> For the complete documentation index, see [llms.txt](https://docs.myshell.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.myshell.ai/create/pro-config-mode/api-reference/widgets/26-stable-diffusion-inpaint.md).

# Stable Diffusion Inpaint

## Try it in the Widget Center

Click this [url](https://app.myshell.ai/robot-workshop/widget/1782399147535691776) to try this widget and copy the Pro Config template.

## Usage

Utilize diffusion model to fill in the masked region of your image!

**Input Parameters**

<table><thead><tr><th>Name</th><th>Type</th><th>Description</th><th>Default</th><th data-type="checkbox">Required</th></tr></thead><tbody><tr><td>image</td><td><code>string</code></td><td>The input image, can be a url or base64 sting</td><td></td><td>true</td></tr><tr><td>mask</td><td><code>string</code></td><td>The correspond mask, can be a url or base64 sting. 1 for mask region</td><td></td><td>true</td></tr><tr><td>model</td><td><code>string</code></td><td>The model id from civitai (SD1.5, SDXL 1.0, PlaygroundV2). How to get it? Click on a model page on civitai, and copy the series number within the download link.</td><td>64094</td><td>true</td></tr><tr><td>prompt</td><td><code>string</code></td><td>The text prompt for image transformation. Add lora? add `` to your prompt. `$id` is the series number and `$weight` is the lora weight you want (always set to 1.0). You can use multiple loras.</td><td></td><td>true</td></tr><tr><td>negative_prompt</td><td><code>string</code></td><td>The negative prompt for image transformation.</td><td>(worst quality, low quality:1.4),(malformed hands:1.4),(poorly drawn hands:1.4),(mutated fingers:1.4),(extra limbs:1.35),(poorly drawn face:1.4),bad leg,strange leg, poor eyes, full screen of face</td><td>false</td></tr><tr><td>mask_blur</td><td><code>integer</code></td><td>Mask blur refers to the feathering of a mask (from edges to inside the mask), adjusted between 0-64. A smaller value results in sharper edges. Default to 4</td><td>4</td><td>false</td></tr><tr><td>inpainting_fill</td><td><code>integer</code></td><td>Choose the fill content in mask: 0 - fill, 1 - original, 2 - latent noise, 3 - latent nothing</td><td>1</td><td>false</td></tr><tr><td>inpainting_mask_invert</td><td><code>integer</code></td><td>0 - Inpaint masked region, 1 - Inpaint not masked region</td><td>0</td><td>false</td></tr><tr><td>sampler</td><td><code>string</code></td><td>Sampler for diffusion model inference</td><td>DPM++ 2M Karras</td><td>false</td></tr><tr><td>steps</td><td><code>integer</code></td><td>Steps for sampler to step whle sampling</td><td>25</td><td>false</td></tr><tr><td>cfg_scale</td><td><code>number</code></td><td>Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results. Default to 7.</td><td>7.0</td><td>false</td></tr><tr><td>seed</td><td><code>integer</code></td><td>Random seed for generation process. -1 means random seed</td><td>-1</td><td>false</td></tr><tr><td>clip_skip</td><td><code>integer</code></td><td>Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.</td><td>1</td><td>false</td></tr><tr><td>denoising_strength</td><td><code>number</code></td><td>Strength of image transfomation during inpainting precess. High means more influence during transformation</td><td>0.7</td><td>false</td></tr></tbody></table>

**Output Parameters**

| Name | Type     | Description                                                                                                  | File Type |
| ---- | -------- | ------------------------------------------------------------------------------------------------------------ | --------- |
| url  | `string` | The url of generated image, stored in the cloud. Only temporarily effective, will be cleared in a few hours. | `image`   |

**Output Example**

{% tabs %}
{% tab title="success" %}
{% code fullWidth="false" %}

```json
{
  "url": "https://image.myshell.ai/image/chat/embed_obj/40295/20240423/2f1f812747e6468b959ea7dde217b78b.jpg"
}
```

{% endcode %}
{% endtab %}

{% tab title="fail" %}
{% code fullWidth="false" %}

```json
throw a Http error.
```

{% endcode %}
{% endtab %}
{% endtabs %}

## Detailed Guidelines

* **inpaint**
  * Main parameter:
    * `image` : The input image, can be a url or base64 sting. Any size
    * `mask`: The correspond mask, can be a url or base64 sting. 1 means the masked region
    * `mask_blur` : Mask blur refers to the feathering of a mask (from edges to inside the mask), adjusted between 0-64. A smaller value results in sharper edges. Default to 4
    * `inpainting_fill` : Choose the fill content in mask: 0 - fill, 1 - original, 2 - latent noise, 3 - latent nothing. Default to 1
    * `inpainting_mask_invert`: 0 - Inpaint masked region, 1 - Inpaint not masked region
    * `denoising_strength`: Strength of image transfomation during inpainting precess. High means more influence during transformation