About the eyeshadow tag
eyeshadow is a face part tag that NovelAI Diffusion can use. On Danbooru it has 47,462 posts, and its best-rated still image scores 1,276. 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 eyeshadow
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 eyeshadow in a prompt
Put the subject first, then this tag, then quality tags.
1girl, solo, eyeshadow, best quality, masterpiecewlop, 1girl, eyeshadowThe 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 type of eye makeup. A colored powder applied to the eyelids to make the eyes stand out or look more attractive.
Not to be confused with eyeliner, which is applied to the lash line instead of the eyelids, often to create a cat eye effect.
Examples
- : grey eyeshadow
- : half cut blue eyeshadow
- : with glitter makeup
- : red eyeshadow
- : gradient aqua & purple eyeshadow
Not eyeshadow
See also
- eyeshadow under eye
- smokey eyeshadow
- eyelash ornament
- eyeliner
- fake eyelashes
- mascara
- tag group:makeup
External links
FAQ
Does NovelAI recognize eyeshadow?
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 eyeshadow.
How do I write eyeshadow in a prompt?
Write "eyeshadow" 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.