The shruggingface submission is very interesting and very instructive.
Nonetheless, it would be odd and a weak argument to point criticism towards not spending adequate «time and effort» (as if it made sense to renounce tools and work through unnecessary fatigue and wasting time). More proper criticism could be in the direction of "you can produce pleasing graphics but you may not know what you are doing".
This said, I'd say that Stable Diffusion is a milestone of a tool, incredible to have (though difficult to control). I'd also say that the results of the latest Midjourney (though quite resistant to control) are at "speechless" level. (Noting in case some had not yet checked.)
> More proper criticism could be in the direction of "you can produce pleasing graphics but you may not know what you are doing".
I don't get this. If one "can produce pleasing graphics," how does that not equal knowing what they're doing? I only see this as being true in the sense of "Sure, you can get places quickly in a car, but you don't really know how it works."
> how does that not equal knowing what they're doing
The goal may not be to produce something pleasant. The artist will want some degree of artistic value; the communicator will want a high degree of effectiveness etc. The professional will implicitly decide a large number of details, in a supposedly consistent idea of the full aim. The non professional armed with some generative AI tool may on the contrary leave a lot to randomness - and obtain a "pleasant" result, but without real involvement, without being the real author nor, largely, the actual director.
That seems untrue. In this case, the author set out with a specific goal, then tried to do it, and then succeded.
What are you suggesting, that the author lied in the blog post and actually worked backwards, post hoc? Seems incredibly unlikely based on the details they wrote.
You must have misunderstood what was intended to be expressed. I will reformulate.
"Pleasant" is not necessarily the goal. The goal may be "artistic", which implies some inner logic that the artist intends to express; the goal may be "communicative", which implies that the creator will focus on the effectiveness of the thought-structure presentation.
There is an amount of knowledge that is in the professional that may not be codified for explicit fruition in the machine. This may for example suggest that the knowledgeable author will want a very high degree of control on the output, as the details are involved in his intention - so, he will not leave much space for random randomness.
The z-movies director will shout "cut, good, keep this, next" very frequently; Kubrick will shoot scenes in dozens of takes, even over a hundred. Apprentices in music will explore; Hollis directed authentic professional musicians for very long sessions looking for specific qualities in results, and could delete entire parts for being imperfect or alien, while even excessively nice.
Perfectionist authors are demanding in all sides of creation. (And delegation, as said above, not just detail, will not be left to randomness.)
Nonetheless, it would be odd and a weak argument to point criticism towards not spending adequate «time and effort» (as if it made sense to renounce tools and work through unnecessary fatigue and wasting time). More proper criticism could be in the direction of "you can produce pleasing graphics but you may not know what you are doing".
This said, I'd say that Stable Diffusion is a milestone of a tool, incredible to have (though difficult to control). I'd also say that the results of the latest Midjourney (though quite resistant to control) are at "speechless" level. (Noting in case some had not yet checked.)