About the kasukabe tsumugi tag
kasukabe tsumugi is a character tag that NovelAI Diffusion can use. On Danbooru it has 865 posts, and its best-rated still image scores 414. 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 kasukabe tsumugi
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 kasukabe tsumugi in a prompt
Put the subject first, then this tag, then quality tags.
kasukabe tsumugi, solo, best quality, masterpiecewlop, kasukabe tsumugi, 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 character and voice library for the VOICEVOX software designed and voiced by Kasukabe Tsukushi, who is now also her cousin. She is a gyaru-ish highschooler from Saitama.
She has messy grey or brown hair with one side up and blue eyes with a small mole. Her outfit is magatama necklace, a long-sleeved collared black shirt, an open yellow cardigan with bandaids, a yellow necktie, a plaid purple miniskirt, loose white socks, and black loafers.
She is often seen with other Voicevox characters like Zundamon and Shikoku Metan.
Appearance
- !asset #26233782: Profile
- !asset #49388040: Vocaloid6 outfit
FAQ
Does NovelAI recognize kasukabe tsumugi?
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 kasukabe tsumugi.
How do I write kasukabe tsumugi in a prompt?
Write "kasukabe tsumugi" 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.