<h3 id="model-summary">概要 / Model Summary</h3>LunerriaMixAnime ILLは、Illustrious系モデルをベースとした、VAE内蔵のマージモデルです。先行モデルであるLunerriaMix ILLの汎用性を活かしつつ、よりアニメ調の質感に近づくよう微調整を行いました。そっち系も得意みたい。LunerriaMixAnime ILL is a merge model based on the Illustrious-XL series with a built-in VAE. Building on the versatility of the previous LunerriaMix ILL, this version has been fine-tuned for a slightly more anime-like aesthetic. Good at that sort of thing.今すぐオンラインで生成を試したい方は、こちらのサイトをご覧ください：If you'd like to try online generation right now, please visit the following site:<ul><li>Tensor.Art - <a target="_blank" rel="ugc" href="https://tensor.art/models/988077873694807695">v3</a> | <a target="_blank" rel="ugc" href="https://tensor.art/models/965061948188145335">v2</a> | <a target="_blank" rel="ugc" href="https://tensor.art/models/953984709988206668">v1</a></li><li>PixAI - <a target="_blank" rel="ugc" href="https://pixai.art/ja/model/1968139347952533933/2001432168126126123">v3</a> | <a target="_blank" rel="ugc" href="https://pixai.art/model/1968139347952533933/1978956080637881592">v2</a> | <a target="_blank" rel="ugc" href="https://pixai.art/model/1968139347952533933/1968139348602651154">v1</a></li></ul><h3 id="license"> 📜 ライセンス / License</h3><a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> <h3 id="usage-notes">⚠️ ご利用上の注意 / Usage Notes</h3>❗ご利用開始前に必ずお読みください：最適な結果を得るため、以下の「おすすめ設定」と「おすすめプロンプト」を必ず確認してください。 ❗MUST READ Before Use: To achieve optimal results, please ensure you check the "Recommended Settings" and "Recommended Prompts" sections below. <h3 id="restrictions">⚠️ 制限事項 / Restrictions</h3>この制限はv2以降に適用され、v1には適用されません。These restrictions apply to v2 and all subsequent versions, but do not apply to v1.<ul><li>商用利用について: 生成された画像をそのまま（白黒化などの簡易的な加工のみを含む）の状態で商用利用することは禁止されています。商用利用する場合には、実質的な編集や加工が必要です。</li><li>非営利での共有: 収益化を目的としない場合に限り、制限なく画像を共有することが可能です。</li><li>Commercial Use: You cannot use the generated images for commercial purposes if they are unedited (including simple filters like converting to black and white). Substantial editing or modification is required for commercial use.</li><li>Non-Commercial Sharing: You are free to share the generated images without any restriction, provided that they are not monetized.</li></ul><h3 id="recommended-settings">✨ おすすめ設定 / Recommended Settings</h3><ul><li>CLIP skip: 2</li><li>CFG scale(Euler a): 3-7</li><li>CFG scale(Euler a CFG++): 1.5</li><li>Steps: 20-40(おすすめ/Recommended 28)</li><li>Sampler: Euler a, Euler a CFG++ </li></ul><h3 id="recommended-prompts">💬 おすすめプロンプト / Recommended Prompts</h3>Positive:<pre><code>Masterpiece, Best quality, Amazing quality, Very aesthetic, Absurdres, Highres, Hi res, Newest</code></pre>Positive(Optional):<pre><code>Anime coloring, Anime screencap, Shiny skin</code></pre>Negative:<pre><code>Nsfw, Lowres, Bad quality, Worst quality, Poorly drawn, Flat color, Sketch, Jpeg artifacts,
Bad anatomy, Ugly, Bad eyes, Bright pupils, White pupils, Bad hands, 
Simple background, Transparent background, Blurry, Furry, Watermark</code></pre><h3 id="about-sample-illustrations">🖼️サンプルイラストについて / About Sample Illustrations</h3>サンプルイラストは全てHires. fixしています。All sample illustrations have been Hires.fix.<hr />Hugging Face: <a target="_blank" rel="ugc" href="https://huggingface.co/Noginowa/LunerriaMixAnime-ILL">https://huggingface.co/Noginowa/LunerriaMixAnime-ILL</a><hr />

