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.
Video effects work differently from regular image-to-video calls:
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.
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.
For parameters and complete code samples, see 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
promptfield. Omit the parameter and focus on choosing an effect. - Choose one template: Set the
templateparameter 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.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
| Effect | template value | Supported models | Input image guidance |
|---|---|---|---|
| Stress-relief squish | squish | wan2.1-i2v-plus, wan2.1-i2v-turbo | Any subject. Use an image where the subject is prominent and clearly separated from the background. |
| Spin | rotation | wan2.1-i2v-plus, wan2.1-i2v-turbo | Any subject. Use an image where the subject is prominent and clearly separated from the background. |
| Poke | poke | wan2.1-i2v-plus, wan2.1-i2v-turbo | Any subject. Use an image where the subject is prominent and clearly separated from the background. |
| Balloon inflate | inflate | wan2.1-i2v-plus, wan2.1-i2v-turbo | Any subject. Use an image where the subject is prominent and clearly separated from the background. |
| Molecular dissolve | dissolve | wan2.1-i2v-plus, wan2.1-i2v-turbo | Any subject. Use an image where the subject is prominent and clearly separated from the background. |
| Heat-wave melt | melt | wan2.1-i2v-plus | Any subject. Use an image where the subject is prominent and clearly separated from the background. |
| Ice-cream planet | icecream | wan2.1-i2v-plus | Any subject. Use an image where the subject is prominent and clearly separated from the background. |
Single-person effects
| Effect | template value | Supported models | Input image guidance |
|---|---|---|---|
| Time carousel | carousel | wan2.1-i2v-plus, wan2.1-i2v-turbo | One person. Use a front-facing half-body or full-body photo. |
| Love you | singleheart | wan2.1-i2v-plus, wan2.1-i2v-turbo | One person. Use a front-facing half-body or full-body photo. |
| Groove time | dance1 | wan2.1-i2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Top dance | dance2 | wan2.1-i2v-plus | One person. Use a front-facing full-body photo. |
| Star sway | dance3 | wan2.1-i2v-plus | One person. Use a front-facing full-body photo. |
| Finger beat | dance4 | wan2.1-i2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Dance switch | dance5 | wan2.1-i2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Mermaid awakening | mermaid | wan2.1-i2v-plus | One person. Use a front-facing half-body photo. |
| Academic coronation | graduation | wan2.1-i2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Beast chase | dragon | wan2.1-i2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Fortune falls | money | wan2.1-i2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Jellyfish promise | jellyfish | wan2.1-i2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Pupil portal | pupil | wan2.1-i2v-plus | One person. Use a front-facing half-body or full-body photo. |
Single-person or animal effects
| Effect | template value | Supported models | Input image guidance |
|---|---|---|---|
| Magic levitation | flying | wan2.1-i2v-plus, wan2.1-i2v-turbo | One person or an animal. Use a front-facing full-body photo. |
| Gift of roses | rose | wan2.1-i2v-plus, wan2.1-i2v-turbo | One person or an animal. Use a front-facing half-body or full-body photo with hands out of frame. |
| Sparkling rose | crystalrose | wan2.1-i2v-plus, wan2.1-i2v-turbo | One person or an animal. Use a front-facing half-body or full-body photo with hands out of frame. |
Two-person effects
| Effect | template value | Supported models | Input image guidance |
|---|---|---|---|
| Loving hug | hug | wan2.1-i2v-plus, wan2.1-i2v-turbo | Two people. Both should face the camera or stand facing each other; half-body or full-body photos work. |
| French kiss | frenchkiss | wan2.1-i2v-plus, wan2.1-i2v-turbo | Two people. Both should face the camera or stand facing each other; half-body or full-body photos work. |
| Double heartbeat | coupleheart | wan2.1-i2v-plus, wan2.1-i2v-turbo | Two 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
| Effect | template value | Supported models | Input image guidance |
|---|---|---|---|
| Hanfu elegance | hanfu-1 | wan2.1-kf2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Mecha transformation | solaron | wan2.1-kf2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Shining cover | magazine | wan2.1-kf2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Mecha awakening | mech1 | wan2.1-kf2v-plus | One person. Use a front-facing half-body or full-body photo. |
| Cyber entrance | mech2 | wan2.1-kf2v-plus | One person. Use a front-facing half-body or full-body photo. |