Chubby♨️@kimmonismus

2026-07-04 17:22·14小时前

AI 摘要

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.

Be that as it may， the more questionable issue is why there seems to be so little interest and focus on video models. My assumption is that they are simply not relevant. They are basically a nice gimmick， but currently negligible in the race for the best models. More specifically， the focus on LLMs， which are making outstanding progress in important areas such as SWE， is simply so much more important for winning overall that one would not use compute for video models instead. OpenAI is known to have completely ended Sora for the moment.

Maybe the more important point is that consumer video is probably not the real endgame for AI video models. Yes， they are useful for creators， ads， short-form content and entertainment， and for ByteDance this obviously fits perfectly into CapCut， Dreamina and TikTok. But strategically， the bigger reason to train these systems may be that video is one of the richest training signals we have for learning the dynamics of the physical world： motion， causality， object permanence， spatial consistency and interaction. In that sense， video models are not just content generators， but early world models （Google， NVIDIA）. Or in short： for Western labs， AI video segments for the consumer sector are too cost-inefficient with too little real benefit.

Chubby♨️@kimmonismus · X

48导出 Markdown

2026-07-04 17:22·14小时前

在 X 看原推· x.com

AI 摘要

Still， no Western text-to-video model comes close to Seedance 2.0， and Seedance 2.5 is already ready.