About the levi elipha tag
levi elipha is a character tag that NovelAI Diffusion can use. On Danbooru it has 262 posts, and its best-rated still image scores 152. 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 levi elipha
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 levi elipha in a prompt
Put the subject first, then this tag, then quality tags.
levi elipha, solo, best quality, masterpiecewlop, levi elipha, 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 Nijisanji VTuber. Designed by Kirudai.
She is portrayed with two-tone black-orange demon horns, short white hair, blue eyes, and sharp teeth.
Costumes
Regular costumes
- : Default
- !asset #38770011: 2nd costume: Live
- !asset #38770056: School uniform
- : 4th costume
- !asset #25826151: 5th costume: Gothic lolita
Costumes shared with other Nijisanji livers
- !asset #30934007: Nijisanji Fes t-shirt: Violet class (illustration-only)
- : Nijisanji matching outfit
See also
- Levizou - Mascot
External links
FAQ
Does NovelAI recognize levi elipha?
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 levi elipha.
How do I write levi elipha in a prompt?
Write "levi elipha" 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.