Lists (2)
Starred repositories
a local-first desktop pet powered by MiniCPM5
Claude Code 泄露源码 - 本地可运行版本，新增跨平台桌面端软件补齐Computer Use（附带核心模块解析）
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Voice activity detector (VAD) for the browser with a simple API
真正的死亡不是肉身的终结，而是被彻底遗忘。主动留下自己，让 AI 记住你，实现数字永生。| True death is not the end of the body — it's being completely forgotten. Leave yourself behind, let AI remember you.
LlamaIndex is the leading document agent and OCR platform
A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.
A Deep Learning based project for colorizing and restoring old images (and video!)
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
(AAAI 2025) Official PyTorch implementation of paper "SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection".
The official code for “Deep Unrestricted Document Image Rectification”, TMM, 2023.
[TPAMI 2025] MOWA: Multiple-in-One Image Warping Model
使用onnxruntime部署MOWA：多合一图像扭曲模型，能处理6种图像扭曲任务，依然是包含C++和Python两个版本的程序
The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.
在图像的采集和传输过程中，常常会产生各种形式的损坏，这些损坏会降低对图像信息的准确解释，同时也有一些老照片因保存不当而出现污渍或者划痕缺失的情况。本课题结合变分编码器（VAEs）、Vision Transformer与对抗生成网络（GAN）的深度学习算法和图像处理技术为基础，设计开发了一款图像修复深度学习算法小程序。这款程序为用户带来了基于 BS 结构的 Web 应用程序。用户操作时，只需轻…
python处理图片，包括图片平移、图片旋转、图片缩放、图片翻转、透视变换。选择图片中的四个关键点和将要变换的点，用来生成新的透视图
🔥 A library for cropping image in a smart way that can identify the border and correct the cropped image. 智能图片裁剪框架。自动识别边框，手动调节选区，使用透视变换裁剪并矫正选区；适用于身份证，名片，文档等照片的裁剪。
Vue3 + Pinia 仿抖音，Vue 在移动端的最佳实践 . Imitate TikTok ，Vue Best practices on Mobile
🥽🖼️ WebXR Voice Call UI, Make AI-Powered characters appear to you.
Added vLLM support to IndexTTS for faster inference.