Imagen Video: high definition video generation with diffusion models

#1

Post by jasondavies » Wed, Oct 05, 2022, 5:38 PM UTC

Imagen Video: high definition video generation with diffusion models
imagen.research.google

Re: Imagen Video: high definition video generation with diffusion models

#2

Post by alphabetting » Wed, Oct 05, 2022, 5:46 PM UTC

We're about a week into text-to-video models and they're already this impressive. Insane to imagine what the future holds in this space.

Re: Imagen Video: high definition video generation with diffusion models

#3

Post by naillo » Wed, Oct 05, 2022, 5:48 PM UTC

Probably only 6 months until we get this in stable diffusion format. Things are about to get nuts and awesome.

Re: Imagen Video: high definition video generation with diffusion models

#4

Post by J5892 » Wed, Oct 05, 2022, 5:50 PM UTC

naillo wrote: post #3

Probably only 6 months until we get this in stable diffusion format. Things are about to get nuts and awesome.

No post body was provided.

Re: Imagen Video: high definition video generation with diffusion models

#5

Post by jasonjamerson » Wed, Oct 05, 2022, 5:50 PM UTC

The most exciting thing about this to me is the possibility of doing photogrammetry from the frames and getting 3D assets. And then if we can do it all in real time...

Re: Imagen Video: high definition video generation with diffusion models

#6

Post by minimaxir » Wed, Oct 05, 2022, 5:52 PM UTC

jasonjamerson wrote: post #5

The most exciting thing about this to me is the possibility of doing photogrammetry from the frames and getting 3D assets. And then if we can do it all in real time...

There's a bunch of NERF tools that can get pretty close to good 3D assets from static images already.

Re: Imagen Video: high definition video generation with diffusion models

#7

Post by dwohnitmok » Wed, Oct 05, 2022, 5:54 PM UTC

How has progress like this affected people's timelines of when we will get certain AI developments?

Re: Imagen Video: high definition video generation with diffusion models

#8

Post by gamegoblin » Wed, Oct 05, 2022, 5:54 PM UTC

naillo wrote: post #3

Probably only 6 months until we get this in stable diffusion format. Things are about to get nuts and awesome.

Emad (founder of Stability AI) has said they already have video model training underway, as well as text and audio. Exciting times.

Re: Imagen Video: high definition video generation with diffusion models

#9

Post by naillo » Wed, Oct 05, 2022, 5:54 PM UTC

J5892 wrote: post #4

naillo wrote: post #3

Probably only 6 months until we get this in stable diffusion format. Things are about to get nuts and awesome.

Quoted post unavailable.

jarvis render a video of nutsome cream spread on a piece of toast 4k HD

Re: Imagen Video: high definition video generation with diffusion models

#10

Post by J5892 » Wed, Oct 05, 2022, 5:55 PM UTC

alphabetting wrote: post #2

We're about a week into text-to-video models and they're already this impressive. Insane to imagine what the future holds in this space.

Insane, terrifying, incredible, etc.

We're rapidly stumbling into the future of media.

Who would've imagined a year ago that trivial AI image generation would not only be this advanced, but also this pervasive in the mainstream.

And now video is already this good. We'll have full audio/video clips within a month.