Stars
PyTorch code and models for the DINOv2 self-supervised learning method.
Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)
[ECCV 2022] Flow-Guided Transformer for Video Inpainting
[CVPR 2022] Inertia-Guided Flow Completion and Style Fusion for Video Inpainting
[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
The official codebase for "Empowering Diffusion Models on the Embedding Space for Text Generation" (NAACL 2024)
TransNet V2: Shot Boundary Detection Neural Network
Open source implementation and models of One-step Diffusion with Distribution Matching Distillation
Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).
Official inference repo for FLUX.1 models
LaTeX style file for the Journal of Machine Learning Research
Scenic: A Jax Library for Computer Vision Research and Beyond
Rapid fuzzy string matching in Python using various string metrics
The Levenshtein Python C extension module contains functions for fast computation of Levenshtein distance and string similarity
Benchmark for generative image models
PyTorch code and model checkpoints for Score identity Distillation (SiD) published in ICML 2024
CVPR2021 Learning Multi-Scale Photo Exposure Correction论文的非官方pytorch代码
Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).
Pytorch implementation of LEGO-Diffusion: Learning stackable and skippable LEGO bricks for efficient, reconfigurable, and variable-resolution diffusion modeling
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022
Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)
In defence of metric learning for speaker recognition
official code for Diff-Instruct algorithm for one-step diffusion distillation
Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.