Image to Video

curl --request POST \
  --url https://api.maxapi.io/api/v1/task/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "grok-imagine/image-to-video",
  "callBackUrl": "https://example.com/webhook",
  "input": {
    "prompt": "Camera dollies in slowly, subject turns head",
    "imageUrls": [
      "https://example.com/portrait-a.jpg",
      "https://example.com/portrait-b.jpg"
    ],
    "duration": 10,
    "ratio": "9:16",
    "mode": "normal"
  }
}'

{
  "code": 0,
  "msg": "ok",
  "data": {
    "taskId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
  }
}

POST

api

task

submit

curl --request POST \
  --url https://api.maxapi.io/api/v1/task/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "grok-imagine/image-to-video",
  "callBackUrl": "https://example.com/webhook",
  "input": {
    "prompt": "Camera dollies in slowly, subject turns head",
    "imageUrls": [
      "https://example.com/portrait-a.jpg",
      "https://example.com/portrait-b.jpg"
    ],
    "duration": 10,
    "ratio": "9:16",
    "mode": "normal"
  }
}'

{
  "code": 0,
  "msg": "ok",
  "data": {
    "taskId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
  }
}

Generate a video guided by 1-5 reference images plus a text prompt.

Available Model

grok-imagine/image-to-video — $0.007 per second of generated video.

string

required

Must be grok-imagine/image-to-video.

string

Webhook callback URL.

object

required

Hide properties

string

required

Describe the motion and scene evolution.

array

required

1-5 reference image URLs (publicly accessible).

integer

One of 6, 10, 12, 15. Default: 6.

string

1:1, 16:9, or 9:16. Default: 9:16.

string

480p or 720p. Default: 720p.

string

fun, normal, spicy, or custom. Default: custom.

curl --request POST \
  --url https://api.maxapi.io/api/v1/task/submit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "grok-imagine/image-to-video",
  "callBackUrl": "https://example.com/webhook",
  "input": {
    "prompt": "Camera dollies in slowly, subject turns head",
    "imageUrls": [
      "https://example.com/portrait-a.jpg",
      "https://example.com/portrait-b.jpg"
    ],
    "duration": 10,
    "ratio": "9:16",
    "mode": "normal"
  }
}'

{
  "code": 0,
  "msg": "ok",
  "data": {
    "taskId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
  }
}

Up to 5 reference images. Images are fetched by the backend and forwarded upstream; make sure the URLs are publicly reachable.

Overview

Task API

Veo 3 Video

Nano Banana Image

Seedream Image

Grok Imagine (xAI)

GPT Image 2 (OpenAI)

Available Model

​Available Model

Available Model