---
title: Seedream 4.0 | Runware Docs
url: https://runware.ai/docs/models/bytedance-seedream-4-0
description: High speed 4K AI image generation and editing model
---
# Seedream 4.0

![Seedream 4.0](https://assets.runware.ai/covers/bytedance-seedream-4-0.jpg)

Seedream 4.0 is ByteDance’s multimodal image model for fast 2K to 4K generation. It supports text prompts, image editing with natural language, and multi image reference. It maintains style consistency across batches and handles bilingual Chinese and English workflows.

- **Status**: live
- **ID**: `bytedance:5@0`
- Try in Playground
- **Creator**: ByteDance
- **Release Date**: September 9, 2025
- **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint

## Pricing

$0.03 per run · ~1m 14s per request

**4 example generations**

- [sequential-images](https://runware.ai/docs/models/bytedance-seedream-4-0/examples#example-peatland-firefighting-game-concept-sequence) · 2304×1728: `$0.03` (~2m 20s)
- [sequential-images](https://runware.ai/docs/models/bytedance-seedream-4-0/examples#example-subsea-cable-repair-thumbnail-series) · 2304×1728: `$0.03` (~1m 50s)
- [reference-to-image](https://runware.ai/docs/models/bytedance-seedream-4-0/examples#example-coastal-restoration-textile-wall-print) · 1728×2304: `$0.03` (~39s)
- [text-to-image](https://runware.ai/docs/models/bytedance-seedream-4-0/examples#example-aerospace-acoustic-engineer-executive-portrait) · 3024×1296: `$0.03` (~16s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1K (1:1)` | `1024x1024` |
| `2K (1:1)` | `2048x2048` |
| `2K (4:3)` | `2304x1728` |
| `2K (3:4)` | `1728x2304` |
| `2K (16:9)` | `2560x1440` |
| `2K (9:16)` | `1440x2560` |
| `2K (3:2)` | `2496x1664` |
| `2K (2:3)` | `1664x2496` |
| `2K (21:9)` | `3024x1296` |
| `4K (1:1)` | `4096x4096` |
| `4K (4:3)` | `4608x3456` |
| `4K (3:4)` | `3456x4608` |
| `4K (16:9)` | `5120x2880` |
| `4K (9:16)` | `2880x5120` |
| `4K (3:2)` | `4992x3328` |
| `4K (2:3)` | `3328x4992` |
| `4K (21:9)` | `6048x2592` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/bytedance-seedream-4-0#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/bytedance-seedream-4-0#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-4-0#request-outputtype)

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

Image output type.

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

### [outputFormat](https://runware.ai/docs/models/bytedance-seedream-4-0#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-4-0#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-4-0#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-4-0#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-4-0#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-4-0#request-safety)

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

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/bytedance-seedream-4-0#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-4-0#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-4-0#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/bytedance-seedream-4-0#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-4-0#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `14`

List of reference images (UUID, URL, Data URI, or Base64).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/bytedance-seedream-4-0#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `bytedance:5@0`

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-4-0#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **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-4-0#request-width)

- **Type**: `integer`
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/bytedance-seedream-4-0#request-height)

- **Type**: `integer`
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [seed](https://runware.ai/docs/models/bytedance-seedream-4-0#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

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

**Settings**

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

### [maxSequentialImages](https://runware.ai/docs/models/bytedance-seedream-4-0#request-settings-maxsequentialimages)

- **Path**: `settings.maxSequentialImages`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `15`

Maximum number of sequential images to generate. Combined total of reference images plus sequential images cannot exceed 15. The model may generate fewer images than requested depending on prompt complexity.

**Features**

Standalone addons and post-processing features.

### [watermark](https://runware.ai/docs/models/bytedance-seedream-4-0#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-4-0#request-advancedfeatures-watermark-text)

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

Watermark text.

#### [image](https://runware.ai/docs/models/bytedance-seedream-4-0#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-4-0#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-4-0#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-4-0#request-advancedfeatures-watermark-fontcolor)

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

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/bytedance-seedream-4-0#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-4-0#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-4-0#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-4-0#response-imageuuid)

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

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/bytedance-seedream-4-0#response-imageurl)

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

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/bytedance-seedream-4-0#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/bytedance-seedream-4-0#response-imagedatauri)

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

Data URI of the output image.

