---
title: Nano Banana 2 | Runware Docs
url: https://runware.ai/docs/models/google-nano-banana-2
description: Gemini 3.1 Flash Image fast high quality AI image generation and editing
---
# Nano Banana 2

![Nano Banana 2](https://assets.runware.ai/covers/google-nano-banana-2.jpg)

Nano Banana 2 (officially known as Gemini 3.1 Flash Image) is Google’s upgraded AI image generation and editing model that brings advanced visual creation capabilities to a broad audience. It generates detailed, expressive images from text and image prompts with sharp details, richer lighting, and improved adherence to complex instructions. Nano Banana 2 also supports multi-object and multi-character consistency, accurate text rendering within images, and flexible resolution control up to 4K. It is now integrated across Google’s AI platforms including the Gemini app, Search AI Mode, and other Gemini-powered services.

- **Status**: live
- **ID**: `google:4@3`
- Try in Playground
- **Creator**: Google
- **Release Date**: February 26, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Video to Image, Edit, Checkpoint

## Pricing

$0.0466 from, per run · ~29s per request

**Rates**

- 0.5K · per run: `$0.0466`
- 1K · per run: `$0.0689`
- 2K · per run: `$0.103`
- 4K · per run: `$0.153`
- Input image · per input image: `$0.00028`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/google-nano-banana-2/examples#example-winter-silo-lighting-visualization) · 1376×768: `$0.0689` (~32s)
- [text-to-image](https://runware.ai/docs/models/google-nano-banana-2/examples#example-underground-salt-cathedral-campaign-hero) · 1376×768: `$0.0689` (~25s)
- [reference-to-image](https://runware.ai/docs/models/google-nano-banana-2/examples#example-subsea-cable-repair-explainer-thumbnail) · 2K: `$0.103` (~54s)
- [reference-to-image](https://runware.ai/docs/models/google-nano-banana-2/examples#example-orchard-robot-case-study-hero) · 2K: `$0.103` (~27s)

a minimum: a request producing more than these cover is billed per token · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.referenceImages` is required.

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `0.5K (1:1)` | `512x512` |
| `0.5K (3:2)` | `632x424` |
| `0.5K (2:3)` | `424x632` |
| `0.5K (4:3)` | `600x448` |
| `0.5K (3:4)` | `448x600` |
| `0.5K (4:5)` | `464x576` |
| `0.5K (5:4)` | `576x464` |
| `0.5K (9:16)` | `384x688` |
| `0.5K (16:9)` | `688x384` |
| `0.5K (21:9)` | `784x336` |
| `0.5K (4:1)` | `1024x256` |
| `0.5K (1:4)` | `256x1024` |
| `0.5K (8:1)` | `1536x192` |
| `0.5K (1:8)` | `192x1536` |
| `1K (1:1)` | `1024x1024` |
| `1K (3:2)` | `1264x848` |
| `1K (2:3)` | `848x1264` |
| `1K (4:3)` | `1200x896` |
| `1K (3:4)` | `896x1200` |
| `1K (4:5)` | `928x1152` |
| `1K (5:4)` | `1152x928` |
| `1K (9:16)` | `768x1376` |
| `1K (16:9)` | `1376x768` |
| `1K (21:9)` | `1584x672` |
| `1K (4:1)` | `2048x512` |
| `1K (1:4)` | `512x2048` |
| `1K (8:1)` | `3072x384` |
| `1K (1:8)` | `384x3072` |
| `2K (1:1)` | `2048x2048` |
| `2K (3:2)` | `2528x1696` |
| `2K (2:3)` | `1696x2528` |
| `2K (4:3)` | `2400x1792` |
| `2K (3:4)` | `1792x2400` |
| `2K (4:5)` | `1856x2304` |
| `2K (5:4)` | `2304x1856` |
| `2K (9:16)` | `1536x2752` |
| `2K (16:9)` | `2752x1536` |
| `2K (21:9)` | `3168x1344` |
| `2K (4:1)` | `4096x1024` |
| `2K (1:4)` | `1024x4096` |
| `2K (8:1)` | `6144x768` |
| `2K (1:8)` | `768x6144` |
| `4K (1:1)` | `4096x4096` |
| `4K (3:2)` | `5056x3392` |
| `4K (2:3)` | `3392x5056` |
| `4K (4:3)` | `4800x3584` |
| `4K (3:4)` | `3584x4800` |
| `4K (4:5)` | `3712x4608` |
| `4K (5:4)` | `4608x3712` |
| `4K (9:16)` | `3072x5504` |
| `4K (16:9)` | `5504x3072` |
| `4K (21:9)` | `6336x2688` |
| `4K (4:1)` | `8192x2048` |
| `4K (1:4)` | `2048x8192` |
| `4K (8:1)` | `12288x1536` |
| `4K (1:8)` | `1536x12288` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/google-nano-banana-2#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/google-nano-banana-2#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-nano-banana-2#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/google-nano-banana-2#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-nano-banana-2#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-nano-banana-2#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses 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/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/google-nano-banana-2#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

