About the tojo kirumi tag
tojo kirumi is a character tag that NovelAI Diffusion can use. On Danbooru it has 800 posts, and its best-rated still image scores 82. 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 tojo kirumi
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 tojo kirumi in a prompt
Put the subject first, then this tag, then quality tags.
tojo kirumi, solo, best quality, masterpiecewlop, tojo kirumi, 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 ▴
Character from Danganronpa V3: Killing Harmony.
The Ultimate Maid. Because of her adaptability to any task, many have approached her for jobs like standing bodyguard for a political figure or being used as a key figure in a coup. She cleans often in the Gifted Inmates Academy since she never takes her mind off of work.
As she is a maid, her clothes are a black pinafore dress with pantyhose and a maid headdress. She wears black gloves. Her hair is short, silver, and covers one of her green eyes.
Appearance
FAQ
Does NovelAI recognize tojo kirumi?
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 tojo kirumi.
How do I write tojo kirumi in a prompt?
Write "tojo kirumi" 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.