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

101–110 of 399 posts

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

#101

Post by EamonnMR »

dahfizz wrote: post #84
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…

I think we will definitely see a content explosion. The pessimist in me says that general levels of creativity and quality will go down, if anything. It's AI written blogspam, but for images and video too. The signal to noise ratio is getting worse and worse

Less Cambrian Explosion, more Permian-Triassic Extinction.

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

#102

Post by bottlepalm »

soheil wrote: post #55
bottlepalm wrote: post #14

I don’t want to think reality is a simulation, but wouldn’t our everyday experience being generated by a neural network be far far simpler to achieve than a universe of infinite minuscule atoms all interacting.. like ozcam’s razor is pointing towards our lives being a realistic dream. Like in 10 years you could plug this tech into high end VR and get a prompted reality dynamically generated that would be indistinguis…

If you're assuming each atom is independent of other atoms then yes. But if you believe the universe is deterministic and atoms are just following the laws of physics then you can think of the universe as nothing more than a computer with electrons instead of atoms just floating around.

It’d be simpler to say there are no atoms, just a neural net fed into your senses making you think that there are atoms.

The neural net itself is built on a much simpler substrate in an external universe.

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

#103

Post by aero-glide2 »

bottlepalm wrote: post #14

I don’t want to think reality is a simulation, but wouldn’t our everyday experience being generated by a neural network be far far simpler to achieve than a universe of infinite minuscule atoms all interacting.. like ozcam’s razor is pointing towards our lives being a realistic dream. Like in 10 years you could plug this tech into high end VR and get a prompted reality dynamically generated that would be indistinguis…

Thought of the exact same thing, this seems plausible.

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

#104

Post by fullshark »

VoodooJuJu wrote: post #12

A 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.

The only way it will be over is that tiktok/instagram will attract more eyeballs and hurt their bottom line. Ultimately this is for amateurs to create really short form content for the foreseeable future.

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

#105

Post by generalizations »

asutekku wrote: post #88
Xelynega wrote: post #46

Earlier quoted context omitted.

I don't think modern movies are stuck in a "low risk reboot loop" because of the cost to produce, it's because of the potential profit. Why spend money on a film with new IP and ideas that you're not sure will be popular when the data science team has already worked with marketing to figure out exactly what movie will sell well? Good luck finding your movie with compelling and thought provoking writing in the big pil…

With the future version of this you could theoretically prototype movies way faster and try ideas with test audiences without requiring to actually film them

In the future version of this, the end user asks for a movie and gets a custom movie generated just for them.

You want a thought-provoking Bourne-style action thriller with hints of Jane Austen and a bollywood dance sequence? How about a Matrix sequel that lives up to the first one, but ends just the way you like it? Just ask.

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

#106

Post by terafo »

VoodooJuJu wrote: post #12

A 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.

You are hilariously wrong if you think it will not improve. Combination of prompt engineering, better and bigger datasets, better architectures, bigger models, artifact-fixing tools and sheer human creativity will seriously challenge traditional movie-making within two years.

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

#107

Post by sphars »

castlecrasher2 wrote: post #98
sphars wrote: post #51

Earlier quoted context omitted.

I've been looking into some of the 3D model generators this past week, and there is some work happening in that field. See the following non-exhaustive list: https://github.com/snap-research/NeROIC https://github.com/threedle/text2mesh https://github.com/AutodeskAILab/Clip-Forge https://nv-tlabs.github.io/GET3D/

Have you by chance tried out NeROIC? I'm a 3D printing enthusiast, mostly video game stuff, and it seems like like it would be excellent for that purpose.

I actually have been trying it out this week, and in fact it's currently trying to process the video generation, like their example shows. While I was able to follow their steps for training using their dataset, and generate the lighting/depth maps for the milkcarton example, the video generation is taking a long time (over 24 hours so far, using a 3070Ti with 8GB VRAM).

From what I understand with NeROIC, it's not particularly meant to be able to generate an 3D model that can be imported into Blender (or other software). It requires more work to take the meshes it generates to do something with it. See https://github.com/snap-research/NeROIC/issues/10

I too was looking into it to generate 3D models for some software I've been working on.

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

#108

Post by echelon »

Xelynega wrote: post #46
fasteddie31003 wrote: post #4

I'm rooting for this tech. Hopefully this will get modern movies out of their low risk reboot loop since it will be cheaper to make a movie that have new story lines that are commercially untested. I'd be happy to watch a movie that doesn't look AAA, but has compelling writing and makes me think. Or maybe I'll just stick to books.

I don't think modern movies are stuck in a "low risk reboot loop" because of the cost to produce, it's because of the potential profit. Why spend money on a film with new IP and ideas that you're not sure will be popular when the data science team has already worked with marketing to figure out exactly what movie will sell well? Good luck finding your movie with compelling and thought provoking writing in the big pil…

Films today require institutional capital. There are less than a thousand directors a year that get greenlit. There isn't enough conceptual or directorial diversity, and it sucks.

In the future, kids will be making their own Star Wars movies from home. All kinds of people from all kinds of backgrounds will make novel films that would ordinarily never be made, such as "Steampunk Vampires of Venus", starring John Wayne, a young Betty White, and Samuel L. Jackson. This is absolutely the future.

I'm working on building this. I'm sure lots of others are too.

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

#110

Post by MichaelCollins »

mikepurvis wrote: post #61
criddell wrote: post #16

Earlier quoted context omitted.

> I don't think it will improve much from here That's a bold prediction. Why do you think that? The first thing I thought was the exact opposite. This isn't very good, but it's only version 1. Motion pictures are less than 150 years old. In another 150 years I bet virtual filmmaking will progress a lot.

Absolutely, particularly if you see this as simply another tool in the belt, like how Jurassic Park's thirty year old special effects absolutely stand the test of time because of them being a convincing mix of early CGI and puppetry. It's not hard to imagine that this kind of thing could end up doing a lot of the heavy lifting for things like background scenes in the future, opening up the kind of stuff we saw in The…

The first Jurassic Park holds up unusually well. They used CGI for things they couldn't convincingly do any other way, and used practical effects for almost everything else. And for the most part they hid the CGI well, they took a lot of care to mix it up with close ups of practical effects, the way they framed the shots to direct audience attention, etc.

I think in a lot of modern stuff they go too far. They now use CGI for things that could easily be practical effects, but they go with CGI because it's simply cheaper or because they want to A/B test different colors of wall paneling behind a character in post production, or who knows what. The end result is apparently good enough to make a billion dollars, but I can't stand it. Movies don't feel authentic anymore. It's hard to describe rationally, but the word 'soulless' sums up how movies made the new way make me feel. Even the scenes which are wholly practical/real get degraded; the excessive CGI and compositing used in the rest of the movie cast a miasma of unrealness across the entire movie.

https://64.media.tumblr.com/248d25e2185a58bf827d329490480fb9...

Post reply on HN