LoRA is generated entirely from anime images.
-----------------------------------
Check samples for prompts :)
Note: Even though her dataset was trained with 'purple skirt',
'red skirt' works much better. Very limited dataset with a few good shots.
Purple dress is a bit better but there were also just a few decent shots.
At least, it does recreate her face/hair somewhat decent.
So please keep that in mind.
Chara collection here: https://civitai-proxy.pages.dev/collections/76071
-----------------------------------
Leave a like, comment, review but first of all, ENJOY ;)
If you wish to support me in my work,
you can do that here: Ko-Fi.com/LittleJelly