### [seed](https://runware.ai/docs/models/bytedance-seedream-4-0#response-seed)

- **Type**: `integer`

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

### [NSFWContent](https://runware.ai/docs/models/bytedance-seedream-4-0#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/bytedance-seedream-4-0#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)

![Aerospace Acoustic Engineer Executive Portrait](https://assets.runware.ai/examples/bytedance-seedream-4-0/be76e37b-e696-4d7d-bba9-e10b10d0f1e2.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e98d767c-0d5a-4efd-bbea-91ac5bbba5d3",
  "model": "bytedance:5@0",
  "positivePrompt": "Create a premium ultrawide environmental executive portrait of Dr. Mina Park, a Korean American aerospace acoustic engineer in her early 50s, photographed inside a full-scale anechoic testing chamber. She has a composed, quietly confident expression, intelligent direct eye contact, natural shoulder-length black hair with subtle silver strands, and realistic age detail. Dress her in a sharply tailored graphite blazer over a muted mineral-blue blouse, understated silver stud earrings, no visible logos. Frame her chest-up on the right third of the 3024x1296 composition, shoulders angled slightly toward camera, face and eyes unmistakably the focal point. The chamber’s repeating charcoal acoustic wedges recede across the left side in strong geometric perspective, creating sophisticated negative space suitable for a corporate website masthead without adding any text. Include restrained evidence of her field in the background: a suspended precision microphone array, a small section of matte aircraft fuselage test panel, fine measurement cables, all credible and secondary. Cinematic but authentic commercial photography: a large soft key light from camera left shaping the face, gentle cool fill, narrow warm rim light separating her dark blazer from the acoustic foam, subtle cyan instrument indicators deep in the room. Palette of graphite, slate blue, soft skin tones, and restrained amber highlights. Crisp eyes, lifelike skin texture and pores, natural makeup, accurate hands only if visible, polished yet approachable demeanor. Shallow-to-moderate depth of field with the nearest chamber wedges softly resolving into texture; clean tonal separation, controlled highlights, rich blacks without crushed detail. Shot with medium-format editorial clarity and an 85mm portrait character, realistic optical falloff, no exaggerated wide-angle distortion. A single finished professional photograph, refined aerospace-industry art direction, calm, precise, modern, credible, no lettering, no watermark, no interface, no collage.",
  "width": 3024,
  "height": 1296
}
```

---

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

![Coastal Restoration Textile Wall Print](https://assets.runware.ai/examples/bytedance-seedream-4-0/32ff0f70-e055-4a79-8f0f-c39300081e27.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "a82ce7c0-e7fe-42a0-a0e6-c5b9f4094901",
  "model": "bytedance:5@0",
  "positivePrompt": "Create a finished portrait-format print-on-demand wall artwork translating coastal wetland restoration into contemporary fiber art. Use reference image 1 strictly for the composition: retain its recognizable top-down branching tidal-creek structure, the placement of the main channel, fine tributaries, islands, and negative spaces, while simplifying minor photographic detail into elegant organic shapes. Use reference image 2 strictly for the material language and palette: draw from its faded indigo, slate blue, unbleached linen, irregular sashiko stitching, layered cotton patches, frayed edges, and subtle age variation; do not copy its original patch layout. Render the marsh landforms as hand-cut indigo fabric fields and the waterways as exposed warm linen, with delicate stitched contour lines following the flow of the channels. Add restrained raised seams and visible fibers for convincing tactile depth. Refined Japanese mending aesthetic interpreted through contemporary environmental design, calm and meditative, asymmetrical but balanced, crisp enough for large-format printing. Flat frontal artwork, edge-to-edge composition with a narrow natural-linen border, no frame, no room mockup, no typography, no labels, no map symbols, no people, no buildings.",
  "width": 1728,
  "height": 2304,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/9be247dc-cad8-4473-8dc3-1774c7602a59.jpg",
      "https://assets.runware.ai/assets/inputs/b74b5e7b-5e4b-4ef8-9db3-5423df5d5b01.jpg"
    ]
  }
}
```

