Halfway down, next to the caption "Smooth even all white background", is this image: https://codyznash.github.io/white_paintings/images/SDXL_2.pn... Doesn't that count?

I was hoping to create a white monochrome image from an idea, not just 'a white background'. The first couple sections were just to see if the AI could do it at all. The image you're pointing to is also a gradient, less monochrome than most of the human works shown at the top.

Close, that's more gray with a tint.

I thought of this article: https://www.crosslabs.org/blog/diffusion-with-offset-noise I don't know how much this applies to SDXL, but you might need a LORA to get very bright or very dark images. Gray could be a much easier targer.

That's an interesting article. I wonder if SDXL was trained with this in mind while earlier versions maybe weren't?