I use AI images to accompany roughly 18 to 19 out of 20 Daily-Ink posts. My general rule is that I’ll try one or two requests and pick from those. I don’t want to spend 10 or 15 minutes of my precious morning schedule to search for images, they are the side quest, my writing is the adventure.

However, it being the weekend, yesterday I had time to play… and yet I failed.

Here was my original request for my last blog post:

When that didn’t work, I got more and more detailed, even pausing the requests to ask Copilot (which uses DALL•E 3 to create images) if it knew what a waterpolo cap looked like. It described it perfectly… then I got it to reiterate my request before continuing. This is what I got:

But the caps still came out with helmet masks and at no point was the shooter facing the net. I finally gave up and cropped an image. Here is what I used, and then the full image:

Below are many of the fails. I recognize these are not common requests, and the images have some redeeming qualities, but there is still a way to go when it comes to AI text-to-image requests. So, when you see a less-than-perfect image added to my Daily-Ink posts, please recognize that I’m trying, but I’m not wasting time trying to get everything just right… I’d rather use that time to write, meditate, or exercise.