Generate Image
The Generate Image node allows you to create AI-generated images based on text descriptions. Powered by OpenAI’s latest 4o image generation model.
Node Inputs
Required Fields
-
Prompt: A detailed description of the image you want to create
Example: “A professional product photo of a sleek smartphone on a marble desk with soft lighting and minimal shadows”
Optional Fields
- Number of Images: How many image variations to generate (1-10)
- Default: 1
- Note: Each additional image costs 30 credits
Configuration Options
-
Quality: Controls the detail and resolution of generated images
- Auto: System determines optimal quality (default)
- High: Maximum detail and clarity
- Medium: Balanced quality and time to generate
- Low: More efficient option for drafts or less critical uses
-
Size: Dimensions of the generated image
- Auto: System determines optimal size (default)
- 1024x1024: Standard square format
- 1536x1024: Landscape orientation
- 1024x1536: Portrait orientation
-
Background: Controls the background type
- Auto: System determines appropriate background (default)
- Transparent: Creates image with transparent background (works with PNG format)
- Opaque: Ensures solid background
-
Output Format: Image file format
- PNG: Supports transparency, best for graphics
- JPEG: More compressed, suitable for photographs
- WebP: Modern format with good compression and quality
Node Output
- Image URLs: List of URLs pointing to the generated images
- Format: A list of text strings, each containing a full URL
- Note: These URLs can be used directly with other nodes like Slack Message Sender, Google Drive File Writer, etc.
Credit Cost
- 30 credits per image generated
- This cost is fixed regardless of quality settings, size, or format
Common Use Cases
Marketing and Advertising
Product Visualization
Content Creation
UI/UX Mockups
Effective Prompt Strategies
Structure
For best results, include these elements in your prompts:
- Subject: What is the main focus?
- Style: Photo, illustration, 3D render, etc.
- Setting: Where is the subject located?
- Lighting: How is the scene lit?
- Perspective: What angle is the subject viewed from?
- Colors: What is the color scheme?
Examples of Strong Prompts
Basic prompt: “A coffee cup on a table”
Improved prompt: “A ceramic coffee cup with steam rising, placed on a rustic wooden table by a window with morning sunlight streaming in, photographed with shallow depth of field, warm color tones”
Integration with Other Nodes
The Generate Image node pairs effectively with:
- Slack Message Sender: Share generated images directly in channels or DMs
- Google Drive File Writer: Save images to your Drive for storage or sharing
- Gmail Sender: Include generated images as email attachments
- Content Management Nodes: Incorporate images into CMS posts via API
Important Considerations
- Restricted Content: The model won’t generate inappropriate or harmful imagery. Refer to OpenAI’s docs for content guidelines.
Troubleshooting
If your images aren’t generating as expected:
- Prompt Clarity: Be more specific about what you want to see
- Style Guidance: Explicitly mention the artistic style or medium
- Composition Details: Specify camera angle, lighting, and scene details
- Technical Terms: Use photography or design terminology for more precise control
- Iteration: Try variations of your prompt to find what works best using
Loop Mode