Skip to main content
POST
https://llm.ai-nebula.com
/
v1
/
video
/
generations
Create Video Generation Task
curl --request POST \
  --url https://llm.ai-nebula.com/v1/video/generations \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "image": "<string>",
  "duration": 123,
  "resolution": "<string>",
  "aspect_ratio": "<string>"
}
'
{
  "id": "video_task_abc123",
  "object": "video.generation",
  "status": "pending",
  "model": "sora-2",
  "created": 1234567890,
  "prompt": "A cat running on grass, sunny day, cinematic quality",
  "duration": 5,
  "resolution": "1080p",
  "aspect_ratio": "16:9"
}

​
Introduction

Submit video generation task, supporting text-to-video and image-to-video. Returns task ID for status polling.

​
Authentication

​
Authorization
string
required
Bearer Token, e.g. Bearer sk-xxxxxxxxxx

​
Request Parameters

​
model
string
required
Model name, e.g. sora-2, veo-2
​
prompt
string
required
Video description text
​
image
string
Reference image for image-to-video (base64 or URL)
​
duration
integer
default:"5"
Video duration in seconds: 5, 10, 15
​
resolution
string
default:"1080p"
Resolution: 720p, 1080p, 4k
​
aspect_ratio
string
default:"16:9"
Aspect ratio: 16:9, 9:16, 1:1

​
cURL Example

curl https://llm.ai-nebula.com/v1/video/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-XyLy**************************mIqSt" \
  -d '{
    "model": "sora-2",
    "prompt": "A cat running on grass, sunny day, cinematic quality",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

​
Python Example

import requests

url = "https://llm.ai-nebula.com/v1/video/generations"
headers = {
    "Authorization": "Bearer sk-XyLy**************************mIqSt",
    "Content-Type": "application/json"
}

data = {
    "model": "sora-2",
    "prompt": "A cat running on grass, sunny day, cinematic quality",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
}

response = requests.post(url, headers=headers, json=data)
task = response.json()
print(f"Task ID: {task['id']}")

{
  "id": "video_task_abc123",
  "object": "video.generation",
  "status": "pending",
  "model": "sora-2",
  "created": 1234567890,
  "prompt": "A cat running on grass, sunny day, cinematic quality",
  "duration": 5,
  "resolution": "1080p",
  "aspect_ratio": "16:9"
}

​
Image-to-Video Example

import base64

with open("reference.jpg", "rb") as f:
    image_base64 = base64.b64encode(f.read()).decode()

data = {
    "model": "sora-2",
    "prompt": "Make the person in the image smile and wave",
    "image": f"data:image/jpeg;base64,{image_base64}",
    "duration": 5
}

response = requests.post(url, headers=headers, json=data)

​
Task Status

StatusDescription
pendingQueued
processingGenerating
completedDone
failedFailed

​
Notes

  • Video generation is async, poll for status after submission
  • Generation time depends on duration and resolution, typically 1-5 minutes
  • Download video from returned URL when completed
  • Requires requests: pip install requests