V4.5Faces
▾
>

:i

4,084 Danbooru posts · top score 1,351 · V4.5

seed 1234Tap an image to enlarge
AI-generated NovelAI V4.5 sample of the ":i" tag
V4.5NAI Diffusion Anime V4.5
Prompt:i, 1girl, solo, best quality, masterpiece, cowboy shot, sfw, fully clothed, looking at viewer

About the :i tag

:i is a face tag that NovelAI Diffusion can use. On Danbooru it has 4,084 posts, and its best-rated still image scores 1,351. 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 :i

V5

Follows composition and expression instructions closely, so the effect shows in a tidy form.

V4.5

Reacts to the tag more strongly, so its effect is easier to see.

ILLUST

WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.

Writing :i in a prompt

Put the subject first, then this tag, then quality tags.

Basic1girl, solo, :i, best quality, masterpiece
With artistwlop, 1girl, :i

The 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 ▾

Puffing out both cheeks, forming a :I shape with the mouth. Similar to :T, except with lines at both sides of the mouth. Usually indicates that the character is pouting, eating, having their cheeks squashed, puffing their cheeks, or holding their breath.

Actually :I (with serif) but not capitalized due to technical restrictions and may be confused with lowercase "l"(L).

Examples

See also

Source: Danbooru wiki · :i ↗

FAQ

Does NovelAI recognize :i?

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 :i.

How do I write :i in a prompt?

Write ":i" 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.