---
title: Seedream 5.0 Pro | Runware Docs
url: https://runware.ai/docs/models/bytedance-seedream-5-0-pro
description: Flagship image model for controlled editing, multi-reference generation, and layer-aware visual workflows
---
# Seedream 5.0 Pro

![Seedream 5.0 Pro](https://assets.runware.ai/covers/bytedance-seedream-5-0-pro.jpg)

Seedream 5.0 Pro is ByteDance's flagship image generation and editing model for teams that need stronger control than prompt-only workflows provide. It supports text-to-image and reference-guided image editing with up to 10 input images, and is designed for precise local changes using coordinates, masks, bounding boxes, sketches, and material or color instructions. The model also supports multi-image fusion, advanced layer separation, and strong multilingual rendering, making it well suited to design, marketing, e-commerce, and storyboard-driven content production.

- **Status**: live
- **ID**: `bytedance:seedream@5.0-pro`
- Try in Playground
- **Creator**: ByteDance
- **Release Date**: July 8, 2026
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.0481 from, per run · ~1m 32s per request

**Rates**

- 1.5K · per run: `$0.0481`
- 2K · per run: `$0.0963`
- Input imageper input image · beyond 1: `$0.00321`

**4 example generations**

- [text-to-image](https://runware.ai/docs/models/bytedance-seedream-5-0-pro/examples#example-edwardian-station-vfx-clean-plate) · 1536×1024: `$0.0481` (~1m 20s)
- [text-to-image](https://runware.ai/docs/models/bytedance-seedream-5-0-pro/examples#example-bioluminescent-algae-culture-kit-packaging) · 1536×1024: `$0.0481` (~1m 20s)
- [reference-to-image](https://runware.ai/docs/models/bytedance-seedream-5-0-pro/examples#example-museum-astrolabe-catalog-cleanup): `$0.0514` (~2m 11s)
- [reference-to-image](https://runware.ai/docs/models/bytedance-seedream-5-0-pro/examples#example-urban-beekeeper-linocut-profile-avatar): `$0.0514` (~1m 44s)

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` or `resolution`.

---

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

---

Inside `settings`, `background` cannot be used with `layerDecomposition`.

---

When `settings.background` is `transparent`, `outputFormat` is limited to `PNG`, `WEBP` and `inputs.referenceImages` is limited to 1 item.

---

When `settings.layerDecomposition` is `true`, `width/height` and `positivePrompt` cannot be used.

---

When `settings.layerDecomposition` is not `true`, `positivePrompt` is required.

---

When `settings.layerDecomposition` is `true`, `inputs.referenceImages` is limited to 1 item.

---

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

## Notes

**Supported dimensions:** `width` and `height` must have a total pixel area between **921,600** and **4,624,220**, with an aspect ratio between 1:16 and 16:1. Defaults to **1024 × 1024** if not specified.

**Recommended dimensions:**

| Aspect Ratio | 1K | 2K |
| --- | --- | --- |
| 1:1 | 1024 × 1024 | 2048 × 2048 |
| 4:3 | 1152 × 864 | 2368 × 1776 |
| 3:4 | 864 × 1152 | 1776 × 2368 |
| 16:9 | 1424 × 800 | 2816 × 1584 |
| 9:16 | 800 × 1424 | 1584 × 2816 |
| 3:2 | 1248 × 832 | 2496 × 1664 |
| 2:3 | 832 × 1248 | 1664 × 2496 |
| 21:9 | 1568 × 672 | 3136 × 1344 |

**Layer decomposition pricing:** with `settings.layerDecomposition`, the base image and each returned layer are billed as separate output images. The model decides how many layers to return, up to 16, so a single request can cost up to 17 times the per-image price.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-taskuuid)

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

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-outputformat)

- **Type**: `string`
- **Default**: `JPG`

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

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-webhookurl)

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

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

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

**Learn more** (1 resource):

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

### [uploadEndpoint](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-uploadendpoint)

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

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-safety-checkcontent)

