Inteleon LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. Works quite well, main issue was YiffyMix trying to add a nose. Adding (noseless) to the positive and (nose) to the negative helped with that. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on a mixed male/female dataset.