A preview video model that renders clips from 1 to 15 seconds in three quality tiers, from a description or one starting image.
Preview status means the model is live in the workspace but its behaviour can change between releases. Length, quality tier and shape are the controls you get today.
This workspace offers no sound on/off switch for the model. In the output samples we have checked, finished files carried a sound track, so decide in the edit whether to keep or mute it.
Set length, quality tier and shape before generating. The shape selector stays available when you start from an image, and auto is the default.
Render a single second to check how a description moves, then repeat it at full length within the same 1 to 15 second range.
Leave the shape on auto to let the model decide, or pick an explicit ratio in either mode.
480p, 720p and 1080p, selectable per task with lengths from 1 to 15 seconds.
Place the clip under narration and mute its generated track in the edit so the two do not compete.
One-second renders to explore how a description moves before a longer version.
Animate a still while keeping explicit control of 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 packagesNo. There is no audio on/off switch in this workspace, and the output samples we have checked carried a sound track. Plan to mute it in your edit if you need silence.
From 1 to 15 seconds in whole seconds.
The model is selectable today, but as a preview it can change or be adjusted between platform releases.
Yes. The shape selector stays available in image-to-video mode, including the auto option.
Other models on this platform that do a similar job, or that pair well with this one.
PixVerse V6 Max renders clips from a single second to fifteen, across four quality tiers, from a description or from one uploaded still.
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 guideThe second selectable GPT Image 2.5 product: the same tiers, shapes, background control and credit prices as Flare, with this guide focused on editing your own images.
Read the guide