I used nightcafe.studio, a VQGAN+CLIP webservice a bunch in March for the worldbuilding.ai entry I was working on. I found it.. okay for generating images that I could then edit in photoshop, but it took many many tries to get something decent. I’d be particularly interested in seeing what DALLE-E 2 does with these prompts:
“Beautiful giant sunset over the saltwater marsh with tiny abandoned buildings in the distance”
“Glass greenhouse with a beautiful forest inside, with people and drones flying”
“People dropping into a beautiful marsh from flying drones on a sunny day”
“Happy children hanging from flying drones on a sunny day beautiful storybook illustration”
“People falling from robotic flying drones into a beautiful marsh, on a sunny day, matte painting” I think some of the “people” are also robotic? DALL-E is trying though!
“People and drones flying around inside a giant glass greenhouse with a beautiful forest inside, 3D rendering”.
I swapped the order because when entered verbatim, the prompt you gave had DALL-E forgetting to include any people or drones. I find it’s more likely to actually include smaller or foreground features of a scene if I put them at the front and describe the larger backdrop after.
“3D rendering” is the best I got out of several style prompts (I tried “digital art” and “screenshots from a scifi blockbuster movie” as well.)
“Beautiful giant sunset over the saltwater marsh with tiny abandoned buildings in the distance, matte painting” (came out better IMO than the original prompt with no style guidance, which sort of forgot about the buildings.)
“Happy children hanging from flying quadcopter drones on a sunny day, beautiful storybook illustration”. Adding “quadcopter” made the drones much easier to recognize!
I used nightcafe.studio, a VQGAN+CLIP webservice a bunch in March for the worldbuilding.ai entry I was working on. I found it.. okay for generating images that I could then edit in photoshop, but it took many many tries to get something decent. I’d be particularly interested in seeing what DALLE-E 2 does with these prompts:
“Beautiful giant sunset over the saltwater marsh with tiny abandoned buildings in the distance” “Glass greenhouse with a beautiful forest inside, with people and drones flying” “People dropping into a beautiful marsh from flying drones on a sunny day” “Happy children hanging from flying drones on a sunny day beautiful storybook illustration”
“People falling from robotic flying drones into a beautiful marsh, on a sunny day, matte painting” I think some of the “people” are also robotic? DALL-E is trying though!
“People and drones flying around inside a giant glass greenhouse with a beautiful forest inside, 3D rendering”.
I swapped the order because when entered verbatim, the prompt you gave had DALL-E forgetting to include any people or drones. I find it’s more likely to actually include smaller or foreground features of a scene if I put them at the front and describe the larger backdrop after.
“3D rendering” is the best I got out of several style prompts (I tried “digital art” and “screenshots from a scifi blockbuster movie” as well.)
Oooooh, these are much better than the ones I was got from nightcafe (I just checked, I was actually using “CLIP guided diffusion”.)
DALL-E 2′s marshes and sunset marshes are slightly better than what I was getting.
“Beautiful giant sunset over the saltwater marsh with tiny abandoned buildings in the distance, matte painting” (came out better IMO than the original prompt with no style guidance, which sort of forgot about the buildings.)
“Happy children hanging from flying quadcopter drones on a sunny day, beautiful storybook illustration”. Adding “quadcopter” made the drones much easier to recognize!