Skip to main content

​
Overview

Video generation is asynchronous. You submit a request, receive a task ID and poll_url, then poll for the result.
For the most reliable polling behavior, follow the exact poll_url returned by the create request.

​
Request Body

​
model
string
default:"sora-2"
Video model ID. API default is sora-2. See the Video Generation Guide for the current model matrix and supported capabilities.
​
prompt
string
required
Text description of the video to generate.
​
image_url
string
Publicly accessible URL of the starting image for image-to-video (I2V) generation. For best cross-model compatibility, prefer image_url.
​
image
string
Inline image as a data URL (for example, data:image/jpeg;base64,...). Supported by compatible models, but image_url provides the broadest compatibility across video models.
​
duration
integer
Video duration in seconds (model-dependent).
​
aspect_ratio
string
Aspect ratio (e.g., 16:9, 9:16, 1:1).
​
resolution
string
Video resolution (e.g., 1080p, 720p).
​
fps
integer
Frames per second (1-120).
​
negative_prompt
string
What to avoid in the video generation.
​
seed
integer
Random seed for reproducible generation.
​
cfg_scale
number
Classifier-free guidance scale (0-20).
​
motion_strength
number
Motion intensity (0-1).
​
start_image
string
URL of starting frame image.
​
end_image
string
URL of ending frame image.
​
user
string
A unique identifier for the end-user.

​
Response

​
task_id
string
Unique task identifier for polling.
​
poll_url
string
Recommended polling URL for this task. Use this exact path when checking status.
​
status
string
Initial status: pending.
​
model
string
Model used.
curl -X POST "https://api.lemondata.cc/v1/videos/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2",
    "prompt": "A cat walking through a garden, cinematic lighting",
    "operation": "text-to-video",
    "duration": 4,
    "aspect_ratio": "16:9"
  }'

{
  "task_id": "video_abc123",
  "poll_url": "/v1/tasks/video_abc123",
  "status": "pending",
  "model": "sora-2",
  "created_at": 1706000000
}

​
Image to Video

response = requests.post(
    "https://api.lemondata.cc/v1/videos/generations",
    headers={"Authorization": "Bearer sk-your-api-key"},
    json={
        "model": "hailuo-2.3-fast",
        "prompt": "The scene begins from the provided image and adds gentle natural motion.",
        "operation": "image-to-video",
        "image_url": "https://example.com/image.jpg",
        "duration": 6,
        "aspect_ratio": "16:9"
    }
)

​
Keyframe Control

Use start_image and end_image to control the first and last frames (supported by Vidu Q2 Pro): 
response = requests.post(
    "https://api.lemondata.cc/v1/videos/generations",
    headers={"Authorization": "Bearer sk-your-api-key"},
    json={
        "model": "viduq2-pro",
        "prompt": "Smooth transition from day to night",
        "operation": "start-end-to-video",
        "start_image": "https://example.com/day.jpg",
        "end_image": "https://example.com/night.jpg",
        "duration": 5,
        "resolution": "720p",
        "aspect_ratio": "16:9"
    }
)

​
Available Models

The model list is updated frequently. For the latest available models and pricing, visit the Models page.
For a complete guide with capability comparisons and usage examples, see the Video Generation Guide.

​
Sora (OpenAI)

ModelCapabilities
sora-2T2V (default)
sora-2-proT2V, higher quality
sora-2-charactersT2V, character-focused

​
Kling (Kuaishou)

ModelCapabilities
kling-v2.6-proT2V, latest gen
kling-v2.6-stdT2V, fast
kling-v2.5-turbo-stdT2V, turbo tier
kling-v2.1-masterT2V, I2V, master quality
kling-v2.1-proT2V, I2V
kling-videoT2V, I2V
kling-video-extendVideo extension
kling-video-o1-proT2V, O1 reasoning
kling-effectsVisual effects

​
Veo (Google)

ModelCapabilities
veo2T2V
veo3.1T2V, I2V, keyframe
veo3.1-proT2V, I2V, keyframe, professional
veo3.1-4kT2V, I2V, keyframe, 4K output
veo3.1-fastT2V, I2V, keyframe, fast
veo3T2V, I2V, previous gen

​
Seedance (ByteDance)

ModelCapabilities
seedance-2-0T2V, I2V, keyframe, extension, editing
seedance-1-5-proT2V, I2V
seedance-1-0-proT2V, I2V
seedance-1-0-lite-t2vT2V, lightweight
seedance-1-0-lite-i2vI2V, lightweight

​
Other Providers

ModelProviderCapabilities
hailuo-2.3MiniMaxT2V, I2V
hailuo-2.3-proMiniMaxT2V, I2V, higher quality
hailuo-2.3-fastMiniMaxI2V, fast tier
wan-2.6AlibabaT2V
wan2.6-i2vAlibabaI2V
runwayml-gen4-turbo-5RunwayI2V (5s)
runwayml-gen4-turbo-10RunwayI2V (10s)
luma-video-apiLumaT2V
luma-video-extend-apiLumaVideo extension
viduq3-proShengshuT2V, I2V, keyframe
viduq3-turboShengshuT2V, I2V, keyframe, turbo tier
viduq2-proShengshuI2V, keyframe, reference
grok-video-3xAIT2V
higgsfield-turboHiggsfieldT2V