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
From Prompt to Conditioning Signal

Tokens Become Contextual Vectors

2 / 4
Those token IDs are just addresses. Each one points to a learned vector, a list of numbers, but on its own that vector is context-free. The word "boat" would look identical whether it is a paper boat or a battleship.
0:00 / 0:00

Each token ID indexes a learned embedding vector, but that vector is only a starting point. The sequence then passes through a transformer, where self-attention lets every token look at every other token and update its own representation. The output is a sequence of contextual embeddings: the vector for "boat" already encodes that the boat is paper and that it is drifting. This is why the encoder's output is a sequence, not one vector — each position carries meaning shaped by its neighbors.

参考资料

  1. [1]Attention Is All You Need (Vaswani et al., 2017)arxiv.org
  2. [2]Hugging Face NLP Course: Transformers and attentionhuggingface.co
上一页2 / 4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