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

Seiichi Kinoshita - Illustrious (SHIROBAKO)

#男性#肥胖#褐色皮膚男性#肌肉男#熟男

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
Seiichi Kinoshita - Illustrious (SHIROBAKO) - AI Model cover image
上傳時間
2026年1月4日 凌晨3:26
使用數
300
評論
暫無評論
觸發詞

seiichikino, male focus, glasses, blue shirt

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

カレン(タイムボカン24)calen - AI Model cover image

用戶LoRA

カレン(タイムボカン24)calen
2
座剣邪寧代 - AI Model cover image

用戶LoRA

座剣邪寧代
3
Toudou Kasane 藤堂重音 藤堂かさね | Hoshizora e Kakaru Hashi 架向星空之桥 星空へ架かる橋 | Illustrious - AI Model cover image

用戶LoRA

Toudou Kasane 藤堂重音 藤堂かさね | Hoshizora e Kakaru Hashi 架向星空之桥 星空へ架かる橋 | Illustrious
0
Sawa Nakamura (Aku no Hana Manga) - AI Model cover image

用戶LoRA

Sawa Nakamura (Aku no Hana Manga)
5

描述

Main prompt tags: seiichikino, male focus, glasses, blue shirt <----------- should always be includedStyle controlfor the original anime TV show style add following positive prompt: anime screenshotto avoid the style from the anime show, remove anime screenshot from positive prompt and put it into negative promptRecommended sampler settings:- Euler Ancestral Scheduler: Normal/Karras CFG: 5.0-6.0 Steps: 20-25 Lora strength: 1.0Prompt tips (green - positive, red - negative)- chubby if your model doesn't generate him fat enough- glasses, blue shirt - base clothes- striped shirt - alt shirt- stubble, facial hair into negative prompt to avoid facial hair that sometimes is generated- shirt under shirt and undershirt into negative prompts - for some reason Illustrious loves adding a undershirt to his clothes, also try generating using lower CFG / step count / LORA strength (this is still canon tho - he wears two shirts in some episodes)The LoRa was tested with two Illustrious checkpoint merges and works well with them:WAI-NSFW-illustrious-SDXL v12.0 - recommendedIllustrious XL personal mergeTo improve details:- generate using higher base resolution (e.g. 1216x1216) or use latent upscaling / highres fix - especially when trying to do full body poses- for fixing wonky face/eyes I use FaceDetailer node (comfyui) + Adetailer Face finder modelLast image in the gallery can be imported into ComfyUI with a basic workflow:Just Copy&Paste into ComfyUI (you might be required to download missing nodes)

評論