[ICCV 2025][Few-Step Student Surpasses Teacher Diffusion] Learning Few-Step Diffusion Models by Trajectory Distribution Matching

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

Wan: Open and Advanced Large-Scale Video Generative Models

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

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

Download market data from Yahoo! Finance's API

A unified inference and post-training framework for accelerated video generation.

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

A high-throughput and memory-efficient inference and serving engine for LLMs

Code for our ICCV 2025 paper "Adaptive Caching for Faster Video Generation with Diffusion Transformers"

[ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

Unofficial implementation of LSQ-Net, a neural network quantization framework

VideoSys: An easy and efficient system for video generation

PyTorch extensions for high performance and large scale training.

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

LPIPS metric. pip install lpips

MobileFaceSwap: A Lightweight Framework for Video Face Swapping (AAAI 2022)

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

Official implementation of the NeurIPS 2023 paper "Photoswap: Personalized Subject Swapping in Images"

An arbitrary face-swapping framework on images and videos with one single trained model!

StyleSwap: Style-Based Generator Empowers Robust Face Swapping (ECCV 2022)

[CVPR 2023] DiffSwap is a diffusion-based face-swapping framework.

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models