A lora based on the protaganist of soul hackers 2
Trained with 20 images
Image info
Model used kotomix
Model used abyssorange2hard
Known Issues
getting her sidelocks to come out correctly is a bit of gacha(due to the small dataset) using the prompt sidelocks helps increasing intensity helps with backview
Training settings?
The most important part of training is getting a good dataset!
Training settings can be found by installing the additional networks extension in auto1111
Extensions -> available -> load from -> additional networks
Restart webui
place lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora
To view the training settings
Go to additional network tab -> choose model -> training paramters