Skip to main content
POST
/
bytedance
/
seedream-4.5-t2i
curl --request POST \
  --url https://api.modellix.ai/api/v1/bytedance/seedream-4.5-t2i \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "Majestic dragon flying over medieval castle, epic fantasy art"
}
'
{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-ghi789",
    "model_id": "model-123",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-ghi789"
    }
  }
}

Authorizations

​
Authorization
string
header
required

API Key authentication. Format: Bearer YOUR_API_KEY.

Body

application/json
​
prompt
string
required

Image description text, supports Chinese and English. We recommend keeping the prompt under 600 words. Excessively long prompts may scatter information, causing the model to overlook details and focus only on major elements, which can result in missing details in the generated image.

Required string length: 1 - 10000
Example:

"Majestic dragon flying over medieval castle, epic fantasy art"

​
size
string
default:2048x2048

Image size in format 'widthxheight'. Minimum pixels: 2560x1440 (approx 2K) = 3,686,400. Range: Total pixels 3,686,400 to 16,777,216, aspect ratio 1/16 to 16

Example:

"2048x2048"

​
sequential_image_generation
enum<string>
default:disabled

Batch generation mode

Available options:
auto,
disabled
Example:

"auto"

​
sequential_image_generation_max_images
integer
default:5

Maximum number of images for batch generation

Required range: 1 <= x <= 15
Example:

5

​
optimize_prompt_mode
enum<string>
default:standard

Prompt optimization mode. Only 'standard' mode is supported for 4.5

Available options:
standard
Example:

"standard"

Response

Task submitted successfully

​
code
integer
required

Response code, 0 indicates success

Example:

0

​
message
string
required

Response message

Example:

"success"

​
data
object
required

Detailed data about the submitted asynchronous task.