Skip to main content
First frame

Wan video effects list

Complete list of Wan video effect templates, including template values, supported models, and input image guidance for first-frame and first-and-last-frame models.

Wan provides video effects: specify an effect template and the preset motion is applied without a text prompt. Video effects are supported only by Image-to-video: first frame and Image-to-video: first and last frames.
Model IDs differ by region. In Singapore (ap-southeast-1), use wan2.1-i2v-plus, wan2.1-i2v-turbo, and wan2.1-kf2v-plus. In China North 2 (Beijing) (cn-beijing), use wanx2.1-i2v-plus, wanx2.1-i2v-turbo, and wanx2.1-kf2v-plus.The samples below use China North 2 (Beijing). For Singapore, replace the region in the URL and use the wan2.1-* model IDs.

Usage

Video effects work differently from regular image-to-video calls:
  • Provide only a first frame: With either a first-frame model or a first-and-last-frame model, provide only one first-frame image.
  • No prompt needed: In effect mode, the model ignores the prompt field. Omit the parameter and focus on choosing an effect.
  • Choose one template: Set the template parameter to one value from the list below. The model generates the corresponding motion.
Each model supports a different set of templates. Check First-frame effects and First-and-last-frame effects to make sure the template value matches your model.

Sample code

  • Image-to-video: first frame
  • Image-to-video: first and last frames
First-frame effect: Generate an effect video from the first frame.
# China North 2 (Beijing). This model is available only in this region.
# API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
curl --location 'https://cn-beijing.maas.qwencloudapi.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"
  }
}'
For the full sample, see Image-to-video: first frame.

First-frame effects

The result depends on both the template and the input image. Preview the template examples and follow the input image guidance before trying your own image.

General effects

Effecttemplate valueSupported modelsInput image guidance
Stress-relief squishsquishwan2.1-i2v-plus, wan2.1-i2v-turboAny subject. Use an image where the subject is prominent and clearly separated from the background.
Spinrotationwan2.1-i2v-plus, wan2.1-i2v-turboAny subject. Use an image where the subject is prominent and clearly separated from the background.
Pokepokewan2.1-i2v-plus, wan2.1-i2v-turboAny subject. Use an image where the subject is prominent and clearly separated from the background.
Balloon inflateinflatewan2.1-i2v-plus, wan2.1-i2v-turboAny subject. Use an image where the subject is prominent and clearly separated from the background.
Molecular dissolvedissolvewan2.1-i2v-plus, wan2.1-i2v-turboAny subject. Use an image where the subject is prominent and clearly separated from the background.
Heat-wave meltmeltwan2.1-i2v-plusAny subject. Use an image where the subject is prominent and clearly separated from the background.
Ice-cream planeticecreamwan2.1-i2v-plusAny subject. Use an image where the subject is prominent and clearly separated from the background.

Single-person effects

Effecttemplate valueSupported modelsInput image guidance
Time carouselcarouselwan2.1-i2v-plus, wan2.1-i2v-turboOne person. Use a front-facing half-body or full-body photo.
Love yousingleheartwan2.1-i2v-plus, wan2.1-i2v-turboOne person. Use a front-facing half-body or full-body photo.
Groove timedance1wan2.1-i2v-plusOne person. Use a front-facing half-body or full-body photo.
Top dancedance2wan2.1-i2v-plusOne person. Use a front-facing full-body photo.
Star swaydance3wan2.1-i2v-plusOne person. Use a front-facing full-body photo.
Finger beatdance4wan2.1-i2v-plusOne person. Use a front-facing half-body or full-body photo.
Dance switchdance5wan2.1-i2v-plusOne person. Use a front-facing half-body or full-body photo.
Mermaid awakeningmermaidwan2.1-i2v-plusOne person. Use a front-facing half-body photo.
Academic coronationgraduationwan2.1-i2v-plusOne person. Use a front-facing half-body or full-body photo.
Beast chasedragonwan2.1-i2v-plusOne person. Use a front-facing half-body or full-body photo.
Fortune fallsmoneywan2.1-i2v-plusOne person. Use a front-facing half-body or full-body photo.
Jellyfish promisejellyfishwan2.1-i2v-plusOne person. Use a front-facing half-body or full-body photo.
Pupil portalpupilwan2.1-i2v-plusOne person. Use a front-facing half-body or full-body photo.

Single-person or animal effects

Effecttemplate valueSupported modelsInput image guidance
Magic levitationflyingwan2.1-i2v-plus, wan2.1-i2v-turboOne person or an animal. Use a front-facing full-body photo.
Gift of rosesrosewan2.1-i2v-plus, wan2.1-i2v-turboOne person or an animal. Use a front-facing half-body or full-body photo with hands out of frame.
Sparkling rosecrystalrosewan2.1-i2v-plus, wan2.1-i2v-turboOne person or an animal. Use a front-facing half-body or full-body photo with hands out of frame.

Two-person effects

Effecttemplate valueSupported modelsInput image guidance
Loving hughugwan2.1-i2v-plus, wan2.1-i2v-turboTwo people. Both should face the camera or stand facing each other; half-body or full-body photos work.
French kissfrenchkisswan2.1-i2v-plus, wan2.1-i2v-turboTwo people. Both should face the camera or stand facing each other; half-body or full-body photos work.
Double heartbeatcoupleheartwan2.1-i2v-plus, wan2.1-i2v-turboTwo people. Both should face the camera or stand facing each other; half-body or full-body photos work.

First-and-last-frame effects

The result depends on both the template and the input image. Preview the template examples and follow the input image guidance before trying your own image.
First-and-last-frame effects are trained on the first-and-last-frame models, but in practice you provide only a first frame. The result is equivalent to a first-frame video. See Usage.

Single-person effects

Effecttemplate valueSupported modelsInput image guidance
Hanfu elegancehanfu-1wan2.1-kf2v-plusOne person. Use a front-facing half-body or full-body photo.
Mecha transformationsolaronwan2.1-kf2v-plusOne person. Use a front-facing half-body or full-body photo.
Shining covermagazinewan2.1-kf2v-plusOne person. Use a front-facing half-body or full-body photo.
Mecha awakeningmech1wan2.1-kf2v-plusOne person. Use a front-facing half-body or full-body photo.
Cyber entrancemech2wan2.1-kf2v-plusOne person. Use a front-facing half-body or full-body photo.

API reference

For parameters and complete code samples, see Image-to-video: first frame and Image-to-video: first and last frames.