Verified: a year ago
SafeTensor
Type | |
Stats | 1,946 20,467 |
Reviews | (227) |
Published | Jun 28, 2023 |
Base Model | |
Training | Steps: 22,725 Epochs: 15 |
Trigger Words | left-eyepatch right-eyepatch decorated leather |
Hash | AutoV2 D2D3E1919C |
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.