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

WAI-NSFW-illustrious-SDXL

AI 工具
  • AI 動漫生成器
  • 動漫手辦生成器
  • 角色設定圖生成器
  • 雜誌封面生成器
  • 玩偶生成器
  • 巨型雕像生成器

探索

  • 熱門 Tags
  • 排名
  • 模型市集
  • 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
WAI-NSFW-illustrious-SDXL - AI Model cover image
上傳時間
2024年11月18日 清晨5:33
使用數
978k
評論
非常好  (64)
取樣步數

30

CFG Scale

7

負面

bad quality,worst quality,worst detail,sketch,censor,

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

DMD2 - AI Model cover image

用戶LoRA

DMD2
6.43k
Luna (The Boondocks) [Pony/IL] - AI Model cover image

用戶LoRA

Luna (The Boondocks) [Pony/IL]
8
lisa christy ill - AI Model cover image

用戶LoRA

lisa christy ill
4
Pony: People's Works - AI Model cover image

用戶LoRA

Pony: People's Works
191

描述

If you want to use more my checkpoint online generation, please visit here.https://tensor.art/u/762555264535746522All example images are generated at 1024x1360, without using AD and hires fix.Online generation has been added.Character referenceIllustrious Character Embedding Map | CivitaiStyle referenceIllustrious Style Tags Embedding Map | Civitaiv7Adjusted the color balance,Reduced the probability of overexposure,Added more composition elements, incorporated some special effects,More NSFW.Recommended settings:Steps: 30CFG scale: 5-7Sampler: Euler aNot very necessary to use ADetailer correctionPositive Promptmasterpiece,best quality,amazing quality,Negative PromptBase:bad quality,worst quality,worst detail,sketch,censor, Optional:simple background,transparent backgroundV6Positive Prompt and Negative Prompt is Updated, please check again.More NSFW , overall balance adjustment.Recommended settings:Steps: 30CFG scale: 5-7Sampler: Euler aNot very necessary to use ADetailer correctionPositive Promptmasterpiece,best quality,amazing quality,Negative PromptBase:bad quality,worst quality,worst detail,sketch,censor, Optional:simple background,transparent backgroundV5I further adjusted the weights to better support the SDXL and Pony LoRA, optimizing some of the composition logic and backgrounds.Recommended settings same with v2V4Increased more training materials and adjusted the default weights.Some of the pony LoRA can also be used, and you may need to adjust the weight to over 1 for testing.Recommended settings same with v2V3adjusted the weights and changed the default style.Recommended settings same with v2V2I adjusted the default style weight to make the model easier to use. I optimized the composition and human anatomy, and added more NSFW materials.The example images are all generated directly at 1360x1024. NO AD NO hires fix.Please try experimenting with artists and characters on your own. I have only tested a portion of popular artists and characters that can be used directly.Recommended settings:Steps: 30CFG scale: 5-7Sampler: Euler aNot very necessary to use ADetailer correctionPositive Promptmasterpiece,best quality,amazing quality,very aesthetic,absurdres,newest,Negative Promptlowres,(bad quality,worst quality:1.2),bad anatomy,sketch,jpeg artifacts,ugly, poorly drawn,(censor),blurry,watermark,simple background,transparent backgroundv1Base: IllustriousXLSince the adjustments were minimal, the artists and characters available in the base model can still be used directly.Recommended settings:Steps: 30CFG scale: 7Sampler: Euler aNot very necessary to use ADetailer correctionPositive Promptmasterpiece, best quality, high resolution, absurdres,uncensored,Negative Promptworst quality,bad quality,bad hands,very displeasing,extra digit,fewer digits,jpeg artifacts,

留言2