Re:Illustrating Gutenberg library using Stable Diffusion
by frameset on Sunday September 04, 2022 @11:55AM
(#32714337)
If I was a commercial artist doing illustration work for articles or the like, I'd be getting worried about now.
[ Parent
| on HN ]
Re:Illustrating Gutenberg library using Stable Diffusion
by iamflimflam1 on Sunday September 04, 2022 @12:20PM
(#32714639)
I’ve been using midjourney to add a bunch of images to a conference talk I’m doing. It’s great for “ambience” type pictures, but hopeless if you actually want to represent anything concrete.
Re:Illustrating Gutenberg library using Stable Diffusion
by shredprez on Sunday September 04, 2022 @12:33PM
(#32714788)
It's definitely possible to get concrete representation out of DALL•E, although it takes some experimentation to achieve realism within the constraints of the tech today. Still, we're not far off at all from indistinguishable synth imagery.
Some generated work in a photographic style: — https://www.hearthe.art/ — https://objkt.com/profile/heartheart/created
Re:Illustrating Gutenberg library using Stable Diffusion
by rahimnathwani on Sunday September 04, 2022 @12:24PM
(#32714694)
You can use Stable Diffusion to make more specific compositions, but you usually need multiple steps and a little bit of manual editing.
Re:Illustrating Gutenberg library using Stable Diffusion
by odessacubbage on Sunday September 04, 2022 @12:54PM
(#32715057)
i think people underestimate just how many commercial images effectively fall within the 'ambience' category.
i'm really convinced that in the mid to longterm, the only viable future for human artists will be a matter of GANs being subjected to the same sort of social stigma that is attached to other forms of highly economically lucrative, but morally dubious practices like child labour. ultimately sustaining a living in art has always been a matter of convincing the layman that what we produce has value and this will be the same at scale. if society does not value human-made art, there wont be any.
Re:Illustrating Gutenberg library using Stable Diffusion
by egypturnash on Sunday September 04, 2022 @12:52PM
(#32715030)
I am a professional artist and I am worried.
Re:Illustrating Gutenberg library using Stable Diffusion
by dehrmann on Sunday September 04, 2022 @01:00PM
(#32715137)
It feels like self-driving cars and the 80/20 rule; it'll be impressively good but not ready for prime time for a decade.
Re:Illustrating Gutenberg library using Stable Diffusion
by trention on Sunday September 04, 2022 @01:56PM
(#32715734)
Self-driving cars have already been not ready for prime time for 15 years and they have at least 5 more years in this state.
Re:Illustrating Gutenberg library using Stable Diffusion
by usrusr on Sunday September 04, 2022 @02:38PM
(#32716250)
But self-driving cars have a serious good enough threshold that isn't remotely as life-or-death for illustration
Re:Illustrating Gutenberg library using Stable Diffusion
by barrysteve on Sunday September 04, 2022 @02:40PM
(#32716282)
Playin devil's avocado here. SD sucks at depth. It makes 3D images which should have well set perspective, look flat and uninspired. Tastes will change and people will want to move away from the "tiny rooms, flat images and only-faces" trend that's dominating art at the moment. SD will ride the wave.
Until tastes change and after the current youth generation driving the demand for this washes out, it'll probably suck to be an artist without a strong brand.