Earlier quoted context omitted.
doctors ? We are a looooooong way to go before AI can replace actual doctors.
A month ago I would have said that about actual artists.
No post body was provided.
Make-A-Video: AI system that generates videos from text
361–370 of 399 posts
Re: Make-A-Video: AI system that generates videos from text
#362Whenever there is an explosion of content, curation and search become important. Meta has many of the products people use to show off their taste, so having more content to curate and share is good for their ecosystem (until people stop consuming as much because they know they can produce even better with their own imagination). This may be good for Google - the more content there is, the more you need search to find…
Creators are already curators. Musicians often don’t produce their own sounds, they curate and piece together samples. Designers and software engineers cut and paste from existing work. The idea of a blank slate creator has been dead long before ML tools were introduced :)
No post body was provided.
Re: Make-A-Video: AI system that generates videos from text
#363Earlier quoted context omitted.
And what exactly are your senses and your brain made out of?
In the sim theory, the external neural net tells us our brain is made of atoms.. you could theoretically feed your senses a Minecraft reality and you'd think your head is full of interacting blocks - which is still capable of performing the same NN functions as a wet brain... So I don't know, the brain could be made out of anything that fits the requirements of running the computation. That's assuming there even real…
Why then program the brain to try to understand that it's in a simulation when the goal was to create a realistic simulation in the first place? That'd be a rookie mistake on part of the simulation developers.
Re: Make-A-Video: AI system that generates videos from text
#364At this rate, within a few years we'll have people creating low quality movies just by describing what they want the movie to look like. Soon, every book will have a video version. As someone who has written several unpublished science fiction novels, I can't wait.
Re: Make-A-Video: AI system that generates videos from text
#365As an owner of a Video Production studio, this kind of tech is blowing my mind and makes me equally excited and scared. I can see how we could incorporate such tools in our workflows, and at the same time I'm worried it'll be used to spam the internet with thousands and thousands of souless generated videos, making it even harder to look through the noise. A fun related experiment, I thought it was fun to see what ki…
"Soulless" -- they'll be low quality, both in rendering and in plot/acting, but they'll be anything but soulless. Each will be a labor of love of someone with a dream.
Re: Make-A-Video: AI system that generates videos from text
#366As an owner of a Video Production studio, this kind of tech is blowing my mind and makes me equally excited and scared. I can see how we could incorporate such tools in our workflows, and at the same time I'm worried it'll be used to spam the internet with thousands and thousands of souless generated videos, making it even harder to look through the noise. A fun related experiment, I thought it was fun to see what ki…
I love this! But after trying it a few times I got this result :). So fascinating. https://thismoviedoesnotexist.org/movie/the-terminator Brings up the age-old question of how much the learning in these models is just memorization. Though in cases like these it’s hard to tell.
Note to mention "In the Land of Oz: The Search for the Wizard":
https://thismoviedoesnotexist.org/movie/in-the-land-of-oz-th...
Which reads like a bad translation of a bad translation. Like the the old joke about the AI program which was supposed to translate "The spirit is willing but the flesh is weak" from English to Russian to English, and after the roundtrip came up with "The vodka is good but the meat is rotten."
Re: Make-A-Video: AI system that generates videos from text
#367Earlier quoted context omitted.
Where do the inputs for the machines come from? ex: having a machine that generates CPUs out of sand and works for free would mean cheaper CPUs, but it would also mean a lot more employment in the sand industry, and there might not be a machine for creating sand. https://en.m.wikipedia.org/wiki/Jevons_paradox
Large mining robots? Some dump trucks are already autonomous, I'm guessing excavators aren't far.
Do they stop being autonomous when they get a flat tire?
Re: Make-A-Video: AI system that generates videos from text
#368Earlier quoted context omitted.
> It's scary to think about it but seems plausible—like if someone can make an app with Tiktok-like ubiquity of only AI content. Although to your point I imagine there will be so much nonsensical noise that curating will become a useful skill, it is today but even more so. This just gave me a disturbingly vivid vision of exactly what you described. A seemingly likely future where everyone's in their homes scrolling e…
Well, what's so scary about this exactly? That's exactly what people do today on Tiktok, modulo the part where AI generates the content.
plus the part where NPCs generate the content.
Re: Make-A-Video: AI system that generates videos from text
#369All the animals have human hands - kind of creepy looking. I assume that is because the images used for training the models only humans have hands.
Re: Make-A-Video: AI system that generates videos from text
#370I was pretty surprised to see that the WebVid-10M Dataset used as part of this training - https://m-bain.github.io/webvid-dataset/ - consists entirely of video preview clips scraped from Shutterstock! I built a quick search engine over that data: https://webvid.datasette.io/webvid/videos Wrote more about that here: https://simonwillison.net/2022/Sep/29/webvid/
I wonder why the generated videos don't all contain the shutterstock watermark?