photo taken in a white room of (a basketball and a soccer ball), a giant basketball BREAK photo taken in a white room of (a basketball and a soccer ball), a giant soccer ball
photo taken in a white room of (a basketball and a soccer ball), a giant basketball BREAK photo taken in a white room of (a basketball and a soccer ball), a giant soccer ball
edit: this was just to study region-specific prompting
strangely when the guidance is low (2), the result is closer to what was prompted
of course, every model had its own ideas about what a soccer ball may be. I started with "football" but that gave some american results
Lol @ the windows 10 logo style window
Interestingly for me guidance seems to have less of an affect than resolution. Idk if this is different in different versions of SD but only landscape images reliably makes both balls.
Square almost never does
and portrait also very rarely tho slightly more often than square
yes, landscape is more loyal to the prompt
👆same configuration with the posted image, except orientationthanks
How long will you survive?