.webp)
About the screwllum (honkai: star rail) tag
screwllum (honkai: star rail) is a character tag that NovelAI Diffusion can use. On Danbooru it has 225 posts, and its best-rated still image scores 178. 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 screwllum (honkai: star rail)
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 screwllum (honkai: star rail) in a prompt
Put the subject first, then this tag, then quality tags.
screwllum (honkai: star rail), solo, best quality, masterpiecewlop, screwllum (honkai: star rail), 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 recurring character from Honkai: Star Rail, but remains unplayable.
He is portrayed in a robotic form; his default outfit consists of a black vest and long-sleeved black jacket worn over a white shirt, red ascot, black gloves, white pants, single thigh strap on his left leg, black fedora, golden monocle, and white shoes.
FAQ
Does NovelAI recognize screwllum (honkai: star rail)?
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 screwllum (honkai: star rail).
How do I write screwllum (honkai: star rail) in a prompt?
Write "screwllum (honkai: star rail)" 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.