Lora for Shuzen Kokoa from the Rosario + Vampire anime.
Trained on anime screencaps using Illustrious-XL v0.1. No fanart or other official art was included in the dataset. Her hair tends to be more orange in the anime so that's how it turned out.
Basic prompt for canon outfit: shuzen_kokoa, 1girl, solo, serafuku, hair bow, green eyes, plaid skirt, thighhighs
Very few other tags were used like loafers for her shoes and pink panties. Check metadata of the Lora.
My examples use DOMKU01 (version: v1 ) checkpoint and unaestheticXL | Negative TI(version: _cbp62) negative embedding that can both be found on CivitAI: DOMKU01 & unaestheticXL. They were generated using basic Auto1111 so you should be able to use the prompts after verifying that the lora and negative embedding names match what you have saved locally.
Use low CFG (3+) for softer image with less saturated colors.
Use high CFG for more saturated colors & more emphasis on prompt.
Example using CFG of 3:
Same example using CFG of 6.5:
People tend to like more saturated colors (despite my personal tastes) so examples use high CFG.