SeeDance 2.0
Multi-Modal
text-to-videoimage-to-videovideo-to-video
Combine image, video, and audio inputs into one generation
Multi-Modal
Combine image, video, and audio inputs into one generation
0/2 frames selectedUpload up to 9 images total, including start and end framesMax 10MB per image
Start Frame*
End Frame(Optional)
Upload up to 3 extra videos as multi-modal inputs
0 / 2000
Tip: Be detailed and specific for better results. Describe the subject, style, lighting, mood, and composition.
Available Credits
--
"Blend uploaded frames, reference clips, and audio into one cinematic short video"
Example Gallery
See what you can create with multi modal