Comfy-Org · comfyui-wiki · Jul 5, 2026 · Jul 5, 2026
diff --git 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
@@ -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
@@ -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
@@ -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 **Note:** This node is deprecated and superseded by the Concatenate Text node.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
@@ -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 **This node is deprecated** and superseded by the Concatenate Text node.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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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"`<br />`"fill"`<br />`"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
@@ -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"`<br />`"select"`<br />`"custom"` |
 | `max_resolution` | The maximum resolution for the output video (default: "1080p"). | COMBO | Yes | `"720p"`<br />`"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
@@ -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
@@ -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