📷 Create beautiful images of your source code

Virtual Machine for the Web

Let your Claude able to think

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Training-free Regional Prompting for Diffusion Transformers 🔥

ML-powered speech recognition directly in your browser

Various AI scripts. Mostly Stable Diffusion stuff.

Official repository of In-Context LoRA for Diffusion Transformers

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

A very compact representation of a placeholder for an image.

🖼️ A library to show colorful blurry placeholders while your content loads.

📸 A powerful, high-performance React Native Camera library.

🔥 High-performance TensorFlow Lite library for React Native with GPU acceleration

Slint is a declarative GUI toolkit to build native user interfaces for Rust, C++, or JavaScript apps.

ComfyUI nodes to edit videos using Genmo Mochi

InstantIR: Blind Image Restoration with Instant Generative Reference 🔥

TestDisk & PhotoRec

Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

JavaScript version of GPAC's MP4Box tool

WebAV is an SDK built on WebCodecs, designed for creating and editing video files on the web platform. WebAV 是基于 WebCodecs 构建的 SDK，用于在 Web 平台上创建/编辑视频文件。

The best OSS video generation models

Our main browser engine repository.

A lightweight React component that harnesses the power of CSS animations to create silky smooth marquees.

Examples for using ONNX Runtime for machine learning inferencing.

Select a portrait, click to move the head around (please use your own space / GPU!)

Segment Anything 2, 100% in the browser (with WebGPU!)

Export Segment Anything Models to ONNX

Python scripts for the Segment Anythin 2 (SAM2) model in ONNX