---
title: "p-image-try-on"
url: "https://docs.api.pruna.ai/apis/models-api-0/versions/783e153b-8e8d-4c8d-a80b-b80ec976bc53/schemas/p-image-try-on"
---

> Full API specification: https://docs.api.pruna.ai/apis/models-api-0/versions/783e153b-8e8d-4c8d-a80b-b80ec976bc53.md

# p-image-try-on

Virtual try-on model that fits one or more garment images onto a person image. Rate limit: 500 requests per minute.

## OpenAPI definition

```yaml
openapi: 3.0.3
info:
  title: P-API
  version: 0.6.0
servers:
  - url: https://api.pruna.ai
    description: Production server
components:
  schemas:
    p-image-try-on:
      type: object
      required:
        - input
      properties:
        input:
          type: object
          properties:
            seed:
              title: Seed
              description: Random seed. Leave blank for a random seed.
              type: integer
            prompt:
              title: Prompt
              default: ""
              description: EXPERIMENTAL. For non-flatlay garment images, indicates which
                garment of an image to use, e.g. 'the green t-shirt from image 1
                and the trousers from image 2'.
              type: string
            turbo:
              title: Turbo
              default: false
              description: If turned on, the model will run faster with additional
                optimizations. Not recommended for more than 4 garments.
              type: boolean
            person_image:
              title: Person Image
              format: uri
              description: Person image to edit.
              type: string
            output_format:
              enum:
                - webp
                - jpg
                - png
              title: output_format
              description: Format of the saved output image.
              default: jpg
              type: string
            garment_images:
              items:
                type: string
                format: uri
              title: Garment Images
              description: Garment reference images. Up to 6 recommended, up to 11 supported.
              type: array
            output_quality:
              title: Output Quality
              default: 95
              maximum: 100
              minimum: 0
              description: Quality for jpg/webp outputs from 0 to 100.
              type: integer
            reference_pose:
              title: Reference Pose
              format: uri
              description: Optional reference pose image. When provided, the person is reposed
                to match this reference before virtual try-on.
              type: string
            preserve_input_size:
              title: Preserve Input Size
              default: true
              description: "Return the output at the original input resolution. "
              type: boolean
          required:
            - person_image
            - garment_images
          additionalProperties: false
      description: "Virtual try-on model that fits one or more garment images onto a
        person image. Rate limit: 500 requests per minute."
```