About the kaguya madoka tag
kaguya madoka is a character tag that NovelAI Diffusion can use. On Danbooru it has 456 posts, and its best-rated still image scores 186. 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 kaguya madoka
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 kaguya madoka in a prompt
Put the subject first, then this tag, then quality tags.
kaguya madoka, solo, best quality, masterpiecewlop, kaguya madoka, 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
Star Twinkle Precure character. Civilian identity of Cure Selene.
Kaguya Madoka/Cure Selene, a third year middle school student who does her best to be ladylike. She is from a family with a storied history: her father works in the government and her mother is a world-famous pianist. She herself holds national championship titles in piano and archery. She also does flower arrangement and tea ceremony, and gets excellent grades. As the student council president, she is known as the "moon" of her school.
Appearance
FAQ
Does NovelAI recognize kaguya madoka?
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 kaguya madoka.
How do I write kaguya madoka in a prompt?
Write "kaguya madoka" 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.