A creative director and an AI created this comic together

Filled with startlingly evocative color and monochrome panels, Summer Island is a tribute to decades of fantasy movies, TV series and comic books. But it also reflects the current state of the art and offers glimpses of what humans and machines can achieve together.

The work draws palpable power from its deliberately derivative narrative. These are things we’ve seen before, in other media – things some of us love, which have inspired countless sequels, links and scams. Coulson skillfully mixes, remixes and shapes the source materials into something instantly familiar yet compelling on his own terms.

Below is Coulson, whose Campfire work includes projects like Amazon Prime Radio Resistance and HBO Westworld experience– explains how Summer Island came together. He notes that the story’s fiery conclusion, taken directly from Wicker Man, can be read as a parable for the human versus AI debate. (That’s more a nod to the inevitability of change in our evolving media sphere than a grim prediction. We hope.)

Muse: Your main character is a photographer. Why did you make this choice?

Steve Coulson: I have a college degree in film and photography, and worked as a cinematographer for a few years, so telling visual stories is part of my DNA. If you read the comic, you’ll see it was inspired by a “photo essay” I first created with Midjourney. It’s actually much easier to get a very realistic “photograph” from the AI ​​than a defined, consistent cartoon style.

What are your favorite comics?

I’m from the UK, and this style of black and white comics was pretty common in the 70s with Dr. Who, Gerry Anderson [comic adaptations] and 2000 AD. As the story itself is set in the early 70s, that seemed like a good style.

One of the keys to total immersion is authenticity. Which often means you have to think like a forger rather than a creative director. So it wasn’t so much an attempt to create a comic as to to forge a. Could I use artificial intelligence to create something that looks and reads like a traditional comic book? And the answer, I think, is “close enough”.

Well, “falsifier” has negative connotations, especially for AI

There’s a big debate to be had about the ethics of a system that has ingested all the works of living and dead artists and can spit out a convincing simulation on demand. What does this mean for traditional artists and illustrators and their livelihoods? What is Midjourney’s obligation to them while serving a community that fully embraces and works with the future? So, the story speaks – spoiler! – of a small isolated community that worships a monster and sacrifices a professional photographer to feed it.

Can you describe the workflow?

All images were created from written prompts, with no photo references. Midjourney can spit out a cover page in a minute like the world’s fastest art forger, and gladly generates 100 alternatives on demand. When you have this kind of tool, it changes the way you think about a story. It sounds a bit more like improvisational jazz, with a looping call and response. The story kept changing as I wrote it because each image the system created inspired me in new directions.

Can you give me an example?

To be honest, the engine I used for the BD has already been upgraded to a higher version. Technology is improving exponentially right now, so every two to three weeks there’s a big leap. Here’s a panel I just generated for a possible follow-up story: