Instructions for Use:

1. Upload images that are preferably front-facing photos of the upper body or above.

2. Both music style and lyrics support Chinese input.

3. Music duration: 60 seconds. 1=1 minute, and so on.

4. Mode selection: 1, 2, 3

Option "1" is to use your own created lyrics and songs to generate a digital human.

Option "2" is to use the audio songs you upload to generate a digital human.

Option "3" is to use the video songs you upload to generate a digital human.

5. The two mode selections must remain consistent

For example, if the first mode selects "1," the second model must also select "1."

If you use "1" to generate a created song, you don't need to upload audio or video, and so on.

6. Synchronize audio duration options

Follow the duration of your audio. For example, if the audio is 60 seconds, then input 60. 1=61, and so on.