Skip to main content
POST
/
v1
/
videos
curl --request POST \
  --url https://api.powertokens.ai/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "wan2.2-kf2v-flash",
  "images": [
    "https://example.com/first-frame.png",
    "https://example.com/last-frame.png"
  ],
  "prompt": "Realistic style, a black kitten curiously looking at the sky, camera moving up from eye level to top-down",
  "seconds": "5",
  "size": "720P",
  "prompt_extend": true
}
'
{
  "id": "<string>",
  "task_id": "<string>",
  "object": "video",
  "model": "<string>",
  "status": "pending",
  "progress": 123,
  "created_at": 123
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
enum<string>
required

Wanxiang first-and-last-frame-to-video model.

Available options:
wan2.2-kf2v-flash,
wan2.1-kf2v-plus
​
images
string[]
required

Array of first-frame and last-frame image URLs. Exactly 2 items are required in order: images[0] is the first frame and images[1] is the last frame. Output video aspect ratio follows the first frame, and the last frame is cropped to match it.

Required array length: 2 elements
​
prompt
string

Text prompt describing transition from first to last frame. Supports Chinese and English, max 800 characters.

​
seconds
string
default:5

String form of the video duration in seconds. Currently fixed at "5".

​
size
enum<string>
default:720P

Video resolution. wan2.2-kf2v-flash supports 480P/720P/1080P, wan2.1-kf2v-plus supports 720P only.

Available options:
480P,
720P,
1080P
​
prompt_extend
boolean
default:true

Whether to enable prompt intelligent rewriting.

​
watermark
boolean
default:false

Whether to add watermark to video.

​
seed
integer

Random seed, range [0, 2147483647].

​
negative_prompt
string

Negative prompt describing content to avoid. Max 500 characters.

Response

Submission successful, returns video task object.

​
id
string
​
task_id
string
​
object
string
Example:

"video"

​
model
string
​
status
enum<string>
Available options:
pending,
queued,
running,
succeeded,
failed,
cancelled
​
progress
integer
​
created_at
integer<int64>