---
title: Nano Banana Pro | Runware Docs
url: https://runware.ai/docs/models/google-nano-banana-pro
description: Nano Banana Pro image preview for precise visual control
---
# Nano Banana Pro

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

Nano Banana Pro (also known as Nano Banana 2) is a Gemini 3 Pro Image Preview model for controlled visual creation. It improves reasoning over lighting and camera angle. It supports high resolution output and multi image blending for production ready design workflows and creative tools.

- **Status**: live
- **ID**: `google:4@2`
- Try in Playground
- **Creator**: Google
- **Release Date**: November 20, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.138 from, per run · ~47s per request

**Rates** (per run)

- 1K: `$0.138`
- 2K: `$0.138`
- 4K: `$0.244`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/google-nano-banana-pro/examples#example-semiquincentennial-numismatics-magazine-cover) · 1376×768: `$0.138` (~47s)
- [text-to-image](https://runware.ai/docs/models/google-nano-banana-pro/examples#example-sail-assisted-freighter-woodblock-feature) · 1376×768: `$0.138` (~31s)
- [reference-to-image](https://runware.ai/docs/models/google-nano-banana-pro/examples#example-freshwater-mussel-classroom-science-poster) · 2K: `$0.14` (~47s)
- [reference-to-image](https://runware.ai/docs/models/google-nano-banana-pro/examples#example-master-bell-tuner-headshot) · 2K: `$0.14` (~48s)

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

Either provide `inputs.referenceImages`, or specify `width/height`.

---

`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 |
| --- | --- |
| `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` |
| `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` |
| `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` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

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

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

Image output type.

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

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

- **Type**: `boolean`

Include task cost in the response.

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

**Core Parameters**

Primary parameters that define the task output.

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

- **Type**: `string`
- **Required**: true
- **Value**: `google:4@2`

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-pro#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-pro#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.referenceImages is not provided
- **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-pro#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.referenceImages is not provided
- **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-pro#request-resolution)

- **Type**: `string`

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

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

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

**Features**

Standalone addons and post-processing features.

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

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

Text color in hex format.

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

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

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

UUID of the output image.

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

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

URL of the output image.

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

- **Type**: `string`

Base64-encoded image data.

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

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

Data URI of the output image.

