About the kanade izuru tag
kanade izuru is a character tag that NovelAI Diffusion can use. On Danbooru it has 428 posts, and its best-rated still image scores 473. 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 kanade izuru
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 kanade izuru in a prompt
Put the subject first, then this tag, then quality tags.
kanade izuru, solo, best quality, masterpiecewlop, kanade izuru, 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 Holostars VTuber and member of its 1st generation. Designed by TCB.
He has pale skin and black hair with hair between eyes. His eyes are purple and have slit pupils, and his nails are painted black. When there is hood in his outfit, he usually has them up.
Costumes
- : 1st costume: Default
- !asset #23772744: 2nd costume: White Day
- !asset #23772761: 3rd costume: Summer
- !asset #25751630: 4th costume: New Years
- !asset #25751633: 5th costume: Casual
- !asset #25751642: Fall/Winter
- !asset #25751645: 7th costume: Bratt Unit Costume
- !asset #47718462: 8th costume
External links
- YouTube channel
- Twitter: main sub
FAQ
Does NovelAI recognize kanade izuru?
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 kanade izuru.
How do I write kanade izuru in a prompt?
Write "kanade izuru" 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.
