I noticed no one had done this, so I took it upon myself to make a model of his style. The onsite trainer is notoriously difficult to work with, especially with artists like Andava, so I had to work some magic to make it not hate the dataset.

Use with whatever MOSS Checkpoint you want. Use it however you want and do whatever you want. I don't care.

I strongly recommend this workflow since MOSS seems to work best in Comfy.
https://civarchive.com/models/3008600/moss-image-text-to-image-or-4-step-turbo-seedvr2-2x