[Feature Request] Text to video model

[Wendong-Fan]

Required prerequisites

• [X] I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
• [ ] Consider asking first in a Discussion.

Motivation

further enhance CAMEL's mult-modal capability, integrate text to video model

Solution

https://github.com/THUDM/CogVideo

Alternatives

No response

Additional context

No response