Gemini Image Generator

This node allows you to generate or edit images using Gemini or Imagen models. Gemini supports image editing, while Imagen models do not.

To generate an image, provide a descriptive prompt. The more detailed your prompt, the better the resulting image will be.

To edit images (Gemini only), connect a table containing image columns to the optional input port. You can select which image columns to use for editing and provide instructions on how to modify or combine the images.

Note: Image generation may be significantly more expensive than text generation. Please refer to Gemini Docs for more details on how the costs are calculated.

Options

Model Type

The type of model to use for image generation.

Available options:

  • Gemini: Multimodal model that supports both text-to-image generation and image editing.
  • Imagen: Specialized text-to-image generation model that offers faster generation but no image editing.
Model

Select the specific Gemini model to use.

Model

Select the specific Imagen model to use.

Prompt

The prompt describing the image you want to generate or how to edit the input images.

For text-to-image generation, describe the image you want to create in detail. For image editing, describe how you want to modify, combine, or enhance the input images.

The token limit depends on the selected model: - Gemini models: 32,768 tokens - Imagen models: 480 tokens

Images to edit

Select the image columns to use for editing. When multiple columns are selected, the model will use all the images to generate a new image based on your prompt.

For example, you could have one column with objects and another with backgrounds, then instruct the model to combine them.

Note: This feature is only available for Gemini models.

Imagen Settings

Aspect Ratio

Changes the aspect ratio of the generated image.

Available options:

  • Square: Square format
  • Portrait 3:4: Portrait format
  • Landscape 4:3: Landscape format
  • Vertical 9:16: Vertical mobile format
  • Horizontal 16:9: Horizontal widescreen format
Person Generation

Allow the model to generate images of people.

  • "Block People": Block generation of images of people.
  • "Adults Only": Generate images of adults, but not children (default).

Available options:

  • Block People: Block generation of images containing people.
  • Adults Only: Generate images of adults only, but not children (default).

Input Ports

Icon

Validated authentication for Google AI Studio.

Icon…

Table containing the images to edit.

Output Ports

Icon

The image generated by the model.

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found

Views

View
View of the generated image.

Workflows

  • No workflows found

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.

Installation

To use this node in KNIME, install the extension KNIME Python Extension Development (Labs) from the below update site following our NodePit Product and Node Installation Guide:

v5.7

A zipped version of the software site can be downloaded here.

Plugin provider: KNIME AG, Zurich, Switzerland
Plugin version: 5.7.0.v202508221720
On NodePit since: 2025-08-31
Last update: 2025-09-02

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!