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

Conversational creation

AI Tools
NEW
Guide

User LoRA

DiT.2XL
Style

⊹ 雫 / Droplet ⊹

AI Tools

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

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
⊹ 雫 / Droplet ⊹ - AI Model cover image
Trained by
Avatar image of *Mimi*

*Mimi*

Train Your Own LoRA
Uploaded at
Apr 17, 2026, 5:23 PM
Uses
3.3k
Earned
280,070
Reviews
Excellent  (3)
Trigger Words

masterpiece, ultra detailed, droplets_floating_in_the_air, droplets_in foreground, depth_of_field, suspend_moment, floating_hair, white_background,

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

Recommended LoRAs

Victorique de Blois - GOSICK - SDXL - AI Model cover image

User LoRA

Victorique de Blois - GOSICK - SDXL
1
martha Rider [Fate Grand Order] - AI Model cover image

User LoRA

martha Rider [Fate Grand Order]
16
ラゼ・オーファン - AI Model cover image

User LoRA

ラゼ・オーファン
4
Vanitas No Carte anime style - AI Model cover image

User LoRA

Vanitas No Carte anime style
20

Description

This LoRA is a “droplet‑expression specialized” model trained on data derived from DALL‑E. Its purpose is to add softly floating droplets to characters and backgrounds, and the training data does not include any underwater images. Therefore, it is originally designed to generate only droplets. However, depending on compatibility with the base model, the output may sometimes depict subjects as if they are underwater, or produce splash‑like water effects. In rare cases, it may also generate non‑water objects hanging from above. When such behavior occurs, adding “water” before “droplets” in the prompt can help resolve the issue.

このLoRAは、DALL‑E由来のデータを用いて学習された「水滴表現専用」のモデルです。人物や背景に柔らかく浮かぶ雫を追加することを目的としており、学習データには水中の画像は一切含まれていません。そのため、本来は水滴のみを生成する設計ですが、ベースモデルとの相性によっては被写体が水の中に入ったような描写になったり、スプラッシュ状の水が現れる場合があります。また、まれに水ではない物体が上からぶら下がっているような表現になることもあります。こうした挙動が出た際には、プロンプト内で「droplets」の前に「water」を加えることで改善される場合があります。

Comments