How Imagen Works • Hacker News Board

Re: How Imagen Works

#101

Post by varispeed » Fri, Jun 24, 2022, 7:30 PM UTC

sumy23 wrote: post #86

varispeed wrote: post #32

> is trained on hundreds of millions of images and their associated captions So how do you get access to hundreds of millions of images and use them to create derivative works? Did they get consent from millions of authors? Or is something like that only available to the rich with access to lawyers on tap? I mean I can imagine if a nobody wanted to do something like this, they'd get bankrupted by having to deal with…

There are open datasets with that many image-text pairs. E.g. https://laion.ai/blog/laion-400-open-dataset/ There is even a dataset with 5 billion image-text pairs if you're feeling adventurous: https://laion.ai/blog/laion-5b/

I didn't know about this! Thank you

Re: How Imagen Works

#102

Post by astrange » Fri, Jun 24, 2022, 9:07 PM UTC

treesprite82 wrote: post #96

astrange wrote: post #75

Earlier quoted context omitted.

You can just type a request in the box if you don't particularly care what the result looks like and also don't care that some of the features might be copyrighted (since large models are quite capable of memorizing their training data.) Asking for two different images in a series that have similar "art styles" is going to be enough work to still need a specialist aka an artist; it'll be most useful in cases you neve…

> Asking for two different images in a series that have similar "art styles" is going to be enough work to still need a specialist aka an artist Running a separate style transfer network on the generated images is currently possible, although won't achieve the best possible results. I wouldn't be surprised in the near future to see generation models that can take a text prompt and an image to mimic the style of, whic…

Since “style” isn’t at the surface level, you can’t take it into account with a single input. It means whatever the client wants it to mean. Getting an AI to do what you want there is still going to be a long conversation they won’t want to do.

It might (likely will be) easier to use the AI as a storyboard generator and have your in-house artists redraw it.

Re: How Imagen Works

#103

Post by natch » Sat, Jun 25, 2022, 6:54 AM UTC

bpiche wrote: post #92

natch wrote: post #69

Earlier quoted context omitted.

"This thing" has already been trained. Nobody is saying the algorithm is not interesting. Just that "this thing" has not been released.

Yes, nobody said one way or another. I chose to shine a light on the algorithm. What’s your point?

Rather rude to ask it that way. My point is there for you to read, or miss. Up to you.

Re: How Imagen Works

#104

Post by trention » Sat, Jun 25, 2022, 1:42 PM UTC

Workaccount2 wrote: post #99

trention wrote: post #58

Earlier quoted context omitted.

If that happens, all art will simply have no value and art as % of GDP will plummet. Incidentally, this hasn't happened in areas where AI already dominates like chess and go. Magnus Carlsen alone probably generates more "revenue" than all chess AIs combined.

If there was a way to have an AI feed you moves without being caught, then I am positive Carlson wouldn't be at the top for long.

He wouldn't be at the top only if he was not using said way and his competitors were. This is of course missing the point. If chess enthusiasts knew that grandmasters were using AI to aid them when playing in tournaments, the interest (and the revenues) would simply plummet.