OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

SOTA Open Source TTS

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

Api tool for local offline text translation supporting multiple languages/支持多语言的本地离线文字翻译api

The open source platform for AI-native application development.

A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.

The HTML5 Creation Engine: Create beautiful digital content with the fastest, most flexible 2D WebGL renderer.

High performance Node.js image processing, the fastest module to resize JPEG, PNG, WebP, AVIF and TIFF images. Uses the libvips library.

High performance self-hosted photo and video management solution.

Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

每个人都能用的数字人

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，并添加配音

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

智能视频多语言AI配音/翻译工具 - Linly-Dubbing — “AI赋能，语言无界”

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

real time face swap and one-click video deepfake with only a single image (uncensored)

Download pictures (or videos) along with their captions and other metadata from Instagram.

Code for Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

基于Faster-whisper和modelscope一键生成双语字幕，双语字幕生成器,基于离线大模型,Generate bilingual subtitles with one click based on Faster-whisper and modelscope. Off-line large model

Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

🚀🚀🚀一款漂亮易用的在线设计器，支持PSD导入、PSD解析，可用于海报设计器、广告设计器、logo设计器、AI创作图片合成器等。常用于生成二维码海报，图片海报，二维码推广海报，图片处理，名片设计，电商产品图，节假日海报等。http://gzm-design.guozimi.cn/#/editor

基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快

A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley II, 2018.

[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Process audio/video data in the browser using WebCodecs. 基于 WebCodecs 在浏览器中处理音视频数据。

The HTML Presentation Framework

📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion