Replace the background of an image

This page describes replacing the background of an image. Imagen on Vertex AI lets you use automatic object segmentation to maintain that content while modifying other image content. With Imagen 3 you can also provide your own mask area for more control when editing.

View Imagen for Editing and Customization model card

Product image editing example

The following use case highlights enhancing a product image by modifying an image's background, but preserving a product's appearance within the image.

Before you begin

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

2. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Go to project selector

3. Make sure that billing is enabled for your Google Cloud project.

4. Enable the Vertex AI API.

   Enable the API

5. In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

   Go to project selector

6. Make sure that billing is enabled for your Google Cloud project.

7. Enable the Vertex AI API.

   Enable the API

8. Set up authentication for your environment.

   Select the tab for how you plan to use the samples on this page:

   Console

   When you use the Google Cloud console to access Google Cloud services and APIs, you don't need to set up authentication.

   Python

   To use the Python samples on this page in a local development environment, install and initialize the gcloud CLI, and then set up Application Default Credentials with your user credentials.

   1. Install the Google Cloud CLI.

   2. If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

   3. To initialize the gcloud CLI, run the following command:

      gcloud init

   4. If you're using a local shell, then create local authentication credentials for your user account:

      gcloud auth application-default login

      You don't need to do this if you're using Cloud Shell.

      If an authentication error is returned, and you are using an external identity provider (IdP), confirm that you have signed in to the gcloud CLI with your federated identity.

   For more information, see Set up ADC for a local development environment in the Google Cloud authentication documentation.

   REST

   To use the REST API samples on this page in a local development environment, you use the credentials you provide to the gcloud CLI.

   After installing the Google Cloud CLI, initialize it by running the following command:

   gcloud init

   If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

   For more information, see Authenticate for using REST in the Google Cloud authentication documentation.

Edit with an automatically detected background mask

Imagen lets you edit product images with automatic background detection. This can be helpful if you need to modify a product image's background, but preserve the product's appearance. Product image editing uses Google Product Studio (GPS) offering. You can use the GPS feature as part of Imagen using the console or API.

Use the following instructions to enable and use product image editing with automatic background detection.

pip install --upgrade google-genai

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=us-central1
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import RawReferenceImage, MaskReferenceImage, MaskReferenceConfig, EditImageConfig

client = genai.Client()

# TODO(developer): Update and un-comment below line
# output_file = "output-image.png"

raw_ref = RawReferenceImage(
    reference_image=Image.from_file(location='test_resources/suitcase.png'), reference_id=0)
mask_ref = MaskReferenceImage(
    reference_id=1,
    reference_image=None,
    config=MaskReferenceConfig(
        mask_mode="MASK_MODE_BACKGROUND",
    ),
)

image = client.models.edit_image(
    model="imagen-3.0-capability-001",
    prompt="A light blue suitcase in front of a window in an airport",
    reference_images=[raw_ref, mask_ref],
    config=EditImageConfig(
        edit_mode="EDIT_MODE_BGSWAP",
    ),
)

image.generated_images[0].image.save(output_file)

print(f"Created output image using {len(image.generated_images[0].image.image_bytes)} bytes")
# Example response:
# Created output image using 1234567 bytes

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagen-3.0-capability-001:predict

{
  "instances": [
    {
      "prompt": "TEXT_PROMPT",
      "referenceImages": [
        {
          "referenceType": "REFERENCE_TYPE_RAW",
          "referenceId": 1,
          "referenceImage": {
            "bytesBase64Encoded": "B64_BASE_IMAGE"
          }
        },
        {
          "referenceType": "REFERENCE_TYPE_MASK",
          "referenceId": 2,
          "maskImageConfig": {
            "maskMode": "MASK_MODE_BACKGROUND",
            "dilation": MASK_DILATION
          }
        }
      ]
    }
  ],
  "parameters": {
    "editConfig": {
      "baseSteps": EDIT_STEPS
    },
    "editMode": "EDIT_MODE_BGSWAP",
    "sampleCount": EDIT_IMAGE_COUNT
  }
}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagen-3.0-capability-001:predict"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagen-3.0-capability-001:predict" | Select-Object -Expand Content

{
  "predictions": [
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    },
    {
      "mimeType": "image/png",
      "bytesBase64Encoded": "BASE64_IMG_BYTES"
    },
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    },
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    }
  ]
}

import vertexai
from vertexai.preview.vision_models import Image, ImageGenerationModel

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# input_file = "input-image.png"
# output_file = "output-image.png"
# prompt = "" # The text prompt describing what you want to see in the background.

