# Nano Banana 2 (Gemini 3.1 Flash Image) - Core.Today AI API

> Google's fast image generation model built on Gemini 3.1 Flash Image. The high-efficiency counterpart to Nano Banana Pro — combining Pro-level visual quality with Flash-level speed and pricing. Features conversational editing, multi-image fusion, character consistency, accurate text rendering, and Google Search grounding. Supports up to 14 reference images and resolutions up to 4K.

- **Provider**: Google
- **Model ID**: google/nano-banana-2
- **Category**: Image Generation
- **Credits**: 190 per image (1K), 280 for 2K, 370 for 4K
- **Speed**: Fast
- **Quality**: Ultra

## Features
- Gemini 3.1 Flash Image-powered generation with Pro-level quality
- Accurate text rendering in multiple languages
- Google Web Search and Image Search grounding
- Up to 14 reference images for multi-image fusion
- Up to 4K output resolution (1K, 2K, 4K)
- New extreme aspect ratios: 1:4, 4:1, 1:8, 8:1

## Use Cases
- Typography, logos, and branding with accurate multilingual text
- Real-time data visualization using Google Search grounding
- Multi-image character consistency and style fusion
- High-resolution content production up to 4K
- Conversational image editing with reference images

## 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
- **resolution**: string (default: 1K) - Resolution of the generated image
  Options: 1K, 2K, 4K
- **google_search**: boolean (default: false) - Use Google Web Search grounding for real-time information
- **image_search**: boolean (default: false) - Use Google Image Search grounding for visual context
- **output_format**: string (default: jpg) - Format of the output image
  Options: jpg, png

## Examples

### Photorealistic Portrait
Generate a high-quality portrait with natural lighting
```json
{
  "model": "google/nano-banana-2",
  "input": {
    "prompt": "A photorealistic close-up portrait of an elderly Japanese ceramicist with deep wrinkles and a warm smile, carefully inspecting a freshly glazed tea bowl in his rustic sun-drenched workshop.",
    "aspect_ratio": "3:4",
    "resolution": "2K",
    "output_format": "jpeg"
  }
}
```

### Anime Style Transfer
Transform a photo into Studio Ghibli anime style using reference image
```json
{
  "model": "google/nano-banana-2",
  "input": {
    "prompt": "Transform this photograph into a Studio Ghibli anime style illustration. Keep the same composition but render everything with soft cel-shading, warm colors, and the dreamy atmosphere of a Miyazaki film.",
    "aspect_ratio": "match_input_image"
  }
}
```

## 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
- Best balance of speed and quality — ideal upgrade from Nano Banana for production use
- Use Google Search grounding for real-time data (weather, sports, news) in generated images
- Text rendering is significantly improved over Nano Banana — great for posters, logos, and infographics
- Use 1K (240 credits) for most tasks; 4K (480 credits) for final production assets
- Supports extreme aspect ratios (1:8, 8:1) for banners and vertical content
- Combine multiple reference images with text prompts for powerful style fusion and editing