An app for creating audio-based content such as song covers and speech using Retrieval-based Voice Conversion.

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Nitro-T is a family of text-to-image diffusion models focused on highly efficient training.

Light Image Video Generation Inference Framework

Truly independent web browser

Tiny AutoEncoder for Hunyuan Video (and other video models)

Random nodes for ComfyUI

A new ecosystem similar to World Wide Web, featuring gurt:// protocol, custom browser (from scratch), HTML + CSS + Lua sites, DNS, search engine, server management tool, and more.

Microscopic NixOS build designed for embedded environments. [Maintainers=@NotAShelf, @DamitusThyYeetus123]]

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.