# Nano Banana (Edit) - Core.Today AI API

> Dedicated edit endpoint for Nano Banana, Google's Gemini 2.5 Flash-based image model. Pass input image URLs to perform conversational editing with character consistency and multi-image fusion.

- **Provider**: Google
- **Model ID**: fal-ai/nano-banana/edit
- **Category**: Image Generation
- **Credits**: 91 per image
- **Speed**: Fast
- **Quality**: High

## Features
- Edit-mode endpoint optimized for image inputs
- Multimodal editing with character consistency
- Multi-image fusion
- Conversational editing instructions
- Multiple aspect ratio support

## Use Cases
- Conversational photo retouching
- Brand-consistent character variations
- Multi-image scene composition
- Iterative editing workflows

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - How you want to edit the image
- **image_urls**: array - Input image URLs to edit (required for edit mode)

### Optional
- **num_images**: integer (default: 1) - Number of images to generate
- **seed**: integer - The seed for the random number generator.
- **aspect_ratio**: string (default: auto) - Output aspect ratio
  Options: auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
- **output_format**: string (default: png) - Output image format
  Options: jpeg, png, webp
- **safety_tolerance**: string (default: 4) - Safety tolerance level (1 strictest, 6 most permissive)
  Options: 1, 2, 3, 4, 5, 6
- **sync_mode**: boolean (default: false) - If `True`, the media will be returned as a data URI and the output data won't be available in the request history.
- **limit_generations**: boolean (default: true) - Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate.

## Examples

### Lighting Edit
Apply a sunset glow to an existing photo
```json
{
  "model": "fal-ai/nano-banana/edit",
  "input": {
    "prompt": "Make the colors more vibrant and add a sunset glow",
    "image_urls": [
      "https://example.com/input-image.jpg"
    ],
    "aspect_ratio": "match_input_image",
    "output_format": "png",
    "safety_tolerance": "2",
    "num_images": 1
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Use this endpoint when you have one or more input images to edit
- Pass multiple image_urls to fuse subjects from different photos
- match_input_image keeps the original aspect ratio
- For pure text-to-image generation, use the base google/nano-banana model instead