About the juniper actias tag
juniper actias is a character tag that NovelAI Diffusion can use. On Danbooru it has 429 posts, and its best-rated still image scores 433. 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 juniper actias
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 juniper actias in a prompt
Put the subject first, then this tag, then quality tags.
juniper actias, solo, best quality, masterpiecewlop, juniper actias, 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 ▴
Juniper's original moth girl character, now also her avatar as an Indie Virtual YouTuber. Has several more monstrous forms, as well as a baby form as a chibi moth.
Appearance
Regular costumes
- : 1st costume: Paladin of Lune
- : Full Moon
- : Idol (Armored/Fluffy) / v3.5
- : Tomboy / v5
- : Commander / v6
- !asset #37150551: 6th costume: Meep
- : Lab Experiment / Biological Mistake
- : Tactical / Hunter's Moon
- : Librarian / Disciple of Lune
- : Creature
- : Racing Queen
- : Snoth / Lamioth
- !asset #37150276: Admiral
- : Space Invader
Other costumes
- : Baby form (Goober)
See also
- Joomfie - fanbase
External links
FAQ
Does NovelAI recognize juniper actias?
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 juniper actias.
How do I write juniper actias in a prompt?
Write "juniper actias" 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.
