Seedance 2.0: FAQ

1. What is Seedance 2.0?

Seedance 2.0 (ByteDance) is a video generation model with native synchronized audio. It runs in two modes: a Keyframe mode for text-to-video and image-to-video, and a Reference mode for multimodal generation driven by reference images, videos, and audio. It's a strong pick for reference-driven and audio-synced work.

2. What resolution and duration does Seedance 2.0 support?

Resolutions:

• 480p (faster, cheaper drafts)

• 720p (balanced)

• 1080p (higher quality)

• 4K (maximum detail, slowest and most expensive)

Durations (clip lengths):

• Any whole number of seconds from 4s to 15s (longer clips cost more)

3. How does Seedance 2.0 handle audio?

Audio is native, synchronized, and on by default:

• Dialogue: enclose spoken lines in double quotes for cleaner sync.

• Sound & ambience: describe them in the prompt.

• Silent output: turn audio generation off.

4. Can you combine inputs with Seedance 2.0 in one prompt?

Yes, and it's a core strength. The two modes are mutually exclusive:

Keyframe mode:

• A Start Frame with an optional End Frame for interpolation.

Reference mode (multimodal):

• Up to 9 reference images

• Up to 3 reference videos (each 4–15s; combined ≤15s; order is semantic, becoming Video 1, 2, 3)

• Up to 3 reference audio clips (each 2–15s; cannot be used alone, must pair with a reference image or video)

Note: you can't mix keyframes and reference inputs in the same generation; pick one mode.

5. What aspect ratios are available?

• 16:9 (landscape)

• 9:16 (portrait / vertical)

• 1:1 (square)

• 4:3, 3:4, 21:9

• adaptive (the model picks based on your inputs)

6. Are keyframes available with the Seedance 2.0 model?

Yes, in Keyframe mode:

• Start Frame: the model animates outward from this image.

• End Frame: optional, requires a Start Frame, and drives keyframe interpolation between the two.

Modes at a glance