Available now

Seedance 2.0: video from references

By ByteDance

Seedance 2.0 is ByteDance's video model. It makes clips of 4 to 15 seconds with sound from a prompt, a first frame or reference images.

Model ID
Maker
ByteDance

Input

Fields marked * are required. Review the price before generating.

The text prompt used to generate the video.

Example prompt. Edit it or write your own.

Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP, BMP, TIFF, GIF, HEIC, HEIF. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB · 0/9

Duration of the video in seconds.

Additional settings

Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech.

Starting price$0.56 / run

You sign up first. Your settings are kept.

About this model

Overview

Seedance 2.0 renders 480p, 720p or 1080p video (references up to 720p), 4 to 15 seconds long, in six aspect ratios from 21:9 to 9:16. Sound effects, ambience and lip-synced speech are generated with the picture by default; you can turn sound off.

The image mode starts from a first frame and can end on a last frame you upload. The reference mode follows up to 9 images, which you call @Image1, @Image2 and so on in the prompt.

What you can build

  • Dialogue scenes with matching lip movement
  • A move from one still image to a second one
  • Character or product clips that follow your reference images
  • One idea in ultrawide, square and vertical versions

Prompting tips

  • Put spoken lines in quotation marks and name the speaker so the voice lands on the right face.
  • Tell the model what each reference is: "@Image1 is the dancer, @Image2 is the stage".
  • Describe the sound with the picture: footsteps, wind, a crowd, music in the next room.

What to check

Watch the full clip for changing faces, objects and background details. Check generated speech and effects before sharing.

Inputs

  • Prompt (required): The text prompt used to generate the video.
  • Images (optional): Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP, BMP, TIFF, GIF, HEIC, HEIF. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12.
  • Resolution (optional) Options: 480p, 720p.
  • Duration (optional): Duration of the video in seconds. Options: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
  • Aspect Ratio (optional): The aspect ratio of the generated video. Options: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
  • Generate Audio (optional): Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech.

Output and limits

  • Length: 4 seconds to 15 seconds.
  • Resolutions: 480p, 720p.
  • Aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
  • Sound can be generated together with the video.
  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 480p · 5 s · up to: $0.56 / run
  • 720p · 5 s · up to: $1.21 / run