Stars
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
Add virtual monitors to your windows 10/11 device! Works with VR, OBS, Sunshine, and/or any desktop sharing software.
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
A web-based Video Editing SDK built on WebCodecs. 基于 WebCodecs 构建的网页视频编辑 SDK。
Enjoy the magic of Diffusion models!
The complete stack for AI Engineers: framework, runtime and control plane.
Official implementation of "DCT-Net: Domain-Calibrated Translation for Portrait Stylization", SIGGRAPH 2022 (TOG); Multi-style cartoonization
[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation
Book_5_《统计至简》 | 鸢尾花书：从加减乘除到机器学习；上架！
Book_6_《数据有道》 | 鸢尾花书：从加减乘除到机器学习；欢迎大家批评指正！纠错多的同学会得到赠书感谢！
Book_7_《机器学习》 | 鸢尾花书：从加减乘除到机器学习；欢迎批评指正
Book_4_《矩阵力量》 | 鸢尾花书：从加减乘除到机器学习；上架！
Book_3_《数学要素》 | 鸢尾花书：从加减乘除到机器学习；上架；欢迎继续纠错，纠错多的同学还会有赠书！
Book_2_《可视之美》 | 鸢尾花书：从加减乘除到机器学习，欢迎批评指正
Book_1_《编程不难》 | 鸢尾花书：从加减乘除到机器学习；请多多批评指正！
Source code of a multiple series of tutorials about the hypervisor. Available at: https://rayanfam.com/tutorials
llama3 implementation one matrix multiplication at a time
Just draw a bounding box and you can remove the object you want to remove.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Background Remover lets you Remove Background from images and video using AI with a simple command line interface that is free and open source.
🪞 Instant AI Face Swap 一键 AI 换脸，发现更美的你
A high-throughput and memory-efficient inference and serving engine for LLMs
[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant
Generative Models by Stability AI