概要 / Model Summary
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 - v1
PixAI - v1
📜 ライセンス / License
⚠️ 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.
✨ おすすめ設定 / Recommended Settings
CLIP skip: 2
CFG scale(Euler a): 3-7
CFG scale(Euler a CFG++): 1.5
Steps: 20-50(おすすめ/Recommended 36)
Sampler: Euler a, Euler a CFG++
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.
🖼️ サンプル画像 / Sample Images
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.
💬 おすすめプロンプト / Recommended Prompts
Positive:
Masterpiece, Best quality, Amazing quality, Very aesthetic, Absurdres, Highres, Hi res, Newest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:
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🔗リンク / Link
Hugging Face: https://huggingface.co/Noginowa
Bluesky: https://bsky.app/profile/noginowa-ailab.bsky.social
Description
This model merged the following models:
Checkpoint:
LoRA:
VAE:
Thank you to the original model creators.
sd-mecha for Comfyui recipe
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 &3 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &4
merge "add_opposite" &1 &0 &2 &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 &7 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &8
merge "add_opposite" &6 &0 &2 &9
model "Illustrious_Realistic_V1.safetensors" model_config="sdxl-kohya_kohya_lora" merge_space="weight"
merge "convert_'sdxl-kohya_kohya_lora'_to_base" &11
merge "convert_'sdxl-kohya'_to_'sdxl-sgm'" &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 &14 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &15
merge "add_difference" &10 &13 &16
merge "fallback" &17 &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 &19 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &20
merge "weighted_sum" &0 &18 &21
literal 0.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &23 "clip_l"
merge "pick_component" &23 "clip_g"
merge "fallback" &24 &25
merge "pick_component" &23 "vae"
merge "fallback" &26 &27
literal 1.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &29 "diffuser"
merge "fallback" &28 &30
merge "weighted_sum" &0 &22 &31
VAE
sdxl-vae-fp16-fix