ByteDance Launches AI Model for Video Production in CapCut

This article was generated with the help of AI and may contain errors.

ByteDance has launched its new AI model for video production, Dreamina Seedance 2.0, within the editing platform CapCut. The model enables creators to produce, edit, and synchronize video and audio content using text prompts, images, or reference videos.

Dreamina Seedance 2.0 Rolls Out in CapCut

The gradual rollout of Dreamina Seedance 2.0 begins with users in Brazil, Indonesia, Malaysia, Mexico, the Philippines, Thailand, and Vietnam, with additional markets to be added over time. This launch follows earlier reports that the global rollout had been paused to address intellectual property concerns, which drew criticism from Hollywood over alleged copyright infringements.

The model operates without reference images, meaning creators can use just a few words to describe the scene they want to create. CapCut is also capable of rendering realistic textures, movements, and lighting from various visual perspectives. This can be used to edit, enhance, or correct existing footage. Dreamina Seedance 2.0 supports content such as recipes, workout tutorials, business overviews, and motion videos—areas where AI models have previously faced challenges. At launch, the model supports clips up to 15 seconds in six different aspect ratios. ByteDance has also implemented safety restrictions to prevent the model from generating videos from images or videos containing real faces. Content created with Dreamina Seedance 2.0 will include an invisible watermark to identify the content when shared outside the platform.

Implications for U.S. Creators and the Market

AIny brief analysis: ByteDance’s launch of Dreamina Seedance 2.0 offers U.S. creators new AI-powered tools for video production, potentially boosting creativity and innovation in content creation. With its focus on addressing copyright concerns, this development may also help strengthen intellectual property protections for creators in the American market.

Source: TechCrunch

Read the full story in Norwegian

Les på norsk

Read also: Gemini 3.1 Flash Live: Enhancing AI Voice with Natural Conversations