Skip to main content

Image Generation

The Image Generation component allows you to create images using various AI models. Each model has its own specific capabilities and configuration options, but they all share the common functionality of generating images based on text prompts.

Credit Cost​

Varies by model. Each model has its own credit cost per generation. You can see the cost when selecting a model.

Usage​

The Image Generation component has a single input handle that accepts multiple text variables, which can be combined in the prompt to guide the image generation. The component outputs the generated image through a single output handle.

Common use cases include:

  • Product visualization
  • Marketing material creation
  • Concept art development
  • Content illustration

Variable Handling​

Variables must be explicitly referenced in the prompt to be used. Simply connecting a variable to the input handle is not enough - you must use the {{variable}} syntax in the prompt to include its value. Any connected variable that is not referenced in the prompt will be ignored.

If a referenced variable contains empty data, that variable will be replaced with an empty string in the prompt.

Properties​

Model​

  • Type: model selector
  • Description: Choose which AI model to use for image generation. Each model has its own set of properties and capabilities.
  • Available Models:
    • Flux 1.1 Pro Ultra
    • Recraft v3 SVG
    • Ideogram v2
    • Each with specific:
      • Resolution options
      • Style capabilities
      • Generation parameters

Model-Specific Properties​

Each model has its own set of configurable properties, but they all include:

Prompt​

  • Type: text
  • Description: Instructions for the AI model describing what image to generate. Use {{variable}} syntax to include dynamic content.
  • Best Practices:
    • Be specific and detailed
    • Describe visual elements clearly
    • Specify style and mood
    • Include composition details

Additional model-specific properties are available and vary by model. Hover over each property's info icon to see detailed descriptions and options.

Important Notes​

  1. Different models excel at different types of images
  2. Prompt engineering significantly impacts results
  3. Model-specific features can greatly enhance output quality
  4. Some models may have content restrictions
  5. Best practices for prompts:
    • Start with a clear subject
    • Specify important details
    • Include style references
    • Mention technical aspects (lighting, angle, etc.)
    • Use descriptive adjectives
  6. Refer to each model's specific documentation for model-optimized prompting techniques and best practices