Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Help with "out of memory" message #18

Open
ClothingAI opened this issue Aug 24, 2024 · 3 comments
Open

Help with "out of memory" message #18

ClothingAI opened this issue Aug 24, 2024 · 3 comments

Comments

@ClothingAI
Copy link

Hey
I usually have a good GPU,
but I recently got a problem with pytorch library in comfyui so i tried to fix it and it seemed to work fine,
but when I tried catVTON (which caused this problem with pytorch btw)
I got this error:
`!!! Exception during processing !!! Allocation on device
Traceback (most recent call last):
File "C:\Users\aaas\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 317, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.....
...
File "C:\Users\aaas\AI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_CatVTON_Wrapper\py\catvton\attn_processor.py", line 88, in call
hidden_states = F.scaled_dot_product_attention(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
torch.OutOfMemoryError: Allocation on device

Got an OOM, unloading all loaded models.
`

I tried modifyin the choice of segmentation model in that particular node, but same result!
What is wrong?
Thanks

@kaishanguai2012
Copy link

same.Strangely, I successfully ran the workflow once and then encountered this issue when I ran it again.

@ClothingAI
Copy link
Author

Yeah, I think I read inside another post a solution about changing a value on the catvon node, somethign about using fp16 or something.

@chflame163
Copy link
Owner

I tested successfully on 16G VRAM Nvidia GPU

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants