You may know Antti Karppinen for his amazing conceptual photos and photo manipulations. He’s been combining illusion with reality in his work for some time, and now he’s adding an interesting twist: artificial intelligence.
Thanks to tools like DALL-E and Midjourney, you can create an image out of just about anything you can spell. Antti was curious to see if that would be possible with his work. Being dreamy and surreal, Midjourney seemed like a logical choice – and it did a remarkably good job!
Antti tells DIYP that Midjourney doesn’t have features similar to Stable Diffusion when creating new content. However, you can feed it images as input references and then use the command prompt to direct it to generate something similar. Here are the basics on how to do it:
To recreate his work, Antti placed an image at a time as input and typed its content into AI. Midjourney returned a grid of four images, and Antti picked the best one and scaled it up. For example, he used his image and a prompt “Dolores from Westworld holding a gun, sunset canyons” for this one:
“I’ve been playing with AI for almost a year now and I’m starting to get the hang of it, even though the technology is evolving at the speed of light,” Antti writes. “Learn a new way of doing something and the next day something new pops up that catches my attention.”
“It takes about 30 seconds to a minute for Midjourney to create these images,” Antti tells DIYP. And it’s both amazing and a little worrying how quickly technology is changing. “From images to animations generated by text prompts, this industry is changing a lot of things and also revolutionizing industries,” concludes Antti. “How we create images is no longer the same.”
Check out more photos below and let Antti know which one you prefer. The real ones or the ones recreated by the AI? Be sure to check out more of his work (without the AI touch) on his website, Instagram, and Facebook.