A lora for creating implied fellatio scenes
Trained on 212 images
Notes
use keywords such as kneeling/squatting/sitting to adjust the girls position
the size of the image effects the pose ALOT e.g squatting positions look much better at a square resolution(640x640) rather than vertical (512x768)
This lora works with other loras very well so feel free to experiment
Made a slight mistake by not pruning the extra implied fellatio tag(woops)
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