PixAI会員
PixAI
PixAI
Generate
Sign in
ホーム
生成
モデル
Studio
NEW
コンテスト
Mio.2 で作成
ツールボックス
NEW
ガイド

ユーザーLoRA

XL
キャラ

CottontailVA - MSM Talent [PonyXL]

創作

  • AI画像生成
  • AI動画生成
  • ツールボックス
  • テーマジェネレーター
  • LoRA学習
  • Mio.2 エージェント
  • Studio

探索

  • 人気タグ
  • ランキング
  • モデルマーケット
  • コンテスト
  • お知らせ

PixAIについて

  • ガイド
  • PixAI ブログ
  • Tsubaki.2
  • マスコットのミオに会う
  • コンテンツ規則

料金とヘルプ

  • 会員
  • クレジットパック
  • お問い合わせ

アプリ

  • PixAI アプリを入手
  • App Store
  • Google Play
© 2026 PixAI
  • 利用規約
  • プライバシーポリシー
  • 著作権ポリシー
  • 特定商取引法
CottontailVA -  MSM Talent [PonyXL] - AI Model cover image
アップロード日時
2024/09/23 18:35
採用数
545
レビュー
大好評  (4)
トリガーワード

cottontailva, rabbit ears, large breasts, multicolored hair, pink hair, blue hair, heterochromia, pink eye, blue eye, pink bunny costume, fishnet pantyhose, pink pumps, heels,

権限
  • 画像生成と共有を許可する
  • ユーザーによるモデルのダウンロードを許可する
  • 生成画像の商用利用を許可する

おすすめLoRA

Viera Race Specific Equipment (Final Fantasy XIV) - AI Model cover image

ユーザーLoRA

Viera Race Specific Equipment (Final Fantasy XIV)
11
ymir fritz my wife ♡♡♡ - AI Model cover image

ユーザーLoRA

ymir fritz my wife ♡♡♡
8
学生服/school uniform(XL,pony) - AI Model cover image

ユーザーLoRA

学生服/school uniform(XL,pony)
21
シャルロット(原神)/genshin impact/charlotte - AI Model cover image

ユーザーLoRA

シャルロット(原神)/genshin impact/charlotte
9

詳細説明

Character LoRA for CottontailVA's Vtuber "original" model (the blue and pink bunny girl model, not the new goth bunny girl model).If you like the LoRA, please leave a reaction, review and/or tip. Enjoy!UsageTrigger word: cottontailvaSupport tags (optional, use to increase consistency): heterochromia, pink eye, blue eye, gradient hair, pink hair, blue hairRecommended strength 0.8 - 1.0Use Clip skip=1 or Clip skip=2 (other values may also work, use at own risk)Works best at 1024x1024. Similar resolutions (e.g. 800x1200) also work well.ExampleSee preview images (generated with pruned version)Unpruned vs. Pruned vs. LiteI offer three variations of the model, which only differ in the file size and quality. Pick the one that best suits your preferences. If you can not decide, simply pick the "pruned" version. Note that the quality is relative, even the lite version usually produces images which closely resemble the intended subject.unpruned: The originally trained model. Largest file size, best quality. Pick if you want the best possible quality, at the cost of disk space.pruned: Downsized model. Almost same quality as the unpruned version, with noticably smaller file size.lite: Drastically downsized model. Smallest file size. Still has good quality, but noticeably worse than unpruned and pruned.Using training dataFeel free to contact me if you want access to the training data.The training data (images and tags) have been mostly sourced from rule34.xxx and other images boards. They have been cleaned up manually by me. When using the training data or modified versions of it to create models or datasets, please credit me as appropriate.NotesSimply had to make a LoRA of everyones favorite scuffed, 6'9" tall, dommy-mommy bunny girl. It has some issues, especially in getting the hair right, but that is mostly because every artist draws her hair different, so the dataset is pretty inconsistent. Other than that, it also mixes up the sides of her blue/pink eye and blue/pink ear, but that's just SD struggling with such concepts in general.I also messed up the comparison image a little, because I dared to use weights on tags which SDXL models seem to hate. I only noticed after already generating all of the preview images, so I was too lazy to fix it.DisclaimerThis LoRA is not affiliated with the character it is based on. If you like the character, check them out at one of their socials:https://twitter.com/cottontailvahttps://www.twitch.tv/cottontailvahttps://www.youtube.com/@CottontailVA

コメント