[Note: All position are "of the screen".]
What is truly amazing is the soft body and clothes deformation are fairly accurate as well as the fluids.
That means the AI internalize all the physics and material properties.
No, what it truly amazing is how easily AI enthusiastic can miss so many things when they looks at an image.
Take the time to really look at the second image, and come again tell that the soft body and clothes deformation are fairly accurate.
In no world the boobs fat can fold up on itself ; especially on a so large distance since it cover entirely the bra. And what amazing asymmetrical bra ; the right part is plain and large, the left one is small with a big all in the middle.
On the same image, also note how the hand of the guy on the right pop out of the girl's arm. Hand that have a forefinger smaller than the thumb, while the other hand enter inside the boobs.
As for the left guy, it have a really long arm, what is relatively understandable since it's partly not attached to his body ; as you can see below the left boob.
On the third image, the hand on the right clearly have a double pinky. This while the left boobs also partly fold up ; or she have two boobs of radically different size, coupled with a really large and fat left armpit zone. There's also the hand on the right, that is clearly the one of the girl, and also clearly masculine.
And what about the background ? The guy we see the face have no right (his one) arm. The wall is slightly tilted to the right, while the window (?) is largely tilted to the left. And the leg you see on the bottom left, the one with the big red tumor, is attached to no body ; but it have a hand, directly attached to it.
And on the last image, the girl hand have dislocated fingers.
As for the first image, the girl have to left (hers) feet. The one we see on the right, and one that slightly appear between her tights.
Not to mention the lighting as if it got that wrong you would have immediately noticed.
But everything is shaded and in shadow as it should based on the light source with enough ambient light for things not to be too dark.
You know, it don't suffice that there's shades for the lighting to be correct. The shades also need to be consistent with the light(s) source(s).
The first picture have a shadow coming from nowhere on the vertical on the top left corner (the second one) ; the roof need to have a big hole in it for this shadow to exist. And the frontal highlight spots on front of the girl imply a top (a bit on the right) front light that cast no other shadow than for the left boob. This while the head shadow is telling that there's a light above (and on front of) the girl ; light that should then cast boob shadow on the right arm.
On the second one, the light is expected to be on the top right, but the girl cast no shadow on the left guy. Said left guy that have a shadow cast by his head, accordingly to a light that would be on his left ; light that cast no other shadow than this one.
On the third, the shadow on the upper part of the girl come from the middle left, while the ones under her boobs come from the top left. And the leg with no body attached is also lighted from the top left, but clearly by another light.
As for the last girl, the lighting is relatively consistent, being lighted from the middle right. Except for her boobs, that are clearly lighted from the front.
This is what AI Skeptics do not understand and cannot comprehend, AI do not just merely mimic art, they have already internalize the "Rules" and Anatomy that make up the Technical Skill of Drawing.
Well, if it's the case, then they have the same understanding of those rules than a preschooler.
Not that the images are inherently bad, but they aren't good for the reasons you said. Because the reasons you said clearly do not apply
