Update: I've uploaded a Pony LoRA. It's fidelity is a bit better than the Animagine one, because there was quite a bit more fan artwork since her redebut. I'll update the Animagine version at a later date.

Trained on her early sailor collar outfit (sailor) and her later frilly outfit (frilly). Use these prompts in Auto1111 (I've already escaped the brackets for you):

Sailor: mint fantome \(sailor\)

Frilly: mint fantome \(frilly\)

The tokens above alone should be enough. To help with correctness, you can still add additional tags:

General: white hair, gradient hair, blue eyes

Sailor: corset, paw pose, ghost hair ornament, hair ribbon, black ribbon, blue ribbon, ahoge

Frilly: frilly, maid headdress, sleeves past fingers, cross hair ornament, two side up

Additional notes:

• Sometimes produces ghosts unprompted

• The bridal garter'ed legs in the frilly outfit barely work, there's not a lot of artwork with her legs in it that I could find

• I reduced dimensions after training (at dim/alpha=8/4) dynamically with sv_fro and a target of 0.9. It has on average the size of a 4/2 LoRA after resizing.

• I've used around double the usual LR. What should be an overfit LoRA seems to perform surprisingly well