About the zhu yuan tag
zhu yuan is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,957 posts, and its best-rated still image scores 1,250. 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 zhu yuan
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 zhu yuan in a prompt
Put the subject first, then this tag, then quality tags.
zhu yuan, solo, best quality, masterpiecewlop, zhu yuan, 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 ▴
Playable character in Zenless Zone Zero belonging to the New Eridu Public Security faction. Voiced by Inoue Marina in Japanese.
She is portrayed with long black hair with orange streaks with an ahoge and tied to a ponytail, orange eyes, and large breasts. Her outfit, fitting of her policewoman role, consists of a white collared shirt, checkered necktie, blue jacket with the name "PubSec" inscribed, black gloves, headset, high-waist black pants, and blue shoes.
Leader of the Criminal Investigation Special Response Team of New Eridu's Public Security.
Appearance
See also
External links
FAQ
Does NovelAI recognize zhu yuan?
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 zhu yuan.
How do I write zhu yuan in a prompt?
Write "zhu yuan" 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.