About the eremes guile tag
eremes guile is a character tag that NovelAI Diffusion can use. On Danbooru it has 389 posts, and its best-rated still image scores 37. 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 eremes guile
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 eremes guile in a prompt
Put the subject first, then this tag, then quality tags.
eremes guile, solo, best quality, masterpiecewlop, eremes guile, 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
Show the wiki text ▾Hide ▴
Assassin Cross of the Bio Lab in Ragnarok Online. He has long blue hair and red eyes. Childhood friend of Cecil Damon and friends with Kathryne Keyron. Becomes a Guillotine Cross in the Tomb of Honor.
Eremes dropped a particularly difficult item to craft, making him one of the most popular monsters to hunt. Because of this, he appeared in Ragnarok Online 2: Legend of the Second.
[spoilers]Died fourth.[/spoilers]
External Links
Profile Card iW Database RateMyServer Database Divine-Pride Database
FAQ
Does NovelAI recognize eremes guile?
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 eremes guile.
How do I write eremes guile in a prompt?
Write "eremes guile" 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.