This LORA was mostly trained on photos, so it should work best with a photorealistic model. I attempted to split eyepatches on the left and right eyes into two separate concepts, but this doesn't seem to have held up. Nevertheless, the trigger words are 'left-eyepatch' and 'right-eyepatch', left and right being from the viewer's point of view rather than the subject's.
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights.