[ICML 2025 Oral] Mixture of Lookup Experts

A collection of easy-to-use image/video filter.

Converted CoreML Model Zoo.

Wan: Open and Advanced Large-Scale Video Generative Models

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

Offical Implementation of SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations

ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation

Weighs the soul of incoming HTTP requests to stop AI crawlers

MLX native implementations of state-of-the-art generative image models

General purpose 3D and 2D game engine using Go (golang) and Vulkan with built in editor

True P2P Email on top of Yggdrasil Network for Android

LiveLinkFace ARKit Receiver is a Blender add-on that receives facial tracking data sent from the Live Link Face app on iPhone and automatically applies it to Shape Keys in Blender.

CanoKey implementation on Nordic nRF52840 MCU

Track personal Bluetooth devices via Apple's "Find My" network using OpenHaystack and Macless-Haystack with tools written in Go/TinyGo. No Apple hardware required!

Cross-platform Bluetooth API for Go and TinyGo. Supports Linux, macOS, Windows, and bare metal using Nordic SoftDevice or HCI

Notepad + calculator

DeepSeek-OCR Inspired Optical Encoder for Qwen3-VLM

Unofficial Galaxy Buds Manager for Windows, macOS, Linux, and Android

Unofficial Galaxy Buds Manager for Windows, macOS, Linux, and Android

Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Su…

LL3M writes Python code that generates 3D assets in Blender.

DeepFuze is a state-of-the-art deep learning tool that seamlessly integrates with ComfyUI to revolutionize facial transformations, lipsyncing, Face Swapping, Lipsync Translation, video generation, …

Wan: Open and Advanced Large-Scale Video Generative Models

FlashAttention (Metal Port)

A simple web-based tool for Spriting and Pixel art.

Portable file server with accelerated resumable uploads, dedup, WebDAV, SFTP, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025