---
title: Qwen-Image-Layered | Runware Docs
url: https://runware.ai/docs/models/alibaba-qwen-image-layered
description: Layered image decomposition model for editable RGBA outputs
---
# Qwen-Image-Layered

![Qwen-Image-Layered](https://assets.runware.ai/covers/alibaba-qwen-image-layered.jpg)

Qwen-Image-Layered decomposes a static image into multiple RGBA layers, enabling independent editing of semantically distinct components without interfering with other parts of the image. This layered representation supports high-fidelity image editing tasks like resizing, repositioning, recoloring, and object manipulation with consistent detail and transparency handling.

- **Status**: live
- **ID**: `alibaba:qwen-image@layered`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: December 19, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Image to Image, Checkpoint, Transparency

## Pricing

$0.144 from, per run · ~30s per request

**Measured runs**

- steps 30 · settings.layers 4 · 1024×1024 input: `$0.144` (~2m 9s)
- steps 50 · settings.layers 4 · 1024×1024 input: `$0.232` (~3m 8s)
- steps 30 · settings.layers 10 · 1024×1024 input: `$0.384` (~4m 50s)

**4 example generations**

- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-layered/examples#example-historic-observatory-photo-cleanup): `$0.0141` (~26s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-layered/examples#example-heritage-railway-crew-portrait): `$0.0141` (~27s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-layered/examples#example-fossil-skull-background-separation): `$0.0141` (~26s)
- [reference-to-image](https://runware.ai/docs/models/alibaba-qwen-image-layered/examples#example-urban-beekeeping-screenprint-illustration): `$0.0154` (~30s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-outputformat)

- **Type**: `string`
- **Default**: `TIFF`

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

- \`TIFF\`: High-quality output supporting layers.

> [!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**: `TIFF`

### [outputQuality](https://runware.ai/docs/models/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/alibaba-qwen-image-layered#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.

### [acceleratorOptions](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions)

- **Path**: `acceleratorOptions.cacheEndStep`
- **Type**: `object (10 properties)`

Advanced caching mechanisms to speed up generation.

#### [cacheEndStep](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-cacheendstep)

- **Path**: `acceleratorOptions.cacheEndStep`
- **Type**: `integer`
- **Min**: `1`

Absolute step number to end caching. Must be greater than `cacheStartStep` and less than or equal to `steps`.

#### [cacheEndStepPercentage](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-cacheendsteppercentage)

- **Path**: `acceleratorOptions.cacheEndStepPercentage`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`

Percentage of steps to end caching. Alternative to `cacheEndStep`. Must be greater than `cacheStartStepPercentage`.

#### [cacheMaxConsecutiveSteps](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-cachemaxconsecutivesteps)

- **Path**: `acceleratorOptions.cacheMaxConsecutiveSteps`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `5`
- **Default**: `3`

Limits the maximum number of consecutive steps that can use cached computations before forcing a fresh computation.

#### [cacheStartStep](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-cachestartstep)

- **Path**: `acceleratorOptions.cacheStartStep`
- **Type**: `integer`
- **Min**: `0`

Absolute step number to start caching. Must be less than `cacheEndStep`.

#### [cacheStartStepPercentage](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-cachestartsteppercentage)

- **Path**: `acceleratorOptions.cacheStartStepPercentage`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `99`

Percentage of steps to start caching. Alternative to `cacheStartStep`. Must be less than `cacheEndStepPercentage`.

#### [fbCache](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-fbcache)

- **Path**: `acceleratorOptions.fbCache`
- **Type**: `boolean`

First Block Cache (FBCache) acceleration. Reuses feature block computations across steps.

#### [fbCacheThreshold](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-fbcachethreshold)

- **Path**: `acceleratorOptions.fbCacheThreshold`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.25`

Controls the sensitivity threshold for determining when to reuse cached computations. Lower values reuse more aggressively.

#### [dbCache](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-dbcache)

- **Path**: `acceleratorOptions.dbCache`
- **Type**: `boolean`

DB Cache (CacheDiT) acceleration. Caches and reuses intermediate transformer block outputs to skip redundant computations.

#### [dbCacheThreshold](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-dbcachethreshold)

- **Path**: `acceleratorOptions.dbCacheThreshold`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.25`

Controls the sensitivity threshold for DB Cache. Lower values reuse cached blocks more aggressively, higher values prioritize quality.

