.webp)
About the knight (hollow knight) tag
knight (hollow knight) is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,028 posts, and its best-rated still image scores 232. 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 knight (hollow 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 knight (hollow knight) in a prompt
Put the subject first, then this tag, then quality tags.
knight (hollow knight), solo, best quality, masterpiecewlop, knight (hollow 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
Player character and protagonist of the game Hollow Knight.
They are canonically genderless. They have a white head with two upright horns with an inward curve and hollow, black eyes. They wear a dark grey cloak and wield a sword-like weapon called a nail. They are significantly smaller than most bugs of Hallownest.
Initially found wandering outside the kingdom, they return to uncover its story and the mysteries it hides.
Appearance
See also
FAQ
Does NovelAI recognize knight (hollow 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 knight (hollow knight).
How do I write knight (hollow knight) in a prompt?
Write "knight (hollow 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.