Name: Pruna AI P-Image Try-On Virtual Try-On API
Brand: magicapi
SKU: api-magicapi-virtual-try-on-ai-api-prunaai-p-image-try-on
Availability: InStock
Author: API Market

Shashank Agarwal

# 👗 Virtual Try-On API (Pruna AI P-Image Try-On)

## Overview
P-Image Try-On is a virtual try-on model from Pruna AI. Its developer describes it as putting one or more garments onto a person photo while keeping their face, pose and body.

Send a `person_image` and one or more `garment_images`. Each request returns the URL of one image of the person wearing the garments.

## Features
- **Several garments at once**: up to 6 garment images recommended, up to 11 supported.
- **Keeps the person**: face, pose and body come from `person_image`.
- **Garment selection (experimental)**: when a garment image is not a flat lay, use `prompt` to say which garment to take, for example "the green t-shirt from image 1 and the trousers from image 2".
- **Reference pose (experimental)**: `reference_pose` reposes the person to match a reference image before the try-on. Might fail for some seeds.
- **Turbo**: `turbo` runs faster with extra optimizations; not recommended for more than 4 garments.
- **Output**: `jpg` (default), `png` or `webp`, `output_quality` 0 to 100, and `preserve_input_size` (default `true`) to keep the person photo's resolution.

## Use Cases
1. **Product page previews**: show catalog garments on a model photo without a new shoot.
2. **Outfit building**: combine a top, trousers and outerwear on one person.
3. **Shopper try-on**: let customers see a garment on their own photo.
4. **Design mockups**: preview a new garment design on a person.

## Visual Examples
### Example Input
A person photo and one garment photo, both generated by us with other models on api.market, with all other fields at their defaults (`turbo` off, `jpg` at quality 95, input size preserved).

Person image (`person_image`):

![Input person: a young woman in a white t-shirt and light blue jeans against a light grey background](https://blog.api.market/wp-content/uploads/2026/11/z-image-turbo-output-zfy68yms-api-market.jpg)

Garment image (`garment_images`):

![Input garment: a forest green knitted cardigan with wooden buttons laid flat on white](https://blog.api.market/wp-content/uploads/2026/11/grok-imagine-image-quality-output-n60p8v5y-api-market.jpg)

```json
{
  "prompt": "",
  "person_image": "https://blog.api.market/wp-content/uploads/2026/11/z-image-turbo-output-zfy68yms-api-market.jpg",
  "garment_images": [
    "https://blog.api.market/wp-content/uploads/2026/11/grok-imagine-image-quality-output-n60p8v5y-api-market.jpg"
  ],
  "turbo": false,
  "no_op": false,
  "output_format": "jpg",
  "output_quality": 95,
  "preserve_input_size": true
}
```

### Example Output
![P-Image Try-On output: the same woman, pose and jeans, now wearing the buttoned green knitted cardigan in place of the white t-shirt](https://blog.api.market/wp-content/uploads/2026/11/p-image-try-on-output-b1frsatf-api-market.jpg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `person_image` | string (URL) | Yes |  |  | Person image (URL) to edit. |
| `garment_images` | array of URLs | Yes |  |  | Garment reference images (URLs). Up to 6 recommended, up to 11 supported. |
| `reference_pose` | string (URL) | No | none |  | Experimental. Optional reference pose image (URL). When provided, the person is reposed to match it before the try-on. Might fail for some seeds. |
| `prompt` | string | No | `""` |  | Experimental. For garment images that are not flat lays, says which garment of an image to use, e.g. 'the green t-shirt from image 1 and the trousers from image 2'. |
| `turbo` | boolean | No | `false` |  | Runs faster with additional optimizations. Not recommended for more than 4 garments. |
| `seed` | integer | No | none |  | Random seed. Leave blank for a random seed. |
| `preserve_input_size` | boolean | No | `true` |  | Return the output at the original input resolution. |
| `output_format` | string | No | `jpg` | `webp`, `jpg`, `png` | Format of the output image. |
| `output_quality` | integer | No | `95` | 0 to 100 | Quality for jpg and webp outputs, from 0 to 100. |
| `no_op` | boolean | No | `false` |  | Health check mode: returns a status without running the model. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.001 per API unit.
- **Metered billing**: a request is billed for what it uses, summed over each priced item, then rounded up to a whole API unit.
- **Prices** (one price row for every request):

| Item | Price |
| --- | --- |
| Request | $0.00824 |
| Input image megapixel | $0.00942 |

