Is this AI generated?
Getting that feeling.
Yup.
How awesome / terrifying is it that this is a question which no longer has a clear answer?
I think it might just be old fashioned photo editing.
How does it look AI generated?
I’m legitimately asking
First of all, its way too clean. The picture has this really sharp look, and the blur looks artificial. The hind leg doesn’t seen normal for the way you see the rest of the dog. Also, the ring of the dog collar has no imperfections, and the dog looks way to still for it to be living.
Look closely at the crud around the eyes, and the matching reflections. No way this is AI. Blur looks entirely normal for a modern smartphone, focus on the eyes with the nose falling off slightly.
Right? Like I’m pretty sure it’s just a brand new collar and it’s sitting at a slight angle
For me, the dog has a cartoonish look. The eyes seem too large, the head seems too large, and something seems a little too perfect in general.
I think people just can’t believe that a dog can be that adorable.
It definitely looks it (for me the lighting and the eyes) but I don’t think it is. The bag in the bottom right might be puppy’s first food bag, and I don’t think I’ve seen many AI photos with just a partial thing like that that still obeys the laws of reality. If it’s AI, it’s heavily human involved to tweak things until it got perfect.
AI “art” is allowed here?
Not this good boi, but you reminded me of:
Do you have a flag?
Not for long!
Baby Scooby-doo
Omg that good boy is so hypnotic!
Ahh scrumpah
How does this look AI generated, to those who’ve made the comments. Honestly how?
I don’t think it is, honestly.
-
AI sucks at legible text in general. It can certainly do it, but very often the text very clearly does not belong there. You can usually tell it wasn’t written or printed there by anyone, it just does not fit very well. This image has very natural looking text in the lower right corner, on that bag thing.
-
AI sucks at consistent reflections in the eye. This dog has a pair of quite consistent reflections in its eyes. You can even see the phone that’s taking the photo in its right (our left) eye.
-
AI images are generated from noise. Some of that noise is leftover at the end of the process, especially when you’re rendering intricate stuff, like fur. That noise looks blurry, but it looks nothing like blur. I can’t see any of that in this image, it all the natural smartphone post-processing and compression feel, mixed with regular ol’ blur of being out of focus.
-
AI sucks at consistently aligning lines in the background when they’re interrupted by an object in the foreground. Like edges where the wall meets the floor, or edges where walls meet each other. Very often the AI does create a continuous wall behind the object, but the lines will be misaligned. None of that here.
-
AI is also not the best at drawing thin hair-like things that stick out against “open” background, like individual strands of hair or, in this case, whiskers. They often look wrong somehow.
Now none of those things is sufficient evidence by itself because AI can and will occasionally get those right, but together all at once, they make a convincing case that this image is altered at best, but probably not AI generated.
-
All these AI-related comments are giving me a McCarthyism vibe