About the furukawa sanae tag
furukawa sanae is a character tag that NovelAI Diffusion can use. On Danbooru it has 214 posts, and its best-rated still image scores 90. 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 furukawa sanae
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 furukawa sanae in a prompt
Put the subject first, then this tag, then quality tags.
furukawa sanae, solo, best quality, masterpiecewlop, furukawa sanae, 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 ▴
Character from the visual novel/anime Clannad. Wife of Furukawa Akio and mother of Furukawa Nagisa. She has brown eyes and long, brown hair that sticks out like an antenna at the front and is tied into a ponytail with a blue hair ribbon.
She runs a bakery with her husband, but her baking is of poor quality. It is a common gag for people (mainly her husband) to make negative comments about her bread unknowing that she is around to hear it.
Voiced by Inoue Kikuko in the anime.
FAQ
Does NovelAI recognize furukawa sanae?
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 furukawa sanae.
How do I write furukawa sanae in a prompt?
Write "furukawa sanae" 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.