This is an unofficial PyTorch implementation of the following paper.
Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
Andreas Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn, Seung Wook Kim, Sanja Fidler, Karsten Kreis
https://arxiv.org/abs/2304.08818
from videoldm import VideoLDM
model = VideoLDM.from_pretrained(
'CompVis/stable-diffusion-v1-4',
subfolder='unet',
low_cpu_mem_usage=False
)
- This code builds on diffusers. Thanks for open-sourcing!