Skip to main content
POST
/
v1
/
videos
/
generations
Kling O3 Reference-to-Video
curl --request POST \
  --url https://api.foxapi.cc/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "kling-o3-reference-to-video",
  "prompt": "Referencing the coastline composition of @Image1 and the character appearance of @Element1, generate a travel clip in morning mist",
  "resolution": "720p",
  "start_image_url": "https://picsum.photos/id/1015/1280/720.jpg",
  "image_urls": [
    "https://picsum.photos/id/1016/1280/720.jpg"
  ],
  "elements": [
    {
      "frontal_image_url": "https://picsum.photos/id/1027/768/1024.jpg",
      "reference_image_urls": [
        "https://picsum.photos/id/1028/768/1024.jpg"
      ]
    }
  ],
  "aspect_ratio": "16:9",
  "duration": 5
}
'
{
  "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:kling-o3-reference-to-video
required

kling-o3-reference-to-video: Video generation driven by reference images and subject elements

Example:

"kling-o3-reference-to-video"

​
prompt
string | null

Text prompt

Notes:

  • Maximum 2500 characters
  • Use @Image1 / @Element1 to reference materials
  • Mutually exclusive with multi_prompt
Maximum string length: 2500
Example:

"Referencing the coastline composition of @Image1 and the character appearance of @Element1, generate a travel clip in morning mist"

​
resolution
string
default:720p

Output resolution

Options:

  • 720p — 720P SD
  • 1080p — 1080P HD
  • 4k — Native 4K UHD (independent tier, billing not affected by generate_audio)
Example:

"720p"

​
generate_audio
boolean
default:false

Whether to generate accompanying audio

Example:

false

​
start_image_url
string | null

First-frame reference image URL

Example:

"https://picsum.photos/id/1015/1280/720.jpg"

​
end_image_url
string | null

End-frame image URL

Example:

"https://picsum.photos/id/1016/1280/720.jpg"

​
image_urls
string[] | null

Reference image URL list

Notes:

  • Use @Image1 / @Image2 in the prompt to reference
  • When elements contains video subjects, the total count is limited to 4
Example:
[
  "https://picsum.photos/id/1016/1280/720.jpg"
]
​
elements
object[] | null

Subject element list

Notes:

  • Use @Element1 / @Element2 in the prompt to reference
  • When video subjects are included, the combined total of elements and image_urls is limited to 4

Do not pass this parameter unless necessary.

Example:
[
  {
    "frontal_image_url": "https://picsum.photos/id/1027/768/1024.jpg",
    "reference_image_urls": [
      "https://picsum.photos/id/1028/768/1024.jpg"
    ]
  }
]
​
aspect_ratio
string | null

Output video aspect ratio

Available values: 16:9, 9:16, 1:1

Example:

"16:9"

​
duration
integer | null

Output video duration (seconds), 3-15

Example:

5

​
shot_type
string | null
default:customize

Multi-shot segmentation mode, currently fixed to customize

Do not pass this parameter unless necessary.

Example:

"customize"

​
multi_prompt
object[] | null

Multi-prompt sequence

Notes:

  • Mutually exclusive with prompt
  • The sum of all segment duration values should equal the total duration

Do not pass this parameter unless necessary.

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

Async task information

​
type
enum<string>

Task output type

Available options:
video
Example:

"video"