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

用戶LoRA

XL
角色

Meguri Shiromeguri (school uniform) / やはり俺の青春ラブコメはまちがっている。 / SNAFU

創作

  • AI 圖像生成器
  • AI 動畫生成器
  • 工具箱
  • 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

  • App Store
  • Google Play
© 2026 PixAI
  • 服務條款
  • 隱私政策
  • 版權政策
  • 特定商業交易法
Meguri Shiromeguri (school uniform) / やはり俺の青春ラブコメはまちがっている。 / SNAFU - AI Model cover image
上傳時間
2026年6月9日 凌晨3:32
使用數
20
評論
暫無評論
觸發詞

olive eyes,parted bangs,red hairclip,pink hairclips,olive hair,long hair,twin braids,, black jacket,white collared shirt,red neckribbon, white plaid skirt, balck kneehighs,brown loafers,

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

MUCU style (illustrious) - AI Model cover image

用戶LoRA

MUCU style (illustrious)
5
Kyrie Florian - Mahou Shoujou Lyrical Nanoha - AI Model cover image

用戶LoRA

Kyrie Florian - Mahou Shoujou Lyrical Nanoha
8
FFXIV LALAFELL - AI Model cover image

用戶LoRA

FFXIV LALAFELL
3
Amane Konata | AkashicPulse v4.0 - AI Model cover image

用戶LoRA

Amane Konata | AkashicPulse v4.0
4

描述

https://civitai.red/models/2597819/meguri-shiromeguri-school-uniform-snafu ■ Learning Model = illustriousXL_v01■ Operation check = JANKU Trained+v6.0■ Recommended generation environmentGenerate Model = JANKU Trained+(v5.0 or v6.0) / WAI-illustrious-SDXLSampling method = Euler aSchedule type = KarrasSampling steps = 30CFG Scale = 5LoRA weight = 0.6-0.9■ Positive prompthighres, highly detailed, amazing quality, very aesthetic, +α = anime screenshot,■ Negative prompt123qweasdz, 3D, deformation, (worst quality, low quality,normal quality), lowres, monochrome, grayscale, watermark, flat colour, no shading,■ caption design・Adding "anime screenshot" to the positive prompt makes the output closer to anime original art. Removing it slightly reduces character fidelity, but improves the quality of highlights, shading, and other texture details.・The caption design uses "123qweasdz" as a dummy token to absorb non-character noise from the dataset (such as background variations and dataset-specific artifacts). Placing it in the negative prompt suppresses those unwanted elements while preserving character features and clothing, which significantly improves generation stability.■ Recommended resolution21:9 = 1806 x 7742:1 = 1672 x 83616:9 = 1576 x 8873:2 = 1448 x 9654:3 = 1365 x 10241:1 = 1182 x 1182

評論