PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generate
Models
Studio
Contest
Mio.2

Conversational creation

AI Tools
Guide

User LoRA

XL

[PonyV6 XL]Anime Poster Style LoRA/アニメピンナップLoRA

#Megami Magazine

AI Tools

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
Mio with expression sulk

Oops, this cover can't be shown

It didn't pass our content check — no worries, your model is still fully searchable and usable! Just swap in a cover that works for everyone.

Uploaded at
May 11, 2024, 9:56 AM
Uses
22
Reviews
No reviews
Trigger Words

mgmmz, absurd res, source_anime, score_9

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Description

megami magazineライクな彩度が高く、クリアでシャープな画像を生成できるLoRAです。データセットに文字がない為文字が出現しにくくなっています。当LoRAはあくまでアニメ雑誌のピンナップを目標とし、ハイディティールにならないようにデータセットを調整しています。オリジナルのPonyV6 XLで最も良い結果になると思います。プロンプト"megami magazine"や"anime screencap"の代替、もしくは組み合わせで上手く動作します。プロンプトは"mgmmz,absurd res,source_anime,score_9"で学習させています。トリガーワードは必要ではありませんが、結果が大きく変わります。"mgmmz,absurd res,source_anime,score_9"以外のクオリティタグを使用すると結果が大きく変わります。推奨するstrengthは0.6-0.8です。他のLoRAと組み合わせる場合、画風を強く学習しているLoRAとは相性が悪いです。アニメキャプチャライクなLoRAは結果が少しシャープになります。////////////////////////////////////////////////////////////////////////////////////////////////This is a LoRA that can generate clear and sharp images with high saturation, similar to the style of Megami Magazine. Since there are no texts in the dataset, texts are less likely to appear. The goal of this LoRA is a poster of an anime magazine. The dataset is adjusted to avoid excessive high detail..I think that the best results will be achieved with the original PonyV6 XL.It works well as an alternative or in combination with prompts like “megami magazine” or “anime screencap”.The prompts used for training are “mgmmz, absurd res, source_anime, score_9”. Trigger words are not necessary, but it changes the results.The use of quality tags other than "mgmmz,absurd res,source_anime,score_9" will change the results.Recommended strength is 0.6-0.8.When combining with other LoRAs, it does not work well with LoRAs that have strongly learned art styles. The results with LoRAs that are like anime captures will be slightly sharper.

Comments