A lora for creating invincible dragons sailor dragon outfit
Created through the help of rerorerorero amazing guide
Trained with 34 images
Image info
Model used based64
use (faceless,identity censor) in the negatives if your getting grey boxes for faces
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
Description
-changed trigger word to avoid creating dragons
-reduced the small style change it caused
FAQ
Comments (2)
v1 works much better with realistic models
It would be great if you put changes between versions (e.g: v2 has 1000 more trained images to tune up anime models). I noticed v2 is better but for anime only. v1 works better in realistic models.