成视频潜在表示。该节点处理视频生成，并支持可配置的尺寸和长度参数。 ## 输入 @@ -26,8 +27,8 @@ WanFunInpaintToVideo 节点通过在起始图像和结束图像之间进行修 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向` | 处理后的正向条件输出 | CONDITIONING | -| `latent` | 处理后的负向条件输出 | CONDITIONING | +| `正向` | 处理后的正向条件输出 | CONDITIONING | +| `负向` | 处理后的负向条件输出 | CONDITIONING | | `latent` | 生成的视频潜在表示 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanFunInpaintToVideo/zh.md) diff --git a/zh/built-in-nodes/WanHuMoImageToVideo.mdx b/zh/built-in-nodes/WanHuMoImageToVideo.mdx index f6daa3364..8f842c305 100644 --- a/zh/built-in-nodes/WanHuMoImageToVideo.mdx +++ b/zh/built-in-nodes/WanHuMoImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanHuMoImageToVideo" icon: "circle" mode: wide --- + ### 概述 WanHuMoImageToVideo 节点通过生成视频帧的潜在表示，将图像转换为视频序列。它处理条件输入，并可结合参考图像和音频嵌入来影响视频生成。该节点输出修改后的条件数据以及适用于视频合成的潜在表示。 diff --git a/zh/built-in-nodes/WanImageToImageApi.mdx b/zh/built-in-nodes/WanImageToImageApi.mdx index d4aaf1e12..82a17256f 100644 --- a/zh/built-in-nodes/WanImageToImageApi.mdx +++ b/zh/built-in-nodes/WanImageToImageApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToImageApi" icon: "circle" mode: wide --- + Wan 图像到图像节点根据一张或两张输入图像以及文本提示生成一张新图像。它会根据您提供的描述对输入图像进行变换，创建一张保持原始输入图像宽高比的新图像。无论输入尺寸如何，输出图像固定为 1.6 百万像素。 ## 输入 diff --git a/zh/built-in-nodes/WanImageToVideo.mdx b/zh/built-in-nodes/WanImageToVideo.mdx index 4ca5ab85f..562c1f774 100644 --- a/zh/built-in-nodes/WanImageToVideo.mdx +++ b/zh/built-in-nodes/WanImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToVideo" icon: "circle" mode: wide --- + WanImageToVideo 节点为视频生成任务准备条件化（conditioning）和潜在空间（latent）表示。它会为视频生成创建一个空的潜在空间，并可选择性地结合起始图像和 CLIP 视觉输出，以引导视频生成过程。该节点会根据提供的图像和视觉数据修改正向和负向条件化输入。 ## 输入 @@ -27,9 +28,9 @@ WanImageToVideo 节点为视频生成任务准备条件化（conditioning）和 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面` | 已整合图像和视觉数据的修改后正向条件化 | CONDITIONING | -| `潜在` | 已整合图像和视觉数据的修改后负向条件化 | CONDITIONING | -| `latent` | 可用于视频生成的空潜在空间张量 | LATENT | +| `正面` | 已整合图像和视觉数据的修改后正向条件化 | CONDITIONING | +| `负面` | 已整合图像和视觉数据的修改后负向条件化 | CONDITIONING | +| `潜在` | 可用于视频生成的空潜在空间张量 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanImageToVideo/zh.md) diff --git a/zh/built-in-nodes/WanImageToVideoApi.mdx b/zh/built-in-nodes/WanImageToVideoApi.mdx index d89834702..9070092ff 100644 --- a/zh/built-in-nodes/WanImageToVideoApi.mdx +++ b/zh/built-in-nodes/WanImageToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanImageToVideoApi" icon: "circle" mode: wide --- + Wan 图像转视频节点可根据单张输入图像和文本提示词生成视频。该节点将提供的图像作为第一帧，并基于描述创建视频序列，支持分辨率、时长、音频及其他高级设置选项。 ## 输入 diff --git a/zh/built-in-nodes/WanInfiniteTalkToVideo.mdx b/zh/built-in-nodes/WanInfiniteTalkToVideo.mdx index 6275c114c..c76d2647e 100644 --- a/zh/built-in-nodes/WanInfiniteTalkToVideo.mdx +++ b/zh/built-in-nodes/WanInfiniteTalkToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanInfiniteTalkToVideo" icon: "circle" mode: wide --- + WanInfiniteTalkToVideo 节点可根据音频输入生成视频序列。