-
ECNU
- shanghai
Starred repositories
CatVTON warpper for ComfyUI
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
Enjoy the magic of Diffusion models!
[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation
This repository implements a lane detection and classification model.
Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
YOLOv10: Real-Time End-to-End Object Detection
pytorch单精度、半精度、混合精度、单卡、多卡(DP / DDP)、FSDP、DeepSpeed模型训练代码,并对比不同方法的训练速度以及GPU内存的使用
[ICCV2023] ADNet: Lane Shape Prediction via Anchor Decomposition
Lane detection with PaddlePaddle. PPLanedet contains many SOTA methods, e.g. CondLaneNet, SCNN, RESA, RTFormer,UFLD
TensorRT Extension for Stable Diffusion Web UI
Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Unofficial Implementation of Animate Anyone
A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.
Easily use MagicAnimate within ComfyUI
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
A plugin for multilingual translation of ComfyUI,This plugin implements translation of resident menu bar/search bar/right-click context menu/node, etc
extra nodes to be used in comfyUI
基于TensorRT的C++高性能推理库,Yolov10, YoloPv2,Yolov5/7/X/8,RT-DETR,单目标跟踪OSTrack、LightTrack。