V4.5Characters
▾
>

haimiya mio (kamiyama sumu)

102 Danbooru posts · top score 61 · V4.5

seed 1234Tap an image to enlarge
AI-generated NovelAI V4.5 sample of the "haimiya mio (kamiyama sumu)" tag
V4.5NAI Diffusion Anime V4.5
Prompthaimiya mio (kamiyama sumu), 1girl, solo, best quality, masterpiece, cowboy shot, sfw, fully clothed, looking at viewer

About the haimiya mio (kamiyama sumu) tag

haimiya mio (kamiyama sumu) is a character tag that NovelAI Diffusion can use. On Danbooru it has 102 posts, and its best-rated still image scores 61. 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 haimiya mio (kamiyama sumu)

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 haimiya mio (kamiyama sumu) in a prompt

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

Basichaimiya mio (kamiyama sumu), solo, best quality, masterpiece
With artistwlop, haimiya mio (kamiyama sumu), solo

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.

FAQ

Does NovelAI recognize haimiya mio (kamiyama sumu)?

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 haimiya mio (kamiyama sumu).

How do I write haimiya mio (kamiyama sumu) in a prompt?

Write "haimiya mio (kamiyama sumu)" 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.