它使用视频扩散模型，以从一个或两个说话者提取的音频特征为条件，生成说话人头视频的潜在表示。该节点可以生成新序列，或利用先前帧的运动上下文来扩展现有序列。 ## 输入 @@ -41,11 +42,11 @@ WanInfiniteTalkToVideo 节点可根据音频输入生成视频序列。它使用 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `正向提示` | 已应用音频条件的修补模型。 | MODEL | -| `负向提示` | 正向条件，可能已通过额外上下文（例如起始图像、CLIP 视觉）进行修改。 | CONDITIONING | -| `latent` | 负向条件，可能已通过额外上下文进行修改。 | CONDITIONING | -| `裁剪图像` | 潜在空间中生成的视频序列。 | LATENT | -| `trim_image` | 扩展序列时，应从运动上下文起始处裁剪的帧数。 | INT | +| `模型` | 已应用音频条件的修补模型。 | MODEL | +| `正向提示` | 正向条件，可能已通过额外上下文（例如起始图像、CLIP 视觉）进行修改。 | CONDITIONING | +| `负向提示` | 负向条件，可能已通过额外上下文进行修改。 | CONDITIONING | +| `latent` | 潜在空间中生成的视频序列。 | LATENT | +| `裁剪图像` | 扩展序列时，应从运动上下文起始处裁剪的帧数。 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanInfiniteTalkToVideo/zh.md) diff --git a/zh/built-in-nodes/WanMoveConcatTrack.mdx b/zh/built-in-nodes/WanMoveConcatTrack.mdx index 5b461f9b7..9d66d31bb 100644 --- a/zh/built-in-nodes/WanMoveConcatTrack.mdx +++ b/zh/built-in-nodes/WanMoveConcatTrack.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveConcatTrack" icon: "circle" mode: wide --- + WanMoveConcatTrack 节点将两组运动跟踪数据合并为一条更长的序列。其工作原理是将输入轨迹中的跟踪路径和可见性掩码沿各自维度拼接。如果仅提供一组轨迹输入，则直接将该数据原样传递。 ## 输入 diff --git a/zh/built-in-nodes/WanMoveTrackToVideo.mdx b/zh/built-in-nodes/WanMoveTrackToVideo.mdx index 36fde33b1..35fa7c7da 100644 --- a/zh/built-in-nodes/WanMoveTrackToVideo.mdx +++ b/zh/built-in-nodes/WanMoveTrackToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveTrackToVideo" icon: "circle" mode: wide --- + WanMoveTrackToVideo 节点用于准备视频生成所需的 conditioning 和潜在空间数据，并可整合可选的运动跟踪信息。它将起始图像序列编码为潜在表示，并能够融合来自对象轨迹的位置数据，以引导生成视频中的运动。该节点输出修改后的正向和负向 conditioning，以及一个可供视频模型使用的空潜在张量。 ## 输入 @@ -29,9 +30,9 @@ WanMoveTrackToVideo 节点用于准备视频生成所需的 conditioning 和潜 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面条件` | 修改后的正向 conditioning，可能包含 `concat_latent_image`、`concat_mask` 和 `CLIP视觉输出`。 | CONDITIONING | -| `Latent` | 修改后的负向 conditioning，可能包含 `concat_latent_image`、`concat_mask` 和 `CLIP视觉输出`。 | CONDITIONING | -| `latent` | 一个空潜在张量，其维度由 `批次大小`、`时长`、`高度` 和 `宽度` 输入决定。 | LATENT | +| `正面条件` | 修改后的正向 conditioning，可能包含 `concat_latent_image`、`concat_mask` 和 `CLIP视觉输出`。 | CONDITIONING | +| `负面条件` | 修改后的负向 conditioning，可能包含 `concat_latent_image`、`concat_mask` 和 `CLIP视觉输出`。 | CONDITIONING | +| `Latent` | 一个空潜在张量，其维度由 `批次大小`、`时长`、`高度` 和 `宽度` 输入决定。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTrackToVideo/zh.md) diff --git a/zh/built-in-nodes/WanMoveTracksFromCoords.mdx b/zh/built-in-nodes/WanMoveTracksFromCoords.mdx index 3c3233f1b..bb0cd5406 100644 --- a/zh/built-in-nodes/WanMoveTracksFromCoords.mdx +++ b/zh/built-in-nodes/WanMoveTracksFromCoords.