Live data from Hacker News

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

gorgeous.adityashankar.xyz

201–205 of 205 posts

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

#201
post #191
post #165

I lecture in painting, and to me some of these are truly impressive. Not surprisingly, those artists is not predominantly painting (e.g. Josph Beuys) or is predominantly linear (Audrey Beardly) do not fare so well. There is a lot of talk in our department as to how we might prepare our students for this technology. It is scary how fast it is growing, and how it is spreading to things like 3D and texturing. One of my…

I'd be interested in hearing your take because you are actively involved in this field. From my perspective outside of it, it seems that it's going to be an absolute bloodbath in terms of opportunities for people to actually live as artists (excluding those who work in mediums that can't be represented on a 2D screen).

Yep. A bloodbath is certainly on its way. Our illustration program will be first in the figuring line.

We think that there may be some room for our students as 'high class' art directors. What will give them unique merit is their deep knowledge of pictorial formalities. Anyone can give the text hint 'flowers in a vase'. But what about...

'Move the camera down to avoid the strong coincidence line between the edge of the vase and the edge of the table. Change the saturation value of the vase to emphasize background/foreground contrast. Increase the amount of negative spaces around the periphery of the flower mass' etc.

Tek like Stable Diffuse may also lead to a resurgence of interest in natural media, like oil paint, water colour and suchlike.

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

#202
post #201
post #191

Earlier quoted context omitted.

I'd be interested in hearing your take because you are actively involved in this field. From my perspective outside of it, it seems that it's going to be an absolute bloodbath in terms of opportunities for people to actually live as artists (excluding those who work in mediums that can't be represented on a 2D screen).

Yep. A bloodbath is certainly on its way. Our illustration program will be first in the figuring line. We think that there may be some room for our students as 'high class' art directors. What will give them unique merit is their deep knowledge of pictorial formalities. Anyone can give the text hint 'flowers in a vase'. But what about... 'Move the camera down to avoid the strong coincidence line between the edge of t…

I suspect that we'll end up with a split similar to amateur and professional photography, with generative models for the latter trained not on plain English but on something much more stringently structured, with ability to unambiguously specify many important but non-trivial parameters in the prompt, including for specific well-defined areas of the output etc. Probably with a GUI on top where you can literally highlight specific objects etc and adjust parameters, and it'll construct the query for the next iteration.

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

#203
post #115

Earlier quoted context omitted.

Whatever else this emergent "creative AI" phenomenon may or may not do, it's definitely touching nerves in people who still believe there's something ineffable and transcendent about the creative experience.

Stable Diffusion is literally copy-pasting existing artwork. It's not creating anything new. If anything, this sort of "AI" only makes human ineffable creative experiences even more valuable, because without it there would be no training set and no "AI".

The training set for human artists is the entirety of human art that they have been exposed to in their lifetime, even accidentally.

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

#204
post #61

Earlier quoted context omitted.

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

Music composition?

I fail to see why that would be more beneficial than to generate art.
Post reply on HN