# Fal with Nano Banana 2 API Reference

# Setup

Install the client:

```plaintext
npm install @fal-ai/client
```

Set your API key (option 1 - environment variable, safer):

```plaintext
export FAL_KEY="your_key_here"
```

Set your API key (option 2 - in code):

```js
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "your_key_here",
});
```

* * *

# Generate Image from Text

Endpoint: `fal-ai/nano-banana-2`

```js
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/nano-banana-2", {
  input: {
    prompt: "a cat sitting on the moon",
  },
});

console.log(result.data.images[0].url);
```

* * *

# Edit Image

Endpoint: `fal-ai/nano-banana-2/edit`

Pass one or multiple image URLs plus a prompt describing the edit.

```js
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/nano-banana-2/edit", {
  input: {
    prompt: "make the background a sunset",
    image_urls: ["https://example.com/my-photo.png"],
  },
});

console.log(result.data.images[0].url);
```

Multiple images example:

```js
const result = await fal.subscribe("fal-ai/nano-banana-2/edit", {
  input: {
    prompt: "make a photo of the man driving the car down the coastline",
    image_urls: [
      "https://example.com/person.png",
      "https://example.com/car.png",
    ],
  },
});
```

* * *

# Optional Settings

These work on both endpoints. Add them to the `input` object.

| Setting | Default | Options |
| --- | --- | --- |
| `aspect_ratio` | `"auto"` | auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 |
| `resolution` | `"1K"` | 0.5K, 1K, 2K, 4K |
| `output_format` | `"png"` | jpeg, png, webp |
| `num_images` | `1` | any integer |
| `seed` | random | any integer (for reproducible results) |
| `safety_tolerance` | `"4"` | 1 (strictest) to 6 (least strict) |
| `limit_generations` | `true` | true/false - limits to 1 generation per prompt round |
| `enable_web_search` | not set | true/false - lets model use web info |

* * *

# Response Format

Both endpoints return the same structure:

```json
{
  "images": [
    {
      "url": "https://...",
      "content_type": "image/png",
      "file_name": "output.png",
      "file_size": 123456,
      "width": 1024,
      "height": 1024
    }
  ],
  "description": ""
}
```

Access in code: `result.data.images[0].url`

* * *

# Queue System (Advanced)

For more control instead of using `fal.subscribe`.

**Submit:**

```js
const { request_id } = await fal.queue.submit("fal-ai/nano-banana-2", {
  input: { prompt: "a cat on the moon" },
  webhookUrl: "https://optional.webhook.url/for/results",
});
```

**Check status:**

```js
const status = await fal.queue.status("fal-ai/nano-banana-2", {
  requestId: "your-request-id",
  logs: true,
});
```

**Get result:**

```js
const result = await fal.queue.result("fal-ai/nano-banana-2", {
  requestId: "your-request-id",
});
```

* * *

# File Upload

If you need to upload a local file to get a URL for editing:

```js
import { fal } from "@fal-ai/client";

const file = new File([buffer], "photo.png", { type: "image/png" });
const url = await fal.storage.upload(file);
// now use this url in image_urls
```

The client also auto-uploads if you pass a binary object like a File or Blob.