Store

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

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

One-click installer for Microsoft TRELLIS.2: High-quality 3D asset generation from images with PBR textures.

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

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. https://github.com/deepbeepmeep/Wan2GP

Contribute to Tongyi-MAI/Z-Image development by creating an account on GitHub.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Contribute to LujiaJin/FlashVSR-Pro development by creating an account on GitHub.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Distill and quantize models using TorchAO with intelligent GPU/CPU management

Get up and running with GLM-4.7, DeepSeek, gpt-oss, Qwen, Gemma and other models.

AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Fast, multi-speaker TTS (44.1kHz) with voice cloning

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team

The ultimate training toolkit for finetuning diffusion models

Video Matting with complete cross-platform support for Windows, macOS, and Linux

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.