Wanted

[ICCV 2025] From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Use OCR in Windows quickly and easily with Text Grab. With optional background process and notifications.

A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.

[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

Generate responsive pages and apps on HTML, Tailwind, Flutter and SwiftUI.

#1 PDF Application on GitHub that lets you edit PDFs on any device anywhere

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

Foundational Models for State-of-the-Art Speech and Text Translation

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

Automatically generate, translate, and overlay subtitles for any video.

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Caller ID Spoofing Ultimate Edition

CallerID spoofing script using PHPAGI

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

🦜🔗 The platform for reliable agents.

Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles.

Code for a proof of concept for OMR (Optical Mark Recognition) using opensource tools