About the don-chan (usada pekora) tag
don-chan (usada pekora) is a character tag that NovelAI Diffusion can use. On Danbooru it has 3,251 posts, and its best-rated still image scores 1,206. 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 don-chan (usada pekora)
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 don-chan (usada pekora) in a prompt
Put the subject first, then this tag, then quality tags.
don-chan (usada pekora), solo, best quality, masterpiecewlop, don-chan (usada pekora), 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
"Wait... that's not a muffler. Luna-san, you don't know the name of Pekora's friend?" -Houshou Marine, 2020
Don-chan is a mysterious, perpetually inexpressive rabbit-like creature that spends most of its time complacently wrapped upon virtual YouTuber Usada Pekora's neck. In Pekora's prisoner outfit, it's instead wrapped around her right leg, holding a carrot-shaped ball and chain with its mouth.
FAQ
Does NovelAI recognize don-chan (usada pekora)?
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 don-chan (usada pekora).
How do I write don-chan (usada pekora) in a prompt?
Write "don-chan (usada pekora)" 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.
.webp)