Another newbie question. It’s clear to me that the generator has trouble with the details of placing 3 or 4 people in a single image. Can someone give me an example or two of prompts that would generate multiple people in a scene without most of them being garbage?
You must log in or # to comment.
Hmm … 2 people are not that problematic, but 3-4? You might have success if you skim over each person each person … there’s only so much pixels, and eventually, even this Flux model has its issues keeping them separate. Same as if you describe two characters very detailed with different colors.
Hi
You have probably figured this out already, but if you haven’t then you can try this. Please understand that this is how I make my prompts and they seem to work halfway decently. I also use an external note pad program, namely “word pad, Rich Text Document” to wright all of my prompts in first. I do this namely because you can not use the enter key to move to the next line of dialect. Spacing is very important when creating your prompts.
Try using the words, “Two People. or Three People. or Four People.”. These have to be the first words you wright if you are adding multiple people. Then double space, and then start describing the first person, start with what there body looks like, " when I say body I mean the whole body from head to toe" then there clothing, add coma’s, apostrophes, quotes, and spaces, but do not use a period until you have finished the first person. You will end up with a long continues sentence, describing the first person. Also make sure the spacing between words is done right, two spaces between two words is enough to derail your description.
Here is a “VERY” simple example.
The extra spacing between descriptions makes a big difference, I us double row spacing.