plug.directory
Add my server

ViTPose Transformers

by hystsco.huggingface.hysts/vitpose-transformers

  • Remote endpoint
  • 2 tools
  • ViTPose_transformers_detect_pose_image Detects persons and estimates their poses in a single image. 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: tuple[PIL.Image.Image, list[dict]]:, - Annotated image with bounding boxes and pose keypoints drawn., - List of dictionaries containing human-readable pose estimation results for each detected person.
  • ViTPose_transformers_detect_pose_video Detects persons and estimates their poses for each frame in a video, saving the annotated video. 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: str: Path to the output video file with annotated bounding boxes and pose keypoints.

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