Solve Visual Understanding with Reinforced VLMs

Visual code dependency graph creation for C/C++ projects

Bookmarks Extension for Visual Studio Code

[CVPR2025] HVI: A New Color Space for Low-light Image Enhancement && "You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement"

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

PyTorch implementation of FractalGen https://arxiv.org/abs/2502.17437

Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown

YOLOv12: Attention-Centric Real-Time Object Detectors

Edit, preview and share mermaid charts/diagrams. New implementation of the live editor.

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

Official implementation of "DepthMaster: Taming Diffusion Models for Monocular Depth Estimation".

DeepSeek Coder: Let the Code Write Itself

Official implementation of ICCV2023 "Towards Real-World Burst Image Super-Resolution: Benchmark and Method"

Arbitrary-steps Image Super-resolution via Diffusion Inversion (CVPR 2025)

这是各个主干网络分类模型的源码，可以用于训练自己的分类模型。

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

Packer is a tool for creating identical machine images for multiple platforms from a single source configuration.

YOLO-UniOW: Efficient Universal Open-World Object Detection

frp跨平台桌面客户端，可视化配置，轻松实现内网穿透！ 支持所有frp版本

对一段视频防抖，对实时视频防抖（usb相机、rtsp相机）

Comflowyspace is an intuitive, user-friendly, open-source AI tool for generating images and videos, democratizing access to AI technology.

ComfyUI-Yolain-Workflows 一份非常全面的 ComfyUI 工作流合集，由 @yolain 整理并开源分享，包含文生图、图生图、背景去除、重绘/扩图、换脸、透明图层生成、重绘光影、三视图、电商产品主图等多种工作流。并且按基础、进阶、实战应用进行了分类

Code release for paper EventCLIP: Adapting CLIP for Event-based Object Recognition

[ECCV2024] Official implementation of Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes

The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything