Uranus Embodied World Model

by hugging-appsco.huggingface.hugging-apps/uranus-embodied-world-model

  • Remote endpoint
  • 1 tool
  • APACHE-2.0

Tools

  • uranus_embodied_world_model_simulate Roll out the Uranus world model on a robot joint trajectory. Given a sample (zip with meta.json, temporal.json with per-frame MuJoCo qpos, the robot MJCF with calibrated cameras, and one reference image per camera), Uranus autoregressively generates synchronized multi-view RGB video that follows the joint trajectory, 4 frames per latent step. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: (generated multi-view video, comparison video GT/GEN/SKELETON/PLUCKER, used seed)

As the server's own listing gives them. We never call a tool.