1.
2.
3.
4.
5.
6.
- Fake
2 . Real 3. Fake 4. Real 5. Fake 6. Real
You are correct! 0 is also real.
AI, those trees have too many fingers…
They’re all AI because whatever phone took those pictures has AI upscaling
Nature shots have been cheating for a while, because most errors are still plausible.
The major tell is how screen-space anything is. In real life, there’s very few angles where the top of a close thing stops at the bottom of a far thing… but neural networks aren’t modeling depth. Probably. So things are tangent or coincident all the dang time. Even in the patterns of grass and brush and whatnot, where the network does T-junction patterns like brickwork or cracked pottery, when it should be closer to woven or thatched.
0, very good, but I feel the grass on the bottom left is off (see comment on 6, probably real) 1, the dead grass on the right looks off 2, the trees to the top left look shifty 3, the dead sedg/grass in the center looks too even 4, might be real 5, the dead grass again looks off 6, same location and time as 0, either the same seed or real
You gonna tell us the answer?
I am, but I was going to wait until at least the middle of the afternoon.
With the HDR effect added to these it’s honestly difficult to tell which are generations and which are just heavily post processed
In this instance these are straight out of the camera jpegs. I did zero post processing.
Lol I knew it. I was right.
1, 3, 5 are all fake. Rest are real, including 0.
0 has extra reflections of vertical trunks that aren’t on the shoreline
Those are just actual sticks sticking out of the water…