ByteDance confirmed on Thursday that it will be rolling out its new audio and video model, Dreamina Seedance 2.0, on its editing platform CapCut. The company said the model allows creators to draft, edit, and sync video and audio content by using prompts, images, or reference videos.
The phased rollout would begin with CapCut users in Brazil, Indonesia, Malaysia, Mexico, the Philippines, Thailand, and Vietnam. More markets will be added over time.
The news of this rollout came following a recent report that said the model’s global rollout would be paused, while it worked to address intellectual property issues that drew criticism from Hollywood over alleged copyright infringement. This might explain the limited number of markets where this model is available through CapCut. In China, the model is available to users of ByteDance’s Jianying app.
READ: TikTok’s parent ByteDance valued at $550 billion in a proposed sale (February 25, 2026)
Dreamina Seedance 2.0 works without reference images, even if the creator only uses a few words to describe the scene they have in mind, according to ByteDance. CapCut is also good at rendering realistic textures, movement, and lighting across a range of visual perspectives and angles, which the company notes could be used to edit, enhance, or correct creators’ own footage.
ByteDance also mentioned that 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 motion or action-focused content, where AI video models have historically faced challenges. At launch, the model supports clips of up to 15 seconds long across six aspect ratios.
ByteDance also said it has added safety restrictions, so the model won’t have the ability to make videos from images or videos that contain real faces. CapCut will also block the use of unauthorized generation of intellectual property. The content made by the model will also contain an invisible watermark which will help to identify content made with the model when it’s shared off-platform. This can help with takedown requests from copyright holders, in the event that the model allows copyright content through.
READ: China’s ByteDance partners with Samsung to develop AI chip (February 11, 2026)
In CapCut, Dreamina Seedance 2.0 will be rolled out across different areas, including editing features such as AI Video and generation tools like Video Studio. It will also come to ByteDance’s AI generation platform, Dreamina, and its marketing platform, Pippit.
This comes shortly after OpenAI shut down Sora, its artificial intelligence video-generation app, in less than two years after its launch. The ChatGPT-maker also revealed it will wind down its $1 billion partnership with Disney. According to reports, this move is part of efforts by OpenAI to focus its business on potentially more lucrative areas such as coding tools and corporate customers.