curl --request POST \
--url https://api.powertokens.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "seedream-4-5-251128",
"prompt": "A cute corgi running on grass, sunny day, realistic style",
"size": "2048x2048",
"response_format": "url"
}
'{
"created": 123,
"data": [
{
"url": "<string>",
"b64_json": "<string>",
"size": "<string>",
"error": {
"code": "<string>",
"message": "<string>"
}
}
],
"metadata": {}
}For Seedream image models.
Supported models include seedream-5-0-260128, seedream-4-5-251128, and seedream-4-0-250828. This document covers model, prompt, image, size, seed, sequential_image_generation, sequential_image_generation_options, response_format, and watermark. Generated file links are typically temporary and should be downloaded promptly.
curl --request POST \
--url https://api.powertokens.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "seedream-4-5-251128",
"prompt": "A cute corgi running on grass, sunny day, realistic style",
"size": "2048x2048",
"response_format": "url"
}
'{
"created": 123,
"data": [
{
"url": "<string>",
"b64_json": "<string>",
"size": "<string>",
"error": {
"code": "<string>",
"message": "<string>"
}
}
],
"metadata": {}
}Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Image generation model name. Supported models include seedream-5-0-260128, seedream-4-5-251128, and seedream-4-0-250828.
seedream-5-0-260128, seedream-4-5-251128, seedream-4-0-250828 Image generation prompt. Recommended max 300 Chinese characters or 600 English words.
Reference images. The public Seedream models currently documented here support 1-14 reference images.
Output image size.
"2048x2048"
Response format.
url, b64_json Random seed. Supported by some Seedream models. Range [-1, 2147483647].
Sequential image generation switch. auto for auto mode, disabled for single image. Supported by the Seedream models currently documented here.
auto, disabled Sequential image generation options. Effective only when sequential_image_generation=auto.
Show child attributes
Whether to add watermark.
Success, returns image generation result.