このシリーズのモデルおよびその派生モデルは、LiblibAIまたはShakkerAIにアップロードすることは禁止されています。この制限はAnything XLより引き継いでいます。Models in this series and their derivative models are prohibited from being uploaded to LiblibAI or ShakkerAI. This restriction is inherited from Anything XL.<hr /><h3 id="about-this-model">このモデルについて / About this model</h3>Animagine XLベースのVAE内蔵マージモデルです。必ずおすすめ設定、おすすめプロンプトを確認してください。This is a merged model based on Animagine XL with a built-in VAE. Be sure to check the recommended settings and recommended prompts.より良いイラストを生成するにはできるだけ詳しくプロンプトを記述してください。シンプルなプロンプトでも悪くないイラストは生成できますが、1girlと品質プロンプトだけでは良いイラストにはなりません。Describe your prompts in as much detail as possible to generate better illustrations. Simple prompts can still generate decent illustrations, but using only "1girl" and quality tags will not result in a great illustration.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><a target="_blank" rel="ugc" href="https://tensor.art/models/933156667665681851">Tensor.Art - v3</a></li><li><a target="_blank" rel="ugc" href="https://pixai.art/model/1954678347683351630/1954678349507874072">PixAI - v3</a></li><li><a target="_blank" rel="ugc" href="https://tensor.art/models/942343331055184549">Tensor.Art - v2.1</a></li><li><a target="_blank" rel="ugc" href="https://pixai.art/model/1954678347683351630/1956769576248257689">PixAI - v2.1</a></li><li><a target="_blank" rel="ugc" href="https://tensor.art/models/804081954699077172">Tensor.Art - v2</a></li><li><a target="_blank" rel="ugc" href="https://tensor.art/models/804074434211223100">Tensor.Art - v1</a></li></ul><h3 id="license">ライセンス / License</h3>AnimaMixColorXLは <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a> に該当します。マージレシピについては「About this version」を参照してください。AnimaMixColorXL is subject to the <a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a>. Please refer to the "About this version" section for the merge recipe.<h3 id="recommended-settings">おすすめ設定 / Recommended Settings</h3>CFG scale : 4-7 (おすすめ/Recommended: 5)Steps: 25-30 (おすすめ/Recommended: 28)Sampler: Euler-a<h3 id="sample-prompts-for-busy-people">忙しい人のためのサンプルプロンプト / Sample prompts for busy people</h3>Positive:<pre><code>Depth of field, Upper body, Dynamic angle, 1girl, Solo, Light smile, Light blush, Standing, Looking at viewer, Light-blue hair, BLue eyes, Long hair, Medium breasts, Casual dress, White background, Masterpiece, Best quality, Amazing quality, Very aesthetic, Absurdres</code></pre>Negative:<pre><code>Nsfw, Lowres, Bad quality, Worst quality, Low score, Bad score, Average score, Poorly drawn, Flat illustration, Flat color, Anime style, Sketch, Jpeg artifacts, Bad anatomy, Ugly, Bad eyes, Bright pupils, White pupils, Bad hands, Bad fingers, Extra fingers, Simple background, Transparent background, 3D, Blurry, Furry, Watermark</code></pre>より良いイラストを生成するにはできるだけ詳しくプロンプトを記述してください。Describe your prompts in as much detail as possible to generate better illustrations.<h3 id="recommended-prompt">おすすめプロンプト / Recommended Prompt</h3>Quality Positive:<pre><code>Masterpiece, Best quality, Amazing quality, Very aesthetic, Absurdres</code></pre>Quality Negative:<pre><code>Nsfw, Lowres, Bad quality, Worst quality, Low score, Bad score, Average score, Poorly drawn, Flat illustration, Flat color, Anime style, Sketch, Jpeg artifacts, Bad anatomy, Ugly, Bad eyes, Bright pupils, White pupils, Bad hands, Bad fingers, Extra fingers, Simple background, Transparent background, 3D, Blurry, Furry, Watermark</code></pre><h3 id="detailed-usage">詳しい使い方 / Detailed usage</h3>v3は<a target="_blank" rel="ugc" href="https://huggingface.co/cagliostrolab/animagine-xl-4.0">Animagine XL 4.0</a>、v2以前は<a target="_blank" rel="ugc" href="https://huggingface.co/cagliostrolab/animagine-xl-3.1">Animagine XL 3.1</a>と互換性があります。詳しくは各Animagine XLページのUsage Guidelinesを参照して下さい。v3 is compatible with <a target="_blank" rel="ugc" href="https://huggingface.co/cagliostrolab/animagine-xl-4.0">Animagine XL 4.0</a>, and v2 and earlier versions are compatible with <a target="_blank" rel="ugc" href="https://huggingface.co/cagliostrolab/animagine-xl-3.1">Animagine XL 3.1</a>. For more details, please refer to the "Usage Guidelines" section on the respective Animagine XL pages.<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 images have been generated using Hires. fix.<hr />Hugging Face: <a target="_blank" rel="ugc" href="https://huggingface.co/Noginowa/AnimaMixColorXL">https://huggingface.co/Noginowa/AnimaMixColorXL</a><hr />英文はGeminiを使用して翻訳されています。The English text was translated using Gemini.

AnimaMixColorXL

v2.1は、v2のレシピをベースに怪しい部分を修正し、sd-mechaでマージし直しました。v2.1 was re-merged with sd-mecha after correcting problematic areas found in the v2 recipe.This model merged the following models:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/cagliostrolab/animagine-xl-3.1">Animagine XL V3.1</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/261336?modelVersionId=597138">anima_pencil-XL v5.0.0</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/9409?modelVersionId=384264">Anything XL</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/266052?modelVersionId=554048">Async's MIX XL v3.2</a></li></ul>Thank you to the original model creators.sd-mecha for ComfyUI recipe<pre><code>model "AnythingXL_xl.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "animagineXLV31_v31.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "asyncsMIXXL_v32.safetensors" model_config="sdxl-sgm" merge_space="weight"
merge "slerp" &amp;1 &amp;2 0.23
model "animaPencilXL_v500.safetensors" model_config="sdxl-sgm" merge_space="weight"
merge "slerp" &amp;3 &amp;4 0.63
merge "train_difference" &amp;5 &amp;4 &amp;1 1.0
dict BASE=0.0 IN00=0.73 IN01=0.73 IN02=0.73 IN03=0.73 IN04=0.73 IN05=0.73 IN06=0.73 IN07=0.73 IN08=0.73 M00=0.0 OUT00=0.35 OUT01=0.35 OUT02=0.35 OUT03=0.35 OUT04=0.35 OUT05=0.35 OUT06=0.35 OUT07=0.35 OUT08=0.35 VAE=0.0
literal &amp;7 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;8
merge "slerp" &amp;6 &amp;0 &amp;9
dict BASE=1.0 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</code></pre>

Files with SHA256: 8f3831337d04603349dabd44e525ad3908b9089ae61b14a86d7ad35f413e7d84