<h3 id="model-summary">概要 / Model Summary</h3>MirageCanvas 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。セミリアル調で、美しいライティングと、衣服や背景の繊細な質感が特徴のモデルです。MirageCanvas ILL is a merge model based on the Illustrious-XL series with a built-in VAE. A semi-realistic model featuring beautiful lighting and delicate textures for both clothing and backgrounds. 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:Tesor.Art - <a target="_blank" rel="ugc" href="https://tensor.art/models/1004661358752459990">v1</a>PixAI - <a target="_blank" rel="ugc" href="https://pixai.art/ja/model/2017627732633421643">v1</a><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><ul><li>❗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。 </li><li>❗MUST READ Before Use: To achieve optimal results, please ensure you check the "Recommended Settings" and "Recommended Prompts" sections below. </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: 20-50(おすすめ/Recommended 36)</li><li>Sampler: Euler a, Euler a CFG++</li></ul>Hires.fixを使用する場合は、denoiseを0.1以下にすることをおすすめします。 When using Hires. fix, it is recommended to set the denoising strength to 0.1 or lower. <h3 id="sample-images">🖼️ サンプル画像 / Sample Images</h3>サンプル画像はMirageCanvas ILL v1で生成し、Hires. fixをしています。Sample images were generated with MirageCanvas ILL v1 and Hires. fix.<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>基本的にRealisticは不要ですが、使用するとよりリアルなイラストが生成されます。The prompt "Realistic" is generally not needed, but adding it will generate a more realistic illustration. 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="link">🔗リンク / Link</h3>Hugging Face: <a target="_blank" rel="ugc" href="https://huggingface.co/Noginowa">https://huggingface.co/Noginowa</a>Bluesky: <a target="_blank" rel="ugc" href="https://bsky.app/profile/noginowa-ailab.bsky.social">https://bsky.app/profile/noginowa-ailab.bsky.social</a>

MirageCanvas ILL

This model merged the following models:Checkpoint:<ul><li><a target="_blank" rel="ugc" href="https://civitai.red/models/827184/wai-illustrious-sdxl?modelVersionId=2883731">WAI-illustrious-SDXL v17.0</a></li><li><a target="_blank" rel="ugc" href="https://civitai.red/models/1125067/cyberrealistic-cyberillustrious?modelVersionId=2879194">CyberRealistic CyberIllustrious v11.0</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0">Illustrious-XL v0.1</a></li></ul>LoRA:<ul><li><a target="_blank" rel="ugc" href="https://civitai.red/models/2149527/cyberrealistic-cyberillustrious-realism-lora?modelVersionId=2431219">CyberRealistic CyberIllustrious Realism LoRa v1.0</a></li></ul>VAE:<ul><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 "cyberrealistic_v110.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "waiIllustriousSDXL_v170.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "Illustrious-XL-v0.1.safetensors" model_config="sdxl-sgm" merge_space="weight"
dict BASE=0.0 IN00=0.5 IN01=0.5 IN02=0.5 IN03=0.5 IN04=0.5 IN05=0.5 IN06=0.7 IN07=0.7 IN08=0.7 M00=0.0 OUT00=0.6 OUT01=0.6 OUT02=0.6 OUT03=0.6 OUT04=0.6 OUT05=0.6 OUT06=0.8 OUT07=0.8 OUT08=0.8 VAE=0.0
literal &amp;3 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;4
merge "add_opposite" &amp;1 &amp;0 &amp;2 &amp;5
dict BASE=0.0 IN00=0.0 IN01=0.0 IN02=0.0 IN03=0.0 IN04=0.0 IN05=0.0 IN06=0.3 IN07=0.3 IN08=0.3 M00=0.0 OUT00=0.0 OUT01=0.0 OUT02=0.0 OUT03=0.0 OUT04=0.0 OUT05=0.0 OUT06=0.7 OUT07=0.7 OUT08=0.7 VAE=0.0
literal &amp;7 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;8
merge "add_opposite" &amp;6 &amp;0 &amp;2 &amp;9
model "Illustrious_Realistic_V1.safetensors" model_config="sdxl-kohya_kohya_lora" merge_space="weight"
merge "convert_'sdxl-kohya_kohya_lora'_to_base" &amp;11
merge "convert_'sdxl-kohya'_to_'sdxl-sgm'" &amp;12
dict BASE=0.0 IN00=0.0 IN01=0.0 IN02=0.0 IN03=0.0 IN04=0.0 IN05=0.0 IN06=0.4 IN07=0.4 IN08=0.4 M00=0.0 OUT00=0.0 OUT01=0.0 OUT02=0.0 OUT03=0.0 OUT04=0.0 OUT05=0.0 OUT06=0.6 OUT07=0.6 OUT08=0.6 VAE=0.0
literal &amp;14 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;15
merge "add_difference" &amp;10 &amp;13 &amp;16
merge "fallback" &amp;17 &amp;10
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;19 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &amp;20
merge "weighted_sum" &amp;0 &amp;18 &amp;21
literal 0.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &amp;23 "clip_l"
merge "pick_component" &amp;23 "clip_g"
merge "fallback" &amp;24 &amp;25
merge "pick_component" &amp;23 "vae"
merge "fallback" &amp;26 &amp;27
literal 1.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &amp;29 "diffuser"
merge "fallback" &amp;28 &amp;30
merge "weighted_sum" &amp;0 &amp;22 &amp;31

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

Files with SHA256: f2e3fa14839931d81c9428e316dcb6018339f5514a9e427e4fc4bf30190d4b8d