Verified: 2 years ago
SafeTensor
Type | |
Stats | 379 |
Reviews | (28) |
Published | Apr 13, 2023 |
Base Model | |
Trigger Words | irina |
Hash | AutoV2 07C8F7FDE1 |
LORA for Irina Shayk trained on 1.5 base model.
This is my first attempt at making a LORA. I didn't think it would work but from my testing it seems to have turned out fine so I am uploading here.
Open to feedback and constructive criticism.
Big thanks to Hollowstrawberry for their guide on making LORAs.
Disclaimers -
I am not a fan of this person. I just randomly chose a celebrity and used their publicly available images.
I didn't know what I was doing so I chose some photos with camera flash and that seems to sometimes make the skin overexposed so watch out for that.
If you are using generation data from the sample images replace the LORA name with the new one as I have used an older test name in there.