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

### [uploadEndpoint](https://runware.ai/docs/models/google-nano-banana-2#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-nano-banana-2#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (1 property)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/google-nano-banana-2#request-safety-checkcontent)

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

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

### [ttl](https://runware.ai/docs/models/google-nano-banana-2#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-nano-banana-2#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/google-nano-banana-2#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.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/google-nano-banana-2#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `14`

List of reference images (UUID, URL, Data URI, or Base64).

### [referenceVideos](https://runware.ai/docs/models/google-nano-banana-2#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `items: 1`

List of reference videos (UUID, URL, or public YouTube URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/google-nano-banana-2#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `google:4@3`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/google-nano-banana-2#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `3`
- **Max**: `45000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/google-nano-banana-2#request-width)

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

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/google-nano-banana-2#request-height)

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

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/google-nano-banana-2#request-resolution)

- **Type**: `string`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `0.5K` `1K` `2K` `4K`

### [seed](https://runware.ai/docs/models/google-nano-banana-2#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [systemPrompt](https://runware.ai/docs/models/google-nano-banana-2#request-settings-systemprompt)

- **Path**: `settings.systemPrompt`
- **Type**: `string`
- **Min**: `1`
- **Max**: `50000`

System-level instruction that guides the model's behavior and output style across the entire generation.

### [temperature](https://runware.ai/docs/models/google-nano-banana-2#request-settings-temperature)

- **Path**: `settings.temperature`
- **Type**: `float`
- **Min**: `0`
- **Max**: `2`
- **Step**: `0.01`

Controls randomness in generation. Lower values produce more deterministic outputs, higher values increase variation and creativity.

### [topP](https://runware.ai/docs/models/google-nano-banana-2#request-settings-topp)

- **Path**: `settings.topP`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`

Nucleus sampling parameter that controls diversity by limiting the probability mass. Lower values make outputs more focused, higher values increase diversity.

### [thinking](https://runware.ai/docs/models/google-nano-banana-2#request-settings-thinking)

- **Path**: `settings.thinking`
- **Type**: `string`

Controls the depth of internal reasoning the model performs before generating a response.

**Allowed values**: `MINIMAL` `HIGH`

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/google-nano-banana-2#request-advancedfeatures-watermark)

- **Path**: `advancedFeatures.watermark`
- **Type**: `object (6 properties)`

Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both.

**Text watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "© 2025 Company",
    "displayPosition": "bottom-right",
    "opacity": 0.6,
    "fontColor": "#ffffff",
    "bgColor": "#000000"
  }
}
```

**Image watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "image": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "displayPosition": "top-left",
    "opacity": 0.6
  }
}
```

