Trigger words: Digital illustration from muk (monsieur) , it works without it, but you will get a stronger effect by adding it.

The very basic workflow + prompt is available in the images (even if civit doesn't show it)

Lora trained on 70 muk (monsieur) images at 1MP, using kohya-ss/sd-scripts with Adamw -2e04 LR constant for ~5k steps

There is a lot of room for improvement by changing the LR to something smaller at the end, adding a reg dataset, masking image with white background, ...

The captioning is also mediocre at best (JoyCaption makes a LOT of mistakes).

I might do a V2 once I have a better pipeline going.