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

Even “Divided” or “Negated”, Kandinsky Still Inspires

I have been using various ways to prompt AI Art with the name of Kandinsky, and regardless of the approach, it produces rich images. As I mentioned in the article <"Negating Kandinsky: Unveiling Fascinating AI Art”, providing negative prompts along with positive prompts for “Kandinsky” results in diverse images. This time, I tried “dividing” the name of Kandinsky into two, such as “K_andinsky” or “Ka_ndinsky,” using Stable Diffusion 2.1. Here are some examples of the images created in this way. Although they differ from Kandinskyʼs style, they are intriguing artworks.

Here are some images obtained using “K_andinsky”: The first two images have an animalistic feel to them. In the third image, a person is depicted, but a sense of a person can also be felt in the first image.

The following images are created using “Ka_ndinsky”: These two images share a common theme of a cityscape with water.

The following image was generated using “Kand_insky”: It depicts a Building and has a unique atmosphere of a night scene.

From “Kandi_nsky,” I obtained images like the following. When using only “Kandi” for drawing, arrayed candies are depicted, but the resulting image appears to be more detailed.

As the name ends with “sky,” it often produces attractive depictions of the sky. This tendency is particularly noticeable with “Kandin_sky,” where there is a clear break before “sky.”

However, even in the images created using “Kand_insky” or “Kandinsk_y,” there is an alluring presence of the sky.