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveTracksFromCoords" icon: "circle" mode: wide --- + WanMoveTracksFromCoords 节点可根据 JSON 格式的坐标字符串创建运动轨迹。它会将坐标数据转换为张量格式，供其他视频处理节点使用，并可选择应用遮罩来控制轨迹随时间变化的可见性。 ## 输入 @@ -21,7 +22,7 @@ WanMoveTracksFromCoords 节点可根据 JSON 格式的坐标字符串创建运 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | | `轨道长度` | 生成的轨迹数据，包含每条轨迹的路径坐标和可见性信息。 | TRACKS | -| `track_length` | 生成轨迹的总帧数。 | INT | +| `轨道长度` | 生成轨迹的总帧数。 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanMoveTracksFromCoords/zh.md) diff --git a/zh/built-in-nodes/WanMoveVisualizeTracks.mdx b/zh/built-in-nodes/WanMoveVisualizeTracks.mdx index 9070bef9b..8b663e1a8 100644 --- a/zh/built-in-nodes/WanMoveVisualizeTracks.mdx +++ b/zh/built-in-nodes/WanMoveVisualizeTracks.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanMoveVisualizeTracks" icon: "circle" mode: wide --- + WanMoveVisualizeTracks 节点可将运动跟踪数据叠加到图像序列或视频帧上。它会绘制跟踪点的可视化表示，包括其运动路径和当前位置，使运动数据可见且更易于分析。 ## 输入 diff --git a/zh/built-in-nodes/WanPhantomSubjectToVideo.mdx b/zh/built-in-nodes/WanPhantomSubjectToVideo.mdx index bf72e390e..92985792f 100644 --- a/zh/built-in-nodes/WanPhantomSubjectToVideo.mdx +++ b/zh/built-in-nodes/WanPhantomSubjectToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanPhantomSubjectToVideo" icon: "circle" mode: wide --- + WanPhantomSubjectToVideo 节点通过处理条件化输入和可选的参考图像来生成视频内容。它会为视频生成创建潜在表示，并在提供输入图像时融入其中的视觉引导。该节点为视频模型准备带有时间维度拼接的条件化数据，并输出修改后的条件化数据以及生成的潜在视频数据。 ## 输入 @@ -26,10 +27,10 @@ WanPhantomSubjectToVideo 节点通过处理条件化输入和可选的参考图 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面文本` | 当提供图像时，经过时间维度拼接修改后的正面条件化数据 | CONDITIONING | -| `负面图像文本` | 当提供图像时，经过时间维度拼接修改后的负面条件化数据 | CONDITIONING | -| `潜变量` | 当提供图像时，使用零值时间维度拼接的负面条件化数据 | CONDITIONING | -| `latent` | 生成的具有指定尺寸和长度的潜在视频表示 | LATENT | +| `正面提示词` | 当提供图像时，经过时间维度拼接修改后的正面条件化数据 | CONDITIONING | +| `负面文本` | 当提供图像时，经过时间维度拼接修改后的负面条件化数据 | CONDITIONING | +| `负面图像文本` | 当提供图像时，使用零值时间维度拼接的负面条件化数据 | CONDITIONING | +| `潜变量` | 生成的具有指定尺寸和长度的潜在视频表示 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanPhantomSubjectToVideo/zh.md) diff --git a/zh/built-in-nodes/WanReferenceVideoApi.mdx b/zh/built-in-nodes/WanReferenceVideoApi.mdx index b65554f6a..c72b92ca3 100644 --- a/zh/built-in-nodes/WanReferenceVideoApi.mdx +++ b/zh/built-in-nodes/WanReferenceVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanReferenceVideoApi" icon: "circle" mode: wide --- + 此文档由 AI 生成。如发现任何错误或有改进建议，欢迎随时贡献！[在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanReferenceVideoApi/en.md) Wan 参考视频节点利用一个或多个输入参考视频的视觉外观和语音，结合文本提示，生成新的视频。它在根据您的描述创建新内容的同时，保持与参考素材中角色的一致性。 diff --git a/zh/built-in-nodes/WanSCAILToVideo.mdx b/zh/built-in-nodes/WanSCAILToVideo.mdx index 7a42bfd5c..68ee075ba 100644 --- a/zh/built-in-nodes/WanSCAILToVideo.mdx +++ b/zh/built-in-nodes/WanSCAILToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSCAILToVideo" icon: "circle" mode: wide --- + WanSCAILToVideo 节点用于为视频生成准备 conditioning 和空潜在空间。