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

A code-completion engine for Vim

Stable Diffusion with Core ML on Apple Silicon

Video editing with Python

A Blender script to procedurally generate 3D spaceships

Very efficient backup system based on the git packfile format, providing fast incremental saves and global deduplication (among and within files, including virtual machine images). Please post prob…

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

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

A simple CalDAV (calendar) and CardDAV (contact) server.

Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”

Download the entire Wayback Machine archive for a given URL.

Fully open data curation for reasoning models

MB-Lab is a character creation tool for Blender 4.0 and above, based off ManuelBastioniLAB

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

Text-to-Music Generation with Rectified Flow Transformers

AI for GNU Image Manipulation Program

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

Chromecast local files from Linux - supports MKV, subtitles, 5.1 sound and 4K!

Artificial Neural Engine Machine Learning Library

Create deployable system images from OS X installer

Command-line tools for speech and intent recognition on Linux

An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

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

VPTQ, A Flexible and Extreme low-bit quantization algorithm

Erlang node implemented in Python 3.5+ (Asyncio-based)

Putting the 'C' back in CouchDB

[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

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, …

zfec -- an efficient, portable erasure coding tool