A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

State-of-the-art 2D and 3D Face Analysis Project学习文档

A Python Perceptual Image Hashing Module

Lightweight HTML5 Speedtest

OpenVLA: An open-source vision-language-action model for robotic manipulation.

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

MobileSAM already integrated into Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

Connection to the Motoman Ethernet Server, available on some Yaskawa Motoman Controllers. Tested on DX200 and YRC1000.

支持rockchip mpp硬件加速编解码的ffmpeg版本。Forked ffmpeg that supports rkmpp decodeing, encoding and rga scaling

⭐ Linux / Windows / macOS 跨平台 V2Ray 客户端 | 支持 SSR / Trojan / Trojan-Go / NaiveProxy | 使用 C++ / Qt5 开发 | 可拓展插件式设计 ⭐

[验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.

A platform for building proxies to bypass network restrictions.