AI art is better than most humans, including most artists.
You can take the outputs and immediately turn them into animation. Suddenly I, as a single individual, can easily make film content without figuring out set and lighting logistics or roping in dozens of people.
I've said it before and I'll say it again: The fact that you didn't think to include an example is telling. If you think AI 'art' is good, show me, and tell me why you think it's good.
Conflating "art" (the "snobbish" definition if you will) with realistic depictions of imagined worlds, stories and settings is not helpful here. There are so many talented, imaginative people out there that have previously had Zero ability to manifest their thoughts into a visual form. AI has enabled that on so many levels and we should be grateful for it.
Then why not show me? Why is getting AI 'art' advocates to actually post something they think is good and explain why so hard? Where are these talented imaginative people and what are they doing?
You also don't see the everyday people using it to generate pictures about their own experiences and lives, using it to populate their DnD worlds, their personal unpublishable fanfics, etc.
This part is important since I'm still yet to see evidence that the AI artist is capable of thinking more deeply than "(full_body:1.2) , best quality, (8k, RAW photo, best quality, masterpiece:1.2) , (realistic, photo-realistic:1.4) , ultra-detailed, (Kpop idol) , perfect detail, looking at the viewer, makeup, pretty South Korean lady wearing a bathing suit, wet skin, light reflections, angelic cute face, half body shot, short brownish black hair".
You've gotten me confused about what you're going for. I figure the goal is "this is what this would look like, if there were a person with a balloon for a head and we captured him with a video camera".
The linked video isn't there yet, but it seems obvious what would or wouldn't make it good, and the list of traits you describe is really all I want in an image generator. I don't care what the girl is thinking about; that doesn't show up in the image anyway.
I do want to be able to say "no, make the hair shorter", or "turn her to face more toward the left of the frame" or "have her pointing at the door in the background". If that command takes the form of a comma-delimited list of traits, so what?
The balloon is a different shape from shot to shot, and - much worse - in a few of the shots it appears to be hovering in front of the rest of the image rather than occupying the space where Air Head's neck should be.
Is it better than I could do? Yep.
Is it failing a bar that any human would pass? Yep.
Is it better than relevant artists? Nope. But it is cheaper.
Literally everyone in this space is working on controllability. The cherry picked issue you cited has hundreds of the best minds tackling it as we speak.
This is the worst it will ever look. It's only going to improve from here.
Compare that to the early days of silent film. The profess with Gen AI is astounding.
We're going to have Disney/Pixar and Scorsese outputs by the end of the decade. (I'd be willing to wager even sooner than that.)
> The cherry picked issue you cited has hundreds of the best minds tackling it as we speak.
Did you mean to respond to my other, nearby comment? The issue I cite above isn't cherry-picked in any sense; it's a big, glaring problem with what was cited as an example of "good work". If someone's head is a balloon, the balloon should occupy the same position in 3D space as the head would.
> Compare that to the early days of silent film.
This is an interesting comparison. I don't think it really works. Early silent films were aware of what could and couldn't be done in the medium; there aren't any that rely on a nonexistent soundtrack. Generative AI stuff doesn't seem to be very concerned with "what kinds of things can we do well?". Instead, they're attempting everything, almost none of it is being done particularly well, and there are theoretical arguments over whether it makes sense to try to improve on individual tasks.
I don't get it, show you what? You want me to google it and pick a few examples? What purpose would that even serve? It's not even my main point (that you ignored), and I sense you have some "angle" you're pushing because you think it's some sure-fire put-down of AI generated images.
And yet you didn't make an attempt to name a single one. If there are it shouldn't be this hard to provide an example. Could it be that they're all so forgettable that they're completely gone from your mind five seconds after you scroll past them?
My friends and I are making an animated film. Here's a fully controlled test shot from the aesthetic board we created earlier in the year (so it isn't indicative of our current progress, themes, or quality):
I was somewhat with you through the first sentence then it got a bit breathless. As someone with some graphic design experience but who isn’t very good and can’t really draw, I used Photoshop and it’s genAI capability recently to put together a book cover for an ebook.
Would it win any awards? I’m pretty sure not but it’s more than adequate for its purpose and is almost certainly better than anything I could have come up with even if I used some CC artwork.
ADDED: I also had something of a vision for what I was looking for and (I think) enough of an eye to fiddle with things and get to the point where I went "This isn't half bad."
AI art is better than most humans, including most artists.
You can take the outputs and immediately turn them into animation. Suddenly I, as a single individual, can easily make film content without figuring out set and lighting logistics or roping in dozens of people.
This stuff is magic.