.webp)
About the fu hua (shadow knight) tag
fu hua (shadow knight) is a character tag that NovelAI Diffusion can use. On Danbooru it has 306 posts, and its best-rated still image scores 574. 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 fu hua (shadow knight)
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 fu hua (shadow knight) in a prompt
Put the subject first, then this tag, then quality tags.
fu hua (shadow knight), solo, best quality, masterpiecewlop, fu hua (shadow knight), 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 ▴
A playable battlesuit of Honkai Impact 3rd's Fu Hua.
It is a black bodysuit with additional black elbow gloves and armor pieces for her chest and waistline, armored black thighhighs, black shoes, and mechanical hair ornaments on both sides of her head. In the story, it was provided to her by Otto Apocalpyse for when she was a spy for the Schicksal to watch Kiana Kaslana at St. Freya.
Appearance
- : Profile
FAQ
Does NovelAI recognize fu hua (shadow knight)?
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 fu hua (shadow knight).
How do I write fu hua (shadow knight) in a prompt?
Write "fu hua (shadow knight)" 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.