# UrangDiffusion v3.1 - v3.1

> <p><strong>UrangDiffusion XL v3.1</strong> is fine-tuned from <strong>Animagine XL 4.0 Base</strong> (not Zero). This 4.0 Base model serves as the base model pre-trained for the final release of <strong>Animagine XL 4.0</strong> (not the Opt version).</p><p>I have received permission from the team to fine-tune the base model using my own method and release it under the <strong>UrangDiffusion</strong> series.</p><p><strong>Base model</strong>: Animagine XL 4.0 Base<br /><strong>Fine-tuning details</strong>:</p><ul><li><p><strong>Dataset size</strong>: ~1,600 images</p></li><li><p><strong>GPU</strong>: 1× A100 80GB</p></li><li><p><strong>Optimizer</strong>: AdaFactor</p></li><li><p><strong>UNet learning rate</strong>: 1.25e-6</p></li><li><p><strong>Text encoder learning rate</strong>: N/A (disabled)</p></li><li><p><strong>Batch size</strong>: 48</p></li><li><p><strong>Gradient accumulation</strong>: 1</p></li><li><p><strong>Warmup steps</strong>: 5%</p></li><li><p><strong>Minimum SNR</strong>: 5</p></li><li><p><strong>Epochs</strong>: 15</p></li></ul><p>Due to some quirks of the model, please keep the following in mind:</p><ul><li><p><strong>v3.0</strong> may perform better with anatomy</p></li><li><p><strong>v3.1</strong> may perform better with more <strong>fluid poses</strong></p></li></ul><p>If you encounter anatomical issues at <strong>28 steps</strong>, try lowering to <strong>27</strong> or increasing to <strong>29</strong>. If it improves but isn’t perfect, continue adjusting slightly up or down. If the result worsens, the previous step count was likely the optimal one.</p><p><strong>UPDATE [19/04/2025]</strong></p><ul><li><p>Some generations are stable at step 30++ with Euler a. You might wanna crank up the steps a bit.</p></li><li><p>Some generations are also better with <code>realistic, 3d</code> included in the negative. Try that too.</p></li></ul>

## Overview

- **Model ID**: `urangdiffusion-v3-1-v3-1`
- **Category**: stable diffusion xl
- **Provider**: modelslab
- **Status**: model_ready
- **Screenshot**: `https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/db532537-0294-4d17-a8cd-70593bb9fa50/width=1664/70751074.jpeg`

## API Information

This model can be used via our HTTP API. See the API documentation and usage examples below.

### Endpoint

- **URL**: `https://modelslab.com/api/v6/images/text2img`
- **Method**: POST

### Parameters

- **`prompt`** (required): prompt help in image generation
  - Type: textarea
  - Example: Enter prompt

- **`model_id`** (required): Enter model_id that can help in image generation
  - Type: text
  - Example: Enter model_id here

- **`lora_model`** (required): 
  - Type: multiple_models

- **`width`** (required): width of the image 
  - Type: number (range: 512-1024)

- **`height`** (required): height of the image 
  - Type: number (range: 512-1024)

- **`negative_prompt`** (optional): Negative prompt help in avoid things that you do not want in image 
  - Type: textarea
  - Example: Enter negative prompt that you do not want see in image

- **`scheduler`** (optional): 
  - Type: select (options: DPM++ 2M, DPM++ SDE, Euler, Euler a)

- **`guidance_scale`** (optional): 
  - Type: number (range: 1-10)

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v6/images/text2img \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "urangdiffusion-v3-1-v3-1",
    "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro",
    "width": "1024",
    "height": "1024",
    "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
    "scheduler": "DPMSolverMultistepScheduler",
    "guidance_scale": "7.5"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v6/images/text2img",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "urangdiffusion-v3-1-v3-1",
        "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro",
        "width": "1024",
        "height": "1024",
        "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
        "scheduler": "DPMSolverMultistepScheduler",
        "guidance_scale": "7.5"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v6/images/text2img", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "urangdiffusion-v3-1-v3-1",
    "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro",
    "width": "1024",
    "height": "1024",
    "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
    "scheduler": "DPMSolverMultistepScheduler",
    "guidance_scale": "7.5"
  })
})
.then(response => response.json())
.then(data => console.log(data));
```

## Links

- [Model Playground](https://modelslab.com/models/community-model/urangdiffusion-v3-1-v3-1)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)