[CVPR 2026 Oral] VGGT Omega

Official implementation for SIFT-VTON

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.

🖥️ 📱 ▶️ Wrap your iPhone screen recordings in a beautiful device frame, add cinematic zoom moments, and export ready-to-share videos.

[TOG 2026] LiveLight: This repo is the official implementation of "LiveLight : Real-time video relighting via interactive control"

Reusable AI English picture-book workflow with consistent illustrations and local Chatterbox TTS.

An interactive demo of an iOS 26 style Liquid Glass effect for the web

SOTA-Class TTS at Compact Scale

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

The inference and trainging code for WordVoice.

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

XR Blocks is a lightweight WebXR + AI library for rapidly prototyping advanced AI + XR experiences.

👩🏿‍💻👨🏾‍💻👩🏼‍💻👨🏽‍💻👩🏻‍💻中国独立开发者项目列表 -- 分享大家都在做什么

A multi-instrument music transcription model developed by Kyutai and Mirelo.

Real-time face parsing and facial semantic segmentation with BiSeNet - PyTorch training, ONNX export, pretrained weights.

A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

Code release for "i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models"

Boogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.

AI powered speech denoising and enhancement

My running list of free design resources — fonts, icons, illustrations, mockups, UI kits, color tools, stock media, and more.

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

A modern video editor built with Tauri, React, and TypeScript. Focus on building free capabilities of premium capcut functionalities

Long Video Gen Infrastructure

Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation

[ICCV 2025] FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration

Magenta RealTime 2: An Open-Weights Live Music Model