The model I think is fairly self explanatory.

So, odd thing with this one, I guess with anima, training with images that use a transparent background might be an issue, suggested to generate at a strength of .7, and to ensure that you're prompting in a background scene, like how I did with the previews of being at the beach, otherwise you'll get this sort of strange wooden looking blocky outline around the characters. Never seen that issue before.

https://vocaroo.com/1dCKgpymuk1M

Back to my devilish tricks.

Works well at a strength of 1

Previews made with Anima Base Model 1.0