# Virtual Try-On API Reference

{% hint style="info" %}
**Good to know:** A quick start guide can be good to help folks get up and running with your API in a few steps. Some people prefer diving in with the basics rather than meticulously reading every page of documentation!
{% endhint %}

## Get your API keys

Your `API` requests are authenticated using `API` keys. Any request that doesn't include an `API` key will return an `error`.

You can generate an `API` key from your user `dashboard` in [Miragic](https://miragic.ai/) website anytime.

<figure><img src="/files/20ehQwfdabPgUTlxGVtj" alt=""><figcaption></figcaption></figure>

## Authentication

All requests must include the `X-API-Key` header containing your assigned `API` key.

{% tabs %}
{% tab title="cURL" %}

```bash
curl -X POST "https://backend.miragic.ai/api/v1/virtual-try-on" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "garmentType=full_body" \
  -F "humanImage=@path/to/human_image.jpg;type=image/jpeg" \
  -F "clothImage=@path/to/cloth_image.jpg;type=image/jpeg"
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
import axios from "axios";
import FormData from "form-data";
import fs from "fs";

const API_KEY = "YOUR_API_KEY";
const BASE_URL = "https://backend.miragic.ai";

async function virtualTryOn() {
  const url = `${BASE_URL}/api/v1/virtual-try-on`;

  // Prepare form data
  const formData = new FormData();
  formData.append("garmentType", "full_body");
  formData.append("humanImage", fs.createReadStream("path/to/human_image.jpg"));
  formData.append("clothImage", fs.createReadStream("path/to/cloth_image.jpg"));

  try {
    const response = await axios.post(url, formData, {
      headers: {
        ...formData.getHeaders(),
        "X-API-Key": API_KEY,
      },
      maxBodyLength: Infinity, // useful for large files
    });

    console.log("✅ Success!");
    console.log(response.data);
  } catch (error) {
    if (error.response) {
      console.error("❌ API Error:", error.response.status, error.response.data);
    } else {
      console.error("❌ Request Error:", error.message);
    }
  }
}

virtualTryOn();
```

{% endtab %}

{% tab title="Python" %}

```python
import requests
import time

api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'

def virtualtryon():
    url = f'{base_url}/api/v1/virtual-try-on'
    data = {'garmentType': 'full_body'}

    files=[
    ('humanImage',('human_image.jpg',open('path/to/human_image.jpg','rb'),'image/jpeg')),
    ('clothImage',('cloth_image.jpg',open('path/to/cloth_image.jpg','rb'),'image/jpeg'))
    ]
    headers = {'X-API-Key': api_key}
    response = requests.request("POST", url, headers=headers, data=data, files=files)
    print(response.text)
    
if __name__ == '__main__':
    virtualtryon()
```

{% endtab %}
{% endtabs %}

## How To Create VTO Process

<mark style="background-color:green;">POST</mark>   `/api/v1/virtual-try-on`

This `API` starts the `virtualtry-on` process by creating a task that generates an image of the model wearing the specified clothing. It supports both `single-item try-ons` and `combo try-ons` (upper and lower body clothing combined).

### Try-on Options

<mark style="color:green;">**Single Item Try-on:**</mark>

* `Upper Body`: Try on shirts, t-shirts, jackets, etc.
* `Lower Body`: Try on pants, shorts, skirts, etc.
* `Full Body`: Try on dresses, jumpsuits, etc.

<mark style="color:green;">**Combo Try-on:**</mark>

* Try on upper and lower body clothing simultaneously.
* Particularly useful for coordinating complete outfits.
* Requires a compatible model pose for both items.

{% hint style="info" %}
Processing Information

* Tasks are processed asynchronously in the background
* Progress can be monitored using the `Get Task Status API`
* The final result will be a high-quality image up to `2048`px resolution
  {% endhint %}

### Request

<mark style="color:green;">**Form Data (Case 1: Single Clothing Try-on)**</mark>

<table><thead><tr><th width="135">Parameter</th><th width="82">Type</th><th width="106">Required</th><th>Description</th></tr></thead><tbody><tr><td>humanImage</td><td>File</td><td>Yes</td><td>Human image (recommended size: <code>2048</code>px)</td></tr><tr><td>clothImage</td><td>File</td><td>Yes</td><td>Garment image to try on (recommended size: <code>1024</code>px)</td></tr><tr><td>garmentType</td><td>String</td><td>Yes</td><td>Type of garment: <code>upper_body</code>, <code>lower_body</code>, or <code>full_body</code></td></tr></tbody></table>

