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

Mori Kaede [TerasuMC] [黒人の転校生に幼馴染をNTRる] - Lora

#熟女#寝取られ#女の子
AIツール
  • AIアニメ生成
  • AI画像生成
  • AI動画生成
  • アニメフィギュア生成
  • キャラクターシート生成
  • 雑誌表紙生成
  • ぬいぐるみ生成
  • 巨大彫像生成

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
Mori Kaede [TerasuMC] [黒人の転校生に幼馴染をNTRる] - Lora - AI Model cover image
アップロード日時
2024/05/17 4:22
採用数
2.8k
レビュー
レビューがありません
トリガーワード

mori_kaede_\(terasu_mc\)

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

おすすめLoRA

Aku no Onna Kanbu - Oboro [IL] - AI Model cover image

ユーザーLoRA

Aku no Onna Kanbu - Oboro [IL]
0
Momo Yaoyorozu (My Hero Academia) | [Illustrious] - AI Model cover image

ユーザーLoRA

Momo Yaoyorozu (My Hero Academia) | [Illustrious]
6
Futaba Sakura (佐倉双葉) - Persona 5 - AI Model cover image

ユーザーLoRA

Futaba Sakura (佐倉双葉) - Persona 5
7
Aschen Brodel [Super Robot Wars Endless Frontier][PONY/IL] - AI Model cover image

ユーザーLoRA

Aschen Brodel [Super Robot Wars Endless Frontier][PONY/IL]
6

詳細説明

Update PonyXL v1PonyXL version added!Trained on autismmixSDXL_autismmixPonyThanks to PonyXL, the model is now more flexible compared with the 1.5 verLora Block weights is no longer necessary for this model in PonyXLUpdate v3Added new images to the training datasetChanged base model to AnyLoRAImportant: To avoid overfitting I recommend using the extension sd-webui-lora-block-weight and setting the weight to: OUTALLAlso check out the other characters of this pack!Model CharacteristicsThere are 4 different LoRA's available, one for each of the characters and each with its own trigger word.Trigger words: mori_kaede_(terasu_mc)Use weight of 0.7 to 1. See what works best for you.I'm using DivineEleganceMix and Cartunafied and got good results, so I'd recommend using checkpoints that have an anime style.Play around with the samplers, but I got best results with DPM++ 2M Karras and DPM++ SDE Karras.Clip Skip 2 works best.The Ayumu LoRA can be a bit tricky to get good results due to limited dataset.Hires Fix works like a charm, I recommend using Lanczos or R-ESRGAN 4x+ Anime6B as the upscaler.Although not fully tested, I got some interesting results when using dramaticgecko1600 TerasuMC Art style, so I'd recommend to give it a try and see what results you get ;)TrainingI'm relatively new to LoRA trainning so any tips for improvement are much appreciated!Dataset size: 80 (Combined)Model: AnyLoRABuckets enabledEpoch: 1Repeats: Good dataset - 100 & Bad dataset - 50Total steps: 12000 (Combined), Around 3k each.////////////////////////////////////////////////////////////////////////////////////////////////////////Update v2Added new images to the training datasetChanged base model to Hardcore-Hentai for better r18 scenesLike my stuff? Buy me a Monster!All my models and images will always be 100% free, don't feel obligated to donate!////////////////////////////////////////////////////////////////////////////////////////////////////////Greetings!My first LoRA model here, and starting off with an absolute banger.The model works well with weights between 0.7-1 + Euler a @ 25 steps, with the AnyLora checkpoint, but it should work well with pretty much anything anime related.You can also use TerasuMC Art Style to really bring up TerasuMC's art style to the image!I'd be happy if you guys could give me any character suggestions for my next LoRA!Cheers.Like my stuff? Buy me a Monster!All my models and images will always be 100% free, don't feel obligated to donate!

コメント