5 years ago there were no AI videos. A bit over a year ago the best AI videos were hilarious hallucinations of Will Smith eating spaghetti.
Today we have these realistic videos that are still in the uncanny valley. That's insane progress in the span of a year. Who knows what it will be like in another year.
Disco Diffusion was a (bad) thing in 2021 that lead to the spaghetti video / weird Burger Kind Ads level quality. But it ran on consumer GPUs / in Jupyter notebook.
2 years ago we had decent video generation for clips
With these things, like DALL-E 1 and GPT-3, the original release of the game changer often comes ca. 2 years before people can actually use it. I think that's what we're looking at.
So you're right to be excited, I agree. And I don't know, Meta, like OpenAI, seems to release conditionally, though yes, more. I doubt it before the election.
When the Will Smith one was released, it was kind of a parody though. Tech had already been able to produce that level of "quality" for about 2 years at the time of it's publishing. The Will Smith one is honestly something you could have created with Disco Diffusion in early 2021, I used to do this back then...
The subtle "errors" are all low hanging fruit. It reminds me of going to SIGGRAPH years back and realizing most of the presentations were covering things which were almost imperceptible when looking at the slides in front. The math and the tech was impressively, but qualitatively it might have not even mattered.
The only interesting questions now have nothing to do with capability but with economics and raw resources.
In a few years, or less, clearly we'll be able to take our favorite books and watch unabridged, word-for-word copies. The quality, acting, and cinematography will rival the biggest budget Hollywood films. The "special effects" won't look remotely CG like all of the newest Disney/Marvel movies -- unless you want them to. If publishers put up some sort of legal firewall to prevent it, their authors, characters, and stories will all be forgotten.
And if we can spend $100 of compute and get something I described above, why wouldn't Disney et al throw $500m at something to get even more out of it, and charge everyone $50? Or maybe we'll all just be zoo animals soon (Or the zoo animals will have neuralink implants and human level intelligence, then what?)
> In a few years, or less, clearly we'll be able to take our favorite books and watch unabridged, word-for-word copies. The quality, acting, and cinematography will rival the biggest budget Hollywood films. The "special effects" won't look remotely CG like all of the newest Disney/Marvel movies -- unless you want them to. If publishers put up some sort of legal firewall to prevent it, their authors, characters, and stories will all be forgotten.
I'm also expecting, before 2030, that video game pipelines will be replaced entirely. No more polygons and textures, not as we understand the concepts now, just directly rendering any style you want, perfectly, on top of whatever the gameplay logic provided.
I might even get that photorealistic re-imagining of Marathon 2 that I've been wanting since 1997 or so.
> In a few years, or less, clearly we'll be able to take our favorite books and watch unabridged, word-for-word copies. The quality, acting, and cinematography will rival the biggest budget Hollywood films. The "special effects" won't look remotely CG like all of the newest Disney/Marvel movies -- unless you want them to. If publishers put up some sort of legal firewall to prevent it, their authors, characters, and stories will all be forgotten.
I don't think so at all. You're thinking a movie is just the end result that we watch in theaters. Good directing is not a text prompt, good editing is not a text prompt, good acting is not a text prompt. What you'll see in a few years is more ads. Lots of ads. People who make movies aren't salivating at this stuff but advertising agencies are because it's just bullshit content meant to distract and be replaced by more distractions.
But at the same time, while it is indeed true that the end result is far more than simply just making good images, LLMs are weird interns at everything — with all the negative that implies as well as the positive, so they're not likely to produce genuinely award winning content all by themselves even though they can do better by asking them for something "award winning" — so it's certainly conceivable that we'll see AI indeed do all these things competently at some point.
Today we have these realistic videos that are still in the uncanny valley. That's insane progress in the span of a year. Who knows what it will be like in another year.
Let'em cook.