Stars
Official Code for DragGAN (SIGGRAPH 2023)
WebUI extension for ControlNet
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Character Animation (AnimateAnyone, Face Reenactment)
pytorch structural similarity (SSIM) loss
[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization
AgentEvolver: Towards Efficient Self-Evolving Agent System
[NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Official code of SmartEdit [CVPR-2024 Highlight]
[AAAI2025] DesignEdit: Unify Spatial-Aware Image Editing via Training-free Inpainting with a Multi-Layered Latent Diffusion Framework
ECCV 2022, Oral, VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Simple framework for image and video deblurring, implemented by PyTorch
Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"
Official code for "AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation" (CVPR2023)
Q-Insight Family: Q-Insight, VQ-Insight and RALI (NeurIPS 2025 Spotlight, AAAI 2026 Oral, and ICLR 2026 Oral)
Toward Convolutional Blind Denoising of Real Photograph
DreamO native implementation for ComfyUI
Codes for "Metric Learning based Interactive Modulation for Real-World Super-Resolution"
Accepted by CVPR 2022
[ICLR 2026] GenCompositor: Generative Video Compositing with Diffusion Transformer
NeurIPS 2021, Spotlight, Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution
Code for [CVPR 2025] ROICtrl: Boosting Instance Control for Visual Generation
Dynamic Attentive Graph Learning for Image Restoration, ICCV2021 [PyTorch Code]
NTIRE 2023 Challenge on 360° Omnidirectional Image and Video Super-Resolution