Model Marketplace

Wan - Image to Video

Copy success!
Add to Compare

Overview

The upgraded Wan2.5 Preview image to video model, newly upgraded model architecture supports synchronized audio generation with visuals, enables 10-second long video generation, and offers enhanced instruction adherence, improved motion capabilities, and superior image quality.

Input

TextImageAudio

Output

VideoAudio

Features

Prefix Completion

Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling

Use function calling to connect large language models with external tools and systems.View docs

Cache

Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs

Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Asynchronously process requests in batches to reduce costs.View docs

Web Search

Enable web search so the model can answer with real-time retrieved data.View docs

Fine-tuning

Train models on sample data to better adapt them to specific tasks.View docs

Pricing

  • Video Generation(480P)
    $0.05Per second
  • Video Generation(720P)
    $0.1Per second
  • Video Generation(1080P)
    $0.15Per second

Rate Limits

  • Concurrency
    5concurrent
  • Async Queue Limit
    500tasks
  • RPMRequests Per Minute
    300

API Reference

Call API
Copy success!
123456789101112131415161718192021222324252627282930313233343536373839404142434445
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope

dashscope.base_http_api_url = 'https://maas.qwencloudapi.com/api/v1'

# Get DashScope API Key from environment variable (Model Studio API key)
api_key = os.getenv("DASHSCOPE_API_KEY")

img_url = "https://cdn.translate.alibaba.com/r/wanx-demo-1.png"

def sample_async_call_i2v():
    # call async api, will return the task information
    # you can get task status with the returned task id.
    rsp = VideoSynthesis.async_call(model='wan2.5-i2v-preview',
                                    prompt='A cat running on the grass',
                                    img_url=img_url)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print("task_id: %s" % rsp.output.task_id)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))
   
    # get the task information include the task status.
    status = VideoSynthesis.fetch(rsp)
    if status.status_code == HTTPStatus.OK:
        print(status.output.task_status)  # check the task status
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (status.status_code, status.code, status.message))

    # wait the task complete, will call fetch interval, and check it's in finished status.
    rsp = VideoSynthesis.wait(rsp)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (rsp.status_code, rsp.code, rsp.message))


if __name__ == '__main__':
    sample_async_call_i2v()