vertexai.init(project=PROJECT_ID, location="us-central1")

model = ImageGenerationModel.from_pretrained("imagegeneration@006")
base_img = Image.load_from_file(location=input_file)

images = model.edit_image(
    base_image=base_img,
    prompt=prompt,
    edit_mode="product-image",
)

images[0].save(location=output_file, include_generation_parameters=False)

# Optional. View the edited image in a notebook.
# images[0].show()

print(f"Created output image using {len(images[0]._image_bytes)} bytes")
# Example response:
# Created output image using 1234567 bytes

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagegeneration@006:predict

{
  "instances": [
    {
      "prompt": "TEXT_PROMPT",
      "image": {
          "bytesBase64Encoded": "B64_BASE_IMAGE"
      },
    }
  ],
  "parameters": {
    "editConfig": {
      "editMode": "product-image",
      "productPosition": "PRODUCT_POSITION",
    }
  }
}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagegeneration@006:predict"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagegeneration@006:predict" | Select-Object -Expand Content

{
  "predictions": [
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    },
    {
      "mimeType": "image/png",
      "bytesBase64Encoded": "BASE64_IMG_BYTES"
    },
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    },
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    }
  ]
}

Edit with a defined mask area

You can choose to mask the area that is replaced, rather than letting Imagen detect the mask automatically.

pip install --upgrade google-genai

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=us-central1
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai
from google.genai.types import RawReferenceImage, MaskReferenceImage, MaskReferenceConfig, EditImageConfig

client = genai.Client()

# TODO(developer): Update and un-comment below line
# output_file = "output-image.png"

raw_ref = RawReferenceImage(
    reference_image=Image.from_file(location='test_resources/suitcase.png'), reference_id=0)
mask_ref = MaskReferenceImage(
    reference_id=1,
    reference_image=Image.from_file(location='test_resources/suitcase_mask.png'),
    config=MaskReferenceConfig(
        mask_mode="MASK_MODE_USER_PROVIDED",
        mask_dilation=0.0,
    ),
)

image = client.models.edit_image(
    model="imagen-3.0-capability-001",
    prompt="A light blue suitcase in an airport",
    reference_images=[raw_ref, mask_ref],
    config=EditImageConfig(
        edit_mode="EDIT_MODE_BGSWAP",
    ),
)

image.generated_images[0].image.save(output_file)

print(f"Created output image using {len(image.generated_images[0].image.image_bytes)} bytes")
# Example response:
# Created output image using 1234567 bytes

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagen-3.0-capability-001:predict

{
  "instances": [
    {
      "prompt": "TEXT_PROMPT": [
        {
          "referenceType": "REFERENCE_TYPE_RAW",
          "referenceId": 1,
          "referenceImage": {
            "bytesBase64Encoded": "B64_BASE_IMAGE"
          }
        },
        {
          "referenceType": "REFERENCE_TYPE_MASK",
          "referenceId": 2,
          "referenceImage": {
            "bytesBase64Encoded": "B64_MASK_IMAGE"
          },
          "maskImageConfig": {
            "maskMode": "MASK_MODE_USER_PROVIDED",
            "dilation": MASK_DILATION
          }
        }
      ]
    }
  ],
  "parameters": {
    "editConfig": {
      "baseSteps": EDIT_STEPS
    },
    "editMode": "EDIT_MODE_BGSWAP",
    "sampleCount": EDIT_IMAGE_COUNT
  }
}

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagen-3.0-capability-001:predict"

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/imagen-3.0-capability-001:predict" | Select-Object -Expand Content

{
  "predictions": [
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    },
    {
      "mimeType": "image/png",
      "bytesBase64Encoded": "BASE64_IMG_BYTES"
    },
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    },
    {
      "bytesBase64Encoded": "BASE64_IMG_BYTES",
      "mimeType": "image/png"
    }
  ]
}

Limitations

Because masks are sometimes incomplete, the model may try to complete the foreground object when extremely small bits are missing at the boundary. As a rare side effect, when the foreground object is already complete, the model may create slight extensions.

A workaround is to segment the model output and then blend. The following is an example python snippet demonstrating a workaround:

blended = Image.composite(out_images[0].resize(image_expanded.size), image_expanded, mask_expanded)

What's next

Read articles about Imagen and other Generative AI on Vertex AI products:

• A developer's guide to getting started with Imagen 3 on Vertex AI
• New generative media models and tools, built with and for creators
• New in Gemini: Custom Gems and improved image generation with Imagen 3
• Google DeepMind: Imagen 3 - Our highest quality text-to-image model