Skip to main content
POST
/
v1
/
videos
/
generations
curl --request POST \
  --url https://api.foxapi.cc/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "wan-2.7-image-to-video",
  "generation_type": "image-to-video",
  "image_urls": [
    "https://example.com/start.jpg"
  ],
  "prompt": "The camera slowly pushes in as the subject smiles",
  "duration": 5,
  "resolution": "1080p"
}
'
{
  "created": 1757165031,
  "id": "task-unified-1757165031-uyujaw3d",
  "model": "<string>",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 45
  },
  "type": "video"
}

Authorizations

​
Authorization
string
header
required

All APIs require Bearer Token authentication

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
string
default:wan-2.7-image-to-video
required

wan-2.7-image-to-video: Single-image-to-video, first-last-frame transition, video continuation

Example:

"wan-2.7-image-to-video"

​
generation_type
enum<string> | null

Generation mode

Options:

  • image-to-video -- Single image to video, exactly 1 image in image_urls
  • first-last-frame -- First-last-frame transition, exactly 2 images in image_urls
  • video-continuation -- Video continuation based on video_url

Notes:

  • Auto-inferred from input when not specified
Available options:
image-to-video,
first-last-frame,
video-continuation
Example:

"image-to-video"

​
image_urls
string[] | null

List of image URLs

Notes:

  • Image-to-video: provide 1 image
  • First-last-frame transition: provide 2 images, in order of first frame and last frame
Example:
["https://example.com/start.jpg"]
​
video_url
string | null

Public URL of the input video

Notes:

  • Used for video continuation mode
  • Cannot be provided together with image_urls
Example:

"https://example.com/clip.mp4"

​
prompt
string | null

Optional prompt for describing desired camera movement, subject actions, or scene transitions

Maximum string length: 5000
Example:

"The camera slowly pushes in as the subject smiles"

​
audio_url
string | null

Public URL of the driving audio

Notes:

  • Optional, supports WAV / MP3
  • Model generates background music automatically if not provided
Example:

"https://example.com/music.mp3"

​
duration
integer
default:5

Output video duration in seconds, supports integer values from 2-15

Required range: 2 <= x <= 15
Example:

2

​
resolution
enum<string>
default:1080p

Output video resolution

Options: 720p, 1080p

Available options:
720p,
1080p
Example:

"720p"

​
negative_prompt
string | null

Negative prompt describing content to avoid

Maximum string length: 500
Example:

"blurry, jitter"

​
seed
integer | null

Random seed for reproducibility

Required range: 0 <= x <= 2147483647
Example:

123

​
enable_prompt_expansion
boolean | null

Whether to enable prompt expansion. Uses model default if not specified

Example:

true

​
enable_safety_checker
boolean | null

Whether to enable safety checker. Uses model default if not specified

Example:

true

Response

Task created successfully

​
created
integer

Task creation timestamp

Example:

1757165031

​
id
string

Task ID

Example:

"task-unified-1757165031-uyujaw3d"

​
model
string

Actual model name used

​
object
enum<string>

Specific task type

Available options:
video.generation.task
​
progress
integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100
Example:

0

​
status
enum<string>

Task status

Available options:
pending,
processing,
completed,
failed
Example:

"pending"

​
task_info
object

Asynchronous task information

​
type
enum<string>

Task output type

Available options:
video
Example:

"video"