About the takagi-san tag
takagi-san is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,536 posts, and its best-rated still image scores 1,324. 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 takagi-san
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 takagi-san in a prompt
Put the subject first, then this tag, then quality tags.
takagi-san, solo, best quality, masterpiecewlop, takagi-san, 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 ▴
Title protagonist of Karakai Jouzu no Takagi-san. She is a middle school student in Class 1-2 and a blunt girl who likes teasing her classmate, Nishikata. Easily recognized for her brown, medium hair and parted bangs that reveal her prominent forehead.
She wears a serafuku consisting of a blue sailor collar, red neckerchief, long sleeved white shirt, blue pleated skirt, blue shorts under the skirt, and black kneehighs.
[spoilers]In Karakai Jouzu no (moto) Takagi-san she is married to Nishikata and they have a child, Chii.[/spoilers]
She is voiced by Takahashi Rie in Japanese, and Sarah Wiedenheft (Seasons 1-3) and Kayli Mills (Season 2) in English.
FAQ
Does NovelAI recognize takagi-san?
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 takagi-san.
How do I write takagi-san in a prompt?
Write "takagi-san" 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.