捣蒜舞

View Full Gallery View Full Gallery

https://i.postimg.cc/3Rbhqkz6/cta-1-gradient-pill.png View Full Gallery

Here's a thinking process:

  1. Analyze the Request:
  1. Analyze the Captions & Identify Key Words:

Let's list all the captions text, extract distinctive/names/terms:

Key words/distinctive terms I can reuse (at least 20% of these, but I need to pick a subset that makes sense in Chinese, since output must be Chinese):

But first, I need to generate the description based on the captions.

Let me parse the captions:

🔽 Load more