A lora based on the best the smug rival from Pokémon sword and shields DLC

Klara

Trained with 175 images

Outfit's

• use klara for general clothing

• use klaragym to get her in game look

Image info

• Model used kotomix

• Model used abyssorange2hard

• bad hands embedding

• bad artist embedding

• bad prompt embedding

• deep negative embedding

Known Issues

• getting her alternate thigh-highs is a bit of gacha

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