Wan 2.2 Text-To-Video Plus Generation

Generate videos from text prompts using the wan2.2-t2v-plus model.

POST /vendors/alibaba/v1/wan2.2-t2v-plus/generation

Create Generation Task

cURL

curl --request POST \
  --url https://api.mulerun.com/vendors/alibaba/v1/wan2.2-t2v-plus/generation \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>",
  "negative_prompt": "<string>",
  "size": "1920*1080",
  "prompt_extend": true,
  "seed": 1073741823
}
'

202

{
  "task_info": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z"
  }
}

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 text prompts using the wan2.2-t2v-plus model. This is the Plus version with enhanced stability.

Key Features

• Text-to-video generation
• 480P or 1080P resolution options
• Fixed 5s duration
• 30fps output

Resolution Options

480P

• 832×480 (16:9)
• 480×832 (9:16)
• 624×624 (1:1)

1080P

• 1920×1080 (16:9)
• 1080×1920 (9:16)
• 1440×1440 (1:1)
• 1632×1248 (4:3)
• 1248×1632 (3:4)

Example Requests

Basic Text-to-Video

{
  "prompt": "A small cat running in the moonlight, slow motion close-up",
  "size": "1920*1080",
  "duration": 5
}

With Negative Prompt

{
  "prompt": "Sunset over the ocean, waves crashing on the shore",
  "negative_prompt": "blurry, low quality",
  "size": "1280*720",
  "duration": 5
}

Parameters

duration

• Fixed: 5 seconds
• FPS: 30fps

prompt

• Max length: 800 characters (shorter than Wan2.5/2.6 models)

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

Text prompt for the video (max 800 characters).

Maximum string length: 800

negative_prompt · string

Negative prompt describing unwanted content (max 500 characters).

Maximum string length: 500

size · enum<string> · default: 1920*1080

Output resolution ("width*height"). Supported tiers:

• 480P: 832*480 (16:9), 480*832 (9:16), 624*624 (1:1)
• 1080P: 1920*1080 (16:9), 1080*1920 (9:16), 1440*1440 (1:1), 1632*1248 (4:3), 1248*1632 (3:4)

Available options: 832*480, 480*832, 624*624, 1920*1080, 1080*1920, 1440*1440, 1632*1248, 1248*1632

duration · enum<integer>

Video duration in seconds (30 fps). Fixed at 5 seconds.

Available options: 5

prompt_extend · boolean · default: true

Enable intelligent prompt rewriting.

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