Skip to main content

Edit Image

Edits images using Google's Gemini API based on a text prompt and mask image.

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.
  • Edit Prompt - Describe what changes you want to make to the image.
  • Base Image Path - Path to the image you want to edit.
  • Mask Image Path - Path to mask image (white areas will be edited).

Options​

  • Model - The model to use for image editing. Options include:
    • Imagen 3.0 Edit
    • Custom Model
  • Custom Model - Custom model name when "Custom Model" is selected for Model.
  • Number of Images - Number of variations to generate (1-4). Default is 1.
  • Negative Prompt - Describe what you don't want in the edited areas.
  • Output Format - Format for the output images. Options are:
    • PNG
    • JPEG
    • WebP
  • Output Quality - JPEG quality (1-100, only for JPEG format).
  • Timeout (seconds) - Request timeout in seconds (default: 120).

Output​

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

How It Works​

The Edit Image node modifies images using Google's Gemini API based on a text prompt and mask. When executed, the node:

  1. Validates the provided connection ID, edit prompt, and image file paths
  2. Ensures the base and mask image files exist
  3. Configures the image editing parameters including model, number of images, and output format
  4. Reads the base and mask images from the file system
  5. Sends an image editing request to the Gemini API
  6. Saves the edited images to a temporary directory
  7. Returns structured information about the edited images including file paths and metadata

Requirements​

  • A valid Google Gemini API key
  • Connection ID from a successful Connect node execution
  • Valid base image file path
  • Valid mask image file path
  • Edit prompt describing the desired changes

Error Handling​

The node will return specific errors in the following cases:

  • Empty or invalid Connection ID
  • Empty or invalid Edit Prompt
  • Empty or invalid Base Image Path
  • Empty or invalid Mask Image Path
  • Base image file not found
  • Mask image file not found
  • Edit prompt too long (maximum 1000 characters)
  • Negative 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
  • API errors from Google's Gemini service

Usage Notes​

  • The edit prompt should clearly describe the changes you want to make
  • The mask image should have white areas where you want edits to occur
  • Edited images are saved to a temporary directory with unique names
  • The maximum length for edit prompts and negative prompts is 1000 characters
  • For JPEG output, quality can be adjusted between 1-100
  • The default timeout is 120 seconds, which can be adjusted for complex edits
  • The node returns file paths to the edited images, which can be used by other nodes