Pooled Text Embedding

[ryancll]

I notice that you use pooled text embedding for T2V models. Using full text embedding for T2I and T2V models should be an good alternative (like officical Latte). Hope this option will be available.

https://github.com/NUS-HPC-AI-Lab/OpenDiT/blob/c15d82b738d0efb7f8f9e79c2f5277cbb417c8e2/opendit/embed/clip_text_emb.py#L86

[KKZ20]

Thanks for your advice! We will try it!