SD can’t generate coherent images if you increase the output size. They’re basically always unusable unless you don’t need any global architecture to them.
I'm not sure what you mean. with the 1.4 checkpoint i can make a scene "a sky full of blimps" and then img2img that into a space battle where all the blimps in the sky are either fires or spacecraft afterburners. at 2k pixels, and then use the built in "GAN" stuff to bring it to 4k, 5k, or 8k.
It isn't perfect and it takes a lot of fiddling and sysadmin stuff, but it is way better than nextchar = CHR$(RAND64); color = (rand65535); of yore.
