Apps

Free Text-To-Speech generator with Emotion control (OpenAI)

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

AI-powered digital human video generation platform for TikTok marketing

TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.

Paste long text, clean it into readable sections, summarize each section, and ask questions in-browser with WebGPU.

Rust CLI for AI subtitle workflows: transcribe, segment, translate, evaluate, and burn or mux subtitles.

Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction

Private clean Hermes Agent v0.14.0 baseline backup

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

A variety of custom ComfyUI nodes and workflows

Audio-driven talking-head video generation (Meituan LongCat)

[CVPR 2026] EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing

A standalone, fully local image upscaler and denoiser — a "hi-res fix" tool that enlarges images and reinjects clean detail without altering the composition. No ComfyUI, no SwarmUI, no cloud. Everything runs on your own machine, which matters for sensitive client work.

Converts text to speech in realtime

Self-hosted AI workspace.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

MediaCMS is a modern, fully featured open source video and media CMS, written in Python/Django and React, featuring a REST API.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Official Pytorch Code of the Paper "FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization"

Agentic looper