TLDR (Because I don't care)

Use Sabrina Young <lora:SabrinaYoung:1> in positiv promt.

If you like the LoRa, please feel free to share your generated images here and leave a review (or at least a rating) ;D

About

Well, this is my first LoRa that I have trained, her name is Sabrina Young, a ???? model known from MetArt... The main reason why I trained this LoRa is the fact that I wanted to see her in different costumes, because just being ????? is boring. ^^

Training

Not much to say, I followed the LoRa guide from theally (really nice tutorials btw ^^) and used 31 highres only images as training data...

Usage

No weight adjustments are needed, so basic prompting is quite easy:

Sabrina Young <lora:SabrinaYoung:1>

In addition, I have made the best images using the DPM++ 2M Karras sampler with a fairly high number of steps - around 50 steps is the sweet spot for me. Activating face fix depends on the situation, if the eyes are screwed up I always retry the same seed with face fix activated...

Disclaimer (Because some people are stupid af)

All people used in training pictures or shown in my sample pictures are over the age of 18. And yes it is stupid that I even have to mention it... 🤦