VertexAIImageGenerator

Generate images using Google Vertex AI generative model.

Key Features

• Generates images from text prompts using Google Vertex AI
• Supports negative prompts to exclude unwanted elements from generated images
• Returns images as ByteStream objects
• Authenticates using Google Cloud Application Default Credentials (ADCs)

Configuration

1. Drag the VertexAIImageGenerator component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Enter your GCP project ID. Create a secret with the key GCP_PROJECT_ID. For detailed instructions, see Create Secrets.
   2. Optionally, enter the location. If not set, uses us-central1.
   3. The default model is imagegeneration.
4. Go to the Advanced tab to configure additional model keyword arguments.

Connections

VertexAIImageGenerator accepts a text prompt (str) and an optional negative_prompt (Optional[str]) as inputs. It outputs generated images as a list of ByteStream objects through its images output.

Connect PromptBuilder's prompt output to this component's prompt input.

Source Code

To check this component's source code, open image_generator.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  VertexAIImageGenerator:
    type: haystack_integrations.components.generators.google_vertex.image_generator.VertexAIImageGenerator
    init_parameters:
      model: imagegeneration

This pipeline uses VertexAIImageGenerator to generate images from text prompts:

# haystack-pipeline
components:
  VertexAIImageGenerator:
    type: haystack_integrations.components.generators.google_vertex.image_generator.VertexAIImageGenerator
    init_parameters:
      project_id:
      model: imagegeneration
      location:
  PromptBuilder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      template: "Generate an image described in the query.\n\nQuery: {{ query }}"
      required_variables: "\\n"
      variables:

max_runs_per_component: 100

metadata: {}

connections:
- sender: PromptBuilder.prompt
  receiver: VertexAIImageGenerator.prompt

inputs:
  query:
  - PromptBuilder.query

Parameters

Inputs

Parameter	Type	Default	Description
prompt	str		The prompt to generate images from.
negative_prompt	Optional[str]	None	A description of what you want to omit in the generated images.

Outputs

Parameter	Type	Description
images	List[ByteStream]	A list of ByteStream objects, each containing an image.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
project_id	Optional[str]	None	ID of the GCP project to use. By default, it is set during Google Cloud authentication.
model	str	imagegeneration	Name of the model to use.
location	Optional[str]	None	The default location to use when making API calls. If not set, uses us-central-1.
kwargs	Any		Additional keyword arguments to pass to the model. See the ImageGenerationModel.generate_images() documentation.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
prompt	str		The prompt to generate images from.
negative_prompt	Optional[str]	None	A description of what you want to omit in the generated images.

Related Information

• Create Secrets
• Google Cloud Application Default Credentials