.webp)
.webp)
.webp)
.webp)
.webp)
.webp)
About the train 90 tag
train 90 is an artist tag that NovelAI Diffusion can use. On Danbooru it has 127 posts, and its best-rated still image scores 36. 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 train 90
Follows pose and expression instructions closely. Good for clean standing portraits.
Picks up face shape, line and palette more strongly. Good when you want the style to lead.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing train 90 in a prompt
Put the artist tag near the front, then add the subject and quality tags.
train 90, 1girl, solo, best quality, masterpiecetrain 90, hatsune miku, 1girltrain 90, natsu (anta tte hitoha), 1girlThe mix example uses natsu (anta tte hitoha), 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.
From the Danbooru wiki
Artist, mangaka. The author of the Waguruma! webcomic adaptation.
Pen-name: train The other names: 電車 or 戦車 Most used user ID: train_90 Circle & site name: trainでGO!! The other circle: 石の上のさかな (Ishimori Sakana's circle)
FAQ
Does NovelAI recognize train 90?
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 train 90.
How do I write train 90 in a prompt?
Write "train 90" near the front of the prompt and separate it from other tags with commas.
Which artists draw in a similar style to train 90?
natsu (anta tte hitoha), fukuoka katsumi, tonari (ichinichime azuma) are the closest on this site, judged from the V4.5 samples.
Should I use V5 or V4.5?
V4.5 gives a stronger train 90 look. V5 gives steadier poses and fewer artifacts.