How to use video effect templates with the Wan image-to-video API? - Alibaba Cloud Model Studio

A video effect template is a preset for video generation effects. In a video generation based on the first frame task, you only need to provide a first-frame image and a template parameter to generate a video with a specific dynamic effect, such as "Magic Levitation" or "Squeeze". This feature is suitable for scenarios such as social media, marketing promotions, and interactive entertainment.

Important

This document applies only to the China (Beijing) region. To use the model, you must use an API key from the China (Beijing) region.

Input first-frame image

wanx-demo-1

Output example 1: Use the "Magic Levitation" effect

The template is set to "flying"

Output example 2: Use the "Squeeze" effect

The template is set to "squish"

How to use

Scope: The video effect feature described in this section is supported only in Wan - image-to-video - first frame tasks.
How to use: In the request, pass the template parameter and specify 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.

Video generation based on the first frame (using video effects)

The following code block shows only the request. For a complete call example, see Image-to-Video API.

curl --location 'https://dashscope.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"
    }
}'

Video effect templates

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

General effects

Effect name	template value	Example effect	Supported models	Input image suggestions
Squeeze	squish		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports any entity. We recommend that you use an image where the entity is prominent and clearly distinguished from the background.
Spin	rotation		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports any entity. We recommend that you use an image where the entity is prominent and clearly distinguished from the background.
Poke	poke		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports any entity. We recommend that you use an image where the entity is prominent and clearly distinguished from the background.
Balloon Inflation	inflate		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports any entity. We recommend that you use an image where the entity is prominent and clearly distinguished from the background.
Molecular Diffusion	dissolve		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports any entity. We recommend that you use an image where the entity is prominent and clearly distinguished from the background.

Single-person effects

Effect name	template parameter value	Example effect	Supported models	Input image suggestions
Carousel	carousel		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports single-person photos. We recommend that you use a half-body to full-body frontal photo.
Love You	singleheart		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports single-person photos. We recommend that you use a half-body to full-body frontal photo.
Swing Time	dance1		wanx2.1-i2v-plus	Supports single-person photos. We recommend that you use a half-body to full-body frontal photo.
Swing Dance	dance2		wanx2.1-i2v-plus	Supports single-person photos. We recommend that you use a full-body frontal photo.
Star Swing	dance3		wanx2.1-i2v-plus	Supports single-person photos. We recommend that you use a full-body frontal photo.
Mermaid Awakening	mermaid		wanx2.1-i2v-plus	Supports single-person photos. We recommend that you use a half-body frontal photo.
Academic Coronation	graduation		wanx2.1-i2v-plus	Supports single-person photos. We recommend that you use a half-body to full-body frontal photo.
Beast Pursuit	dragon		wanx2.1-i2v-plus	Supports single-person photos. We recommend that you use a half-body to full-body frontal photo.
Money from Heaven	money		wanx2.1-i2v-plus	Supports single-person photos. We recommend that you use a half-body to full-body frontal photo.

Single-person or animal effects

Effect name	template value	Example effect	Supported models	Input image suggestions
Magic Levitation	flying		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports single-person or animal photos. We recommend that you use a full-body frontal photo.
Rose for You	rose		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports single-person or animal photos. We recommend that you use a half-body to full-body frontal photo and avoid showing hands.
Shining Rose	crystalrose		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports single-person or animal photos. We recommend that you use a half-body to full-body frontal photo and avoid showing hands.

Two-person effects

Effect name	template value	Example effect	Supported models	Input image suggestions
Loving Hug	hug		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports two-person photos. We recommend that you use a half-body or full-body photo where two people face the camera or each other.
Interdependent	frenchkiss		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports two-person photos. We recommend that you use a half-body or full-body photo where two people face the camera or each other.
Double Heartbeat	coupleheart		wanx2.1-i2v-plus wanx2.1-i2v-turbo	Supports two-person photos. We recommend that you use a half-body or full-body photo where two people face the camera or each other.

References

For API parameter descriptions and code examples, see Image-to-video API.