Ampharos LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Can have trouble with tail placement and adding her 'tail orb'. Has no idea what her feet look like, so your base model will fill in that detail. Can add too many stripes sometimes. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.
