Stay updated with the latest and most popular GitHub repositories. We fetch data from the official GitHub API, analyze it in-house, and update our listings every hour to bring you the freshest trends.
本项目是基于dify开源项目实现的dsl工作流脚本合集
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
🚀「Douyin_TikTok_Download_API」是一个开箱即用的高性能异步抖音、快手、TikTok、Bilibili数据爬取工具,支持API调用,在线批量解析及下载。
An encyclopedia of jailbreaking techniques to make AI models safer.
Industry leading face manipulation platform
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
The modern API client that lives in your terminal.
A JavaScript / TypeScript / Python / C# / PHP / Go cryptocurrency trading API with support for more than 100 bitcoin/altcoin exchanges
GUI for a Vocal Remover that uses Deep Neural Networks.
Download your Spotify playlists and songs along with album art and metadata (from YouTube if a match is found).
Translate the video from one language to another and add dubbing. 将视频从一种语言翻译为另一种语言,同时支持语音识别转录、语音合成、字幕翻译。
Easily download and manage game cheats for your convenience
⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。
Multilingual Voice Understanding Model
YOLOE: Real-Time Seeing Anything
带带弟弟 通用验证码识别OCR pypi版
Enjoy the magic of Diffusion models!
Tenacious tool calling built on LangGraph
你还在为自己存放的VV表情包不够多,使用时觉得不够贴切而感到烦恼吗?快来试试这个项目吧!
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
Open Source framework for voice and multimodal conversational AI
My learning notes/codes for ML SYS.
python版本的小智ai,主要帮助那些没有硬件却想体验小智功能的人
Aether: Geometric-Aware Unified World Modeling
Retrieval and Retrieval-augmented LLMs
ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.
TEN Agent is a conversational voice AI agent powered by TEN, integrating Deepseek, Gemini, OpenAI, RTC, and hardware like ESP32. It enables realtime AI capabilities like seeing, hearing, and speaking, and is fully compatible with platforms like Dify and Coze.
A framework for few-shot evaluation of language models.
The LLM Evaluation Framework
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS
An interactive TLS-capable intercepting HTTP proxy for penetration testers and software developers.
A Library for Advanced Deep Time Series Models.
Real time interactive streaming digital human
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Official Implementation of Video-T1: Test-Time Scaling for Video Generation
Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"
deferred computational framework for multi-engine pipelines
可循环值守和多人录制的直播录制软件,支持抖音、TikTok、Youtube、快手、虎牙、斗鱼、B站、小红书、pandatv、sooplive、flextv、popkontv、twitcasting、winktv、百度、微博、酷狗、17Live、Twitch、Acfun、CHZZK、shopee等40+平台直播录制
Rembg is a tool to remove images background
Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.5 Pro - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Streaming & Non-Streaming Support. ✨ Experience the Future of AI – Today! Click to Try Now! ✨
Cross-platform, fast, feature-rich, GPU based terminal
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
AIInfra(AI 基础设施)指AI系统从底层芯片等硬件,到上层软件栈支持AI大模型训练和推理。
Di♪♪Rhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion