V4.5Copyright
▾
>

oshi no ko

7,628 Danbooru posts · top score 1,211 · V4.5

seed 1234Tap an image to enlarge
AI-generated NovelAI V4.5 sample of the "oshi no ko" tag
V4.5NAI Diffusion Anime V4.5
Promptoshi no ko, 1girl, solo, best quality, masterpiece, cowboy shot, sfw, fully clothed, looking at viewer
CharactersCHARACTERS IN OSHI_NO_KO · 7
[1/1]
arima kana
CHAR0x0000
0
hoshino ruby
CHAR0x0001
0
hoshino aquamarine
CHAR0x0002
0
hoshino ai
CHAR0x0003
0
memcho
CHAR0x0004
0
kurokawa akane
CHAR0x0005
0
saitou miyako
CHAR0x0006
0

About the oshi no ko tag

oshi no ko is a series tag that NovelAI Diffusion can use. On Danbooru it has 7,628 posts, and its best-rated still image scores 1,211. 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 oshi no ko

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 oshi no ko in a prompt

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

Basicoshi no ko, solo, best quality, masterpiece
With artistwlop, oshi no ko, 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 oshi no ko?

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 oshi no ko.

How do I write oshi no ko in a prompt?

Write "oshi no ko" 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.