Turn the prompt rewriter off

Veo offers an LLM-based prompt enhancement tool, also known as a prompt rewriter. The prompt rewriter offers the option to rewrite your prompts to add video description, camera motions, transcription, and sound effects to your prompt. More detailed prompts result in higher quality videos.

If you disable prompt enhancement, the quality of the videos and how well the output resembles the prompt that you supplied may be impacted. This feature is enabled by default for veo-2.0-generate-001.

A rewritten prompt is delivered by API response only if the original prompt is fewer than 30 words long.

For more information about writing effective text prompts for video generation, see the Veo prompt guide.

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. Enable the Vertex AI API.

    Enable the API

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

    Go to project selector

  5. Enable the Vertex AI API.

    Enable the API

    6.

  6. 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.

    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.

      Install the Google Cloud CLI. After installation, initialize the Google Cloud CLI 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.

Turn off prompt rewriter

To turn prompt enhancement off, do the following:

Console

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

    Go to Media Studio

  2. Click Veo.

  3. In Settings, click the Enable prompt enhancement toggle.

  4. In the Write your prompt box, enter your prompt and then click Generate.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# 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=global
export GOOGLE_GENAI_USE_VERTEXAI=True
 

import time
from google import genai
from google.genai.types import GenerateVideosConfig

client = genai.Client()

# TODO(developer): Update and un-comment below line
# output_gcs_uri = "gs://your-bucket/your-prefix"

operation = client.models.generate_videos(
    model="veo-2.0-generate-001",
    prompt="a cat reading a book",
    config=GenerateVideosConfig(
        aspect_ratio="16:9",
        output_gcs_uri=output_gcs_uri,
        number_of_videos=1,
        duration_seconds=5,
        person_generation="dont_allow",
        enhance_prompt=False,
    ),
)

while not operation.done:
    time.sleep(15)
    operation = client.operations.get(operation)
    print(operation)

if operation.response:
    print(operation.result.generated_videos[0].video.uri)

# Example response:
# gs://your-bucket/your-prefix

REST

After you set up your environment, you can use REST to test a text prompt. The following sample sends a request to the publisher model endpoint.

For more information about the Veo API, see the Veo on Vertex AI API.

  1. Use the following command to send a video generation request. This request begins a long-running operation and stores output to a Cloud Storage bucket you specify.

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

  • PROJECT_ID: Your Google Cloud project ID.
  • MODEL_ID: The model ID to use. Available values:
    • veo-2.0-generate-001
  • TEXT_PROMPT: The text prompt used to guide video generation.
  • OUTPUT_STORAGE_URI: Optional: The Cloud Storage bucket to store the output videos. If not provided, video bytes are returned in the response. For example: gs://video-bucket/output/.
  • RESPONSE_COUNT: The number of video files you want to generate. Accepted integer values: 1-4.
  • DURATION: The length of video files that you want to generate. Accepted integer values are 5-8.
  • ENHANCED_PROMPT: Whether to use enhanced prompts or not. You can use one of the following:
    • True: (default) use Gemini to enhance your prompts.
    • False: don't use Gemini to enhance your prompts.

  • Additional optional parameters

    Use the following optional variables depending on your use case. Add some or all of the following parameters in the "parameters": {} object. 

    "parameters": {
  "aspectRatio": "ASPECT_RATIO",
  "negativePrompt": "NEGATIVE_PROMPT",
  "personGeneration": "PERSON_SAFETY_SETTING",
  // "resolution": RESOLUTION, // Veo 3 models only
  "sampleCount": RESPONSE_COUNT,
  "seed": SEED_NUMBER
}
    • ASPECT_RATIO: string. Optional. Defines the aspect ratio of the generated videos. Values: 16:9 (default, landscape) or 9:16 (portrait).
    • NEGATIVE_PROMPT: string. Optional. A text string that describes what you want to discourage the model from generating.
    • PERSON_SAFETY_SETTING: string. Optional. The safety setting that controls whether people or face generation is allowed. Values:
      • allow_adult (default value): Allow generation of adults only.
      • disallow: Disallows inclusion of people or faces in images.
    • RESOLUTION: string. Optional. Veo 3 models only. The resolution of the generated video. Values: 720p (default) or 1080p.
    • RESPONSE_COUNT: int. Optional. The number of output images requested. Values: 1-4.
    • SEED_NUMBER: uint32. Optional. A number to make generated videos deterministic. Specifying a seed number with your request without changing other parameters guides the model to produce the same videos. Values: 0 - 4294967295.

HTTP method and URL: 

POST https://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:predictLongRunning

Request JSON body: 

{
  "instances": [
    {
      "prompt": "TEXT_PROMPT"
    }
  ],
  "parameters": {
    "storageUri": "OUTPUT_STORAGE_URI",
    "sampleCount": "RESPONSE_COUNT",
    "durationSeconds": "DURATION",
    "enhancePrompt": ENHANCED_PROMPT
  }
}

To send your request, choose one of these options:

curl

Save the request body in a file named 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://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:predictLongRunning"

PowerShell

Save the request body in a file named 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://us-central1-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID:predictLongRunning" | Select-Object -Expand Content
This request returns a full operation name with a unique operation ID. Use this full operation name to poll that status of the video generation request. 
{
  "name": "projects/PROJECT_ID/locations/us-central1/publishers/google/models/MODEL_ID/operations/a1b07c8e-7b5a-4aba-bb34-3e1ccb8afcc8"
}

What's next