---
title: Qwen-Image | Runware Docs
url: https://runware.ai/docs/models/alibaba-qwen-image
description: Qwen-Image high fidelity text aware image generation model
---
# Qwen-Image

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

Qwen-Image is a 20B parameter vision language model from Alibaba Cloud. It focuses on precise text conditioned image generation and supports complex Chinese or English typography. It also enables accurate image editing workflows that need layout control and strong prompt following.

- **Status**: live
- **ID**: `runware:108@1`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: August 4, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.0045 from, per run · ~7s per request

**Measured runs**

- 512×512 · steps 20: `$0.0045` (~3s)
- 1024×1024 · steps 20: `$0.0119` (~8s)
- 1024×1024 · steps 40: `$0.0208` (~15s)
- 2048×2048 · steps 20: `$0.0625` (~43s)

**4 example generations**

- [image-to-image](https://runware.ai/docs/models/alibaba-qwen-image/examples#example-pediatric-lab-journey-learning-panel) · 1280×768: `$0.0026` (~6s)
- [inpaint](https://runware.ai/docs/models/alibaba-qwen-image/examples#example-coastal-eco-thriller-series-poster) · 768×1024: `$0.0026` (~7s)
- [expand](https://runware.ai/docs/models/alibaba-qwen-image/examples#example-meteorological-observatory-linocut-wall-art) · 1024×768: `$0.0026` (~6s)
- [text-to-image](https://runware.ai/docs/models/alibaba-qwen-image/examples#example-subsea-documentary-square-expansion) · 1024×1024: `$0.0032` (~5s)

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)

## Compatibility & Validation

When `strength` or `inputs.maskImage` is provided, `inputs.seedImage` is required.

---

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

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

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

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

Image output type.

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

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

- **Type**: `boolean`

Include task cost in the response.

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

- **Path**: `acceleratorOptions.cacheEndStep`
- **Type**: `object (12 properties)`

Advanced caching mechanisms to speed up generation.

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

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

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

TeaCache acceleration for transformer-based models. Estimates step differences to skip redundant computations.

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

- **Path**: `acceleratorOptions.teaCacheDistance`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.5`

Controls the aggressiveness of the TeaCache feature. Lower values prioritize quality, higher values prioritize speed.

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

### [seedImage](https://runware.ai/docs/models/alibaba-qwen-image#request-inputs-seedimage)

- **Path**: `inputs.seedImage`
- **Type**: `string`

Image used as a starting point for the generation (UUID, URL, Data URI, or Base64).

**Learn more** (3 resources):

- [Image To Image: Seed Image The Foundation](https://runware.ai/docs/learn/image-to-image#seed-image-the-foundation) (learn)
- [Image Inpainting: Seed And Mask Image The Foundation](https://runware.ai/docs/learn/image-inpainting#seed-and-mask-image-the-foundation) (learn)
- [Image Outpainting: Seed Image The Starting Point](https://runware.ai/docs/learn/image-outpainting#seed-image-the-starting-point) (learn)

### [maskImage](https://runware.ai/docs/models/alibaba-qwen-image#request-inputs-maskimage)

- **Path**: `inputs.maskImage`
- **Type**: `string`

Image used to specify which areas of the input image should be edited (UUID, URL, Data URI, or Base64). White marks the area to edit, black is preserved.

**Learn more** (1 resource):

- [Image Inpainting: Seed And Mask Image The Foundation](https://runware.ai/docs/learn/image-inpainting#seed-and-mask-image-the-foundation) (learn)

**Core Parameters**

Primary parameters that define the task output.

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

- **Type**: `string`
- **Required**: true
- **Value**: `runware:108@1`

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#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#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)

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

- **Type**: `integer`
- **Required**: true
- **Min**: `256`
- **Max**: `2048`
- **Step**: `8`

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/alibaba-qwen-image#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `256`
- **Max**: `2048`
- **Step**: `8`

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)

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

- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`
- **Default**: `20`

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#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#request-cfgscale)

- **Type**: `float`
- **Min**: `1`
- **Max**: `20`
- **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)

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

- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.8`

Strength of the transformation. Lower values result in more influence from the original input.

