This post-apocalyptic, cyberpunk style image used my brain’s fMRI scan to inspire the face with red eyes and cables running along its hairless head. The lone person beneath it seems tired or defeated. It makes me think of a nightmare and choking on smoke or smog. Yet, there is that one bright light in the upper right that gives hope to an otherwise desolate scene. It was created with Stable Diffusion, A1111, and controlnet.
I used controlnet in A1111 to feature an fMRI scan of my brain in this image that I call, Mind Manifesting Mind. In all of the images that I create using Stable Diffusion that feature a brain, I use screenshots of my brain’s fMRI scan that I created using Osirix for MacOS some years ago.
One of my favorite kinds of images to create with Stable Diffusion are those involving anthropomorphic cats. Here’s a cat as an astronaut aboard the International Space Station. It required a lot of inpainting for the star field and the Earth’s curvature. SD 1.5 models often have trouble with keeping track of a line, of say a table or in this case a celestial object, bisected by a foreground subject. The final image here isn’t perfect but it was as good enough for me.
For the next few weeks, I’m going to be sharing some of the images that I have created using Stable Diffusion, an opensource generative AI text-to-image model created by Stability.AI. Today begins the series with images based on a classic video game.
Later, I took another stab at transforming the gameplay screenshot to a high resolution version. This time, I used controlnet to create the moon buggy based on the Alvis Stalwart. With inpainting, I was able to achieve great detail and lighting on the buildings.
Wouldn’t it be cool to see a new Moon Patrol game with high resolution graphics and ray tracing? Layer on backstory, mythos, and a brooding protagonist and it could be the next Halo series!