Trained based off of the work of Kyouda Suzuka, Images taken from safebooru. Trained on anything v4.5
Example images were made with hypernetwork strength on 0.9 on anything v4.5 with clip skip on 2.
Note that the further the subject is from the viewer the thinner the outline is
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.