From Civitai: https://civitai.com/models/378336/mint-fantome-sdxl-2-outfits
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
Trained on AnimagineXL 3.1 (I will publish a LoRA for Pony at a later date)
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
