Attempting to teach AI underwater stuff. Combines Amanchu!, Rou (rou22) and saver (artbysaver) into single lora.

It is better at doing underwater stuff in general. Also it is better at using styles other than the styles used in the training.

I recommend prompting for any artist style. The default style of the lora is a bit odd.

It can still do all the trained styles too. Saver and Amanchu! styles are perhaps a bit better than their own idividual loras. Rou style still works but the results are a bit odd, especially colors.
But it did learn muoltiple styles in a single lora surprisingly well.

Training details: 942 images from Amanchu!, 634 images from Rou, 771 images from Saver.

Trained on Illustrious v0.1 for 5 epochs (5868 steps).