<mark style="color:green;">**Form Data (Case 2: Combo Try-on)**</mark>

<table><thead><tr><th width="180">Parameter</th><th width="86">Type</th><th width="107">Required</th><th>Description</th></tr></thead><tbody><tr><td>garmentType</td><td>String</td><td>Yes</td><td>Can be any text for this case</td></tr><tr><td>clothImage</td><td>File</td><td>Yes</td><td>Upper garment image (recommended size: <code>1024</code>px)</td></tr><tr><td>bottomClothImage</td><td>File</td><td>Yes</td><td>Lower garment image (recommended size: <code>1024</code>px)</td></tr><tr><td>humanImage</td><td>File</td><td>Yes</td><td> Human image (recommended size: <code>2048</code>px)</td></tr></tbody></table>

The best way to interact with our `API` is to use one of our official libraries:

{% hint style="info" %}
**Best Practices:**

* Resize images to the recommended dimensions before uploading to ensure optimal performance.
* Make sure the human’s pose matches the garment type being tried on.
* For combo try-ons, ensure the human image is appropriate for both upper and lower clothing.
  {% endhint %}

<mark style="color:green;">**Request Example (Case 1: Single Clothing Try-on)**</mark>

{% tabs %}
{% tab title="cURL" %}

```bash
curl -X POST "https://backend.miragic.ai/api/v1/virtual-try-on" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "garmentType=full_body" \
  -F "humanImage=@path/to/human_image.jpg;type=image/jpeg" \
  -F "clothImage=@path/to/cloth_image.jpg;type=image/jpeg"
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
import axios from "axios";
import FormData from "form-data";
import fs from "fs";

const API_KEY = "YOUR_API_KEY";
const BASE_URL = "https://backend.miragic.ai";

async function virtualTryOn() {
  const url = `${BASE_URL}/api/v1/virtual-try-on`;

  // Prepare form data
  const formData = new FormData();
  formData.append("garmentType", "full_body");
  formData.append("humanImage", fs.createReadStream("path/to/human_image.jpg"));
  formData.append("clothImage", fs.createReadStream("path/to/cloth_image.jpg"));

  try {
    const response = await axios.post(url, formData, {
      headers: {
        ...formData.getHeaders(),
        "X-API-Key": API_KEY,
      },
      maxBodyLength: Infinity, // useful for large files
    });

    console.log("✅ Success!");
    console.log(response.data);
  } catch (error) {
    if (error.response) {
      console.error("❌ API Error:", error.response.status, error.response.data);
    } else {
      console.error("❌ Request Error:", error.message);
    }
  }
}

virtualTryOn();
```

{% endtab %}

{% tab title="Python" %}

```python
import requests
import time

api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'

def virtualtryon():
    url = f'{base_url}/api/v1/virtual-try-on'
    data = {'garmentType': 'full_body'}

    files=[
    ('humanImage',('human_image.jpg',open('path/to/human_image.jpg','rb'),'image/jpeg')),
    ('clothImage',('cloth_image.jpg',open('path/to/cloth_image.jpg','rb'),'image/jpeg'))
    ]
    headers = {'X-API-Key': api_key}
    response = requests.request("POST", url, headers=headers, data=data, files=files)
    print(response.text)

if __name__ == '__main__':
    virtualtryon()
```

