ByteDance’s new AI video creation model, Dreamina Seedance 2.0, is coming to CapCut

OpenAI may be stepping back from its efforts in the video creation market with the shutdown of its Sora app, but ByteDance confirmed Thursday that its new audio and video model, Dreamina Seedance 2.0, is now rolling out to its editing platform, CapCut.

ByteDance says the model allows creators to craft, edit and sync video and audio content using prompts, images or reference videos.

The phased rollout will begin for CapCut users in Brazil, Indonesia, Malaysia, Mexico, Philippines, Thailand and Vietnam, with more markets added over time.

CapCut’s launch news comes on the heels of a recent report that the global rollout of the model will be paused, while it works to address intellectual property issues that have drawn criticism from Hollywood over alleged copyright infringement. This likely explains the limited number of markets the model is currently available within CapCut.

In China, the model is available to users of ByteDance’s Jianying app.

The video creation model works without reference images, even if the creator uses just a few words to describe the scene they have in mind, ByteDance said in its announcement. CapCut is also good at rendering realistic textures, motion, and lighting across a range of visual perspectives and angles, which the company notes can be used to edit, enhance, or correct creators’ shots.

Another use case is to allow creatives to test potential ideas based on early concepts or sketches before shooting the actual video.

Additionally, Dreamina Seedance 2.0 can be used for a wide range of content, including cooking recipes, fitness tutorials, business or product overviews, and videos with action or motion-focused content, where AI video models have historically faced challenges, the company explains.

At launch, the model supports clips of up to 15 seconds across six aspect ratios.

At CapCut, the model will be rolled out across different regions, including editing features like AI Video and creation tools like Video Studio. It will also come to ByteDance’s AI generation platform, Dreamina, and its marketing platform, Pippit.

Given its ability to create photorealistic content, ByteDance says it has added safety restrictions, so the model will not have the ability to create videos from photos or videos containing real faces. CapCut will also prohibit unauthorized use of intellectual property. (However, if the restrictions had worked properly, the model would now be available in the US. More modifications are likely still in the works.)

ByteDance added that content produced by Dreamina Seedance 2.0 will also include an invisible watermark, which will help identify content created using the model when shared outside the platform. This can help with things like takedown requests from rights holders if the form allows copyright content to pass through.

ByteDance says it will collaborate with experts and creative communities as the model rolls out to iterate and improve the model’s capabilities.