About the osaka shizuku tag
osaka shizuku is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,756 posts, and its best-rated still image scores 955. 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 osaka shizuku
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 osaka shizuku in a prompt
Put the subject first, then this tag, then quality tags.
osaka shizuku, solo, best quality, masterpiecewlop, osaka shizuku, 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 from Love Live! Nijigasaki High School Idol Club, Shizuku is a level-headed and mature honor student. She is considered a traditional Japanese beauty, and is quite timid at times. She is also a member of the theater club and dreams of being an actress.
She has blue eyes and long brown hair with sidelocks and choppy double-parted bangs reaching between her eyes, which she keeps in a half updo tied into a ponytail with a red hair bow.
She is a member of A・ZU・NA.
Voiced by Maeda Kaori.
Appearance
FAQ
Does NovelAI recognize osaka shizuku?
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 osaka shizuku.
How do I write osaka shizuku in a prompt?
Write "osaka shizuku" 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.
