Wan 3.0: Text to Video
Text to Video with Wan 3.0, with the model already selected.


A clean acoustic guitar playing a gentle fingerpicked melody with a festive, serene feel.
How it works
Try it now- 01
Say what you want
A sentence or two is enough.
- 02
Use Wan 3.0
Choose the settings that fit what you want to make.
03Make it
Start creating, then keep working with HowWorks.
Explore the possibilities

Wan 3.0 at a glance
- Good at
- Top-ranked text to video. 2–30s in one take, up to 1080p, up to 10 reference images.
- Modes
- Text to Video, Image to Video, Reference to Video
- Length
- 2–30 s (presets 5, 10, 15, 30 s)
- Resolution
- 480p, 720p, 1080p
- Aspect ratios
- 16:9, 9:16, 1:1, 4:3, 3:4
- Image-led framing
- May follow the input image; check the output frame
- Sound
- On by default, can be switched off
- Reference images
- Up to 10
About
Describe a shot rather than an entire film: setting, subject, action and camera movement. A slow move through a snowy street needs a different brief from a little boat drifting on a pond. Keep the action readable within the selected duration and watch the whole result, including the sound and final frames. Choose only the inputs and controls shown for this operation; other operations or model versions can have different limits.
Questions
How should I prompt Wan 3.0 for a video?
Describe a clear subject, one main action and a camera movement that suits the shot. Include sound direction where supported. A short, coherent scene is easier to review than several unrelated events in one request.
What should I check in the Wan 3.0 text to video example?
Watch subject identity, facial movement, hands and the background for changes. The portrait preview is a visual example; review sound separately when creating an audiovisual result.
Can Wan 3.0 make a silent video?
The current HowWorks model exposes a sound toggle. Choose the sound setting deliberately and check the finished file; the page’s visual preview does not guarantee the same soundtrack or result on a new run.











































