Seedance 2.0 logo

Seedance 2.0

Free

An image-to-video and text-to-video model developed by Niobotics ByteDance.

FreeFree tier
Inputs: text, image, audio, videoOutputs: video
Type
Open Source
Company
ByteDance

About Seedance 2.0

Seedance 2.0 is a unified multimodal audio-video joint generation model developed by ByteDance. It supports text, image, audio, and video inputs, enabling the most comprehensive multimodal content reference and editing capabilities in the industry. The model achieves leading performance across various task types, including text-to-video, image-to-video, and multimodal tasks, as demonstrated by the SeedVideoBench-2.0 evaluation.

Key Features

Unified multimodal audio-video joint generation architecture
Supports text, image, audio, and video inputs
Comprehensive multimodal content reference and editing capabilities
Leading performance across Text-to-Video, Image-to-Video, and Multimodal tasks

Pros & Cons

Pros
  • State-of-the-art performance across multiple task types as per SeedVideoBench-2.0
  • Supports a wide range of input modalities (text, image, audio, video)
  • Offers advanced content reference and editing capabilities

Best For

Generate videos from text descriptionsCreate videos from images with added motionProduce videos driven by audio inputsEdit videos by referencing multiple modalities (text, images, audio)