I would highly recommended using both of trigger words, u usually will get better results.
Also, couple of recommendations:
Use lawlassYiffymix20 for results as showed on the page
recommended clip skip 2
set around 0.9 scale (I was using exactly 0.9)
the model trained on 512x512 images
If you dont get good results, write an feedback with your generations. I'll try to fix this.
Description
More epochs
More images ai to eat
release v2
FAQ
Comments (9)
Just a warning, nsfw images of young characters is not allowed on this site, so I would recommend deleting those images before this gets deleted
alright got it
Downloading. Looks decent! gonna grab that checkpoint too. Sad I need a different checkpoint to make it work, but I get why.
Will you make more Sonic loras? I sure hope so!
yeah, I will make some more of them, thanks for support!
NSFW possible?
yeah, just make sure your prompt is ok to avoid weird results
I love that you made this. However I'm getting quite a bit of mutation even after quite a bit of experimentation. Heres hoping a V2 comes out at some point.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.