This ADetailer model helps to annotate eyes on images to inpaint them automatically. Model was trained using yolov8s model.

Usage:

1. Copy into your "models/adetailer" folder and extract

2. Activate adetailer extension and select model by it's name

I suggest to use it with 0.3 threshold and mask only the top k largest 2 and mask merge mode - merge, but usually detections outputs are with confidences 0.7 and more.