Image loading, customizable loading path, including subdirectories
- Please rename the file extra_help_file.yaml.example to extra_help_file.yaml and remove the annotation # . Add a custom loading directory such as images_dir: D:\AIGC\ComfyUI-Data\images_input, Linux is /.
Automatic video watermarking;
Automatic image watermarking;
Image face alignment (frontal);
Face detection and cropping, with optional alignment, adjustable crop area size, and angle;
One-click generation of various passport photos;
Photo enhancement, including brightness, saturation, sharpening, and skin smoothing.

Examples:

📣 Updates

[2025-04-28]⚒️: Image loading, customizable loading path, including subdirectories.

[2025-04-24]⚒️: Add automatic video watermarking.

[2025-04-14]⚒️: Add automatic image watermarking.

[2025-04-11] ⚒️: Released version v1.0.0.

Installation

cd ComfyUI/custom_nodes
git clone https://github.com/billwuhao/ComfyUI_PortraitTools.git
cd ComfyUI_PortraitTools
pip install -r requirements.txt

# python_embeded
./python_embeded/python.exe -m pip install -r requirements.txt

Model Download

If you are using the ComfyUI-ReActor and ComfyUI-RMBG nodes, you do not need to download the models, as they are shared.

Otherwise, download detection_Resnet50_Final.pth and place it in the ComfyUI\models\facedetection folder. The models for ComfyUI-RMBG will be automatically downloaded to the ComfyUI\models\RMBG folder.

Acknowledgements

Thank you @1038lab for their excellent work. The RMBG code used in this GitHub repository is sourced from ComfyUI RMBG. And follow the same GPL-3.0 license

Thanks to the following projects: