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 team is already using it in production. It used to take his artists three days to come up with five visual development ideas. Now he can get fifty overnight to choose from.
I agree, they are nice results. But Joseph Beuys is better known for performance art. In his most famous piece, he covered himself in gold foil, and explained art to a dead hare (below). To my mind, it makes little sense to apply this method to his art.
The Audrey Beardly results are a bit better, but if I wanted Beardly-ish drawings I would likely be disappointed. Beardly's lines were very fine... 'filigree', like a spider crawling over the paper, and he almost never made art in colour. Also, a lot of his work was as sexy as hell. NSFW last link (bottom of page) for relatively mild examples.
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.
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.
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 team is already using it in production. It used to take his artists three days to come up with five visual development ideas. Now he can get fifty overnight to choose from.