Second try at the medieval drolleries LoRA.
This time the 300 images are processed for IL with Prodigy and a lot of epochs. Theoretically as a concept, but I still do not understand what differences there are between that and styles...
It is possibile the tags 'parody' and 'fine art parody' will get you some result, those were chosen by the automathic tagger.
For the rest, you have to softly alter the style. Do not blindly use embeddings, some tag could ruin the soup. These work quite well:
fine art parody, faded background, basic coloring, colored ink \(medium\), branches, inkblot, leaves, text, soft gradients, detailed, stylized anatomy, side view, antiqued, rough paper texture \(traditional media\)
For some negative, reduce 3d and complexity:
volumetric shadowing, 3d, render, complex background, photorealistic
Description
This is utilizable, from preliminary testing. Same instructions for the less cooked version, forms are less modern, less dynamic. The rumor can generate more characters (see second showcase example, the "sentinel"). If you manage to tame it, the final effect can very well be worth it.