This Lora was trained using 67 images from the official Blue Archive series, season 1 with 12 episodes.

No fan art or AI-generated images were used; I wanted to keep the art style as close to the original as possible.

I checked all the images, removing the worst or blurry ones, as well as other characters in the background to avoid training errors.

Based on my quick tests, a weight of 0.8 is ideal, but it may vary from one checkpoint to another, so feel free to try different weights.

I did not use trigger words in the Lora, it was trained with a tag database, however I advise you to use

mutsuki (blue archive),

Here is my test setup (note that this isn't necessarily the most optimized) :

I'm using the official Anima Base checkpoint version 1.0 : Link.