1.
2. 3. 4. 5. 6.

all 30 comments

sorted by: hot top controversial new old
[+] 18 points 2 years ago* (last edited 2 years ago)
[–] 7 points 2 years ago (1 child)

Assuming some are real and some are fake, my bet is 1 and 3 are fake.

  • source
  • hideshow 2 child comments
  • [–] 5 points 2 years ago

    AI, those trees have too many fingers..

  • source
  • [–] 4 points 2 years ago (1 child)

    You gonna tell us the answer?

  • source
  • hideshow 2 child comments
  • [–] 4 points 2 years ago*

    Are AI images I'm pretty sure, a lot of odd hashing of lines in some of those distant trees.

  • source
  • [–] 4 points 2 years ago (1 child)

    1, 3, 5 are all fake. Rest are real, including 0.

  • source
  • hideshow 2 child comments
  • [–] 4 points 2 years ago*

    1,3 and 5. They have that weird pattern in the grass and trees. However, it's getting close. I think soon most people would never be able to tell.

  • source
  • [–] 4 points 2 years ago* (1 child)
    1. Fake

    2 . Real 3. Fake 4. Real 5. Fake 6. Real

  • source
  • hideshow 2 child comments
  • [–] 4 points 2 years ago

    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.

  • source
  • [–] 4 points 2 years ago

    I agree with many others, 1, 3, 5 look most suspicious (assuming numbers precede pictures)

    Others seem to have heavy upscaling but it doesn't tend to become too patterned. In 1, 3, 5 grass tends to become something like a fractal rather than grass, plus reflections are sometimes off (that is why 2 is a bit suspicious because of a small tree reflection, but maybe it's just hard to see the original tree), and the branches tend to grow from multiple trees at the same time

  • source
  • [–] 2 points 2 years ago
    1. Is definitely AI

    About the rest I'm not sure. 3. and 5. look a bit suspicious

  • source
  • [–] 2 points 2 years ago* (last edited 2 years ago) (1 child)
    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
    
  • source
  • hideshow 2 child comments
  • [–] 2 points 2 years ago (1 child)
  • My guess is they're all real except #5. That one doesn't have as many good reflections off the water.

  • source
  • [–] 2 points 2 years ago

    Only 4 looks real to me. Rest AI

  • source
  • [–] 2 points 2 years ago

    I guess 5 and 6 are real

  • source
  • [–] 2 points 2 years ago (1 child)

    With the HDR effect added to these it's honestly difficult to tell which are generations and which are just heavily post processed

  • source
  • hideshow 2 child comments
  • [–] 2 points 2 years ago

    5 is the only one that looks real to me.

  • source
  • [–] 2 points 2 years ago

    The only one that looks like AI to me is 2

  • source
  • [–] 1 point 2 years ago*

    1, 3, 5, and 6. The grass is all funky on 1, 3, and 5. The tree and grass on the far left side of 6 is all smeared and stretchy.

  • source
  • I think its AI on 1,5, & 6

  • source