sai88uk/openpose-skeleton-detector-v2

Generate pose skeleton detection with face and hand keypoints from any photo using ControlNet OpenPose. Returns a colorful skeleton visualization on black background with body keypoints (25 points), face keypoints (70 points), and hand keypoints (21 point

Public
440 runs
License
GitHub
Weights
Playground API Examples README Versions

Examples

View more

Run time and cost

This model costs approximately $0.0015 to run on Replicate, or 666 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 7 seconds.

Readme

OpenPose Skeleton Detector Generate precise pose skeletons with face and hand keypoints from any photo using ControlNet OpenPose. Features 🦴 Full body pose detection (25 keypoints) 😊 Facial keypoints (70 facial landmarks) 👋 Hand keypoints (21 points per hand) 🎨 Colorful skeleton visualization on black background ⚡ Fast GPU processing (2-5 seconds)

Use Cases Animation reference and motion capture Pose analysis and body tracking ControlNet conditioning for AI image generation Character design and illustration reference Input image: Photo containing a person (PNG, JPG, WebP) include_face: Enable facial keypoints (default: true) include_hands: Enable hand keypoints (default: true) Output High-quality pose skeleton with connected joints, facial landmarks, and hand keypoints rendered as a colorful visualization on black background.

Model created