to see that AIs have as many problems as they do with drawing hands.
Arguably, AI struggles with hands because the creators of the training data struggled with hands.
AI sucks at hands precisely because humans suck at hands.
It’s also because generative AI relies on statistics so an approximation of the number of fingers is used. In that sense 4 and 6 are close enough to 5.
A third reason is that not all fingers are always visible in pictures and drawings, depending on the angle and position. If you try right now to make a ‘c’ with your hand, you could only see three fingers. This is relevant as while artists know that hands have five fingers, generative models do not ‘know’ what a hand or a finger are.
Not to mention animators have traditionally gone with 3 fingers and a thumb, making the AI have to work even harder.
Just to explain more of this “approximate amount of fingers”: you might have seen this in the wild, imagine the AI starting out with white noise, and then slowly brushing over different parts to add different things the model would expect. There’s gonna be areas where the AI expects “heads” and “limbs” and finally “fingers”. But it’s more like a texture. Those AIs have no direct concept of what the right amounts are for animals and humans. That’s why they paint “finger texture” in about the right spot and move on, and of course that’s gonna look weird 50% of the time.
There’s actually specific techniques modern AIs use to make sure any human or animal has the right amount of limbs and stuff because the AI on it’s own would never learn how to do this well otherwise. With text it’s really similar btw., although at least you can see the AI nailing the type of font before failing at coherent text. New AIs do a separate pass to recognize specific text in the prompt and then manually add that after the base sampling process iirc.
AIs are so interesting on many levels and the more you learn about them, the more respect you gain for artists and how much work goes into a piece of art. And it also really puts in perspective that (my opinion) AI will never completely replace artists. Our expertise on arts is just too strong so for the foreseeable future AIs will just be a solid helper to every artist at most.
AI is fun to play around with if you are like me with zero artistic talent but currently is no comparison with a real talented artist.
I can’t even draw a bit of spaghetti never mind a hand!
that’s why you use open pose controlnet
As an artist, I can say no, it’s not.
++ I get so bummed out that people who are running models are unabashedly stealing from people left and right and then shrugging their shoulders for their unethical practices. Perhaps pay people for their catalogues at an agreed upon rate or be a disgusting pig and buy from their estate after death. But don’t just come out here and train your models on everything as if it were a free for all and as if creativity amounted to nothing more than fodder for unabashed capitalism =/!
I think that AI is gonna really propel artists to making some awesome weird stuff. AI will be only be able to produce art that already exists or realism. Artists are still going to be the only ones creating new styles, which is going to make their original creations much more appreciable.
Idk bullshit peddler, I can’t get with you on this one. Because I think at the end of the day - anything will be seen as “up for grabs” and illustrators will be on the outs like loomers. And while I am somewhat okay with the idea of rug makers (among other loomable items) being antiquated - creativity should not be because it’s the pulse of human expression for many and if we lessen it/deny it - I think the whole world will begin to taste like corn-flakes.
I saw this growing up in a way, they took our arts program and nobody really found any way to express themselves and at the end of the day where I grew up very few people ever amounted to much of anything =/! I think expression is needed, and must be safeguarded because you need to feel safe to express and must know that it’s a worthwhile venue to venture into. But this is all kinda arm flapping. You can’t stop the future and clearly AI is here to stay - so now we’ve got to work around what we can.
But, by the by - I still love the bs you’re putting down =)
AI will be only be able to produce art that already exists or realism.
Well, that is not true at all.
Generative AI isn’t just limited to imitating or copying existing art. It’s fully capable of creating original pieces, much like humans do. Sure, AI models learn from large datasets of existing art, but that doesn’t mean they’re limited to mere copying. Instead, they take these inputs, find patterns, blend concepts, and can then generate something entirely new. This isn’t too different from how human artists operate. They too absorb influences from the world and other pieces of art and generate new ones based on that. Nobody is creating art in a vacuum.
The additional benefit AI has is not being tied down by existing concepts. Human creativity often gets shaped by cultural trends or personal experiences, but AI can step outside those constraints, giving us a fresh take on art and creativity in ways that many human artists can’t. Not to even mention that you need a human in the loop to write the prompt. AI doesn’t create art alone no more than a paint brush does.
It will make it much more difficult to make a living as an artist, and a less viable pursuit.
It’s already impossible to make money as an artist
I can’t draw a hand for shit, but my hand can be traced for one hell of a turkey.
