Vertex AI Advanced icon

Vertex AI Advanced

Interact with Google Vertex AI models — multimodal text, image, audio, and video

Actions9

Image → Generate an Image

AI-generated

Summary

Generate one or more images from a specified text prompt using a chosen Google Vertex AI image generation model within a given GCP project.

Inputs

  • Project ID (required) — The Google Cloud Platform project ID to use for the generation request.
  • Model (required) — The ID of the image generation model to use, selectable from a searchable list or by direct ID entry.
  • Prompt (required) — A text description serving as the basis for generating the image(s).
  • Options — Additional optional parameters including the number of images to generate (supported by Imagen models) and the binary output field name for storing the generated image(s).

Output shape

a list of output items each containing a binary file with the generated image data in the specified output field.

If using a Gemini model (identified by model ID substring), the operation returns images embedded in the response candidates, each as a separate binary file in the specified field. If using an Imagen model, multiple images can be generated at once if sampleCount is set, returned as separate items with binary image data. An error is thrown if an unsupported model is used.

Links

Discussion