Skip to main content

​
What can you do with it?

The /image-edit command enables image-to-image regeneration using the premium Nano Banana model. By providing an input image and text instructions, you can regenerate the image with modifications, transformations, style changes, and enhancements. This is a generative process that creates new images based on your input image and prompts, rather than traditional pixel-level editing.

​
How to use it?

​
Basic Command Structure

/image-edit [instruction]

​
Parameters

Required:
  • prompt - Text description of what you want to generate, or instruction on how to edit the given image
  • input_image - Image to edit (URL or uploaded file). Must be jpeg, png, gif, or webp
Optional:
  • aspect_ratio - Aspect ratio: “match_input_image”, “1:1”, “16:9”, “9:16”, “4:3”, “3:4”, “3:2”, “2:3”, “4:5”, “5:4”, “21:9”, “9:21”, “2:1”, “1:2” (defaults to “match_input_image”)
  • prompt_upsampling - Automatic prompt improvement (boolean, defaults to false)
  • seed - Random seed for reproducible generation (integer, optional)
  • output_format - Output format: “jpg”, “png” (defaults to “png”)
  • safety_tolerance - Safety tolerance: 0-6 (defaults to 2). 0 is most strict, 6 is most permissive. Max 2 when input images are used
  • fileLinksExpireInDays - How long generated files remain accessible: 1-7 days (defaults to 7)
  • fileLinksExpireInMinutes - How long generated files remain accessible in minutes (takes precedence over days)

​
Response Format

The command returns: 
{
  "output": [
    {
      "url": "https://generated-file-url",
      "mimeType": "image/png"
    }
  ]
}
Note: All edited images are automatically saved to your “Multimedia Artifact” file store and will be accessible for the duration specified by the fileLinksExpireInDays parameter.

​
Examples

​
Basic Image-to-Image Regeneration

/image-edit
prompt: Add a sunset sky background to this portrait
input_image: portrait-photo.jpg
Regenerates the portrait with a beautiful sunset sky background.

​
Product Enhancement

/image-edit
prompt: Remove the scratches and improve the lighting on this product photo
input_image: product-watch.jpg
output_format: png
safety_tolerance: 1
Enhances product photos by removing imperfections and improving lighting quality.

​
Style Transfer

/image-edit
prompt: Transform this photo into a watercolor painting style while keeping the subject recognizable
input_image: landscape-photo.jpg
aspect_ratio: match_input_image
output_format: png
Converts a photograph into an artistic watercolor painting style.

​
Typography and Text Addition

/image-edit
prompt: Add elegant serif typography saying "Grand Opening" at the top of this restaurant interior image
input_image: restaurant-interior.jpg
aspect_ratio: 16:9
output_format: png
prompt_upsampling: true
Adds professional typography to marketing images with improved text generation.

​
Object Removal

/image-edit
prompt: Remove the power lines from this landscape photo and make the sky look more natural
input_image: mountain-landscape.jpg
aspect_ratio: match_input_image
seed: 42
Removes unwanted objects from photos while maintaining natural appearance.

​
Fashion and Apparel Editing

/image-edit
prompt: Change the color of the dress from red to navy blue while maintaining the fabric texture
input_image: model-dress.jpg
aspect_ratio: 3:4
output_format: jpg
safety_tolerance: 2
Modifies clothing colors and styles in fashion photography.

​
Interior Design Visualization

/image-edit
prompt: Replace the furniture in this living room with modern minimalist pieces in white and black
input_image: living-room.jpg
aspect_ratio: 4:3
output_format: png
prompt_upsampling: true
Visualizes interior design changes for real estate or design presentations.

​
Logo and Branding Integration

/image-edit
prompt: Add the company logo in the bottom right corner and make it blend naturally with the image
input_image: corporate-event.jpg
aspect_ratio: match_input_image
output_format: png
fileLinksExpireInDays: 7
Integrates branding elements seamlessly into marketing photographs.

​
Creative Compositing

/image-edit
prompt: Transform this daytime cityscape into a futuristic cyberpunk scene with neon lights and flying cars
input_image: city-skyline.jpg
aspect_ratio: 21:9
output_format: png
seed: 123
Creates dramatic scene transformations for creative projects.

​
Professional Retouching

/image-edit
prompt: Professional headshot retouching: smooth skin, brighten eyes, improve lighting, maintain natural look
input_image: headshot-raw.jpg
aspect_ratio: 1:1
output_format: jpg
safety_tolerance: 1
Provides professional photo retouching while maintaining authenticity.

​
Notes

Model Capabilities (Nano Banana):
  • Premium image-to-image regeneration with maximum performance
  • Excellent typography generation and text integration
  • Advanced object manipulation and removal through regeneration
  • Professional-grade style transfers
  • Precise color and lighting adjustments
  • Complex scene transformations
Key Features:
  • Generative image-to-image process (not pixel-level editing)
  • Maintains aspect ratio of input images by default
  • Advanced prompt upsampling for better results
  • Reproducible results with seed control
  • Professional safety filtering
Best Practices:
  • Use specific, descriptive prompts for better results
  • Enable prompt_upsampling for complex transformations
  • Use PNG format for images requiring transparency
  • Use JPG format for final output to reduce file size
  • Lower safety_tolerance for more creative freedom (max 2 with input images)
  • Understand this is regeneration, not traditional editing - results may vary
Limitations:
  • Requires input image for all regeneration tasks
  • This is a generative process, not precise pixel editing
  • Safety tolerance is limited when using input images (max 2)
  • Processing time varies based on regeneration complexity
  • Results depend on input image quality and prompt clarity

​
Model Parameters (google/nano-banana)

​
Image-to-Image Regeneration Parameters

  • prompt (required): Text description of how you want to regenerate the image
  • input_image (required): Source image for regeneration. Must be jpeg, png, gif, or webp (URI format)
  • aspect_ratio: Aspect ratio (“match_input_image”, “1:1”, “16:9”, “9:16”, “4:3”, “3:4”, “3:2”, “2:3”, “4:5”, “5:4”, “21:9”, “9:21”, “2:1”, “1:2”, default: “match_input_image”)
  • prompt_upsampling: Automatic prompt improvement (boolean, default: false)
  • seed: Random seed for reproducible generation (integer, nullable, optional)
  • output_format: Output format (“jpg”, “png”, default: “png”)
  • safety_tolerance: Safety tolerance (0-6, default: 2). 0 is most strict, 6 is most permissive. Max 2 when input images are used
⌘I