V4.5Artists
▾
>

josal

77 Danbooru posts · top score 313 · V4.5 / ILLUST

Same seed · seed 1234Tap an image to enlarge
AI-generated NovelAI V4.5 sample of the "josal" tag
V4.5NAI Diffusion Anime V4.5
AI-generated NovelAI ILLUST sample of the "josal" tag
ILLUSTWAI illustrious SDXL v17
Promptjosal, 1girl, solo, best quality, masterpiece, cowboy shot, sfw, fully clothed, looking at viewer

Artists with a similar style

Ranked from this site's V4.5 samples, not the artists' own works.
AI-generated NovelAI V4.5 sample of the "anza tomo" tag♥0
AI-generated NovelAI V4.5 sample of the "hayama kazusa" tag♥0
AI-generated NovelAI V4.5 sample of the "kodama yuu" tag♥0
AI-generated NovelAI V4.5 sample of the "kuzu (miduhana)" tag♥0
AI-generated NovelAI V4.5 sample of the "soba (saz)" tag♥0
AI-generated NovelAI V4.5 sample of the "akazawa red" tag♥0
AI-generated NovelAI V4.5 sample of the "wakamesan" tag♥0
AI-generated NovelAI V4.5 sample of the "suruga (xsurugax)" tag♥0
AI-generated NovelAI V4.5 sample of the "komainu (yamaha1997)" tag♥0
AI-generated NovelAI V4.5 sample of the "try (lsc)" tag♥0
AI-generated NovelAI V4.5 sample of the "hoshi usagi" tag♥2
AI-generated NovelAI V4.5 sample of the "clover (lapis lazure)" tag♥0

About the josal tag

josal is an artist tag that NovelAI Diffusion can use. On Danbooru it has 77 posts, and its best-rated still image scores 313. 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 josal

V5

Follows pose and expression instructions closely. Good for clean standing portraits.

V4.5

Picks up face shape, line and palette more strongly. Good when you want the style to lead.

ILLUST

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

Writing josal in a prompt

Put the artist tag near the front, then add the subject and quality tags.

Basicjosal, 1girl, solo, best quality, masterpiece
Characterjosal, hatsune miku, 1girl
Mixjosal, anza tomo, 1girl

The mix example uses anza tomo, the closest style on this site. 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 josal?

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 josal.

How do I write josal in a prompt?

Write "josal" near the front of the prompt and separate it from other tags with commas.

Which artists draw in a similar style to josal?

anza tomo, hayama kazusa, kodama yuu are the closest on this site, judged from the V4.5 samples.

Should I use V5 or V4.5?

V4.5 gives a stronger josal look. V5 gives steadier poses and fewer artifacts.