The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Brand new TTS solution

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

State-of-the-art 2D and 3D Face Analysis Project

Code and dataset for photorealistic Codec Avatars driven from audio

PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA，你的个性化图像动画生成器，利用文本提示将图像变为奇妙的动画

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"

Code examples that accompany various MDN DOM and Web API documentation pages

Examples built with TensorFlow.js

Write full featured WGSL pipelines in plain javascript.

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

A mostly 1:1 re-implementation of webpmux as a Node module in pure Javascript. Only thing currently missing is a command-line version.

Whisper on the web - turbocharged by your GPU 🏎️

Robust Speech Recognition via Large-Scale Weak Supervision

A well-designed cross-platform ChatGPT UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT 应用。

为ChatGPT/GLM提供实用化交互界面，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm2等本地模型。兼容文心一言, moss, llama2, rwkv, claude2, 通义千问, 书生, 讯飞星火等。

Extension module for Windows Explorer to render SVG thumbnails, so that you can have an overview of your SVG files

JavaScript 3D library.

A lightweight 3D physics engine written in JavaScript.

Split {Japanese, English} text into sentences.