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

61–70 of 205 posts

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

#61

Post by Wistar »

_zoltan_ wrote: post #53
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?

Music composition?

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

#62

Post by wcedmisten »

Very cool! I recently made a game kind of like AI "pictionary" where the user has to guess the "artist", subject, and description of a piece of art generated by stable diffusion:

https://wcedmisten.fyi/project/paintingGuesser/

I tried to make something more general, but stable diffusion is fairly inconsistent in how well the output matches the semantics of the input.

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

#63

Post by ShamelessC »

jazzyjackson wrote: post #46
ShamelessC wrote: post #7

Earlier quoted context omitted.

> What is this list?! No Picasso, Renoir or Vrubel present Comments like this are why people think HN is nothing but a place to receive a shallow dismissal of your efforts. It's a list. Make your own.

> Comments like this are why people think HN is nothing but a place to receive a shallow dismissal of your efforts. whatever

What is this?! One word comments?!

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

#64

Post by ghusbands »

MattPalmer1086 wrote: post #44
alexmolas wrote: post #40

Nice experiment! I would only change two things: (1) sort the artists in alphabetical order, and (2) allow users to write the name of the artist and show if it's in the list. I'm saying that because it's a little bit tedious to search for the artist you're looking for. A part from that, I find the idea super-interesting :)

They are in alphabetical order, but by last name. Took me a while to see that though.

Though with names like "de Hooch" under "d" and names like "van Gogh" under "v".

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

#65

Post by the_only_law »

ShamelessC wrote: post #63
jazzyjackson wrote: post #46

Earlier quoted context omitted.

> Comments like this are why people think HN is nothing but a place to receive a shallow dismissal of your efforts. whatever

What is this?! One word comments?!

Yes, it’s been like this for a while.

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

#66

Post by matthewfcarlson »

wcedmisten wrote: post #62

Very cool! I recently made a game kind of like AI "pictionary" where the user has to guess the "artist", subject, and description of a piece of art generated by stable diffusion: https://wcedmisten.fyi/project/paintingGuesser/ I tried to make something more general, but stable diffusion is fairly inconsistent in how well the output matches the semantics of the input.

This is really awesome

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

#67

Post by krumbie »

What's kind of crazy is how the images tend to have similarities in small features that become very apparent when flipping back and forth between images, but which are not obvious per se.

For example, I flipped back and forth between Beatrix Potter and Paulus Potter. A rounded white bonnet in one picture becomes a couple of blossoms in the other. The roof of a house becomes some shadowy wall with plants in the other. Two flower pots are very similar, just with slightly different coloring.

It makes it more apparent that the algorithm etches the images out of noise, and if the seed is the same for two images with different prompts, you're likely to see traces of that noise represented differently but recognizable in both images.

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

#68

Post by nopenopenopeno »

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…

I am a filmmaker and most films are essentially crafted this way. Beyond hiring and securing resources, directors essentially create by communicating ideas in short prompts because there isn’t enough time to do anything more.

I could absolutely see an AI model doing the job of an entire film crew. I have issues with this, but only with respect to the longer term aggregate affects on culture in the broad sense. I cannot honestly believe that much would be lost from the perspective of one project or another.

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

#70

Post by ForRealsies »

wcedmisten wrote: post #62

Very cool! I recently made a game kind of like AI "pictionary" where the user has to guess the "artist", subject, and description of a piece of art generated by stable diffusion: https://wcedmisten.fyi/project/paintingGuesser/ I tried to make something more general, but stable diffusion is fairly inconsistent in how well the output matches the semantics of the input.

No post body was provided.
Post reply on HN