This project provide the Ultimate Modular Menu System for Unreal Engine 5 using Common UI where everything is easy to reuse/build on. For the options menu, there is everything you need from basic s…

Public releases and CI for the Vita3K Android app

A fixed width (web)font in a cool liquid-crystal display (LCD) style.

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

Xiaomi Home Integration for Home Assistant

Tool for manage Unreal Engine Plugins (.uplugins) set to Enabled By Default .

Cycles material converter project for Blender Octane.

CPP Implementation of "ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation"

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | 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

faster_whisper GUI with PySide6

🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手 - 视频字幕生成、断句、校正、字幕翻译全流程处理！- A powered tool for easy and efficient video subtitling.

LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & k…

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Wrapper for X-Portrait for running in ComfyUI

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation

A procedural textures authoring and 3D model painting tool based on the Godot game engine

package google mediapipe hand and holistic tracking into a dynamic link library

A feature-rich command-line audio/video downloader

Create face depth frames from images using landmarks

XQUIC Library released by Alibaba is a cross-platform implementation of QUIC and HTTP/3 protocol.

A port of tencent/DepthCrafter into ComfyUI

[arXiv'24] [Image-to-Scene on a 4090(24G)] VistaDream: Sampling multiview consistent images for single-view scene reconstruction

Cross-platform, customizable ML solutions for live and streaming media.

WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild

Completely Rebuild of official Houdini Engine from Zero, 2x - 15x Faster I/O, and More functionalities optimized for making procedural landscape and city toolset

Publish some small parts in my personal daily-used Houdini accessories

An unofficial Zerotier Android client patched from official client