#
Starred repositories
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
[CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
The python library for real-time communication
PoC to record audio from a Bluetooth device
A video translation and dubbing tool powered by LLMs, offering professional-grade translations and one-click full-process deployment. It can generate content optimized for platforms like YouTube，T…
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A private messenger for Android.
自动化上传视频到社交媒体：抖音、小红书、视频号、tiktok、youtube、bilibili
Release repo for our SLAM Handbook
LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & k…
SuiteCRM - Open source CRM for the world
This package contains the original 2012 AlexNet code.
⚡ 一款用于自动语音识别 (ASR)、翻译的高性能异步 API。不需要购买Whisper API，使用本地运行的Whisper模型进行推理，并支持多GPU并发，针对分布式部署进行设计。还内置了包括TikTok、抖音等社交媒体平台的爬虫，可实现来自多个社交平台的无缝媒体处理，为媒体内容数据自动化处理提供了强大且可扩展的解决方案。
高性能开源弹幕代理与转发器 | 支持抖音、哔哩哔哩、快手、斗鱼、虎牙等主流平台，统一弹幕数据格式，实时转发毫秒延迟，0% 消息丢失，超小体积！🔥 开发者的跨平台互动神器！
A Gradio app that transcribes YouTube videos using audio extraction and OpenAI’s Whisper model.
StoryMaker: Towards consistent characters in text-to-image generation