Support videoclip with newer version of dependencies

🚀 Feature Request

I hope there could be a code base for videoclip with newer version of dependencies (such as python, pytorch, transformers, diffusers, etc)

Motivation

Recently I am working on a project trying to combine videoclip with diffusion model, but found the denpendencies for videoclip (MMPT) in this repository confilict with modern diffusion models, As the modern diffusion models require newer version of diffusers, transformers and other dependencies.

Pitch

Would you please provide support for videoclip models with newer version of dependencies such as diffusers, transformers, tokenizers, etc?