#### [dbCacheSkipInterval](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-acceleratoroptions-dbcacheskipinterval)

- **Path**: `acceleratorOptions.dbCacheSkipInterval`
- **Type**: `integer`
- **Min**: `1`
- **Default**: `5`

Controls how many steps to skip between cache refreshes. Higher values skip more steps for faster generation at the cost of quality.

**Inputs**

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

### [referenceImages](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Required**: true
- **Min items**: `items: 1`

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/alibaba-qwen-image-layered#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `alibaba:qwen-image@layered`

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/alibaba-qwen-image-layered#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `32000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

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

### [negativePrompt](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-negativeprompt)

- **Type**: `string`
- **Min**: `1`
- **Max**: `32000`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

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

### [seed](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `9223372036854776000`

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

**Learn more** (1 resource):

- [Seed](https://runware.ai/docs/learn/seed) (learn)

### [steps](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-steps)

- **Type**: `integer`
- **Min**: `5`
- **Max**: `50`
- **Default**: `30`

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

**Learn more** (1 resource):

- [Steps](https://runware.ai/docs/learn/steps) (learn)

### [scheduler](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-scheduler)

- **Type**: `string`

Scheduler to use for the diffusion process.

**Allowed values**: `DDIM` `DDIMScheduler` `DDPMScheduler` `DEISMultistepScheduler` `Default` `DPM++` `DPM++ 2M` `DPM++ 2M Beta` `DPM++ 2M Exponential` `DPM++ 2M Karras` `DPM++ 2M SDE` `DPM++ 2M SDE Beta` `DPM++ 2M SDE Exponential` `DPM++ 2M SDE Karras` `DPM++ 2M SDE Uniform` `DPM++ 2M Uniform` `DPM++ 3M` `DPM++ 3M Beta` `DPM++ 3M Exponential` `DPM++ 3M Karras` `DPM++ 3M SDE Uniform` `DPM++ 3M Uniform` `DPM++ Beta` `DPM++ Exponential` `DPM++ Karras` `DPM++ SDE` `DPM++ SDE Beta` `DPM++ SDE Exponential` `DPM++ SDE Karras` `DPM++ Uniform` `DPM++ Uniform Beta` `DPM++ Uniform Exponential` `DPM++ Uniform Karras` `DPMSolverMultistepInverse` `DPMSolverMultistepScheduler` `DPMSolverSinglestepScheduler` `EDMDPMSolverMultistepScheduler` `EDMEulerScheduler` `Euler` `Euler a` `Euler Beta` `Euler Exponential` `Euler Karras` `EulerAncestralDiscreteScheduler` `EulerDiscreteScheduler` `FlowMatchEulerDiscreteScheduler` `Heun` `HeunDiscreteScheduler` `Heun Karras` `IPNDMScheduler` `IPNDM Uniform` `IPNDM Uniform Beta` `IPNDM Uniform Exponential` `IPNDM Uniform Karras` `KDPM2AncestralDiscreteScheduler` `KDPM2DiscreteScheduler` `LCM` `LCMScheduler` `LMS` `LMSDiscreteScheduler` `LMS Karras` `PNDMScheduler` `TCDScheduler` `UniPC` `UniPC 2M` `UniPC 2M Karras` `UniPC 2M Uniform` `UniPC 3M` `UniPC 3M Karras` `UniPC 3M Uniform` `UniPC Karras` `UniPC Uniform` `UniPC Uniform Beta` `UniPC Uniform Exponential` `UniPC Uniform Karras`

**Learn more** (2 resources):

- [Schedulers](https://runware.ai/docs/learn/schedulers) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [CFGScale](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-cfgscale)

- **Type**: `float`
- **Min**: `0`
- **Max**: `10`
- **Step**: `0.01`

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

**Learn more** (1 resource):

- [Cfg Scale](https://runware.ai/docs/learn/cfg-scale) (learn)

### [lora](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-lora)

- **Path**: `lora.model`
- **Type**: `array of objects (2 properties)`
- **Min items**: `1`

With LoRA (Low-Rank Adaptation), you can adapt a model to specific styles or features by emphasizing particular aspects of the data. This technique enhances the quality and relevance of generated content and can be especially useful when the output needs to adhere to a specific artistic style or follow particular guidelines.

Multiple LoRA models can be used simultaneously to achieve different adaptation goals.

