Trending storyWatching
Google tackles coherent long-form video generation
1 report1 sourceupdated 2 days ago
What happened
Summary
Google 研究博客发了一篇关于自动化生成长视频的文章，重点解决场景切换时的连贯性问题——比如角色长相不突变、背景不穿帮。系统会先规划镜头再逐段生成，算是 Sora 之后 Google 第一次正面回应“长视频”这个方向。但正文没披露模型架构、最大能生多长的视频，也没给定量对比结果。对做视频生成或 AI 电影工具的人来说，方向对，但信息太薄，先打个折看。
Coverage
Follow the reports to see the story from different sides.
Sep 25
- Google Research BlogGoogle tackles coherent long-form video generation
Google published research on automating long-form video generation, focusing on coherence across scene transitions. The post doesn't disclose model architecture or max video length, only that the system plans shots and maintains character/background consistency. For video generation or AI filmmaking practitioners, this is Google's first long-form answer post-Sora, but technical details are thin—take it with a grain of salt.
Heat over time
Not enough continuous observations to draw a trend yet.