This asset is only available as a PickleTensor which is an insecure format. We've taken precautions to ensure the safety of these files but please be aware that some may harbor malicious code.
Trained on 186 images of semi-realistic characters with highly detailed painted backgrounds. No specific characters or people in data-set. I recommend 0.7 strength.
All example images use AyoniMix V4 and V3 with hypernet strength at 0.7.