A test LoKr trained using my fork of diffusion-pipe (https://github.com/levzzz5154/diffusion-pipe/tree/feature/lycoris-loha-lokr) on 11 images for 100 epochs. Works in ComfyUI out of the box.
PS: not sure why this particular artist was excluded from Anima training. It may be just that the model didn't pick up on it for some reason.