OpenAI may be returning its efforts to the video production market by shutting down its Sora app, but ByteDance confirmed Thursday that its new audio and video model, Dreamina Seedance 2.0now live on its editing platform, CapCut.
ByteDance says the model allows creators to design, edit and sync video and audio content using prompts, images or reference videos.
The rollout will begin with CapCut users in Brazil, Indonesia, Malaysia, Mexico, the Philippines, Thailand and Vietnam, with more markets to be added over time.
The news of the CapCut release follows a recent report that said the model’s global release would be halted while it worked to address intellectual property issues that drew criticism from Hollywood. alleged copyright infringement. This probably explains the limited number of markets where the model is currently available on CapCut.
In China, the model is available to users of ByteDance’s Jianying app.
The video production model works without reference images, even if the creator uses only a few words to describe the scene in mind, ByteDance says. communication. CapCut is also good at rendering realistic textures, motion and lighting across a range of visual perspectives and angles, which the company notes could be used to edit, enhance or correct creators’ footage.
Another use case would be to allow creators to test potential ideas based on early ideas or sketches before shooting the actual video.
In addition, 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, the company explains.
At launch, the model supports clips of up to 15 seconds in six aspect ratios.
In CapCut, the model will be developed in different areas, including editing functions such as AI Video and production tools such as Video Studio. It will also come to ByteDance’s AI production platform, Dreamina, and its marketing platform, Pippit.
Given its ability to create realistic content, ByteDance says it has added security restrictions, so the model won’t be able to create videos from images or videos containing real faces. CapCut will also prevent the use of unauthorized creation of intellectual property. (However, if the restrictions worked correctly, the model would be available now in the United States. More modifications are likely still in the works.)
Content produced by Dreamina Seedance 2.0 will also include an invisible watermark, which will help identify content created with the model when shared off-platform, ByteDance added. This could help with things like takedown requests from rights holders if the model allowed copyright content to pass through.
ByteDance says it will work with experts and creative communities as the model rolls out to iterate and improve the model’s capabilities.
