Cosmos 3 Super

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 in

Capabilities

No supported capabilities recorded.

Details

Model IDnvidia/cosmos-3-super/text-to-image
Provider fal
Creator NVIDIA
Family—
License—
Statusactive
Typeimage
Input modalitiestext, image
Output modalitiesimage
Open weight—
Parameters—
Architecture—
Max resolution—
Resolutions—
Aspect ratios—
Batch size—
Release date
Sourceofficial

Endpoints

imagesPOST
https://fal.run/images

API

GET/v1/models/fal/nvidia/cosmos-3-super/text-to-image

Cosmos 3 Super

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 in

Changes · 4 entries
nvidia/cosmos-3-super/text-to-imagecreateca7a400Nov 2, 2026, 03:02 AM
nvidia/cosmos-3-super/text-to-imageupdatebf78dcfJul 25, 2026, 05:49 AM
last_seen_at2026-07-01→2026-07-22
nvidia/cosmos-3-super/text-to-imageupdate53ef452Jul 9, 2026, 02:32 AM
last_seen_at2026-06-02→2026-07-01
nvidia/cosmos-3-super/text-to-imagecreate80c574aJun 3, 2026, 07:05 AM