The backgrounds are a dead giveaway for me most of the time. Granted, I’m a professional photographer and spend a lot of time looking at photos taken with various lenses, so have become pretty familiar with depth of field and all that jazz.
That, or the backgrounds have the weird discombobulated shapes and structures that only vaguely resemble real things, which I’ve also noticed in other AI generation tools.
Either way, it still fools me sometimes and it’s pretty remarkable how quickly this has all been happening.
As a photographer what started throwing me off was back focus issues in the synthetic images. I assume if anything the GAN would generate an image that was uniformly sharp, but I kept seeing images where the focus was just past the subject's eyes, more around the ears and hairline. Just like a real autofocus system might lock onto shirt fabric or something.
That, or the backgrounds have the weird discombobulated shapes and structures that only vaguely resemble real things, which I’ve also noticed in other AI generation tools.
Either way, it still fools me sometimes and it’s pretty remarkable how quickly this has all been happening.