A LoRa that aims to emulate Fukudahda's artstyle.
A bit of an emphasis on aims here, because I've been experimenting with training parameters and I'm not entirely convinced by the results. Try fiddling with the weight or adjust your negative prompt if it looks too generic.
Trigger is by by Fukudahda.
The source material is a bit censored, so prompt/negative prompt with that in mind.
experimenting with network alpha and batches, second iteration of this
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.