About the vignette tsukinose april tag
vignette tsukinose april is a character tag that NovelAI Diffusion can use. On Danbooru it has 402 posts, and its best-rated still image scores 293. 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 vignette tsukinose april
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 vignette tsukinose april in a prompt
Put the subject first, then this tag, then quality tags.
vignette tsukinose april, solo, best quality, masterpiecewlop, vignette tsukinose april, 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
A character from the anime Gabriel Dropout. Just as Gabriel is an angel working in the human world under the guise of a high school student, Vignette is a demon doing the same thing, and the two are good friends.
Vigne is everything Gab is supposed to be: sweet, good-natured, and generous, to the point where it affects her salary as a demon. How Hell managed to produce her is the biggest mystery of the series.
Voiced by Oonishi Saori.
External links
FAQ
Does NovelAI recognize vignette tsukinose april?
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 vignette tsukinose april.
How do I write vignette tsukinose april in a prompt?
Write "vignette tsukinose april" 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.
