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

SD

AI Beast Mix v2.1

#ケモノ

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
AI Beast Mix v2.1 - AI Model cover image
アップロード日時
2024/03/26 23:56
採用数
16.6k
レビュー
大好評  (1)
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

Detailed Furry - AI Model cover image

ユーザーLoRA

Detailed Furry
90
Smoky mix 5 - AI Model cover image

ユーザーLoRA

Smoky mix 5
1
Volibear - League of Legends - AI Model cover image

ユーザーLoRA

Volibear - League of Legends
23
Wolpertinger Jackalope Bnuys - AI Model cover image

ユーザーLoRA

Wolpertinger Jackalope Bnuys
2

詳細説明

Not mine: https://civitai.com/models/90259?modelVersionId=389224

Author notes(https://civitai.com/user/Kotarou):

ABOUT

AI Beast Mix is a model merge to achieve semi-realism result for furry character with NSFW kink such as muscle or hyper. The model also can generate several style as well. Sometime the model generate human character which can be prevent by specify the furry species. If you're into hyper, this model capable support those kink and even work well with lot loras and lycoris. Prompt properly and this model will work wonders. prompt works well with e621 prompt tag.

Also, Hires.Fix is recommended to get better details and result.

Which one to Download?

Pruned fp16 - Suitable if you feel like to generate image only. May lack some data but still close enough generate image like full model. Good for those want to save disk space.

Full Model fp32 - Normal and Heavy model but contain all the data that you can use to merge with other model. Feel free to use this model to make your own mix.

VERSION 2.0

FINALLY! I able to make a huge leap of improving the model. There no secret I've involve lora into the merging recipe. It was an interesting procedure learning and research to try to understand how it works. Now the model are getting more closer to what I aim. Downside for now it generate bad hand/ fingers. In future update, I'll try update it but as for now I think it works great!

old models:-

version 1.3 - initial model where I experiment model merge to get the result I wanted.

version 1.4 - merge lot of model with proper merge order and structure

version 1.5 - change model merge method for better result

version 1.6 - attempt model merge close to realism

version 1.7 - try different merge model method

コメント