---
title: Nano Banana 2 Lite | Runware Docs
url: https://runware.ai/docs/models/google-nano-banana-2-lite
description: Lighter Nano Banana 2 image model for faster generation and editing workflows
---
# Nano Banana 2 Lite

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

Nano Banana 2 Lite is a lighter variant in Google's Nano Banana 2 image model family. It is positioned as a more efficient option for teams that want the same broad text-to-image and image-editing workflow shape as Nano Banana 2 but with faster turnaround and a smaller model footprint. It is best understood as a lower-latency, higher-throughput entry point into the Nano Banana 2 family rather than a separate creative direction.

- **Status**: live
- **ID**: `google:nano-banana@2-lite`
- Try in Playground
- **Creator**: Google
- **Release Date**: June 30, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Video to Image, Edit, Checkpoint

## Pricing

$0.000337 from, per run · ~5s per request

**Rates**

- Input · per 1M tokens: `$0.25`
- Text output · per 1M tokens: `$1.50`
- Image output · per 1M tokens: `$30.00`
- Example: 1K image output · per run: `$0.0336`
- Example: 1K image input · per run: `$0.000337`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/google-nano-banana-2-lite/examples#example-historic-dry-dock-lighting-visualization) · 1376×768: `$0.0338` (~4s)
- [text-to-image](https://runware.ai/docs/models/google-nano-banana-2-lite/examples#example-airport-wildlife-biologist-picture-book-spread) · 1376×768: `$0.0338` (~4s)
- [reference-to-image](https://runware.ai/docs/models/google-nano-banana-2-lite/examples#example-mineral-saltworks-square-wall-print) · 1024×1024: `$0.0344` (~7s)
- [reference-to-image](https://runware.ai/docs/models/google-nano-banana-2-lite/examples#example-textile-conservation-journal-cover) · 1024×1024: `$0.0344` (~7s)

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` |
| `1K (4:1)` | `2048x512` |
| `1K (1:4)` | `512x2048` |
| `1K (8:1)` | `3072x384` |
| `1K (1:8)` | `384x3072` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

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

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

Image output type.

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

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

- **Type**: `boolean`

Include task cost in the response.

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

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

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-lite#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-lite#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-2-lite#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-2-lite#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`

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

- **Path**: `settings.temperature`
- **Type**: `float`
- **Min**: `0`
- **Max**: `2`
- **Step**: `0.01`
- **Default**: `1`

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-lite#request-settings-topp)

- **Path**: `settings.topP`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.95`

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-lite#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-lite#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-lite#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-lite#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-lite#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-lite#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-lite#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-lite#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-2-lite#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`

## Response Parameters

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

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

UUID of the output image.

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

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

URL of the output image.

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

- **Type**: `string`

Base64-encoded image data.

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

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

Data URI of the output image.

