---
title: Imagen 4 Ultra | Runware Docs
url: https://runware.ai/docs/models/google-imagen-4-ultra
description: High fidelity text to image model with sharp typography
---
# Imagen 4 Ultra

Imagen 4 Ultra is Google's highest quality text to image model. It focuses on photorealism, sharp details, and accurate text rendering. It targets production workloads that need strict prompt adherence, optional higher resolution output, and fast generation through the Gemini API.

- **ID**: `google:2@2`
- **Status**: live
- **Creator**: Google
- **Release Date**: June 24, 2025
- **Capabilities**: Text to Image

## Pricing

Each image generation costs $0.06 at 1024x1024.

- **1024x1024**: `$0.06`

## Compatibility & Validation

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1K (1:1)` | `1024x1024` |
| `1K (9:16)` | `768x1408` |
| `1K (16:9)` | `1408x768` |
| `1K (7:10)` | `896x1280` |
| `1K (10:7)` | `1280x896` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/google-imagen-4-ultra#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/google-imagen-4-ultra#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/google-imagen-4-ultra#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/google-imagen-4-ultra#request-outputformat)

- **Type**: `string`
- **Default**: `JPG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/google-imagen-4-ultra#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/google-imagen-4-ultra#request-webhookurl)

- **Type**: `string`
- **Format**: `URI`

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/google-imagen-4-ultra#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/google-imagen-4-ultra#request-uploadendpoint)

- **Type**: `string`
- **Format**: `URI`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/google-imagen-4-ultra#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/google-imagen-4-ultra#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`
- **Default**: `false`

Enable or disable content safety checking. When enabled, defaults to `fast` mode.

#### [mode](https://runware.ai/docs/models/google-imagen-4-ultra#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `none`

Safety checking mode for image generation.

**Allowed values**:

- `none` Disables checking.
- `fast` Performs a single check.

### [ttl](https://runware.ai/docs/models/google-imagen-4-ultra#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/google-imagen-4-ultra#request-includecost)

- **Type**: `boolean`
- **Default**: `false`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/google-imagen-4-ultra#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Generation Parameters**

Core parameters for controlling the generated content.

### [model](https://runware.ai/docs/models/google-imagen-4-ultra#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `google:2@2`

Identifier of the model to use for generation.

**Learn more** (3 resources):

- [Text To Image: Model Selection The Foundation Of Generation](https://runware.ai/docs/guides/text-to-image#model-selection-the-foundation-of-generation) (guide)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/guides/image-inpainting#model-specialized-inpainting-models) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [positivePrompt](https://runware.ai/docs/models/google-imagen-4-ultra#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `3000`

Text prompt describing elements to include in the generated output.

**Learn more** (2 resources):

- [Text To Image: Prompts Guiding The Generation](https://runware.ai/docs/guides/text-to-image#prompts-guiding-the-generation) (guide)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide)

### [width](https://runware.ai/docs/models/google-imagen-4-ultra#request-width)

- **Type**: `integer`
- **Required**: true
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Image To Image: Dimensions Changing Aspect Ratio](https://runware.ai/docs/guides/image-to-image#dimensions-changing-aspect-ratio) (guide)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/guides/image-outpainting#dimensions-critical-for-outpainting) (guide)

### [height](https://runware.ai/docs/models/google-imagen-4-ultra#request-height)

- **Type**: `integer`
- **Required**: true
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Image To Image: Dimensions Changing Aspect Ratio](https://runware.ai/docs/guides/image-to-image#dimensions-changing-aspect-ratio) (guide)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/guides/image-outpainting#dimensions-critical-for-outpainting) (guide)

## Response Parameters

### [taskType](https://runware.ai/docs/models/google-imagen-4-ultra#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Type of the task.

### [taskUUID](https://runware.ai/docs/models/google-imagen-4-ultra#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the task.

### [imageUUID](https://runware.ai/docs/models/google-imagen-4-ultra#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/google-imagen-4-ultra#response-imageurl)

- **Type**: `string`
- **Format**: `URI`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/google-imagen-4-ultra#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/google-imagen-4-ultra#response-imagedatauri)

- **Type**: `string`
- **Format**: `URI`

Data URI of the output image.

### [seed](https://runware.ai/docs/models/google-imagen-4-ultra#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/google-imagen-4-ultra#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/google-imagen-4-ultra#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### Frosted Funicular Platform Dawn (Text to Image)

![Frosted Funicular Platform Dawn](https://assets.runware.ai/examples/google-imagen-4-ultra/f1a05a72-874b-4675-af6b-c7f7fafee15b.jpg)

**Request**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "7601e189-8b84-4bbf-af94-bce2c2a4f18c",
  "model": "google:2@2",
  "positivePrompt": "Ultra-detailed photorealistic wide cinematic view of a high-altitude funicular platform at first light in late winter, empty except for a single red luggage trolley and a bundled station attendant sweeping powdery snow. Glass shelter panels edged with frost crystals, steel rails descending into a pine valley, distant mountain ridgelines catching pale gold sunrise. Crisp printed station signage with clearly readable text: 'Aster Ridge Funicular', 'Platform 2', and a small timetable board. Subtle boot prints in fresh snow, textured wood benches, safety lines, overhead cables, faint breath in the cold air, realistic reflections on glass, natural color palette, sharp micro-details, depth haze in the background, documentary-grade realism, impeccable composition, no people facing camera, no tram stop, no urban setting.",
  "width": 1408,
  "height": 768
}
```

**Response**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "7601e189-8b84-4bbf-af94-bce2c2a4f18c",
  "imageUUID": "4710047b-2e3d-4dda-bf98-21b2eadbbc3c",
  "imageURL": "https://im.runware.ai/image/os/a24d12/ws/2/ii/4710047b-2e3d-4dda-bf98-21b2eadbbc3c.jpg",
  "seed": 185062939,
  "cost": 0.06
}
```

