About the kunimi tama tag
kunimi tama is a character tag that NovelAI Diffusion can use. On Danbooru it has 766 posts, and its best-rated still image scores 99. 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 kunimi tama
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 kunimi tama in a prompt
Put the subject first, then this tag, then quality tags.
kunimi tama, solo, best quality, masterpiecewlop, kunimi tama, 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 ▴
One of the main heroines in Heaven Burns Red, a member of Team 31A.
Genetically-engineered tiny-tot battleship captain. Despite her tiny size, she's a former captain of a warship Kotetsu Maru which was defeated on the Sea of Okhotsk. She's a lot sillier than she realizes.
Appearance
- !asset #24893234: Default
- : Rocking Cradle (casual / swimsuit)
- : Elemental Of The Magic Kingdom (magical girl)
- : Charge!! Air Bass (new year)
- : Coral Reverie (swimsuit)
- : Twilight Memories (suit)
- : Welcome To Nightmare Parade (halloween)
- : Special Night Girls Jam (rocker)
FAQ
Does NovelAI recognize kunimi tama?
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 kunimi tama.
How do I write kunimi tama in a prompt?
Write "kunimi tama" 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.