阿里云盘命令行客户端，支持JavaScript插件，支持同步备份功能。

一款轻量级、高性能、功能强大的内网穿透代理服务器。支持tcp、udp、socks5、http等几乎所有流量转发，可用来访问内网网站、本地支付接口调试、ssh访问、远程桌面，内网dns解析、内网socks5代理等等……，并带有功能强大的web管理端。a lightweight, high-performance, powerful intranet penetration proxy serv…

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Nightly release of ControlNet 1.1

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Stable Diffusion web UI

(SFW Friendly) Fast and Simple Face Swap Extension for StableDiffusion WebUI (A1111, SD.Next, Cagliostro)

one-click face swap

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

SOTA Open Source TTS

Python interface to the WebRTC Voice Activity Detector

集成Webrtc的VAD，用于切分音频文件

Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

llm-export can export llm model to onnx.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

An ImageSearch demo running on SG2300X

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

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

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

Machine learning compiler based on MLIR for Sophgo TPU.

适用于sophon bm1684x，基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答

Run generative AI models in sophgo BM1684X

A Clash GUI based on tauri. Supports Windows, macOS and Linux.