LunerriaMixAnime ILL

v2に比べ、全体的な発色を鮮明にし、コントラストを調整しました。また、細部のディテールやライティングの表現力も向上しました。Compared to v2, v3 features more vibrant colors and enhanced contrast. We've also improved the lighting and fine details.This model merged the following models:<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/models/376130?modelVersionId=2837020">Nova Anime XL IL v18.0</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/OnomaAIResearch/Illustrious-XL-v2.0">Illustrious XL v2.0-STABLE</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/2307979?modelVersionId=2685234">LunerriaMixAnime ILL v2</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/madebyollin/sdxl-vae-fp16-fix">sdxl-vae-fp16-fix</a></li></ul>Thank you to the original model creators.sd-mecha for Comfyui recipe<pre><code>model "novaAnimeXL_ilV180.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "LunerriaMixAnime_ILL_v2.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "Illustrious-XL-v2.0.safetensors" model_config="sdxl-sgm" merge_space="weight"
dict BASE=0.0 IN00=0.0 IN01=0.0 IN02=0.0 IN03=0.0 IN04=0.0 IN05=0.0 IN06=0.0 IN07=0.0 IN08=0.0 M00=0.0 OUT00=0.35 OUT01=0.35 OUT02=0.35 OUT03=0.4 OUT04=0.4 OUT05=0.4 OUT06=0.45 OUT07=0.45 OUT08=0.45 VAE=0.0
literal &amp;3 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;4
merge "train_difference" &amp;1 &amp;0 &amp;2 &amp;5
dict BASE=0.0 IN00=0.2 IN01=0.2 IN02=0.2 IN03=0.2 IN04=0.2 IN05=0.2 IN06=0.2 IN07=0.2 IN08=0.2 M00=0.0 OUT00=0.2 OUT01=0.2 OUT02=0.2 OUT03=0.2 OUT04=0.2 OUT05=0.2 OUT06=0.2 OUT07=0.2 OUT08=0.2 VAE=0.0
literal &amp;7 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;8
merge "add_cosine_b" &amp;6 &amp;0 &amp;9
dict BASE=0.0 IN00=1.0 IN01=1.0 IN02=1.0 IN03=1.0 IN04=1.0 IN05=1.0 IN06=1.0 IN07=1.0 IN08=1.0 M00=0.0 OUT00=1.0 OUT01=1.0 OUT02=1.0 OUT03=1.0 OUT04=1.0 OUT05=1.0 OUT06=1.0 OUT07=1.0 OUT08=1.0 VAE=0.0
literal &amp;11 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;12
merge "weighted_sum" &amp;0 &amp;10 &amp;13
literal 0.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &amp;15 "clip_l"
merge "pick_component" &amp;15 "clip_g"
merge "fallback" &amp;16 &amp;17
merge "pick_component" &amp;15 "vae"
merge "fallback" &amp;18 &amp;19
literal 1.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &amp;21 "diffuser"
merge "fallback" &amp;20 &amp;22
merge "weighted_sum" &amp;0 &amp;14 &amp;23

VAE
sdxl-vae-fp16-fix</code></pre>

lunerriamixanimeILL_v3.safetensors

概要 / Model SummaryLunerriaMixAnime ILLは、Illustrious系モデルをベースとした、VAE内蔵のマージモデルです。先行モデルであるLunerriaMix ILLの汎用性を活かしつつ、よりアニメ調の質感に近づくよう微調整を行いました。そっち系も得意みたい。LunerriaMixAnime ILL is a merge model based on the Illustrious-XL series with a built-in VAE.Building on the versatility of the previous LunerriaMix ILL, this version has been fine-tuned for a slightly more anime-like aesthetic.Good at that sort of thing.📜 ライセンス / LicenseFair AI Public License 1.0-SD⚠️ ご利用上の注意 / Usage Notes❗ご利用開始前に必ずお読みください：最適な結果を得るため、以下の「おすすめ設定」と「おすすめプロンプト」を必ず確認してください。❗MUST READ Before Use: To achieve optimal results, please ensure you check the "Recommended Settings" and "Recommended Prompts" sections below.⚠️ 制限事項 / Restrictionsこの制限はv2以降に適用され、v1には適用されません。These restrictions apply to v2 and all subsequent versions, but do not apply to v1.<ul><li>商用利用について: 生成された画像をそのまま（白黒化などの簡易的な加工のみを含む）の状態で商用利用することは禁止されています。商用利用する場合には、実質的な編集や加工が必要です。</li><li>非営利での共有: 収益化を目的としない場合に限り、制限なく画像を共有することが可能です。</li><li>Commercial Use: You cannot use the generated images for commercial purposes if they are unedited (including simple filters like converting to black and white). Substantial editing or modification is required for commercial use.</li><li>Non-Commercial Sharing: You are free to share the generated images without any restriction, provided that they are not monetized.</li></ul>✨ おすすめ設定 / Recommended Settings<ul><li>CLIP skip: 2</li><li>CFG scale: 3-7</li><li>Steps: 20-40(おすすめ/Recommended 28)</li><li>Sampler: Euler a</li></ul>💬 おすすめプロンプト / Recommended PromptsPositive:Masterpiece, Best quality, Amazing quality, Very aesthetic, Absurdres, Highres, Hi res, NewestPositive(Optional):Anime coloring, Anime screencap, Shiny skinNegative:Nsfw, Lowres, Bad quality, Worst quality, Poorly drawn, Flat color, Sketch, Jpeg artifacts,Bad anatomy, Ugly, Bad eyes, Bright pupils, White pupils, Bad hands,Simple background, Transparent background, Blurry, Furry, Watermark🖼️ サンプル画像 / Sample Imagesサンプルイラストは全てHires. fixしています。All sample illustrations have been Hires.fix.その他 / OthersHugging Face: <a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/Noginowa/LunerriaMixAnime-ILL">https://huggingface.co/Noginowa/LunerriaMixAnime-ILL</a>

v2に比べ、全体的な発色を鮮明にし、コントラストを調整しました。また、細部のディテールやライティングの表現力も向上しました。
Compared to v2, v3 features more vibrant colors and enhanced contrast. We've also improved the lighting and fine details.

マージレシピについてはHugging Faceを参照してください。
Please refer to Hugging Face for merge recipes.

https://huggingface.co/Noginowa/LunerriaMixAnime-ILL

Files with SHA256: 1b11f650f2f1475b4e018023e48c3c574a6ed2971fa11d15c79bb4630033057e