---

### sequential-images (sequential-images)

![Peatland Firefighting Game Concept Sequence](https://assets.runware.ai/examples/bytedance-seedream-4-0/9b954b19-f21a-4c97-9633-9e66d8a17193.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "244f56df-ed24-458b-9876-4efd3a64f7d4",
  "model": "bytedance:5@0",
  "positivePrompt": "Create a coherent sequence of landscape concept-art images for a real tactical firefighting game set in a remote Scottish peat bog. Use the reference image as the exact visual anchor. Preserve the same Mire Tender vehicle in every output: low cream-colored cab, vermilion safety panels, broad rubber tracks, articulated water cannon, rear hose reels, amber hazard lights, mud and soot wear. Preserve the same operator: a middle-aged woman in dark green waterproof overalls and a white rescue helmet. Maintain identical proportions, equipment placement, costume, facial identity, and art direction throughout.\n\nAcross the sequential outputs, show a clear operational progression: the Mire Tender first scouting through cold rain and shallow floodwater; discovering thin blue smoke escaping from cracks in black peat; deploying heat probes and long hoses while the operator surveys the ground; confronting an advancing orange fire line beneath violent wind; pumping water into a cut trench as steam engulfs the tracks; and finally resting at dawn beside a contained, smoking burn scar with new rain falling. Each output should depict one distinct moment rather than a collage, storyboard sheet, or split panel.\n\nArt direction: premium indie strategy-game concept art, bold hand-painted gouache with restrained screen-print grain, simplified angular silhouettes, crisp vehicle design, expressive weather, and believable peatland ecology. Palette dominated by charcoal gray, wet black peat, muted moss green, cold blue rain, cream paint, and vivid vermilion-orange emergency accents. Cinematic wide compositions with strong depth layers, low horizons, distant wind-bent grasses, drainage channels, and sparse utility poles. Keep the mood tense, practical, and grounded rather than fantastical. Clearly readable gameplay spaces and hazards, realistic firefighting procedures, no monsters, no futuristic weapons, no lettering, no logos, no interface, no borders.",
  "width": 2304,
  "height": 1728,
  "providerSettings": {
    "bytedance": {
      "maxSequentialImages": 4
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/3eefc13f-b8dc-4731-bf8f-b04c77a7a814.jpg"
    ]
  }
}
```

---

### sequential-images (sequential-images)

![Subsea Cable Repair Thumbnail Series](https://assets.runware.ai/examples/bytedance-seedream-4-0/3c626ec1-17ef-439e-a2ad-c00ffaf2394f.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "04f73ba8-5688-45b8-bc6d-de1dcb79dc36",
  "model": "bytedance:5@0",
  "positivePrompt": "Create a coherent sequence of six separate landscape video-thumbnail images for a premium engineering documentary about an emergency transoceanic fiber-optic cable repair. Use the supplied reference image as the strict visual anchor: preserve the exact yellow work-class ROV, its proportions, black protective frame, twin manipulator arms, lamps and recognizable equipment in every image. Show a clear chronological progression, one scene per output: 1) the ROV descending beneath a cable-repair ship into dark open water, 2) searching above a rugged abyssal plain with scanning lights, 3) discovering the severed black cable half-buried in sediment, 4) carefully lifting and cleaning the cable with its manipulators, 5) installing a cylindrical pressure-rated splice housing, 6) hovering above the secured repaired cable as its lights recede into the blue. Each output must be a single finished thumbnail, never a collage, contact sheet, split screen or storyboard panel. Cinematic factual realism, plausible subsea engineering, immense ocean scale, cold midnight-blue and cyan palette punctuated by the ROV's safety yellow and a few warm work lights, suspended marine particles, volumetric beams, crisp machinery, rich blacks, controlled highlights. Strong foreground subject and immediate visual hierarchy at small thumbnail size. Use varied camera angles while maintaining continuity: wide descent, overhead search, low seabed reveal, intimate manipulator close-up, heroic three-quarter repair view, quiet concluding wide shot. Keep a clean area of dark water in the upper-right third for optional editorial titling, but include no words, logos, interface elements, borders or watermarks.",
  "width": 2304,
  "height": 1728,
  "providerSettings": {
    "bytedance": {
      "maxSequentialImages": 4
    }
  },
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/29509b4b-bf73-4d3c-a1dc-27e61ea20200.jpg"
    ]
  }
}
```