.webp)
About the ashigara kai ni (kancolle) tag
ashigara kai ni (kancolle) is a character tag that NovelAI Diffusion can use. On Danbooru it has 474 posts, and its best-rated still image scores 134. 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 ashigara kai ni (kancolle)
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 ashigara kai ni (kancolle) in a prompt
Put the subject first, then this tag, then quality tags.
ashigara kai ni (kancolle), solo, best quality, masterpiecewlop, ashigara kai ni (kancolle), 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
Ashigara's kai ni form.
Appearance
(See post #1883659.)
Her second remodel gives her a new modified uniform shared with her sister ships' second remodel. Her main difference is the addition of a patterned neckerchief made up of various international maritime signal flags (the ones identified so far are the G, L, M, X, Y and Z flags). Some have guessed that the flags, when read together, actually mean "stand clear, taking in survivors", a reference to her part in rescuing Kiyoshimo's survivors in the Rei-Go Operation (26/12/1944).
FAQ
Does NovelAI recognize ashigara kai ni (kancolle)?
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 ashigara kai ni (kancolle).
How do I write ashigara kai ni (kancolle) in a prompt?
Write "ashigara kai ni (kancolle)" 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.