Longer actions
give a movement more time without splitting the idea immediately.
Video generation
Explore longer scenes with visual references and frame control.
Loading model settings…
Your prompt, settings, and references stay together in a new Canvas.
01 / Meet the model
Wan 3.0 combines text, visual-reference, and frame-led video workflows with included audio. Its supported durations extend beyond a short single beat, making it useful when an action needs time to develop. Keep the sequence focused and inspect subject consistency throughout the full clip.
02 / Choose it for
give a movement more time without splitting the idea immediately.
use a selected reference set to describe the visual world.
guide the opening and closing composition with frames.
03 / Before you create
Model settings. Availability, input mode, and references can narrow the choices offered in Canvas.
04 / A closer look
Start with one coherent scene. Longer duration gives more time, but does not guarantee reliable cuts, identity, or chronology. Use separate Canvas shots when scene changes need independent review.
Text prompt · Reference images · Start frame · End frame. The input controls above show the options available for your selected mode.
Adaptive · 16:9 · 4:3 · 1:1 · 3:4 · 9:16. 480p · 720p · 1080p. The composer on this page accepts image references and frames; video/audio reference uploads are not exposed here.
Start with the format you intend to publish, then choose the available output settings. Changing inputs can change the choices. Review the current Gem estimate before Generate; availability and cost can vary.