Back to models

Cosmos 3 Super Image to Video

VideoImage to video
nvidia/cosmos-3-super/image-to-videoView on fal.ai

Parameters

Dictation ready.

Text prompt describing the motion and scene of the video to generate.

Dictation ready.

Content to steer the generation away from (artifacts, unwanted motion). Defaults to NVIDIA's recommended i2v negative prompt; pass an empty string to disable.

URL of the conditioning first-frame image for the video.

Result

Run the model to see the result here.