About the wakiyama tamami tag
wakiyama tamami is a character tag that NovelAI Diffusion can use. On Danbooru it has 213 posts, and its best-rated still image scores 617. 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 wakiyama tamami
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 wakiyama tamami in a prompt
Put the subject first, then this tag, then quality tags.
wakiyama tamami, solo, best quality, masterpiecewlop, wakiyama tamami, 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
An iDOLM@STER Cinderella Girls character in the Cool (Blue Diamond) category. Tamami is a Kendo practitioner and a romanticist of when Samurai defended Japan. She was her team’s captain, and her initial dream was to become a samurai.
Tamami is an insecure, yet reliable girl. She refers to the Producer with the “dono” suffix. Tamami is easily brought to happiness with flattery, particularly if told that she looks adult-like, cute, or like a hero. She likes to perform on large stages, and has confused golf with Kendo in the past.
She is voiced by Kayama Misa (ANN profile
Appearance
External links
FAQ
Does NovelAI recognize wakiyama tamami?
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 wakiyama tamami.
How do I write wakiyama tamami in a prompt?
Write "wakiyama tamami" 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.