search

nihaomiao / CVPR23_LFDM

The pytorch implementation of our CVPR 2023 paper "Conditional Image-to-Video Generation with Latent Flow Diffusion Models"
BSD 2-Clause "Simplified" License
443 stars 42 forks source link

Hardware Requirements #10

Closed emjay73 closed 1 year ago

emjay73 commented 1 year ago

Thank you for sharing the code!

Can you also share the hardware environment required to run this code? (minimum memory requirements, GPU spec.. etc)

nihaomiao commented 1 year ago

Hi, @emjay73, I think 24GB should be enough for training with a small batch size according to my preliminary experiments. The released model checkpoints are trained with one A100 (~81GB).

emjay73 commented 1 year ago

Oh I get it. Thanks!