This is a full finetune using 600+ images with a variety of themes and subjects.

The data set has been designed with an emphasis on Oatmeal, gunge and custard. The low learning rate and high number of steps gives the model a high degree of flexibility and realism.

I have uploaded the FP8 version of the model initially and will be following with a LORA next.

The Model plays very well with other Loras. As always, you will need to tweak the guidance and steps to find a good balance depending on the Lora.

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 8 days end to end on an A6000. Training does not come cheap so any contribution of Buzz will help to support continuing development