About the tachibana kanade tag
tachibana kanade is a character tag that NovelAI Diffusion can use. On Danbooru it has 2,504 posts, and its best-rated still image scores 329. 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 tachibana kanade
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 tachibana kanade in a prompt
Put the subject first, then this tag, then quality tags.
tachibana kanade, solo, best quality, masterpiecewlop, tachibana kanade, 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
A character from Angel Beats!, primarily known as Angel/Tenshi. Voiced by Hanazawa Kana.
She is the acting Student Council president and antagonist to the Shinda Sekai Sensen (Afterlife War Front). She is capable of performing various supernatural abilities called "Guard Skills", such as summoning out of thin air blades from her forearms. She is sometimes depicted with white wings, while her main physical attributes are long light blue or aqua hair and yellow eyes.
Her favorite food is extremely spicy mapo tofu.
FAQ
Does NovelAI recognize tachibana kanade?
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 tachibana kanade.
How do I write tachibana kanade in a prompt?
Write "tachibana kanade" 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.