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

ユーザーLoRA

XL
背景

Tzeentch Background (Landscape) (Illustrious) (AD)

#風景#風景#ウォーハンマー・ファンタジー

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
Tzeentch Background (Landscape) (Illustrious) (AD) - AI Model cover image
アップロード日時
2026/04/05 3:13
採用数
51
レビュー
大好評  (1)
トリガーワード

TzeentchBackground, background, landscape

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

詳細説明

This is an Illustrious background lora for backgrounds and landscapes typical of lands corrupted by Tzeentch in the Warhammer fantasy and Warhammer 40K series.A weight of 1 to 1.5 works well with this with most models and depending on certain models, with best results tending to be around 1.25. Sampling Steps of 15 to 35 works well with most models, as does a CFG Scale of 3.5 to 7.5.Prompts for this lora are ( TzeentchBackground, background, landscape, ). It helps the picture be made if one were to add ( purple blue pink, glimmering surfaces, glowing surfaces, dark picture, vivid colors, indigo ground, blue trees, ) to the positive prompts and ( floating head, head, grass, skulls, pillars, ) to the negative prompts. I remade this lora several times. The one I am posting is the best result that doesn't show too many characters or floating islands, yet tends to show pillars and heads for some reason, hence why I made the suggestion for the negative prompts.This version of this lora nearly drove me mad. Besides needing to be remade three times, like the other two, this one I had spent the better part 12 hours trying to figure out the right prompts and such to use. There was a massive tendency to either display floating crystals, a shadow figure or creature, or an anime women in the front and center of the results with most models despite the sample pictures not even having an of that in the file. This is one of those times I curse the checkpoints for either not working nicely with the prompts or fanatically focusing on characters that ought not be in a landscape picture. Please look to the samples I post to get an idea of how to prompt the things if you yourself are having problems with the thing. In the end I bit the thumb and used other loras to help improve the image.

コメント