This is the first version of my WAM/Sploshing Lora.

The Lora has been training on 400 WAM/Sploshing images that I've curated from my collection. The image set contains a mixture of Gunge, Custard and Oatmeal scenes with the subjects wearing a variety of outfits, costumes in various poses and locations to give a varied data set.

The Lora works best with natural language prompts. There are are no trigger words needed for the lora. Simply specify the subject location, pose and substance is enough. Try to describe how the substance specifically interacts with the subject for the best results.

I have noticed that Flux is very good learning concepts and whilst I have trained with these 3 substances you may also have success with other substances like mud too.

As far as settings go, The lora works well for strengths 0.5 to 1 but I prefer to weight the lora between 0.5 and 0.7.

I find it helps to give random names, especially if you want multiple people.

I've been sampling with guidance 3.0-5, simple euler schedule with 40 steps.

The usual samplers should work well Euler Simple/Beta and Deis/ddim_uniform are my go to samplers. I usually run 30 steps, but 20-40 is fine too.

It is trained with the full precision t5/clip conditioning. I have tested FP16 and FP8; both give excellent results obviously depending on the seed used.

Feedback welcome.