Skip to main content

Generate Images

Generates images from text prompts using Google's Imagen models.

Common Properties​

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. The default value is false.
info

If the ContinueOnError property is true, no error is caught when the project is executed, even if a Catch node is used.

Inputs​

  • Connection Id - The connection ID obtained from the Connect node.
  • Prompt - The text prompt describing the image to generate.

Options​

  • Model - The Imagen model to use for image generation. Options include:
    • Imagen 3.0 Generate (Latest)
    • Imagen 3.0 Generate v1
    • Imagen 3.0 Fast Generate
    • Custom Model
  • Custom Model - Custom model name when "Custom Model" is selected.
  • Number of Images - Number of images to generate (1-4). Default is 1.
  • Aspect Ratio - Image aspect ratio. Options are:
    • 1:1
    • 3:4
    • 4:3
    • 9:16
    • 16:9
  • Negative Prompt - Describe what you don't want in the image.
  • Person Generation - Control generation of adult content. Options are:
    • Allow Adult
    • Don't Allow
  • Output Format - Format for the output images. Options are:
    • PNG
    • JPEG
    • GIF
    • WebP
    • BMP
    • TIFF
    • ICO
  • Output Quality - JPEG quality (1-100, only for JPEG format).

Output​

  • Images - The generated images with file paths and metadata.

How It Works​

The Generate Images node creates images from text prompts using Google's Imagen models. When executed, the node:

  1. Validates the provided connection ID and prompt
  2. Configures the selected model with all specified parameters
  3. Sets up generation parameters including number of images, aspect ratio, and safety settings
  4. Sends an image generation request to the Imagen API
  5. Saves the generated images to a temporary directory
  6. Returns structured information about the generated images including file paths and metadata

Requirements​

  • A valid Google Gemini API key
  • Connection ID from a successful Connect node execution
  • Valid text prompt describing the desired image

Error Handling​

The node will return specific errors in the following cases:

  • Empty or invalid Connection ID
  • Empty Prompt
  • Prompt too long (maximum 1000 characters)
  • Invalid number of images value
  • Invalid output quality value (must be between 1 and 100 for JPEG)
  • Invalid custom model name
  • Negative prompt too long (maximum 1000 characters)
  • API errors from Google's Imagen service

Usage Notes​

  • The maximum length for prompts and negative prompts is 1000 characters
  • Images are saved to a temporary directory with unique names
  • For JPEG output, quality can be adjusted between 1-100
  • The default aspect ratio is 1:1
  • Person generation settings control adult content filtering
  • The node returns file paths to the generated images, which can be used by other nodes
  • Different models offer different capabilities and performance characteristics
  • The default model is "imagen-3.0-generate-002" (latest version)