西方至今没有文生视频模型能接近字节跳动的 Seedance 2.0,而 Seedance 2.5 已就绪。原因可能是 Seedance 拥有海量视频素材且版权审查不严,但谷歌同样有 YouTube 却未产出类似模型。当前市场对视频模型关注度低,因其更像噱头,LLM 在 SWE 等关键领域的进步更为重要——OpenAI 已完全暂停 Sora。消费者视频并非终局,视频模型更大的意义在于作为早期世界模型学习物理世界动态。Dreamina Seedance 2.5 即将在 CapCut Web、桌面和移动端上线,支持最多 50 个多模态参考、30 秒单镜头生成与编辑,提供更精细的创意控制和更可靠的结果。
Still, no Western text-to-video model comes close to Seedance 2.0, and Seedance 2.5 is already ready.
There are certainly several explanations for this. One of them is that it is often at least claimed that this is because Seedance has access to such a vast amount of video material and does not take copyright protection all that seriously. That is a vague assumption, and honestly, I cannot imagine it being the only reason. Google, in turn, has YouTube, a platform with countless videos that could surely be used to train good models. Just remember when Mira Murati was asked how they had trained Sora and whether YouTube videos had been used for it.