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.
Choose text to video for a written description, image to video for one starting picture, or video to video for one source clip. The buttons on this page open all three workspaces with Wan 2.6 selected.
Length is where the workspaces differ. Text and image tasks offer 5, 10 and 15 seconds. A task that starts from a video offers 5 and 10 seconds only — 15 seconds is not on that entry, so a longer result has to come from the text or image workspace. Every entry offers 720p and 1080p.
Pick the workspace first, then a length, 720p or 1080p, and the Multi-shots switch if you want it. There is no shape selector and no sound switch on this model. Descriptions are capped at 2000 characters in the text and image workspaces, and are required in the text workspace.
Begin with nothing but a description, with a single picture you have already approved, or with an owned clip whose look you want changed. The controls stay familiar across the three, so switching the starting point does not mean relearning the panel.
Enable Multi-shots when you want to request multiple shots within a clip. It is off by default. Review the generated transitions before using the result.
720p and 1080p are offered on every entry, and 5, 10 and 15 seconds on the text and image entries. The number changes with the pair you pick, which makes it easy to weigh a 15-second plan against two shorter ones before you commit.
When 5 seconds is too short for the story, move to 10 or 15 in the text or image workspace and weigh the number against two separate shorter tasks before you decide how to spend the credits.
Open the video-to-video entry with a clip from your own library, describe the look you want instead, and keep the length at 5 or 10 seconds to match the source you are working from.
Choose source material with the subject positioned for your intended placement. Check the generated framing and crop the final clip if needed; source proportions do not guarantee the output shape.
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 packagesText to video, image to video and video to video. Use the corresponding button on this page to open Wan 2.6 in that workspace.
5, 10 or 15 seconds in the text and image workspaces, and 5 or 10 seconds in the video-to-video workspace. Fifteen seconds is not offered on a task that starts from a video.
Enable Multi-shots when you want to request multiple shots within a clip. It is off by default. Review the generated transitions before using the result.
There is no aspect-ratio selector. Prepare your source material for the intended composition, then check the output framing before publishing.
There is no sound switch. Listen to the generated result before publishing, and mute or replace its audio in editing when needed.
One. The image workspace takes one starting picture and the video-to-video workspace one source clip. There are no other material slots on this model.
In the text workspace and in the video-to-video workspace, yes. In the image workspace you can leave it empty and the workspace sends a short instruction asking for natural motion. The limit is 2000 characters in the text and image workspaces.
The number rises with the length you pick and with the quality setting, and is shown per task before you confirm. Because the video-to-video entry stops at 10 seconds, a 15-second plan always comes from the text or image workspace.
Other models on this platform that do a similar job, or that pair well with this one.
Wan 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 guideWan 3.0 Prime is the second selectable product in the Wan 3.0 family: the same controls and length range as the standard variant, quoted at a higher credit rate.
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