Build AI image & video pipelines visually.
Chain prompts, models, reference images, and automations on an infinite canvas.

---

Demo

You can check the demo here: https://demo.sdd.cash/ And create an account and use it here : https://helios.sdd.cash/

---

📸 Screenshots

✨ Simple Image & Video Generation

---

🔄 Workflow Generation

---

🧠 Native JSON Prompt Preview

---

💬 AI Prompt Improvement Assistant

✨ HeliosGen

HeliosGen is a free & open source visual AI workflow builder for image and video generation.

Build reusable AI pipelines with:

• infinite node-based workflows,
• multi-model generation,
• reference images,
• automation chains,
• and self-hosted infrastructure.

No subscriptions.
No disappearing credits.
No vendor lock-in.

---

💳 Credits

HeliosGen now works with kie.ai.

All credits are purchased directly on your own account and never expire.

That means:

• no monthly reset,
• no lost credits,
• no subscription lock-in,
• and full ownership of your usage.

You only pay for what you generate.

---

🚀 Features

• Infinite node-based canvas
• AI image & video generation
• Drag-and-connect workflow system
• Multi-model pipelines
• Reference image support
• Parallel & sequential pipeline execution
• Shareable public workflows
• Per-user API keys
• Real-time generation history
• Self-hostable architecture
• Modern responsive UI

---

⚡ Supported Models

Images

• GPT Image 2 (OpenAI)
• Nano Banana / Nano Banana 2 / Nano Banana 2 Lite / Nano Banana Pro (Google)
• Seedream 5.0 Lite / Pro (Seedream)
• Z-Image (Z-AI)
• Grok Imagine (X)

Videos

• Veo 3.1 Lite / Fast / Quality, Gemini Omni Video (Google)
• Kling 3.0, Kling 3.0 Turbo, Motion Control 2.6 / 3.0 (Kling)
• Seedance 2.0 / Fast / Mini (Bytedance)
• Grok Imagine, Grok Imagine 1.5 preview (X)
• HappyHorse (Alibaba)

More models are coming.

---

🏗️ Tech Stack

Layer	Technology
Frontend	Next.js + React + TypeScript
Backend	Next.js API Routes
Database	Supabase / JSON
Storage	Cloudflare R2 / Local disk
AI Backend	Kie.ai
Deployment	Vercel / Railway / Render

---

🚀 Getting Started

1. Clone the repository

git clone https://github.com/SegFault42/HeliosGen
cd HeliosGen
npm install

---

2. Guest Mode (quick setup)

Requirements:

• Kie.ai API key
• ngrok

cp .env.guest .env.local

Fill your .env.local:

GUEST_MODE=true
KIE_API_KEY=your_key
CALLBACK_BASE_URL=https://xxxx.ngrok-free.app

Start ngrok:

ngrok http 3000

Run the app:

npm run dev

---

3. Cloud Mode (production)

Requirements:

• Supabase
• Cloudflare R2
• Kie.ai API key

3a. Database setup

Open the SQL Editor in your Supabase project and run the two migration files in order:

1. supabase-setup.sql — core tables (generations, uploads, spaces, settings)
2. supabase-folders.sql — gallery folders & folder items

3b. Environment variables

Create .env.local:

CALLBACK_BASE_URL=https://your-domain.com

NEXT_PUBLIC_SUPABASE_URL=
NEXT_PUBLIC_SUPABASE_ANON_KEY=
SUPABASE_SERVICE_ROLE_KEY=

R2_ACCOUNT_ID=
R2_ACCESS_KEY_ID=
R2_SECRET_ACCESS_KEY=
R2_BUCKET_NAME=
R2_PUBLIC_URL=

3c. Run

npm run dev

---

🤖 Codex CLI (optional — alternate GPT Image 2 backend)

Instead of routing GPT Image 2 through Kie.ai credits, HeliosGen can generate through your own ChatGPT Codex subscription via codex-imagegen-cli. This is a single shared login on the server — not a per-user API key — so it's best suited to self-hosted / single-user setups.

Requirements:

• A ChatGPT Plus/Pro/Team/Enterprise account with Codex access
• codex CLI installed on the machine running the server
• uv (Python package manager)

1. Install the Codex CLI

# macOS
brew install codex

# or, cross-platform
npm install -g @openai/codex

2. Install codex-imagegen-cli

git clone https://github.com/jdmnk/codex-imagegen-cli.git
cd codex-imagegen-cli
uv sync --dev
uv tool install -e .

This installs the codex-imagegen binary — make sure it's on the server's PATH.

3. Log in

Either:

• run codex login in a terminal on the server (opens a browser to sign in), or
• open the app → Settings → API Keys → Codex CLI → Connect Codex, which walks you through a device-code login — visit the printed URL and enter the code, no terminal needed.

⚠️ Starting a new login (either way) immediately invalidates any existing session on that machine — the CLI clears old credentials the moment a login attempt begins, whether or not it's ever completed. Only start one when the status badge below shows NOT CONFIGURED.

4. Enable it for GPT Image 2

In Settings → Image Models, set GPT Image 2's provider toggle to Codex CLI. The status badge in Settings → API Keys shows READY once both the CLI and login are in place.

---

🌍 Deployment

Recommended platforms:

• Vercel
• Railway
• Render
• Fly.io

npm run build && npm start

---

🤝 Contributions

Contributions are welcome.

If you find a bug, have an idea, or want to improve HeliosGen:

• Open an issue
• Submit a pull request
• Share feedback or feature requests

All contributions are appreciated.

---

📄 License

MIT License

---

Built for creators building the future of AI workflows.