About the marcille donato tag
marcille donato is a character tag that NovelAI Diffusion can use. On Danbooru it has 4,210 posts, and its best-rated still image scores 1,202. 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 marcille donato
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 marcille donato in a prompt
Put the subject first, then this tag, then quality tags.
marcille donato, solo, best quality, masterpiecewlop, marcille donato, 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 ▴
Main character of Dungeon Meshi and one of the original members of Laios' party. She is an elven mage who wields a tall wooden mage staff that forms a loop at the top, called Ambrosia. She has long blonde hair and green eyes, and wears a blue robe with matching blue hooded capelet.
She hates eating monsters, which (given the manga she's stuck in) is a source of constant frustration, and has led to a good amount of memes and emotes.
Appearance
External links
FAQ
Does NovelAI recognize marcille donato?
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 marcille donato.
How do I write marcille donato in a prompt?
Write "marcille donato" 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.