Seedance 2.0

Seedance 2.0

Seedance 2.0 is ByteDance's multimodal video model: text, stills, video clips, and audio share one input space, and a single generation returns picture plus soundtrack together. Dialogue, Foley, and score stay locked to the frames without a separate audio stage.

That shared input space lets you steer with references instead of only prose - a still for appearance, a clip for motion language, a track for rhythm - then describe how they should combine in plain English.

Why choose Seedance 2.0

Key strengths

• Multimodal direction: images, video clips, and audio can each contribute composition, motion, identity, pacing, or sound cues.
• Strong control over complex movement, multi-subject interaction, camera direction, and continuity across a short sequence.
• Joint audio-video generation supports dialogue, ambience, music, and effects that belong to the scene instead of feeling added later.

Good fit for

• Short narrative sequences that need several coordinated shots.
• Character, product, or location work anchored by multiple reference assets.
• Dialogue, music-led, or sound-driven scenes where timing matters.
• Transitions between a supplied first and last frame.

Inputs and output settings

This table reflects the model routes and controls currently exposed by MachGen.

Using Seedance 2.0

1. Choose a supported generation mode in Playground.
2. Add the required prompt and source or reference assets.
3. Select output settings from the controls shown for that mode.
4. Generate, then inspect the returned asset before reusing the settings through the API.

Practical guidance

• Describe the subject, action or composition, environment, and visual direction in a clear order.
• For image animation, describe the intended motion and camera behavior instead of repeating what is already visible.
• Give each reference a clear role in the prompt, using the names inserted by the Playground.
• Use compatible start and end frames, then describe the transition between them.
• When audio is enabled, include any dialogue, ambience, or sound cues that matter to the scene.

Prompting notes

• Give each reference a short subject name, then use the inserted @name token when the prompt should call it out.
• State the role of every image, video, or audio reference instead of asking the model to copy all of it.
• Write actions, camera direction, dialogue, and sound cues in chronological order.
• For edits or transitions, state both what should change and what must remain consistent.

How to get better Seedance 2.0 results

• Assign every reference a specific role. Say which image defines the character, which clip defines motion, and which audio file defines voice or rhythm.
• Write multi-shot prompts in chronological order and give each shot one main action, camera instruction, and transition.
• For consistent characters, repeat stable visual anchors such as clothing, silhouette, age, and lighting instead of relying on a name alone.
• Start with fewer references and a shorter clip. Add assets only when each one contributes information the prompt cannot express clearly.

Limits and availability

• MachGen admits only the modes and settings listed above for this catalog model.
• Source assets must finish uploading before a request can be submitted.
• Generated results can vary between requests, including when the same prompt and settings are reused.
• Seedance 2.0 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

Learn more

For model background, technical details, and architecture, see the official Seedance 2.0 page.

Try this model in the MachGen Playground.

Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.

Seedance 2.0 pricing

See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.

Seedance 2.0 on MachGen

Deployment: Pass-through. Seedance 2.0 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

The Playground and API sections on this page list the inputs and output settings exposed for this model.