**Examples**:

```json
"lora": [
  {
    "model": "<lora-model-air>",
    "weight": 0.8
  }
]
```

**Learn more** (1 resource):

- [Loras](https://runware.ai/docs/learn/loras) (learn)

#### [model](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-lora-model)

- **Path**: `lora.model`
- **Type**: `string`
- **Required**: true

LoRA model identifier.

#### [weight](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-lora-weight)

- **Path**: `lora.weight`
- **Type**: `float`
- **Min**: `-4`
- **Max**: `4`
- **Step**: `0.01`
- **Default**: `1`

Strength of the LoRA influence. A value of 0 means no influence. Higher values increase the influence, and negative values can be used to steer away from the LoRA's style.

**Settings**

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

### [layers](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-settings-layers)

- **Path**: `settings.layers`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `10`
- **Default**: `4`

Number of layers the image is decomposed into.

### [trueCFGScale](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-settings-truecfgscale)

- **Path**: `settings.trueCFGScale`
- **Type**: `float`

True Classifier-Free Guidance scale. Higher values increase prompt adherence at the cost of quality.

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-advancedfeatures-watermark-image)

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

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

#### [displayPosition](https://runware.ai/docs/models/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/alibaba-qwen-image-layered#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/alibaba-qwen-image-layered#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/alibaba-qwen-image-layered#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/alibaba-qwen-image-layered#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/alibaba-qwen-image-layered#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/alibaba-qwen-image-layered#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/alibaba-qwen-image-layered#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/alibaba-qwen-image-layered#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/alibaba-qwen-image-layered#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/alibaba-qwen-image-layered#response-cost)

- **Type**: `float`

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

## Examples

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

```
{
  "taskType": "imageInference",
  "taskUUID": "2ccb991c-ddb8-426e-aad0-cb3a81f67b68",
  "imageUUID": "7e346894-1e43-4b8f-ab39-5c3673bec593",
  "imageURL": "https://im.runware.ai/image/os/a07dlim3/ws/3/ii/7e346894-1e43-4b8f-ab39-5c3673bec593.tiff",
  "seed": 1393187809,
  "cost": 0.0141
}
```

```json
{
  "taskType": "imageInference",
  "taskUUID": "2ccb991c-ddb8-426e-aad0-cb3a81f67b68",
  "model": "alibaba:qwen-image@layered",
  "positivePrompt": "Decompose the supplied observatory photograph into coherent, independently editable RGBA layers while preserving the original composition, camera perspective, lighting, color, texture, shadows, reflections, and photorealistic appearance when all layers are visible. Place the orange rolling maintenance ladder and its attached black power cable on a dedicated foreground removal layer with precise edges, wheel details, openings between the ladder rails, natural contact shadows, and clean transparency. Reconstruct a continuous clean-plate base beneath and behind that equipment, generatively filling the obscured pale speckled terrazzo floor, grout lines, subtle reflections, and adjacent architectural surfaces so the ladder and cable can be hidden without a visible patch. Separate the historic brass-and-cream refracting telescope and pedestal as the principal midground layer. Keep the circular railing and dark green equipment cabinets on distinct midground layers where practical. Preserve the curved ribbed plaster dome, open viewing slit, dusk sky, and uninterrupted architectural illumination as the continuous background layer. Retain all fine mechanical detail and ensure clean alpha boundaries without halos, duplicated edges, missing geometry, or unintended changes to the scene.",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/d616c40d-1313-4d3e-a387-6f48cde878c0.jpg"
    ]
  }
}
```

