This LoRA model is derived from 86 generated images using SDXl (RealVisXL V5.0), I have done testing with a few Schnell and Dev models.

It seems to produce fairly consistent faces. Using "black hair" seems to make the hair very black. I have had good results including "dark hair" in the prompts.

All the training images used had brunette/black hair but the LORA appears to be happy with other shades of hair as well. I have tested blue, green, rainbow and blonde.

The model aims to generate a consistent face with a tendency to high cheek bones. It usually generates dark hair, and most images minimize or have no "Flux Chin".

Any resemblance to real persons, living or dead, is purely coincidental and unintentional.