(日本語説明は後半にあります)v2.0 Update : Specialized for Illustrious checkpoints. Pony checkpoint users should continue using v1.0.Reproduces slanted down eyes, called "Tareme" in Japanese, a familiar anime/comic expression. <a target="_blank" rel="ugc" href="https://civarchive.com/models/881323">"Tsurime" (slanted up eyes) set</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/2329458/">"Jitome" (scornful eyes) set</a> are also available.4 shape types are available. To download each types, switch version tabs ↑ above.This LoRA is suitable for 2D-2.5D illustrations only and not suitable for photorealistic checkpoints. Some checkpoints may have less compatibility. 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> (listed on "Suggested Resources" section) will make good outputs.<a target="_blank" rel="ugc" href="https://civarchive.com/models/353306">SD1 version</a> is also available.<h3 id="usage">Usage</h3>Easy to use. No trigger prompts are necessary.<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.<hr />v2.0 変更点 : Illustrious用に調整しました。Pony系モデルではv1.0を使用してください。キャラクターの目つきをタレ目に変更できます。<a target="_blank" rel="ugc" href="https://civarchive.com/models/881323">吊り目セット</a>、<a target="_blank" rel="ugc" href="https://civarchive.com/models/2329458/">ジト目セット</a>も公開しています。形の異なる4種類を用意しました。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。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。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。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>」（"Suggested Resources"セクションに掲載）と組み合わせると、高い効果を発揮します。<a target="_blank" rel="ugc" href="https://civarchive.com/models/353306">SD1バージョン</a>も公開しています。<h3>使い方</h3>LoRAを有効にするだけで発動します。階層調整済みですので、基本的には階層指定せず強度指定のみで大丈夫です。<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。

[SDXL] Tareme(タレ目) set 1

hotarueye_xl_tareme4_v10.safetensors

Type4 v1.0

Type4 v2.0

Type3 v2.0

Type2 v2.0

Type1 v2.0

Type3 v1.0

Type2 v1.0

Type1 v1.0

Created by JujoHotaruThe popular "Hotaru's LoRA series" (for SD1) is now available for SDXL! More will be released gradually on CivitAI (already available on HuggingFace).Reproduces slanted down eyes, called "Tareme" in Japanese, a familiar anime/comic expression.4 shape types are available. To download each types, switch version tabs ↑ above.Compatible with both Animagine-based and Pony-based checkpoints, but Pony-based checkpoints will make better results.<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/models/353306">SD1 version</a> is also available.</li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/881323">"Tsurime" (slanted up eyes) set</a> is also available.</li></ul>This LoRA series 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.Easy to use. No trigger prompts are necessary.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.

Type 4

Files with SHA256: 34b3866049a9ec2cbc6230b87bc39fda349e96d26af9f4c13b5886861a8761ba