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

kabachuha / sd-webui-text2video

Auto1111 extension implementing text2video diffusion models (like ModelScope or VideoCrafter) using only Auto1111 webui dependencies

Other

1.28k stars 106 forks source link

[Feature Request]: Implement Nvidia's VideoLDM using the unofficial implementation #169

Open kabachuha opened 1 year ago

kabachuha commented 1 year ago

Is there an existing issue for this?

[X] 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

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

Additional information

No response

Maki9009 commented 1 year ago

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