**Learn more** (3 resources):

- [Image To Image: Strength The Transformation Intensity](https://runware.ai/docs/learn/image-to-image#strength-the-transformation-intensity) (learn)
- [Image Inpainting: Strength Controlling Transformation Intensity](https://runware.ai/docs/learn/image-inpainting#strength-controlling-transformation-intensity) (learn)
- [Image Outpainting: Strength Understanding The Critical Threshold](https://runware.ai/docs/learn/image-outpainting#strength-understanding-the-critical-threshold) (learn)

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

- **Type**: `integer`
- **Min**: `32`
- **Max**: `128`

Extra context pixels around the masked region during inpainting. The model zooms into the masked area with these additional pixels for better integration.

**Learn more** (1 resource):

- [Image Inpainting: Mask Margin Enhancing Detail](https://runware.ai/docs/learn/image-inpainting#mask-margin-enhancing-detail) (learn)

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

- **Path**: `outpaint.top`
- **Type**: `object (5 properties)`

Pixel extensions for each boundary direction of the source image. At least one direction is required.

**Learn more** (1 resource):

- [Image Outpainting: Outpaint Defining The Expansion](https://runware.ai/docs/learn/image-outpainting#outpaint-defining-the-expansion) (learn)

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

- **Path**: `outpaint.top`
- **Type**: `integer`
- **Min**: `0`
- **Step**: `64`

Number of pixels to extend to the top.

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

- **Path**: `outpaint.bottom`
- **Type**: `integer`
- **Min**: `0`
- **Step**: `64`

Number of pixels to extend to the bottom.

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

- **Path**: `outpaint.left`
- **Type**: `integer`
- **Min**: `0`
- **Step**: `64`

Number of pixels to extend to the left.

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

- **Path**: `outpaint.right`
- **Type**: `integer`
- **Min**: `0`
- **Step**: `64`

Number of pixels to extend to the right.

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

- **Path**: `outpaint.blur`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `32`

Amount of blur to apply to the mask edge.

**Learn more** (1 resource):

- [Image Outpainting: Outpaint Defining The Expansion](https://runware.ai/docs/learn/image-outpainting#outpaint-defining-the-expansion) (learn)

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

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

LoRA model identifier.

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

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

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

- **Path**: `ultralytics.CFGScale`
- **Type**: `object (9 properties)`

Configuration object for Ultralytics face enhancement during generation. This feature uses face detection and inpainting to improve facial details in the same generation step, without requiring post-processing.

> [!NOTE]
> Face enhancement is available for Stable Diffusion 1.X, SDXL, and FLUX models. The system automatically detects faces and applies targeted refinement to improve quality while maintaining consistency with the overall generation.

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

- **Path**: `ultralytics.CFGScale`
- **Type**: `float`
- **Min**: `0`
- **Max**: `50`
- **Step**: `0.1`
- **Default**: `8`

Face refinement guidance scale.

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

- **Path**: `ultralytics.confidence`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.9`

Confidence threshold for detection.

#### [inpaintSize](https://runware.ai/docs/models/alibaba-qwen-image#request-ultralytics-inpaintsize)

- **Path**: `ultralytics.inpaintSize`
- **Type**: `integer`
- **Min**: `128`
- **Max**: `2048`
- **Default**: `1024`

Image size (in pixels) to use for each inpainting region. YOLO detects faces, crops the region, and scales it to this size before running diffusion. Set so most faces land in the 2–4× range of their original pixel size. Going beyond 8× may degrade identity resemblance.

#### [maskBlur](https://runware.ai/docs/models/alibaba-qwen-image#request-ultralytics-maskblur)

- **Path**: `ultralytics.maskBlur`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `100`
- **Default**: `5`

Mask feathering amount. Higher values create softer transitions between the enhanced face region and surrounding areas.

#### [maskPadding](https://runware.ai/docs/models/alibaba-qwen-image#request-ultralytics-maskpadding)

- **Path**: `ultralytics.maskPadding`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `20`
- **Default**: `5`

Padding around detected face in pixels. Expands the refinement area to include surrounding context like hair and neck.

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

- **Path**: `ultralytics.negativePrompt`
- **Type**: `string`

Negative prompt for detection.

#### [positivePrompt](https://runware.ai/docs/models/alibaba-qwen-image#request-ultralytics-positiveprompt)

- **Path**: `ultralytics.positivePrompt`
- **Type**: `string`

Positive prompt for detection.

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

- **Path**: `ultralytics.steps`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`
- **Default**: `20`

Number of face refinement steps.