它会处理参考图像、姿态视频和 CLIP 视觉输出等可选输入，并将它们嵌入到视频模型的正负 conditioning 中。该节点输出修改后的 conditioning 以及指定视频尺寸的空白潜在张量。 ## 输入 @@ -31,8 +32,8 @@ WanSCAILToVideo 节点用于为视频生成准备 conditioning 和空潜在空 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向` | 修改后的正 conditioning，可能包含嵌入的参考图像潜在向量、CLIP 视觉输出或姿态视频潜在向量。 | CONDITIONING | -| `latent` | 修改后的负 conditioning，可能包含嵌入的参考图像潜在向量、CLIP 视觉输出或姿态视频潜在向量。 | CONDITIONING | +| `正向` | 修改后的正 conditioning，可能包含嵌入的参考图像潜在向量、CLIP 视觉输出或姿态视频潜在向量。 | CONDITIONING | +| `负向` | 修改后的负 conditioning，可能包含嵌入的参考图像潜在向量、CLIP 视觉输出或姿态视频潜在向量。 | CONDITIONING | | `latent` | 形状为 `[batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8]` 的空潜在张量。 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSCAILToVideo/zh.md) diff --git a/zh/built-in-nodes/WanSoundImageToVideo.mdx b/zh/built-in-nodes/WanSoundImageToVideo.mdx index 9f83e2d00..241891ee3 100644 --- a/zh/built-in-nodes/WanSoundImageToVideo.mdx +++ b/zh/built-in-nodes/WanSoundImageToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSoundImageToVideo" icon: "circle" mode: wide --- + WanSoundImageToVideo 节点可根据图像生成视频内容，并支持可选的音频条件控制。该节点接收正面和负面条件提示以及 VAE 模型来创建视频潜在表示，并可结合参考图像、音频编码、控制视频和运动参考来引导视频生成过程。 ## 输入 @@ -27,9 +28,9 @@ WanSoundImageToVideo 节点可根据图像生成视频内容，并支持可选 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面提示词` | 经过修改以适应视频生成的正面条件处理结果 | CONDITIONING | -| `潜变量` | 经过修改以适应视频生成的负面条件处理结果 | CONDITIONING | -| `latent` | 在潜在空间中生成的视频表示，可解码为最终视频帧 | LATENT | +| `正面提示词` | 经过修改以适应视频生成的正面条件处理结果 | CONDITIONING | +| `负面提示词` | 经过修改以适应视频生成的负面条件处理结果 | CONDITIONING | +| `潜变量` | 在潜在空间中生成的视频表示，可解码为最终视频帧 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideo/zh.md) diff --git a/zh/built-in-nodes/WanSoundImageToVideoExtend.mdx b/zh/built-in-nodes/WanSoundImageToVideoExtend.mdx index e9ee9345c..4efffc813 100644 --- a/zh/built-in-nodes/WanSoundImageToVideoExtend.mdx +++ b/zh/built-in-nodes/WanSoundImageToVideoExtend.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanSoundImageToVideoExtend" icon: "circle" mode: wide --- + WanSoundImageToVideoExtend 节点通过生成额外帧来扩展已有的视频潜在表示，可选的引导方式包括音频、参考图像和控制视频。它接收一个起始视频潜在表示，并利用提供的条件提示和音频线索影响新内容，从而生成更长的视频序列。 ## 输入 @@ -24,9 +25,9 @@ WanSoundImageToVideoExtend 节点通过生成额外帧来扩展已有的视频 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面提示词` | 已应用视频上下文的处理后的正向条件 | CONDITIONING | -| `潜变量` | 已应用视频上下文的处理后的负向条件 | CONDITIONING | -| `latent` | 生成的视频潜在表示，包含扩展后的视频序列 | LATENT | +| `正面提示词` | 已应用视频上下文的处理后的正向条件 | CONDITIONING | +| `负面提示词` | 已应用视频上下文的处理后的负向条件 | CONDITIONING | +| `潜变量` | 生成的视频潜在表示，包含扩展后的视频序列 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanSoundImageToVideoExtend/zh.md) diff --git a/zh/built-in-nodes/WanTextToImageApi.mdx b/zh/built-in-nodes/WanTextToImageApi.mdx index aa38ce4ab..4c156eb10 100644 --- a/zh/built-in-nodes/WanTextToImageApi.mdx +++ b/zh/built-in-nodes/WanTextToImageApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTextToImageApi" icon: "circle" mode: wide --- + Wan 文生图节点根据文本描述生成图像。