---

### Subway Violin Case Advertisement (Text to Image)

![Subway Violin Case Advertisement](https://assets.runware.ai/examples/google-imagen-4-ultra/0140afc2-0823-4514-9722-44cea99c6d8d.jpg)

**Request**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "97cb5427-10c8-49c8-a278-412f2537cbf7",
  "model": "google:2@2",
  "positivePrompt": "Ultra-detailed photorealistic subway platform at midday, viewed from standing eye level. A weathered violin case lies open on a bench beside a commuter in a mustard wool coat, while a large backlit station advertisement dominates the wall behind them. The advertisement must contain clean, perfectly legible text reading: 'ARBOR SPRING QUARTET' on the first line, 'ONE NIGHT ONLY' on the second line, and 'APRIL 18 - GRAND HALL' on the third line. Include smaller readable ticket text beneath. Brushed steel columns, tiled floor with subtle scuffs, route map, soft daylight filtering from stairwell entrance, a few travelers passing with slight motion blur, realistic reflections on polished surfaces, shallow depth of field but text remains sharp, natural color palette, cinematic realism, exceptional texture fidelity, precise typography, production-quality photography.",
  "width": 1408,
  "height": 768
}
```

**Response**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "97cb5427-10c8-49c8-a278-412f2537cbf7",
  "imageUUID": "b9f532cf-9f7e-4cab-9add-ab5d2e1288eb",
  "imageURL": "https://im.runware.ai/image/os/a20d05/ws/2/ii/b9f532cf-9f7e-4cab-9add-ab5d2e1288eb.jpg",
  "seed": 996374410,
  "cost": 0.06
}
```

---

### Rain-Soaked Tram Stop Signage (Text to Image)

![Rain-Soaked Tram Stop Signage](https://assets.runware.ai/examples/google-imagen-4-ultra/a1395c3a-8681-4b1e-b16e-17d59a3d5ab0.jpg)

**Request**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "b6b8aafb-73fc-40ac-835a-2876c25e97af",
  "model": "google:2@2",
  "positivePrompt": "A photorealistic early-evening street scene in a coastal European city after a spring downpour, viewed from sidewalk level across tram tracks. Main focus: a glass tram shelter with crystal-clear printed route information and a large illuminated destination sign that reads exactly: 'Line 7 - Harbor Station'. A timetable board inside the shelter shows clean legible text with rows, numbers, and station names. Across the street, a corner bakery has a painted sign reading exactly: 'Marin Bread House' and a smaller window decal reading 'Open 6:00-20:00'. Wet pavement reflects amber streetlights, passing tram headlights, umbrellas, and old stone facades. Include a red tram approaching in the midground, subtle motion only on wheels, sharply resolved raindrops on the shelter glass, detailed cobblestones, puddles, overhead power cables, and realistic pedestrians in weather coats. Natural color palette, cinematic composition, ultra-high detail, crisp focus, faithful typography, realistic materials, production-quality photography, 35mm lens look, deep depth and excellent prompt adherence.",
  "width": 1408,
  "height": 768
}
```

**Response**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "b6b8aafb-73fc-40ac-835a-2876c25e97af",
  "imageUUID": "370d62e3-1aa3-4106-87e7-b9d4628e7164",
  "imageURL": "https://im.runware.ai/image/os/a03d21/ws/2/ii/370d62e3-1aa3-4106-87e7-b9d4628e7164.jpg",
  "seed": 47048902,
  "cost": 0.06
}
```

---

### Hand-Painted Bakery Window Display (Text to Image)

![Hand-Painted Bakery Window Display](https://assets.runware.ai/examples/google-imagen-4-ultra/7adf3bb9-971e-4d24-b65d-fcb9547aed1d.jpg)

**Request**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "f599eb2a-9568-4c8c-833e-2d9c0356f03a",
  "model": "google:2@2",
  "positivePrompt": "Ultra-realistic street-level view of a charming neighborhood bakery storefront in early morning, seen from just outside the front window. The glass window features elegant hand-painted lettering that clearly reads: \"Marigold Bakery\" and below it \"Fresh Bread • Butter Croissants • Open 7 AM\". Inside the display are neatly arranged loaves, fruit tarts, croissants, seeded baguettes, and paper labels with legible names and prices. A small chalkboard near the door reads exactly: \"Today: Plum Danish\". Warm golden sunlight, realistic reflections on glass without obscuring the text, finely detailed pastry textures, natural wood trim, ceramic tiles, subtle flour dust, fresh flowers in a simple vase, authentic candid scene, high-end commercial photography look, sharp focus, true-to-life colors, impeccable typography rendering, rich micro-detail, depth and realism.",
  "width": 1280,
  "height": 896
}
```

**Response**:

```json
{
  "taskType": "imageInference",
  "taskUUID": "f599eb2a-9568-4c8c-833e-2d9c0356f03a",
  "imageUUID": "527cfd2b-fc11-46f5-99aa-7e32942e7e0b",
  "imageURL": "https://im.runware.ai/image/os/a19d05/ws/2/ii/527cfd2b-fc11-46f5-99aa-7e32942e7e0b.jpg",
  "seed": 1705701365,
  "cost": 0.06
}
```