.webp)
About the hitomi (doa) tag
hitomi (doa) is a character tag that NovelAI Diffusion can use. On Danbooru it has 403 posts, and its best-rated still image scores 352. 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 hitomi (doa)
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 hitomi (doa) in a prompt
Put the subject first, then this tag, then quality tags.
hitomi (doa), solo, best quality, masterpiecewlop, hitomi (doa), 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 in Dead or Alive, first appearing in Dead or Alive 3.
In DOA3, she wears a denim jacket over a cropped white tank top, and jeans. In DOA4, she wears a cropped yellow vest, a brown belt, jeans,. Her most well-known outfit in DOA5 consists of a cropped white tank top with a pink trim, torn jeans, a studded belt, and a pair of white sneakers. Her appearance in DOAD consists of a cropped black tank top with a pink trim. She has long brown hair, a pink hairband, and red fingerless gloves in every appearance.
Appearance
- : Dead or Alive 5.
FAQ
Does NovelAI recognize hitomi (doa)?
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 hitomi (doa).
How do I write hitomi (doa) in a prompt?
Write "hitomi (doa)" 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.