Hacker News new | ask | show | jobs
by gus_massa 1427 days ago
Did you use the same prompt for all the images? How much cherrypicking did you do? How many images did you generate to get this set?
2 comments
emadehsan 1427 days ago
Most inputs were a combination from these:

"Painting/Digital Art/3D Render] of [Animals/Foxes/Monkeys] playing Chess in [Jungle/Dune/Desert]"

Some inputs were specific: "Capaybara vs Groundhog Chess match" or "Llama vs Panda/Red Panda in chess match"

I almost used all the credits OpenAI gave me for DALL-E. This set consists of about 50-60% of all the images I generated.

link
Plutoberth 1426 days ago
Not OP, but I generated over 150 images using DALL-E 2. Results in the quality of the images in the gallery are very common. Usually, for prompts as simple as this most of the output images (there are 4) look as good or better.
link