概要 / Model Summary
LunerriaMixCute 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。LunerriaMixAnime ILLの繊細な質感を継承しつつ、キャラクターの可愛らしさを強調しました。そっち系も得意みたい。
LunerriaMixCute ILL is a VAE-baked merge model based on the Illustrious architecture. While inheriting the delicate textures of LunerriaMixAnime ILL, this model places a stronger emphasis on character cuteness. 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:
📜 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.
⚠️ 制限事項 / Restrictions
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。
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。
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.
Non-Commercial Sharing: You are free to share the generated images without any restriction, provided that they are not monetized.
✨ 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: 20-40(おすすめ/Recommended 28)
Sampler: Euler a, Euler a CFG++
💬 おすすめプロンプト / Recommended Prompts
Positive:
Masterpiece, Best quality, Amazing quality, Very aesthetic, Absurdres, Highres, Hi res, Newest, CutePositive(Optional):
Realistic, Realistic lighting, Realistic textureリアル系の鼻が気になる場合は、ポジティブプロンプトに「No nose」や「Dot nose」を追加し、ネガティブプロンプトに「Nose」を指定して調整してみてください。
If the realistic nose style doesn't fit your preference, try adding "No nose" or "Dot nose" to your positive prompt, and "Nose" to your negative prompt for a more stylized look.
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🖼️ 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.
Hugging Face: https://huggingface.co/Noginowa/LunerriaMixCute-ILL
Description
This model merged the following models:
Thank you to the original model creators.
sd-mecha for Comfyui recipe
model "LunerriaMixAnime_ILL_v2.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "illusionbreed_v70.safetensors" model_config="sdxl-sgm" merge_space="weight"
model "Illustrious-XL-v2.0.safetensors" model_config="sdxl-sgm" merge_space="weight"
merge "train_difference" &0 &1 &2 1.0
dict BASE=0.0 IN00=0.55 IN01=0.48 IN02=0.5 IN03=0.5 IN04=0.48 IN05=0.48 IN06=0.48 IN07=0.48 IN08=0.48 M00=0.0 OUT00=0.36 OUT01=0.36 OUT02=0.36 OUT03=0.36 OUT04=0.36 OUT05=0.36 OUT06=0.36 OUT07=0.38 OUT08=0.38 VAE=0.0
literal &4 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &5
merge "add_cosine_b" &3 &1 &6
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 &8 model_config="sdxl-supermerger_blocks" merge_space="param"
merge "convert_sdxl_blocks_to_sgm" &9
merge "weighted_sum" &0 &7 &10
literal 0.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &12 "clip_l"
merge "pick_component" &12 "clip_g"
merge "fallback" &13 &14
merge "pick_component" &12 "vae"
merge "fallback" &15 &16
literal 1.0 model_config="sdxl-sgm" merge_space="param"
merge "pick_component" &18 "diffuser"
merge "fallback" &17 &19
merge "weighted_sum" &0 &11 &20





