About the southern ocean oni tag
southern ocean oni is a character tag that NovelAI Diffusion can use. On Danbooru it has 244 posts, and its best-rated still image scores 62. 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 southern ocean oni
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 southern ocean oni in a prompt
Put the subject first, then this tag, then quality tags.
southern ocean oni, solo, best quality, masterpiecewlop, southern ocean oni, 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
An Abyssal ship from Kantai Collection.
Featuring a female humanoid armed with two pairs of twin-barreled turrets on her clawed gauntlets and two pairs of triple-barreled turrets attached to the bracing on her legs. Like Southern Ocean War Oni, she is dressed in an open jacket over her bikini and boots that reach to the bracing. She wears her long silvery hair tied in twintails with the bangs over her right eye. Unlike her "war" counterpart, her hair ties do not have a fiery glow.
FAQ
Does NovelAI recognize southern ocean oni?
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 southern ocean oni.
How do I write southern ocean oni in a prompt?
Write "southern ocean oni" 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.