About the isaki riona tag
isaki riona is a character tag that NovelAI Diffusion can use. On Danbooru it has 405 posts, and its best-rated still image scores 288. 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 isaki riona
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 isaki riona in a prompt
Put the subject first, then this tag, then quality tags.
isaki riona, solo, best quality, masterpiecewlop, isaki riona, 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 ▴
A Virtual YouTuber and member of of hololive DEV_IS' 2nd group FLOW GLOW. Designed by shirabi.
She has red eyes and long grey hair decorated with a crown-shaped hairclip tied into a one side up held with a black hair bow with nose-length double-parted bangs and sidelocks. She also has a spiked earclip on one ear and an ear chain on the other as well as a navel piercing.
Appearance
Official costumes with a model
- : 1st costume: Default
- !asset #38046680: Flowglow Uniform
- !asset #41223518: New Year
Other costumes
External links
FAQ
Does NovelAI recognize isaki riona?
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 isaki riona.
How do I write isaki riona in a prompt?
Write "isaki riona" 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.