---

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

```
{
  "taskType": "imageInference",
  "taskUUID": "08708418-6947-499e-8c2e-9b82b0d71a25",
  "imageUUID": "c24042f4-8170-4a53-bc4b-fb289c47b88e",
  "imageURL": "https://im.runware.ai/image/os/a02d21/ws/3/ii/c24042f4-8170-4a53-bc4b-fb289c47b88e.tiff",
  "seed": 1216296447,
  "cost": 0.0141
}
```

```json
{
  "taskType": "imageInference",
  "taskUUID": "08708418-6947-499e-8c2e-9b82b0d71a25",
  "model": "alibaba:qwen-image@layered",
  "positivePrompt": "Decompose the supplied heritage railway crew portrait into coherent, independently editable RGBA layers while preserving the source image's exact composition, people, facial appearance, clothing, lighting, color palette, perspective, texture, and photographic realism. Isolate the seated retired chief engineer in the foreground as a clean standalone subject layer with precise boundaries around his hair, burgundy neckerchief, navy coveralls, hands, boots, toolbox, and natural contact shadows so he can be removed or repositioned without affecting anyone else. Separate the standing restoration crew in the midground into logically editable person layers wherever their silhouettes permit, preserving all overlaps and depth order. Place the steam locomotive and workshop props on distinct midground layers. Create a continuous engine-shed background layer containing the brick wall, floor, structural details, pendant lights, and plausible clean reconstruction behind foreground and midground subjects, enabling the seated engineer to be removed cleanly. Retain natural edge softness, fine fabric detail, reflections, ambient shadows, and transparent antialiased boundaries. The layered result must visually match the supplied photograph when all layers are composited.",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/02c3191c-9d79-4d2d-a3d7-40e33bf77f2a.jpg"
    ]
  }
}
```

---

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

```
{
  "taskType": "imageInference",
  "taskUUID": "ccccd4e9-467c-4143-8b6a-9f5993dddff1",
  "imageUUID": "3623ab17-9dcd-40a8-a98a-b3d2cddb9dd2",
  "imageURL": "https://im.runware.ai/image/os/a02d21/ws/3/ii/3623ab17-9dcd-40a8-a98a-b3d2cddb9dd2.tiff",
  "seed": 1442175814,
  "cost": 0.0154
}
```

```json
{
  "taskType": "imageInference",
  "taskUUID": "ccccd4e9-467c-4143-8b6a-9f5993dddff1",
  "model": "alibaba:qwen-image@layered",
  "positivePrompt": "Transform the supplied rooftop beekeeping photograph into a polished mid-century civic screenprint illustration for the cover of an urban agriculture annual report. Preserve the original vertical composition, camera angle, subject identity, pose, honey-frame details, hive placement, planters, skyline silhouette, lighting direction, and spatial depth. Use bold hand-cut shapes, subtle imperfect ink registration, restrained paper grain, simplified dimensional shading, and a sophisticated limited palette of honey gold, deep petrol blue, warm cream, brick red, and charcoal. Keep the mood practical, optimistic, and documentary rather than whimsical. No lettering, logos, border, or added objects. Decompose the finished image into coherent, independently editable RGBA layers while maintaining a seamless match when composited: isolate the foreground beekeeper and honey frame with clean transparent edges; separate the midground hive boxes; separate the rooftop planters and vegetation; retain the city skyline and sky as a continuous full-frame background; preserve natural occlusion, edge detail, shadows, and visual continuity between every layer.",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/02f7285a-412b-4c35-961f-ed1ae626afaf.jpg"
    ]
  }
}
```

---

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

```
{
  "taskType": "imageInference",
  "taskUUID": "0d3a0b8c-1a6e-4faa-ab65-625b3346d896",
  "imageUUID": "7e0f5270-c803-4efe-aa80-9f34e0f27720",
  "imageURL": "https://im.runware.ai/image/os/a01d21/ws/3/ii/7e0f5270-c803-4efe-aa80-9f34e0f27720.tiff",
  "seed": 714776651,
  "cost": 0.0141
}
```

```json
{
  "taskType": "imageInference",
  "taskUUID": "0d3a0b8c-1a6e-4faa-ab65-625b3346d896",
  "model": "alibaba:qwen-image@layered",
  "positivePrompt": "Decompose the supplied museum preparation-lab photograph into coherent, independently editable RGBA layers while preserving the original composition, framing, scale, lighting, color, texture, and photographic appearance. Create a clean foreground layer for the complete Triceratops skull replica and its dark steel rolling mount, retaining every horn edge, opening, frill contour, support bar, wheel, and natural contact detail with accurate transparency and no halos. Separate the cast shadow beneath the mount where practical. Group the stainless-steel workbench, archival specimen crates, folded moving blanket, and rolling tool cart into logical midground layers. Preserve the pale-gray wall and sealed concrete floor as a continuous, complete background layer suitable for removal or replacement. Reconstruct any background areas hidden behind extracted objects so the background remains visually continuous when foreground and midground layers are disabled. Maintain exact alignment between all layers and avoid changing, redesigning, adding, or removing visible content.",
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/1eeaaf35-4b58-437b-9d2e-7620875d0c7f.jpg"
    ]
  }
}
```