{% endtab %}
{% endtabs %}

<mark style="color:green;">**Request Example (Case 2: Combo Try-on)**</mark>

{% tabs %}
{% tab title="cURL" %}

```bash
curl -X POST "https://backend.miragic.ai/api/v1/virtual-try-on" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "garmentType=comb" \
  -F "humanImage=@path/to/human_image.jpg;type=image/jpeg" \
  -F "clothImage=@path/to/cloth_image.jpg;type=image/jpeg" \
  -F "bottomClothImage=@path/to/bottom_cloth_image.jpg;type=image/jpeg"
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
import axios from "axios";
import FormData from "form-data";
import fs from "fs";

const API_KEY = "YOUR_API_KEY";
const BASE_URL = "https://backend.miragic.ai";

async function virtualTryOn() {
  const url = `${BASE_URL}/api/v1/virtual-try-on`;

  // Prepare form data
  const formData = new FormData();
  formData.append("garmentType", "comb");
  formData.append("humanImage", fs.createReadStream("path/to/human_image.jpg"));
  formData.append("clothImage", fs.createReadStream("path/to/cloth_image.jpg"));
  formData.append("bottomClothImage", fs.createReadStream("path/to/bottom_cloth_image.jpg"));

  try {
    const response = await axios.post(url, formData, {
      headers: {
        ...formData.getHeaders(),
        "X-API-Key": API_KEY,
      },
      maxBodyLength: Infinity, // useful for large files
    });

    console.log("✅ Success!");
    console.log(response.data);
  } catch (error) {
    if (error.response) {
      console.error("❌ API Error:", error.response.status, error.response.data);
    } else {
      console.error("❌ Request Error:", error.message);
    }
  }
}

virtualTryOn();
```

{% endtab %}

{% tab title="Python" %}

```python
import requests
import time

api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'

def virtualtryon():
    url = f'{base_url}/api/v1/virtual-try-on'
    data = {'garmentType': 'comb'}

    files=[
    ('humanImage',('human_image.jpg',open('path/to/human_image.jpg','rb'),'image/jpeg')),
    ('clothImage',('cloth_image.jpg',open('path/to/cloth_image.jpg','rb'),'image/jpeg')),
    ('bottomClothImage',('bottom_cloth_image.jpg',open('path/to/bottom_cloth_image.jpg','rb'),'image/jpeg'))
    ]
    headers = {'X-API-Key': api_key}
    response = requests.request("POST", url, headers=headers, data=data, files=files)
    print(response.text)

if __name__ == '__main__':
    virtualtryon()
```

{% endtab %}
{% endtabs %}

<mark style="color:green;">**Response (Case 1: Single Clothing Try-on)**</mark>

```bash
{"success":true,"message":"Virtual try-on job created and processing started","data":{"jobId":"25331fb2-d0b0-44bd-b932-44f6fcc85e3e","status":"PENDING","mode":"SINGLE","createdAt":"2025-10-08T13:46:57.867Z"}}
```

<mark style="color:green;">**Response (Case 2: Combo Try-on)**</mark>

```bash
{"success":true,"message":"Virtual try-on job created and processing started","data":{"jobId":"89011007-ea00-4160-9f3d-b15e77b719bc","status":"PENDING","mode":"TOP_BOTTOM","createdAt":"2025-10-08T14:25:18.213Z"}}
```

**Response Field**

<table><thead><tr><th width="107">Field</th><th width="88">Type</th><th>Description</th></tr></thead><tbody><tr><td>jobId</td><td>String</td><td>A unique identifier used to track task status and retrieve results.</td></tr><tr><td>status</td><td>String</td><td>The initial status will be <code>PENDING</code>. Use the <code>Get Task Status API</code> to track progress.</td></tr><tr><td>mode</td><td>String</td><td>String to indicate single clothing try-on(<code>SINGLE</code>) or combo try-on(<code>TOP_BOTTOM</code>).</td></tr><tr><td>createdAt</td><td>String</td><td>Date</td></tr><tr><td>success</td><td>Logic</td><td><code>true</code> or <code>false</code> to indicate whether task is successful or not.</td></tr></tbody></table>

## How To Get Process Status

<mark style="background-color:green;">GET</mark>   `/api/v1/virtual-try-on/:jobId`

This `API` lets you check the status of a try-on task and retrieve the final result. Because the try-on process runs asynchronously, you’ll need to poll this endpoint until the task is finished.

