>>33128
I'm doubtful it will ever be perfect.
There's of course AI art commonly screwing up hands and feet, but other than that it seems to have difficulty with varied poses and angles. A lot of AI art you can clearly see it filling details with things that don't make any sense like pieces of clothing that should fall apart if they actually existed, objects merging into other objects, lighting/shading being off, or random things added that give the appearance of complexity akin to greebles.
A lot of people seem to make the mistake of ascribing AI ability and anthropomorphism (such as that guy who claimed Google was sentient or the various people who think the same of ChatGPT) it doesn't actually have. Ultimately the sort of AI art programs and chatbots we have now aren't much different than other algorithms in use for more than a decade. All it's doing is processing data with no internal understanding of what it's trained with or what it produces which shows if paying attention.
The "good" AI art actually has a human doing the editing afterwards to fix the random bits.
Humans have always been really bad at predicting technological and scientific progress. Going by predictions in both fiction and by actual engineers and scientists made decades ago or more we should have already had flying cars, sapient robots, interplanetary or interstellar travel, automation sufficient to make the majority of work unnecessary, etcetera. The AI algorithims we have now are no different.