Anima version of this LoRA. This one has a slightly different dataset (because I lost the original one...) but based on my testing it has roughly the same effects.

Keep in mind the "improvements" are subjective (or more like self-indulgent) so whether it "works" for you will depend on your taste. I mainly made it for myself, but give it a try if you want.

Maybe I'll rewrite this description later...