#diffusion-models Repositories
473 repositories total
A unified inference and post-training framework for accelerated video generation.
Whether you are a complete beginner, project application in CV, NLP, LLM, or advanced engineering deployment and implementation, you will find everything here in "Practical PyTorch Tutorial" (2nd Edition). We believe that with the help of this book, readers will be able to easily master the use of PyTorch and become excellent deep learning engineers.
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
Diffusion model papers, survey, and taxonomy
PixArt-ฮฑ: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models
[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.
High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
[ECCV 2026 Spotlight] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"
A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and efficient deployment.
Official PyTorch implementation of One-Minute Video Generation with Test-Time Training
๐น A more flexible framework that can generate videos at any resolution and creates videos from images.