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

SDXL

Raehoshi Illust XL

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
 Raehoshi Illust XL - AI Model cover image
アップロード日時
2025/05/27 23:13
採用数
4.0k
レビュー
好評  (2)
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

https://civitai.com/models/846917/raehoshi-illust-xl?modelVersionId=1838339

Raehoshi Illust XL an enhanced iteration built upon the Illustrious XL model. It aims to elevate the visual style by addressing some of the limitations in the original, such as oversaturation and artifact noise. While these issues are not entirely eliminated, noticeable improvements have been made. The goal is to deliver a more polished, balanced output while staying true to the strengths of the base model.

Why Early Access?

Early access helps cover the cost of training and development. By purchasing early access, you're directly supporting the development of my models. If you'd like to support me further, you can also buy me a coffee on Ko-fi! Your support keeps the project going and ensures even better models in the future.

Recommended setting Positive prompt :

masterpiece, best quality, good quality Negative prompt :

lowres, bad quality, worst quality, bad anatomy, sketch, missing finger, extra digits, fewer digits, signature, watermark, username Steps : 25-28

CFG : 5-6

Sampler : euler_a

Supported resolution :

1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536 Hires.fix Setting:

Upscaler : 4x NMKD YandereNeo XL / 4x Illustration Janai

Hires step : 10-15

Denoise : 0.1-0.3

Training Details The model was developed using a two-stage fine-tuning process. In Stage 1, new series and characters were introduced into the model. Stage 2 focused on fixing issues and enhancing the overall style for improved output.

Stage 1

Dataset : v1-31k, v2-37k, v3-34k, v4-60k, v5-18k

Hardware : 2x A100 80gb, v3 and v4, v5-2x H100 80gb

Batch size : 32

Gradient accumulation steps : 2

Learning rate : 6e-6

Text encoder : 3e-6

Epoch : 15

Stage 2

Dataset : v1-2.5k, v2 and v3-2.3k, v4-2.5k, v5-2k

Hardware : 1x A100 80gb

Batch size : 48

Gradient accumulation steps : 1

Learning rate : 3e-6

Text encoder : disable

Epoch : 15

List of New Series/Characters Trained: Zenless zone zero character up to 1.7

Wuthering waves character up to 2.4

HSR character up to 3.3

Genshin character up to 5.6

Dandadan

Make heroine ga oo sugiru

Kusuriya no Hotorigoto

Hololive from justice and dev is

Indie Vtuber dooby and yuuki Sakuna

100 girlfriends who really love you

For character prompts, please refer to the Danbooru site for accurate tags and references.

License Fair AI Public License 1.0-SD

Special thanks to Joe for supporting my works

コメント1