How Imagen Works • Hacker News Board

Re: How Imagen Works

#11

Post by natch » Thu, Jun 23, 2022, 4:48 PM UTC

> Imagen, released just last month, can generate high-quality, high-resolution images given only a description of a scene

“Released”? What? Papers are published. Websites are published. Tools are “released.”

Where has Imagen been released?

Re: How Imagen Works

#12

Post by watmough » Thu, Jun 23, 2022, 4:49 PM UTC

coding123 wrote: post #2

Is this by a person that knows or is guessing?

The important part seems to be the diffusion model.

Explanation linked from same page: https://www.assemblyai.com/blog/diffusion-models-for-machine...

Re: How Imagen Works

#13

Post by visarga » Thu, Jun 23, 2022, 5:18 PM UTC

SleekEagle wrote: post #9

dubswithus wrote: post #8

If Google has something similar or better it definitely makes it look like OpenAI is wasting its time. None of this relates to AGI.

I don't think anyone is saying that humanity is close to AGI, but check out DeepMind's Gato work for a more well-rounded agent: https://www.deepmind.com/publications/a-generalist-agent

I think we're past a certain threshold, maybe not AGI but some definite qualitative change is happening.

Re: How Imagen Works

#14

Post by bpiche » Thu, Jun 23, 2022, 5:25 PM UTC

natch wrote: post #11

> Imagen, released just last month, can generate high-quality, high-resolution images given only a description of a scene “Released”? What? Papers are published. Websites are published. Tools are “released.” Where has Imagen been released?

This implementation popped up on hacker news not too long ago. I got it working on Colab first, and then my own GPU at home. But just barely. Need more memory :)

https://github.com/lucidrains/imagen-pytorch

Re: How Imagen Works

#15

Post by stavros » Thu, Jun 23, 2022, 5:29 PM UTC

bpiche wrote: post #14

natch wrote: post #11

> Imagen, released just last month, can generate high-quality, high-resolution images given only a description of a scene “Released”? What? Papers are published. Websites are published. Tools are “released.” Where has Imagen been released?

This implementation popped up on hacker news not too long ago. I got it working on Colab first, and then my own GPU at home. But just barely. Need more memory :) https://github.com/lucidrains/imagen-pytorch

Wait, so I can try this on Colab right now?

Re: How Imagen Works

#16

Post by refulgentis » Thu, Jun 23, 2022, 5:35 PM UTC

stavros wrote: post #15

bpiche wrote: post #14

Earlier quoted context omitted.

This implementation popped up on hacker news not too long ago. I got it working on Colab first, and then my own GPU at home. But just barely. Need more memory :) https://github.com/lucidrains/imagen-pytorch

Wait, so I can try this on Colab right now?

No, something that's been causing a lotta confusion in AI art is people stand up quick implementations generally matching the general description in the paper, but, they're not really investing in training them. Then people see "imagen-pytorch" on GitHub and get confused, either think it's Imagen itself or a suitable replica of it.

There's like 3 projects named DallE, and then the 2 real DallEs...frustrating.

Re: How Imagen Works

#17

Post by Workaccount2 » Thu, Jun 23, 2022, 5:46 PM UTC

I have shown imagen (and dalle2) to a number of people now (non-tech, just everyday friends, family, co-workers) and I have been pretty stunned by the response I get from most people:

"Meh, that's kinda cool? I guess?" or "What am I looking at?"..."Ok? So a computer made it? That seems neat"

To me I am still trying to get my jaw off the floor from 2 months ago. But the responses have been so muted and shoulder shrugging that I think either I am missing something or they are missing something. Even really drilling in, practically shaking them "DO YOU NOT UNDERSTAND THAT THIS IS A ORIGINAL IMAGE CONSTRUCTED ENTIRELY BY AN AI?!?!" and people just seem to see it as a party trick at best.

Re: How Imagen Works

#18

Post by monkeybutton » Thu, Jun 23, 2022, 5:55 PM UTC

Workaccount2 wrote: post #17

I have shown imagen (and dalle2) to a number of people now (non-tech, just everyday friends, family, co-workers) and I have been pretty stunned by the response I get from most people: "Meh, that's kinda cool? I guess?" or "What am I looking at?"..."Ok? So a computer made it? That seems neat" To me I am still trying to get my jaw off the floor from 2 months ago. But the responses have been so muted and shoulder shrugg…

Perhaps it's the combination of AI being so overhyped in the general public plus media that's already inundated with CGI, that it just doesn't blow them away?

Re: How Imagen Works

#19

Post by spullara » Thu, Jun 23, 2022, 5:55 PM UTC

refulgentis wrote: post #16

stavros wrote: post #15

Earlier quoted context omitted.

Wait, so I can try this on Colab right now?

No, something that's been causing a lotta confusion in AI art is people stand up quick implementations generally matching the general description in the paper, but, they're not really investing in training them. Then people see "imagen-pytorch" on GitHub and get confused, either think it's Imagen itself or a suitable replica of it. There's like 3 projects named DallE, and then the 2 real DallEs...frustrating.

It is a suitable replica of it. Just isn't trained.

Re: How Imagen Works

#20

Post by echelon » Thu, Jun 23, 2022, 5:56 PM UTC

bpiche wrote: post #14

natch wrote: post #11

> Imagen, released just last month, can generate high-quality, high-resolution images given only a description of a scene “Released”? What? Papers are published. Websites are published. Tools are “released.” Where has Imagen been released?

This implementation popped up on hacker news not too long ago. I got it working on Colab first, and then my own GPU at home. But just barely. Need more memory :) https://github.com/lucidrains/imagen-pytorch

Are there any large publicly available models, ready to fine tune and deploy, that were trained on massive data sets?

I really want to build services with these.