### Task Status:

<table><thead><tr><th width="110">Status</th><th width="213">Description</th><th width="110">Progress</th><th>Next Action</th></tr></thead><tbody><tr><td><code>PENDING</code></td><td>Task is currently being processed.</td><td><code>0</code>~<code>99</code>%</td><td>Continue polling</td></tr><tr><td><code>COMPLETED</code></td><td>Task has finished successfully.</td><td><code>100</code>%</td><td>Download result using download_signed_url</td></tr><tr><td><code>FAILED</code></td><td>Task processing failed.</td><td>N/A</td><td>Check error details and retry if needed</td></tr></tbody></table>

{% hint style="info" %} <mark style="color:green;">**Progress Tracking:**</mark>

* The `progress` field indicates the percentage of task completion (`0`-`100`)
* Progress updates are available in real-time during the `PENDING` state
* Progress increases as the AI processes different stages of the try-on task
  {% endhint %}

{% hint style="info" %}
**Polling Guidelines:**

* Start polling immediately after creating the task
* Implement exponential backoff to avoid rate limiting
* The download\_signed\_url is temporary and should be used promptly
* Consider implementing a timeout after extended polling
  {% endhint %}

### Request:

<mark style="color:blue;">**URL Parameters**</mark>

<table><thead><tr><th width="122">Parameter</th><th width="94">Type</th><th width="111">Required</th><th>Description</th></tr></thead><tbody><tr><td>JobId</td><td>String</td><td>Yes</td><td>This value indicates task ID assigned by requesting <code>VTO</code> process <code>API</code></td></tr></tbody></table>

<mark style="color:blue;">**Request Example**</mark>

{% tabs %}
{% tab title="cURL" %}

```bash
curl -X GET https://backend.miragic.ai/api/v1/virtual-try-on/25331fb2-d0b0-44f6fcc85e3e \
  -H "X-API-Key: YOUR_API_KEY"
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
const fetch = require("node-fetch"); // for Node.js

const apiKey = "YOUR_API_KEY";
const jobId = "25331fb2-d0b0-44f6fcc85e3e";
const url = `https://backend.miragic.ai/api/v1/virtual-try-on/${jobId}`;

const options = {
  method: "GET",
  headers: {
    "X-API-Key": apiKey
  }
};

fetch(url, options)
  .then(response => response.json())
  .then(data => {
    console.log("Response:", data);
  })
  .catch(error => {
    console.error("Error:", error);
  });
```

{% endtab %}

{% tab title="Python" %}

```python
import requests

api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
job_id = "25331fb2-d0b0-44f6fcc85e3e"
url = f"https://backend.miragic.ai/api/v1/virtual-try-on/{job_id}"

headers = {
    "X-API-Key": api_key
}
response = requests.get(url, headers=headers)

# Print status code and response JSON
print("Status Code:", response.status_code)
print("Response:", response.json())
```

{% endtab %}
{% endtabs %}

<mark style="color:blue;">**Response Example**</mark>

#### Completed Status (200):

```bash
{
    'success': True,
    'data': {
        'id': '25331fb2-d0b0-44f6fcc85e3e',
        'status': 'COMPLETED', 
        'mode': 'SINGLE', 
        'humanImagePath': 'https://backend.miragic.ai/uploads/temp/1759935012047-9783377-1.jpg', 
        'clothImagePath': 'https://backend.miragic.ai/uploads/virtualtryon/original/clothes/single/0f01f45d-37e5-4796-ae1d-aca695a0d792/3baecbdb-d7fe-4599-b542-b86f4d28fa90.jpg', 
        'bottomClothImagePath': None, 
        'resultImagePath': 'https://backend.miragic.ai/uploads/virtualtryon/processed/single/0f01f45d-37e5-ae1d-aca695a0d792/b86386c0-7626-4d3b-9572-5dae9c59fccd.jpg', 
        'processedUrl': 'https://backend.miragic.ai/uploads/virtualtryon/processed/single/0f01f45d-4796-ae1d-aca695a0d792/b86386c0-7626-4d3b-9572-5dae9c59fccd.jpg', 
        'createdAt': '2025-10-08T14:50:12.191Z', 
        'processingStartedAt': '2025-10-08T14:50:12.194Z', 
        'processingCompletedAt': '2025-10-08T14:50:32.211Z', 
        'errorMessage': None
    }
}
```

