This is kind of experimental. I wanted to see if I could finetune an anime model to replicate the style of a game in Unreal Engine. I think this was kind of a success. It works on AbyssOrangeMixV2 with a normal negative prompt, or on AnyLoRA with my usual negative prompt with negative embeddings (but don't mix them up, as that neg prompt doesn't work well on AOM with this LoRA). See the examples for the various comparisons.