nvidia/cosmos-3-super/text-to-image
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. You can customize them by clicking on the "Playground" button.
950s-inspired tourism poster for Milford Sound. Lush, painterly depiction of mirrored waters and towering Mitre Peak. 'MILFORD SOUND: Eighth Wonder of the World' in cheerful, mid-century typeface. Retro cruise ship in foreground. 'Experience Nature's Majesty' at bottom. Misty greens and blues with sunset orange sky.
num_inference_steps50
guidance_scale2.5
seed5555
image_size1024x768
950s-inspired tourism poster for Milford Sound. Lush, painterly depiction of mirrored waters and towering Mitre Peak. 'MILFORD SOUND: Eighth Wonder of the World' in cheerful, mid-century typeface. Retro cruise ship in foreground. 'Experience Nature's Majesty' at bottom. Misty greens and blues with sunset orange sky.
num_inference_steps28
guidance_scale2.5
seed5555
image_size1024x1024
A herd of wild horses galloping across a windswept plain under dramatic clouds, manes and dust flying, kinetic power in the style of painter Rosa Bonheur, golden backlight
num_inference_steps50
guidance_scale4
image_size1024x768
A dutch-angle street-style fashion group shot with bold 70s vibes color and dynamic energy in the style of Mert and Marcus, mat flower themed editorial
num_inference_steps28
guidance_scale4
image_size1024x1024