About the vill-v tag
vill-v is a character tag that NovelAI Diffusion can use. On Danbooru it has 677 posts, and its best-rated still image scores 525. 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 vill-v
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 vill-v in a prompt
Put the subject first, then this tag, then quality tags.
vill-v, solo, best quality, masterpiecewlop, vill-v, 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 Honkai Impact 3rd character. One of the Thirteen Flame-Chasers, codenamed Helix, voiced by Kanemoto Hisako in Japanese.
She is portrayed with short brown hair, brown eyes, and large breasts. Her default outfit, Helical Contraption, is composed of a brown steampunk-inspired shirt with a cleavage cutout, white shirt underneath, hip vents, brown short shorts, black gloves, brown hat, brown thighhighs, and black high heels.
Note: Despite their shared inventor-messenger traits, she should not be considered as the HI3 counterpart of Tribbie.
Appearance
- : Helical Contraption (default)
- : I'm The Storm
- : Summer 2024
FAQ
Does NovelAI recognize vill-v?
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 vill-v.
How do I write vill-v in a prompt?
Write "vill-v" 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.