Asanagi Style Lora. *could act in a funny overtrained way, kill its strength to maybe rein it in a little bit **impossible not to have a big chunk of the dataset be monochrome/black and white, so often it outputs that. Consider putting "monochrome, black and white" in the negative. Maybe even give it more strength like 1.2 or 1.3 https://civitai.com/models/908787/asanagi-style-il-or-ponyxl