README.md

---
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
language:
- ja
- en
pipeline_tag: text-to-image
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
library_name: diffusers
---

![Cover](https://huggingface.co/Noginowa/AnimaMixColorXL/resolve/main/images/AnimaMixColorXL_cover.jpeg)
Animagine系のモデルをミックスしたVAE内蔵マージモデルです。<br>
This is a VAE built-in merge model with a mix of Animagine-type models.<br>
<br>
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。<br>
Please be as detailed as possible in your prompts to generate better illustrations. Simple prompts can generate not bad illustrations, but 1girl and quality prompts alone do not generate good illustrations.<br>
<br>

# ライセンス / License
[Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)<br>
<br>

# 以下のモデルをマージしています / The following models are merged
* Animagine XL V3.1
* Anything XL
* Async's MIX XL v3.1
* anima_pencil-XL v5.0.0
* anima_pencil-XL v4.0.0

Thank you for the model creators.<br>
<br>

# レシピ/ Recipe
1. animagineXLV31_v31 x 0.115 + AnythingXL_xl x 0.685 + asyncsMIXXL_v31 x 0.2
2. \[1\] x 0.575 + animaPencilXL_v500 x 0.425
3. \[2\] + \(animaPencilXL_v500 - animaPencilXL_v400\) x 1_smoothAdd MT
4. \[3\] + \(\[3\] - asyncsMIXXL_v31\) x 0.725_trainDifference
5. \[4\] + \(\[4\] - AnythingXL_xl\) x 1_trainDifference
6. \[5\] x \(1-alpha\) + AnythingXL_xl x alpha \(0.8,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0\)
<br><br>

# 作者
Civitai: [Noginowa](https://civitai.com/user/Noginowa)<br>
Bluesky: [のぎのわ](https://bsky.app/profile/noginowa-ailab.bsky.social)