Project updates
Latest Master Branch
Fork from https://github.com/facefusion/facefusion-pinokio Which always installs / Updates to the latest Mast...
X-Voice The universal translator
X-Voice is a voice clone app that lets you clone voices in any language. The Zero-Shot Voice Cloning tab work...
I’ve completed a full installer for FluxRT and have already integrated several new modes into the UI, includi...
Fooocus2026 — Pinokio launcher available now
A one-click way to install my fork of Fooocus 2.5.5, with the quality-of-life additions I kept missing in ups...
Store
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
Remove backgrounds from videos and images with precision AI matting. Runs locally on 12GB VRAM — Windows, Linux, and macOS.
AI Song Generation on Mac Apple Silicon, with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model.
[AMD ONLY] Super Optimized Gradio UI for AI video creation for GPU poor machines (6GB+ VRAM). Supports Wan 2.1/2.2, Qwen, Hunyuan Video, LTX Video and Flux. (On Windows supported by 7900(XT), 7800(XT), 7600(XT), Phoenix, 9070(XT) and Strix Halo)
14 check-ins
FramePackFeatured
[NVIDIA ONLY] Generate Video Progressively. FramePack is a next-frame (next-frame-section) prediction neural network structure that generates videos progressively. https://github.com/lllyasviel/FramePack
10 check-ins
Pinokio launcher for LTX-Desktop-WanGP (local video generation with WanGP backend)
@hoodtronik3 check-ins
Local UI for MLX Video (Next.js frontend + FastAPI backend).
[NVIDIA, ROCM] One app to train them all. LORA training and Model finetuning for Z-Image, Qwen Image, FLUX.1, Flux.2 Dev and Klein, Chroma, SD 1.5 - 3.5, SDXL, Würstchen-v2, Stable Cascade, PixArt-Alpha, PixArt-Sigma, Sana, Hunyuan Video and inpainting models.
[NVIDIA, ROCM] One app to train them all. LORA training and Model finetuning for Z-Image, Qwen Image, FLUX.1, Flux.2 Dev and Klein, Chroma, SD 1.5 - 3.5, SDXL, Würstchen-v2, Stable Cascade, PixArt-Alpha, PixArt-Sigma, Sana, Hunyuan Video and inpainting models.
Practical human video matting framework that preserves fine details. Drop your video, assign target masks with a few clicks, and get foreground/alpha matting results.
Native C++ AI music generation — no Python required
SillyTavernFeatured
a local-install interface that allows you to interact with text generation AIs (LLMs) to chat and roleplay with custom characters. https://docs.sillytavern.app/
Transform flat 2D sprite PNGs into layered 2.5D asset packs (albedo, normal map, emission, shadow) for Unity, UE5, or custom renderers.
OpenAI-compatible Speech-to-Text and Text-to-Speech server. Powered by Faster-Whisper, Kokoro, and Piper.
Practical human video matting framework that preserves fine details. Drop your video, assign target masks with a few clicks, and get foreground/alpha matting results.
A fully local, cross-platform audio visualizer editor. Create reactive music videos with layered graphics, AI-transcribed lyrics, and frame-perfect MP4 exports — all running in your browser
@theawakenone2 check-ins
Pinokio launcher for the MLX-only SongGeneration Studio.