Chapter 1: A New Medium of Imagination

Recently, I participated in a beta initiative by Midjourney, a self-identified "independent research lab exploring new forms of thought." This team has developed a tool akin to DALL·E, an algorithm that generates images based on text descriptions. Although the AI relies on a broad array of existing human-created artwork to generate visuals, it exhibits a remarkable ability to produce outputs that respond to the nuanced details users provide.

Delving into this technology, I tasked it with visualizing the opening lines of fourteen different novels. The user interface is integrated into Discord servers, allowing users to invoke the Midjourney Bot with the command /imagine, accompanied by specific parameters. There are numerous values and specifications that can guide the program in crafting the desired image. By offering minimal or extensive input, the algorithm produces four low-resolution interpretations, which can serve as a starting point for further modifications or be enhanced to a higher resolution.

For this particular project, I provided the AI with just the first sentences of the novels and instructed it to create images in a 16:9 aspect ratio. I then selected one of the initial four visuals that I felt resonated best with the text.

“When he woke in the woods in the dark and the cold of the night he’d reach out to touch the child sleeping beside him.”

— The Road, Cormac McCarthy

“Early in the morning, late in the century, Cricklewood Broadway.”

— White Teeth, Zadie Smith

“Everyone now knows how to find the meaning of life within himself.”

— The Sirens of Titan, Kurt Vonnegut

“It was a queer, sultry summer, the summer they electrocuted the Rosenbergs, and I didn’t know what I was doing in New York.”

— The Bell Jar, Sylvia Plath

“Many years later, as he faced the firing squad, Colonel Aureliano Buendía was to remember that distant afternoon when his father took him to discover ice.”

— 100 Years of Solitude, Gabriel Garcia Marquez

“There’s a person living not too far from me known as the Woman in the Purple Skirt.”

— The Woman in the Purple Skirt, Natsuko Imamura

“A screaming comes across the sky.”

— Gravity’s Rainbow, Thomas Pynchon

“She rides out of the forest alone.”

— Matrix, Lauren Groff

“We were somewhere around Barstow on the edge of the desert when the drugs began to take hold.”

— Fear and Loathing in Las Vegas, Hunter S. Thompson

“Your house glows at night like everything inside is on fire.”

— The Push, Ashley Audrain

“In my younger and more vulnerable years my father gave me some advice that I’ve been turning over in my mind ever since.”

— The Great Gatsby, F. Scott Fitzgerald

“I like to think I know what death is.”

— Sing, Unburied, Sing, Jesmyn Ward

“Far out in the uncharted backwaters of the unfashionable end of the Western Spiral arm of the Galaxy lies a small unregarded yellow sun.”

— The Hitchhiker’s Guide to the Galaxy, Douglas Adams

Through this process, I encountered a collection of striking visuals, some aligning closely with the source material, while others appeared intriguingly off-mark. The more I engaged with the program, the clearer its strengths and limitations became. Achieving optimal results requires a user’s guidance through experimentation to reach the desired effect. When grappling with abstract concepts, the AI can capture essential nouns and adjectives to create a literal representation.

Ultimately, it remains true that human creativity drives the imagination. With the vast history of art at its fingertips, AI can replicate our styles and astonish us with its complexity, but it will take time before it can replace human artists entirely. This technology currently empowers those lacking technical skills to express their artistic vision, reducing barriers while still conveying the intent behind their creations. It is indeed humbling to witness a machine accomplishing tasks once reserved for human hands.