Sylveon LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Has a lot of trouble getting ribbon and bow placement right. Tail placement is also pretty unstable. I highly recommend using this LoRA at 0.8 or lower strength if your base model already has an understanding of Sylveon. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.