nvidia

cosmos-predict1-5b

PREVIEW

Generates future frames of a physics-aware world state based on simply an image or short video prompt for physical AI development.

AI models generate responses and outputs based on complex algorithms and machine learning techniques, and those responses or outputs may be inaccurate, harmful, biased or indecent. By testing this model, you assume the risk of any harm caused by any response or output of the model. Please do not upload any confidential information or personal data unless expressly permitted. Your use is logged for security purposes.
Input
World Creation Mode
Video-to-World
Generate future frames based on a video input.
Image-to-World
Generate future frames based on an image input.
Input Video
View Examples
Prompt (Read Only)
Output
Generated Future World