This was arguably a failed experiment.

So since that one other (various) artists LoRA seemed to work, arguably, I thought I'd try a real full fledged anthology manga, out of curiosity if a larger non-uniform dataset comprised with several styles could produce something interesting or work at all in a cohesive unified way. At a strength of 1, I couldn't see this LoRA producing anything different than the checkpoint would at it's own, and at a strength of 2, it -feels- a bit different than the checkpoint but it's kind of an uncanny valley feeling where it may just be hopeful imagination that this one does anything at all, even at a strength of 2. I likely won't try this sort of thing again as I don't think it's going to work in the future, and I would argue this LoRA was a failure. However I'll post it to the site as sort of a reference for anyone curious of such an experiment and the results of my attempt to further the understanding of creative ways to create LoRAs.

May do something at +2 strength, questionable if it does anything at all.

List of artists and the Manga for reference can be found at https://nhentai.net/g/464065/

Previews made with novaFurryXL_illustriousV20.