Also this came up kind of biased towards FF7 characters, so while this is mainly a style LoRA, it could replicate characters from the main cast of the game fairly well without embeddings or additional LoRA.
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.
https://civitai.com/models/7228?modelVersionId=8493
