LoRa extract of 4th tail model.
3 sizes, the bigger – the more accurate.
Original model comes with over 300 artist styles, lots of anime characters (animal ears and tails -focused) and some other features.
After LoRa compression some artist are fine, some are damped but still works, others barely recognizable. Same for character knowledge and style mixing. See grids below.
But who cares if you only want to use a small part that satisfies you directly on your favourite model?
Works with original PonyDiffusion model (effect is reduced comparing to original checkpoint), works with merges/finetunes based on PonyDiffusion (influence is even less, but you may like it).
Prompting:
by ARTISTNAME
by is mandatory, then quality tags, your prompt with full character name like on boorus. Check out 4th tail description for more.