This lora was trained on 50-70 images from the artist 陽子 (@hrn_yc). A special shout out to flyx3 for making me aware of this artist. They also made a lora with this artist using Animagine XL V3 as the base, if you like this artstyle I recommend you give that one a try as well.
V3 is trained on Noob 1.0 V-Pred.
V2 is trained on Zootlustrious V2.
V1 is trained on Pony.
To get the results you see in the images above, these are the settings I used.