Wanxiang - Image-to-Video - Video Effects

A video effect template is a preset for video generation effects. Provide a first-frame image and a template value to generate a video with a specific dynamic effect -- such as "Magic Levitation" or "Squeeze". This feature is suitable for social media, marketing promotions, and interactive entertainment.

Usage

• Scope: Video effect templates are supported only in Wan Image-to-Video (first frame) tasks.
• Method: In the request body, set the template parameter to the desired template value, such as flying. For all available templates, see Video effect templates.
• Note: When you use the template parameter, the model ignores the prompt field. You can omit this field or leave it empty.

Send a request

The Image-to-Video API uses an asynchronous workflow. You submit a video generation task and then query the task status to retrieve the result. For the complete workflow, including how to poll for task status and download the generated video, see the Image-to-Video API reference.

The following example shows how to submit a video generation request using a video effect template:

# The URL below is for the China (Beijing) region. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
curl --location 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/video-generation/video-synthesis' \
    -H 'X-DashScope-Async: enable' \
    -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
    "model": "wanx2.1-i2v-turbo",
    "input": {
        "img_url": "https://cdn.translate.alibaba.com/r/wanx-demo-1.png",
        "template": "flying"
    },
    "parameters": {
        "resolution": "720P"
    }
}'

from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope
import os

# If you have not configured environment variables, replace the following line with your API Key: api_key="sk-xxx"
# Get API Key: https://help.aliyun.com/en/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY")

def sample_async_call():
    # Submit video generation task asynchronously
    rsp = VideoSynthesis.async_call(api_key=api_key,
                                model='wanx2.1-i2v-turbo',
                                img_url='https://cdn.translate.alibaba.com/r/wanx-demo-1.png',
                                template='flying',
                                resolution='720P')
    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))

    # Query task status
    status = VideoSynthesis.fetch(task=rsp, api_key=api_key)
    if status.status_code == HTTPStatus.OK:
        print(status.output.task_status)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' %
              (status.status_code, status.code, status.message))

    # Wait for task to complete
    rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
    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()

Video effect templates

For optimal results, refer to the "Input image suggestions" column for each template.

Model support summary

General effects

All general effects support both wanx2.1-i2v-plus and wanx2.1-i2v-turbo.

These effects work with any entity. For best results, use an image where the entity is prominent and clearly distinguished from the background.

Single-person effects

These effects work with single-person photos. Unless noted otherwise, a half-body to full-body frontal photo is recommended.

Single-person or animal effects

All effects in this category support both wanx2.1-i2v-plus and wanx2.1-i2v-turbo.

These effects work with single-person or animal photos.

Two-person effects

All effects in this category support both wanx2.1-i2v-plus and wanx2.1-i2v-turbo.

These effects work with two-person photos. A half-body or full-body photo where both people face the camera or each other is recommended.

References

• For API parameter descriptions and complete code examples, see Image-to-Video API.