Skip to main content

Generate Image

Generates images from text descriptions using OpenAI's DALL-E and GPT-Image 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 - Connection identifier from Connect node. Optional if providing API Key directly.
  • API Key - OpenAI API key credential. Optional if using Connection Id.
  • Prompt - Detailed description of the image you want to generate. Be specific for best results.
  • Use Robomotion AI Credits - Use Robomotion credits instead of your own API key.

Options​

Model Selection​

  • Model - Image generation model to use:
    • GPT-Image-1 - Latest high-quality image generation (default)
    • DALL-E 3 - Advanced model with superior understanding
    • DALL-E 2 - Fast and cost-effective

Generation Settings​

  • Number of Images - Number of images to generate (1-4). Note: DALL-E 3 only supports 1 image.
  • Size - Output image dimensions:
    • Auto - Model chooses optimal size (recommended for GPT-Image-1)
    • 1024x1024 - Square format
    • 1536x1024 - Landscape format
    • 1024x1536 - Portrait format
    • 1792x1024 - Wide landscape (DALL-E 3)
    • 1024x1792 - Tall portrait (DALL-E 3)
    • 512x512 - Small square (DALL-E 2)
    • 256x256 - Tiny square (DALL-E 2)
  • Quality - Image quality level:
    • Auto - Model determines quality
    • High/Medium/Low - For GPT-Image-1
    • HD - Highest quality for DALL-E 3
    • Standard - Standard quality for DALL-E 3
  • Style - Visual style (DALL-E 3 only):
    • Vivid - Dramatic, artistic images (default)
    • Natural - More realistic, natural images

GPT-Image-1 Specific Options​

  • Background - Background handling:
    • Auto - Model decides
    • Transparent - Generate with transparency
    • Opaque - Solid background
  • Output Format - File format:
    • PNG - Best quality, larger files (default)
    • JPEG - Smaller files
    • WebP - Modern format, good compression

Advanced​

  • User - Unique identifier for your end-user.
  • Timeout (seconds) - Request timeout. Default: 120.
  • Include Raw Response - Include the full API response. Default: false.

Outputs​

  • Image - File path to the generated image. Returns a string if Number of Images is 1, or an array of strings if more than 1.
  • Raw Response - Complete API response object (only set when "Include Raw Response" is enabled).

How It Works​

The Generate Image node creates images based on text descriptions. When executed:

  1. Validates the connection or API key
  2. Processes your text prompt
  3. Configures size, quality, and style parameters
  4. Sends the request to the selected image model
  5. Downloads and saves the generated image(s) to temporary storage
  6. Returns the file path(s) to the generated image(s)

Usage Examples​

Example 1: Generate a Simple Image​

Input:
- Prompt: "A serene mountain landscape at sunset with a lake"
- Model: gpt-image-1
- Size: auto

Output:
- Image: "/tmp/robomotion/images/image_0.png"

Example 2: Generate Logo with Transparency​

Input:
- Prompt: "Modern minimalist logo for a tech company, blue and white"
- Model: gpt-image-1
- Background: transparent
- Output Format: png

Output:
- Image: "/tmp/robomotion/images/image_0.png" (with transparency)

Example 3: Generate Multiple Variations​

Input:
- Prompt: "Abstract geometric pattern"
- Model: dall-e-2
- Number of Images: 4
- Size: 1024x1024

Output:
- Image: ["/tmp/image_0.png", "/tmp/image_1.png", "/tmp/image_2.png", "/tmp/image_3.png"]

Example 4: High-Quality Portrait​

Input:
- Prompt: "Professional headshot of a business executive, natural lighting"
- Model: dall-e-3
- Size: 1024x1536
- Quality: hd
- Style: natural

Output:
- Image: "/tmp/robomotion/images/image_0.png"

Example 5: Product Image for E-commerce​

Input:
- Prompt: "Elegant wristwatch on white background, product photography style"
- Model: gpt-image-1
- Background: opaque
- Quality: high
- Size: 1024x1024

Output:
- Image: "/tmp/robomotion/images/image_0.png"

Requirements​

  • Either a Connection Id from Connect node OR an API Key credential
  • Non-empty prompt describing the desired image
  • Sufficient API credits or balance
  • Write access to temporary file storage

Error Handling​

The node will return errors in these cases:

  • ErrInvalidArg: Prompt is empty or invalid
  • ErrAPICall: OpenAI API errors (rate limits, content policy violations, insufficient credits)
  • File errors: Unable to save generated image to disk
  • Timeout errors: Request exceeded timeout duration

Tips for RPA Developers​

  • Prompt Engineering: Be specific and descriptive. Include details about style, lighting, composition, and mood.
  • Model Selection:
    • Use GPT-Image-1 for latest quality with transparency support
    • Use DALL-E 3 for superior prompt understanding and quality
    • Use DALL-E 2 for faster, more affordable generation
  • Size Selection: Use "auto" for GPT-Image-1. Choose specific sizes for DALL-E models based on your use case.
  • Quality vs Cost: Higher quality/HD increases cost. Use standard quality for drafts.
  • Batch Generation: Generate multiple images at once (DALL-E 2 only) to compare variations.
  • Content Policy: OpenAI filters inappropriate prompts. Keep requests appropriate and within policy.
  • File Management: Generated images are saved to temp storage. Copy them to permanent storage if needed.
  • Transparency: Only GPT-Image-1 supports transparent backgrounds.
  • Format Choice: Use PNG for quality, JPEG for smaller files, WebP for modern apps.

Common Errors and Solutions​

Error: "Prompt cannot be empty"

  • Solution: Provide a descriptive text prompt for the image you want to generate.

Error: "OpenAI API error: content policy violation"

  • Solution: Your prompt was flagged as inappropriate. Revise it to comply with OpenAI's usage policies.

Error: "OpenAI API error: rate limit exceeded"

  • Solution: You've exceeded your API rate limit. Wait and retry, or upgrade your plan.

Error: "Failed to save image"

  • Solution: Check disk space and write permissions to the temporary directory.

Image quality is poor

  • Solution: Try GPT-Image-1 or DALL-E 3, use larger sizes, enable HD quality, and make your prompt more specific.

DALL-E 3 ignoring Number of Images > 1

  • Solution: DALL-E 3 only generates 1 image at a time. Use DALL-E 2 for batch generation.