Store

A UI for creating and sharing interactive ML apps, built with Gradio.

Download from YouTube or upload any track and effortlessly split it into four separate stems — vocals, drums, bass, and other — with StemXtract. Create clean instrumentals, isolate individual stems, mix custom combinations, or craft unique mashups by blending tracks. Features smart tempo/beat matching, simple effects, and easy mixing controls.

🎨 High-quality AI image generation with FLUX.2-dev (NVFP4/4-bit). Text-to-image and image-to-image generation optimized for 24GB VRAM GPUs with remote text encoder support.

⚡️ Efficient 6B parameter image generation model with sub-second inference. Generate high-quality, photorealistic images with only 8 inference steps. Features bilingual text rendering (Chinese & English) and Single-Stream Diffusion Transformer architecture.Minimum 4GB graphics memory is supported.

Real-time AI video generation tool.

Extract any sound with text prompts. Memory-optimized SAM-Audio with modern UI.

Convert your text into speech using Microsoft Edge TTS

Generate a story with AI or type your own, and convert it with voice cloning from uploaded samples

🎮 Classic Tetris game with modern web UI. Play the timeless puzzle game in your browser with smooth controls, score tracking, and beautiful graphics.

Diffusion-based rhythm generation with DiffRhythm2 model

[NVIDIA ONLY] Generate videos with less than 10GB VRAM https://github.com/THUDM/CogVideo

[NVIDIA ONLY] Advanced Web UI for CogVideo (text to video, image to video, video to video, extend video, etc) -- Generate videos with less than 10GB VRAM

Ad-free YouTube frontend with Ollama AI summarization (forked from christian-fei/my-yt)

Full-featured backup & restore tool for Pinokio models and apps

Web GUI for yt-dlp with playlist support. Download videos from YouTube and dozens of other sites.