Thành viên PixAI
PixAI
PixAI
Generate
Sign in
Trang chủ
Tạo
Mô hình
Studio
Cuộc thi
Mio.2

Conversational creation

Hộp công cụ
Guide

User LoRA

XL
Khác

[SDXL] Embarrased face / 赤面(茹でダコ顔)

Công cụ AI

  • 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

Khám phá

  • Thẻ Đang Thịnh Hành
  • Xếp hạng
  • Thị trường Mô hình
  • Cuộc thi
  • Tin tức

Giới thiệu

  • Guide
  • Cách sử dụng PixAI
  • Tsubaki.2
  • Gặp gỡ Mio
  • Quy tắc nội dung

Giá & Trợ giúp

  • Thành viên
  • Gói tín dụng
  • Liên hệ

Ứng dụng di động

  • Tải ứng dụng PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Điều khoản dịch vụ
  • Chính sách quyền riêng tư
  • Chính sách bản quyền
  • Attributions
  • Luật Giao dịch Thương mại Đặc định
[SDXL] Embarrased face / 赤面(茹でダコ顔) - AI Model cover image
Đã tải lên vào
05:30 27 thg 12, 2024
Lượt sử dụng
66.7k
Đánh giá
Xuất sắc  (1)
Quyền
  • Allow image generation & sharing
  • Cho phép người dùng tải xuống mô hình của bạn
  • Sử dụng thương mại

Recommended LoRAs

『Manhwa』물가의 밤 / Low Tide in Twiligh Style | DiT.1 - AI Model cover image

User LoRA

『Manhwa』물가의 밤 / Low Tide in Twiligh Style | DiT.1
13
石鍋環 illustrious Ishinabe Tamaki (Can Can Bunny Premiere 2) - AI Model cover image

User LoRA

石鍋環 illustrious Ishinabe Tamaki (Can Can Bunny Premiere 2)
3
Ria Kujoh_(Twinkle Crusaders / Twinkle Star Knights) - AI Model cover image

User LoRA

Ria Kujoh_(Twinkle Crusaders / Twinkle Star Knights)
2
平安貴族束帯衣 - AI Model cover image

User LoRA

平安貴族束帯衣
9

Mô tả

(日本語説明は後半にあります)The popular "Hotaru's LoRA series" (for SD1) is now available for SDXL! More will be released gradually on CivitAI (already available on HuggingFace).Reproduces a face strongly turned red with embarrassment.3 types are available. To download each types, switch version tabs ↑ above.Type 1 : full faceType 2 : red tint and red lines on the face, cheeks onlyType 3 : no red lines but only a red tint, cheeks onlyThis LoRA is compatible with Pony / Animagine / Illustrious based checkpoints, but Pony based checkpoints will make better results. Some checkpoints may have less compatibility.This LoRA is suitable for 2D-2.5D illustrations only and not suitable for photorealistic checkpoints. My "Breed" series checkpoints will make good outputs. Sample images are generated with "Breed" series listed on "Suggested Resources" section.SD1 version is also available.About file name: Yudedako(茹でダコ) is a Japanese word meaning "boiled octopus", and is a slung that refers to a blushing or embarrassed facial expression. Just like how a boiled octopus turns red when cooked, this idiom vividly captures the feeling of being bashful or ashamed.UsageIt works by simply enabling LoRA. Effect strength(redness) can be controlled by LoRA weight (approx. 0.5 - 2.0).With stronger weight, it sometimes reproduces unexpected red areas or red lines on background and clothes. Then, repaint only faces by img2img or ADetailer with this LoRA.Minus weight is not supported.Prompts embarrassed or shame will make better results.More various other SD1/SDXL LoRA's and checkpoints are available on my HuggingFace repository or CivitAI models list. Please check it out.CAUTION : Some sample images' prompt is using NegPiP extension for minus weight.SD1でご好評いただいていた十条蛍のLoRAシリーズが、SDXL対応になって再登場します。HuggingFaceで先行公開中ですが、CivitAIにも順次掲載していきます。俗に「茹でダコのような」などと呼ばれる、恥ずかしさで真っ赤になった顔を少しオーバー気味に表現できます。以下の3種類から選ぶことができます。各タイプをダウンロードするには、ページ上部のバージョンタブを切り替えてください。Type 1 : 顔全体が赤く染まるType 2 : 顔中央部(頬部分)が赤く染まるが、赤線は目立たないType 3 : 顔中央部(頬部分)が赤く染まり、赤線も付くPony系・Animagine系・Illustrious系のデータモデルに対応していますが、Pony系での使用においてもっとも高い効果を発揮します。一部のデータモデルでは、うまく再現されないことがあります。2D・2.5Dイラスト系のデータモデル用で、実写系には不向きです。拙作データモデル「Breedシリーズ」と組み合わせると、高い効果を発揮します。サンプル画像もBreedシリーズ("Suggested Resources"セクションに掲載)で生成されています。SD1系対応バージョンも公開しています。使い方LoRAを有効にするだけで動作しますが、embarrassedやshameのプロンプトを組み合わせると効果が強まる場合があります。open mouth, wavy mouthと組み合わせると、より雰囲気の出た恥ずかし顔になるでしょう。適用強度によって赤みの追加具合をコントロールできます。0.5~2.0くらいまでが実用範囲です。強度を上げると、人物以外(背景や服装)にも赤色や赤線が出てしまう場合があります。その場合は全体出力にはLoRAを適用せず、後からimg2imgやADetailerなどを使い、LoRAを指定して顔だけを出し直すようにしてみてください。他にもさまざまなSD1/SDXL用LoRAおよびデータモデルを公開していますので、HuggingFaceリポジトリまたはCivitAIの配布モデルリストをご覧ください。掲載しているサンプル画像のプロンプトの一部では、NegPiP拡張機能を使ったマイナス強度指定を使用しています。

Bình luận