#48 · Primary category: Image Generation

biniou

animatediff audiocraft bark controlnet diffusers flux generative-ai gfpgan gradio huggingface insightface ip-adapter kandinsky llama-cpp-python photomaker real-esrgan stable-diffusion stable-diffusion-3-5 webui whisper

a self-hosted webui for 30+ generative ai

Project last updated:08/29/26

GitHub Stars

1.1K

Forks

137

Contributors

6

License

GPL-3.0

Why we included this project

biniou turns your own computer into a generative AI studio, bundling more than thirty models behind one browser interface so you can produce images, audio, video, and even chat without leaving your machine. Image generation is the strongest area, with Stable Diffusion, Flux, ControlNet, and IP-Adapter, plus upscalers like GFPGAN and Real-ESRGAN. The same install also provides speech synthesis and a chatbot, and a send panel lets you chain outputs between modules, say captioning an image and feeding that text to an audio generator. It runs on modest hardware, starting from about 8GB of RAM and no dedicated GPU, and works offline once models are downloaded. Docker images and cross-platform guides make it easy to try in a team setting.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category