Set output resolution

Console

1. In the Google Cloud console, go to the Vertex AI > Vertex AI Studio page.

   Go to Vertex AI Studio

2. Click Generate media .

3. Click Image .

4. From the Tasklist, select Text-to-image.

5. From the Modellist, select the Imagen model to use.

6. In the Promptbox, enter a prompt that describes how to edit the image.

7. Click chevron_forward Parameters, and then adjust the following options:

   • Aspect ratio: Choose an aspect ratio from the available options.
   • Number of results: Adjust the slider to select 1 to 4 generated images.
   • Output resolution: Choose an output resolution from the available options.

8. Click Run.

REST

Before using any of the request data, make the following replacements:

• REGION : The region that your project is located in. For more information about supported regions, see Generative AI on Vertex AI locations .
• TEXT_PROMPT : The text prompt to use to generate images.
• PROJECT_ID : Your Google Cloud project ID.
• MODEL_VERSION : The Imagen model version to use. The following are accepted values when using sampleImageSize :
  • imagen-4.0-generate-001
  • imagen-4.0-ultra-generate-001
• IMAGE_RESOLUTION : The output image resolution. The following are accepted:
  • "1K"
  • "2K"

  The default setting is "1K" .

• IMAGE_COUNT : The number of images to generate. The accepted range of values is 1 to 4 .

HTTP method and URL:

POST https:// REGION 
-aiplatform.googleapis.com/v1/projects/ PROJECT_ID 
/locations/ REGION 
/publishers/google/models/ MODEL_VERSION 
:predict

Request JSON body:

{
  "instances": [
    {
      "prompt": " TEXT_PROMPT 
"
    }
  ],
  "parameters": {
    "sampleImageSize": " IMAGE_RESOLUTION 
",
    "sampleCount": IMAGE_COUNT 
}
}

To send your request, choose one of these options:

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

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