它利用 AI 模型从文字提示中创建视觉内容，支持中英文文本输入。该节点提供多种控制选项，用于调整输出图像的尺寸、质量和风格偏好。 ## 输入 diff --git a/zh/built-in-nodes/WanTextToVideoApi.mdx b/zh/built-in-nodes/WanTextToVideoApi.mdx index 46ea73663..4b8705526 100644 --- a/zh/built-in-nodes/WanTextToVideoApi.mdx +++ b/zh/built-in-nodes/WanTextToVideoApi.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTextToVideoApi" icon: "circle" mode: wide --- + Wan 文生视频节点根据文本描述生成视频内容。它利用 AI 模型从提示词创建视频，支持多种视频尺寸、时长以及可选的音频输入。该节点可在需要时自动生成音频，并提供提示词增强和添加水印的选项。 ## 输入 diff --git a/zh/built-in-nodes/WanTrackToVideo.mdx b/zh/built-in-nodes/WanTrackToVideo.mdx index e398fa94c..16fb0e29e 100644 --- a/zh/built-in-nodes/WanTrackToVideo.mdx +++ b/zh/built-in-nodes/WanTrackToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanTrackToVideo" icon: "circle" mode: wide --- + WanTrackToVideo 节点通过处理轨迹点并生成相应的视频帧，将运动跟踪数据转换为视频序列。它接收跟踪坐标作为输入，并生成可用于视频生成的条件控制信号和潜在表示。当未提供轨迹时，它会回退到标准的图像到视频转换模式。 ## 输入 @@ -30,8 +31,8 @@ WanTrackToVideo 节点通过处理轨迹点并生成相应的视频帧，将运 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负面提示词` | 应用了运动轨迹信息的正向条件控制 | CONDITIONING | -| `latent` | 应用了运动轨迹信息的负向条件控制 | CONDITIONING | +| `正面提示词` | 应用了运动轨迹信息的正向条件控制 | CONDITIONING | +| `负面提示词` | 应用了运动轨迹信息的负向条件控制 | CONDITIONING | | `latent` | 生成的视频潜在表示 | LATENT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanTrackToVideo/zh.md) diff --git a/zh/built-in-nodes/WanVaceToVideo.mdx b/zh/built-in-nodes/WanVaceToVideo.mdx index d0b0b18aa..aefa687d9 100644 --- a/zh/built-in-nodes/WanVaceToVideo.mdx +++ b/zh/built-in-nodes/WanVaceToVideo.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WanVaceToVideo" icon: "circle" mode: wide --- + WanVaceToVideo 节点用于处理视频生成模型的视频条件数据。它接收正面和负面条件输入以及视频控制数据，并准备用于视频生成的潜在表示。该节点处理视频放大、遮罩和 VAE 编码，以创建适用于视频模型的适当条件结构。 ## 输入 @@ -29,10 +30,10 @@ WanVaceToVideo 节点用于处理视频生成模型的视频条件数据。它 | 输出名称 | 描述 | 数据类型 | | --- | --- | --- | -| `负向` | 应用了视频控制数据的正面条件 | CONDITIONING | -| `latent` | 应用了视频控制数据的负面条件 | CONDITIONING | -| `裁剪latent` | 准备用于视频生成的空潜在张量 | LATENT | -| `trim_latent` | 使用参考图像时需要裁剪的潜在帧数 | INT | +| `正向` | 应用了视频控制数据的正面条件 | CONDITIONING | +| `负向` | 应用了视频控制数据的负面条件 | CONDITIONING | +| `latent` | 准备用于视频生成的空潜在张量 | LATENT | +| `裁剪latent` | 使用参考图像时需要裁剪的潜在帧数 | INT | > 本文档由 AI 生成。如果您发现任何错误或有改进建议，欢迎贡献！ [在 GitHub 上编辑](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/WanVaceToVideo/zh.md) diff --git a/zh/built-in-nodes/WavespeedFlashVSRNode.mdx b/zh/built-in-nodes/WavespeedFlashVSRNode.mdx index b0d4ff6fb..bfd9cab06 100644 --- a/zh/built-in-nodes/WavespeedFlashVSRNode.mdx +++ b/zh/built-in-nodes/WavespeedFlashVSRNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WavespeedFlashVSRNode" icon: "circle" mode: wide --- + ## 概述 WavespeedFlashVSRNode 是一款快速、高质量的视频超分辨率节点，可提升低分辨率或模糊视频的分辨率并恢复清晰度。