**Tiled watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "PREVIEW",
    "tiled": true,
    "opacity": 0.4,
    "fontColor": "#cccccc"
  }
}
```

#### [text](https://runware.ai/docs/models/google-nano-banana-2#request-advancedfeatures-watermark-text)

- **Path**: `advancedFeatures.watermark.text`
- **Type**: `string`
- **Min**: `2`
- **Max**: `32`

Watermark text.

#### [image](https://runware.ai/docs/models/google-nano-banana-2#request-advancedfeatures-watermark-image)

- **Path**: `advancedFeatures.watermark.image`
- **Type**: `string`

Watermark image (UUID, URL, Data URI, or Base64).

#### [displayPosition](https://runware.ai/docs/models/google-nano-banana-2#request-advancedfeatures-watermark-displayposition)

- **Path**: `advancedFeatures.watermark.displayPosition`
- **Type**: `string`

Watermark position.

**Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled`

#### [opacity](https://runware.ai/docs/models/google-nano-banana-2#request-advancedfeatures-watermark-opacity)

- **Path**: `advancedFeatures.watermark.opacity`
- **Type**: `float`
- **Min**: `0.1`
- **Max**: `1`
- **Step**: `0.01`

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/google-nano-banana-2#request-advancedfeatures-watermark-fontcolor)

- **Path**: `advancedFeatures.watermark.fontColor`
- **Type**: `string`

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/google-nano-banana-2#request-advancedfeatures-watermark-bgcolor)

- **Path**: `advancedFeatures.watermark.bgColor`
- **Type**: `string`

Background color in hex format.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.google\` object.

### [imageSearch](https://runware.ai/docs/models/google-nano-banana-2#request-providersettings-google-imagesearch)

- **Path**: `providerSettings.google.imageSearch`
- **Type**: `boolean`

Enable image search grounding to incorporate visual references from the web into image generation.

### [safetyTolerance](https://runware.ai/docs/models/google-nano-banana-2#request-providersettings-google-safetytolerance)

- **Path**: `providerSettings.google.safetyTolerance`
- **Type**: `string`
- **Default**: `none`

Safety filter tolerance level. Use `off` to use Google's defaults.

**Allowed values**: `high` `medium` `low` `none` `off`

### [webSearch](https://runware.ai/docs/models/google-nano-banana-2#request-providersettings-google-websearch)

- **Path**: `providerSettings.google.webSearch`
- **Type**: `boolean`

Enable live web search grounding to incorporate real-world, up-to-date information into image generation.

## Response Parameters

### [taskType](https://runware.ai/docs/models/google-nano-banana-2#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/google-nano-banana-2#response-taskuuid)

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

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/google-nano-banana-2#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/google-nano-banana-2#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/google-nano-banana-2#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/google-nano-banana-2#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [seed](https://runware.ai/docs/models/google-nano-banana-2#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-nano-banana-2#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/google-nano-banana-2#response-cost)

- **Type**: `float`

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

## Examples

### text-to-image (text-to-image)

![Winter Silo Lighting Visualization](https://assets.runware.ai/examples/google-nano-banana-2/d31ecfd5-b904-4de0-80c1-54596b39052f.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "6682abfb-9e7b-400a-936e-f61cb461fc7e",
  "model": "google:4@3",
  "positivePrompt": "Create a finished photorealistic architectural lighting visualization for a design consultancy’s presentation: a row of monumental 1930s concrete grain silos converted into a public climbing and arts center on a northern harbor, shown during deep winter at blue hour. Fresh snow blankets the quay, rooflines and dormant grasses; thin ice gathers along the dark water. Preserve a grounded industrial character with weathered concrete, steel catwalks, loading gantries and tall cylindrical forms. Present the proposed relighting scheme clearly: warm amber uplights graze the curved silo walls, narrow concealed fixtures emphasize vertical ribs, softly illuminated windows reveal climbing walls and timber gathering spaces inside, and low shielded path lights guide pedestrians without glare. A few bundled visitors provide scale, leaving subtle footprints in the snow. Reflections of amber light stretch across wet patches and black-blue harbor water while the sky transitions from cobalt to pale icy cyan near the horizon. Compose as a wide landscape hero image from across the quay, with the silos forming a strong rhythmic diagonal, ample atmospheric sky, and a distant tugboat and cranes kept secondary. Crisp realistic materials, controlled highlights, accurate architectural perspective, calm Scandinavian editorial photography, quiet civic mood, sophisticated blue-and-amber palette, no logos, no captions, no signage, no border, no split-screen or before-and-after layout.",
  "width": 1376,
  "height": 768,
  "settings": {
    "thinking": "HIGH"
  }
}
```

