About the takabushi kengo tag
takabushi kengo is a character tag that NovelAI Diffusion can use. On Danbooru it has 393 posts, and its best-rated still image scores 22. 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 takabushi kengo
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 takabushi kengo in a prompt
Put the subject first, then this tag, then quality tags.
takabushi kengo, solo, best quality, masterpiecewlop, takabushi kengo, 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
Tokyo Afterschool Summoners character. Designed by BomBom
A second-year student at Shinjuku Academy in Shinjuku Ward. He was taught martial arts by his parents and he takes great pride in it. He has sworn to live by the fist and skips school to make his way to Ikebukuro and party it up at the underground Colosseum. He grew up with Shiro Motoori. His hobbies include training in the mountains so he has a soft spot for people who like the mountains. His full name is Takabushi Kengo.
External links
FAQ
Does NovelAI recognize takabushi kengo?
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 takabushi kengo.
How do I write takabushi kengo in a prompt?
Write "takabushi kengo" 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.