_(umamusume).webp)
About the haru urara (bestest prize) (umamusume) tag
haru urara (bestest prize) (umamusume) is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,676 posts, and its best-rated still image scores 289. 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 haru urara (bestest prize) (umamusume)
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 haru urara (bestest prize) (umamusume) in a prompt
Put the subject first, then this tag, then quality tags.
haru urara (bestest prize) (umamusume), solo, best quality, masterpiecewlop, haru urara (bestest prize) (umamusume), 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
The racing outfit of Umamusume's Haru Urara.
It is a gym uniform consisting of a white shirt top, red buruma, white jacket with a red trim, red fingerless gloves, striped socks, white shoes, and bandaids on her legs.
Appearance
- : Current
- : Draft
FAQ
Does NovelAI recognize haru urara (bestest prize) (umamusume)?
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 haru urara (bestest prize) (umamusume).
How do I write haru urara (bestest prize) (umamusume) in a prompt?
Write "haru urara (bestest prize) (umamusume)" 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.