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

131–140 of 399 posts

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

#131

Post by SethMurphy »

generalizations wrote: post #105
asutekku wrote: post #88

Earlier quoted context omitted.

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.

This could certainly be entertaining. The trick will be for the studios to continue to brand it as recognizable, yet have it be unique. It begs to ask what part of the experience will be a shared experience since it could be radically different for all of us. Would we then share the story created for us with friends? Will there be an Oscar for best mind to have a video created for them?

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

#132

Post by ragazzina »

indigodaddy wrote: post #109

So how long before we can “Hey music-stable-diffusion-service,” play me “relaxing baroque violin and flute music in the style of game of thrones” ?

I've found this is my biggest issue with music streaming services. Often I just want another song similar to the one I am listening to, but no "generate radio from this track" comes close.

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

#133

Post by lairv »

Reading the paper, what's interesting is that they really build upon text-to-image models. Instead of generating 1 image with diffusion model, they generate 16, and then use several upsampling/interpolation methods to increase the resolution/framerate. For the text-image model, they use the DALL-E 2 architecture, so in theory just switching to a latent diffusion model (like stable diffusion) would boost training/inference cost of the model

The shortcoming is that, since they don't use any video/text annotation (just image/text pairs), complex temporal prompts would probably not work, something which require multiple steps like "a bear scoring a goal, then doing the Ronaldo celebration"

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

#134

Post by appleflaxen »

j_m_b wrote: post #28

What I want to see is a model that can generate 3D models for use in applications such as Blender. It would provide a good starting point for someone with talent to make beautiful. Or just save people like me time for making games.

Agree! And it seems like this should be the easiest thing to train!

Let the AI generate random blender files.

Render them.

Train on source => render mapping (which is 1:many)

Repeat.

You should be able to get an incredibly high-fidelity decoder to go from image to blender source.

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

#136

Post by looknee »

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.…

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.

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

#137

Post by dwohnitmok »

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.…

> The best chess seems to be when AI is used along with humans.

I don't think this is true anymore. I don't think I've heard about successful centaur chess games in years. I would love to be wrong there though (in particular if anyone knows about how correspondence chess games have been played in the last 2 or 3 years with the availability of Leela Zero and Stockfish NNUE).

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

#138

Post by fooblaster »

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.…

top tier chess ais crush human grandmasters and achieve super human performance with no assistance

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

#139

Post by MichaelCollins »

consumer451 wrote: post #54
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…

Once I heard or realized (don't remember which) that simulation theory is just deism for techies, I stopped entertaining these ideas.

Exactly. The simulation theory proponents almost always seem to presume the existence of some sort of being that deliberately created the simulation. What if the simulation is a complete accident that has arisen from the complex interaction of brainless bacteria competing for scarce resources on the surface of a big rock? An accidental simulation emerging from randomly initialized 'cellular automata' on one rock in a host universe containing trillions of such rocks.

The usual presumption of the simulation being a deliberate construction of a conscious being makes the whole thing seem like nu-religion for people who reject supernatural things. With the presumption of a being deliberately creating the situation, you pull in these notions: We're special, we exist on purpose, we are probably being examined and judged. This reeks of religion.

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

#140

Post by mjr00 »

indigodaddy wrote: post #109

So how long before we can “Hey music-stable-diffusion-service,” play me “relaxing baroque violin and flute music in the style of game of thrones” ?

A long time. Much like self-driving cars, AI can take you 90% of the way there, but the last 10% is the difference between music that sort-of-seems-competent, and music that people will actually listen to and enjoy.
Post reply on HN