About the rensouhou-chan tag
rensouhou-chan is a character tag that NovelAI Diffusion can use. On Danbooru it has 6,019 posts, and its best-rated still image scores 491. 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 rensouhou-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 rensouhou-chan in a prompt
Put the subject first, then this tag, then quality tags.
rensouhou-chan, solo, best quality, masterpiecewlop, rensouhou-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
Show the wiki text ▾Hide ▴
Shimakaze's familiar-like gun turret sidekicks in Kantai Collection. They are based on the ship's twin 12.7 cm/50 naval gun turrets. One of them has a lifebuoy with the word "ぜかまし" ("Zekamashi", "Shimakaze" reversed) on it.
Amatsukaze also has one which she calls "Rensouhou-kun". The difference compared to Shimakaze's is that it is encased in a ship-like hull and it has rounder facial features.
Akizuki, Teruzuki_, Suzutsuki_, and Hatsuzuki_ have their own familiars called "Chou-10cm-hou-chan".
Appearance
See also
FAQ
Does NovelAI recognize rensouhou-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 rensouhou-chan.
How do I write rensouhou-chan in a prompt?
Write "rensouhou-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.