Standard preview
$0.72
Most popularaudio incl.
AI video · Wan
Wan 3
Your idea. Your references. Your settings.
Wan 3 is an Alibaba/Tongyi model for text-to-video, image animation, mixed references, video editing and extension. Choose 2–30 seconds and 480p, 720p or 1080p, then review the price before generation.
No preview available yet.
Text direction for planned scenes
Describe the subject, setting, main action, camera path and final beat in a clear order. Wan 3 can render between two and thirty seconds, so the prompt should match the chosen length instead of overloading a short clip.
Opening and ending frame control
Use a required start image and an optional end image. Keep these frames separate from mixed-reference inputs; describe the motion between the visual anchors.
Mixed reference workflow
Guide the scene with up to 10 images, 5 video clips and 5 audio clips. Video and audio each have a 15-second combined limit. All input videos plus the generated video must total no more than 30 seconds. An eligible document or public webpage can provide context; choose one of those two URL types.
Resolution chosen per delivery
Use 480p for inexpensive exploration, 720p for review, or 1080p when the approved composition needs a higher-resolution output. The displayed quote updates from the same canonical pricing calculation used at generation.
