[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

Fast and memory-efficient exact attention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Docs for GGUF quantization (unofficial)

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

根据wan2.2官方提供的提示词文档制作的提示词选取器

GGUF Quantization support for native ComfyUI models

LLM inference in C/C++

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

Enjoy the magic of Diffusion models!

HunyuanVideo: A Systematic Framework For Large Video Generation Model

We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a re…

Wan: Open and Advanced Large-Scale Video Generative Models

一个超轻量级、可以在移动端实时运行的数字人模型

talking-face video editing

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

Taming Stable Diffusion for Lip Sync!

Official inference repo for FLUX.1 models

Examples of ComfyUI workflows

A powerful tool that translates ComfyUI workflows into executable Python code.

some wyrde workflows for comfyUI

Unofficial implementation of YOLO-World + EfficientSAM for ComfyUI