About the rias gremory tag
rias gremory is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,403 posts, and its best-rated still image scores 1,027. 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 rias gremory
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 rias gremory in a prompt
Put the subject first, then this tag, then quality tags.
rias gremory, solo, best quality, masterpiecewlop, rias gremory, 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 ▴
Main female protagonist in High School DxD. She a Pure-Blooded Demon as well as the heiress of the Gremory Clan and the former President of the Occult Research Club. She is also known as the "Crimson-Haired Ruin Princess" due to her hair color.
She has blue/green eyes, large breasts, and long red hair stylized with crossed bangs, an ahoge, and hair between eyes. She usually wears the Kuoh Academy School Uniform.
She represents the king chess piece.
Voiced by Hikasa Youko in the anime.
See Also
FAQ
Does NovelAI recognize rias gremory?
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 rias gremory.
How do I write rias gremory in a prompt?
Write "rias gremory" 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.