Generate a clip of 5 or 10 seconds from a description, or animate one picture you already have. Both workspaces offer five shapes, two quality tiers and an optional watermark text field.
Runway appears as one entry in each video workspace. Both take 5 or 10 seconds, a quality tier of 720p or 1080p, a shape from 16:9, 9:16, 1:1, 4:3 or 3:4, and an optional watermark text field that adds the wording you type to the picture.
The text entry needs only a description. The image entry animates exactly one picture, and a description left empty is sent as a short instruction asking for natural motion. Ten seconds renders at the lower tier, so the higher tier belongs to the five-second length.
Choose 5 or 10 seconds, 720p or 1080p — ten seconds renders at 720p — and a shape from 16:9, 9:16, 1:1, 4:3 or 3:4. Both workspaces take an optional watermark text. There is no sound switch, no negative prompt, no strength control and no seed field.
Pick 16:9 for landscape players, 9:16 for vertical feeds, 1:1 for grids, or 4:3 and 3:4 when the placement is wider or taller than the usual feeds. The same five shapes are offered in both workspaces.
The watermark field adds the text you type to the finished picture, so a working file can carry a name or a date before it leaves the workspace. An empty field sends nothing.
Choose 5 or 10 seconds and 720p or 1080p. The ten-second length is delivered at 720p, so the two settings are not independent: the five-second length is the one that can use the higher tier.
Type a name or a date into the watermark field, generate from one description, and check the delivered file before it goes into an edit.
Start from a picture that has already been signed off, describe the motion, and keep the shape that matches the placement it was designed for.
Generate the same description in 16:9 and again in 9:16, then compare the two results side by side instead of rewriting the brief for each channel.
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 packages5 or 10 seconds, in both workspaces. The ten-second length is delivered at 720p, so the higher tier is only available at five seconds.
Yes, in both workspaces: 16:9, 9:16, 1:1, 4:3 or 3:4. The shape selector stays available when you animate a picture.
There is no sound on or off switch, and audio is not something you can set here. Check the delivered file and mute it in your editor when you need silence.
It adds the text you type to the finished picture. Leave it empty to send no text, and treat it as a label on the clip rather than a control over the result.
No. The image entry takes exactly one starting picture. There is no closing frame, no reference set and no second start frame.
The figure is set by the length and the tier you pick, and one task is quoted as one generation rather than per second. The workspace shows the total for your exact settings before you confirm.
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, in 5 or 10 seconds. Both workspaces carry a negative prompt and a CFG Scale field, and the image entry takes a closing frame.
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 guideGenerate 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.
Read the guide