About the nishikitaitei-chan tag
nishikitaitei-chan is a character tag that NovelAI Diffusion can use. On Danbooru it has 319 posts, and its best-rated still image scores 243. 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 nishikitaitei-chan
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 nishikitaitei-chan in a prompt
Put the subject first, then this tag, then quality tags.
nishikitaitei-chan, solo, best quality, masterpiecewlop, nishikitaitei-chan, 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
The "familiar" of Akitsushima from Kantai Collection.
Nishikitaitei-chan is a pseudo-anthropomorphized four engine flying boat seaplane (specifically, a Kawanishi H8K Type 2 Flying Boat) that is carried around by Akitsushima. A relatively subtle "face" is painted on the left side of the cockpit, which changes mood depending upon the damage state, making it fairly similar to what Rensouhou-chan is to Shimakaze.
Sometimes, Akitsushima calls it "Taitei-chan".
See also
FAQ
Does NovelAI recognize nishikitaitei-chan?
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 nishikitaitei-chan.
How do I write nishikitaitei-chan in a prompt?
Write "nishikitaitei-chan" 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.