A lora based on the style of an amazing artist sky freedom
If you like his stuff please consider supporting him!
◆http://fantia.jp/fanclubs/478213
◆http://subscribestar.adult/Sky_FreeDom
Trained with 96 images
Image info
Model used abyssorange2hard
Known Issues
Getting a clean white background is a bit of gacha
Has issues with generating dark skin people
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 parameters
Hide