Skip to main content
Generate visual observations from robot movements or your existing simulator. Explore a learned manipulation environment with Cosmos3 Nano Sim Bimanual, or turn simulator depth into realistic-looking video with Cosmos3 Nano Sim Transfer.

What do you want to build?

Interactive simulation

Cosmos3 Nano Sim BimanualMove robot arms and operate grippers while a learned scene responds with generated video.

Visual transfer

Cosmos3 Nano Sim TransferTurn depth from your physics simulator into camera-like RGB for viewing or policy evaluation.

Choose a model

Text supplies context for generation; it does not command robot movements. In Bimanual, your arm poses and gripper values drive the motion. In Transfer, your simulator drives the motion and supplies the resulting depth frames; the description guides their rendered appearance. The Transfer initialization and advance inputs above describe its incremental simulator workflow. For a recorded trajectory, upload the complete control video and provide an appearance description instead.

Use rendered observations in a policy loop

Your policy chooses an action, your simulator executes it, and Cosmos3 Nano Sim Transfer renders the resulting depth as RGB for the policy’s next observation. Your simulator keeps control of physics and task scoring. Connect Transfer to a simulator for the step-by-step integration and feedback timing. For recorded trajectories, you can also generate appearance variants to explore different lighting and materials.

Looking for robot actions?

These models generate observations. To predict actions from camera images and robot state, start with policy inference.