---

### text-to-image (text-to-image)

![Underground Salt Cathedral Campaign Hero](https://assets.runware.ai/examples/google-nano-banana-2/e91d3ee1-9cec-4140-a584-03cb81167288.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "07c08b32-dab6-4bbf-a3ba-95304979102e",
  "model": "google:4@3",
  "positivePrompt": "Create a premium tourism campaign hero image of the Chapel of St. Kinga deep inside Poland’s Wieliczka Salt Mine. Show the immense subterranean sanctuary from a slightly elevated position near the entrance, looking down the long central nave toward the illuminated altar. Monumental walls, columns, relief sculptures, balustrades and floor tiles are all intricately carved from gray rock salt. Elaborate salt-crystal chandeliers glow overhead like warm constellations. A small guided group of adult travelers in understated contemporary clothing descends the broad staircase at lower left, providing human scale without dominating the architecture. One visitor pauses at the railing in quiet awe. Use a wide landscape composition with strong leading lines, layered depth and generous open space through the center. Sophisticated cinematic architectural photography, crisp mineral texture, atmospheric underground haze, warm amber chandelier light against cool slate-gray and subtle emerald shadows, restrained highlights, realistic proportions, inviting yet mysterious mood. The image should feel culturally significant, transportive and suitable for the lead visual of an international heritage-tourism campaign. Photorealistic, polished editorial finish, deep focus, natural human anatomy, no staged poses. No typography, logos, signs, borders, collage, interface elements or watermark.",
  "width": 1376,
  "height": 768,
  "settings": {
    "thinking": "HIGH"
  }
}
```

---

### reference-to-image (reference-to-image)

![Subsea Cable Repair Explainer Thumbnail](https://assets.runware.ai/examples/google-nano-banana-2/ae5712c5-87da-42c7-9309-95ba2d6c9d12.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "8dd9fd9d-9971-4200-a97c-fdf09ddb453a",
  "model": "google:4@3",
  "positivePrompt": "Create a finished cinematic 16:9 video thumbnail for a serious technology documentary about repairing the undersea cables that carry global internet traffic. Use the reference image as the primary authority for the hero subject: reproduce that same severed fiber-optic cable construction, materials, frayed optical fibers, salt wear and distinctive three-quarter profile with convincing engineering accuracy. Enlarge the broken cable into a dramatic foreground element running diagonally from the lower left toward the center, its exposed colorful fiber strands catching the light and remaining legible at thumbnail size. Use the reference video only as supplementary visual guidance for the operational setting, underwater atmosphere and action: place a realistic orange work-class ROV in the middle distance on the right, echoing the video's manipulator-arm posture, hard white work lights, drifting sediment, deep-sea particles and slow documentary camera perspective. Show one manipulator reaching toward the cable without obscuring its exposed cross-section. Dark cobalt and near-black water, muted seabed brown, safety-orange machinery and small jewel-like fiber colors. Strong separation between foreground cable and background vehicle, directional beams through particulate water, restrained contrast, crisp tactile detail, credible scale, sophisticated investigative-journalism art direction, tense but factual mood. Compose with an uncluttered pocket of dark water in the upper left for optional editorial headline placement, but render no words, letters, logos, interface elements, borders or watermarks. The result must be a single immersive underwater still, not a collage, screenshot or mockup.",
  "resolution": "2K",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/fa56a831-822e-4e65-93cb-12f8e1b5de1d.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/dc5cfd30-e940-44ee-b08c-9b9d113c2545.mp4"
    ]
  }
}
```

---

### reference-to-image (reference-to-image)

![Orchard Robot Case Study Hero](https://assets.runware.ai/examples/google-nano-banana-2/dcc9933e-4282-4731-8b5c-64e3136cb531.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "42201cc9-85d7-4456-b9d0-1477b15b5fe6",
  "model": "google:4@3",
  "positivePrompt": "Create a finished wide editorial photograph for an agricultural robotics case study. Use the reference image as the authoritative primary reference for the subject: preserve the exact orchard rover’s design, proportions, matte cream body panels, four narrow rugged tires, lidar mast, cameras, articulated sensor arms, safety lights, surface wear, and three-quarter viewing angle. Remove its plain studio background and place the same rover convincingly into a real working apple orchard.\n\nUse the reference video only as supplementary visual guidance for the replacement environment and cinematography: match its mature tunnel-like orchard rows, dense sage-green leaves, small red apples, damp reddish soil, irrigation tubing, fallen leaves, faint low mist, subdued dawn palette, soft overcast directional light, and grounded documentary mood. Derive the row perspective and environmental texture from the video while keeping the robot from the image as the unmistakable principal subject.\n\nPosition the rover traveling between the trees, slightly left of center, with clear breathing room ahead of it and layered orchard depth extending across the wide frame. Integrate it physically: tires should compress into moist soil, lower foliage may naturally overlap a small part of the chassis, and soft reflections on the body should inherit the green canopy and warm earth tones. Add restrained tire tracks and a trace of disturbed dew, but no dramatic dust or staged action. Match light direction, contact shadows, lens perspective, focus falloff, color temperature, and atmospheric haze so this looks like one authentic on-location exposure rather than a composite.\n\nArt direction: premium agricultural trade editorial, observational and credible, muted sage, cream, rust-red, and cool gray palette; crisp mechanical detail with gentle background falloff; realistic 35mm environmental product photography at rover height. No people, no extra robots, no altered components, no floating wheels, no studio backdrop remnants, no logos, no captions, no borders, and no on-image text.",
  "resolution": "2K",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/7ddd8c61-6472-47e8-9a64-e1cda76ec67f.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/b0e8181a-d73b-42fe-93d6-e90f935d05e1.mp4"
    ]
  }
}
```