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

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

### [ttl](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-numberresults)

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

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

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

### [referenceImages](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `10`
- **Area (each) (with layerDecomposition true)**: `0.26 MP or more`

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/bytedance-seedream-5-0-pro#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bytedance:seedream@5.0-pro`

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/bytedance-seedream-5-0-pro#request-positiveprompt)

- **Type**: `string`
- **Required**: conditional — Required when settings.layerDecomposition is not true
- **Min**: `2`
- **Max**: `3000`

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/bytedance-seedream-5-0-pro#request-width)

- **Type**: `integer`
- **Min**: `256`
- **Max**: `16383`

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/bytedance-seedream-5-0-pro#request-height)

- **Type**: `integer`
- **Min**: `256`
- **Max**: `16383`

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/bytedance-seedream-5-0-pro#request-resolution)

- **Type**: `string`

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

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

**Settings**

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

### [background](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-settings-background)

- **Path**: `settings.background`
- **Type**: `string`
- **Default**: `opaque`

Background handling in generated images.

**Allowed values**:

- `opaque` Solid background, no transparency.
- `transparent` Transparent background. The reference image must contain transparent pixels.

### [layerDecomposition](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-settings-layerdecomposition)

- **Path**: `settings.layerDecomposition`
- **Type**: `boolean`

Enables layer decomposition of the reference image. The layers are returned in `outputs.layers` next to the base image. `outputFormat` applies to the base image only, layers are always PNG.

### [thinking](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-settings-thinking)

- **Path**: `settings.thinking`
- **Type**: `boolean`
- **Default**: `true`

Enables thinking mode for improved quality at the cost of increased generation time.

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-advancedfeatures-watermark)

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

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

**Text watermark**:

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

**Image watermark**:

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

**Tiled watermark**:

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

#### [text](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-advancedfeatures-watermark-image)

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

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

#### [displayPosition](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-advancedfeatures-watermark-displayposition)

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

Watermark position.

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

#### [opacity](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-advancedfeatures-watermark-opacity)

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

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#request-advancedfeatures-watermark-bgcolor)

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

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-tasktype)

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

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-taskuuid)

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

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

### [imageUUID](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-imagedatauri)

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

Data URI of the output image.

### [NSFWContent](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-cost)

- **Type**: `float`

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

### [outputs](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs)

- **Path**: `outputs.layers`
- **Type**: `object (9 properties)`

Generated output artifacts.

#### [layers](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers)

- **Path**: `outputs.layers`
- **Type**: `array of objects (8 properties)`
- **Max items**: `16`

Layers decomposed from the reference image, returned when `settings.layerDecomposition` is enabled. Each layer is a PNG with transparency.

##### [description](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers-description)

- **Path**: `outputs.layers.description`
- **Type**: `string`

Description of the layer content.

##### [boundingBox](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers-boundingbox)

- **Path**: `outputs.layers.boundingBox`
- **Type**: `object (2 properties)`

Position of the layer on the base image, as \[left, top, right, bottom\].

##### [absolute](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers-boundingbox-absolute)

- **Path**: `outputs.layers.boundingBox.absolute`
- **Type**: `array of integers`
- **Min items**: `items: 4`

Coordinates in pixels of the base image.

##### [normalized](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers-boundingbox-normalized)

- **Path**: `outputs.layers.boundingBox.normalized`
- **Type**: `array of integers`
- **Min**: `0`
- **Max**: `1000`
- **Min items**: `items: 4`

Coordinates on a 0 to 1000 scale.

##### [name](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers-name)

- **Path**: `outputs.layers.name`
- **Type**: `string`

Short name of the layer.

##### [url](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers-url)

- **Path**: `outputs.layers.url`
- **Type**: `string`
- **Required**: true
- **Format**: `uri`

URL of the output image.

