Difficult to do it in a way that is physically consistent with a camera lens/sensor.
I don’t see any of the expected issues with AI (garbled text, impossible geometry, strange anatomy, etc) in this picture. Of course it’s quite possible to just edit a portion of an existing picture with AI, and it will match the rest. So I may have been overstating the difficulty.
Difficult to do it in a way that is physically consistent with a camera lens/sensor.
That’s really not true at all. Lots of photo software has precise metrics on a multitude of actual camera lenses specifically to compensate (remove) for the inherent optical properties of said lenses. Using those same metrics to mimic the optical properties of those lenses, rather that remove them, is also fairly common. The optical properties of the sensors are obviously also well known, otherwise digital photography simply wouldn’t work. This photo may or may not be AI, but the existence of blurring neither proves nor excludes either possibility.
Difficult to do it in a way that is physically consistent with a camera lens/sensor.
I don’t see any of the expected issues with AI (garbled text, impossible geometry, strange anatomy, etc) in this picture. Of course it’s quite possible to just edit a portion of an existing picture with AI, and it will match the rest. So I may have been overstating the difficulty.
That’s really not true at all. Lots of photo software has precise metrics on a multitude of actual camera lenses specifically to compensate (remove) for the inherent optical properties of said lenses. Using those same metrics to mimic the optical properties of those lenses, rather that remove them, is also fairly common. The optical properties of the sensors are obviously also well known, otherwise digital photography simply wouldn’t work. This photo may or may not be AI, but the existence of blurring neither proves nor excludes either possibility.