About the taikogane sadamune tag
taikogane sadamune is a character tag that NovelAI Diffusion can use. On Danbooru it has 261 posts, and its best-rated still image scores 49. 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 taikogane sadamune
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 taikogane sadamune in a prompt
Put the subject first, then this tag, then quality tags.
taikogane sadamune, solo, best quality, masterpiecewlop, taikogane sadamune, 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
Personifiation of the sword Taikogane in Touken Ranbu. One of the many swords Date Masamune handled over his lifetime, including Shokudaikiri Mitsutada, Ookurikara, and Tsurumaru Kuninaga.
In-game, he has a close relationship with Mitsutada, whom calls him "Sada-chan" (in turn he's referred to as "Micchan"). He's characterized as proud, and is very conscious of his looks in the Citadel and in battle, to the point where he gets angry if anything happens to his outfit.
FAQ
Does NovelAI recognize taikogane sadamune?
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 taikogane sadamune.
How do I write taikogane sadamune in a prompt?
Write "taikogane sadamune" 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.