Radar

Browser-based motion graphics editor for short-form video. Timeline clips, live preview, and MP4 export on the host (OpenGL when available).

Iris-3B: pixel-space generation & general vision learner. A 3B diffusion transformer that generates every pixel directly (no VAE); the same prior, fine-tuned, does monocular depth estimation and 4x image restoration. Paper, weights, training code and demo.

🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.

🗣️ PersonaPlex - NVIDIA's real-time speech-to-speech conversational AI model. Natural full-duplex conversations with customizable personas and voices.

[NVIDIA ONLY] Autocomplete any voice(s), powered by Hertz AI (Standard Intelligence)

Uncensored Image-to-Video generation system using CogVideoX, Hunyuan Video, and Stable Video Diffusion

Desktop app to generate 3D models from images or prompt using local AI — runs entirely on your GPU

Uncensored AI generative desktop app by Hope Theory. T2I, I2I, Inpaint, T2V, I2V with ComfyUI primary. Local-first, zero censorship.

All-in-one AI music studio by GANTASMO. Stable Audio 3 and Magenta RealTime 2 generation, Chimera multi-track fusion, Demucs stems, MIDI and notation, DJ and VJ rigs, DAW project import, VST3 and .gan plugins, and a RAG-backed in-app assistant.

Diffusion Engine for Musical Orchestrated Noise — a real-time streaming diffusion engine for music generation, built on ACE-Step v1.5. Requires an NVIDIA GPU.

Discover amazing ML apps made by the community

Turn document pixels into structured, grounded content with LightOnOCR-3

[NVIDIA ONLY] Advanced Web UI for CogVideo (text to video, image to video, video to video, extend video, etc) -- Generate videos with less than 10GB VRAM

Self-hosted Whisper API for Open WebUI

Video Dubbing with Open Source Projects

Locally colorize black-and-white public domain movies and historical photos with DDColor. Optional AI vision guidance for historically accurate palettes. Runs on CPU, Intel Graphics, Apple Silicon, or NVIDIA CUDA.

Customizing Realistic Human Photos via Stacked ID Embedding https://huggingface.co/spaces/TencentARC/PhotoMaker-V2

Local-first Suno-style music studio powered by ACE-Step 1.5.

A live 3D intelligence console for planet Earth.

A powerful, AI-powered Gradio application for downloading, transcribing, and analyzing YouTube videos and audio.