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 looks up at the sky, the camera gradually rises from eye level, ending with a top-down shot of its curious eyes.",
  "seconds": "5",
  "size": "720P",
  "prompt_extend": true
}
'

{
  "id": "<string>",
  "task_id": "<string>",
  "object": "video",
  "model": "<string>",
  "progress": 123,
  "created_at": 123
}

{
  "error": {
    "message": "Malformed request body or invalid field value",
    "type": "invalid_request_error",
    "code": "bad_request_body",
    "param": ""
  }
}

{
  "error": {
    "message": "Invalid token",
    "type": "api_error",
    "code": "access_denied",
    "param": ""
  }
}

{
  "error": {
    "message": "Request body too large, please reduce the input and retry",
    "type": "api_error",
    "code": "read_request_body_failed",
    "param": ""
  }
}

{
  "error": {
    "message": "Insufficient account quota, please try again later",
    "type": "api_error",
    "code": "insufficient_user_quota",
    "param": ""
  }
}

{
  "error": {
    "message": "Internal processing failed, please try again later",
    "type": "api_error",
    "code": "gen_relay_info_failed",
    "param": ""
  }
}

{
  "error": {
    "message": "The upstream provider returned an invalid response",
    "type": "api_error",
    "code": "bad_response_status_code",
    "param": ""
  }
}

{
  "error": {
    "message": "No available channel for the current model, please try again later",
    "type": "api_error",
    "code": "get_channel_failed",
    "param": ""
  }
}

Alibaba

Wan First-Last Frame to Video

wan2.2-kf2v-flash

Applies to Wan series first-last-frame image-to-video models. After submitting a task, query its status via GET /v1/videos/{task_id}.

Public fields: model, images, prompt, seconds, size, prompt_extend, watermark, seed, and negative_prompt. The images array must contain exactly 2 images in order: images[0] is the first frame and images[1] is the last frame. The first frame determines the base composition, while the last frame controls the closing scene.

POST

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 looks up at the sky, the camera gradually rises from eye level, ending with a top-down shot of its curious eyes.",
  "seconds": "5",
  "size": "720P",
  "prompt_extend": true
}
'

{
  "id": "<string>",
  "task_id": "<string>",
  "object": "video",
  "model": "<string>",
  "progress": 123,
  "created_at": 123
}

{
  "error": {
    "message": "Malformed request body or invalid field value",
    "type": "invalid_request_error",
    "code": "bad_request_body",
    "param": ""
  }
}

{
  "error": {
    "message": "Invalid token",
    "type": "api_error",
    "code": "access_denied",
    "param": ""
  }
}

{
  "error": {
    "message": "Request body too large, please reduce the input and retry",
    "type": "api_error",
    "code": "read_request_body_failed",
    "param": ""
  }
}

{
  "error": {
    "message": "Insufficient account quota, please try again later",
    "type": "api_error",
    "code": "insufficient_user_quota",
    "param": ""
  }
}

{
  "error": {
    "message": "Internal processing failed, please try again later",
    "type": "api_error",
    "code": "gen_relay_info_failed",
    "param": ""
  }
}

{
  "error": {
    "message": "The upstream provider returned an invalid response",
    "type": "api_error",
    "code": "bad_response_status_code",
    "param": ""
  }
}

{
  "error": {
    "message": "No available channel for the current model, please try again later",
    "type": "api_error",
    "code": "get_channel_failed",
    "param": ""
  }
}

Authorizations

Authorization

string

header

required

Pass Authorization: Bearer <token> in the request header.

Body

application/json

model

enum<string>

required

Model name.

Available options:

wan2.2-kf2v-flash

images

string[]

required

First-last-frame image URL array. Must contain exactly 2 images in order: images[0] is the first frame, images[1] is the last frame. The output video aspect ratio matches the first frame image; the last frame is cropped to fit the first frame aspect ratio.

Required array length: 2 elements

prompt

string

required

Text prompt. Supports Chinese and English, up to 800 characters (each Chinese character or letter counts as one character). Excess characters will be automatically truncated.

If the subject and scene change significantly between the first and last frames, it is recommended to describe the transition, such as camera movement (e.g., camera panning left) or subject motion (e.g., a person running forward).

Example: A small black cat curiously looks up at the sky, the camera gradually rises from eye level, finally looking down at its curious eyes.

seconds

enum<string>

default:5

Video duration (seconds) as a string. Currently fixed at "5".

Available options:

5

size

enum<string>

default:720P

Output video resolution tier. wan2.2-kf2v-flash supports 480P/720P/1080P, wan2.1-kf2v-plus supports 720P.

Available options:

480P,

720P,

1080P

prompt_extend

boolean

default:true

Whether to enable intelligent prompt rewriting. When enabled, a large language model rewrites the input prompt intelligently. Significantly improves results for short prompts, but increases processing time.

true: Default, enable intelligent rewriting.
false: Disable intelligent rewriting.

Example: true.

watermark

boolean

default:false

Whether to add a watermark. The watermark appears at the bottom-right corner with the text "AI Generated".

false: Default, no watermark.
true: Add watermark.

Example: false.

seed

integer

Random seed, range [0, 2147483647].

When not specified, a random seed is automatically generated. To improve reproducibility of results, it is recommended to fix the seed value.

Note: Due to the probabilistic nature of model generation, even with the same seed, results may not be identical every time.

negative_prompt

string

Negative prompt describing content you do not want in the video, used to restrict the video output.

Supports Chinese and English, up to 500 characters. Excess characters will be automatically truncated.

Example: Low resolution, error, worst quality, low quality, disfigured, extra fingers, bad proportions, etc.

Response

Submitted successfully. Returns a video task object.

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>

Wan Text to Video

Wan First-Last Frame to Video

Chat Models

Image Models

Video Models

Audio Models

asset library

Wan First-Last Frame to Video

Authorizations

Body

Response