How do I get access to this?
Make-A-Video: AI system that generates videos from text
71–80 of 399 posts
Re: Make-A-Video: AI system that generates videos from text
#72Delighted this is in Facebook’s hands. No doubt responsible and careful thought of implications have been baked in from the start.
Please don't post snarky comments, or shallow dismissals, to HN. You may not owe BigCo better but you owe this community better if you're participating in it:
Re: Make-A-Video: AI system that generates videos from text
#73A lot of people saying it's over for traditional movie-making - lmao. I look at these and see nothing but uncanny valley artifacts, and I don't think it will improve much from here. It's like self-driving cars. They use almost very effective statistical models, certainly better than our previous models, but they never seem to shake off that "almost" and become truly effective.
> A lot of people saying it's over for traditional movie-making While these early versions are primitive, as a traditional filmmaker I think in a couple years these technologies will creatively empower visual storytellers in exciting new ways. The key will be developing interfaces which allow us to engage, direct and constrain the AI to help us achieve specific goals.
> these technologies will creatively empower visual storytellers in exciting new ways
Exactly. Every step forward in creative technology is additional leverage for the artist with a vision.
Re: Make-A-Video: AI system that generates videos from text
#74A lot of people saying it's over for traditional movie-making - lmao. I look at these and see nothing but uncanny valley artifacts, and I don't think it will improve much from here. It's like self-driving cars. They use almost very effective statistical models, certainly better than our previous models, but they never seem to shake off that "almost" and become truly effective.
This is a good example of the most abject type of Luddism: telling yourself that a fast-developing tech you happen to dislike is already at or near the limit of its potential and that defects you notice now will be there forever.
Please make your substantive points without name-calling.
Re: Make-A-Video: AI system that generates videos from text
#75A lot of people saying it's over for traditional movie-making - lmao. I look at these and see nothing but uncanny valley artifacts, and I don't think it will improve much from here. It's like self-driving cars. They use almost very effective statistical models, certainly better than our previous models, but they never seem to shake off that "almost" and become truly effective.
This is a good example of the most abject type of Luddism: telling yourself that a fast-developing tech you happen to dislike is already at or near the limit of its potential and that defects you notice now will be there forever.
The Luddites were a labor rights movement reacting to the new shifting power dynamic of centralized production owned by a few, in an era with virtually no safety and worker rights regulations. How would you feel if your career evaporated and you were forced to choose between starvation and sending your children to work in a textile factory where they get maimed by the machines they're told to crawl into and repair? You probably wouldn't find much comfort in the popular retort of "but shirts are really cheap now!"
That Luddites have been successfully maligned as irrationally anti-technology crazy people is a propaganda victory by industrialist factory owners and their friends, the newspaper men.
Re: Make-A-Video: AI system that generates videos from text
#76I remember the threads about StableDiffusion less than 4 weeks ago where people were confidently saying this kind of thing is 6 to 12 months away. Turns out it was a month. Singularity soon?
Re: Make-A-Video: AI system that generates videos from text
#77The > A golden retriever eating ice cream on a beautiful tropical beach at sunset, high resolution example is terrifying.
The hands throw me off. The same with the cat holding the remote... never thought that hands on animals would be able to trigger my uncanny valley response, but here we are
Eugh, thanks for warning me.
Re: Make-A-Video: AI system that generates videos from text
#78Earlier quoted context omitted.
The ‘outside’ reality only needs to be the size of a data center, not the entire universe. And maybe the outside reality only needs to be a trained 100gb model. A much simpler outside reality than we have now. You don’t even need to sim 8 billion people, just 1, you.
Occans razor in this case applies to the complexity giving rise to a situation here though, not the complexity of a described system. Conventional physics giving birth to our universe is currently the model with the fewest assumptions. What would have to take place to give rise to a universe the size of a data center, running an AI model of a human? It feels like we have to bake in assumptions of stable physics, a ri…
The outside universe doesn’t require our complex particles or physics - all that is overkill to run a neural net. Also think of all the data we can store in a fingernail, stable diffusion is like 4gb, what could a 4tb model produce?
Re: Make-A-Video: AI system that generates videos from text
#79A lot of people saying it's over for traditional movie-making - lmao. I look at these and see nothing but uncanny valley artifacts, and I don't think it will improve much from here. It's like self-driving cars. They use almost very effective statistical models, certainly better than our previous models, but they never seem to shake off that "almost" and become truly effective.
I'm not sure I'd agree with the "it won't improve much from here" sentiment, but I am a little confused by the sharp disagreements with this comment. They seem to contain a tacit assumption that the complexity curve for this problem is smoothe, but I could easily imagine a very sharp elbow in that curve, making any progress come to a seemingly grinding halt.
Re: Make-A-Video: AI system that generates videos from text
#80How do I get access to this?
>Our goal is to eventually make this technology available to the public, but for now we will continue to analyze, test, and trial Make-A-Video to ensure that each step of release is safe and intentional.