This is a lora trained to create a more simplistic and flat anime than the base models. The goal was to take away a bit of the realism and make the characters appear more like old cartoons and comics. My goal with this is to be able to use these to animate movement easier as the simple shapes and colors make it less likely to get confused during animation.
Its cute, its simple, its trained on about 135 images of simple anime style. It does lose a bit of prompt adherence but it works really well for quick character generations.
Description
anime not required for most images, but certain topics and backgrounds will still override with a realistic style, add anime if that happens and run it again to get the full effect.