Trained on a limited Dataset on Anima 1.0 Base Model. Using <a target="_blank" rel="ugc" href="https://civarchive.com/articles/28641/anima-lora-trainer-app">Anima Lora Trainer App.</a> I'm very happy with it.It has a trigger word, but it's not required for everything, but it does help force the style. If the style is too much, leave out the trigger word. I usually leave it out.Weight of 0.9 with the trigger word seems the be good to get closer to the actual style, if that interests you.It does lean towards adding muscles, but they are easy to prompt out. It doesn't produce the blue background of the game, although I did train background images. I don't personally mind it. There might be a way to prompt for the blue, but I haven't cared to find it.

Files with SHA256: 8c912fcc7533b1b0c813d8c5af4cce5b30806b3c0915d25102d7e42d87a03b24