Virtual Model

Overview

Virtual Model lets you automatically convert one or more clothing photos into a polished, lifestyle photoshoot image, using either pre-defined or custom models:

(original image)	(edited image)
	virtualModel.mode=ai.auto virtualModel.model.preset.name=avery virtualModel.scene.preset.name=street virtualModel.pose=standing
+	virtualModel.mode=ai.auto virtualModel.model.custom virtualModel.scene.preset.name=random virtualModel.pose=random
	virtualModel.mode=ai.auto virtualModel.model.preset.name=jackson virtualModel.scene.preset.name=library virtualModel.pose=crossedarms
+	virtualModel.mode=ai.auto virtualModel.model.custom virtualModel.scene.preset.name=random virtualModel.pose=random
	virtualModel.mode=ai.auto virtualModel.model.preset.name=ava virtualModel.scene.preset.name=bedroom virtualModel.pose=seated
+	virtualModel.mode=ai.auto virtualModel.model.custom virtualModel.scene.preset.name=random virtualModel.pose=random

To keep the background around the virtual model, set the parameters removeBackground=false and referenceBox=originalImage. If not set, that background will be removed.

If you want to give it a try, here's the code to reproduce the first example above:

curl --request POST \
  --url https://image-api.photoroom.com/v2/edit \
  --header 'x-api-key: YOUR_API_KEY_HERE' \
  --form imageFile=@/path/to/image.png \
  --form removeBackground=false \
  --form referenceBox=originalImage \
  --form virtualModel.mode=ai.auto \
  --form virtualModel.model.preset.name=avery \
  --form virtualModel.scene.preset.name=street \
  --form virtualModel.pose=standing \
  --output result.png

Try it now!

Virtual Model is meant to be used with images that feature clothing items.

Main Parameters

To use Virtual Model, you'll need to use the following parameters:

virtualModel.mode

To enable Virtual Model, set the parameter virtualModel.mode to ai.auto.

virtualModel.model

The parameter virtualModel.model lets you control the likeness of the model.

You can either use a pre-set model or a custom one.

To use a pre-set model, set the parameter virtualModel.model.preset.name to the name of the pre-set model that you want to use.

List of pre-set models

avery

sam

taylor

kendall

jordan

casey

maya

reece

lena

julia

jackson

sophia

emma

ava

zoe

fiona

To use a custom model, you will need to provide an image of that model using either the parameter virtualModel.model.custom.imageFile or virtualModel.model.custom.imageUrl.

The parameter virtualModel.model.custom.imageFile is only available when using the POST endpoint.

By default, this parameter will be set to virtualModel.model.preset.name=avery.

virtualModel.scene

The parameter virtualModel.scene lets you control the environment in which the model will be placed.

You can either use a pre-set scene or a custom one.

To keep the scene generated around the virtual model, please also set the parameters removeBackground=false and referenceBox=originalImage.

To use a pre-set scene, set the parameter virtualModel.scene.preset.name to the name of the pre-set scene that you want to use.

List of pre-set scenes

random

street

bedroom

sunset

factory

studio

coloredstudio

concretestudio

beach

tropical

library

forest

businessdistrict

countryside

flowers

goldenlight

mountain

pool

latincity

cafe

asiancity

nightlights

desert

To use a custom scene, you will need to provide an image of that scene using either the parameter virtualModel.scene.custom.imageFile or virtualModel.scene.custom.imageUrl.

The parameter virtualModel.scene.custom.imageFile is only available when using the POST endpoint.

By default, this parameter will be set to virtualModel.scene.preset.name=random.

virtualModel.pose

The parameter virtualModel.pose lets you control the pose of the model.

You can pick between a list of pre-set poses:

List of pre-set poses

random

standing

34turn

powerstance

walkingforward

handinpocket

crossedarms

back

overtheshoulder

seated

adjustingclothing

playfulspin

By default, this parameter will be set to virtualModel.pose=random.

Which resolutions are supported?

By default, Virtual Model will produce outputs at a resolution of 1K (1024x1024).

Output resolutions of 2K and 4K are available for Enterprise plans:

(original image)

(default 1K output)

(4K output)

(original image)

(default 1K output)

(4K output)

(original image)

(default 1K output)

(4K output)

Make sure to click on the images to see them in full resolution.

If you're interested to use 2K or 4K resolution, please contact our team to book a demo.

Book a demo

Additional Parameters

virtualModel.additionalProductImages[]

Additional product images showing different angles or details of the same item.

These help the model better understand the product and generate more accurate results.

To provide these images, use either the parameter virtualModel.additionalProductImages[].imageFile or virtualModel.additionalProductImages[].imageUrl.

The parameter virtualModel.additionalProductImages[].imageFile is only available when using the POST endpoint.

virtualModel.prompt

Optional text prompt to guide the generation style.

Example: street style

virtualModel.size

The output size and aspect ratio of the generated image.

Default: PORTRAIT_HD_3_2

Possible values: PORTRAIT_HD_16_9, PORTRAIT_HD_4_3, PORTRAIT_HD_3_2, SQUARE_HD, LANDSCAPE_HD_3_2, LANDSCAPE_HD_4_3, LANDSCAPE_HD_16_9