Skip to main content
POST
/
api
/
v3
/
contents
/
generations
/
tasks
Image to Video
curl --request POST \
  --url https://gptproto.com/api/v3/contents/generations/tasks \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "<string>",
  "prompt": "<string>",
  "loop": true,
  "duration": "<string>",
  "dimension": "<string>",
  "seed": 123,
  "logo": {}
}'
{
  "error": {
    "message": "Invalid request parameters",
    "type": "invalid_request_error",
    "code": "invalid_parameters"
  }
}

​
Overview

This endpoint provides image to video functionality using Volcengine official format.

​
Authentication

This endpoint requires authentication using a Bearer token with your API key.
​
Authorization
string
required
Your API key in the format: Bearer YOUR_API_KEY

​
Request Body

​
model
string
default:"seedance-1-0-pro-250528"
required
The model identifier for video generation (endpoint ID)
​
prompt
string
required
Video generation prompt describing the desired video content
​
loop
boolean
default:"false"
Whether to generate a looping video
​
duration
string
default:"5s"
Video duration. Options: 5s, 10s
​
dimension
string
default:"768:768"
Video resolution. Options: 768:768, 768:1280, 1280:768
​
seed
integer
Random seed for reproducible results (range: 1-2147483647)
Watermark configuration with position and url

​
Request Example

curl -X POST "https://gptproto.com/api/v3/contents/generations/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedance-1-0-pro-250528",
  "prompt": "A serene landscape with mountains and a lake at sunset",
  "loop": false,
  "duration": "5s",
  "dimension": "768:768",
  "seed": -1
}'

​
Response

​
Success
200
Successful response with task creation
{
  "code": 0,
  "message": "Success",
  "data": {
    "task_id": "task_xxxxxxxxxx",
    "status": "pending"
  }
}
Note: This is a task-based API. After creating the task, you need to poll the task status using the task_id to get the final video URL.

​
Error Responses

{
  "error": {
    "message": "Invalid request parameters",
    "type": "invalid_request_error",
    "code": "invalid_parameters"
  }
}