A blog related to original AI artworks. I make AI artworks using coined words and emoji as prompts.

When I let AI draw a picture of “Gerrymander”, it became “Gerrymander + Mandala”

I wondered what kind of image I could get if I gave AI (Stable Diffusion 1.5) the coined word “gerimandala”, which is a combination of “gerimander” and “mandala”. As I intended, I was able to create something that looks like a combination of a “gerrymander” image and a “mandala” image.

If you give the word Gerrymander to AI, you can draw an image of the constituency division, but if you give it a coined word gerrymandara, you can divide the image and draw a mandala.

The bottom left image is less mandala-like, but more like a color-coded map that can be given “gerrymander” to an AI (bottom right image is an example).

Gerimandala posters can be found here．

PS: The normal spelling of the mandala is mandala, but when I used the spelling gerrymandara instead of gerrymandara, only one mandala was displayed. Mandala can mean both mandala and mandara, but gerrymander can also mean gerrymandar, but gerrymandal doesnʼt make sense.

Note: This article is a revised and translated version of an article in Brog from Kanada (in Japanese).