ByteDance

Seedance 1.5

Seedance 1.5 Pro is ByteDance's joint audio-video model for text-driven and image-driven clips. It is designed for prompts that combine action, camera direction, dialogue, ambient sound, and music, and can use first and last frames to constrain the visual transition.

How to use this model

  1. 1

    Write the visual action and the desired audio in the same prompt, separating dialogue, sound effects, and music clearly.

  2. 2

    Upload a first-frame image when the initial composition or character appearance must be preserved.

  3. 3

    Add a last-frame image only together with a first frame, and describe the motion connecting the two states.

  4. 4

    Choose duration and aspect ratio for the target placement; enable generated audio only when the prompt includes a deliberate sound plan.

  5. 5

    Review lip movement, action timing, and sound synchronization together rather than judging the picture alone.

1.5 ProAvailable

1.5 Pro

This version combines visual direction and sound design in one generation. It can start from an image, optionally target a last frame, and generate dialogue, effects, ambience, or music described in the prompt.

Try now

Properties

  • Joint audio-video generation with text-to-video and image-driven inputs.
  • Optional first/last-frame guidance; the last frame requires a first frame.

How to use this model

  1. 1

    Describe visual action and sound as coordinated events on one timeline.

  2. 2

    Add a first frame for composition control; add a last frame only with the first.

  3. 3

    Select duration, aspect ratio, and whether audio should be generated.

  4. 4

    Review action timing and audio synchronization together.

Examples

A reviewed video output created with 1.5 Pro in Omnipix.

Parameters

FPS

fps
Optional

Frame rate (frames per second)

Default: 24

  • 24

Seed

seed
Optional

Random seed. Set for reproducible generation

Image

image
Optional

Input image for image-to-video generation

Prompt

prompt
Required

Text prompt for video generation

Duration

duration
Optional

Video duration in seconds: min: 2, max: 12, default: 5

Default: 5Range: 2 – 12

Aspect Ratio

aspect_ratio
Optional

Video aspect ratio. Ignored if an image is used.

Default: 16:9

  • 21:9

  • 16:9

  • 4:3

  • 1:1

  • 3:4

  • 9:16

  • 9:21

Camera Fixed

camera_fixed
Optional

Whether to fix camera position

Default: false

Generate Audio

generate_audio
Optional

Generate audio synchronized with the video. When enabled, the model outputs a video with audio that matches the visuals.

Default: false

Last Frame Image

last_frame_image
Optional

Input image for last frame generation. This only works if an image start frame is given too.