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

341–350 of 399 posts

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

#341

Post by macrolocal »

bottlepalm wrote: post #334
macrolocal wrote: post #257

Earlier quoted context omitted.

Ever wonder why you weren't born a medieval peasant? Well, from the outside reality's perspective, it's helpful for people to spend the first few decades of their lives in an early 21st century simulation, just so they can gradually acclimate themselves to all this technology. /folly

That thought has crossed a lot of peoples minds especially after the Matrix.

Yeah, my grandfather once said that he lived in the most exciting possible time, having been born before the first automobile, and having lived to see a man on the moon.

But even so, this era feels like it could be a singular phase shift. Maybe.

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

#342

Post by duderific »

EMIRELADERO wrote: post #213
Xeoncross wrote: post #208

Earlier quoted context omitted.

What is interesting to me is the decline in both understanding and communication abilities. When I look at modern speech and compare it to books written hundreds of years ago the deficiencies are stark. I can't imagine how poorly people will speak and mentally process emotions in 20 years.

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.

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

#343

Post by tiborsaas »

tmjdev wrote: post #3

This looks like the video equivalent of Dall-E 1. Hard to believe how far we've come so quickly. The paper talks about "pseudo 3D attention layers" that are used in place of temporal attention layers for each dimension due to memory consumption. It seems like AI research is vastly outpacing GPU development.

Hardware was probably always lagging behind cutting edge research, just consider video games, they pushed hardware limitations very hard since Pong.

It's a good thing to be fair, forcing research teams to optimize their projects is beneficial and creates a competition for limited resources. This gets a bit skewed when we consider a university research team vs. a MANGA type company, but the team behind Stable diffusion proved that innovation can come from unexpected places.

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

#344

Post by Teever »

mjr00 wrote: post #205
consumer451 wrote: post #194

Earlier quoted context omitted.

Is it really the same though? A driving system which can only create a good outcome 90% of the time is not really useful as irl human safety is a factor. However, a creative system curated by a human could end up creating useful outputs, could it not?

Obviously different safety outcomes, but ultimately it's the same idea: unless you can hit that last 10%, it's essentially useless. You could pump out AI songs that are about as good as the 10,000 songs that get uploaded to Soundcloud every day, but nobody listens to those already. It's really only the best Something that can be further refined by humans is more interesting. There's people looking into AI-based sampl…

I'm not so sure that the most popular music is the best 1% of music.

Artists don't always become famous or popular because they're the best, instead it happens because they're pliable in a business sense and fit into a bigger picture of what the product is supposed to be.

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

#345

Post by sgrove »

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…

You should add a “tweet this movie” button that pre-populates the image and the title! I immediately wanted to share one of the funny suggestions.

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

#346

Post by DesaiAshu »

dzink wrote: post #197

Whenever 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 :)

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

#347

Post by area51org »

“Your scientists were so preoccupied with whether they could, they didn't stop to think if they should.” –pithy quote from a summer action movie

I'll just say it now: this is a mistake, quite possibly a huge mistake. The average human is not intelligent enough to deal with computer-generated video that they can mistake for reality, and so this can and will become a tool for despots.

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

#348

Post by washywashy »

I could see this type of technology being used at some point in the future to essentially algorithmically generate content (movies, tv shows, etc) for viewers to watch or engage with. I wonder if it leads to extremely customized content where what I watch is 100% different from any other user on the same platform. However, I also wonder if people enjoy watching the same things because it becomes harder to talk about a movie you’ve seen if there’s no way anyone else could have ever watched it without you sharing it with them.

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

#350

Post by yreg »

treis wrote: post #294
agitator wrote: post #233

What's mind blowing is that you can extrapolate where this is going to go. Eventually, you will be able to generate full movie scenes from descriptions. What's interesting to me is how this is so similar to human imagination. Give me a description and I will fabricate the visuals in my mind. Some aspects will be detailed, others will be vague, or unimportant. Crazy to see how fast AI is progressing. Machines are appr…

IMHO this particular avenue is a dead end. It's an extraordinarily impressive dead end but it's clear that there's no real understanding here. Look at this video of the knight riding a horse: > https://makeavideo.studio/assets/A_knight_riding_on_a_horse_... The horse's face is all wrong The gait is wrong The interface with the ground & hooves is wrong The knight's upper body doesn't match with the lower and they're n…

Of course there "is no understanding here", but yet it's not all wrong. Somehow it did move the horse's legs roughly correctly (using the proper joints and all), somehow the cape is moving roughly as it should through the air and the knight's body absorbs the force of stomping on the ground…

It doesn't seem that the fundamental inability to understand what is going on in the scene is stopping models of this kind to eventually lead to realistic results.

Same applies to DALL-E and GPT.

Post reply on HN