.webp)
About the konngara (touhou) tag
konngara (touhou) is a character tag that NovelAI Diffusion can use. On Danbooru it has 539 posts, and its best-rated still image scores 107. 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 konngara (touhou)
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 konngara (touhou) in a prompt
Put the subject first, then this tag, then quality tags.
konngara (touhou), solo, best quality, masterpiecewlop, konngara (touhou), 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 Touhou PC-98 character. Jigoku route Final Boss in Highly Responsive to Prayers.
They have red eyes, black hair, and a red hair ribbon. They wear a red kimono with white trim and and wields a large sword. Their sprite also has what appears to be a single horn on their forehead, which has led to fanon speculation that they are an oni, though their name appears to be sourced from a yaksha servant of the god Fudou Myou/Acala.
External links
FAQ
Does NovelAI recognize konngara (touhou)?
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 konngara (touhou).
How do I write konngara (touhou) in a prompt?
Write "konngara (touhou)" 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.