# Virtual Try-On

**Description**
Put your garments on a model. Send `person_image` and one to three `garment_images`, and the endpoint returns the person wearing them.
**No prompt needed.** A person photo and the garments are a complete request.
Garment fidelity is the hard half of try-on: print scale, stripe alignment across seams, collar and closure type, and how a garment reads from behind all carry through. The person's identity, pose and background are preserved, along with the original aspect ratio. Send a full outfit together to change several items in one call instead of stacking edits.
Add an optional `instruction` to direct the styling. Commercially safe: built on Bria's fully licensed models, cleared for enterprise use without copyright exposure.
**Example:** "He wears the navy blazer over the white t-shirt he already has, and the grey tailored trousers instead of his jeans."
<table>
<tr>
<th style="text-align: center;">Person</th>
<th style="text-align: center;">Garment</th>
<th style="text-align: center;">Result</th>
</tr>
<tr>
<td align="center" style="vertical-align: middle;">
<img src="https://labs-assets.bria.ai/api-examples/virtual-try-on/person.jpg" width="250" style="border-radius: 8px;">
</td>
<td align="center" style="vertical-align: middle;">
<img src="https://labs-assets.bria.ai/api-examples/virtual-try-on/garment-1.jpg" width="250" style="border-radius: 8px;">
</td>
<td align="center" style="vertical-align: middle;">
<img src="https://labs-assets.bria.ai/api-examples/virtual-try-on/result.jpg" width="250" style="border-radius: 8px;">
</td>
</tr>
</table>

Endpoint: POST /image/edit/product/virtual-tryon
Security: api_token

## Request fields (application/json):

  - `person_image` (string, required)
    The photo of the person to edit. Publicly available URL or Base64-encoded.
Accepted formats: JPEG, JPG, PNG, WEBP.

  - `garment_images` (array, required)
    One to three garment or accessory images to put on the person. Send a full outfit together to change several items in one call.
Each entry is a publicly available URL or Base64-encoded, same as `person_image`.

  - `instruction` (string)
    Extra direction for this shot. This parameter is optional.
The endpoint produces the result without it, so send only the detail you want to steer, for example "He wears the navy blazer over the white t-shirt he already has.", rather than a full prompt.

  - `aspect_ratio` (string)
    The aspect ratio of the output image. This parameter is optional.
**Default:** the aspect ratio of `person_image`, so the shot keeps its original framing.
    Enum: "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9"

  - `seed` (integer)
    Seed for deterministic generation, so a shot can be reproduced exactly. Uses a random seed if omitted. This parameter is optional.

  - `sync` (boolean)
    Specifies the response mode. This parameter is optional.
- When `false` (default), the request is processed asynchronously: the API immediately returns a status URL to track progress.
- When `true`, the request is processed synchronously: the API holds the connection open until the process is complete and then returns the final image URL in the response.

  - `webhook_url` (string)
    Optional URL for receiving the result via webhook when the async job completes. See [webhooks](/getting-started/async-requests#webhooks).

  - `output_type` (string)
    The desired output format.
    Enum: "png", "jpeg"

  - `visual_output_content_moderation` (boolean)
    If true, returns 422 on visual output moderation failure. This parameter is optional.

## Response 202 fields (application/json):

  - `request_id` (string, required)

  - `status_url` (string, required)