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

SD

ItN's Comic Merge

#漫画

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
ItN's Comic Merge - AI Model cover image
アップロード日時
2025/09/08 13:00
採用数
116
レビュー
大好評  (1)
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

I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: https://ko-fi.com/insult_to_ninjary

Your generosity helps me stay motivated to keep improving and to keep trying new things!

At a Glance:

Style: Anime

Works with LoRAs?: It should (though maybe not perfectly with everything...)

VAE: vae-ft-mse-840000-ema-pruned is baked (but you can override if desired)

Clip skip: 1 or 2 (experiment with both!)

Hires. fix: use non-default upscaler; denoising strength 0.5 - 0.4

Description:

While this model doesn't do any specific comic style by default (Western, manga, manhwa, etc.), I feel that it does provide a sort of general anime comic vibe, with a more minimalist style, thicker outlines, and more muted and flat colors. I'll go over its primary pros and cons below.

The good: In my experience, the model is pretty good with anatomy (hands, fingers, etc.) for an SD1.5 model. Of course, it's not gonna be perfect, and you're still gonna get your fair share of jankiness, but I definitely haven't had to inpaint as much with this model compared to other SD1.5 models. For example, all the showcase images are basically the result of either the first or second try with each prompt. I did use adetailer for some of the faces, but I don't think I did any postprocessing at all on the hands. I definitely could've made the showcase images look a lot better by putting in a bit more work, but they do serve as a pretty good example of what you can get immediately out of the box with very little effort.

The bad: The model is not very good at fine details. Stuff in the background (especially in the distance), and small character details (like accessories and detailed clothing designs) usually come out pretty muddy and garbled. This could probably be fixed with some extra effort, but the model definitely works better by leaning into its tendency for minimalism. I think you could expect quicker success if prompting for backgrounds and clothing outfits that are more on the simpler side.

Troubleshooting:

As mentioned above, you may need to deal with some messy details and anatomy problems at times - hands, fingers, general jank, etc. If you're running into problems, just try your best with all the usual fixes - different prompting, use a different VAE, try different clip skip values, use adetailer, inpaint, etc.

Outro:

If you make anything awesome, please consider posting them to the gallery! That goes for all of my models! I really like seeing what kind of stuff you all are able to make!

If you have any questions, feel free to ask! I will try my best to help! Also, if you have any ideas for future models, please don't hesitate to share them with me!

コメント