Skip to main content
POST
/
v1
/
videos
/
generations
curl --request POST \
  --url https://gccai.heqingsong.uk/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "wan2.7",
    "prompt": "A coastal road at sunset, slow-motion camera push-in, cinematic feel",
    "resolution": "1080P",
    "duration": 8,
    "size": "16:9"
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01J9HA7JPQ9A0Z6JZ3V8M9W6PZ"
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://gccai.heqingsong.uk/llms.txt

Use this file to discover all available pages before exploring further.

curl --request POST \
  --url https://gccai.heqingsong.uk/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "wan2.7",
    "prompt": "A coastal road at sunset, slow-motion camera push-in, cinematic feel",
    "resolution": "1080P",
    "duration": 8,
    "size": "16:9"
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01J9HA7JPQ9A0Z6JZ3V8M9W6PZ"
    }
  ]
}

​
Authorization

​
Authorization
string
required
All API endpoints require Bearer Token authenticationGet your API Key:Visit the API Key Management Page to get your API KeyAdd it to the request header:
Authorization: Bearer YOUR_API_KEY

​
Mode Routing

wan2.7 is a unified entry for text-to-video and image-to-video. The backend automatically determines the mode based on the incoming parameters. Both modes are billed identically:
ConditionRoutes ToMode Description
Any of image_urls / image_with_roles / video_urls is providedImage-to-VideoFirst-frame / First-last frame / Video continuation
None of the above parameters providedText-to-VideoGenerate video purely from text description

​
Request Parameters

​
model
string
required
Video generation model name, fixed as wan2.7
​
prompt
string
Video content description, up to 5000 characters
  • Text-to-Video mode (when no image/video provided): required
  • Image-to-Video mode: optional, but recommended to guide camera movement and actions
Example: "A cat chasing butterflies on the grass, bright sunshine, slow motion"
​
image_urls
array<string>
Image URL array. Providing it automatically enters Image-to-Video mode
  • 1 image: first-frame to video
  • 2 images: first-last frame to video (1st = first frame, 2nd = last frame)
Use either this or image_with_roles
image_urls conflicts with audio_url; they cannot be provided at the same time
​
image_with_roles
array<object>
Image array with roles, alternative to image_urls, used to precisely specify the role of each imageFields for each object:
  • url (string): image URL (supports http/https)
  • role (string): image role, first_frame / last_frame, default first_frame
Example:
[
  { "url": "https://cdn.example.com/start.jpg", "role": "first_frame" },
  { "url": "https://cdn.example.com/end.jpg", "role": "last_frame" }
]
image_with_roles conflicts with audio_url; they cannot be provided at the same time
​
video_urls
array<string>
Video URL array. Providing it enters video continuation mode (only the 1st video is used)
video_urls conflicts with audio_url; they cannot be provided at the same time
Video constraints:
  • Format: mp4, mov
  • Duration: 2–10s
  • Resolution: width and height in the range [240, 4096] pixels
  • Aspect ratio: 1:8 – 8:1
  • File size: up to 100MB
​
negative_prompt
string
Negative prompt describing unwanted content, up to 500 charactersExample: "blurry, distorted, low quality"
​
resolution
string
default:"1080P"
Video resolutionOptions:
  • 720P - Standard
  • 1080P - High definition (default)
​
duration
integer
default:"5"
Video duration (seconds)Supported range: 2 ~ 15 secondsDefault: 5
​
size
string
default:"16:9"
Aspect ratio, only effective in Text-to-Video mode (when no image/video provided)Supported formats:
  • 16:9 - Landscape widescreen (default)
  • 9:16 - Portrait
  • 1:1 - Square
  • 4:3 - Landscape
  • 3:4 - Portrait
This parameter is ignored in Image-to-Video mode; the aspect ratio is determined automatically by the input image
​
audio_url
string
Custom audio URL
  • Text-to-Video mode: used as background music
  • Image-to-Video mode: used as driving audio, synchronized with on-screen actions
Format: wav / mp3, duration 2-30 seconds, file size ≤ 15MB
audio_url conflicts with video_urls, image_urls, and image_with_roles; they cannot be provided at the same time
​
prompt_extend
boolean
default:"true"
Whether to enable intelligent prompt rewritingSignificantly improves results for short prompts, but increases processing timeDefault: true
​
watermark
boolean
default:"false"
Whether to add “AI Generated” watermark to the generated video
  • true: add watermark
  • false: no watermark (default)
​
seed
integer
Seed integer used to control the randomness of generated contentValue range: integer ≥0
  • For identical requests, the model generates different results when receiving different seed values (e.g., omitting seed)
  • For identical requests, the model generates similar results when receiving the same seed value, but exact consistency is not guaranteed

​
Response

​
code
integer
Response status code, 200 on success
​
data
array
Response data array

​
Use Cases

​
Case 1: Text-to-Video (Simplest Request)

{
  "model": "wan2.7",
  "prompt": "A coastal road at sunset, slow-motion camera push-in, cinematic feel"
}

​
Case 2: Text-to-Video (Full Parameters)

{
  "model": "wan2.7",
  "prompt": "A cat chasing butterflies on the grass, bright sunshine, slow motion",
  "negative_prompt": "blurry, distorted, low quality",
  "resolution": "1080P",
  "duration": 8,
  "size": "16:9",
  "audio_url": "https://cdn.example.com/bgm.mp3",
  "prompt_extend": true,
  "watermark": false,
  "seed": 42
}

​
Case 3: First-Frame to Video

{
  "model": "wan2.7",
  "prompt": "The character slowly stands up and walks toward the camera",
  "image_urls": ["https://cdn.example.com/person.jpg"],
  "resolution": "1080P",
  "duration": 8
}

​
Case 4: First-Last Frame to Video

{
  "model": "wan2.7",
  "prompt": "The camera pans slowly from the beach to the mountaintop",
  "image_urls": [
    "https://cdn.example.com/beach.jpg",
    "https://cdn.example.com/mountain.jpg"
  ],
  "resolution": "1080P",
  "duration": 10
}
With 2 images: the 1st is the first frame, the 2nd is the last frame. You can also use image_with_roles for precise specification.

​
Case 5: Video Continuation

{
  "model": "wan2.7",
  "prompt": "Continue walking forward, camera follows",
  "video_urls": ["https://cdn.example.com/clip.mp4"],
  "resolution": "1080P",
  "duration": 8
}

​
Case 6: Image + Driving Audio

{
  "model": "wan2.7",
  "prompt": "The character moves to the rhythm of the music",
  "image_urls": ["https://cdn.example.com/dancer.jpg"],
  "audio_url": "https://cdn.example.com/beat.mp3",
  "resolution": "1080P",
  "duration": 8
}

​
Mode Selection Guide

RequirementRecommended Approach
Generate video from text onlyPass only prompt (no image/video)
Make an image “come alive”Pass 1 image to image_urls
Control start and end framesPass 2 images to image_urls (first + last)
Extend an existing videoPass video to video_urls
Make image move to musicPass image + audio_url
Query Task ResultsVideo generation is an async task that returns a task_id upon submission. Use the Get Task Status endpoint to query generation progress and results.