##### [uuid](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers-uuid)

- **Path**: `outputs.layers.uuid`
- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

##### [zIndex](https://runware.ai/docs/models/bytedance-seedream-5-0-pro#response-outputs-layers-zindex)

- **Path**: `outputs.layers.zIndex`
- **Type**: `integer`
- **Required**: true
- **Min**: `1`

Stacking order of the layer.

## Examples

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

![Edwardian Station VFX Clean Plate](https://assets.runware.ai/examples/bytedance-seedream-5-0-pro/321c42ab-a57c-40a0-9286-a4bfb56fd251.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "d64ef638-3093-46ce-8156-0676d56b3f35",
  "model": "bytedance:seedream@5.0-pro",
  "positivePrompt": "Finished photorealistic VFX clean plate for an Edwardian period drama: the grand concourse of a British railway terminus circa 1908, completely empty after the digital removal of cast, crew, cameras, cables, markers, barriers, litter, and modern fixtures. Seamlessly reconstructed encaustic-tile floor, uninterrupted platform edges, complete carved oak benches, intact glazed brick walls, and naturally continued architectural details wherever objects would have obscured them. Vast iron-and-glass arched roof, ornate station clock, brass lamps, dark green painted ironwork, distant steam locomotive beneath a soft veil of white vapor. Low winter sunlight passes through smoky glass and creates long geometric shadows and warm amber highlights across the cool blue-gray interior. Wide eye-level establishing shot with strong central perspective, layered depth, restrained period-authentic palette, crisp masonry and metal detail, subtle filmic grain, realistic lens behavior and exposure. Hushed, atmospheric, historically credible, production-ready environment plate with generous unobstructed foreground and no people, modern signage, vehicles, equipment, or text overlays.",
  "width": 1536,
  "height": 1024,
  "settings": {
    "thinking": true
  }
}
```

---

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

![Bioluminescent Algae Culture Kit Packaging](https://assets.runware.ai/examples/bytedance-seedream-5-0-pro/c54163ae-37f0-48f9-80ba-f130f301c857.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "77d8d06e-380a-46ed-90c3-ade08edacc11",
  "model": "bytedance:seedream@5.0-pro",
  "positivePrompt": "Create a polished landscape packaging-design presentation for a real educational marine-biology product: a home bioluminescent algae culture kit branded “LUMA TIDE.” Show one premium folding carton standing upright in three-quarter view, one carton lying flat behind it, and three small glass culture vials with coordinated labels arranged beside the box. The packaging must be the clear subject, not an advertisement or lifestyle scene.\n\nArt direction: contemporary scientific packaging fused with antique oceanographic illustration. Deep midnight-navy uncoated paperboard, luminous cyan and sea-glass turquoise inks, restrained warm ivory typography, and a single fluorescent coral-red accent. Wrap the carton in an intricate engraved illustration of dinoflagellates, microscopic cell structures, rippling currents, lunar phases, and tiny plankton forms. Use precise hairline diagrams, small registration marks, specimen numbers, and a clean modular grid. Add selective glossy varnish to the cyan organisms so they catch the light, subtle embossed wave lines, crisp folded edges, realistic paper texture, and a crescent-shaped die-cut window revealing one glowing blue vial inside.\n\nFront-panel hierarchy with clear, correctly spelled lettering: large “LUMA TIDE”; beneath it “BIOLUMINESCENT ALGAE CULTURE KIT”; small line “PYROCYSTIS LUNULA”; coral-red circular badge “GLOWS WHEN SWIRLED”; lower line “GROW • OBSERVE • REST • REPEAT.” Side panel includes the headings “LIGHT CYCLE,” “TEMPERATURE,” and “CARE GUIDE” with simple scientific icons. Vial labels read “LUMA TIDE,” “LIVE CULTURE,” and “10 mL.” Keep all other copy minimal and unobtrusive; do not add slogans or unrelated text.\n\nCompose as a high-end packaging portfolio image on a matte warm-gray studio surface, 3:2 landscape. Upright carton slightly left of center, vials forming a measured diagonal toward the lower right, flat carton adding layered depth in the background. Soft directional light from upper left, cool blue glow emanating through the die-cut window and vials, gentle long shadows, controlled highlights on glass, excellent edge definition, realistic print production details, premium product visualization, front and side panels legible, no hands, no people, no website interface, no advertising headline, no extra props.",
  "width": 1536,
  "height": 1024,
  "settings": {
    "thinking": true
  }
}
```

