JOSH’S MIDJOURNEY (11)

By: Joshua Glenn
December 19, 2022

HILOBROW’s Josh Glenn has been experimenting, recently, with Midjourney, an AI-generated art-making tool. We are pleased to share with you a few Josh-prompted MJ creations.

WTF

Some MJ results are bonkers — in a good way. I wonder whether, as these programs continue to learn, they’ll gradually cease to produce such surrealistic marvels unless prompted to do so?

There’s also something disturbing to me, about the images — in this post in particular, but across the entire series too. When you’re monkeying around with Midjourney, you quickly realize that to an artificial intelligence, everything in the material world is… fungible. If you ask Midjourney to produce a picture of a woman on a horse being pursued by wolves, it might do just that — but it might also produce a creature that is part-woman, part-horse, and part-wolf.

Sure, we can train an AI to pretend that the various distinctions we humans take for granted are real and crucial, but at the end of the day an AI is — like a Radium Age superman — entirely indifferent to our petty concerns, and to nitpicking distinctions such as self/other and human/inhuman.

“1950s political campaign poster for Brainy Smurf” (8/17/22). Click for larger version.

“Thor eating a banana” (8/12/22). Click for larger version.

“Cowboy shooting at coin thrown into the air” (8/8/22). Click for larger version.

“1960s paperback crime novel – John Lennon holding a pistol” (7/29/22). Click for closer view.

“Hercules playing Wii Tennis – marble Greek statue, realistic, full length, full body frontal shot, realistic, colourful, epic, cinematic lighting, character, immense, epic pose” (9/12/22). Click for closer view.

“1960s newspaper comic strip by Edward Gorey” (10/20/22). Click for larger version.

“Beatles in 19th century Vienna” (10/3/22). Click for larger version.

Here’s another take on Midjourney-generated “art,” from Michael Sacasas’s newsletter THE CONVIVIAL SOCIETY. (Thanks, Matt B., for sending it.)

I was taken in by [a particular Midjourney] image, which struck me as evocative and intriguing. But as I came back to the image and sat with it for a while, I found that my efforts to engage it at depth were thwarted. This happened when I began to inspect the image more closely. As I did so, my experience of the image began to devolve rather than deepen. When taken whole and at a glance, the image invited closer consideration, but it did not ultimately sustain or reward such attention.

This is not only because the image appeared to fail in some technical sense — hands, for example, seem to give these models trouble — it is that these errors, aberrations, or incongruities are, in a literal sense, insignificant — they signify nothing. They may startle or surprise, which is something, but they do not then go on to capitalize on that initial surprise to lead me on to some deeper insight or aesthetic experience.

Sacasas also quotes a recent Dan Cohen essay on “Humane Ingenuity.” Whereas “true art,” Cohen says, is “resistant to easy consumption, and rewards repeated encounters,” the desire of AI tools “to meet expectations, to align with genres and familiar usage as their machine-learning array informs pixels and characters, is in tension with the human ability to coax new perspectives and meaning from the unusual, unique lives we each live.”

Yes, I think this stuff is spot-on. I’d only add — circling back to my comments above — that the deeper insight and new perspective that I do get from contemplating such images is a chilling one, regarding AI’s inhumanity — it’s “vast and cool and unsympathetic” alien-ness, to quote Wells. Brr!

“Super Mario mosh pit” (11/8/22). Click for larger version.

“George Herriman three panel comic strip” (9/5/22). Click for larger version.

“Totoro collage by Hannah Hoch” (9/19/22). Click for larger version.

“Little Orphan Annie six panel comic strip” (9/22/22). Click for larger version.

***

JOSH’S MIDJOURNEY (11)

Categories

Tags