Trained on Animagine XL V3.1, 12 images.
I'm bringing the SD LoRAs to the SDXL. I think you can notice she generates a bit different compared to the SDXL version, don't know why. You can compare it with the old version, I'd say it's not a biggie.
I forgot if its her or Miyabi or both. Hands can generate poorly, but clothing can be a real pain. Let's just say the AI likes to generate her with cleavage or revealing clothing. Either try "()" to raise weight, or play around with wording if it bother you too much. Also, I spent like 30 tries to get her to pose with another character, but I don't know how to prompt it or what LoRAs to use, sad.
I only used Animagine XV V3.1 to generate the images.
I use Euler A. 34 steps. If you use PixAI or other currency sites, I recommend you go cheap first and then use more steps and stuff when you're sure you'll get the result you want.
8CFG
LoRAs I used in generation:
https://pixai.art/model/1725049259066326012 https://pixai.art/model/1668692278399247652 https://pixai.art/model/1826818504164548813
Thumbnail model: Animagine XV V3.1
