Open Generative AI
Free, self-hosted app for generating AI images and videos with many third-party models.
- Stars
- 32k
- Forks
- 6.1k
- Licence
- MIT
- Language
- JavaScript
- Last update
- 5 days ago
- Type
- App
What it is
Open Generative AI is a desktop and web studio for creating AI images and videos. It gives you access to a large set of image and video models from one interface, and it is MIT licensed so the code is free to inspect and modify. The README says it has no content filters and that you can also use a hosted version in the browser.
- Generate still images from text prompts using a range of image models
- Create short videos from text or from an image using video models
- Explore different models side by side to compare output styles
- Use the hosted browser version without installing anything
Great for
- People who want to try many AI image and video models in one place
- Creators who want a free, self-hostable front end for generative media
- Developers who want to read or modify an Electron and JavaScript studio app
- Users who prefer a one-click desktop installer over setting up tools by hand
Not ideal for
- People who need a fully offline tool: the README describes generation through hosted model services, and it does not say which parts run locally
- Users who want a guarantee of content moderation or safety filtering, since the README advertises no content filters
- Anyone who expects every listed model to be free: the README mentions paid plans and credits for the related hosted service
How to get it
- 1
Download the app
Clone the repository
git clone https://github.com/Anil-matcha/Open-Generative-AIBuild Linux installers (AppImage + .deb)
npm run electron:build:linux - 2
Run it
- Download the installer for your platform from the v2.0.0 release page
- On macOS, run the xattr command in the README or use the System Settings override to open the app
- On Windows, click More info then Run anyway if SmartScreen appears
- Open the app and sign in or configure access to models as the app requires
- Enter a prompt in one of the studios and generate a first result
- 3
Get the most out of it
- Try the hosted browser version first to see the studios before installing the desktop app
- Use the API example repositories (OpenAI, Gemini, Kling, Qwen, MiniMax) if you want to call models from your own code
- Check the awesome-ai-video-models and awesome-ai-image-models repos to compare models by price and capability
- Explore the Workflows and Agents studios listed in the README for multi-step tasks
Downloads
Strengths
- Free and MIT licensed, with source code on GitHub
- Ships one-click installers for macOS, Windows, and Linux
- Gives access to a large catalog of models through one interface
Trade-offs
- The README is promotional in places and links heavily to a commercial hosted service (MuAPI), so it is hard to separate the open-source tool from the paid offering
- Unsigned installers trigger macOS Gatekeeper and Windows SmartScreen warnings that require manual steps to bypass
- Model usage depends on external services; the README does not clearly explain costs or limits for them
How it compares
| Project | Stars | Type | Level | Updated | Best for |
|---|---|---|---|---|---|
| Open-Generative-AI (this) | 32k | App | beginner | 5 days ago | People who want to try many AI image and video models in one place |
| Toonflow-app | 20.2k | App | intermediate | 6 days ago | Independent creators making short dramas or motion comics who want a self-hosted workflow |
| langflow | 156k | App | intermediate | 4 days ago | Developers who want a visual way to prototype LLM workflows and then move them into code |
| mcp-for-blender | 33k | AI model / agent | intermediate | 8 days ago | Blender users who want to try describing scenes or objects in plain language |
| generative-ai-for-beginners | 123k | Learning resource | beginner | 5 days ago | Developers who know some Python or TypeScript and want a guided introduction to generative AI |
| Prompt-Engineering-Guide | 79.8k | Learning resource | beginner | 8 months ago | People who are new to prompting and want structured lessons with examples |
Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.