---

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

![Museum Astrolabe Catalog Cleanup](https://assets.runware.ai/examples/bytedance-seedream-5-0-pro/a0ae3c29-a9e8-4dc2-a5fd-2abb365b1323.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "6c20aade-f1eb-47b2-a1d4-4f908d226bcd",
  "model": "bytedance:seedream@5.0-pro",
  "positivePrompt": "Create one finished museum collection-catalog photograph by editing and combining the two references. Use reference image 1 as the authoritative source for the astrolabe: preserve its exact shape, proportions, orientation, pierced geometry, rotating components, engraved Arabic inscriptions, scratches, oxidation, brass color, and authentic age patina. Remove the blue-gloved hand, accession card, color chart, both archival-foam wedges, and the original beige work surface. Where the foam wedges overlap the plain outer rim, generatively reconstruct only the small hidden rim sections through physically consistent continuation, symmetry, metal thickness, patina, and edge wear; do not invent new inscriptions or ornament. Place the isolated astrolabe naturally onto the charcoal-gray conservation paper and slate setting from reference image 2. Match the second reference's restrained overhead studio lighting and subtle background gradient while retaining believable metallic highlights and adding a delicate contact shadow beneath the instrument. Keep the artifact centered with generous even catalog margins in the landscape frame. The result should look like meticulous high-end cultural-heritage documentation: neutral color management, crisp fine engraving, realistic aged metal, clean edges, no retouching halos, no leftover tools or supports, no extra objects, no captions, no added text, no logo, and no display case reflections.",
  "settings": {
    "thinking": true
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/e30ff7de-3cdf-45e7-80e3-d633f5910528.jpg",
      "https://assets.runware.ai/assets/inputs/045af872-30fd-454d-beae-6f54a1e25612.jpg"
    ]
  }
}
```

---

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

![Urban Beekeeper Linocut Profile Avatar](https://assets.runware.ai/examples/bytedance-seedream-5-0-pro/3183c73f-c0db-4435-ab5d-fb1f4bf34218.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "29e5412f-953c-408a-9f85-b88c8ad6ab4c",
  "model": "bytedance:seedream@5.0-pro",
  "positivePrompt": "Create a finished square profile avatar for a professional urban beekeeper. Use reference image 1 as the identity reference: preserve the woman’s recognizable facial structure, short silver-streaked hair, round tortoiseshell glasses, warm eyes, and calm, capable expression. Translate her portrait into the handcrafted linocut visual language of reference image 2, including bold carved contours, slight ink irregularities, warm cream paper grain, deep charcoal shadows, and restrained mustard-yellow accents. Show a centered head-and-shoulders portrait in a practical dark work jacket, facing slightly three-quarters while maintaining direct eye contact. Integrate the second reference coherently: place a simplified honeybee motif behind one shoulder and a subtle arc of geometric rooftop hives and city rooflines around the lower background, like an emblem rather than a literal scene. Keep the face dominant, readable, and flattering at small icon size. Strong silhouette, balanced negative space, circular-crop-safe composition, warm expert personality, artisanal editorial finish. No words, initials, logos, watermark, photorealistic background, extra people, veil, or full beekeeping suit.",
  "settings": {
    "thinking": true
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/bd275b62-ab73-432b-a574-b56c92871c50.jpg",
      "https://assets.runware.ai/assets/inputs/203b31f5-9b1f-4fe7-b000-9d50e669a75e.jpg"
    ]
  }
}
```