Makes girls similar in style to the official character presentations.

How to use
Just prompt away. While this LoRA is trained for a general style you can prompt individual characters by using their tags. For reference the characters on the site and included in the dataset are Aura, Edel, Ehre, Fern, Flamme, Frieren, Kanne, Laufen, Lawine, Linie, Methode, Sense, Serie and Ubel.
Please see the uploaded zip with their respective tags if you want to prompt someone specifically.

The character presentations consist of a front and side full body shot as well as a couple of face close-ups of which I picked a profile and front imaged effectively training four images per character.

Upper/face outputs tend to be favored unless you prompt otherwise using pose tags or anything worn on the lower part of the body.
The quality tags of PonyXL are rather strong and leaning towards western style so depending on what you prompt you may have to try different ones, different LoRA strength and/or samplers.

I have no plans at the moment to train on the males since I just wanted to make cute girls memes and fake official female characters.

Misc
Trained on Pony SDXL at 1024 resolution with a dataset of 56 images.
All images are untouched txt2img, no inpainting or helper embeddings used for quality transparence, e.g. - things should look even better if you do.
The training was done on a small subset of images, as such the output of this LoRA is not an accurate representation neither in quality or style of the source material. Consider buying the official merchandise if you want the good stuff.