About the mihama chiyo tag
mihama chiyo is a character tag that NovelAI Diffusion can use. On Danbooru it has 504 posts, and its best-rated still image scores 317. 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 mihama chiyo
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 mihama chiyo in a prompt
Put the subject first, then this tag, then quality tags.
mihama chiyo, solo, best quality, masterpiecewlop, mihama chiyo, 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
Azumanga Daioh character.
The pint-size genius girl in the Azumanga class. Chiyo starts the series at 10, but she's already been bumped up to high school. She still has the innocence of a grade-schooler, and with her brains and can-do attitude, she makes friends easily; her only flaw is having a chip on her shoulder about her size. She's also richer than sin and owns a dog so big she can ride it.
Chiyo is universally called Chiyo-chan (with rare exceptions when Yukari gets mad enough to use the insulting "Chiyo-suke"). She wears her hair in pigtails that have a unique shape and, if you ask Osaka, a life of their own. Her father is a whole separate subject.
FAQ
Does NovelAI recognize mihama chiyo?
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 mihama chiyo.
How do I write mihama chiyo in a prompt?
Write "mihama chiyo" 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.