.webp)
About the non-human admiral (kancolle) tag
non-human admiral (kancolle) is a character tag that NovelAI Diffusion can use. On Danbooru it has 2,812 posts, and its best-rated still image scores 79. 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 non-human admiral (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 non-human admiral (kancolle) in a prompt
Put the subject first, then this tag, then quality tags.
non-human admiral (kancolle), solo, best quality, masterpiecewlop, non-human admiral (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
Any Kantai Collection Admiral depicted as any animal other than a human being. Such admiral typically wears the peaked cap to signify its position. Can also apply to robots or extraterrestrial creatures holding such position.
Examples
- Kirisawa Juuzou's hamster admiral
- Mizumoto Tadashi's bird admiral
- kaga3chi's bunny admiral
- suetake's dog (Shiba Inu) admiral
FAQ
Does NovelAI recognize non-human admiral (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 non-human admiral (kancolle).
How do I write non-human admiral (kancolle) in a prompt?
Write "non-human admiral (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.