detailedprojectv1 - anime images trained with detailed backgrounds, a little undertrained, needs strong negatives
detailedprojectv3 - v3 of the above, needs less negatives, a bit overtrained but excellent for merging
leaguev1 - trained on all official league of legends splash art images, no character tags
leaguev2 - minimum character tagging. no spaces, no '
pjsekaiv2 - trained on project sekai bloomed/trained images, weaker style, no character tags
pjsekaiv4 - no character tags, better trained
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.