<mark style="color:blue;">**Response Fields**</mark>

<table><thead><tr><th width="203">Field</th><th width="85">Type</th><th>Description</th></tr></thead><tbody><tr><td>id</td><td>String</td><td>Unique identifier of the task</td></tr><tr><td>status</td><td>String</td><td>Current status of the task (<code>PENDING</code>/<code>COMPLETED</code>/<code>FAILED</code>)</td></tr><tr><td>mode</td><td>String</td><td>String to indicate single clothing try-on(<code>SINGLE</code>) or combo try-on(<code>TOP_BOTTOM</code>).</td></tr><tr><td>humanImagePath</td><td>String</td><td><code>URL</code> to human image</td></tr><tr><td>bottomClothImagePath</td><td>String</td><td><code>URL</code> to lower garment image</td></tr><tr><td>clothImagePath</td><td>String</td><td><code>URL</code> to uppper garment image</td></tr><tr><td>resultImagePath</td><td>String</td><td><code>URL</code> to result image</td></tr><tr><td>createdAt</td><td>Number</td><td>Unix timestamp when processing is created</td></tr><tr><td>processingStartedAt</td><td>Number</td><td>Unix timestamp when processing is started</td></tr><tr><td>processingCompletedAt</td><td>Number</td><td>Unix timestamp when processing is completed</td></tr><tr><td>errorMessage</td><td>String</td><td>Error message</td></tr></tbody></table>

## Rate Limits

To maintain service stability and fair usage, the `API` enforces the following rate limit:

* **`60` requests per minute** per `API` key

If this limit is exceeded, an  error (`Too Many Requests`) will be returned. Please ensure your application includes proper retry logic with exponential backoff.

## Full Code Example

The following code lines are quick example to use our `API` in multiple languages.

<mark style="color:green;">**Case 1: Single Clothing Try-on**</mark>

{% tabs %}
{% tab title="cURL" %}

```bash
curl -X POST "https://backend.miragic.ai/api/v1/virtual-try-on" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "garmentType=full_body" \
  -F "humanImage=@path/to/human_image.jpg;type=image/jpeg" \
  -F "clothImage=@path/to/cloth_image.jpg;type=image/jpeg"
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
import axios from "axios";
import fs from "fs";
import FormData from "form-data";

const apiKey = "YOUR_API_KEY";
const baseUrl = "https://backend.miragic.ai";

async function virtualTryOn() {
  const url = `${baseUrl}/api/v1/virtual-try-on`;

  const formData = new FormData();
  formData.append("garmentType", "full_body");
  formData.append("humanImage", fs.createReadStream("path/to/human_image.jpg"));
  formData.append("clothImage", fs.createReadStream("path/to/cloth_image.jpg"));

  try {
    // Step 1: Create virtual try-on job
    const response = await axios.post(url, formData, {
      headers: {
        "X-API-Key": apiKey,
        ...formData.getHeaders(),
      },
    });

    console.log("Response:", response.data);

    if (response.data.success) {
      const jobId = response.data.data.jobId;
      console.log(`Job ID: ${jobId}`);

      // Step 2: Poll for result
      while (true) {
        const result = await axios.get(`${baseUrl}/api/v1/virtual-try-on/${jobId}`, {
          headers: {
            "X-API-Key": apiKey,
          },
        });

        const status = result.data.data.status;
        console.log("Status:", status);

        if (status === "COMPLETED") {
          console.log("Result:", result.data);
          break;
        } else if (status === "FAILED") {
          console.error("Job failed:", result.data);
          break;
        }

        // Wait 2 seconds before next poll
        await new Promise((resolve) => setTimeout(resolve, 2000));
      }
    } else {
      console.error("Error:", response.data);
    }
  } catch (error) {
    console.error("Error occurred:", error.response?.data || error.message);
  }
}

virtualTryOn();

```

{% endtab %}

{% tab title="Python" %}

```python
import requests
import time

api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'

def virtualtryon():
    url = f'{base_url}/api/v1/virtual-try-on'
    data = {'garmentType': 'full_body'}
    
    files=[
    ('humanImage',('human_image.jpg',open('path/to/human_image.jpg','rb'),'image/jpeg')),
    ('clothImage',('cloth_image.jpg',open('path/to/cloth_image.jpg','rb'),'image/jpeg'))
    ]
    headers = {'X-API-Key': api_key}
    response = requests.request("POST", url, headers=headers, data=data, files=files)
    print(response.text)
    
    if response.json()['success']:
        job_id = response.json()['data']['jobId']
        print(f'Job ID: {job_id}')
        # Poll for results
        while True:
            result = requests.get(
                f'{base_url}/api/v1/virtual-try-on/{job_id}',
                headers=headers
            )
            if result.json()['data']['status'] == 'COMPLETED':
                print('Result:', result.json())
                break
            elif result.json()['data']['status'] == 'FAILED':
                print('Job failed:', result.json())
                break
            time.sleep(2)
    else:
        print('Error:', response.json())

if __name__ == '__main__':
    virtualtryon()
```

