Contact Us 1-800-596-4880

Configuring Image Generation Operations

Configure the IMAGE Generate operation.

Configure the IMAGE Generate Operation

The IMAGE Generate operation generates an image based on a prompt sent to Amazon Bedrock.

To configure the IMAGE Generate operation:

  1. Select the operation on the Anypoint Code Builder or Studio canvas.

  2. In the General properties tab for the operation, enter these values:

    • Text to image

      Instructions for the image generation. Provide a text description of the image you want to generate.

    • Avoid in image

      Instructions specifying what should be avoided in the generated image.

    • Full path output

      The complete file path where the generated image should be saved. For example: mule.home "/apps/" app.name ++ "/Image.png".

    • Model name

      The name of the model to be used for image generation. Select any model from the supported LLM Providers.

    • Region

      The AWS region to be used for the request.

    • Num of images

      The number of images to generate (default: 1).

    • Height

      Height of the generated image in pixels (default: 512).

    • Width

      Width of the generated image in pixels (default: 512).

    • Cfg scale

      CFG scale value for image generation (default: 8.0).

    • Seed

      Seed for randomizing image generation (default: 0).

This is the XML for this operation:

<ms-bedrock:
  image-generate
  doc:name="Image generate"
  doc:id="8304d49f-5e96-4514-ac4c-7abf48fcd8f3"
  config-ref="AWS"
  TextToImage="#[payload.prompt]"
  fullPathOutput='#[mule.home ++ "/apps/" ++ app.name ++ "/Image.png"]'
  AvoidInImage="#[payload.avoid]"
  modelName="amazon.titan-image-generator-v1"
/>

Output Configuration

This operation responds with a JSON payload with the path of the generated image.

View on GitHub