Like the rest of the world, I've been playing around with AI generated art. In my case, I've been using Stable Diffusion UI. Stable Diffusion UI is an easy to install variation of Stable Diffusion that also includes a GUI. I was able to get it running on both Windows and Linux without too much effort. The easy install was what appealed to me the most though I have been using the GUI as well. It's been a while so I don't know how things have changed but the original version of Stable Diffusion could be a pain to get up and working sometimes.
To get reasonably fast results you need a decent GPU. However, you don't actually need a GPU at all to use Stable Diffusion UI, as long as you are willing to wait a while. If you don't have a GPU, each image will take a much longer time to produce as the CPU is much less efficient for this sort of work than a GPU. It can take thirty minutes or even much longer depending on your specific hardware and the settings you use. However, this is open source software so you can generate as many images as you want without having to sign up for anything or paying a subscription fee. The end result is that even with limited hardware, you can still produce as many images as you want as long as you are patient.
I've been generating images in a few different categories with one of them being "steampunk". Some turn out well, some don't, some are subtle in their steampunk theme, some are not. The steampunk attributes in this image are so subtle as to be non-existent. Nevertheless, I still like how the image turned out. It just isn't what I asked for. AI ignores you when it feels like it.