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

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

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

![Historic Dry Dock Lighting Visualization](https://assets.runware.ai/examples/google-nano-banana-2-lite/088f9774-3579-4e20-baa7-89248bf968a7.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "b50ce9c9-e3f3-49cd-9db3-d4116e237e82",
  "model": "google:nano-banana@2-lite",
  "positivePrompt": "Create a finished photorealistic architectural lighting visualization for a municipal public-consultation presentation. Show a decommissioned 19th-century coastal dry dock newly adapted as a maritime heritage park at winter blue hour, immediately after sunset. The long empty dock basin is the central subject, seen from an elevated three-quarter viewpoint near the entrance so its monumental scale and stepped granite walls are clear. Preserve a credible working-waterfront character: weathered granite blocks, iron mooring rings, old rails embedded in the paving, a restored riveted gantry crane, the closed steel caisson gate, low harbor buildings and distant shipyard silhouettes.\n\nDemonstrate the proposed nighttime relighting scheme with precise, believable illumination: narrow warm-white linear fixtures concealed beneath the granite coping trace both sides of the dock; low shielded amber bollards mark a new accessible promenade; subtle grazing light reveals the rough masonry texture without overlighting it; restrained uplights emphasize the gantry crane’s riveted structure; soft recessed lights illuminate stair treads and handrails for safety. The warm 2700K lighting should contrast clearly with the cold cobalt-blue winter sky and blue-gray stone. Include small pools of rainwater on the dock floor and damp paving that produce realistic, understated reflections. A thin trace of sea mist hangs beyond the caisson gate.\n\nAdd a few naturally spaced visitors in winter coats for scale: a couple walking along the promenade, one person reading an interpretive panel, and a wheelchair user accompanied by a friend. Keep people secondary and candid, with no one looking at the camera. Bare wind-shaped grasses in dark steel planters and sparse leafless coastal trees reinforce the season. Harbor work lights glow faintly in the far distance, while the heritage park remains calm, safe and inviting rather than theatrical.\n\nCompose as a wide 16:9 landscape image with strong leading lines running down the dry dock toward the harbor. Place the dock slightly off center, retain open sky above the crane, and show enough foreground promenade to communicate accessibility and material detail. Eye-level architectural photography realism, approximately 28mm lens, corrected verticals, deep focus, natural dynamic range, crisp stone and metal textures, physically plausible shadows, subtle atmospheric depth, premium planning-visualization quality. No snow, no dramatic storm, no fantasy elements, no excessive neon, no visible brand names, no legible text, no captions, no borders, no presentation board, and no interface.",
  "width": 1376,
  "height": 768
}
```

---

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

![Airport Wildlife Biologist Picture-Book Spread](https://assets.runware.ai/examples/google-nano-banana-2-lite/59d55e2e-d1a4-4a05-b7e9-0078944f14b8.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "a31e4cb5-eac2-4ee3-a877-91e03c8036c3",
  "model": "google:nano-banana@2-lite",
  "positivePrompt": "Create a finished full-bleed double-page illustration for a high-quality children’s nonfiction picture book about unusual airport careers. Show an airport wildlife biologist and her trained border collie safely guiding a flock of Canada geese away from the runway at dawn. The biologist is a confident Black woman in her late 30s, wearing practical navy field clothes, rubber boots, hearing protection, and a lime high-visibility vest; she stands on the grassy airfield infield and gives the dog a clear hand signal. The alert black-and-white border collie runs in a wide controlled arc through dew-covered grass, never touching the birds. The geese lift into the peach-colored morning sky in a sweeping diagonal formation that carries the reader’s eye from the lower left page toward the upper right page. In the distance, an airport operations truck waits with an amber beacon, a passenger jet remains stationary well behind the cleared runway line, and a control tower rises through thin lavender mist. Include believable airfield details: blue taxiway edge lights, low red-and-white guidance signs without legible lettering, a striped windsock, runway markings, puddles reflecting the sunrise, seed heads, and a few scattered feathers caught in the breeze. Make the work feel informative, humane, calm, and quietly heroic rather than chaotic.\n\nArt direction: sophisticated contemporary picture-book illustration combining opaque gouache, dry colored-pencil texture, and subtle screen-printed grain on warm off-white paper. Simplified but anatomically convincing people, dog, birds, aircraft, and airport equipment; expressive silhouettes; crisp visual storytelling; layered atmospheric depth. Palette of petrol blue, misty lavender, warm coral, apricot, cream, charcoal, and sharp chartreuse accents. Soft low sunrise creates long translucent shadows and glowing rims around grass and feathers. Use varied brush edges and tactile handmade texture while keeping important shapes clearly readable for children ages 6–9.\n\nComposition: one continuous panoramic scene across a 1376x768 landscape double-page spread, not separate panels and not a book mockup. Keep the central vertical gutter visually quiet, crossing only open grass and soft mist; do not place faces, the dog, or any bird directly on the fold. Position the biologist in the left third and the dog in the lower right third, with the flock forming the main overhead arc. Leave a calm patch of pale sunrise sky in the upper-left quadrant where an editor could later place copy, but include no typography in this generated artwork. Strong foreground, middle ground, and distant runway layers; child-height viewpoint; cinematic wide framing; publication-ready illustration. No title, captions, speech balloons, labels, logos, borders, page numbers, UI, watermark, or legible text.",
  "width": 1376,
  "height": 768
}
```

