I would like to add one thing. If your dataset consists of images in 256x256 or 512x512 format only, when you try to generate an image higher than this resolution, there are tiling issues. I ran into this with my first trained model.

So, with my second model, I kept higher resolution files as they are, did not resize them. And the tiling issues disappeared.

On a side note, I tried generating images in rectangular proportions, all working well. No tiling issues. So, I think it is best to train with the highest image sizes we can afford to train with, in square formats....