About the sweet lolita tag
sweet lolita is a fashion tag that NovelAI Diffusion can use. On Danbooru it has 1,659 posts, and its best-rated still image scores 367. 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 sweet lolita
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 sweet lolita in a prompt
Put the subject first, then this tag, then quality tags.
1girl, solo, sweet lolita, best quality, masterpiecewlop, 1girl, sweet lolitaThe 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
Sweet Lolita or "Amaloli" ( アマーロリ ) is a substyle of Lolita fashion heavily influenced by Rococo styles as well as Victorian and Edwardian children's clothing. Focusing on the child and fantasy aspects of Lolita, the Sweet Lolita style adopts the basic Lolita format and uses lighter colors.
It has all the traditional Lolita elements but with a wider choice of colors, like light pinks, baby blues, whites, and even sometimes colors like lavender, canary yellow and mint green. This is also where you'll find the most fluff and frills.
Examples
See also
FAQ
Does NovelAI recognize sweet lolita?
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 sweet lolita.
How do I write sweet lolita in a prompt?
Write "sweet lolita" 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.