This is a completely reworked Lora using 2000+ images with a variety of sploshing themes and subjects.

The data set has been designed with an emphasis on Oatmeal, gunge and custard as well as pies, chocolate, beans and spaghetti amongst other subtances. The low learning rate and high number of steps gives the model a high degree of flexibility and realism. The Lora works well with a number of other Loras and would recommend playing around depending upon the realism you want.

I'm still not fully happy with the final form and will be updating in due course

My sample images have the prompts embedded, Please share any interesting images, it'd be great to see what can be done with this.

Total training time was just under 14 days end to end on an A6000. Training does not come cheap so any contribution of Buzz will help to support continuing development