Seedance 2.0 adopts a unified multimodal audio-video joint generation architecture that supports text, image, audio, and video inputs, leading to the most comprehensive multimodal content reference and editing capabilities in the industry.
Immersive Audio-visual Experience
Featuring exceptional motion stability and audio-video joint generation, Seedance 2.0 delivers an ultra-realistic immersive experience.
Create with Director-level Control
Supporting images, audios and videos as references, Seedance 2.0 enables creators to transform an idea into visuals with full control over performance, lighting, shadow, and camera movement.
Empower Creativity
Seedance 2.0 delivers cinematic output aligned with industry standards, driving efficiency gains across the industry.
Model Performance
Below are the results of Seedance 2.0 in internal benchmarks using SeedVideoBench-2.0.
SeedVideoBench-2.0: Multi-Dimensional Evaluation
Seedance 2.0 is in the leading position in various dimensions across different types of tasks.
Text-to-Video Radar Chart
Image-to-Video Radar Chart
Multimodal Task Radar Chart
