About the kaai yuki tag
kaai yuki is a character tag that NovelAI Diffusion can use. On Danbooru it has 694 posts, and its best-rated still image scores 164. 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 kaai yuki
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 kaai yuki in a prompt
Put the subject first, then this tag, then quality tags.
kaai yuki, solo, best quality, masterpiecewlop, kaai yuki, 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 ▴
Kaai Yuki is a Japanese VOCALOID developed and distributed by AH-Software Co. Ltd., and was released for the VOCALOID2 engine.
Her appearance was illustrated by Umetani Atarou. She is designed as a young student of Hiyama Kiyoteru. She has black hair in short twintails (held up by hair bobbles) and her eyes are brown. She wears a red dress, white socks, and brown Mary Janes. The instrument she carries in her randoseru is a WIND MIDI CONTROLLER WX5 recorder.
Appearance
- : Vocaloid2
- : Vocaloid4
See also
External links
FAQ
Does NovelAI recognize kaai yuki?
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 kaai yuki.
How do I write kaai yuki in a prompt?
Write "kaai yuki" 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.