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

Stable Diffusion is a big deal

simonwillison.net

Post reply on HN
Print view View original

131–140 of 488 posts

Re: Stable Diffusion is a big deal

#131

Post by akomtu »

phillipcarter wrote: post #87

I'm not really sure I know how to use these tools. I tried the following prompt: "elon musk giving donald trump a massage using pizza sauce instead of oil, in a majestic room filled with flowers and golden toilets" ...and the result was a crappy AI-generated picture of not-quite donald trump holding a terrible rendering of a pizza, and some hands sticking out of random places. There were some red flowers in the pictu…

"some hands sticking out of random places"

That's the absense of reason sticking out: the "ai" mimics, but doesnt understand, so its creations are frankenstein-like bodies, almost human and for this reason more revulsing. So this "ai" represents an insane painter.

Re: Stable Diffusion is a big deal

#132

Post by simonebrunozzi »

thot_experiment wrote: post #2

Maybe this current explosion in the relevance and visibility of this kind of AI model will finally lead us to rethink how insanely nonsensical our IP systems are. I'm not holding my breath, but there's hope that this sort of thing will (combined with situations like the HBO debacle) clarify the need for massive IP reform in the cultural zeitgeist. The problem here isn't that the model was trained on copyrighted works…

Can you summarize what’s the HBO debacle?

Re: Stable Diffusion is a big deal

#133

Post by lulwhatyouex »

>You can use it for commercial and non-commercial purposes, under the terms of the Creative ML OpenRAIL-M license—which lists some usage restrictions that include avoiding using it to break applicable laws, generate false information, discriminate against individuals or provide medical advice.

What I'm going to do is take all those new image-generation AIs, and use them to train an image-generation-AIs-generation AI, this way I won't be bound by copyright anymore.

Re: Stable Diffusion is a big deal

#134

Post by usgroup »

fragmede wrote: post #105
usgroup wrote: post #97

I've been trying to get it to draw a picture of a man trapped inside of a light bulb. Can anyone think of a prompt that works? It draws all sorts of freaky things featuring men and light bulbs but none with the former inside the latter.

Best I got was https://imgur.com/a/g9XcB2a

thank you -- that's something I guess.

Re: Stable Diffusion is a big deal

#135

Post by dogcomplex »

stocknoob wrote: post #103
abhisuri97 wrote: post #67

I’m more trying to see what the utility of stable diffusion (or just the text to image problem) in the long term. Right now people can play around with making weird art pieces and maybe it will be integrated into design tools...but then what? Eg with other AI problems out there I can see a potential application to medicine, self driving cars etc, but I just don’t see what the bigger goal of this is going to be.

Magazine illustrator, concept artist, stock photography, video game art asset creation, logo generation, interior design, fashion design, costume design, political cartoonist, caricature artist, website layout templates, font design, pixel art, book covers, children’s toy plush design, new car concept prototype…?

That's just existing industries. All the new crazy stuff it'll unlock... Custom operating system interfaces for everything based on the data they're working with, truly-open infinite video games where you can run or zoom any direction and have it write itself, bespoke lcd wallpaper customized on the fly to the person walking by, bespoke industrial design creating 3d objects (first digital, then printed) for exactly the context they're needed for merely materials cost...

Re: Stable Diffusion is a big deal

#136

Post by usgroup »

fragmede wrote: post #107
usgroup wrote: post #99

Earlier quoted context omitted.

Try "a green field with sheep on it" versus "a green field with robots on it". From a human position that feels like it should be a simple juxtaposition of objects onto a background. Clearly not so for this model.

Managed https://imgur.com/a/WwybhaI without too much fuss.

in this instance i didn't ask for an example. I was just observing that juxtaposing objects in a sentence doesnt work at all as you might reasonably expect.

Re: Stable Diffusion is a big deal

#137

Post by lulwhatyouex »

amval wrote: post #62
ryandv wrote: post #22

Quoted post unavailable.

Probably because: 1. You don't make any actual point that could lead to a constructive discussion. 2. What you are saying is not true: this model was developed in an university in Germany and sponsored by a private company. The only public founder I could find is this one: https://www.crunchbase.com/person/emad-mostaque Perhaps you should reevaluate your own biases as well.

No post body was provided.

Re: Stable Diffusion is a big deal

#138

Post by systemvoltage »

michaelchisari wrote: post #6

After using SD heavily for a week, I half agree with this. It is incredibly disruptive, and it's wild how much it accelerates the creative process. I'll give you that. But two things I've noticed: First, artists will still have a massive advantage over non-artists with this tool. A photographer who intimately knows the different lenses and cameras and industry terms will get to a representation of their idea much fas…

I always wondered if we massively overestimate human creativity. Maybe it is ingrained in our culture and our very being. I’ve never heard counter arguments that humans are not that creative.

Creativity demonstrated by Alpha zero chess engine blows Magnus Carlsen’s mind (from his recent interview with Lex Fridman), I wonder if at some point in the future, we’ll finally throw in the towel and get out of the denial phase.

Re: Stable Diffusion is a big deal

#140

Post by taneq »

michaelchisari wrote: post #14
Swizec wrote: post #10

Earlier quoted context omitted.

What about using this tech for ideation and artists for production? You could use Stable Diffusion et al to create new characters based on a prompt, then farm the concept out to artists to produce individual works. Kind of like hiring a super expensive agency to design your new logo or brand identity, then using a stable of in-house designers to translate the concept into UI, ads, etc.

That’s where it’ll be truly disruptive. SD for ideation, humanity for the final product.

It’s like that old b(if)tek song. Humans can do the repetitive labour so the machines can do the creative work.
Post reply on HN