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

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

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

![Semiquincentennial Numismatics Magazine Cover](https://assets.runware.ai/examples/google-nano-banana-pro/acde3737-ed7f-4b86-98e4-6d659c3bf23c.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "71074db1-95f3-49ed-97c1-ff045932dfaa",
  "model": "google:4@2",
  "positivePrompt": "Create a finished, edge-to-edge landscape digital magazine cover for a serious contemporary numismatics publication. Before composing, use web search grounding to consult the latest official U.S. Mint sources for the finalized 2026 United States Semiquincentennial circulating coin designs. Accurately reproduce only officially confirmed 2026 designs, denominations, portraits, symbols, dates, inscriptions, metallic colors, reeded or smooth edges, and relative coin sizes; do not invent a coin or mix in rejected design proposals.\n\nArt direction: sophisticated editorial macro still life rather than generic patriotic advertising. Arrange a small selection of the most visually distinctive confirmed 2026 coins across charcoal-gray archival felt, with some lying flat and others subtly raised on nearly invisible museum mounts so both obverse and reverse designs can be seen. The principal coin occupies the right-center and appears exceptionally crisp, tactile, and materially convincing. Use low, raking studio light from the upper left to reveal relief, mint texture, fine scratches, copper warmth, cool nickel, and restrained golden alloy tones. Deep graphite shadows, muted oxblood accents, warm metal highlights, disciplined museum-catalog atmosphere. Include a faint embossed contour-line pattern derived from the continental United States in the background, understated and abstract rather than a literal flag. No fireworks, waving flags, eagles added for decoration, confetti, hands, plastic coin capsules, price stickers, mockup frame, device, webpage, or interface.\n\nBuild a clear premium magazine-cover hierarchy directly into the image. Set the publication masthead across the upper left in large condensed cream sans-serif capitals: “MINTMARK”. Beneath it, small widely spaced text: “FALL 2026  •  THE COLLECTOR’S QUARTERLY”. Place the main headline in the open left-center area, exactly: “AMERICA AT 250”. Below it, in smaller type: “THE NEW COINS, EXPLAINED”. Add one compact footer line: “DESIGN  •  HISTORY  •  COLLECTING”. Include “1776—2026” as a small copper-colored detail near the principal coin. Use only this specified editorial copy and text that is physically part of the accurately depicted official coins; no extra headlines, fake dates, prices, barcode, logos, seals, or filler text. Lettering must be correctly spelled, clean, sharp, aligned, and fully legible.\n\nCompose specifically for 1376x768 landscape with generous safe margins. Keep the left third relatively quiet for cover typography, place the coin grouping through the center and right, and preserve strong visual balance at thumbnail size. Photorealistic metal rendering, exact overhead three-quarter camera geometry, controlled depth of field with every important coin face readable, premium print-editorial color grading, restrained and authoritative mood. Deliver the standalone cover artwork itself, not a magazine photographed on a table and not a presentation mockup.",
  "width": 1376,
  "height": 768,
  "providerSettings": {
    "google": {
      "webSearch": true
    }
  }
}
```

---

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

![Sail-Assisted Freighter Woodblock Feature](https://assets.runware.ai/examples/google-nano-banana-pro/d45e2492-969c-43fb-aa68-74845fff6545.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "adcab35d-0d97-4b57-80ba-ad7600f439ae",
  "model": "google:4@2",
  "positivePrompt": "Create a finished art-style restyle of a contemporary maritime documentary photograph for the opening spread of a serious sustainability magazine. The subject is Canopée, the sail-assisted cargo vessel used to transport Ariane 6 rocket components between Europe and French Guiana. Use web search grounding to inspect recent, reputable 2026 sources and publicly available photographs, confirming the vessel's current exterior configuration, hull proportions, deck equipment, distinctive articulated OceanWings sails, and overall appearance. If recent sources differ from details in this brief, follow the best-supported current visual information.\n\nTranslate the scene completely into an authentic late-Edo Japanese mokuhanga woodblock aesthetic rather than producing a photographic image with a superficial filter. Show the ship in a broad three-quarter profile, moving from left to right through rolling Atlantic water, with its full silhouette and sail system clearly readable. Preserve the engineering credibility of the real vessel: believable hull geometry, correct placement and scale of the rigid wing sails, convincing deck structure, and physically coherent wind direction. A low viewpoint near the water should make the working ship feel purposeful and monumental without turning it into fantasy.\n\nUse hand-carved contour lines, visible registration character, flattened shapes, restrained tonal layering, fibrous warm mulberry-paper texture, and rhythmic wave patterns. Palette: deep Prussian blue, muted teal, weathered cream, persimmon orange, charcoal, and small touches of pale sea-foam green. Render the sky with broad horizontal cloud bands and subtle bokashi gradients. Let white spray cut sharply across the dark water. The mood is disciplined, optimistic, windswept, and industrial rather than nostalgic or whimsical.\n\nLandscape editorial composition at 1376x768. Keep the ship across the lower-middle portion of the frame and leave calm, lightly textured sky in the upper-left area as practical negative space for magazine typography that will be added later. Deliver only the standalone artwork: no headline, caption, border, seal, signature, logo treatment, UI, mockup, or added lettering. Do not invent machinery, extra sails, futuristic structures, or decorative maritime symbols. The result should read immediately as a professionally commissioned woodblock restyle of a current real-world press photograph.",
  "width": 1376,
  "height": 768,
  "providerSettings": {
    "google": {
      "webSearch": true
    }
  }
}
```