{% endtab %}
{% endtabs %}

<mark style="color:green;">**Case 2: Combo Try-on**</mark>

{% tabs %}
{% tab title="cURL" %}

```bash
curl -X POST "https://backend.miragic.ai/api/v1/virtual-try-on" \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "garmentType=comb" \
  -F "humanImage=@path/to/human_image.jpg;type=image/jpeg" \
  -F "clothImage=@path/to/cloth_image.jpg;type=image/jpeg" \
  -F "bottomClothImage=@path/to/bottom_cloth_image.jpg;type=image/jpeg"
```

{% endtab %}

{% tab title="JavaScript" %}

```javascript
import axios from "axios";
import FormData from "form-data";
import fs from "fs";

const apiKey = "YOUR_API_KEY";
const baseUrl = "https://backend.miragic.ai";

async function virtualTryOn() {
  const url = `${baseUrl}/api/v1/virtual-try-on`;

  // Prepare form data
  const formData = new FormData();
  formData.append("garmentType", "comb");
  formData.append("humanImage", fs.createReadStream("path/to/human_image.jpg"));
  formData.append("clothImage", fs.createReadStream("path/to/cloth_image.jpg"));
  formData.append(
    "bottomClothImage",
    fs.createReadStream("path/to/bottom_cloth_image.jpg")
  );

  const headers = {
    "X-API-Key": apiKey,
    ...formData.getHeaders(),
  };

  try {
    // Step 1: Submit try-on request
    const response = await axios.post(url, formData, { headers });
    console.log(response.data);

    if (response.data.success) {
      const jobId = response.data.data.jobId;
      console.log(`Job ID: ${jobId}`);

      // Step 2: Poll for results
      while (true) {
        const result = await axios.get(`${baseUrl}/api/v1/virtual-try-on/${jobId}`, {
          headers: { "X-API-Key": apiKey },
        });

        const status = result.data.data.status;
        if (status === "COMPLETED") {
          console.log("Result:", result.data);
          break;
        } else if (status === "FAILED") {
          console.log("Job failed:", result.data);
          break;
        }

        // Wait before next check
        await new Promise((resolve) => setTimeout(resolve, 2000));
      }
    } else {
      console.log("Error:", response.data);
    }
  } catch (error) {
    console.error("Request failed:", error.response?.data || error.message);
  }
}

virtualTryOn();

```

{% endtab %}

{% tab title="Python" %}

```python
import requests
import time

api_key = 'YOUR_API_KEY' # ← Replace with your actual API key
base_url = 'https://backend.miragic.ai'

def virtualtryon():
    url = f'{base_url}/api/v1/virtual-try-on'
    data = {'garmentType': 'comb'}
    
    files=[
    ('humanImage',('human_image.jpg',open('path/to/human_image.jpg','rb'),'image/jpeg')),
    ('clothImage',('cloth_image.jpg',open('path/to/cloth_image.jpg','rb'),'image/jpeg')),
    ('bottomClothImage',('bottom_cloth_image.jpg',open('path/to/bottom_cloth_image.jpg','rb'),'image/jpeg'))
    ]
    headers = {'X-API-Key': api_key}
    response = requests.request("POST", url, headers=headers, data=data, files=files)
    print(response.text)
    
    if response.json()['success']:
        job_id = response.json()['data']['jobId']
        print(f'Job ID: {job_id}')
        
        # Poll for results
        while True:
            result = requests.get(
                f'{base_url}/api/v1/virtual-try-on/{job_id}',
                headers=headers
            )
            if result.json()['data']['status'] == 'COMPLETED':
                print('Result:', result.json())
                break
            elif result.json()['data']['status'] == 'FAILED':
                print('Job failed:', result.json())
                break
            time.sleep(2)
    else:
        print('Error:', response.json())

if __name__ == '__main__':
    virtualtryon()
```

{% endtab %}
{% endtabs %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.miragic.ai/virtual-try-on-api-reference.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.