.webp)
About the hoshino miyako (wataten) tag
hoshino miyako (wataten) is a character tag that NovelAI Diffusion can use. On Danbooru it has 632 posts, and its best-rated still image scores 416. 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 hoshino miyako (wataten)
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 hoshino miyako (wataten) in a prompt
Put the subject first, then this tag, then quality tags.
hoshino miyako (wataten), solo, best quality, masterpiecewlop, hoshino miyako (wataten), 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 ▴
Main character in Watashi ni Tenshi ga Maiorita!.
Hoshino Miyako has red eyes, large breasts, and short pink hair (sometimes depicted as red or brown) with hair over one eye. She wears a red track suit consisting of a red track jacket, red track pants, and a white shirt.
She is the older sister of Hoshino Hinata and daughter of Hoshino Chizuru.
She is voiced by Ueda Reina.
FAQ
Does NovelAI recognize hoshino miyako (wataten)?
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 hoshino miyako (wataten).
How do I write hoshino miyako (wataten) in a prompt?
Write "hoshino miyako (wataten)" 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.