PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generation
Models
Studio
NEW
Contest
Create with Mio.2
AI Tools
NEW
Guide

User LoRA

DiT.2XL
Style

Whimsique

AI Tools
  • AI Anime Generator
  • Anime Figure Generator
  • Character Sheet Generator
  • Magazine Cover Generator
  • Plushie Generator
  • Giant Statue Generator

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
Whimsique - AI Model cover image
Trained by
Avatar image of amy

amy

Train Your Own LoRA
Uploaded at
Aug 25, 2026, 6:53 PM
Uses
940
Earned
0
Reviews
Excellent  (4)
Trigger Words

whimsical gothic mixed-media illustration, scratchy uneven linework, (thin creepy irregular handwritten letters:1.2), weathered edges, desaturated colors,extremely slim and balanced creepy-cute body, ((tiny round black dot pupil exactly in the center of each white eye:1.2)), thick short black eyelashes evenly surrounding the entire circumference of each eye,tiny dot nose, thin tiny straight mouth,thick voluminous hair, minimal open background, eerie but cute, flat illustrative composition

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Description

遊び心のある顔やスタイル、線画が特徴です。

ゴシックホラーなフォントの英語が入りやすいです。

OCなど顔に特徴がある場合はモデル表紙のような顔にならないことがあります。

Tsubaki.2はスタンダード以上が推奨ですがTsubaki.2での試作はほぼしてないのでこれから検証していきます。

It is characterized by playful facial features, a distinct style, and line-art aesthetics.

It pairs well with English text in gothic horror-style fonts.

If the character (such as an OC) has unique facial features, the result may not always look like a standard model cover image.

While the "Standard" setting or higher is recommended for Tsubaki.2, I have conducted very few test runs with it so far, so I will be verifying its performance moving forward.

Comments