About the yuuki sakuna tag
yuuki sakuna is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,361 posts, and its best-rated still image scores 446. 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 yuuki sakuna
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 yuuki sakuna in a prompt
Put the subject first, then this tag, then quality tags.
yuuki sakuna, solo, best quality, masterpiecewlop, yuuki sakuna, 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 ▴
A Japanese-speaking Indie Virtual YouTuber.
From her profile in her debut teaser's description: "A shy girl who likes games and singing. She is a bit of a clumsy maid, but she's doing her best to become a first-class cat maid."
She is a cat girl with long pink hair and purple eyes.
Appearance
Official costumes with a model
- : 1st costume: Retired default
- : 2nd costume: Retired wa maid
- : 3rd costume: Current default
See also
- Muchao - real life pet cat
- Sakumodeus Beyond Lucifer
External links
FAQ
Does NovelAI recognize yuuki sakuna?
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 yuuki sakuna.
How do I write yuuki sakuna in a prompt?
Write "yuuki sakuna" 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.