This is my first training attempt for the Anima Base model. I think I might add a bit more character tagging to the dataset, but in general I used the same (manually decensored) source material as for my other (PONY) LoRAs. This time around, I trained it locally.

Currently, it leans heavily towards women for obvious reasons. So I might need to tweak the training a bit for more variation.

Version 2 is completely re-tagged and uses new training params. Also character names should (mostly) work.