Stars
Neural network 3D visualization framework, build interactive and intuitive model in browsers, support pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js
A project for processing neural networks and rendering to gain insights on the architecture and parameters of a model through a decluttered representation.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Real-Time High-Resolution Background Matting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Create and share 3D architectural projects.
[ICLR 2026] Official repository of "InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models".
[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…
StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and te…
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Polygon Clipping, Offsetting & Triangulation in C++, C# and Delphi
WASM port of Clipper 2 for Polygon Clipping and Offsetting
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
🎨 Local-first, open-source alternative to Anthropic's Claude Design. ⚡ 19 Skills · ✨ 71 brand-grade Design Systems 🖼 Generate web · desktop · mobile prototypes · slides · images · videos · HyperFra…
Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic
Electronic Circuit Simulator in the Browser
The Open edX LMS & Studio, powering education sites around the world!
Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars.
"3D-Avatar-React-Threejs" is a dynamic repository crafted for those eager to dive into the immersive world of My 3D avatar within the React framework, powered by the versatility of Three.js.