(日本語説明は後半にあります)v3.0 update : Optimized for Illustrious models.The popular "Hotaru's LoRA series" (for SD1) is now available for SDXL! More will be released gradually on CivitAI (already <a target="_blank" rel="ugc" href="https://huggingface.co/JujoHotaru/lora/blob/main/sdxl/README.md">available on HuggingFace</a>).Reproduces semi-closed (thin) eyes. It will help to reproduce better results than <code>half closed eyes</code> prompt only.2 types are available. To download each types, switch version tabs ↑ above.<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/941927?modelVersionId=1912865">Type 1</a> : Slanted up eyelids and eyelashes</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/941927?modelVersionId=1912867">Type 2</a> : Slanted down eyelids and eyelashes</li></ul>v3.0 is for Illustrious based checkpoints while v2.0 is for Pony based checkpoints. Some checkpoints may have less compatibility.This LoRA is suitable for 2D-2.5D illustrations only and not suitable for photorealistic checkpoints. My <a target="_blank" rel="ugc" href="https://civarchive.com/user/JujoHotaru/models?sort=Newest&amp;baseModels=Pony&amp;types=Checkpoint">"Breed" series checkpoints</a> will make good outputs. Sample images are generated with "Breed" series listed on "Suggested Resources" section.<a target="_blank" rel="ugc" href="https://civarchive.com/models/155534">SD1 version</a> is also available.<h3 id="usage-bmtr8jzms">Usage</h3>It works by simply enabling LoRA. No extra prompts are necessary.Narrowness of eyes can be controlled by LoRA weight to some extent (approx. 1.0 - 1.5).<hr />More various other SD1/SDXL LoRA's and checkpoints are available on my <a target="_blank" rel="ugc" href="https://huggingface.co/JujoHotaru">HuggingFace repository</a> or <a target="_blank" rel="ugc" href="https://civarchive.com/user/JujoHotaru/models">CivitAI models list</a>. Please check it out.CAUTION : Some sample images' prompt is using <a target="_blank" rel="ugc" href="https://github.com/hako-mikan/sd-webui-negpip">NegPiP extension</a> for minus weight.<hr />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。<a target="_blank" rel="ugc" href="https://huggingface.co/JujoHotaru/lora/blob/main/sdxl/README.md">HuggingFaceで先行公開中</a>ですが、CivitAIにも順次掲載していきます。目を細めた状態を、<code>half closed eyes</code>プロンプトのみよりも安定して再現できます。眼の形状別に2種類用意しています。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。<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/941927?modelVersionId=1912865">Type 1</a> : 睫毛・目尻が直線に近い形状（吊り目型）</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/941927?modelVersionId=1912867">Type 2</a> : 睫毛・目尻が曲線を描く形状（タレ目型）</li></ul>v3.0はIllustrious系、v2.0はPony系のデータモデルに対応していますが、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「<a target="_blank" rel="ugc" href="https://civarchive.com/user/JujoHotaru/models?sort=Newest&amp;baseModels=Pony&amp;types=Checkpoint">Breedシリーズ</a>」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。<a target="_blank" rel="ugc" href="https://civarchive.com/models/155534">SD1バージョン</a>も公開しています。<h3 id="-gjtr543ig">使い方</h3>LoRAを有効にするだけで発動します。目の細さはLoRA適用強度である程度調整（1.0～1.5程度）することができます。<hr />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、<a target="_blank" rel="ugc" href="https://huggingface.co/JujoHotaru">HuggingFaceリポジトリ</a>または<a target="_blank" rel="ugc" href="https://civarchive.com/user/JujoHotaru/models">CivitAIの配布モデルリスト</a>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、<a target="_blank" rel="ugc" href="https://github.com/hako-mikan/sd-webui-negpip">NegPiP拡張機能</a>を使ったマイナス強度指定を使用しています。

[SDXL] Half closed eyes helper / 細目補助

Specialized for Illustrious checkpoints. Pony checkpoint users should continue using v2.0.Illustrious用に調整しました。Pony系モデルではv2.0を使用してください。

hotarueye_xl_hosome1_v30.safetensors

Type1 v3.0

Type2 v3.0

Type2 v2.0

Type1 v2.0

v3.0 update : Optimized for Illustrious models.The popular "Hotaru's LoRA series" (for SD1) is now available for SDXL! More will be released gradually on CivitAI (already <a target="_blank" rel="ugc" href="https://huggingface.co/JujoHotaru/lora/blob/main/sdxl/README.md">available on HuggingFace</a>).Reproduces semi-closed (thin) eyes. It will help to reproduce better results than half closed eyes prompt only.2 types are available. To download each types, switch version tabs ↑ above.<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/models/941927?modelVersionId=1912865">Type 1</a> : Slanted up eyelids and eyelashes</li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/941927?modelVersionId=1912867">Type 2</a> : Slanted down eyelids and eyelashes</li></ul>v3.0 is for Illustrious based checkpoints while v2.0 is for Pony based checkpoints. Some checkpoints may have less compatibility.This LoRA is suitable for 2D-2.5D illustrations only and not suitable for photorealistic checkpoints. My <a target="_blank" rel="ugc" href="https://civitai.com/user/JujoHotaru/models?sort=Newest&amp;baseModels=Pony&amp;types=Checkpoint">"Breed" series checkpoints</a> will make good outputs. Sample images are generated with "Breed" series listed on "Suggested Resources" section.<a target="_blank" rel="ugc" href="https://civitai.com/models/155534">SD1 version</a> is also available.UsageIt works by simply enabling LoRA. No extra prompts are necessary.Narrowness of eyes can be controlled by LoRA weight to some extent (approx. 1.0 - 1.5).More various other SD1/SDXL LoRA's and checkpoints are available on my <a target="_blank" rel="ugc" href="https://huggingface.co/JujoHotaru">HuggingFace repository</a> or <a target="_blank" rel="ugc" href="https://civitai.com/user/JujoHotaru/models">CivitAI models list</a>. Please check it out.CAUTION : Some sample images' prompt is using <a target="_blank" rel="ugc" href="https://github.com/hako-mikan/sd-webui-negpip">NegPiP extension</a> for minus weight.

Files with SHA256: bd80ec10fa17371179580966147eb0c77ea03ad175b9282a6929636d7a1a3b47