- cross-posted to:
- [email protected]
- cross-posted to:
- [email protected]
cross-posted from: https://programming.dev/post/3974080
Hey everyone. I made a casual survey to see if people can tell the difference between human-made and AI generated art. Any responses would be appreciated, I’m curious to see how accurately people can tell the difference (especially those familiar with AI image generation)
You must log in or register to comment.
15/20 damn this was a lot harder than I expected. I’ve found that analyzing the pictures for small details that make no sense or lack context on why they are there helps greatly. But damn these things have better better fast
I got 9/20 lmao.
12/20, better than expected
10/20 and most of it was just guess work. It has become pretty much impossible to tell when you pick real images that are in the style of AI images, you really have to go pixel hunting to find artifacts and even that is getting difficult, when things get blurry or you get JPEG artifacts when you zoom in.
That said, there are still plenty of images AI has a very hard time creating. Anything involving real world products will always look wonky in AI, interesting framing where you don’t have one object in the center is hard. Unusual aspect ratio are hard, as AI is trained on squares. Complex scenes with multiple characters rarely work. Facial expressions are hard. And generally just normal everyday photos don’t really work, AI stuff always looks like people posing for a stock photo.
16/20. I would imagine I err’d on the side of assuming art was AI made rather than human made. AI generated photos are too ‘smooth’ looking.
14/20 isn’t bad I guess.
The AI overlords will kill you first. Your victory will be hollow and sour.
Good job!
:(
Got 10/20. The second photo really threw me for a loop. All the texture on the skin and and hair led me to believe human; I noticed the weird patch on the shoulder and the unnatural shine on the ear but excused it as technical flaws or something, chose human in the end. I really thought that corporate logo style drawing of the avocado was human, like it wasn’t even a question for me and yet the fact that it was AI really surprised me.
I also got 10/20. The second one is fairly obvious, though, in my opinion. Look at the shape of the glasses – the lenses are uneven and don’t match.
I filled everything out, then it said the connection timed out when I tried to submit. I can’t be bothered to do all the pixel peeping again.
I got 9/20, shoulda done better. 4-5 of those I was so sure I was right and still managed to get em wrong. The rest of the wrong uns were 50/50.
11/20 but many times I wasn’t sure, and most times I thought that this pic doesn’t belong into such a survey, because it is too simple.
The survey question is more meaningful when it’s about photorealistic images. Simple advertising graphics are meaningless either way.
12/20, I got all the photos and line art correct. The paintings and digital art were much harder to tell. Human artists aren’t perfect so the usual tells don’t really apply. I think I only nailed the line art because I’ve done a lot of line art myself.
Funny, with the line art, I struggled bit not the fotorealistc ones. For me the fotorealistic AI generations look like some smoothness filter was applied after taking the foto, or like heavily edited. With the landscapes and the first two cats I struggled as well, and the berserker fan art was like copy paste from the manga. Got 11/20.
Got 7/20, the second photo really did surprise me!
Ditto. Stared at that one for a while. The wrinkles around the eye even distort from the glasses.
No thanks. I get enough google just visiting random websites
Nice try robots! I’m not helping you learn how to fool us humans.
I’m happy with 12/20
At least I can say that I’m better than average
