seedream-5.0-pro

Seedream 5.0 Pro text-to-image and image-to-image API.

Use doubao-seedream-5-0-pro-260628 with the same synchronous endpoint for text-to-image and image-to-image generation.

Select the Special-Ns resource group for specific content requests.

This model does not support grouped image generation, web search, or streaming. Do not send sequential_image_generation, sequential_image_generation_options, tools, or stream.

Text to image

Create an image

POST /v1/images/generations

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro-260628",
    "prompt": "Create a premium product key visual for a smart speaker",
    "size": "2K",
    "response_format": "url",
    "output_format": "png",
    "watermark": false,
    "optimize_prompt_options": { "mode": "standard" }
  }'

model · string · required

Must be doubao-seedream-5-0-pro-260628.

prompt · string · required

The image-generation prompt.

size · string

1K, 2K, or an explicit pixel size such as 2048x1024. Explicit dimensions must meet the documented total-pixel and aspect-ratio limits.

response_format · string · default: "url"

url or b64_json. URLs are temporary and should be saved promptly.

output_format · string · default: "jpeg"

png or jpeg.

watermark · boolean · default: true

Whether to add an AI-generated watermark.

optimize_prompt_options.mode · string · default: "standard"

Prompt optimization mode. Only standard is supported.

Image to image

Create an image

POST /v1/images/generations

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "doubao-seedream-5-0-pro-260628",
    "prompt": "Add a ceramic coffee cup in the marked area while preserving the composition",
    "image": ["https://example.com/reference.png"],
    "size": "2K",
    "response_format": "url",
    "output_format": "png",
    "watermark": false
  }'

model · string · required

Must be doubao-seedream-5-0-pro-260628.

prompt · string · required

The editing instruction. Coordinate edits can use point or bbox tags.

image · string | string[] · required

An image URL, Base64 data URI, or up to 10 reference images.

size · string

1K, 2K, or an explicit pixel size.

response_format · string · default: "url"

url or b64_json. URLs are temporary and should be saved promptly.

output_format · string · default: "jpeg"

png or jpeg.

watermark · boolean · default: true

Whether to add an AI-generated watermark.

optimize_prompt_options.mode · string · default: "standard"

Prompt optimization mode. Only standard is supported.

Supported formats are jpeg, png, webp, bmp, tiff, gif, heic, and heif. Each image must be at most 30 MB, have an aspect ratio in [1/16, 16], have both dimensions at least 14 px, and contain no more than 36,000,000 pixels.

Size limits

Resolution tiers are 1K and 2K. For explicit widthxheight values, the total pixel range is 1280x720 through 2048x2048x1.1025, and the aspect ratio range is [1/16, 16].

Headers

Authorization · string · required

Bearer authentication in the form Bearer <token>.

Content-Type · string · default: "application/json" · required

Request body format.

Response

200

{
  "model": "doubao-seedream-5-0-pro-260628",
  "created": 1775029815,
  "data": [{
    "url": "https://example.com/generated-image.png",
    "output_format": "png",
    "size": "2048x2048"
  }],
  "usage": {
    "generated_images": 1,
    "input_images": 0,
    "output_tokens": 16384,
    "total_tokens": 16384
  }
}

model · string

The model ID used for the request. Upstream responses may return a provider-side model name.

created · integer

Creation time as a Unix timestamp in seconds.

data · object[]

Generated images.

data[].url · string

Temporary image URL when response_format is url.

data[].b64_json · string

Base64 image data when response_format is b64_json.

data[].output_format · string

Generated image format.

data[].size · string

Generated image dimensions.

data[].error · object

Per-image error information when one generated image fails.

data[].error.code · string

Per-image error code.

data[].error.message · string

Per-image error message.

usage.generated_images · integer

Number of generated images.

usage.input_images · integer

Number of input images.

usage.output_tokens · integer

Output token count.

usage.total_tokens · integer

Total token count.

error · object

Request-level error information.

error.code · string

Request-level error code.

error.message · string

Request-level error message.

Error responses

400

The request body is invalid or contains an unsupported parameter value.

{
  "error": {
    "code": "invalid_request_error",
    "message": "Invalid request parameter"
  }
}

401

The API key is missing or invalid.

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid API key"
  }
}

429

The request exceeded the applicable rate limit.

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Rate limit exceeded"
  }
}