Stars
STCDiT for Real-World Video Enhancement and AIGC Enhancement. It achieves temporally stable and structurally faithful restoration even under complex motions.
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
[NeurIPS 2025] 4KAgent: Agentic Any Image to 4K Super-Resolution. An intelligent computer vision agent that can magically restore any image to perfect-4K!
Enjoy the magic of Diffusion models!
A unified inference and post-training framework for accelerated video generation.
The codes for Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】
SkyReels-V2: Infinite-length Film Generative model
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"
Janus-Series: Unified Multimodal Understanding and Generation Models
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation
Iterable datapipelines for pytorch training.
PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations
A comprehensive summary of deep face restoration methods.
[NeurIPS 2024] VideoTetris: Towards Compositional Text-To-Video Generation
Code for ECCV 2024 Paper "Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution"
Generative Models by Stability AI
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.
Open-Sora: Democratizing Efficient Video Production for All
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
[IJCV 2024] LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models
[CVPR 2024] Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution