> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/vercel/ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Image Generation

> Learn how to generate images with the AI SDK.

# Image Generation

The AI SDK provides the [`generateImage`](/docs/reference/ai-sdk-core/generate-image)
function to generate images based on a given prompt using an image model.

```tsx theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { image } = await generateImage({
  model: openai.image('dall-e-3'),
  prompt: 'Santa Claus driving a Cadillac',
});
```

You can access the image data using the `base64` or `uint8Array` properties:

```tsx theme={null}
const base64 = image.base64; // base64 image data
const uint8Array = image.uint8Array; // Uint8Array image data
```

## Settings

### Size and Aspect Ratio

Depending on the model, you can either specify the size or the aspect ratio.

#### Size

The size is specified as a string in the format `{width}x{height}`.
Models only support a few sizes, and the supported sizes are different for each model and provider.

```tsx highlight={"7"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { image } = await generateImage({
  model: openai.image('dall-e-3'),
  prompt: 'Santa Claus driving a Cadillac',
  size: '1024x1024',
});
```

#### Aspect Ratio

The aspect ratio is specified as a string in the format `{width}:{height}`.
Models only support a few aspect ratios, and the supported aspect ratios are different for each model and provider.

```tsx highlight={"7"} theme={null}
import { generateImage } from 'ai';
import { vertex } from '@ai-sdk/google-vertex';

const { image } = await generateImage({
  model: vertex.image('imagen-4.0-generate-001'),
  prompt: 'Santa Claus driving a Cadillac',
  aspectRatio: '16:9',
});
```

### Generating Multiple Images

`generateImage` also supports generating multiple images at once:

```tsx highlight={"7"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { images } = await generateImage({
  model: openai.image('dall-e-2'),
  prompt: 'Santa Claus driving a Cadillac',
  n: 4, // number of images to generate
});
```

<Note>
  `generateImage` will automatically call the model as often as needed (in
  parallel) to generate the requested number of images.
</Note>

Each image model has an internal limit on how many images it can generate in a single API call. The AI SDK manages this automatically by batching requests appropriately when you request multiple images using the `n` parameter. By default, the SDK uses provider-documented limits (for example, DALL-E 3 can only generate 1 image per call, while DALL-E 2 supports up to 10).

If needed, you can override this behavior using the `maxImagesPerCall` setting:

```tsx highlight={"7"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { images } = await generateImage({
  model: openai.image('dall-e-2'),
  prompt: 'Santa Claus driving a Cadillac',
  maxImagesPerCall: 5, // Override the default batch size
  n: 10, // Will make 2 calls of 5 images each
});
```

### Providing a Seed

Some image models support seeds for reproducible generation:

```tsx highlight={"7"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { image } = await generateImage({
  model: openai.image('dall-e-3'),
  prompt: 'Santa Claus driving a Cadillac',
  seed: 12345,
});
```

### Provider Options

Image model settings can be configured using `providerOptions` for provider-specific parameters:

```tsx highlight={"7-11"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { image } = await generateImage({
  model: openai.image('dall-e-3'),
  prompt: 'Santa Claus driving a Cadillac',
  providerOptions: {
    openai: {
      style: 'vivid', // or 'natural'
    },
  },
});
```

## Image Editing

### Image-to-Image

Some models support image-to-image generation, where you provide a source image along with a prompt:

```tsx highlight={"6-9"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';
import { readFile } from 'fs/promises';

const { image } = await generateImage({
  model: openai.image('dall-e-2'),
  prompt: {
    images: [await readFile('source.png')],
    text: 'Make it snowy',
  },
});
```

### Inpainting with Masks

You can also provide a mask to specify which parts of the image should be regenerated:

```tsx highlight={"8-11"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';
import { readFile } from 'fs/promises';

const { image } = await generateImage({
  model: openai.image('dall-e-2'),
  prompt: {
    images: [await readFile('source.png')],
    mask: await readFile('mask.png'),
    text: 'Add a Christmas tree',
  },
});
```

## Response Information

The `generateImage` function returns comprehensive response information:

```tsx highlight={"6-8"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = await generateImage({
  model: openai.image('dall-e-3'),
  prompt: 'Santa Claus driving a Cadillac',
});

console.log(result.images); // Array of generated images
console.log(result.warnings); // Any warnings from the provider
console.log(result.responses); // Raw provider responses
console.log(result.usage); // Token usage information
```

## Retries

The `generateImage` function accepts an optional `maxRetries` parameter
that you can use to set the maximum number of retries.
It defaults to `2` retries (3 attempts in total). You can set it to `0` to disable retries.

```tsx highlight={"7"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { image } = await generateImage({
  model: openai.image('dall-e-3'),
  prompt: 'Santa Claus driving a Cadillac',
  maxRetries: 0, // Disable retries
});
```

## Abort Signals and Timeouts

The `generateImage` function accepts an optional `abortSignal` parameter of
type [`AbortSignal`](https://developer.mozilla.org/en-US/docs/Web/API/AbortSignal)
that you can use to abort the generation process or set a timeout.

```tsx highlight={"7"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { image } = await generateImage({
  model: openai.image('dall-e-3'),
  prompt: 'Santa Claus driving a Cadillac',
  abortSignal: AbortSignal.timeout(30000), // Abort after 30 seconds
});
```

## Custom Headers

The `generateImage` function accepts an optional `headers` parameter
that you can use to add custom headers to the request.

```tsx highlight={"7"} theme={null}
import { generateImage } from 'ai';
import { openai } from '@ai-sdk/openai';

const { image } = await generateImage({
  model: openai.image('dall-e-3'),
  prompt: 'Santa Claus driving a Cadillac',
  headers: { 'X-Custom-Header': 'custom-value' },
});
```

## Image Providers & Models

Several providers offer image generation models:

| Provider                                                                       | Model                          |
| ------------------------------------------------------------------------------ | ------------------------------ |
| [OpenAI](/providers/ai-sdk-providers/openai#image-models)                      | `dall-e-3`                     |
| [OpenAI](/providers/ai-sdk-providers/openai#image-models)                      | `dall-e-2`                     |
| [Google Vertex AI](/providers/ai-sdk-providers/google-vertex#image-models)     | `imagen-4.0-generate-001`      |
| [Google Vertex AI](/providers/ai-sdk-providers/google-vertex#image-models)     | `imagen-3.0-generate-001`      |
| [Stability AI](/providers/ai-sdk-providers/stability-ai#image-models)          | `stable-diffusion-v1-6`        |
| [Stability AI](/providers/ai-sdk-providers/stability-ai#image-models)          | `stable-diffusion-xl-1024-v1`  |
| [Black Forest Labs (via fal.ai)](/providers/ai-sdk-providers/fal#image-models) | `flux/schnell`                 |
| [Black Forest Labs (via fal.ai)](/providers/ai-sdk-providers/fal#image-models) | `flux-pro`                     |
| [Amazon Bedrock](/providers/ai-sdk-providers/amazon-bedrock#image-models)      | `stability.stable-diffusion-*` |