This Lora was trained using the Doujin as base, I didn't use any image from the animation, so the "original style" prompt will imitate the doujin.

Note:

• For some reason, all the images I used for dataset were of her blushing, so she will always come out looking a little red in the face, unless you use “blush” in the negative prompt.

My ko-fi page if you want a commission or support me with a little bit:

https://ko-fi.com/kenderbell

It helps me to keep bringing you Loras almost daily c: