aaargh this image sucks. It 100% looks like AI slop but at the same time I can’t really find the definitive gotcha that reveals it as such. just smol inconsistencies you could explain away with human imperfections too, and the tingly spider sensation I get from the colors and the font.
I saw that one latch next to the belt buckle and thought “ya thats weird but could be human error” and then completely ignored it when zooming in on the image ugh. certified dumbass over here ._.
The giveaway for me is the color grading. It’s as if the entire image had a layer of brown or yellow layered over it- not as strong as the classic yellow one but it’s definitely there.
You are absolutely wrong. Just go look at the recent AI flyer trend. AI has and will always have tells (as long as we talk about the traditional DCGAN distill noise to image concept that’s the norm right now). You can minimize them with more effort, but a lot of people don’t even go thru that effort or know that AI image gen extends far past the “ChatGPT make me a image” paradigm.
I fee like this is AI slop, but i hope it isnt, because it looks cute.
Piss filter. It’s slop.
The indicator for me was the three ‘action lines’ or w/e they’re called near the finger guns.
Them shits are on Every. Single. Sloptastic event poster in my area.
aaargh this image sucks. It 100% looks like AI slop but at the same time I can’t really find the definitive gotcha that reveals it as such. just smol inconsistencies you could explain away with human imperfections too, and the tingly spider sensation I get from the colors and the font.
It’s the pants. Specifically, the belt buckle and the artifacting in her pants.
Sorry.
Well done, you earned a coupon:
Oh yea, thats a pretty obvious one i missed somehow
I saw that one latch next to the belt buckle and thought “ya thats weird but could be human error” and then completely ignored it when zooming in on the image ugh. certified dumbass over here ._.
The giveaway for me is the color grading. It’s as if the entire image had a layer of brown or yellow layered over it- not as strong as the classic yellow one but it’s definitely there.
Can’t you do that manually with an image editor?
yea it could definitely be a stylistic decision. tho one you shouldn’t make in the age of the pissfilter 2.0
When pissfilter 3.0! 2.0.succkkksss
Modern models don’t really have tells anymore. They either explode really obviously or good enough that they just look like a normal casual artist.
The small hints and tells just don’t really happen anymore. Doubly so if words are added by hand :/
You are absolutely wrong. Just go look at the recent AI flyer trend. AI has and will always have tells (as long as we talk about the traditional DCGAN distill noise to image concept that’s the norm right now). You can minimize them with more effort, but a lot of people don’t even go thru that effort or know that AI image gen extends far past the “ChatGPT make me a image” paradigm.
I think the glasses are a suitable indicator.
What’s wrong with them?
It comes back with a positive SynthID for Gemini, unfortunately.
Info about SynthID. It’s not like those AI detection tools that are no better than a coin toss.
SynthID calls about 7 out of 10 pictures I give it as ai incorrectly. The dumb ai trying to call out other ai solutions are never reliable.
:/ all the pictures I tried it on are over two decades old too.
That text “font” is classic ai slop
It definitely is
No artist signature, slop
I hope nobody seriously uses that as evidence.
I’ve seen stupider reasons lol
Oh, yeah, it’s not a clear tell but It’s defo a signifier.
AI has literally started forging signatures
What a bad person this AI seems to be. I think we’d jail it