Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)

Video Processing in Python

Demos for deep learning

Let's train vision transformers (ViT) for cifar 10 / cifar 100!

[🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

从零手搓Flow Matching（Rectified Flow）

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.

Multi-modality pre-training

Rectified Flow Inversion (RF-Inversion) - ICLR 2025

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images

Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

[CVPRW 2022] MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment

CVPR 2025: Frequency Dynamic Convolution for Dense Image Prediction

An easy way to apply LoRA to CLIP. Implementation of the paper "Low-Rank Few-Shot Adaptation of Vision-Language Models" (CLIP-LoRA) [CVPRW 2024].

code based for rectified flow

[CVPR2023] Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

[ECCV 2024] OneRestore: A Universal Restoration Framework for Composite Degradation

[CVPR 2025] Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution

Official Implementation for Diffusion Models Without Classifier-free Guidance

[ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

[ECCV 2024] Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration

Blind/Referenceless Image Spatial QUality Evaluator (BRISQUE)

The official pytorch implemention of our CVPR-2024 paper "MMA: Multi-Modal Adapter for Vision-Language Models".

Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight https://openreview.net/forum?id=XJk19XzGq2J

Offical implementation of Universal Image Restoration Pre-training via Degradation Classification (ICLR2025).

Maximize Efficiency, Elevate Accuracy: Slash GPU Hours by Half with Efficient Pre-training!

Proteus (ICLR2025)

A repo of a modified version of Diffusion Transformer