Generate from a description or from a starting frame. Set 4, 6 or 8 seconds, choose 720p, 1080p or 4K, and pick a shape in both modes. This page covers the two Lite entries.
Veo 3.1 appears in the selector as several separate entries. This page describes the two Lite ones, which are the entries where the clip length and the quality tier are selectable: 4, 6 or 8 seconds at 720p, 1080p or 4K. The shape selector stays available in both modes.
Text to video builds a shot from your description. Image to video takes one picture to define the first frame, or two pictures to define a first and a last frame, and moves between them. Both entries keep a translation switch and an optional watermark text field under Advanced parameters.
Choose 4, 6 or 8 seconds and 720p, 1080p or 4K. Both modes offer 16:9, 9:16 and Auto. Advanced parameters hold a translation switch, which starts on, and an optional watermark text field. Descriptions are capped at 2000 characters, and the image entry accepts one or two pictures.
Choose 4, 6 or 8 seconds and 720p, 1080p or 4K on the same entry. Changing quality creates a new generation; it does not upscale or reproduce an earlier result.
Supply one picture to start from, or two to land on. That is how a move between two composed stills stays inside a single task instead of being joined together afterwards in the edit.
Both modes offer 16:9, 9:16 or Auto. Choose 9:16 for a vertical target. Auto lets the service choose the ratio and may crop an input image; review the result.
A 4-second sting for a feed placement and an 8-second establishing move come from the same entry, so a storyboard with mixed lengths does not need a second product.
Give the image entry a starting frame and a closing frame and describe the move between them. The result is one clip rather than two that have to be joined.
Render the same description at 720p and at 4K and compare the two on your own footage before you commit a campaign to the higher tier.
Use a button on this page. It opens the right workspace with this model already selected, in the language you are reading now.
Write what should happen in the shot or image. Concrete subjects, framing and action give the model more to work with than short labels.
Choose length or quality tier, shape and sound where offered, then read the credit quote for those exact settings before you generate.
Generation uses account credits. Cost depends on the model, quality and output size or duration. Reference images, video or audio may add charges in some modes. Check the workspace quote for your selected inputs and settings before generating; the pricing page lists credit packages.
See credit packagesThis page covers Lite text-to-video and Lite image-to-video. Fast, Quality and the separate reference entry have their own controls and are not covered here.
Choose 4, 6 or 8 seconds in either mode. Check the delivered duration before fitting a clip to an exact editing slot.
Both modes offer 16:9, 9:16 or Auto. Auto selects the ratio automatically and can crop an input image. Select an explicit ratio when the placement requires one.
Generated clips can include audio. Neither entry has a sound on/off switch; review the soundtrack and mute it in your editor when you need silence.
The image entry takes one or two: one starting frame, or a starting frame plus a closing frame. Three pictures belong to the separate reference entry, which this page does not describe.
The current quote depends on resolution. At the same resolution, 4, 6 and 8 seconds have the same credit cost. Check the displayed total before generating.
Other models on this platform that do a similar job, or that pair well with this one.
Generate from a description or animate one starting picture. Choose any whole length from 3 to 15 seconds, switch sound on or off, and pick between the Standard and the Pro product.
Read the guideWan 3.0 is the standard variant of the Wan 3.0 family on this platform: a wide length range, three quality tiers and shape control in both text and image mode.
Read the guideSeedance 2.5 creates a clip from a written description or from one starting image, with whole-second lengths from 4 to 30 seconds and three quality tiers.
Read the guide