The rest of your answer makes sense but this rhetorical question is not helpful IMO. There are lots of things that humans are not good at but at which computers excel.
That’s mostly true, but not fully. Models use human drawn images and photos to learn from. So if you put in millions of drawn images and the hands aren’t perfect in all of them, you might mess up the model too. That’s why negative prompts like “malformed”, “bad quality”, “misformed hands” and so on are popular when playing with image generation.
How? Humans are not good at finding the square root of numbers but computers are much better at it. Human limitations are not relevant in cases like this.
The rest of your answer makes sense but this rhetorical question is not helpful IMO. There are lots of things that humans are not good at but at which computers excel.
That’s mostly true, but not fully. Models use human drawn images and photos to learn from. So if you put in millions of drawn images and the hands aren’t perfect in all of them, you might mess up the model too. That’s why negative prompts like “malformed”, “bad quality”, “misformed hands” and so on are popular when playing with image generation.
Wait. I thought he was perfect with that analogy.
How? Humans are not good at finding the square root of numbers but computers are much better at it. Human limitations are not relevant in cases like this.
We’re not talking about square roots of numbers though, we’re talking about drawing hands.
This happens to be one of the cases that humans and AI both struggle with, because drawing hands is complicated for both entities.
Yes but you can train ML models on photographs of hands to bypass that limitation?
Of course. Just like you can train humans to bypass their limitations.
The problem is training. There’s nothing intrinsic to AI art that prevents it from making perfect hands. It just takes time, and a lot of data.
Is there a dearth of any of these?