---

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

![Freshwater Mussel Classroom Science Poster](https://assets.runware.ai/examples/google-nano-banana-pro/c6a2bbb5-917f-4fd5-bc27-716dd0e070e6.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "57041d7b-3299-48c9-a18c-f277bde8313a",
  "model": "google:4@2",
  "positivePrompt": "Create a finished portrait-format children’s science classroom poster for ages 8–11 titled exactly “THE RIVER’S QUIET FILTER”. Meaningfully synthesize both supplied references into one cohesive educational illustration rather than a collage: preserve the eastern elliptio’s distinctive elongated shell silhouette, olive-brown concentric growth rings and amber edge coloration from reference image 1, and reconstruct the recognizable gravel arrangement, submerged stones, waterweed, clear current and dappled green light of reference image 2 as the surrounding river habitat.\n\nUse a warm, tactile editorial art direction combining opaque gouache, colored pencil texture and crisp screen-printed shapes on lightly speckled cream paper. Palette: river green, mineral blue, warm ochre, clay red, charcoal and cream. Friendly and curious rather than cartoonish; scientifically accurate proportions, no face or human personality added to the animal.\n\nPoster composition: generous cream border and a strong vertical reading path. At the top, set the exact title “THE RIVER’S QUIET FILTER” in large hand-lettered charcoal capitals, followed by the smaller exact subtitle “How a freshwater mussel helps keep water clear”. Below, show the referenced river as a beautiful cutaway scene crossing the waterline and riverbed. Place one large eastern elliptio partly nestled into the gravel as the central subject. Open a clean educational cutaway window through one side of its shell while retaining the recognizable exterior shell around it. Clearly depict the mantle, gills, muscular foot, incurrent siphon and excurrent siphon with simplified but anatomically credible forms.\n\nUse restrained blue arrows to show water entering through the incurrent siphon, passing across the gills and leaving through the excurrent siphon. Show a few suspended particles moving with the incoming water and fewer particles in the outgoing water; do not imply perfectly purified or sterile water. Connect five short leader lines to exact, legible labels: “INCURRENT SIPHON”, “GILLS”, “MANTLE”, “MUSCULAR FOOT”, and “EXCURRENT SIPHON”. Add a small three-frame visual sequence along the bottom labeled exactly “1  WATER FLOWS IN”, “2  GILLS TRAP TINY PARTICLES”, and “3  WATER FLOWS OUT”. Each frame should use the same mussel anatomy and arrow logic as the main diagram.\n\nInclude one compact fact box with the exact heading “WHY MUSSELS MATTER” and the exact two-line copy “They recycle nutrients and create habitat for other river life. Clean, connected rivers help mussels survive.” Keep all wording highly legible, correctly spelled and suitable for elementary science education. Maintain clear hierarchy and ample negative space so the poster can be read from a classroom wall. No logo, no brand, no additional text, no decorative border, no photorealistic pasted elements, no fantasy glow, no extra animals, no anthropomorphic features and no UI or mockup presentation. Deliver the standalone print-ready illustration filling the canvas.",
  "resolution": "2K",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/6560a5bf-0431-4f80-b3f0-13888f143a4f.jpg",
      "https://assets.runware.ai/assets/inputs/b6c821b9-c0af-4a9f-a197-1a82cf339fba.jpg"
    ]
  }
}
```

---

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

![Master Bell Tuner Headshot](https://assets.runware.ai/examples/google-nano-banana-pro/00d1d630-ece4-4b68-ac30-bdd4c6b38067.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "41c3a5e5-0465-4d67-8ebf-37b0f00de99e",
  "model": "google:4@2",
  "positivePrompt": "Create a finished, publication-ready environmental headshot by retouching and enhancing the woman in reference image 1 and meaningfully incorporating the authentic foundry environment, bronze surfaces, patina colors and mixed warm-and-cool lighting from reference image 2. Reference image 1 is the non-negotiable source of identity: preserve her exact facial structure, age, expression, skin tone, eye shape, nose, lips, gray-streaked locs, clear safety glasses, body proportions and charcoal chore coat. Do not idealize, de-age or change her ethnicity. Apply restrained professional portrait retouching: balance exposure and white balance, recover natural eye detail, reduce distracting glare in the glasses while keeping the lenses believable, soften only temporary blemishes and excess shine, gently reduce under-eye fatigue, tidy a few stray hairs and preserve pores, smile lines, natural asymmetry and mature skin texture.\n\nCompose a vertical chest-up headshot with comfortable space above the hair and shoulders, as if photographed with an 85mm portrait lens at eye level. Keep both eyes and the face critically sharp. Refine the background using the visual information from reference image 2: place the large bronze bell off-center behind her as a recognizable but softly defocused shape, with restrained turquoise patina accents, dark timber and a hint of tuning tools. Match the background perspective, light direction and color spill to the subject so the result reads as one real photograph rather than a cutout or composite. Use soft cool window light as the key, subtle warm reflected furnace light along one cheek and shoulder, and controlled shadow detail. The overall palette is charcoal, aged bronze, muted verdigris and warm amber. Mood: grounded, expert, dignified and quietly authoritative, suitable for a craft guild profile, museum press kit or editorial contributor biography. Premium documentary portrait photography, realistic optics, natural depth of field, clean tonal separation, no glamour styling, no excessive skin smoothing, no face reshaping, no added jewelry, no text, no logos, no signage, no frame and no graphic layout.",
  "resolution": "2K",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/58646a22-95f2-4306-b6ad-4fbff4dee480.jpg",
      "https://assets.runware.ai/assets/inputs/fc9dad72-8db0-4e70-a955-7a06a5e61538.jpg"
    ]
  }
}
```