Skip to main content
POST
/
v3
/
seedream-3-0-txt2img
Seedream Text-to-Image 3.0
curl --request POST \
  --url https://api.highwayapi.ai/v3/seedream-3-0-txt2img \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "prompt": "<string>",
  "model": "<string>",
  "response_format": "<string>",
  "size": "<string>",
  "seed": 123,
  "guidance_scale": 123,
  "watermark": true
}
'
{
  "image_urls": [
    "<string>"
  ],
  "binary_data_base64": [
    "<string>"
  ]
}
Seedream 3.0 is an advanced text-to-image model that can efficiently and quickly generate high-quality images from text prompts.
Currently, only the model version seedream-3-0-t2i-250415 is supported for Seedream 3.0.

​
Request Headers

​
Content-Type
string
required
Enum value: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
prompt
string
required
The text prompt used to generate the image.
​
model
string
The model ID or inference Endpoint ID used for this request. Currently, only Seedream 3.0’s seedream-3-0-t2i-250415 is supported.
​
response_format
string
Specifies the format of the image returned in the response. The default value is url.
Supported values:
  • "url": Returns a downloadable JPEG image link.
  • "b64_json": Returns a base64-encoded image JSON string.
​
size
string
Specifies the size of the generated image (pixels, width x height), in the range [512x512, 2048x2048]. The default value is 1024x1024.
Recommended aspect ratios and resolutions:
  • 1024x1024 (1:1)
  • 864x1152 (3:4)
  • 1152x864 (4:3)
  • 1280x720 (16:9)
  • 720x1280 (9:16)
  • 832x1248 (2:3)
  • 1248x832 (3:2)
  • 1512x648 (21:9)
​
seed
integer
The seed value that controls the randomness of image generation. Value range: [-1, 2147483647]. If not specified, it will be generated automatically. To reproduce the same result, use the same seed. The default value is -1.
​
guidance_scale
number
Controls how well the output image matches the input prompt. The higher the value, the less freedom the model has and the stronger the relevance to the prompt. Value range: [1, 10]. The default value is 2.5.
​
watermark
boolean
Whether to add a watermark to the generated image. The default value is true.
  • false: Do not add a watermark
  • true: Add an “AI generated” watermark in the bottom-right corner of the image

​
Response Information

​
image_urls
string[]
An array of links to the generated images. When response_format is set to "url", this array contains downloadable links to the generated images.
​
binary_data_base64
string[]
An array of Base64-encoded image data. When response_format is set to "b64_json", this array contains Base64-encoded image JSON strings.