There are plenty of prompt options, or you can write your own:

• Move the camera forward.
• Move the camera left.
• Move the camera right.
• Move the camera down.
• Rotate the camera 45 degrees to the left.
• Rotate the camera 45 degrees to the right.
• Turn the camera to a top-down view.
• Turn the camera to a wide-angle lens.
• Turn the camera to a close-up. ... There are many possibilities; you can try them yourself.

Usage Tutorial: YouTube: https://youtu.be/UGdW8W1MqW8

Bilibili: https://www.bilibili.com/video/BV1oi1gBBEZV/

I noticed some people wanted to see a comparison between LoRa and the model's native capabilities, so I ran a test. The trained model is indeed more powerful and intelligent, but the base model itself already possesses solid capabilities. It is very powerful—that's why we love this model, and why we need to further tap into its potential.