Seedream-4.0 Image Generation

Generate high-quality images using Seedream 4.0 model

POST /v1/images/generations

cURL

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-4-0",
    "prompt": "A cute panda playing in a bamboo forest",
    "size": "1:1",
    "n": 1,
    "metadata": {
      "resolution": "2K"
    }
  }'

200

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "doubao-seedream-4-0",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}

• Seedream 4.0 high-quality image generation model
• Use model parameter to select doubao-seedream-4-0 model
• Supports text-to-image generation
• Async task management, query results by task ID

Important Change: For better performance and cost control, we no longer support passing base64 image data directly in image_urls. Please use the Upload Image API first to upload images and get URLs, then call this endpoint.

Authorizations

Authorization · string · required

All endpoints require Bearer Token authentication

Get your API Key from the API Key Management Page

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

model · string · default: "doubao-seedream-4-0" · required

Image generation model name

Example: "doubao-seedream-4-0"

prompt · string · required

Text description for image generation

Maximum 1000 characters

size · string · default: "1:1"

Image aspect ratio

Supported aspect ratios:

• 1:1 - Square (default)
• 4:3 - Landscape 4:3
• 3:4 - Portrait 3:4
• 16:9 - Landscape widescreen
• 9:16 - Portrait vertical
• 3:2 - Landscape 3:2
• 2:3 - Portrait 2:3
• 21:9 - Ultra-wide
• 9:21 - Ultra-tall
• auto - Auto-match reference image ratio (requires image_urls)

n · integer · default: 1

Number of images to generate

Range: 1-15 (minimum 1, maximum 15)

Default: 1

Note:

• The actual number of images that can be generated is affected by both this parameter and the number of input reference images. The total of reference images + generated images must be ≤ 15
• Must enter a plain number (e.g., 1), do not use quotes or it will cause an error

Charges will be pre-deducted based on the number

image_urls · string[]

Reference image URL list for image-to-image or image editing

⚠️ URL format only (base64 no longer supported)

• Publicly accessible image URL (http:// or https://)
• Example: https://example.com/image.jpg
• You can use the Upload Image API to upload local images and get URLs

Limitations:

• Maximum 10 images
• Image formats: jpeg, png
• Aspect ratio (width/height) range: [1/3, 3]
• Width and height (px) > 14
• Single image size: not exceeding 10MB
• Total pixels: not exceeding 6000×6000 px

metadata · object

Channel-specific parameters for Seedream 4.0 model advanced configuration

Show metadata properties

metadata.resolution · string · default: "2K"

Image resolution

Supported resolutions:

• 1K - Basic resolution
• 2K - Standard resolution (default)
• 4K - High definition

Resolution reference sizes:

Resolution	1:1 Size	16:9 Size
1K	1024x1024	1280x720
2K	2048x2048	2560x1440
4K	4096x4096	5404x3040

metadata.optimize_prompt_options · object

Prompt optimization options

Properties:

• mode (string): Optimization mode
  • standard: Standard mode, generates higher quality with longer processing time (default)
  • fast: Fast mode, generates content in shorter time with regular quality

Example:

"optimize_prompt_options": { "mode": "standard" }

metadata.sequential_image_generation · string · default: "disabled"

Sequential image generation mode (Doubao-specific feature)

Controls whether to generate multiple images:

• disabled: Disable sequential mode, generates only 1 image (default)
• auto: Enable sequential mode, can generate multiple images

Usage Notes:

• ✅ Set n: 3 or use sequential_image_generation: "auto" + max_images: 3
• ✅ Supports text-to-image: up to 15 images from text prompt only
• ✅ Supports image-to-image: provide image_urls to generate multiple variations
• ⚠️ When n > 1, it will automatically be set to auto

Note:

• Total reference images + generated images must be ≤ 15

metadata.sequential_image_generation_options · object

Sequential image generation options

Available when sequential_image_generation is set to auto

Properties:

• max_images (integer): Specify the number of images to generate, Range: 1-15

Example:

"sequential_image_generation_options": { "max_images": 3 }

metadata.watermark · boolean · default: true

Whether to add a watermark to the generated image

• true: Add watermark (default)
• false: No watermark

Response

id · string

Unique task identifier for status queries

object · string

Object type, always generation.task

model · string

Model name used

status · string

Task status

• queued - Queued for processing
• in_progress - Processing
• completed - Successfully completed
• failed - Failed

progress · integer

Task progress percentage (0-100)

created_at · integer

Task creation timestamp (Unix timestamp)

metadata · object

Task metadata

cURL

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-4-0",
    "prompt": "A cute panda playing in a bamboo forest",
    "size": "1:1",
    "n": 1,
    "metadata": {
      "resolution": "2K"
    }
  }'

200

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "doubao-seedream-4-0",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}