Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How a Stable Diffusion prompt changes its output for the style of 1500 artists

gorgeous.adityashankar.xyz

Post reply on HN
Print view View original

51–60 of 205 posts

Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists

#51

Post by marginalia_nu »

yieldcrv wrote: post #17
norwalkbear wrote: post #6

Truly impressive, though it gives me some great fear for all the people whose career is art. This will likely take the pareto to a new height instead of 20/80 maybe even 1/99

Their career isn't art anymore. Just in case anyone needed to see this spelled out. The people making fliers have been replaced by AI prompting overnight. The people doing contemporary fine art with their audience are unaffected.

> The people doing contemporary fine art with their audience are unaffected.

It's not a particularly well hidden secret that the contemporary fine art is really not about the art or the artist.

https://www.youtube.com/watch?v=ZZ3F3zWiEmc

Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists

#53

Post by _zoltan_ »

logisticpeach wrote: post #49

Hate to say it but when i see stuff like this it only reminds me of what we could have achieved if this ingenuity had been applied in another domain. Can't help feeling that this accidentally harms creative types and risks swamping us with visual junk. The technical achievment is astounding but no-one would seriously claim that crafting an image via a short prompt is creative except in the most cursory way. I'm proba…

what other domain would you suggest which requires roughly the same skill set?

Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists

#54

Post by victor9000 »

logisticpeach wrote: post #49

Hate to say it but when i see stuff like this it only reminds me of what we could have achieved if this ingenuity had been applied in another domain. Can't help feeling that this accidentally harms creative types and risks swamping us with visual junk. The technical achievment is astounding but no-one would seriously claim that crafting an image via a short prompt is creative except in the most cursory way. I'm proba…

Well, robots have been better than humans at playing chess for decades now, and we still have chess players.

Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists

#55

Post by novok »

jhbadger wrote: post #25

What frustrates me about Stable Diffusion is there doesn't seem to be any documentation as to what artists or vocabulary it understands. Generally people say "look at existing prompts or use various prompt generators" but that doesn't really solve the problem. I don't want to just look at what other people have randomly discovered; I want to know what the program really knows.

You can by searching the training image set and their text tags essentially.

https://laion-aesthetic.datasette.io/laion-aesthetic-6pls/im...

Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists

#56

Post by the8472 »

smoldesu wrote: post #37
jhbadger wrote: post #25

What frustrates me about Stable Diffusion is there doesn't seem to be any documentation as to what artists or vocabulary it understands. Generally people say "look at existing prompts or use various prompt generators" but that doesn't really solve the problem. I don't want to just look at what other people have randomly discovered; I want to know what the program really knows.

You can't really debug an AI. The dimensions of it's understanding are quite literally beyond human interpretation, which makes it both smarter/more efficient than humans while also extremely dumb and context-unaware. Most of our attempts at adding a 'memory' to AI has been a hack thus far, which is why all of these prompts consist of people force-feeding word salad down the AI's throat for generally reproducible res…

They're debuggable, with effort. Here's the finance neuron in CLIP: https://microscope.openai.com/models/contrastive_4x/image_bl...

Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists

#57

Post by soulofmischief »

logisticpeach wrote: post #49

Hate to say it but when i see stuff like this it only reminds me of what we could have achieved if this ingenuity had been applied in another domain. Can't help feeling that this accidentally harms creative types and risks swamping us with visual junk. The technical achievment is astounding but no-one would seriously claim that crafting an image via a short prompt is creative except in the most cursory way. I'm proba…

People said this about cameras. About digital cameras. About digital photo editing software. The next generation will normalize these tools and find incredible ways to be creative within their new cutting edge medium.

The post-art world is here! Just think about how history books will remember this period! The styles that will be borne of necessity, of the need to break down art and find what makes it tick.

Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists

#58

Post by etrautmann »

soulofmischief wrote: post #57
logisticpeach wrote: post #49

Hate to say it but when i see stuff like this it only reminds me of what we could have achieved if this ingenuity had been applied in another domain. Can't help feeling that this accidentally harms creative types and risks swamping us with visual junk. The technical achievment is astounding but no-one would seriously claim that crafting an image via a short prompt is creative except in the most cursory way. I'm proba…

People said this about cameras. About digital cameras. About digital photo editing software. The next generation will normalize these tools and find incredible ways to be creative within their new cutting edge medium. The post-art world is here! Just think about how history books will remember this period! The styles that will be borne of necessity, of the need to break down art and find what makes it tick.

Yep, I see this as a start, and very curious to see the ways in which it’ll get used with a human in the loop, and also the ways human artists will be pushed to creat art that’s out of distribution for these models.

Re: How a Stable Diffusion prompt changes its output for the style of 1500 artists

#59

Post by sdenton4 »

smoldesu wrote: post #37
jhbadger wrote: post #25

What frustrates me about Stable Diffusion is there doesn't seem to be any documentation as to what artists or vocabulary it understands. Generally people say "look at existing prompts or use various prompt generators" but that doesn't really solve the problem. I don't want to just look at what other people have randomly discovered; I want to know what the program really knows.

You can't really debug an AI. The dimensions of it's understanding are quite literally beyond human interpretation, which makes it both smarter/more efficient than humans while also extremely dumb and context-unaware. Most of our attempts at adding a 'memory' to AI has been a hack thus far, which is why all of these prompts consist of people force-feeding word salad down the AI's throat for generally reproducible res…

For memory, check out:

1) Retro, which is essentially attention over large databases, and fast as hell.

2) S4 Layers, explicitly designed for handling long dependencies.

These are orthogonal approaches to memory, and both very effective at what they do.

Post reply on HN