Woolverine94/biniou

Health v2 · maintenance only

Adoption not part of the score

1150 stars · 137 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

biniou is a self-hosted web UI for 30+ generative AI models covering image, video, audio, and text generation, built with Gradio and Hugging Face libraries. It runs locally on modest hardware (from 8GB RAM, no dedicated GPU required) and can work fully offline once models are downloaded.

Use cases

• generate images locally with stable diffusion and flux
• run a local chatbot with llama.cpp gguf models
• transcribe audio to text with whisper offline
• generate music and speech with audiocraft and bark
• upscale and restore faces with real-esrgan and gfpgan
• self-host an all-in-one generative ai studio without a gpu
• use generative ai completely offline on my own computer

When to choose

• you want one self-hosted interface for many kinds of generative AI (image, video, audio, text)
• you have limited hardware and no dedicated GPU
• you need offline operation after initial model download
• you want a Gradio-based web UI that is easy to deploy on Linux, Windows, macOS, or Docker

When to avoid

• you need a production-grade, multi-user AI service with authentication and scaling
• you only need one specific model and prefer a lighter dedicated tool
• you require fine-grained programmatic APIs rather than a web UI
• you need macOS Apple Silicon support, which is experimental

Facets

application · maturity active

llm-inference stable-diffusion speech-recognition tts chatbot image-processing audio-processing self-hosted gui artificial-intelligence large-language-models image-processing machine-learning self-hosted windows python cross-platform generative-ai webui gradio huggingface diffusers controlnet flux whisper bark llama-cpp offline-ai multimedia-generation audio linux macos docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Woolverine94/biniou")