search

mayuelala / FollowYourCanvas

[ArXiv 2024] Follow-Your-Canvas: This repo is the official implementation of "Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation"
https://follow-your-canvas.github.io/
95 stars 4 forks source link

Segmentation fault (core dumped) #9

Open levon-khachatryan opened 1 week ago

levon-khachatryan commented 1 week ago

Hi!

First of all, congrats on your great work, and thank you for open-sourcing it!

When I setup a virtual environment using CUDA12.4, python 3.11.10 and install all required packages during inference I get the

/home/levon.khachatryan/projects/VideoSBG/FollowYourCanvas/venv/lib/python3.11/site-packages/transformers/utils/generic.py:441: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( /home/levon.khachatryan/projects/VideoSBG/FollowYourCanvas/venv/lib/python3.11/site-packages/transformers/utils/generic.py:309: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( /home/levon.khachatryan/projects/VideoSBG/FollowYourCanvas/venv/lib/python3.11/site-packages/xformers/ops/fmha/flash.py:211: FutureWarning: torch.library.impl_abstract was renamed to torch.library.register_fake. Please use that instead; we will remove torch.library.impl_abstract in a future version of PyTorch. @torch.library.impl_abstract("xformers_flash::flash_fwd") /home/levon.khachatryan/projects/VideoSBG/FollowYourCanvas/venv/lib/python3.11/site-packages/xformers/ops/fmha/flash.py:344: FutureWarning: torch.library.impl_abstract was renamed to torch.library.register_fake. Please use that instead; we will remove torch.library.impl_abstract in a future version of PyTorch. @torch.library.impl_abstract("xformers_flash::flash_bwd") Segmentation fault (core dumped)

Do you have any idea what might be the reason? Thanks in advance.

levon-khachatryan commented 1 week ago

I am getting the same issue when using CUDA11.8 and python 3.9.20