.webp)
About the azusa (cookie) tag
azusa (cookie) is a character tag that NovelAI Diffusion can use. On Danbooru it has 329 posts, and its best-rated still image scores 110. 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 azusa (cookie)
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 azusa (cookie) in a prompt
Put the subject first, then this tag, then quality tags.
azusa (cookie), solo, best quality, masterpiecewlop, azusa (cookie), 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 ▴
- !asset #21017951
Voice of Kirisame Marisa in Cookie☆☆ S2. Uses the Undefined Fantastic Object model of a black capelet, a red bowtie, and a red star on her hat and a white bow in her hair. While she first appeared in Cookie☆☆☆, her later and better acting in Cookie☆☆ S2 drove her popularity.
The most vocally talented of the Cookie☆☆ actors, even later becoming an underground until 2019. Her main running joke is that she likes mandarin oranges, else mostly appearing the Marisa to Kanna's Reimu. A somewhat far-flung theory is that she is Dola (Nijisanji), so she is sometimes drawn with dragon features.
FAQ
Does NovelAI recognize azusa (cookie)?
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 azusa (cookie).
How do I write azusa (cookie) in a prompt?
Write "azusa (cookie)" 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.