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

- **Path**: `ultralytics.strength`
- **Type**: `float`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.3`

Refinement strength. Lower values preserve more of the original, higher values allow more aggressive reconstruction.

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

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

Text color in hex format.

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

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

UUID of the output image.

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

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

URL of the output image.

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

- **Type**: `string`

Base64-encoded image data.

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

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

Data URI of the output image.

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

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

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

![Subsea Documentary Square Expansion](https://assets.runware.ai/examples/alibaba-qwen-image/709dba93-fd8f-4050-b9ff-408ef615a07a.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "7c511821-5a93-4127-8e04-5eccddd6f488",
  "model": "runware:108@1",
  "positivePrompt": "Create the finished 1:1 square expansion of cinematic key art for a premium documentary about the subsea fiber-optic cables carrying global communications. The composition should feel seamlessly outpainted from an originally narrow vertical underwater image: preserve a strong central corridor containing a bright orange armored cable descending into a midnight-blue abyss, then extend the scene naturally to both sides with a vast dark seafloor, drifting marine snow, faint ridges of basalt, delicate glass sponges, and the distant work lights of a compact inspection ROV. A precise pool of cold cyan light reveals the cable and suspended particles while the outer edges fall into rich indigo-black water. Add restrained analog film grain, subtle halation around the ROV lamps, crisp documentary realism, and an elegant high-contrast editorial finish. Use the expanded side areas to create scale and negative space rather than adding competing subjects. Place the exact title “THE QUIET LINE” in large, clean, condensed white capitals across the upper third, perfectly spelled and sharply typeset. Directly beneath it, render the exact tagline “BENEATH EVERY MESSAGE” in smaller widely tracked white capitals. Keep all lettering level, legible, undistorted, and unobstructed. No other words, logos, credits, borders, interface elements, or mockup framing. Finished standalone documentary campaign artwork, tense, intelligent, technically credible, visually balanced for a square social release.",
  "width": 1024,
  "height": 1024
}
```

---

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

![Pediatric Lab Journey Learning Panel](https://assets.runware.ai/examples/alibaba-qwen-image/05bd8f8c-7660-45de-8f2e-3ace18daa709.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "5f8dc4d4-cefe-43d8-ad26-e6ab5be865ea",
  "model": "runware:108@1",
  "positivePrompt": "Transform the supplied photographic hospital model into a finished educational illustration for a pediatric hospital waiting area, aimed at children ages 7–11. Preserve the seed image’s recognizable four-room left-to-right cutaway layout, the placement of the people and equipment, and especially the continuous pneumatic-tube route. Replace the realistic miniature appearance with warm layered cut-paper collage, opaque gouache textures, rounded geometric shapes, subtle screen-printed dots, and crisp editorial diagram design.\n\nAt the top, set the exact title: “WHERE DOES MY SAMPLE GO?” in large, friendly, highly legible navy uppercase lettering. Organize the journey into four clearly separated but connected stages matching the source composition. Stage one shows a calm child seated beside a reassuring nurse while a small capped sample tube receives a barcode label. Stage two shows the sealed sample carrier entering the transparent blue pneumatic tube and moving through the corridor, with simple directional arrows. Stage three shows a diverse laboratory scientist safely handling the capped tube beside a compact analyzer, wearing gloves and a lab coat. Stage four shows a clinician sharing the result with the child and parent in a bright consultation room. Keep all medical actions accurate, gentle, clean, and non-frightening; no needle, exposed blood, distress, or invasive procedure.\n\nAdd these exact short labels and captions, with no other text:\n“1  LABEL”\n“A barcode keeps it matched to you.”\n“2  SEND”\n“A sealed carrier rides the tube.”\n“3  TEST”\n“Lab scientists check the sample.”\n“4  RESULTS”\n“Your care team gets the answer.”\n\nUse cobalt blue for the tube journey, with coral, apricot, mint, mustard yellow, warm cream, and deep navy throughout the rooms. Make the blue route visually continuous and easy for a child to follow from left to right. Include small friendly visual motifs such as stars, dots, and arrows only where they clarify the process. Balanced 1280x768 landscape layout, generous safe margins, accessible visual hierarchy, diverse characters with natural proportions and expressive but understated faces. Produce the standalone flat artwork itself, not a framed sign, room photograph, website, app interface, or presentation mockup. All specified lettering must be correctly spelled and clearly readable.",
  "negativePrompt": "Photorealism, 3D render, architectural model appearance, horror, visible needle, exposed blood, crying child, medical emergency, clutter, crowded composition, disconnected tube route, inaccurate extra limbs, illegible text, misspelled text, duplicate captions, logos, branding, QR codes, UI elements, frames, wall mockup, perspective-distorted typography.",
  "width": 1280,
  "height": 768,
  "strength": 0.7,
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/b2455271-8911-4600-bf6e-5200314baedc.jpg"
  }
}
```

