About the jiu niangzi tag
jiu niangzi is a character tag that NovelAI Diffusion can use. On Danbooru it has 334 posts, and its best-rated still image scores 50. 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 jiu niangzi
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 jiu niangzi in a prompt
Put the subject first, then this tag, then quality tags.
jiu niangzi, solo, best quality, masterpiecewlop, jiu niangzi, 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
Jiu Niangzi is a playable character from Reverse:1999. She is one of the protagonist of the "Notes on Shuori" sidestory. A kind-hearted tavern owner who loves lending hand on people, despite always ended up in failures. She's actually a Lushu, a mythical beast with the appearance of a horse with a tiger's skin and a red tail. She unknowingly transformed Yenisei's expedition team into half-Lushus through her wooden doll, starting the main conflict of the sidestory.
She is voiced by Melody Peng in English, Xie Ying in Chinese and Tomita Miyu in Japanese.
Appearance
- : Default
- : Insight II: Let There Be Way Out
- : Blossom Spring Fairy
FAQ
Does NovelAI recognize jiu niangzi?
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 jiu niangzi.
How do I write jiu niangzi in a prompt?
Write "jiu niangzi" 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.