[Feature Request]: Implement Nvidia's VideoLDM using the unofficial implementation

[kabachuha]

Is there an existing issue for this?

• I have searched the existing issues and checked the recent builds/commits

What would your feature do ?

Allow using the high-resolution VideoLDM model which is also using StableDiffusion as a base model

See https://github.com/srpkdyy/VideoLDM/ as a reference

srpkdyy's model is implemented for Diffusers, need to convert it for PyTorch

Proposed workflow

1. Same things as always, but using the more advanced HighRes model

Additional information

No response

[Maki9009]

any updates on this? it would be great to be able to create videos using any stable diffusion model