Open Generative AI GitHub Repo: A Self-Hosting Teardown (2026)

说明与用途

Open Generative AI 提供 MIT 许可的 UI，聚合数百个云模型，并提供两种本地推理引擎（sd.cpp 用于图像，Wan2GP 用于视频）。适合原型开发，但需要 Muapi 密钥和强大硬件支持本地推理。

问题

Clients want a free, self‑hosted generative‑AI UI but the repo’s open‑source code hides that many models are still cloud‑based and local inference has high hardware costs.

结果

The repo offers a comprehensive UI but requires a Muapi key for most models and significant hardware for local inference. It is suitable for prototyping and side‑by‑side model comparison, but not ideal for fully offline production workflows.

工作流

• Clone repo with submodules
• Run npm run setup to install dependencies and build packages
• Choose npm run electron:dev for desktop or npm run dev for web
• Configure Muapi key in settings for cloud models
• Install sd.cpp via Settings for image inference
• Install Wan2GP on a CUDA/ROCm GPU and configure MCP URL for video inference

证据

If you search "open generative ai github" in 2026, the repo you land on is Anil‑matcha/Open‑Generative‑AI: an MIT‑licensed Next.js and Electron studio for image, video, and lip sync generation, at roughly 29.7k stars and 5.4k forks as of October 6.

来源

Cloud generation goes through the Muapi.ai API with your own key, and truly local inference only exists in the desktop app, through two engines with real hardware requirements.

来源

The README is clear that most people should grab a prebuilt installer. If you want to hack on it, this is the path, and I checked each script name against package.json: ... npm run setup ... npm run electron:dev ... npm run dev ... npm run build && npm run start

来源

sd.cpp (bundled). Built on stable‑diffusion.cpp. You install it with one click under Settings, then Local Models. It handles image models only: Dreamshaper 8, Realistic Vision 5.1, and Anything v5 (SD 1.5, about 2.1 GB each), SDXL Base 1.0 (6.9 GB), and Z‑Image Turbo and Base, which also need a 2.4 GB Qwen3‑4B text encoder and a 335 MB FLUX VAE.

来源

Wan2GP (bring your own). This is where video lives. The app doesn’t bundle Python or weights. You install Wan2GP yourself on a CUDA or ROCm machine, and the app either runs wgp.py from a local folder or talks to Wan2GP’s MCP server on another box.

来源