curl --request POST \
  --url https://api.powertokens.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "dola-seedream-5-0-pro-260628",
  "prompt": "Convert the image to Studio Ghibli animation style",
  "image": "https://example.com/input.jpg",
  "size": "2K"
}
'

{
  "model": "<string>",
  "created": 123,
  "data": [
    {
      "url": "<string>",
      "b64_json": "<string>",
      "size": "<string>"
    }
  ],
  "usage": {
    "generated_images": 123,
    "output_tokens": 123,
    "total_tokens": 123
  }
}

{
  "error": {
    "message": "Request body format error or invalid field values",
    "type": "invalid_request_error",
    "code": "bad_request_body",
    "param": ""
  }
}

{
  "error": {
    "message": "Invalid token",
    "type": "api_error",
    "code": "access_denied",
    "param": ""
  }
}

{
  "error": {
    "message": "Insufficient account quota, please try again later",
    "type": "api_error",
    "code": "insufficient_user_quota",
    "param": ""
  }
}

{
  "error": {
    "message": "Internal service processing failed, please try again later",
    "type": "api_error",
    "code": "gen_relay_info_failed",
    "param": ""
  }
}

BytePlus

Seedream 5.0 Pro Image-to-Image

Supported models include dola-seedream-5-0-pro-260628. This document covers Image-to-Image and Multi-Image Reference Generation scenarios. Public fields include model, prompt, image, size, response_format, and watermark.

Model Capabilities

Generate single image (does not support sequential_image_generation)
Multi-Image Generation: Input multiple reference images (2-10) + text prompt to generate a single image.
Single Image Generation: Input single reference image + text prompt to generate a single image.
Sequential image generation, web search, and streaming output are not supported.

POST

images

generations

curl --request POST \
  --url https://api.powertokens.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "dola-seedream-5-0-pro-260628",
  "prompt": "Convert the image to Studio Ghibli animation style",
  "image": "https://example.com/input.jpg",
  "size": "2K"
}
'

{
  "model": "<string>",
  "created": 123,
  "data": [
    {
      "url": "<string>",
      "b64_json": "<string>",
      "size": "<string>"
    }
  ],
  "usage": {
    "generated_images": 123,
    "output_tokens": 123,
    "total_tokens": 123
  }
}

{
  "error": {
    "message": "Request body format error or invalid field values",
    "type": "invalid_request_error",
    "code": "bad_request_body",
    "param": ""
  }
}

{
  "error": {
    "message": "Invalid token",
    "type": "api_error",
    "code": "access_denied",
    "param": ""
  }
}

{
  "error": {
    "message": "Insufficient account quota, please try again later",
    "type": "api_error",
    "code": "insufficient_user_quota",
    "param": ""
  }
}

{
  "error": {
    "message": "Internal service processing failed, please try again later",
    "type": "api_error",
    "code": "gen_relay_info_failed",
    "param": ""
  }
}

Authorizations

Authorization

string

header

required

Pass Authorization: Bearer <token> in the request header.

Body

application/json

model

enum<string>

required

Image generation model name. Supported models include dola-seedream-5-0-pro-260628 (Seedream 5.0 pro, supports interactive editing, does not support sequential image generation).

Available options:

dola-seedream-5-0-pro-260628

prompt

string

required

Prompt for image generation, supports Chinese and English. It is recommended not to exceed 300 Chinese characters or 600 English words. Too many words may disperse information, causing the model to ignore details and focus only on key points, resulting in missing elements in the image.

Example:

"Dynamic close-up editorial portrait with sharp gaze, sculptural hat, rich color blocking."

image

required

Input image information, supports URL or Base64 encoding. Supports single or multiple image inputs.

Image URL: Ensure the image URL is accessible.
Base64 encoding: Follow the format data:image/<image_format>;base64,<Base64_encoded>. Note that <image_format> should be lowercase, e.g., data:image/png;base64,<base64_image>.

Notes:

Single image requirements:
- Format: jpeg, png, webp, bmp, tiff, gif, heic, heif
- Aspect ratio (width/height) range: [1/16, 16]
- Width/height (px) > 14
- Size: no more than 30MB
- Total pixels: no more than 6000×6000 = 36000000 px (limit on the product of width and height, not individual values)
Seedream 5.0 pro supports up to 10 reference images.

size

string

default:2K

Specifies the size of the generated image, supports specifying resolution level (e.g., 2K) or width and height pixel values (e.g., 2048x2048), which cannot be mixed.

dola-seedream-5-0-pro-260628 (Seedream 5.0 pro) Supports the following two methods, which cannot be mixed:

Method 1 (Recommended): Specify resolution level and describe aspect ratio, shape, or purpose in the prompt. The model determines the final image size.
- Default: 2K
- Options: 1K, 2K
Method 2: Specify width and height pixel values (widthxheight).
- Total pixel range: [1280x720 (921600), 2048x2048×1.1025 (4624220)]
- Aspect ratio range: [1/16, 16]

Note: When using Method 2, both total pixel range and aspect ratio range must be satisfied. Total pixels refers to the product of width and height, not individual values.

Valid example: 2048x1024 Total pixels 2048x1024=2097152, within [921600, 4624220]; aspect ratio 2048/1024=2, within [1/16, 16], so valid.

Invalid example: 512x512 Total pixels 512x512=262144, below 921600 minimum, so invalid.

Resolution to pixel reference values when using Method 1 (not limited to these standard values, common ones listed):

Resolution	Aspect Ratio	Pixel Dimensions
1K	1:1	1024x1024
	4:3	1152x864
	3:4	864x1152
	16:9	1424x800
	9:16	800x1424
	3:2	1248x832
	2:3	832x1248
	21:9	1568x672
2K	1:1	2048x2048
	4:3	2368x1776
	3:4	1776x2368
	16:9	2816x1584
	9:16	1584x2816
	3:2	2496x1664
	2:3	1664x2496
	21:9	3136x1344

Example:

"2K"

response_format

enum<string>

default:url

Specifies the return format of the generated image. Supported options:

url: Returns image download URL; valid for 24 hours after generation.
b64_json: Returns image data as Base64 encoded JSON.

Available options:

url,

b64_json

watermark

boolean

default:true

Whether to add watermark to generated images.

false: No watermark.
true: Add "AI Generated" watermark at bottom right corner.

Response

Success, returns the image generation result.

model

string

Model ID (model name-version) used for this request.

created

integer<int64>

Unix timestamp (seconds) of creation.

data

object[]

List of generated images.

Show child attributes

usage

object

Usage information for this request.

Show child attributes

Seedream 5.0 Pro Text-to-Image

Image Creation

Chat Models

Image Models

Video Models

Audio Models

asset library

Seedream 5.0 Pro Image-to-Image

Authorizations

Body

Response