Charizard LoRA trained on NovelAI with Kohya training scripts using the DAdaptAdam optimizer at 512x512 resolution. May require adding 'Membraneous Wings' to your prompt to get consistent wings. Tail placement can be unstable, alongside the placement of the tail flame. Should have wide compatibility with model mixes based on NovelAI, which is most of them. Trained on an all female dataset.