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
Prompt examples
Examples are generated using the Cosmos 3 Super Image to Video. You can customize them by clicking on the "Playground" button.
lone astronaut in a detailed white spacesuit standing on the gray cratered lunar surface, vivid blue and white Earth rising in the pitch-black starry sky, cinematic lighting, photorealistic, sharp reflections on the visor
num_inference_steps28
guidance_scale6
image_size832x480