---

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

![Textile Conservation Journal Cover](https://assets.runware.ai/examples/google-nano-banana-2-lite/d79b4bd6-c9b1-4973-831c-1eb503e457cd.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "2d609b5b-a676-4d50-bf82-56f6752d209e",
  "model": "google:nano-banana@2-lite",
  "positivePrompt": "Create a new, finished square editorial cover for a respected professional journal about material and museum conservation. Ground the cover image closely in the two supplied reference photographs: retain the recognizable cream silk map, faded blue geographic linework, muted red route markings, frayed tears, translucent repair tissue, tiny stitches, and the conservator’s blue-gloved hands. Recompose these details into a bold overhead crop in which the hands enter from the lower left and right edges while a branching tear runs diagonally through the center like a river. The artifact must remain visibly delicate, tactile, and historically plausible.\n\nArt direction: rigorous contemporary European design journal, tactile archival photography combined with restrained screen-printed graphic interventions. Use warm ivory, ultramarine blue, signal red, and dense black. Apply a subtle coarse halftone only in selected shadow areas while preserving crisp fiber detail. Add one thin signal-red registration line that follows part of the central tear, suggesting repair analysis without resembling software UI. Calm, intelligent, materially focused mood; precise rather than nostalgic.\n\nBuild a clear square cover hierarchy with generous negative space. At the top, set the large masthead exactly as: “MEND”. Directly beneath it, in much smaller uppercase type, set: “MATERIAL CONSERVATION REVIEW”. Add the issue line: “ISSUE 08 — SILK, MEMORY, REPAIR”. Place the main feature headline in the upper-right negative space across three short lines: “THE MAP / THAT CAME / APART”. Add one small supporting line near the bottom edge: “Invisible stitches, contested histories, and the ethics of restoration”. Use clean, condensed grotesque typography with accurate spelling, sharp alignment, and strong editorial restraint. Keep every line readable and separated from the artifact details.\n\nDeliver a single flat, print-ready cover image filling the entire frame. No book mockup, no magazine lying on a surface, no hands holding the finished cover, no spine, no barcode, no logos beyond the masthead, no browser interface, and no extra or repeated text.",
  "width": 1024,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/faffdc4c-5fc7-4c39-8403-e3ad8e11b374.jpg",
      "https://assets.runware.ai/assets/inputs/4c891337-cce7-4b90-8eb6-3ab01a261fc8.jpg"
    ]
  }
}
```

---

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

![Mineral Saltworks Square Wall Print](https://assets.runware.ai/examples/google-nano-banana-2-lite/940a3ed8-4a4b-4735-98eb-75f17f82e905.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "89fce15d-5143-4c3e-ac12-2b86e78b8301",
  "model": "google:nano-banana@2-lite",
  "positivePrompt": "Create a new finished square wall-art image grounded in the supplied references. Preserve the first reference's recognizable aerial organization of working coastal salt ponds: irregular rectangular evaporation basins, thin earthen levees, shallow mineral-colored water, several small white salt piles, and a single tiny salt worker that provides scale. Reinterpret the scene as a sophisticated limited-edition reduction linocut combined with flat screenprinting, intended for the lobby and guest rooms of a design-led coastal wellness resort. Use the second reference to inform the tactile crystalline details: translucent cubic salt facets, chalky deposits, fractured mineral edges, and granular highlights should appear selectively within the printed textures without turning the landscape into fantasy.\n\nCompose specifically for a 1:1 square print. Use a calm, top-down-to-oblique viewpoint with the pond geometry flowing diagonally from lower left to upper right. Establish one large muted coral pond as the visual anchor near the center, surrounded by smaller basins in dusty rose, sun-baked terracotta, warm limestone, bone white, pale clay, desaturated mauve, and a restrained accent of deep charcoal-blue. Keep the human figure very small but legible, walking along a narrow levee beside a salt pile. Simplify forms into bold interlocking shapes while retaining the functional structure of a real saltworks.\n\nArt direction: collectible mid-century Mediterranean printmaking, crisp carved contours, subtle registration offsets, dry-ink grain, fibrous uncoated paper texture, sparse mineral speckling, balanced negative space, elegant asymmetry, quiet contemplative mood. Lighting should read as low late-afternoon sun through long graphic shadows rather than photorealistic glare. Maintain clear edges and strong tonal separation suitable for high-quality print-on-demand reproduction. No border, frame, room mockup, typography, captions, logos, symbols, watermark, or signature. Deliver only the standalone artwork.",
  "width": 1024,
  "height": 1024,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/2051ae2f-3e26-491e-a5b6-535ce3cbb4b5.jpg",
      "https://assets.runware.ai/assets/inputs/7484a0aa-2a6c-4069-87c4-124aa8dbcd50.jpg"
    ]
  }
}
```