# Nano Banana 2 Lite - Core.Today AI API

> Google's lightweight Nano Banana 2 variant built on Gemini 3.1 Flash Image, tuned for faster and cheaper generation. Retains conversational editing, multi-image fusion, and character consistency from the full Nano Banana 2.

- **Provider**: Google
- **Model ID**: google/nano-banana-2-lite
- **Category**: Image Generation
- **Credits**: 80 per image (fixed price)
- **Speed**: Fast
- **Quality**: Standard

## Features
- Faster, lower-cost variant of the full Nano Banana 2 model
- Built on Gemini 3.1 Flash Image
- Conversational, instruction-based editing
- Multi-image fusion from up to 14 reference images
- Character consistency preserved across generations
- Wide range of aspect ratio presets including auto-match to input image

## Use Cases
- Fast iterative editing where speed matters most
- Multi-image fusion, combining several photos into one scene
- Maintaining consistent characters/subjects across a series of images
- Quick concept exploration before committing to a higher-cost generation
- Conversational detail edits like "change the sky to sunset colors"

## 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 - A text description of the image you want to generate

### Optional
- **image_input**: array (default: []) - Input images to transform or use as reference (supports up to 14 images)
- **aspect_ratio**: string (default: match_input_image) - Aspect ratio of the generated image
  Options: match_input_image, 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9
- **output_format**: string (default: jpg) - Format of the output image
  Options: jpg, png

## Examples

### Fast Iterative Edit
Quick conversational edit on an existing product photo
```json
{
  "model": "google/nano-banana-2-lite",
  "input": {
    "prompt": "Change the background to a warm sunset gradient and add soft rim lighting on the product",
    "image_input": [
      "https://example.com/product-photo.jpg"
    ],
    "aspect_ratio": "1:1"
  }
}
```

### Multi-Image Fusion
Fuse two reference photos into a single composed scene
```json
{
  "model": "google/nano-banana-2-lite",
  "input": {
    "prompt": "Place the person from the first photo into the café scene from the second photo, matching the lighting and perspective",
    "image_input": [
      "https://example.com/person.jpg",
      "https://example.com/cafe.jpg"
    ],
    "aspect_ratio": "3:4",
    "output_format": "png"
  }
}
```

## 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 lite tier for fast draft iterations, then switch to the full Nano Banana 2 for final high-fidelity output
- Combine up to 14 images in image_input for multi-subject fusion
- aspect_ratio: match_input_image keeps edits framed identically to the source photo

## Documentation
https://replicate.com/google/nano-banana-2-lite