Rapidash LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Works pretty well, add (flaming hair) to your prompt for the proper flaming hair effect. Can have issues with the tail in rear views, adding (flaming tail) improves consistency. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.