Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs.
nvidia/cosmos-3-super/image-to-video
Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs.
Inference
Commercial use
Loading examples
Prompt examples
Examples are generated using the Cosmos 3 Super Image to Video. You can customize them by clicking on the "Playground" button.