Stars
Helper toolkit for creating your own Lean 4 UserWidgets
Ai safety research showing a working bypass to Google's synthid on Nano Banana Pro
PastScreen-CN 是一款专注于效率的 macOS 截图工具,截图即刻进入剪贴板,几乎无等待。 它支持全局热键自定义、右键取消、原生截图音效和全中文界面,轻量、快速、不打扰。
将视频瞬间转化为手绘故事 Turn Video Moments into Hand-Drawn Stories
Multi-agent autonomous startup system for Claude Code
[ArXiv 25] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
这是一个面向创作者的 AI 电影生成系统。 你只需输入一个剧本,系统即可自动完成剧本拆解、分镜生成、画面与音频素材生成、视频合成与时间轴编排,并支持一键分发到媒体。 从灵感到成片,不再需要复杂流程,让个人也能创作电影级作品。
JJYB_AI 智剪 - 智能视频自动剪辑与AI解说工具(离线TTS、原创解说、混剪、AI配音)
WordFormatter 是一款用于 自动整理 Word 文档标题编号与段落格式的桌面轻量级工具。它能帮助用户一键格式化word文档,方便生成目录、规范论文或课程报告的排版。
official implement of "Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation"
A high-performance web-based DWG/DXF viewer without requiring any backend server
Train Large Language Models on MLX.
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
WeChatAuto.SDK 是一款面向 AI 的微信 PC 客户端自动化 SDK,基于 .NET 与 UI 自动化技术开发。它支持消息收发、转发、群聊与好友管理、朋友圈操作等多种功能,并专为集成人工智能(如 LLM 上下文交互)场景设计
This project enables stable processing of ultra-high-resolution images on consumer-grade GPUs through intelligent tiling and seamless merging techniques.该项目通过智能分块与无缝合并技术,在消费级显卡上稳定处理超高分辨率图像。
📦Portable package for running Hunyuan3D 2.0/2.1 on Windows. | 混元 3D 2.0/2.1 整合包
Awesome curated collection of images and prompts generated by z-image-turbo state-of-the-art open-source image generation and editing model.
Check if an email address exists without sending any email, written in Rust. Comes with a ⚙️ HTTP backend.
App for Claude Code / Codex / Gemini, vibe coding anytime, anywhere
Official code of Motus: A Unified Latent Action World Model