H3-World

by hugging-appsco.huggingface.hugging-apps/h3-world-action-demo

  • Remote endpoint
  • 6 tools

Tools

  • h3_world_action_demo__fit_keyframe_ui ``image.upload`` handler: snap the canvas to the frame, then crop the frame to the canvas. 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
  • h3_world_action_demo__lambda_
  • h3_world_action_demo_generate Roll a world forward from one frame under a keyboard action script. 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: The generated video (with MiniMax-H3's native soundtrack) and a markdown report holding the, per-frame action timeline.
  • h3_world_action_demo_preview Render the per-latent-frame sentences an action script expands to, without generating.
  • h3_world_action_demo_preview_1 Render the per-latent-frame sentences an action script expands to, without generating.
  • h3_world_action_demo_preview_2 Render the per-latent-frame sentences an action script expands to, without generating.

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