Wan2.7 T2V

Wan2.7 T2V is Alibaba Cloud’s text-to-video model, available through the AnyFast asynchronous video API. It generates 720P or 1080P MP4 videos with synchronized audio and supports multi-shot storytelling. T2V means text-to-video: the request uses a text prompt and does not require an input image or video.

Key capabilities

Text-to-video - Generate video from Chinese or English prompts
Synchronized audio - Supply WAV/MP3 audio or let the model generate matching sound automatically
Resolution - 720P or 1080P
Duration - An integer from 2 to 15 seconds
Aspect ratio - 16:9, 9:16, 1:1, 4:3, or 3:4
Output - 30 fps MP4 video

Quick example

cURL

curl https://www.anyfast.ai/v1/video/generations \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "wan2.7-t2v",
    "input": {
      "prompt": "A paper boat sails through a neon-lit rainy city, cinematic tracking shot."
    },
    "parameters": {
      "resolution": "720P",
      "ratio": "16:9",
      "duration": 5,
      "prompt_extend": true,
      "watermark": false,
      "seed": 42
    }
  }'

Video generation is asynchronous. Save the returned task ID and poll the Wan task query endpoint. Task IDs and successful result URLs remain available for 24 hours.

Enable NSFW generation

Select the Special-Ns resource group when creating the API token.
Set parameters.prompt_extend to false. Its default value is true.

Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Must be `wan2.7-t2v`
`input.prompt`	string	Yes	Video description in Chinese or English, up to 5,000 characters
`input.negative_prompt`	string	No	Content to exclude, up to 500 characters
`input.audio_url`	string	No	Public WAV/MP3 URL; 2-30 seconds and up to 15 MB
`parameters.resolution`	string	No	`720P` or `1080P`. Default: `1080P`
`parameters.ratio`	string	No	Output aspect ratio. Default: `16:9`
`parameters.duration`	integer	No	Duration from 2 to 15 seconds. Default: `5`
`parameters.prompt_extend`	boolean	No	Rewrite and enrich the prompt. Default: `true`
`parameters.watermark`	boolean	No	Add an “AI Generated” watermark. Default: `false`
`parameters.seed`	integer	No	Random seed in `[0, 2147483647]`

If audio_url is omitted, the model generates matching audio. Audio longer than the requested video is truncated; if it is shorter, the remaining video is silent.

API Reference

View the complete request schema.

Task Query

Poll the task and retrieve the result URL.

Official reference

See the Alibaba Cloud Model Studio Wan2.7 text-to-video API reference.

Getting started

Model Introduction

Resources

Key capabilities

Quick example

Enable NSFW generation

Parameters

API Reference

Task Query

Official reference

​Key capabilities

​Quick example

​Enable NSFW generation

​Parameters

API Reference

Task Query

​Official reference

Key capabilities

Quick example

Enable NSFW generation

Parameters

Official reference