.webp)
About the banken (inui toko) tag
banken (inui toko) is a character tag that NovelAI Diffusion can use. On Danbooru it has 410 posts, and its best-rated still image scores 112. 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 banken (inui toko)
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 banken (inui toko) in a prompt
Put the subject first, then this tag, then quality tags.
banken (inui toko), solo, best quality, masterpiecewlop, banken (inui toko), 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
A pair of dog-like companions and mascots of Nijisanji's Inui Toko, resembling inu-hariko.
The vast majority of the time they take the form of Inui's animal hair ornaments. Use this tag only when they appear in some other way.
They are individually named Ban and Ken but are identical in appearance, except in Page of Lambda where they appear as twin dog girls with different hairstyles — for those versions see Ban (Page of Lambda) and Ken (Page of Lambda).
FAQ
Does NovelAI recognize banken (inui toko)?
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 banken (inui toko).
How do I write banken (inui toko) in a prompt?
Write "banken (inui toko)" 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.