Video style transform — Create a task

POST

/services/aigc/video-generation/video-synthesis

cURL

# China North 2 (Beijing). This model is available only in this region.
# API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
curl --request POST \
  --url https://cn-beijing.maas.qwencloudapi.com/api/v1/services/aigc/video-generation/video-synthesis \
  --header 'X-DashScope-Async: enable' \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "video-style-transform",
  "input": {
    "video_url": "https://example.com/input.mp4"
  },
  "parameters": {
    "style": 0,
    "video_fps": 15
  }
}'

{
  "output": {
    "task_id": "a8532587-fa8c-4ef8-82be-0c46b17950d1",
    "task_status": "PENDING"
  },
  "request_id": "7574ee8f-38a3-4b1e-9280-11c33ab46e51"
}

video-style-transform repaints each frame of a video in an artistic style while preserving the appearance of people and objects. It supports eight styles, including Japanese manga, American comic, and 3D cartoon. Supported regions: China North 2 (Beijing) only. Use an API key created in that region and the https://cn-beijing.maas.qwencloudapi.com endpoint. See Regions and endpoints. Input video requirements:

Constraint	Requirement
Resolution	Each side between 256 and 4,096 pixels. Aspect ratio no more than 1.8.
Format	MP4, AVI, MKV, MOV, FLV, TS, MPG, MXF
Duration	Up to 30 seconds
File size	Up to 100 MB
URL	URL-encode paths that contain non-ASCII characters.

Processing is asynchronous: this operation returns a task_id, and you poll Query the result until the task finishes.

Authorizations

string

header

required

QwenCloud API key. See API keys.

Header Parameters

enum<string>

required

Must be set to enable to submit the task asynchronously.

Available options:enable

Body

application/json

enum<string>

required

Model name. Fixed to video-style-transform.

Available options:video-style-transform

Example:video-style-transform

object

required

Input data.

Show child attributes

string

required

URL of the input video. Supports HTTP and HTTPS.

Video requirements:

Format: MP4, AVI, MKV, MOV, FLV, TS, MPG, MXF
Duration: up to 30 seconds
Size: up to 100 MB
Resolution: both sides between 256 and 4,096 pixels
Aspect ratio: no more than 1.8
Codec: H.264 or H.265

Example:https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250704/viwndw/%E5%8E%9F%E8%A7%86%E9%A2%91.mp4

object

Video style transform parameters.

Show child attributes

enum<integer>

default0

Target artistic style. Valid values:

0: Japanese manga
1: American comic
2: Fresh comic
3: 3D cartoon
4: Chinese cartoon (best for inputs with ancient costumes)
5: Paper art
6: Simple illustration
7: Chinese ink wash painting

Available options:0,1,2,3,4,5,6,7

Example:0

integer

default15

Output video frame rate (FPS). Range: 15-25. A higher frame rate produces smoother video but increases billed duration.

Example:15

Required range:15 <= x <= 25

boolean

defaulttrue

Whether to apply emotion transfer. When enabled, facial expressions in the output video are richer, though some scenes may look exaggerated.

enum<integer>

default720

Short-side resolution of the output video. Valid values:

720: 720P output
540: 540P output

Higher resolution produces better quality and costs more.

Available options:720,540

Example:720

boolean

defaultfalse

Whether to enable super-resolution enhancement. Improves output quality but increases processing time.

Response

200-application/json

string

Unique request identifier for tracing and troubleshooting.

Example:7574ee8f-38a3-4b1e-9280-11c33ab46e51

object

Show child attributes

string

Task ID used to poll the task status with GET /tasks/{task_id}.

Example:xxxxxxxx

enum<string>

Initial task status, usually PENDING.

Available options:PENDING,RUNNING,SUSPENDED,SUCCEEDED,FAILED