You might expect a comic book series with art created entirely by artificial intelligence to be filled with surreal images that make you tilt your head and try to comprehend what sense-altering insanity you’re looking at.
Not so with the images in The Bestiary Chronicles, a free four-part comic book series from Campfire Entertainment, a New York-based production company focused on creative storytelling.
The visuals in the comic book series, which is believed to be the first to be created using artificial intelligence art, are stunning. They are also amazingly accurate, as if they came directly from the hands of a skilled digital artist with a very specific story and style.
“Deep underground, the last remnants of humanity gather to learn about the monsters that destroyed their planet,” reads the description of The Lesson, the visually rich retro-futuristic third comic in the four-part series. All four are now available for download on the Campfire site and also come in paperback and hardcover anthologies.
While AI-generated visual art can veer toward the wildly absurd, the photorealistic humans in Bestiary Chronicles don’t have rearranged facial features or limbs sticking out at odd angles. The monsters – with their glowing eyes and amazingly bad teeth – look like the love children of Godzilla and Vhagar, and could hardly be mistaken for anything other than ferocious beasts.
The algorithm-assisted art looks tailor-made for a dark dystopian story that draws on tropes from the 1960 sci-fi horror film Village of the Damned and from THX 1138, George Lucas’ 1971 feature debut.
“We’re seeing the rise of a brand new visualization tool that will radically change the storytelling process in the comics industry and entertainment in general,” said Steve Coulson, series writer and creative director of the award-winning Campfire, which has created immersive fan experiences for shows including Ted Las, Westworld and Watchmen. Its founders came up with The Blair Witch Project.
For The Bestiary Chronicles, Coulson turned to Midjourney, a service that quickly turns short text phrases, or “prompts,” into images by scanning a giant database that people have trained into visual art. Similar artificial intelligence tools, Dall-E and Stable diffusions are capture the internet’s imagination because they allow anyone to manifest images from text in interesting and sometimes disturbing ways.
Bestiary Chronicles is a sci-fi odyssey about monsters born of human technological arrogance. But it also shows the remarkable progress of products like the Midjourney, which create increasingly sophisticated and refined images.
“By the new year, even the trained eye probably won’t be able to discern one generation of AI from any other,” Coulson said. “It’s exciting and scary at the same time. But you can’t put the genie back in the bottle, so we’re embracing the future as fast as we can.”
The AI image generation is progressing so quickly, he adds, that The Lesson, released on November 1, marks a clear visual step forward from the first comic in the trilogy, Summer Island, a folk horror story in spirit Midsummer which came out in August. During those three months, Midjourney went through two upgrades.
AI, partner in art
“Technology is changing our world, with artificial intelligence representing a new frontier of possibility, but also an anxious development,” said Thomas P. Campbell, director and CEO of the Fine Arts Museums of San Francisco. exhibition Uncanny Valley: Being Human in the Age of AI opened in 2020 to explore the ever-expanding space where humans and artificial intelligence meet.
AI generating visual art, songwriting and and writing poetry and film scripts are causing some anxiety and ethical and copyright concerns among artists and even lawyers. The art of artificial intelligence is not created in a vacuum. It works by absorbing and reconstructing existing human-made art. As machine-made art improves, will these people—actual graphic designers, illustrators, composers, and photographers—find themselves out of work?
When an AI-generated image won an art prize in September, some artists were not happy. “We are watching the death of art unfold right before our eyes,” wrote one Twitter user.
An avid comic reader since age 5, Coulson is among those who ponder the complex questions raised by AI art, but he doesn’t think tools like Midjourney will replace the comic artists he’s long loved. “These geniuses have an eye for dramatic composition and dynamic storytelling that I highly doubt machine learning can match,” he writes in the afterword to Summer Island. “But as a visualization tool for a non-artist like me, it’s pretty darn fun.
However, he sees Midjourney as his true collaborator on Bestiary Chronicles, even giving him author credit. Where a comic artist might come up with a story and then create art to illustrate it, AI-assisted images have the potential to more actively drive the story or even change its direction, dramatically redefining the entire creative workflow. Coulson compares this man-machine duet to improvised jazz.
“I would never ask a human artist to just ‘draw 100 splash pages and maybe pick the one I like best,’ but Midjourney will happily spit them out 24/7,” Coulson said. “After we review the images, we begin to piece together the story, almost like an act of collage, filling in the gaps.”
AI is the main star here, but humans had a say in what images made it into the final version of each story. They experimented with text prompts and carefully selected their final images from several of Midjourney’s offerings, doing a Photoshop tweak here and there, but mostly letting the machine-made work stand.
For example, the Campfire team liked the rich effect created by the style challenge “olive green and sepia and teal tritone print on watercolor paper”, so they often used it to give images a painterly effect. For The Lesson, the phrase “JC Leyendecker-esque futuristic underground bunker” made for the perfect retro-futuristic post-apocalyptic hideout.
“We also used the phrase ‘Hitchcock Blonde’ to describe our heroine, and more often than not she looked like Grace Kelly,” Coulson said. This is a fully recognizable Grace Kelly, minus the misplaced ears or dog snout.
“The advances in AI image generation over the past few months have been exponential and astounding,” Coulson said, “and the technology will only get better – faster than we can imagine.”