About the katsura hinagiku tag
katsura hinagiku is a character tag that NovelAI Diffusion can use. On Danbooru it has 959 posts, and its best-rated still image scores 428. 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 katsura hinagiku
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 katsura hinagiku in a prompt
Put the subject first, then this tag, then quality tags.
katsura hinagiku, solo, best quality, masterpiecewlop, katsura hinagiku, 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
A supporting character from Hayate no Gotoku!
Student Council President of Hakuou Academy, where Ayasaki Hayate, Sanzen'in Nagi and Saginomiya Isumi attend, as well as younger sister of Yukiji, one of the school's teachers. Intelligent, well-mannered (in contrast to her alcoholic older sister) and popular with the girls, Hina, as she is known, is also skilled at kendo. After being saved by Hayate from being stuck on a tree (due to her agoraphobia), she has developed feelings for him.
FAQ
Does NovelAI recognize katsura hinagiku?
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 katsura hinagiku.
How do I write katsura hinagiku in a prompt?
Write "katsura hinagiku" 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.