Sunna from Zenless Zone Zero
This lora is far from perfect, it struggles with the hairclips, and getting the correct earings.
You might want to caption the clothing roughly to guide the model towards the base outfit or the "afternoon tea break".
There is some light style bleeding, as this wasn't trained with a reg dataset.
I will do a v2 with a better dataset at a later point.
Description
Trained in OneTrainer with:
Adamw, 1024px, bs 4, beta .9 .96 , orthograd, atan2 scaling, cautious variant, rank 16, alpha 1
FAQ
Comments (2)
very quick short review.
There is a tendency to create a white box on the outside of the picture with a probability of about 3-40%.
It's okay to use outside border on the negative.
A lot of images in the dataset unfortunately have white background. I might train those with mask when I do an update.