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://skyfreedom.fanbox.cc

◆http://subscribestar.adult/Sky_FreeDom

Trained with 96 images

Image info

• Model used abyssorange2hard

• bad hands embedding

• bad artist embedding

• bad prompt embedding

• deep negative embedding

• Lollypop upscaler

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