Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Make-A-Video: AI system that generates videos from text

makeavideo.studio

Post reply on HN
Print view View original

371–380 of 399 posts

Re: Make-A-Video: AI system that generates videos from text

#371

Post by wayeq »

sixQuarks wrote: post #128
slhomme wrote: post #121

As 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…

For those who are scared about this technology, it’s good to look at what AI has done to Chess. The best chess seems to be when AI is used along with humans. I think image and video AI will best be exploited when human input is also taken into account. There is still something special about human creativity, I think AI will just be another tool to expand that. At least, in the short term I would say 10 years perhaps.…

what? Alphazero trained via self play and in ~10 hours became unbeatable by humans

Re: Make-A-Video: AI system that generates videos from text

#372

Post by I-M-S »

duderific wrote: post #342
EMIRELADERO wrote: post #213

Earlier quoted context omitted.

That is a non-sequitor. If you took an average working-class, "blue collar" person from hundreds of years ago, they would speak very differently from how those books are written.

Ok, maybe a better comparison that is sort of apples to apples would be to take a speech by George W. Bush or Donald Trump compared to say, George Washington or Abraham Lincoln. Surely you can see there is a sharp drop off in vocabulary and ability (or desire) to convey complex ideas.

Or think of it as signal to noise ratio improving. Complex words often hide simple thoughts.

Re: Make-A-Video: AI system that generates videos from text

#373

Post by anshumankmr »

maxov wrote: post #179
slhomme wrote: post #121

As 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.

The same could technically be said about Disney which is just remaking their entire classical collection but with CGI.

Re: Make-A-Video: AI system that generates videos from text

#374

Post by Nursie »

the_lonely_road wrote: post #246
barbariangrunge wrote: post #167

Earlier quoted context omitted.

Every 15 year old kid will be making their own blockbusters

Have you talked to the average 15 year old kid? Hell, have you talked to the average 50 year old? It will be the same as ever, a sea of absolute shit surrounding some true gems, be they from novel creativity or just excellent execution of well worn ground. The role of the trusted curator will rise and brands will gain more power. I am sure I will watch MY 15 year old's attempts, and maybe a few from my extended circl…

> It will be the same as ever, a sea of absolute shit surrounding some true gems

Ah, I can see what's wrong there, just turn down shit randomness and increase the true gem sampling steps to proportionally increase the input weight of true gems and fix your output quality.

Basically - if it empowers creative people, their output will be fed back in and parameterised.

Re: Make-A-Video: AI system that generates videos from text

#375

Post by dcl »

Only a small matter of time now before we have Vec2TikTok (or similar) where you'll be served up videos specifically optimised with the kind of content that will keep you scrolling or watching more.

People will end up watching news about events that never happened or product reviews for things that don't exist.

Re: Make-A-Video: AI system that generates videos from text

#376

Post by EmilyHughes »

bottlepalm wrote: post #111
EmilyHughes wrote: post #49

Earlier quoted context omitted.

Sounds good because it seems like it explains what our reality is, but it really doesn't. It just pushes the fundamental problem up X simulations into the supposed "real reality". It also assumes that simply simulating a universe would generate consciouss beings which nobody knows the answer to, but my guess is that it would not.

It does push the problem up, but it does let us factor out a lot of complex particle physics which are not needed to run the simulation. Remember in this case the simulation is not running a model of physical reality - it’s only running a neural net that is fed into your senses. In that case there are no ‘atoms’ it’s just a concept fed into your mind. Just like in dream it’s hard to question reality, you just go alon…

These particle physics are still needed. We generally assume the dream you have at night does not take place within a whole universe, yet it is still governt by some rules - for example you may experience gravity within your dream and understand that to move around when actually there isn't any gravity but it seems like it is.

It's equally important to understand and study the rules of this waking dream you are having while reading, not because there are actually atoms out there but because it behaves like there are. You can do physics without metaphysics, altough the two usually get entangled somewhat.

Re: Make-A-Video: AI system that generates videos from text

#377

Post by 5350-uiop-1130 »

algoatecorn wrote: post #153
5350-uiop-1130 wrote: post #68

Wonder if all these things will bring about a kind of cambrian explosion of creativity. Imagine a future of Prompt Wizards, who are able to coax the AI to generate things in a very specific way. Although we would probably need a much greater level of human curation. The way algorithms curate on youtube and spotify just doesn't really hit the spot. Perhaps stability and Dall-e already kind of showed that the value is…

https://twitter.com/chrisalbon/status/1567688342124503040

that's funny. looking forward to PromptJS, ppm and PromptScript.

Re: Make-A-Video: AI system that generates videos from text

#378

Post by LarsDu88 »

lairv wrote: post #147
looknee wrote: post #136

Earlier quoted context omitted.

I may be mistaken but I believe that human/machine pairing was dominant for a long while, but the last few years the chess solvers have progressed to a point where they're dominant on their own. Poker on the other hand I think human players still win vs GTO solvers, but again I may be mistaken here too.

I think AI now beat humans at poker https://www.sciencedaily.com/releases/2019/07/190711141343.h... https://www.cs.cmu.edu/~noamb/papers/19-Science-Superhuman.p...

Is there a single "intellectual" game left that humans can beat computers at? I suppose an AI has yet to beat lebron james at basketball, but I suppose that's for want of having a body.

Re: Make-A-Video: AI system that generates videos from text

#379

Post by mach1ne »

anigbrowl wrote: post #244
mach1ne wrote: post #96

Earlier quoted context omitted.

It may be that it's the deep learning tech which will never quite get there. GPT-3 has similar shortcomings in its mimicry. We're 95% there, I guess, but may never quite reach 100%.

Nah, the current issues are just because we're trying to do everything in one step. Because we've built tools that have so much of a stimulus-response approach, few efforts have been made toward interfaces that ask for clarification ('when you say X, do you mean XYZ or XXX?'). Image-to-image and tuning already addresses many of these issues; just as inpainting works really well, it won't be long before we have select…

The mistakes the AI makes are too numerous and hard-to-define for this to work I think. They could perhaps be addressed by having two different models trained differently, each fixing the errors of the other. When humans draw a realistic artwork, it's not 'single-pass'; they have to iterate on the details to get it right.

Re: Make-A-Video: AI system that generates videos from text

#380

Post by ckw »

ilaksh wrote: post #268
5350-uiop-1130 wrote: post #68

Wonder if all these things will bring about a kind of cambrian explosion of creativity. Imagine a future of Prompt Wizards, who are able to coax the AI to generate things in a very specific way. Although we would probably need a much greater level of human curation. The way algorithms curate on youtube and spotify just doesn't really hit the spot. Perhaps stability and Dall-e already kind of showed that the value is…

Think about 25 or 30 or 50 years down the line. More interesting than the next couple of years. Speculate a bit. After Neuralink and a few other companies torture enough poor monkeys, they eventually figure out how to create high bandwidth brain computer interfaces. We go through a few more paradigm shifts in computing and get 10000-1000000 X or more performance increase. Metaverse protocols have advanced to allow fo…

Every god eventually tires of indulgence, so contrives a dream set before all desires were fulfilled. I expect it would look something like this.
Post reply on HN