-
Tsinghua University, NICS-EFC Lab
- Beijing, China
Stars
🎁 5,400,000+ Unsplash images made available for research and machine learning
Official Github Repo for Neurips 2024 Paper Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
Release for Improved Denoising Diffusion Probabilistic Models
[IJCV 2024] LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models
Official Code for Stable Cascade
The official implementation of "Relay Diffusion: Unifying diffusion process across resolutions for image synthesis" [ICLR 2024 Spotlight]
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
FMBoost: Boosting Latent Diffusion with Flow Matching (ECCV 2024 Oral)
Implementation of rectified flow and some of its followup research / improvements in Pytorch
Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"
TorchCFM: a Conditional Flow Matching library
Official Pytorch Implementation of the paper: Wavelet Diffusion Models are fast and scalable Image Generators (CVPR'23)
Code of Pyramidal Flow Matching for Efficient Video Generative Modeling
FlashInfer: Kernel Library for LLM Serving
Writing AI Conference Papers: A Handbook for Beginners
Pytorch implementation of MaskGIT: Masked Generative Image Transformer (https://arxiv.org/pdf/2202.04200.pdf)
[arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization
In 2024, the strongest open-source implementation of asymmetric magvit_v2 supports inference code but excludes VQVAE. It supports the joint encoding of images and videos, accommodating arbitrary vi…
Official inference repo for FLUX.1 models
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
The official code of paper "OMS-DPM: Optimizing Model Schedule for Diffusion Probabilistic Model" accepted by ICML 2023