No offense to the creators and not to discourage them, but the whole process already looks so arduous and antique. We're not there yet but I bet that with GPT-x-video-diffusion we get similar results with MUCH less work rather soon. BTW Google just released the other way: a new video-to-text model today.
“An insult to artists.” Oh boy. This is going to be one of those thinly veiled arguments about “authenticity” and how the method is important, but is really just “old man yells at cloud” isn’t it?
I don’t care about your process. If it takes all kinds of esoteric stuff to create a Miyazaki masterpiece, then great! But if we can make the same masterpiece in a fraction of the steps, even better.
If artists feel that the market cares about process and authenticity then they shouldn’t feel threatened. They have a strict advantage there.
And if that matters to the audience, then the 3D print won’t fare well in the market. People won’t want to see it if the real value is to sit and admire how a human could have done that to a slab of marble.
But oftentimes people are happy to buy a print rather than the original because they just like the end product.
Trying to assign value to art is perilous. Who cares if my print that I admire every day isn’t an original? I’m not trying to launder money.
Responding to this video, I really liked this take from Aaron Blaise (animator on Beauty and the Beast and Aladdin and director of Brother Bear) on AI in animation.
> To be honest with you, the biggest threat to our industry is not the AI.
I mean when you look at any technology's ever come along in the entertainment industry, the expressiveness, the ability to create new films and new ideas has exploded.
As an end result it has actually created more jobs and budgets have actually gone up.
If you look at the budgets now compared to what they were back in the 90s, they're doubled.
> The biggest threat I think is an age-old threat: it's bad stories and bad management.
That's what's going to get rid of jobs, if you're putting out consistently bad movies under bad management, because no one's going to go see them.
> So the idea is that it doesn't matter what technology you're putting on it. Make sure that the story underneath all of that technology is good, make sure it's engaging, make sure it's something that people want to go to, so they can laugh and cry and be scared and learn something.
This means that management needs to be good enough to realize that it's a good idea to include young talent, give them opportunity, and respect their different perspectives. This means better stories, and also means that the management holds those beliefs as principles, and are willing to take risks "for the sake of it."
But that seems counter to the idea of a management pastiche drooling over the cost-cutting potential of AI.
Seems like the key to consistency will be generating multiple images in a sequence simultaneously, rather than generating frames independently. Are models being developed along these lines?
17 comments
[ 3.7 ms ] story [ 56.1 ms ] threadBut: this is about adapting stable diffusion to video. Pretty cool.
Turns out that uBlockOrigin on Firefox or one of my other plugins just blocks that out. I never saw an ad. Still don't.
I don’t care about your process. If it takes all kinds of esoteric stuff to create a Miyazaki masterpiece, then great! But if we can make the same masterpiece in a fraction of the steps, even better.
If artists feel that the market cares about process and authenticity then they shouldn’t feel threatened. They have a strict advantage there.
Michealangelo’s David is a masterpiece that took one of the greatest marble workers and masters of human anatomy to carve.
A completely identical David produced by a machine, or a 3D print of it, based on a model derived by a GAN, is worthless.
But oftentimes people are happy to buy a print rather than the original because they just like the end product.
Trying to assign value to art is perilous. Who cares if my print that I admire every day isn’t an original? I’m not trying to launder money.
I know . . . I know . . . the first rule of animator fight club is . . .
https://www.youtube.com/watch?v=xm7BwEsdVbQ
> To be honest with you, the biggest threat to our industry is not the AI. I mean when you look at any technology's ever come along in the entertainment industry, the expressiveness, the ability to create new films and new ideas has exploded. As an end result it has actually created more jobs and budgets have actually gone up. If you look at the budgets now compared to what they were back in the 90s, they're doubled.
> The biggest threat I think is an age-old threat: it's bad stories and bad management. That's what's going to get rid of jobs, if you're putting out consistently bad movies under bad management, because no one's going to go see them.
> So the idea is that it doesn't matter what technology you're putting on it. Make sure that the story underneath all of that technology is good, make sure it's engaging, make sure it's something that people want to go to, so they can laugh and cry and be scared and learn something.
But that seems counter to the idea of a management pastiche drooling over the cost-cutting potential of AI.