它处理视频输入，并以用户选择的更高分辨率输出新视频。 diff --git a/zh/built-in-nodes/WavespeedImageUpscaleNode.mdx b/zh/built-in-nodes/WavespeedImageUpscaleNode.mdx index 45532edac..71317fbe2 100644 --- a/zh/built-in-nodes/WavespeedImageUpscaleNode.mdx +++ b/zh/built-in-nodes/WavespeedImageUpscaleNode.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WavespeedImageUpscaleNode" icon: "circle" mode: wide --- + WaveSpeed 图像放大节点使用外部 AI 服务来提高图像的分辨率和质量。它接收一张输入照片，并将其放大到更高的目标分辨率（例如 2K、4K 或 8K），从而生成更清晰、更精细的结果。 ## 输入 diff --git a/zh/built-in-nodes/WebcamCapture.mdx b/zh/built-in-nodes/WebcamCapture.mdx index 9d6a4245b..31406a1d1 100644 --- a/zh/built-in-nodes/WebcamCapture.mdx +++ b/zh/built-in-nodes/WebcamCapture.mdx @@ -5,6 +5,7 @@ sidebarTitle: "WebcamCapture" icon: "circle" mode: wide --- + WebcamCapture 节点用于从摄像头设备捕获图像，并将其转换为可在 ComfyUI 工作流中使用的格式。该节点继承自 LoadImage 节点，并提供控制捕获尺寸和时机的选项。启用后，每次处理工作流队列时，节点都会捕获新图像。 ## 输入 diff --git a/zh/built-in-nodes/ZImageFunControlnet.mdx b/zh/built-in-nodes/ZImageFunControlnet.mdx index 87bff671e..94ccb9497 100644 --- a/zh/built-in-nodes/ZImageFunControlnet.mdx +++ b/zh/built-in-nodes/ZImageFunControlnet.mdx @@ -5,6 +5,7 @@ sidebarTitle: "ZImageFunControlnet" icon: "circle" mode: wide --- + ZImageFunControlnet 节点应用专门的控制网络来影响图像生成或编辑过程。它使用基础模型、模型补丁和 VAE，允许您调整控制效果的强度。该节点可与基础图像、修补图像和遮罩配合使用，以实现更有针对性的编辑。 ## 输入 diff --git a/zh/built-in-nodes/unCLIPCheckpointLoader.mdx b/zh/built-in-nodes/unCLIPCheckpointLoader.mdx index 0d851f43a..a94b5fdd3 100644 --- a/zh/built-in-nodes/unCLIPCheckpointLoader.mdx +++ b/zh/built-in-nodes/unCLIPCheckpointLoader.mdx @@ -5,6 +5,7 @@ sidebarTitle: "unCLIPCheckpointLoader" icon: "circle" mode: wide --- + 此节点将检测位于 `ComfyUI/models/checkpoints` 文件夹中的模型，同时也会读取 extra_model_paths.yaml 文件中配置的其他路径中的模型。有时，您可能需要**刷新 ComfyUI 界面**，以便它从相应文件夹中读取模型文件。 unCLIPCheckpointLoader 节点专为加载 unCLIP 模型量身定制的检查点而设计。它便于从指定检查点检索和初始化模型、CLIP 视觉模块以及 VAE，从而简化后续操作或分析的设置流程。 diff --git a/zh/built-in-nodes/unCLIPConditioning.mdx b/zh/built-in-nodes/unCLIPConditioning.mdx index 280ff9842..8c59fc57c 100644 --- a/zh/built-in-nodes/unCLIPConditioning.mdx +++ b/zh/built-in-nodes/unCLIPConditioning.mdx @@ -5,6 +5,7 @@ sidebarTitle: "unCLIPConditioning" icon: "circle" mode: wide --- + 此节点旨在将 CLIP 视觉输出整合到条件处理过程中，根据指定的强度和噪声增强参数调整这些输出的影响。它通过视觉上下文丰富条件处理，从而增强生成过程。 ## 输入 diff --git a/zh/built-in-nodes/wanBlockSwap.mdx b/zh/built-in-nodes/wanBlockSwap.mdx index 6972b91d2..0f04fa0a2 100644 --- a/zh/built-in-nodes/wanBlockSwap.mdx +++ b/zh/built-in-nodes/wanBlockSwap.mdx @@ -5,6 +5,7 @@ sidebarTitle: "wanBlockSwap" icon: "circle" mode: wide --- + 此节点已弃用，不执行任何功能。它接受一个模型作为输入，并原样返回相同的模型。描述中的“NOP”表示它不执行任何操作。 ## 输入