<h1 id="yoneyama-mai-or">Yoneyama Mai | 米山舞</h1>Ethereal anime aesthetic for Illustrious-XL | Trigger: <code>yoneyama_mai</code> <h2 id="overview">✨ Overview</h2>This LoRA is fine-tuned on Illustrious-XL v0.1 to replicate the signature ethereal digital anime style inspired by artist Yoneyama Mai. It excels at generating dreamy, soft-toned illustrations with delicate linework, atmospheric lighting, and pastel color harmony.<h2 id="style-highlights">🎭 Style Highlights</h2><ul><li>🌸 Pastel Macaron Palette: Low-saturation tones with smooth gradient transitions</li><li>💫 Ethereal Glow: Soft lighting, light diffusion, and dreamy ambient effects</li><li>👁️ Delicate Rendering: Refined linework, expressive eyes, and subtle character details</li><li>🌌 Abstract Composition: Floating particles, bokeh backgrounds, subject-focused framing</li></ul><h2 id="trigger-word">🔑 Trigger Word</h2><ul><li>Primary: <code>yoneyama_mai</code></li></ul>→ Place at the beginning of your prompt, recommended weight: <code>1.0</code><h2 id="prompt-template">🎨 Prompt Template</h2><pre><code>yoneyama_mai, digital art, anime style, soft lighting, ethereal, pastel colors, [your character/scene description]
</code></pre><h2 id="recommended-settings">⚙️ Recommended Settings</h2>| Parameter | Value | Note ||-----------|-------|------|| Base Model | Illustrious-XL v0.1 | Required — not tested on other XL variants || Resolution | 1024x1024 | SDXL native resolution; other official sizes supported || Sampler | <code>DPM++ 2M Karras</code> | Best for detail fidelity &amp; sharp linework || Sampler | <code>Euler a</code> | Preferred for softer, more aesthetic/painterly results || CFG Scale | 6.5 ~ 7.5 | &gt;8 may overfit; &lt;6 weakens style influence || Steps | 25 ~ 30 | Balanced quality &amp; inference speed || LoRA Weight | 0.8 ~ 1.0 | Full strength recommended for pure style transfer |<h2 id="pro-tips">💡 Pro Tips</h2><ul><li>🔍 More Details: Use <code>DPM++ 2M Karras</code> + CFG 7.0 for crisp linework and fine features</li><li>🎨 More Aesthetic: Try <code>Euler a</code> + slightly lower CFG (6.5) for dreamy, artistic vibes</li><li>🧩 ControlNet Ready: Compatible with lineart/depth ControlNets for pose/structure control (no specific preset required)</li><li>🌐 English Only: Optimized for English prompts; other languages may reduce style consistency</li><li>📐 Resolution Matters: Stick to 1024x1024 or SDXL-native aspect ratios to avoid distortion</li></ul><h2 id="limitations-and-usage-notes">⚠️ Limitations &amp; Usage Notes</h2><ul><li>Trained on 20 Danbooru-sourced images with auto-generated tags (JoyCaption); manual curation minimal</li><li>Hands, text, and complex structures may require post-processing or ControlNet assistance</li><li>Avoid mixing with conflicting keywords: <code>photorealistic</code>, <code>3d render</code>, <code>oil painting</code>, <code>ugly</code>, <code>bad anatomy</code></li><li>Best for single-character illustrations; multi-character or complex scenes may have limited generalization</li><li>🔒 Personal Research Use Only — Commercial use, artist impersonation, or sensitive content generation is strictly prohibited</li></ul><h2 id="future-plans">🔄 Future Plans</h2>Potential updates may include:<ul><li>Compatibility with other Illustrious-XL variants</li><li>Pony diffusion model support</li><li>Expanded dataset for improved multi-scene generalization</li></ul><hr />Model fine-tuned with LoRA (dim=16, alpha=8) on Illustrious-XL v0.1 | fp16 precision | English prompts optimized

Yoneyama Mai | 米山舞

<ul><li>First public version fine-tuned on Illustrious-XL v0.1</li><li>20-image training set (Danbooru source) with JoyCaption auto-tagging</li><li>Specialized in ethereal anime style: pastel colors, soft lighting, delicate linework, abstract backgrounds</li><li>Trigger word: yoneyama_mai (English prompts only)</li><li>Recommended: 1024x1024 resolution, CFG 6.5-7.5, 25-30 steps</li><li>Sampler guidance: DPM++ 2M Karras for detail | Euler a for aesthetic softness</li><li>ControlNet compatible (lineart/depth), no preset required</li><li>🔒 Personal research use only — non-commercial license</li></ul>

yoneyama-mai.safetensors

v1.0

### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('ModelE/yoneyama-mai-il-4')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/ModelE/yoneyama-mai-il-4.git
```

如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。

Files with SHA256: 4da7371cada3688b808f2e8d4ee8eb0a21e11d02fbd9a90bdd851a767e95f400