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
ポーズ

Splits positions [Pony XL]

#開脚#開脚

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
  • クレジット表記
  • 特定商取引法
Splits positions [Pony XL] - AI Model cover image
アップロード日時
2025/06/27 1:37
採用数
4.3k
レビュー
レビューがありません
トリガーワード

horizontal splits, vertical splits, upside-down splits

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

Ssulal/スラル   (Rance 10/ランス10/兰斯10)  [Illustrious] - AI Model cover image

ユーザーLoRA

Ssulal/スラル (Rance 10/ランス10/兰斯10) [Illustrious]
5
Brown Dust 2 - Spatti - AI Model cover image

ユーザーLoRA

Brown Dust 2 - Spatti
4
Erika (Pokemon) - AI Model cover image

ユーザーLoRA

Erika (Pokemon)
44
Psylocke (3 Outfits) (Marvel Rivals) - AI Model cover image

ユーザーLoRA

Psylocke (3 Outfits) (Marvel Rivals)
12

詳細説明

While working on another lora I noticed that Pony doesn't really know the horizontal splits position (it does know vertical splits however).Versions1.0: LyCORIS/Dora (requires Automatic1111 1.9+) with extended dataset and improved tagging0.6: Standard Lora with smaller datasetAdetailer is recommended for both versionsTagsThe model knows the following 3 main positions (bold are the tags)horizontal splitsvertical splitshorizontal splits,upside-downWith the following supportive tags you can generate most splits positions:top-down bottom-uparched backupside-downon stomachon backbent over...Perspective tagsfront viewfrom behindfrom belowfrom abovefrom side...NegativesIf you notice that the model goes too much 3d, put "3d" in the negative prompt. Some of the images in the dataset leaned a bit too much into 3d for my liking, but I wanted the model to learn the concept better."watermark" helps agains the watermark and logos, but unfortunately the model still struggles with it a bit (kinda burnt myself out manually editing the dataset images to get rid of background and watermarks, but as it turned out, this also worsened the model T_T)I've been told that the model quite frequently seems to create two females instead of one. If that is the case for you, specifying 1girl and/or solo female in positive and 2girls in the negative prompt might help. Most likely this happens because there is one image in the training dataset, which has two females in a vertical pose, because I wanted the model to learn to also support multiple persons.I will try to fix it in the next versionResolutionsI mostly use the following resolutions, not sure if others work:1216x8321344x7681024x1024 (sometimes the model tries to fit in the full body making the legs unproportionally short)768x1344832x1216I used a new training method and I'm not entirely content with the results yet, so I will probably retrain the model using my old method, but it will take some time to adjust the dataset etc.For now enjoy the model, it should work pretty well for most casesHappy prompting, I'm looking forward to your creations!

コメント