---

### inpaint (inpaint)

![Coastal Eco-Thriller Series Poster](https://assets.runware.ai/examples/alibaba-qwen-image/2dc90989-a575-49b6-98b4-a807dfe94565.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "1788f48f-7b8d-4525-8fa4-3a89d998e9af",
  "model": "runware:108@1",
  "positivePrompt": "Edit the masked foreground subject only and substantially replace the entire person while preserving the surrounding poster exactly. Transform the generic poncho-clad figure into the lead character: a Chinese woman in her late forties, a senior marine disease investigator, standing confidently and looking directly into the camera. Give her a weathered, intelligent face, short windblown black hair threaded with gray, and a calm but guarded expression. She wears a practical cadmium-orange flotation work suit with reflective strips, dark waterproof gloves, and sea-stained rubber boots. In one hand she holds a compact transparent evidence case containing three sealed seawater sample vials; the case must remain within the masked silhouette. Add convincing damp fabric, salt residue, subtle fog moisture, and cool overcast light so she integrates naturally into the existing seawall scene. Maintain the original stance, scale, grounding, shadow direction, and full-body silhouette. Preserve every unmasked element without alteration: the pale fog, flat gray-green sea, wet concrete seawall, negative space, restrained chalk-white and kelp-green color grade, and the exact campaign typography. Keep the large Chinese title “赤潮线” at the top and the smaller English title “RED TIDE LINE” directly beneath it perfectly legible, correctly spelled, sharply typeset, and unchanged. The final result is polished prestige eco-thriller key art for a six-part streaming series, tense, intelligent, realistic, minimal, and ready for release.",
  "width": 768,
  "height": 1024,
  "strength": 0.85,
  "maskMargin": 64,
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/582ccfaa-64ae-43be-bf64-2cd474138c7c.jpg",
    "maskImage": "https://assets.runware.ai/assets/inputs/80e22933-f9dc-42e3-a756-a6a3108d1177.png"
  }
}
```

---

### expand (expand)

![Meteorological Observatory Linocut Wall Art](https://assets.runware.ai/examples/alibaba-qwen-image/666d57a0-0ef4-4774-a2df-4844f642be54.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "a7119d20-ee79-4d2e-bbd4-8c0e94f05036",
  "model": "runware:108@1",
  "positivePrompt": "Create a finished 1024x768 landscape illustration for print-on-demand wall art and desktop wallpaper by extending the supplied central image naturally beyond both horizontal edges. Preserve the meteorological observatory, its proportions and its central placement. Reveal the full breadth of a remote highland weather station: a low white 1960s concrete observatory with a shallow instrument dome, slender anemometer mast, rain gauge and Stevenson screen, surrounded by windswept grassland. Continue the gently undulating plateau across the left and right sides at the same horizon height, perspective and subject scale. Add sparse survey stakes, small basalt rocks and rhythmic clumps of grass in the expanded foreground, with no large new focal subject. Extend the long layered cloud bands seamlessly across the entire sky and keep the wind direction consistent in every grass tuft and cloud shape. Bold hand-pulled linocut and reduction woodcut aesthetic, visible carved gouges, irregular ink coverage, tactile ivory paper grain, simplified architectural geometry and crisp graphic silhouettes. Limited palette of deep indigo sky, warm ochre grass, muted sage accents, charcoal details and unprinted ivory highlights. Quiet, bracing, contemplative mood; balanced negative space; refined contemporary editorial printmaking; cohesive edge-to-edge composition suitable for a wide art print. Consistent flat directional light from the upper left, consistent shadows, textures and line weight throughout. No lettering, numbers, logos, frame, mat, mockup, people or interface elements.",
  "width": 1024,
  "height": 768,
  "outpaint": {
    "left": 256,
    "right": 256,
    "blur": 16
  },
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/b2e1370e-d2a3-42cc-8042-20fcc2738fe3.jpg"
  }
}
```