Stonewuu/ai-fusion-video

What is it?

Key features

• 01Infinite canvas for linking scripts, storyboards, characters, and generation steps
• 02Built-in assistant that works with project context and can call MCP tools
• 03Import ComfyUI API-format workflows and bind them to image or video models
• 04Script and storyboard management organized by episode and scene
• 05Model configuration for text, image, and video services, with local or S3-compatible storage
• 06One-command Docker Compose deployment

Use cases

• Producing short drama or motion comic episodes from a script to finished video
• Breaking a script into storyboard shots and generating reference images for each
• Self-hosting an AI video production workspace for a small studio or team

Quick start

1. 1

   Clone the repository

   git clone https://github.com/Stonewuu/ai-fusion-video.git
2. 2

   Enter the project directory

   cd ai-fusion-video
3. 3

   Create the environment file from the template

   cp .env.example .env
4. 4

   Start all services with Docker Compose, then open http://localhost:8080 to create the admin account

   docker compose up -d

Things to know

• !Default database and Redis passwords are 123456 and must be changed before public deployment.
• !Image and video generation requires you to configure your own model provider API keys and accounts.
• !Source development also requires FFmpeg and FFprobe installed locally for video composition.

In collections

Topics

FAQ

What is ai-fusion-video?

Open-source Java and Next.js platform that puts scripts, storyboards, and image/video generation for short dramas and motion comics in one agent-driven workspace. Fusion (融光) is an agent-driven creation platform for video creators. It brings projects, scripts, storyboards, and assets together with image and video generation in one workspace. Scripts are organized by episode and scene, storyboards can be split and adjusted, and each shot can have its materials generated and managed.

Is ai-fusion-video free to use? What license does it have?

ai-fusion-video is open source under the MIT license. Check the license terms before using it in commercial products.

Is ai-fusion-video still maintained?

Actively maintained. The last commit to ai-fusion-video was on Nov 4, 2026.

What can I use ai-fusion-video for?

Producing short drama or motion comic episodes from a script to finished video Breaking a script into storyboard shots and generating reference images for each Self-hosting an AI video production workspace for a small studio or team

How do I install ai-fusion-video?

Clone the repository: git clone https://github.com/Stonewuu/ai-fusion-video.git Enter the project directory: cd ai-fusion-video Create the environment file from the template: cp .env.example .env Start all services with Docker Compose, then open http://localhost:8080 to create the admin account: docker compose up -d

Where can I get ai-fusion-video?

The source code and installation instructions are on GitHub: https://github.com/Stonewuu/ai-fusion-video