Skip to content
Latest Effects
Video / Generate video
  • ByteDance
  • Standard
  • Generate video

Seedance 2.0

Direct complex multimodal scenes with references, motion, and native sound.

Compare Seedance 2.0 settings and cost estimates. Reference-guided character and product video with optional generated audio.

  • Generate video

Seedance 2.0 pricing example

$0.462 Estimated per run

  • Aspect ratio: 16:9
  • Resolution: 480p
  • Duration: 4
  • With audio: false

Estimate checked . This example uses the configuration shown above. Inputs and settings can change the price; check the estimate for your own run before generating. Project storage is billed separately.

How AI usage and project pricing work →

Try a controlled product shot with Seedance 2.0

Start with one approved product image and one camera movement. Use the image as a first frame or reference according to the available inputs above. Set duration and resolution before comparing estimates.

Example direction to try:

A slow camera push toward a green glass bottle on a wet stone table. Keep the bottle shape and label consistent. Soft window light from the left; the background stays still. End on a close view of the condensation.

This is a suggested exercise, not the prompt used to create the preview above. Inspect the output for changing label text, distorted edges, or movement that continues after the intended end frame. Keep the strongest take, trim it on the timeline, and add a separate title layer when exact lettering matters.

Compare references, motion, and total cost

Run the same brief through another video model with compatible reference inputs. Keep duration, resolution, and audio settings comparable. Judge whether the subject stays recognizable throughout the shot and whether the camera follows the direction. Include rejected takes in the cost comparison: a low estimate for one run does not establish the cost of an approved shot.

For a multi-shot film, generate and approve each shot before assembling it. Use the video editor to control pacing and the production plan to budget the sequence.

Curated output references.

Current API configuration

What goes in. What comes back.

The model defines every slot it reads and every result it returns. Required inputs must be present before a run can begin.

Inputs

Prompts and source material

Prompt

Text · Required

First frame

Image and Video · Optional

Last frame

Image and Video · Optional

Image reference

Image · Optional · Up to 5

Video reference

Video · Optional

Outputs

Files and structured results

Video

Video

Available controls

Configure the run.

Control Available values Requirement
Aspect ratio 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and auto Optional
Resolution 480p, 720p, 1080p, and 4K Optional
Duration 4–15 Optional
With audio On, Off Optional
Seed Integer Optional

Works especially well for

  • Reference-heavy character and product scenes, with up to five image references, one video reference, and optional audio.

Know the trade-offs

  • LatestEffects exposes 4–15 seconds and resolution tiers through 4K. Reference limits here are narrower than the vendor's full multimodal interface; no audio-reference input is exposed.

Configure the model.
Keep the result in the cut.

The generation returns to the scene, asset folder and timeline it belongs to.