.webp)
About the felt (re:zero) tag
felt (re:zero) is a character tag that NovelAI Diffusion can use. On Danbooru it has 373 posts, and its best-rated still image scores 394. 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 felt (re:zero)
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 felt (re:zero) in a prompt
Put the subject first, then this tag, then quality tags.
felt (re:zero), solo, best quality, masterpiecewlop, felt (re:zero), 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 ▴
A character from Re:Zero Kara Hajimeru Isekai Seikatsu. Felt is the girl who stole Emilia's insignia and is a candidate to become the 42nd King of Lugnica. Was given her name by Rom and doesn't know her real name.
She has red eyes and short blonde hair stylized in a short ponytail with hair between eyes. She is usually depicted wearing a black hair bow, brown fur-trimmed gloves, an open brown fur-trimmed vest, a black bandeau, single pantsleg, and brown footwear.
Also wears a yellow frilled dress with white elbow gloves during Royal Selection.
She is voiced by Akasaki Chinatsu.
Appearance
External links
FAQ
Does NovelAI recognize felt (re:zero)?
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 felt (re:zero).
How do I write felt (re:zero) in a prompt?
Write "felt (re:zero)" 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.