About the souseiseki tag
souseiseki is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,687 posts, and its best-rated still image scores 226. 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 souseiseki
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 souseiseki in a prompt
Put the subject first, then this tag, then quality tags.
souseiseki, solo, best quality, masterpiecewlop, souseiseki, 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 ▴
Lapis Lazuli Stone
The fourth Rozen Maiden doll, and Suiseiseki's younger twin sister. She is the most blunt and pragmatic of the dolls and frequently uses male speech patterns. She battles with her shears, which she can use to enter dreams.
She has short brown hair and red-green heterochromia. Her outfit consists of a black top hat, a blue capelet, a frilled collared white shirt with a frilled collar tied with a black neck ribbon and long frilled sleeves, a black corset, blue shorts, white pantyhose, and black shoes.
Appearance
FAQ
Does NovelAI recognize souseiseki?
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 souseiseki.
How do I write souseiseki in a prompt?
Write "souseiseki" 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.