About the bill cipher tag
bill cipher is a character tag that NovelAI Diffusion can use. On Danbooru it has 348 posts, and its best-rated still image scores 194. 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 bill cipher
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 bill cipher in a prompt
Put the subject first, then this tag, then quality tags.
bill cipher, solo, best quality, masterpiecewlop, bill cipher, 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 ▴
The main antagonist of Gravity Falls. A triangle-shaped demon who causes destruction and madness for fun. Manipulative and tricky, with a very black sense of humor and a fondness for making deceptively appealing deals.
One-eyed with a long, black pupil. Wears a top hat and sometimes carries a cane. In personifications, he usually becomes a blonde haired man with either a yellow suit or a waistcoat, and often missing an eye. Wears a bowtie regardless of form.
Major Spoiler
Helped the real Stanford Pines build a multidimensional portal in the hopes of unleashing Hell on Earth and releasing his demon acquaintances in an event known as Weirdmageggon.
FAQ
Does NovelAI recognize bill cipher?
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 bill cipher.
How do I write bill cipher in a prompt?
Write "bill cipher" 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.