About the nishikata tag
nishikata is a character tag that NovelAI Diffusion can use. On Danbooru it has 548 posts, and its best-rated still image scores 731. 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 nishikata
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 nishikata in a prompt
Put the subject first, then this tag, then quality tags.
nishikata, solo, best quality, masterpiecewlop, nishikata, 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 main characters in Karakai Jouzu no Takagi-san. He is a middle school student in class 1-2 who sits next to Takagi-san and is constantly embarrassed as he quickly falls to her daily teasing, hoping to one day get back at her. [spoilers]In a spin-off manga, Karakai Jouzu no (Moto) Takagi-san, he is married to Takagi and they have a daughter, Chii.[/spoilers]
He has black eyes and short black hair. He wears a gakuran school uniform during the Fall & Winter, and a white collared shirt with black pants during the Spring & Summer.
He is voiced by Kaji Yuuki.
See Also
FAQ
Does NovelAI recognize nishikata?
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 nishikata.
How do I write nishikata in a prompt?
Write "nishikata" 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.