Running on T4 Agents Featured 54 PROMETHEUS v1.0 β World Model Interactive Demo π₯ 54 World-first embodied AI world model
Running on Zero Agents Featured 1.2k Omni Video Factory π 1.2k text to video, image to video, video extend
nvidia/multitalker-parakeet-streaming-0.6b-v1 Automatic Speech Recognition β’ Updated Jan 28 β’ 474 β’ 109
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 Any-to-Any β’ 33B β’ Updated about 1 month ago β’ 519k β’ 337
Running on Zero Agents Featured 45 Marlin 2B Video Understanding π¬ 45 Dense video captions and timestamp search
Running Featured 271 Bonsai Image WebGPU π³ 271 State-of-the-art image generation, in your browser.
Running on Zero Agents Featured 47 Cosmos3-Nano π 47 NVIDIA Cosmos3-Nano β text/image to video + audio
Running on Zero Agents Featured 47 RF-DETR Realtime Webcam Demo π― 47 Segment objects in live webcam and uploaded media
Running on CPU Upgrade Agents Featured 38 Command A Plus 05 2026 π 38 Chat with an AI using text and images
Running on Zero Agents Featured 108 Lance π¬ 108 Generate, edit, and understand images and videos with Lance!
Running on Zero Agents Featured 230 LongCat-Video-Avatar 1.5 π€ 230 Audio-driven talking-head video generation (Meituan LongCat)
Running on Zero Agents Featured 55 VGGT-Omega Demo π 55 3D reconstruction from images/video with VGGT-Omega