This document explains the Generate Image node, which creates custom images using DALL-E models based on text descriptions.

Node Inputs

Required Fields

  • Prompt: Detailed description of desired image

    Example: “A serene mountain lake at sunset with pine trees reflected in the water”

Optional Fields

  • Num Images: Number of variations to generate (1-10)
  • Image Size: Choose resolution:
    • 1024x1024 (default)
    • 512x512
    • 256x256

Node Output

  • Image URLs: List of links to generated images

Node Functionality

The Generate Image node:

  • Converts text to images using AI
  • Creates multiple variations
  • Supports different resolutions
  • Returns accessible URLs
  • Works in batch mode

Common Use Cases

  1. Marketing Content:
Prompt: "Product photo of a minimalist coffee mug on marble background"
Size: 1024x1024
Use: Social media, ads
  1. Design Concepts:
Prompt: "Modern living room with Scandinavian furniture and large windows"
Variations: 4
Use: Interior design mockups
  1. Educational Materials:
Prompt: "Cross-section diagram of a plant cell with labeled parts"
Size: 512x512
Use: Learning resources

Writing Effective Prompts

  1. Be Detailed:
Bad: "A house"
Good: "A modern beach house with floor-to-ceiling windows and wooden deck"
  1. Specify Style:
"Digital art style..."
"Photorealistic..."
"Watercolor painting..."
  1. Include Context:
"Close-up shot..."
"Aerial view..."
"From street level..."

In summary, the Generate Image node helps create custom visuals from text descriptions, perfect for content creation and design work.