About the hair bobbles tag
hair bobbles is an accessory tag that NovelAI Diffusion can use. On Danbooru it has 55,427 posts, and its best-rated still image scores 1,204. 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 hair bobbles
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 hair bobbles in a prompt
Put the subject first, then this tag, then quality tags.
1girl, solo, hair bobbles, best quality, masterpiecewlop, 1girl, hair bobblesThe 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
A hair ornament consisting of an elastic band with one or more bobbles, frequently two large balls, used to tie the hair. It works by wrapping the band around a bundle of hair and securing it by stretching the band over and around the bobble.
Stereotypically associated with young or teenage girls.
Not to be confused with hair beads. Hair beads usually consist of many smaller beads and aren't always used to tie the hair. Hair bobbles usually consist of two larger beads normally used to tie the hair.
Examples
See also
FAQ
Does NovelAI recognize hair bobbles?
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 hair bobbles.
How do I write hair bobbles in a prompt?
Write "hair bobbles" 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.