AI open source project

Synthesis ER-NeRF (Efficient Region-Aware Neural Radiance Fields) is an open-source speaking character synthesis system presented at the ICCV 2023 conference. The project utilizes region-aware god ...

Comprehensive Introduction JoyGen is an innovative two-stage video generation framework for talking faces, focusing on solving the problem of audio-driven facial expression generation. Developed by a team from Jingdong Technology, the project uses advanced 3D reconstruction techniques and audio feature extraction methods to accurately capture the identity characteristics of the speaker and the expression...

综合介绍 OpenHands 是一个由 All-Hands-AI 团队开发的开源项目，旨在通过 AI 技术简化软件开发流程。该平台前身为 OpenDevin，现已更名为 OpenHands，提供了强大...

General Introduction SP-MangaEditer is an independent manga editing platform designed for manga creators. The platform supports image generation, layer editing, image adjustment, filter application and many other functions to help users easily create high-quality manga illustrations. Users can simply manipulate...

综合介绍 ScrapeGraphAI是一个创新的Python网页抓取库，它巧妙地结合了大语言模型(LLM)和直接图逻辑来创建网站和本地文档的抓取管道。这个工具的独特之处在于它的简单性和强大功能的完美平...

综合介绍 视频字幕去除工具（Video-subtitle-remover，简称VSR）是一款基于AI技术的视频处理软件，专门用于去除视频中的硬字幕和文本水印。该工具采用了多种AI算法模型（STTN、L...

Comprehensive Introduction TimesFM 2.0 - 500M PyTorch is a pre-trained time series base model developed by Google Research and designed for time series forecasting. The model is capable of handling up to 2048 time points up and down...

综合介绍 微信视频号下载器是一个开源项目，旨在帮助用户快速下载微信视频号中的视频内容。该工具支持多种视频格式和平台，用户可以方便地在Windows和macOS系统上使用。项目由ltaoo开发，并托管在...

综合介绍 NV Ingest（NVIDIA Ingest） 是一套早期访问的微服务，专为解析数十万复杂、混乱的非结构化 PDF 和其他企业文档而设计。它能够将这些文档转换为元数据和文本，以便嵌入到检索...

综合介绍 Always-On AI Assistant是一个创新的AI助手项目，它通过整合Deepseek-V3、RealtimeSTT和Typer等先进技术，打造了一个功能强大的永久在线AI助理系统...

General Introduction Ichigo is an open source real-time speech AI project that aims to extend text-based language models with native "listening" capabilities. The project uses early fusion techniques inspired by Meta's Chameleon paper.Ichigo's goal is to become...

Comprehensive Introduction STAR (Spatial-Temporal Augmentation with Text-to-Video Models) is an innovative video super-resolution framework jointly developed by Nanjing University, ByteDance and Southwest University...

General Introduction ImBD (Imitate Before Detect) is a pioneering machine-generated text detection project that was presented at the AAAI 2025 conference. With the widespread use of large language models (LLMs) such as ChatGPT, recognizing A...

综合介绍 Moondream 是一个开源的轻量级视觉语言模型，旨在通过深度学习和计算机视觉技术实现图像描述功能。该模型能够在各种平台上高效运行，特别适用于边缘设备。Moondream 采用先进的技术和...

Comprehensive Introduction The Text Extraction API (text-extract-api) is a powerful tool designed to extract and parse content from a variety of document formats (e.g. PDF, Word, PPTX, etc.). The API utilizes state-of-the-art Optical Character Recognition (OCR) technology and Ol...

综合介绍 BrownChat 是一个基于大型语言模型（LLM）技术的实时音频聊天应用。该项目由 GitHub 用户 sugarforever 开发，旨在通过先进的自然语言处理技术提升用户的沟通体验。B...

综合介绍 TANGO (Co-Speech Gesture Video Reenactment with Hierarchical Audio-Motion Embedding and Diffusi...

综合介绍 Ollama OCR是一个强大的光学字符识别(OCR)工具包，它利用Ollama平台提供的最先进视觉语言模型来从图像中提取文本。该项目既可作为Python包使用，也提供了用户友好的Strea...

Comprehensive Introduction FitDiT is a high-fidelity virtual fitting system based on diffusion transformers (Diffusion Transformers). Developed by Tencent AI Lab, the project aims to address the limitations of traditional virtual fitting systems in showing garment details.FitD...