Multi-reference concepts
Combine visual, motion, and audio direction when a text prompt alone cannot communicate the full brief.
A multimodal video model from ByteDance Seed built around text, image, audio, and video references with joint audio-video generation and detailed creative direction.
Published model guide. Production integration planned.

Upload Video
mp4, mov, webm, m4v, gif · up to 500MB · 1s minimum
The official model supports text, image, audio, and video inputs in one generation architecture, allowing several types of context to shape a result.
Seedance 2.0 is designed to create motion and sound together instead of treating audio as a separate finishing step.
Reference materials and prompts can guide performance, lighting, shadow, and camera movement for more intentional scene direction.

Published model facts and current UnblurVideo status, last checked 2026-09-27.
This public guide is the canonical UnblurVideo page for Seedance 2.0 and clearly separates published model capabilities from the current product integration.
Its model design is most useful when the brief depends on several reference types or when picture and sound need to be planned together.
Combine visual, motion, and audio direction when a text prompt alone cannot communicate the full brief.
Describe acting, staging, lighting, and camera movement as connected parts of the same shot.
Explore scenes where dialogue, ambience, or sound cues are part of the concept from the beginning.
Seedance 2.0 is not in the production generation allowlist yet.
Plan the inputs first, then use the fewest references needed to communicate the shot clearly.
Write the subject, action, setting, camera movement, lighting, and intended sound as one concise direction.
Use images for appearance, video for movement, and audio only when each reference contributes information the prompt cannot express precisely.
Check the provider variant, accepted inputs, duration, resolution, and cost before generating; those product limits can differ from the model family overview.
Upload Video
mp4, mov, webm, m4v, gif · up to 500MB · 1s minimum
ByteDance describes Seedance 2.0 as supporting text, image, audio, and video inputs in a unified multimodal architecture.
Yes. The official model description includes joint audio-video generation. The exact audio controls available on UnblurVideo will depend on the provider integration.
Not yet. The current production generator does not include Seedance 2.0, and UnblurVideo will not replace it with a different model without telling you.
No. They are separate model versions. Seedance 1.5 Pro is currently available in the UnblurVideo generator, while this page covers Seedance 2.0.
Source for this guide: ByteDance Seed model page.
Compare current production models, supported settings, duration, and credit cost before submitting a job.