While working on my project to create abstract depictions of human pathogenic bacteria (see here and here), some of my prompts to Stable Diffusion didn't produce an image in the style that I wanted. But they still produced something interesting. For most of them, I have no idea what part of the prompt the AI latched onto or what similar word the AI went with. There were, however, a few themes that came up often. For example, if a bacterial genus named ended in –ella, the images often featured a woman. I guess it has figured out that –ella is a feminine diminutive. It also drew a lot of flowers, birds, and insects. My guess is that the training data set had a lot of flowers, birds, and insects captioned with their scientific names.
This was supposed to be Abiotrophia.
This was supposed to be Acidovorax.
This was supposed to be Acinetobacter.
This was supposed to be Actinobacillus.
This was supposed to be Actinomadura.
This was supposed to be Actinomyces.
This was supposed to be Aerococcus.
This was supposed to be Aeromonas.
This was supposed to be Aggregatibacter.
This was supposed to be Alloscardovia.
This was supposed to be Anaeroglobus.
This was supposed to be Arcanobacterium.
This was supposed to be Atopobium.
This was supposed to be Bacteroides.
This was supposed to be Bartonella.
This was supposed to be Bergeyella.
This was supposed to be Bordetella.
This was supposed to be Borrelia.
This was supposed to be Borreliella.
This was supposed to be Brevundimonas. The AI clearly had someone in mind, but I can't figure out who it is.
This was supposed to be Brucella.
This was supposed to be Budvicia. The AI clearly went for architecture most of the time, but I'm not sure what the connection is. The plant is probably because Vicia is the genus of vetches.
This was supposed to be Burkholderia.
This was supposed to be Campylobacter.
This was supposed to be Catabacter. I think we can all tell what part of the name the AI fixated on in this case.
This was supposed to be Cedecea.
The prompt for these was Chlamydiella. This is not a real bacterial genus (though someday it could be). I confused it with the real bacterial genus, Chlamydophila.
This was supposed to be Chlamydophila.
This was supposed to be Chryseobacterium.
This was supposed to be Citrobacter.
This was supposed to be Corynebacterium.
This was supposed to be Coxiella.
This was supposed to be Delftia.
This was supposed to be Dermabacter.
This was supposed to be Dermacoccus. Spirits? Perfume? Something along those lines.
This was supposed to be Dysgonomonas.
This was supposed to be Edwardsiella.
This was supposed to be Eggerthella. Sometimes, but not always, the AI thought about an egg when creating the image.
This was supposed to be Ehrlichia.
This was supposed to be Eikenella.
This was supposed to be Elizabethkingia. Probably trying for the late Queen Elizabeth.
This was supposed to be Escherichia.
This was supposed to be Facklamia.
This was supposed to be Filifactor.
This was supposed to be Finegoldia.
This was supposed to be Francisella.
These illustrations were drawn using Stable Diffusion 2.1.
