Stars
[ICCV 2025] VisualCloze: A universal image generation framework that can support a wide range of in-domain tasks and generalize to unseen ones. (🔥 🔥 🔥 Merged into offical pipelines of diffusers.)
Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
[SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization
Official implementation of "HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment"
Official implementation of "SPF-Portrait: Towards Pure Portrait Customization with Semantic Pollution-Free Fine-tuning"
HunyuanVideo: A Systematic Framework For Large Video Generation Model
[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer
LLM2CLIP significantly improves already state-of-the-art CLIP models.
[NeurIPS 2024] RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
[ICCV2025] UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
StoryMaker: Towards consistent characters in text-to-image generation
Official inference repo for FLUX.1 models
Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation
Codes for ID-Specific Video Customized Diffusion
[TMM 2025] StableIdentity: Inserting Anybody into Anywhere at First Sight 🔥
RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with the file name of the associated labeled images (no urls or im…
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)
An efficient video loader for deep learning with smart shuffling that's super easy to digest
SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Repository for Detail-revealing Deep Video Super-resolution https://arxiv.org/abs/1704.02738