- Input image megapixels cover `person_image`, `garment_images` and `reference_pose`, as the model measures them (an image that cannot be read counts as 12 megapixels).
- Every request is billed the same way, including health checks with `no_op` set to `true`.
- **Example cost**: the model measured 1 input image megapixel for the example: $0.00824 + 1 x $0.00942 = $0.0177, rounded up to 18 units ($0.018).
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/virtual-try-on-ai-api-prunaai-p-image-try-on`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/virtual-try-on-ai-api-prunaai-p-image-try-on/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "prunaai/p-image-try-on",
    "input": {
      "prompt": "",
      "person_image": "https://blog.api.market/wp-content/uploads/2026/11/z-image-turbo-output-zfy68yms-api-market.jpg",
      "garment_images": [
        "https://blog.api.market/wp-content/uploads/2026/11/grok-imagine-image-quality-output-n60p8v5y-api-market.jpg"
      ],
      "turbo": false,
      "no_op": false,
      "output_format": "jpg",
      "output_quality": 95,
      "preserve_input_size": true
    }
  }'
```

Response (201 Created):
```json
{
  "id": "b1frsatf11rmy0d1n18s79ac1g",
  "version": "prunaai/p-image-try-on",
  "status": "starting",
  "created_at": "2026-11-04T20:47:43.368Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/virtual-try-on-ai-api-prunaai-p-image-try-on/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "b1frsatf11rmy0d1n18s79ac1g",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/p-image-try-on-output-b1frsatf-api-market.jpg",
  "error": null,
  "created_at": "2026-11-04T20:47:43.368Z",
  "started_at": "2026-11-04T20:47:43.376Z",
  "completed_at": "2026-11-04T20:47:46.815Z"
}
```

`output` is a single URL string pointing to the try-on image.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `person_image` or `garment_images`.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/virtual-try-on-ai-api-prunaai-p-image-try-on";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "prunaai/p-image-try-on", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "prompt": "",
  "person_image": "https://blog.api.market/wp-content/uploads/2026/11/z-image-turbo-output-zfy68yms-api-market.jpg",
  "garment_images": [
    "https://blog.api.market/wp-content/uploads/2026/11/grok-imagine-image-quality-output-n60p8v5y-api-market.jpg"
  ],
  "turbo": false,
  "no_op": false,
  "output_format": "jpg",
  "output_quality": 95,
  "preserve_input_size": true
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/virtual-try-on-ai-api-prunaai-p-image-try-on"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "prunaai/p-image-try-on", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "prompt": "",
    "person_image": "https://blog.api.market/wp-content/uploads/2026/11/z-image-turbo-output-zfy68yms-api-market.jpg",
    "garment_images": [
        "https://blog.api.market/wp-content/uploads/2026/11/grok-imagine-image-quality-output-n60p8v5y-api-market.jpg"
    ],
    "turbo": False,
    "no_op": False,
    "output_format": "jpg",
    "output_quality": 95,
    "preserve_input_size": True
}))
```

## FAQ
- **How many garments can I send?**
  - Up to 11 in `garment_images`; up to 6 is recommended. Leave `turbo` off for more than 4 garments.
- **Can I use a photo of someone wearing the garment?**
  - Yes, but say which garment to take in `prompt`, for example "the jacket from image 1". This is experimental; flat-lay product images work without a prompt.
- **Does the output keep the person's photo size?**
  - Yes by default. `preserve_input_size` is `true`; set it to `false` to let the model choose the size.
- **What does a request cost?**
  - $0.00824 per request plus $0.00942 per megapixel of the input images, rounded up to a whole $0.001 unit. The example cost $0.018.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page.


Dress a person photo in one or more garment images with Pruna AI's P-Image Try-On, keeping face, pose and body. From $0.00824 per request plus input size, pay as you go.