About the armin arlert tag
armin arlert is a character tag that NovelAI Diffusion can use. On Danbooru it has 1,328 posts, and its best-rated still image scores 181. 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 armin arlert
Follows composition and expression instructions closely, so the effect shows in a tidy form.
Reacts to the tag more strongly, so its effect is easier to see.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing armin arlert in a prompt
Put the subject first, then this tag, then quality tags.
armin arlert, solo, best quality, masterpiecewlop, armin arlert, soloThe 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
A character from Shingeki no Kyojin.
Childhood friend of Eren Yeager and Mikasa Ackerman and one of the graduates from the 104th Trainees Squad. Physically weak and often prone to self-doubt, Armin did not make it inside the Top 10 of the 104th. Nevertheless, his heart and high intelligence make him a very valuable soldier. Declaring that he'd rather be dead than be a burden, Armin joined the Scouting Legion despite Eren's protests. He shares Eren's dream of exploring the world outside the walls.
Voiced by Inoue Marina.
FAQ
Does NovelAI recognize armin arlert?
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 armin arlert.
How do I write armin arlert in a prompt?
Write "armin arlert" 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.