This page describes how to omit content from Imagen on Vertex AI generated
images. A negative prompt is a description of what you want to omit in generated images.
For example, consider the prompt "a rainy city street at night
with no people". The model may interpret "people" as a directive of what
include instead of omit. To generate better results, you could
use the prompt "a rainy city street at night" with a negative
prompt "people". Imagen generates these images with and without a negative
prompt: Text prompt only Text prompt and negative prompt The following models support negative prompts: To omit content from generated images, do the following: In the Google Cloud console, go to the Vertex AI > Media
Studio page. Click Imagen. The Imagen Media Studio image generation page is
displayed. In the Settings panel, adjust the following options: Model: Choose a model from the available options. For more information about available models, see Imagen
models Number of results: Adjust the slider or enter a value between
1 and 4. In the Negative prompt box, enter a prompt that describes what
you don't want generated in the image. In the Write your prompt box, enter your text prompt that describes
the images to generate. For example, small boat on water in the
morning watercolor illustration. For more information details about writing effective prompts, see
Prompt and image attribute
guide. Click
Negative prompt is an optional field in the
Before using any of the request data,
make the following replacements:
MODEL_VERSION: The Imagen model version
to use. For more information about available models, see
Imagen
models.
Additional optional parameters Use the following optional variables depending on your use
case. Add some or all of the following parameters in the
HTTP method and URL:
Request JSON body:
To send your request, choose one of these options:
Save the request body in a file named
Save the request body in a file named
If you use a model that supports prompt enhancement, the response includes an
additional Replace the following:
imagen-3.0-capability-001
imagen-3.0-fast-generate-001
imagen-3.0-generate-001
Use a negative prompt
Console
REST
parameters
object of a JSON
request body.
us-central1
, europe-west2
, or asia-northeast3
. For a list
of available regions, see
Generative AI on Vertex AI locations.
imagegeneration@002
), 1-4 (all other model versions).
Default value: 4."parameters": {}
object.
This list shows common optional parameters and isn't meant to be exhaustive. For more
information about optional parameters,
see Imagen API reference: Generate images.
"parameters": {
"sampleCount": IMAGE_COUNT,
"addWatermark": ADD_WATERMARK,
"aspectRatio": "ASPECT_RATIO",
"enhancePrompt": ENABLE_PROMPT_REWRITING,
"includeRaiReason": INCLUDE_RAI_REASON,
"includeSafetyAttributes": INCLUDE_SAFETY_ATTRIBUTES,
"outputOptions": {
"mimeType": "MIME_TYPE",
"compressionQuality": COMPRESSION_QUALITY
},
"personGeneration": "PERSON_SETTING",
"safetySetting": "SAFETY_SETTING",
"seed": SEED_NUMBER,
"storageUri": "OUTPUT_STORAGE_URI"
}
true
contains a digital
SynthID that you can use to verify
a watermarked image.
If you omit this field, the default value of true
is used; you must set the value
to false
to disable this feature. You can use the seed
field to get
deterministic output only when this field is set to false
.
1:1
(default, square)3:4
(Ads, social media)4:3
(TV, photography)16:9
(landscape)9:16
(portrait)true
.
true
.
"Death, Harm & Tragedy"
,
"Firearms & Weapons"
, "Hate"
, "Health"
,
"Illicit Drugs"
, "Politics"
, "Porn"
,
"Religion & Belief"
, "Toxic"
, "Violence"
,
"Vulgarity"
, "War & Conflict"
. Default value: false
.
image/jpeg
image/gif
image/png
image/webp
image/bmp
image/tiff
image/vnd.microsoft.icon
0
to 100
, where a higher number means more compression. Default:
75
.
allow_adult
(default): Allow generation of adults only, except for celebrity
generation. Celebrity generation is not allowed for any setting.
dont_allow
: Disable the inclusion of people or faces in generated images.
block_low_and_above
: The highest safety threshold, resulting in the largest
amount of
generated images that are filtered. Previous value: block_most
.
block_medium_and_above
(default): A medium safety threshold that balances
filtering for
potentially harmful and safe content. Previous value: block_some
.
block_only_high
: A safety threshold that reduces the number of
requests blocked
due to safety filters. This setting might increase objectionable content generated by
Imagen. Previous value: block_few
.
"addWatermark": false
to use this field.
Accepted integer values: 1
- 2147483647
.
gs://image-bucket/output/
.
POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_VERSION:predict
{
"instances": [
{
"prompt": "TEXT_PROMPT"
}
],
"parameters": {
"sampleCount": IMAGE_COUNT
}
}
curl
request.json
,
and execute the following command:
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/MODEL_VERSION:predict"PowerShell
request.json
,
and execute the following command:
$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/MODEL_VERSION:predict" | Select-Object -Expand Content"sampleCount":
2
. The response returns two prediction objects, with the generated
image bytes base64-encoded.
{
"predictions": [
{
"bytesBase64Encoded": "BASE64_IMG_BYTES",
"mimeType": "image/png"
},
{
"mimeType": "image/png",
"bytesBase64Encoded": "BASE64_IMG_BYTES"
}
]
}
prompt
field with the enhanced prompt used for
generation:
{
"predictions": [
{
"mimeType": "MIME_TYPE",
"prompt": "ENHANCED_PROMPT_1",
"bytesBase64Encoded": "BASE64_IMG_BYTES_1"
},
{
"mimeType": "MIME_TYPE",
"prompt": "ENHANCED_PROMPT_2",
"bytesBase64Encoded": "BASE64_IMG_BYTES_2"
}
]
}
{
"instances": [
...
],
"parameters": {
"sampleCount": IMAGE_COUNT,
"negativePrompt": "NEGATIVE_PROMPT"
}
}
What's next
Omit content using a negative prompt
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2025-08-27 UTC.