Wan2 Video Edit

This API uses the wan2.1-vace-plus model for advanced video editing with multi-modal inputs. Please refer to Alibaba Cloud’s official documentation for more details.

Overview

The wan2.1-vace-plus model supports multi-modal input including multiple reference images and video editing capabilities. It’s designed for complex video generation tasks that require precise control over content and style.

Supported Model

wan2.1-vace-plus

Advanced video generation model with:

Multi-image reference support
Video editing capabilities
Both first frame and first+last frame support
Enhanced content and motion control

Features

Reference Images: Use multiple images to guide content and style
Keyframe Support: Define both first and last frames
Video Effects: Apply special effect templates
Complex Motion: Better handling of complex motion and physics

Specifications

Property	Value
Audio	No (silent video only)
First Frame	✅ Supported
First & Last Frame	✅ Supported
Resolution	720P only
Duration	5 seconds (fixed)
Frame Rate	30fps
Format	MP4 (H.264)

Example Requests

Multi-Image Reference

{
  "model": "wan2.1-vace-plus",
  "prompt": "Create a video combining the character from the first image with the environment from the second image, showing the character walking forward",
  "images": [
    "https://example.com/character.jpg",
    "https://example.com/environment.jpg"
  ]
}

With Negative Prompt

{
  "model": "wan2.1-vace-plus",
  "prompt": "A person performing a graceful dance move in a studio",
  "negative_prompt": "blurry, distorted, low quality, incomplete, extra limbs, poor motion",
  "images": [
    "data:image/jpeg;base64,/9j/4AAQSkZJRg..."
  ]
}

Style Transfer Video

{
  "model": "wan2.1-vace-plus",
  "prompt": "Apply the artistic style from the reference image to create a video of the subject moving",
  "images": [
    "https://example.com/subject.jpg",
    "https://example.com/style_reference.jpg"
  ],
  "prompt_extend": true
}

Reproducible Output

{
  "model": "wan2.1-vace-plus",
  "prompt": "A character turning around to face the camera, smooth motion",
  "images": [
    "https://example.com/character.jpg"
  ],
  "seed": 42,
  "prompt_extend": false
}

Image Requirements

Property	Requirement
Formats	JPEG, JPG, PNG, BMP, WEBP
File Size	Max 10MB per image
Input	Public URL or Base64 encoded data
Multiple Images	Supported for content and style reference

Prompt Tips

When using wan2.1-vace-plus:

Be specific about motion: Describe exactly what kind of movement you want
Reference the images: Mention how the reference images should influence the output
Describe transitions: If using multiple images, explain how they should blend or interact
Use negative prompts: Exclude unwanted artifacts like distortion or blurriness

Use Cases

Character Animation: Bring still character images to life with motion
Style Transfer: Apply artistic styles to video content
Scene Composition: Combine elements from multiple images into animated sequences
Motion Design: Create videos with specific, controlled movements
Content Remixing: Generate new videos based on existing visual references

Parameters

images (Required)

Type: Array of strings
Description: Reference images for video generation
Can include subject images, style references, or compositional guides

prompt_extend

Default: true
Purpose: AI enhancement of prompts
Recommendation: Enable for short prompts, disable for detailed ones

seed

Range: 0 to 2,147,483,647
Purpose: Improves reproducibility
Note: Results may still vary due to model’s probabilistic nature

Authorizations

Authorization

string

header

required

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

Body

application/json

Multi-image Reference
Video Repainting
Local Editing
Video Extension
Video Outpainting

wan2.1-vace-plus video editing entry point. Select a function and supply the parameters supported by that function.

model

enum<string>

required

Model name (only wan2.1-vace-plus is supported)

Available options:

wan2.1-vace-plus

function

enum<string>

required

Multi-image reference feature selector.

Available options:

image_reference

Allowed value: "image_reference"

prompt

string

required

Text description for the synthesized video (max 800 characters).

Maximum string length: 800

ref_images_url

string<uri>[]

required

Public URLs for 1-3 reference images (JPG/JPEG/PNG/BMP/TIFF/WEBP, 360-2000px, ≤10MB, ASCII URL). Required.

Required array length: 1 - 3 elements

negative_prompt

string

Negative prompt (max 500 characters).

Maximum string length: 500

obj_or_bg

enum<string>[]

Matches ref_images_url to label each image as entity ("obj") or background ("bg"). Required when multiple images are supplied; defaults to ["obj"] for a single image.

Available options:

obj,

bg

size

enum<string>

default:1280*720

Output resolution ("width*height"). Supported: 1280*720 (default), 720*1280, 960*960, 832*1088, 1088*832.

Available options:

1280*720,

720*1280,

960*960,

832*1088,

1088*832

duration

enum<integer> | null

Output duration (seconds). Fixed at 5.

Available options:

5

prompt_extend

boolean

default:true

Enable intelligent prompt rewriting (default true).

seed

integer

Random seed [0, 2147483647].

Required range: 0 <= x <= 2147483647

Response

202 - application/json

Accepted - Task created successfully

task_info

object

Show child attributes

task_info.id

string<uuid>

required

UUID of the task

task_info.status

enum<string>

required

Task status

Available options:

pending,

processing,

completed,

failed

task_info.created_at

string<date-time>

required

Task creation timestamp (ISO 8601)

task_info.updated_at

string<date-time>

required

Task last update timestamp (ISO 8601)

task_info.error

object

Error details (only when status is failed)

Show child attributes

task_info.error.code

integer

MuleRouter Error code

task_info.error.title

string

MuleRouter Error title

task_info.error.detail

string

MuleRouter Error detail

Using the APIs

API reference

LLM

Image Generation

Video Generation

Overview

Supported Model

wan2.1-vace-plus

Features

Specifications

Example Requests

Multi-Image Reference

With Negative Prompt

Style Transfer Video

Reproducible Output

Image Requirements

Prompt Tips

Use Cases

Parameters

images (Required)

prompt_extend

seed

Authorizations

Body

Response

Using the APIs

API reference

LLM

Image Generation

Video Generation

​Overview

​Supported Model

​wan2.1-vace-plus

​Features

​Specifications

​Example Requests

​Multi-Image Reference

​With Negative Prompt

​Style Transfer Video

​Reproducible Output

​Image Requirements

​Prompt Tips

​Use Cases

​Parameters

​images (Required)

​prompt_extend

​seed

Authorizations

Body

Response

Overview

Supported Model

wan2.1-vace-plus

Features

Specifications

Example Requests

Multi-Image Reference

With Negative Prompt

Style Transfer Video

Reproducible Output

Image Requirements

Prompt Tips

Use Cases

Parameters

images (Required)

prompt_extend

seed