About the pattadol tag
pattadol is a character tag that NovelAI Diffusion can use. On Danbooru it has 285 posts, and its best-rated still image scores 334. The samples above put the tag at the front of a fixed base prompt with seed 1234, so the differences between tags come from the tag alone.
How each model draws pattadol
Follows composition and expression instructions closely, so the effect shows in a tidy form.
Reacts to the tag more strongly, so its effect is easier to see.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing pattadol in a prompt
Put the subject first, then this tag, then quality tags.
pattadol, solo, best quality, masterpiecewlop, pattadol, soloThe negative prompt and the full settings are on the terms page.
How these samples were made
Every image uses 832×1216, seed 1234, 23 steps and the k_euler_ancestral sampler. The base prompt and negative prompt stay the same for every tag, and only the tag under test changes. Images flagged by the NSFW check are regenerated with a new seed or hidden.
From the Danbooru wiki
Show the wiki text ▾Hide ▴
One of the "Canaries" in Dungeon Meshi, a squad of elven criminals and nobles sent to dungeons to evaluate the danger they pose to the world.
Pattadol is one of the few non-criminal members (as she has no visible notches cut into her ears), and instead acts as a warden for the others. She keeps a fairy around which she uses for communication with the rest of the squad. She has blonde hair, usually in a half up braid, and blue eyes.
Her squadmates include:
External links
- "Adventurer's Bible entry":[https://mangadex.org/chapter/676edd8f-5ba6-4f1f-bd5d-306abf0c6b87]
FAQ
Does NovelAI recognize pattadol?
Compare the samples on this page. Every tag on this site shares the same seed and base prompt, so any change you see comes from pattadol.
How do I write pattadol in a prompt?
Write "pattadol" near the front of the prompt and separate it from other tags with commas.
Should I use V5 or V4.5?
V4.5 shows the tag's effect more strongly. V5 gives steadier images with fewer artifacts.