A major update focused on film planning, character workflows, and reference control. - AI Director: Enter you...
Apps
Announcements
Television: Persistent workspace for AI agents
Television is a desktop for your AI agent. Instead of interacting with Codex, Claude Code, Hermes, or other a...
Rebrand to Slash Royale Legacy
Slash Royale has been renamed to Slash Royale Legacy, as I am working on a new version for the Slash Royale A...
A little while ago I posted about Orange , a frontend I built for turning ComfyUI workflows into simple tools...
(BETA) AI shouldn't have a meter. Unlimited tokens. Forever. Your machine. Your agent. Use it from anywhere. Terminal-native coding agent powered by local LLMs — 100% open source, free forever, and installed with a single command. Proudly built on C#/.NET, because AI tooling should be infrastructure, not a subscription.
facepokeFeatured
[NVIDIA Only] Select a portrait, click to move the head around https://github.com/jbilcke-hf/FacePoke
Allegro-txt2vidFeatured
[NVIDIA ONLY] Generate videos with Allegro txt2vid model https://github.com/rhymes-ai/Allegro
Contribute to PrismML-Eng/Bonsai-Image-Demo development by creating an account on GitHub.
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer, ICLR 2026
AVTR-1: Avatars that listen back
Hy-MT2 multilingual translation — Gradio UI for 33-language translation with Hy-MT2-1.8B and Hy-MT2-7B.
SA3 medium audio inpainter — MLX SAME-L decoder + FastAPI + vanilla Svelte UI
Open singing synthesis platform / Open source UTAU successor
The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Contribute to manat0912/Avatarify-Pinokio-app development by creating an account on GitHub.
A platform for reproducible world model research and evaluation
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
AI-Powered 3D Print Marketplace
Real-time face swap (Decart Lucy) + voice changer (Fish Audio) fused into one app.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
AI-powered tool that automatically sorts thousands of gymnastics competition photos into folders by team and individual gymnast. Uses YOLOv8, CLIP, InsightFace, ReID and FAISS – fully offline, CUDA-accelerated.
[CVPR'26] Official code for the paper "VGG-T³: Offline Feed-Forward 3D Reconstruction at Scale"