About the mazaki anzu tag
mazaki anzu is a character tag that NovelAI Diffusion can use. On Danbooru it has 626 posts, and its best-rated still image scores 473. 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 mazaki anzu
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 mazaki anzu in a prompt
Put the subject first, then this tag, then quality tags.
mazaki anzu, solo, best quality, masterpiecewlop, mazaki anzu, 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
Yu-Gi-Oh! Duel Monsters character. Known as Téa Gardner in the English dub.
Muto Yugi's childhood friend, an extremely supportive girl with a lot of spirit for her friends. Although her dueling ability is decent and she used to consistently defeat Jonouchi Katsuya in school (before Muto Sugoroku tutored Jonouchi), Anzu doesn't actively play the game herself. Consequently, her ability as a Duelist is well below that of most other Duelists in the series.
Anzu is athletic and secretly works at a fast food restaurant to save money; her dream is to attend dancing school in New York City.
FAQ
Does NovelAI recognize mazaki anzu?
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 mazaki anzu.
How do I write mazaki anzu in a prompt?
Write "mazaki anzu" 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.