KING BLADIMIR THE MAGNIFICENT

“After many missions in a plethora of peculiar realms, he’d managed to keep the fear of monsters locked away, but his own evil terrified him more than any demon."
― William Collins, A Darker Shade of Sorcery

One of my more recent AI creations on Nightcafe came about when I tried to 'spoof' the adipose mayor of Vienna. I tried several ways, even with a input portrait, but nothing much came of it. So I gave up, but did not let the idea go. Instead I re-run a well worn crazy prompt and massaged it, adding the words 'Fat Bellied King Bladimir' (Blad in Austro-German means fat, bloated, and Bladimir was a nickname coined for the mayor by one of the bloggers I follow). Now if you put in prompts that are easy for AI to fill, you get the most predictable result in a flash. With my prompts, the gears are sometimes churning for a while before something happens.
I mentioned before, with every new and improved Stable Diffusion the results get slicker, and usually I prefer the old SD v1.4 and v1.5, but it depends on how the prompts are written. In this case, the brand new SDXL 1.0 worked very good.
In any event I think it is important to instruct AI to center your image and use relevant negative prompts, which usually take care of the problem with extra limbs and fingers or distortions. However, that gets largely ignored if Hieronymus Bosch is in the modifiers, because weird is like his middle name, and that is how I like it.
Another thing I tried out is a new site, ClipDrop where I sometimes try my new prompts. Results from there I might use as seed image on Nightcafe (as well as other sites I use, such as Deep Dream Text2Dream and Dreamwombo).

FAT BELLY KING BLADIMIR SERIES

some had several prompts (but it is recommended to only run one prompt on the new SDXL versions), one is about my own Inner Self Alter Ego Bogomil. I found that AI had quite a bit of training on my style (check the website HAVE I BEEN TRAINED - best when you actually log in, then you can search for yourself and see what AI knows about you) - so using myself in the prompts usually gets me results that reflect my style.
FAT BELLY KING BLADIMIR THE UGLY 1 - UPSCALED - kW7aF5HxJeJ8oMUNWQRO--1.jpg

FAT BELLY KING BLADIMIR THE UGLY 1 - UPSCALED - kW7aF5HxJeJ8oMUNWQRO--1.jpg

BLADIMIR THE MAGNIFICENT
I mentioned before that I sometimes use ClipDrop to test my prompts, so here is one example:
ClipDrop-stable-diffusion-xl - best.jpg

BLADIMIR THE MAGNIFICENT - used as seed image

PROMPT: "Fat belly King Bladimir the Ugly in Cryptid Taxidermy in post apocalyptic wonderland, in heaven everything is fine by lady in the radiator and brothers quay, stopmotion cinema photograph by H.R. Giger, by Giuseppe Arcimboldo, Hieronymus Bosch, Art Nouveau, intricately detailed, hyperrealism, fantasy, imperial colors; Bogomils Universe"

Here are some of the results I got on Nightcafe, using that prompt,
and occasionally the ClipDrop image as a seed.

▲ these last 3 images were done with the older SD versions
◄ all others above it with the new SDXL 1.0

there are many more - because once I start I find it hard to stop. The combo of my latest crazy prompts and the new SDXL modes give me lots to play with.

A previous series was actually the starting point for this. A friend on Facebook suggested to include the phrase 'Cryptid Taxidermy' in my prompt. So I tried it, coupling it up with my 'Lady in the Radiator' and 'Brothers Quay' as well as my 'Bogomils Universe'. It resulted in the weirdest and most surreal images.