Vulpix LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Can add too many tails, can add too few tails, can add none at all. Tails are very inconsistent, but good results are possible. Hair can turn into tails sometimes. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.