跳到主要内容
Learn Motion
探索课程产品能力价格

下载 Learn Motion

用手机扫描二维码,下载 App。

App Store

扫码从 App Store 下载 Learn Motion打开商店页面

Google Play

扫码从 Google Play 下载 Learn Motion打开商店页面
登录
Learn Motion

How Text-to-Video AI Works Under the Hood

1From Prompt to Conditioning Signal2Latent Diffusion: Generating Video in Compressed Space3Spatio-Temporal Attention: Keeping Frames Consistent4Where the Pipeline Breaks: Failure Modes and Their Causes
Spatio-Temporal Attention: Keeping Frames Consistent

Linking the Same Place Across Frames

2 / 5
Now stack the frames and run attention along the other axis. Pick one spatial location, and look at the patch sitting there in frame one, frame two, frame three, all the way down.
0:00 / 0:00

Temporal attention runs along the time axis. For a given spatial location, the patch at that location in frame one, frame two, frame three, and onward are treated as a sequence, and each one attends to the others. A patch representing an eye in frame one can therefore pull in the appearance of that same eye in later frames, so the representation stays anchored to one identity instead of being re-decided from scratch each frame. This is what keeps a face recognizable as it turns and a shirt the same color as the person walks.

参考资料

  1. [1]Video Diffusion Modelsarxiv.org
上一页2 / 5下一页

Learn Motion

生成课程,认真学会。

运营方:Wuhan Daoyin Technology Co., Ltd.

联系我们: [email protected]
隐私政策用户服务协议

© 2026 Learn Motion