All models

Video generation

Seedance 1.5 Pro

Plan a shot around its opening and closing frames.

Loading model settings…

Your prompt, settings, and references stay together in a new Canvas.

01 / Meet the model

What can Seedance 1.5 Pro do?

Seedance 1.5 Pro provides text and frame-guided video workflows with optional audio. Its first- and last-frame controls are useful when you already know the two visual endpoints of a shot. Describe a plausible transition between them rather than expecting exact interpolation of every detail.

02 / Choose it for

Where Seedance 1.5 Pro fits best

Transition planning

define where a shot begins and where it should end.

Motion drafts

use a lower resolution to review timing before a larger output.

Silent or audio versions

choose whether the clip needs generated sound.

03 / Before you create

Seedance 1.5 Pro specifications

Model settings. Availability, input mode, and references can narrow the choices offered in Canvas.

Inputs on this page
Text prompt · Start frame · End frame
Aspect ratios
1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 21:9
Resolution
480p · 720p · 1080p
Duration
4–12 seconds
Audio
Optional generated audio
Frame guidance
Start frame + optional end frame
Default output
480p · 6s · 16:9

04 / A closer look

Questions about Seedance 1.5 Pro

Can I use the last frame on its own?

Use a starting image for a frame-guided shot, then add an ending image if needed. The last frame is an endpoint for that transition, not a replacement for the starting frame.

What can I use as input for Seedance 1.5 Pro?

Text prompt · Start frame · End frame. The input controls above show the options available for your selected mode.

Which formats does Seedance 1.5 Pro support?

1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 21:9. 480p · 720p · 1080p.

How do I choose settings for Seedance 1.5 Pro?

Start with the format you intend to publish, then choose the available output settings. Changing inputs can change the choices. Review the current Gem estimate before Generate; availability and cost can vary.

Explore another approach

Browse all models →