.webp)
About the hoshikawa sara (1st costume) tag
hoshikawa sara (1st costume) is a character tag that NovelAI Diffusion can use. On Danbooru it has 617 posts, and its best-rated still image scores 728. 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 hoshikawa sara (1st costume)
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 hoshikawa sara (1st costume) in a prompt
Put the subject first, then this tag, then quality tags.
hoshikawa sara (1st costume), solo, best quality, masterpiecewlop, hoshikawa sara (1st costume), 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 ▴
The default costume of Nijisanji's Hoshikawa Sara.
It consists of a white tank top tied to the front, black choker, blue short shorts, pink thigh strap to her right, highleg panties, a second thigh strap on her lower left leg with a gold circular piece, blue socks, white fold-over boots, long-sleeved white jacket with a blue ribbon, and a two-tone orange-red hair ribbon tying her hair to a side ponytail.
Appearance
- : Profile
FAQ
Does NovelAI recognize hoshikawa sara (1st costume)?
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 hoshikawa sara (1st costume).
How do I write hoshikawa sara (1st costume) in a prompt?
Write "hoshikawa sara (1st costume)" 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.