PixAI 會員
PixAI
PixAI
Generate
Sign in
主頁
生成
模型
Studio
NEW
比賽
用 Mio.2 創作
AI 工具
NEW
指南

SDXL

Banana Splitz XL

創作

  • AI 圖像生成器
  • AI 動畫生成器
  • AI 工具
  • 藝術主題產生器
  • 訓練 LoRA
  • Mio.2 智慧助手
  • Studio

探索

  • 熱門 Tags
  • 排名
  • 模型市場
  • 比賽
  • 新聞

關於

  • 指南
  • PixAI 部落格
  • Tsubaki.2
  • 認識 Mio,我們的吉祥物
  • 內容規則

定價與說明

  • 會員計劃
  • 購買點數
  • 聯絡

移動端 APP

  • 下載 PixAI App
  • App Store
  • Google Play
© 2026 PixAI
  • 服務條款
  • 隱私政策
  • 版權政策
  • 第三方內容聲明
  • 特定商業交易法
Banana Splitz XL - AI Model cover image
上傳時間
2025年11月5日 下午2:14
使用數
294k
評論
非常好  (15)
許可權
  • 允許圖片生成與分享
  • 允許使用者下載此模型
  • 允許生成圖片用於商業用途

推薦 LoRA

StonicStonic artstyle - AI Model cover image

用戶LoRA

StonicStonic artstyle
10
Ramwam_AI Style - AI Model cover image

用戶LoRA

Ramwam_AI Style
1.27k
🍷 3GS 【Artist Style】︱スタイル - AI Model cover image

用戶LoRA

🍷 3GS 【Artist Style】︱スタイル
59
Suigi (26_suigi) Style Lora (Illustrious / Pony) - AI Model cover image

用戶LoRA

Suigi (26_suigi) Style Lora (Illustrious / Pony)
73

描述

https://civitai.com/models/1261882

BANANA SPLITZ A 'high-quality' kemono-anime hybrid with crisp linework, soft but dimensional shading, and a balanced 2.5D aesthetic.

MERGE DETAILS: 📌 Merge 1: Toon-Kemono Base Weighted Sum: Mol Kun Mix + FurryToonMix (Alpha 0.65) ✅ Mol Kun Mix: Provides kemono depth, shading, and anatomy accuracy. ✅ FurryToonMix: Enhances cartoon elements without over-exaggeration.

📌 Merge 2: Detailed Kemono Refinement Similliar Add Difference: (Fifth Mix + Mol Kun Mix) + FurryToonMix (Alpha 0.5 Beta 0.3) ✅ Fifth Mix: Enhances fur details & kemono shaping.

📌 Merge 3: Base Refinement DARE Merge: Merge1 + Merge2 = KemonoStyleMerge (Alpha 0.6) ✅ Balances deep shading, lighting, and stylization. ✅ Creates a high-quality, fully checkpoint-based foundation.

2️⃣ Baking LoRAs Into Separate Checkpoints 🎯 Goal: Convert LoRAs into stable models before merging into KemonoStyleMerge.

1️⃣ Bake Greyyy Style) Weighted Sum: FurryToonMix + Greyyy Style = GRYBaked (alpha 0.4) ✅ Greyyy Style LoRA baked into FurryToonMix.

2️⃣ Bake Toto Style weighted Sum: Mole Kun Mix + TOTO Style Lora = TOTBaked (Alpha 0.4) ✅ TOT (Toto Style LoRA) baked into Mol Kun Mix.

3️⃣ Bake Haps Style Weighted Sum: Fifth Mix + HAPS Style Lora = HAPBaked (Alpha 0.4) ✅ HAP (Haps Style LoRA) baked into The Fifth Mix.

3️⃣ Merging LoRA-Enhanced Models Into the Final Checkpoint 🎯 Goal: Merge the LoRA-enhanced models into the main base.

Weighted Sum: KemonoStyleMerge + GRYBaked = StyledKemono (Alpha 0.5) ✅ Greyyy’s stylization integrated while preserving kemono structure.

Weighted Sum: StyledKemono + TOTBaked = StyledKemono2 (Alpha 0.5) ✅ Toto’s influence blended into final mix.

Weighted Sum: StyledKemono2 + HapBaked = FinalStyle ✅ HAP (Haps Style LoRA) baked into The Fifth Mix. This concludes all merges. 🎯 Merge Complete!

評論