Then text would be an image 10k pixels tall and N pixels wide, where N is the length of the text.

For each column, exactly 1 pixel is white (corresponding to the word which is there) and the rest are black.

Then the diffusion process is the same. Repeatedly denoising.

Denoising models work because a lot of regions turn out to be smooth, you cannot do that "in a discrete way" if that makes sense.

https://news.ycombinator.com/item?id=44059646