yiyunchen

VAR-CLIP

Implements VAR+CLIP for image generation

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

Deep-Live-Cam

real time face swap and one-click video deepfake with only a single image

ControlNeXt

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

VmambaIR

This is official implementtaion of "VmambaIR: Visual State Space Model for Image Restoration"

SEA-RAFT

[ECCV2024 Oral] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

annotation-tool

FineDiving

FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment

CogVideo

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

COCOCO

Video-Inpaint-Anything: This is the inference code for our paper CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility.

IDM-VTON-training

IDM-VTON-training : This is an unofficial training code of idm-vton

DMT

Deficiency-Aware Masked Transformer for Video Inpainting

FuseFormer

official Pytorch implementation of ICCV 2021 paper FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting.

IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

Sports-QA

Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

SportsHHI

[CVPR 2024] SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos

FineSports_CVPR2024

MultiSports

[ICCV 2021] MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

IDM-VTON

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

decord

An efficient video loader for deep learning with smart shuffling that's super easy to digest

Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

TAdaConv

[ICLR 2022] TAda! Temporally-Adaptive Convolutions for Video Understanding. This codebase provides solutions for video classification, video representation learning and temporal detection.

EssentialMC2

EssentialMC2 Video Understanding.

PaddleVideo

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

PaddleSports

promptbench

A unified evaluation framework for large language models

havenask