Generate from a description or animate a starting picture. Set any whole length from 2 to 15 seconds, choose 720p or 1080p, and pick from five shapes in text mode. This page covers the two generation entries.
Wan 2.7 appears in the text and the image workspace as one entry. Both offer a length slider from 2 to 15 seconds, a quality choice between 720p and 1080p, a negative prompt field, and two switches: prompt extension, which starts on, and watermark, which starts off. Neither entry offers a sound switch.
Text mode offers 16:9, 9:16, 1:1, 4:3 and 3:4, with optional audio upload. Image mode accepts a starting frame with an optional closing frame, or a short video for continuation. It also offers a driving-audio upload. Both entries require a description of up to 5000 characters.
Choose 2–15 seconds in whole seconds and 720p or 1080p. Prompt extension starts on and watermark starts off. Both entries accept a required description of up to 5000 characters and an optional negative prompt of up to 500 characters. Image mode has no separate ratio selector.
Two to fifteen seconds in whole seconds covers everything from a single gesture to a short scene. The slider and the figure move together, so the length is settled before you confirm.
Both entries accept optional audio input. Review the resulting soundtrack and timing before publishing; uploading audio does not guarantee exact synchronization.
In the image entry you can supply a second picture to land on. That is how a move from one composed still to another stays inside a single task instead of being stitched together in the edit.
Upload the voice-over or the music bed first, then set a length that fits it. A 2-second sting and a 14-second explanation both come from the same entry without changing products.
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.
Upload a short clip and describe what should happen next. The selected duration is the total output length, including the input clip; credits apply to that total. Review the transition and motion in the result.
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 packagesThe text-to-video and image-to-video entries, which share the same length range, quality tiers and description limit. Wan 2.7 also appears as a separate reference product and a separate video-edit product, and those are not covered here.
Any whole number of seconds from 2 to 15. The control is a slider and the workspace updates the figure as you move it.
Text mode offers 16:9, 9:16, 1:1, 4:3 and 3:4. Image mode has no separate aspect-ratio selector; check the generated framing before publishing.
Generated clips can include audio. This entry has no sound on/off switch; review the soundtrack and mute it in your editor when you need silence. Both entries accept optional audio input. Review the resulting soundtrack and timing before publishing; uploading audio does not guarantee exact synchronization.
Use a starting frame with an optional closing frame, or a continuation clip. In this workspace, a clip cannot be combined with either frame image.
The figure follows the length and the quality tier you pick, and the workspace shows the total for those exact settings before you confirm. Upload a short clip and describe what should happen next. The selected duration is the total output length, including the input clip; credits apply to that total. Review the transition and motion in the result.
Other models on this platform that do a similar job, or that pair well with this one.
Generate from a description, animate one starting picture, or restyle a clip you already own. Text and image tasks run 5, 10 or 15 seconds at 720p or 1080p; tasks that start from a video run 5 or 10 seconds.
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