Vis's repositories
StreamDiffusion
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
whisper-turbo
Whisper on the web - turbocharged by your GPU 🏎️
audio2photoreal
Code and dataset for photorealistic Codec Avatars driven from audio
cannon.js
A lightweight 3D physics engine written in JavaScript.
ChatGPT-Next-Web
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。
dom-examples
Code examples that accompany various MDN DOM and Web API documentation pages
EdgeSAM
Official PyTorch implementation of "EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM"
gpt_academic
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。
insightface
State-of-the-art 2D and 3D Face Analysis Project
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
llm-awq
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
New-Bing-Anywhere
New-Bing-Anywhere extension's source
node-webpmux
A mostly 1:1 re-implementation of webpmux as a Node module in pure Javascript. Only thing currently missing is a command-line version.
PIA
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
sentence-splitter
Split {Japanese, English} text into sentences.
svg-explorer-extension
Extension module for Windows Explorer to render SVG thumbnails, so that you can have an overview of your SVG files
TensorFlowTTS
:stuck_out_tongue_closed_eyes: 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)
tfjs-examples
Examples built with TensorFlow.js
webgpujs
Write full featured WGSL pipelines in plain javascript.
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
zero123
Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)