Download
1 variant available
insufficient tags surprisingly make for bad models - so a tagger setting error lead to a v2

2K0 1 2 3 4 5 6 7 8 9K
24K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9K
License:
CreativeML Open RAIL++-MThis LoRA tries to emulate Amami-K's artstyle.
The trigger is by Amami-K.
There's censored datasets, and then there's abominations like this, where everything south of the equator is a field of large, splotchy pixels - I'd recommend weighting negatives and doubling up, something like positive: uncensored, negative: censored, mosaic censoring - because otherwise it might not even work. Only then will you be able to enjoy (?) standard issue Pony-style vag00s and pen0rs in all their glory.
You may also want to heavily negative stuff like artist name, website url, watermark, signature or something if that bothers you.


