About the emily stewart tag
emily stewart is a character tag that NovelAI Diffusion can use. On Danbooru it has 520 posts, and its best-rated still image scores 481. 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 emily stewart
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 emily stewart in a prompt
Put the subject first, then this tag, then quality tags.
emily stewart, solo, best quality, masterpiecewlop, emily stewart, 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 ▴
Character from Idolmaster Million Live!
Despite being British, she strives to become a yamato nadeshiko and to embrace Japanese culture as closely as possible, to the point where she's reluctant to even use common loanwords in her Japanese (e.g. referring to Producer as "Shikakenin-sama"). She has purple eyes and long blonde hair in twintails, usually with a hairband.
She is voiced by Kahara Yuu.
Appearance
Million Live!
- : Casual outfit
- : Million Dreams
Theater Days
- : Angelic Nadeshiko
- : L'ange en Blanc
See also
FAQ
Does NovelAI recognize emily stewart?
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 emily stewart.
How do I write emily stewart in a prompt?
Write "emily stewart" 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.