Vampire Queen #2

Like seemingly everybody else on the planet, I've started playing around with AI generated art. In my case, I downloaded Stable Diffusion UI and have been playing around with that. In particular, Stable Diffusion UI is an easy to install variation of Stable Diffusion that also includes a GUI. I was able to get running on both Windows and Linux with minimal effort. I believe the baseline version of Stable Diffusion is command line only so this is a nice option for those that prefer a GUI. I've been using the GUI but the real appeal to me of this version was the fact that it was very easy to install.

Stable Diffusion UI seems to work, within limits, on nVidia GPUs with 4MB or more. Minimum requirements are listed as being higher than that but with some minor adjustments it seems to work pretty well. You don't technically even need a GPU to use Stable Diffusion UI. It's just that if you don't have one and use only the CPU, each image will take 30 minutes or more to produce (depending on how fast your CPU is, the settings you use, and various other factors). However, this is open source software so you can generate as many images as you want for free. So even with limited hardware, you can still produce unlimited images as long as you are patient.

This particular image, like the last one I posted, was generated with a prompt involving a vampire queen. Like the last one, it's quite creepy looking which is what I like to see in a vampire. What makes this one extra creepy also demonstrates one of the current deficiencies in AI art and that is hands. AI just isn't that good at hands (though human artists struggle with hands also). I mean, what is that one hand on the bottom even attached to? These problems can (sometimes) be resolved with additional prompting or by editing from a real (human) artist. Which brought to mind a funny meme I saw recently (not mine):