About the lilpa tag
lilpa is a character tag that NovelAI Diffusion can use. On Danbooru it has 346 posts, and its best-rated still image scores 328. 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 lilpa
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 lilpa in a prompt
Put the subject first, then this tag, then quality tags.
lilpa, solo, best quality, masterpiecewlop, lilpa, 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 Korean-speaking VTuber affiliated with WAKTAVERSE.
She has dark blue hair with streaked hair and orange eyes.
Appearance
Official costumes with a model
- : Gu-lilpa
- : NewLilpa (1st avatar)
- : NewNewLilpa (2nd avatar)
- : LILPACON
- : Goddess of the Night
- : 2025 ISELAB
- : Nameless
Songs
- : Lady (Cover of Kenshi Yonezu's)
- : KIDDING (3rd Single Album)
See also
- Bakjwi - Her fans
- Ddilpa - Her chibi character
- Blueberry-Chan - Her alt maid character
- Nyongpa (Lilpa) - Her alt dragon character
External links
- YouTube: 릴파 lilpa
- SOOP: 릴파♬
- Twitch: lilpaaaaaa
- Instagram: @lilpaaaaaa_
FAQ
Does NovelAI recognize lilpa?
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 lilpa.
How do I write lilpa in a prompt?
Write "lilpa" 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.