This extension contains a custom node for ComfyUI. The node, called 'Bounding Box Crop', is designed to compute the top-left coordinates of a cropped bounding box based on input coordinates and dimensions of the final cropped image. It does so computing the center of the cropping area and then computing where the top-left coordinates would be.
This repository contains a Python implementation for extracting and visualizing human pose keypoints using OpenPose models.
The OpenPoseNode
class allows users to input images and obtain the keypoints and limbs drawn on the images with adjustable transparency.
Additionally, it can provide an image with only the keypoints drawn on a black background, and the keypoints value in a JSON format.
You can find the example workflow here
ComfyUI/models/openpose
Ensure you have the following packages installed:
torch
cv2
(OpenCV)numpy
huggingface_hub
torchvision
you can install them with
pip install -r requirement.txt
or
python install.py
Special thanks to beingjoey/pytorch_openpose_body_25 for the inspiration. Their work provided a foundation and motivation for developing this custom node.
We welcome contributions! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request.
This project is licensed under the GPL-3.0 License. See the LICENSE file for details.
Thank you for using the OpenPose node for ComfyUI. We hope it enhances your image processing workflows!