Submit a resource

Navigation

Back to directory

biniou

A self-hosted web UI for more than 30 kinds of generative AI, including image, audio, video and chat models, able to run offline on modest hardware without a dedicated GPU.

Visit website (opens in a new tab)github.com
biniou

biniou is a self-hosted web UI, built with Gradio, for running more than 30 kinds of generative AI locally, including image generation and editing (Stable Diffusion, SDXL, Flux, Kandinsky, ControlNet, and related models), a text chatbot backed by local GGUF models through llama-cpp-python, speech and audio generation (Bark, AudioCraft), image restoration and upscaling (GFPGAN, Real-ESRGAN), face tools (InsightFace, PhotoMaker), and video (AnimateDiff).

It can run offline once deployed and its models are downloaded, works on systems with as little as 8GB of RAM and no dedicated GPU, and is packaged for several GNU/Linux distributions, Windows, an experimental macOS Intel build, and Docker. It is updated on a roughly weekly cadence with new model and LoRA support across its chatbot, image, and video modules.

It is written in Python and released under the GPL-3.0 license.

More in Inference

See all 770

  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy