ByteDance Launches AI Video Model Dreamina Seedance 2.0 in CapCut

While OpenAI appears to be scaling back its video generation ambitions with the shutdown of its Sora app, ByteDance has confirmed the rollout of its new audio and video model, Dreamina Seedance 2.0, within its CapCut editing platform.

The company states the model enables creators to draft, edit, and synchronize video and audio content using text prompts, images, or reference videos.

The release is beginning with CapCut users in Brazil, Indonesia, Malaysia, Mexico, the Philippines, Thailand, and Vietnam, with plans to expand to additional markets gradually.

This CapCut launch follows reports of a paused global rollout for the model as ByteDance addresses intellectual property concerns, including criticism from Hollywood over alleged copyright infringement. This likely explains the initially limited geographic availability.

In China, the model is already accessible to users of ByteDance's Jianying app.

Image Credits:ByteDance

According to ByteDance, the video generation model can work from simple text descriptions, even without reference images. CapCut excels at rendering realistic textures, motion, and lighting across various perspectives, which can be used to edit, enhance, or correct existing footage.

Another application allows creators to prototype and test ideas based on early concepts or sketches before committing to full-scale production.

Furthermore, Dreamina Seedance 2.0 is designed for a broad spectrum of content, including cooking tutorials, fitness guides, business overviews, and action-oriented scenes—areas where AI video models have traditionally struggled.

At launch, the model supports generating clips up to 15 seconds long in six different aspect ratios.

Image Credits:ByteDance

Within CapCut, the model will be integrated into editing features like AI Video and generation tools such as Video Studio. It will also be available on ByteDance's AI platform, Dreamina, and its marketing platform, Pippit.

Due to its capacity for creating realistic content, ByteDance has implemented safety measures, including restrictions on generating videos from media containing real faces. CapCut will also block the unauthorized generation of copyrighted intellectual property. (The ongoing limited U.S. availability suggests these safeguards are still being refined.)

Content produced by Dreamina Seedance 2.0 will include an invisible watermark to help identify AI-generated material when shared outside the platform, assisting with potential takedown requests from rights holders.

ByteDance plans to collaborate with experts and creative communities throughout the rollout to iteratively enhance the model's capabilities.