Things started to get more interesting when I realized I was an early adapter for durer.ai (renamed exactly.ai). I had access to model creation using my own images. This enabled me to develop a “signature look”, and ownership of the images.

I used images I had previously created with ai and photos of my artwork to train models. This better aligned my ai iteration to my imagined ideas… sometimes. Much of what is generated is not up to snuff, but the impact of using my own artwork and the element of random generation has led to new veins of thought.

Image generated with durer.ai (now exactly.ai)

Screenshot of durer.ai model creation page and images used to create the model. Images generated with durer.ai- now exactly.ai, stable diffusion 2.1, ai craiyon, dream.ai, and photos of my then recent ceramic work (positioned sideways)

ai image generation: a journey

I became intrigued with ai image generation as a way to quickly iterate ideas and concepts. This was one of my first “successful” generations from stable diffusion 2.1. At this point I’ve generated many images from a number of image generators. I’ve used the free versions, and no images I have generated have been sourced from other artists. Though there is controversy surrounding it, to me, ai is a useful and powerful new tool for artists, just as the computer was when it became available. This blog was created to share a glimpse of my ai project journey. The work I create influences the ai images I generate and vice versa in an ongoing dialogue.