The 2023 Microsoft Work Pattern Index report, “Will AI Repair Work?,” landed simply weeks after the launch of Bing Picture Creator, a brand new design device powered by a complicated model of DALL-E. When it got here to creating artwork for the report, the staff noticed a singular alternative to discover how a human artist would incorporate it into their course of. Would it not assist generate concepts? What prompts could be only? And the way would utilizing AI as a co-collaborator impression the ultimate product?

The artist for the job: Los Angeles-based Jon Han. Han makes a speciality of creating thrilling futuristic worlds with out the same old dystopian tropes. As a result of the report knowledge confirmed that most individuals are anticipating AI to assist ease the burden of labor, his model felt like precisely the correct strategy to carry the findings of the WTI report back to life.

Jon began by feeding prompts into Bing Picture Creator, testing how he might collaborate with it. Utilizing AI impressed a extra iterative strategy than what’s typical, as a result of enjoying round with it was fast and straightforward. “The method for this challenge was an experimental one,” he says. “Simply attempting to see what it’s able to.”

Right here, Han takes us inside that course of.

Jon Han: In my normal course of, I learn a inventive temporary, take into consideration the idea and visualize it in my head. So within the early stage right here, I needed to see how the device works with concepting concepts, and distinction that with my normal course of. I needed to see how the picture creator would visualize what I’m pondering.

You’ll be able to see that the device is utilizing a number of photo-reference photos, however usually my work is just not as stiff—it’s extra summary. So I began attempting to push it to go to the specifics that I used to be in search of visually.

Jon Han: Right here I shifted away from bridges and tried to push for a extra summary picture and a digital impact. I appreciated the shapes of the panels and the digital really feel. Nevertheless it seemed an excessive amount of like a sci-fi film. I wanted a happier temper.

Jon Han: This time, I added in ‘lush panorama,’ which made the picture extra atmospheric, not so darkish and digital. However the temperature of the image was slightly too cool. I put within the phrase “heat,” and it got here out like every part was on hearth. Very similar to some other device, like Photoshop or oil portray software program, there’s tips to some of these things, the place sure prompts create sure kinds of photos. So there’s a studying curve to determining easy methods to do these minor changes to get the specifics you need.

Jon Han: This time I added my title to the immediate to see if it might have the ability to reference my specific model based mostly on my printed illustrations. Including my title made the particular person smaller and received the correct viewpoint, seeing the particular person from the again. I do a number of compositions the place I do a small determine in a panorama. Nevertheless it didn’t really feel hyper-referenced to my work, in order that was good.

There are a number of blended emotions amongst artists on AI-generated photos, issues whether or not these techniques may very well be referencing artists’ work with out copyright. I attempted to steer away from something that appears like an artist I do know. However one factor about this device, in comparison with different AI instruments I’ve tried, is that it didn’t seem to be it was referencing somebody’s work. This was an excellent endpoint for the concepting stage.

Jon Han: After these rounds of experimentation I had a transparent picture in my head of what I needed, so I created this idea sketch by hand. The entire image I needed to create was too advanced to speak to the picture creator. So reasonably than carry AI-generated photos instantly into this sketch, I made a decision to make use of the device [or the AI] in later phases to generate choices for specific parts of the illustration, like bushes or sky.

Usually, you would possibly do an web seek for images of issues like that, for reference. An artwork instructor as soon as taught me: by no means use the primary few photos from an web search as your reference, as a result of everybody’s going to make use of these. So with the picture creator, it’s good that these are going to be generated a special means.

Jon Han: Earlier than creating the full-color illustration, I used the picture creator to check completely different sky colours. I additionally tried pixelated bushes and wireframe bushes, in search of one thing attention-grabbing that doesn’t have an excessive amount of of an AI really feel to it. This was all experimentation, discovering limitations, and experiments with management.

---

Han says that for lots of people, AI picture creators are “form of like a shock field.” In his expertise, they’re most helpful while you don’t know precisely what you need. In a case the place a creator already has the picture they need of their head, a picture generator will be good for iterating particular parts.

We’re solely simply starting to see how next-generation AI can match into the inventive course of, and it’ll definitely look completely different for each artist and creator. From the prompts individuals use to information the instruments to the diploma that AI does—or doesn’t—affect the ultimate product, every part is up for exploration.