Stars
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
[ECCV 2024] DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation
Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.
Official implementation of ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
An open-source toolbox for fast sampling of diffusion models. Official implementations for our [CVPR-2024, ICML-2024] papers
Boosting the performance of consistency models with PCM!
Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.
Official Implementation for "Consistency Flow Matching: Defining Straight Flows with Velocity Consistency"
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models
VideoTetris: Towards Compositional Text-To-Video Generation
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
Official repo of our paper "SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions"
MiniSora: A community aims to explore the implementation path and future development direction of Sora.
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)
You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator