Cosmos-Predict2

Cosmos-Predict2 is a key branch of the Cosmos World Foundation Models ecosystem for Physical AI, specializing in future state prediction through advanced world modeling. It offers two powerful capabilities: text-to-image generation for creating high-quality images from text descriptions, and video-to-world generation for producing visual simulations from video inputs.

Cosmos-Predict2 includes the following:

• Diffusion-based world foundation models for Text2Image and Video2World generation, where a user can generate a visual simulation based on text prompts or video prompts.