Skip to main content
POST
/
vendors
/
alibaba
/
v1
/
wan2.5-i2v-preview
/
generation
Create Generation Task
curl --request POST \
  --url https://api.mulerouter.ai/vendors/alibaba/v1/wan2.5-i2v-preview/generation \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>",
  "image": "<string>",
  "negative_prompt": "<string>",
  "audio": true,
  "audio_url": "<string>",
  "resolution": "720P",
  "duration": 5,
  "prompt_extend": true,
  "seed": 1073741823,
  "safety_filter": true
}
'
{
  "task_info": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "status": "pending",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z"
  }
}

Documentation Index

Fetch the complete documentation index at: https://mulerouter.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

This API supports Alibaba Tongyi Wanxiang (Wan2) video generation models. Please refer to Alibaba Cloud’s official documentation for more details.

​
Overview

Generate videos from images using the wan2.5-i2v-preview model with optional audio generation.

​
Key Features

  • Image-to-video generation with auto sound or custom audio
  • Multiple resolution options (480P/720P/1080P)
  • 5s or 10s duration
  • 24fps output

​
Image Requirements

PropertyRequirement
FormatsJPEG, JPG, PNG (no transparency), BMP, WEBP
Dimensions[360, 2000] pixels for both width and height
File SizeMax 10MB
InputPublic URL or Base64 encoded data

​
Audio Features

​
Auto-generated Audio

  • Enabled by default
  • Automatically generates synchronized audio based on video content

​
Custom Audio

  • Supported formats: WAV, MP3
  • Duration: 3-30 seconds
  • Max file size: 15MB

​
Example Requests

​
Basic Image-to-Video

{
  "prompt": "The cat starts running forward",
  "image": "https://example.com/cat.jpg",
  "resolution": "720P",
  "duration": 5
}

​
With Custom Audio

{
  "prompt": "Scene becomes dynamic, clouds drifting",
  "image": "https://example.com/landscape.jpg",
  "audio_url": "https://example.com/ambient.mp3",
  "resolution": "1080P",
  "duration": 10
}

​
With Negative Prompt

{
  "prompt": "Character turns head and smiles",
  "image": "https://example.com/portrait.jpg",
  "negative_prompt": "shaking, distortion",
  "resolution": "720P",
  "duration": 5
}

​
Prompt Tips

For best results:
  • Describe the motion/story you want to see
  • Specify camera movements if needed
  • Include transition descriptions

Authorizations

​
Authorization
string
header
required

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

Body

application/json
​
prompt
string
required

Motion/story description for the video (max 2000 characters).

Maximum string length: 2000
​
image
string
required

First-frame image (URL or Base64). Supported formats: JPEG/JPG/PNG/BMP/WEBP, 360-2000px, ≤10MB.

​
negative_prompt
string

Negative prompt describing unwanted content (max 500 characters).

Maximum string length: 500
​
audio
boolean | null
default:true

Enable automatic audio generation. Set to false to force a silent output.

​
audio_url
string<uri> | null

Custom audio file URL (wav/mp3, 3-30s, ≤15MB). Overrides the audio flag.

​
resolution
enum<string>
default:720P

Output resolution tier:

  • 480P
  • 720P
  • 1080P
Available options:
480P,
720P,
1080P
​
duration
enum<integer>

Video duration in seconds (24 fps). Supported values 5 or 10.

Available options:
5,
10
​
prompt_extend
boolean
default:true

Enable intelligent prompt rewriting (slightly longer latency, better detail).

​
seed
integer

Random seed [0, 2147483647].

Required range: 0 <= x <= 2147483647
​
safety_filter
boolean | null
default:true

Enable content safety filter. Defaults to true. Set to false to disable content safety inspection.

Response

202 - application/json

Accepted - Task created successfully

​
task_info
object