Seedance 2.0: Advancing Video Generation for World Complexity

TL;DR

Seedance 2.0 is a comprehensive multi-modal audio-video generation model supporting text, image, audio, and video inputs, with significant improvements in quality, efficiency, and multi-modal capabilities, released in China in 2026.

Contribution

It introduces a unified large-scale architecture for multi-modal audio-video generation supporting four input modalities with industry-leading content reference and editing features.

Findings

Performance on par with leading models in expert and user evaluations.

Supports 4 to 15 seconds audio-video content at 480p and 720p resolutions.

Provides an accelerated Fast version for low-latency applications.

Abstract

Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users.