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

Always OOM #31

Open
APCOTech opened this issue Nov 24, 2024 · 3 comments
Open

Always OOM #31

APCOTech opened this issue Nov 24, 2024 · 3 comments

Comments

@APCOTech
Copy link

APCOTech commented Nov 24, 2024

image

I updated everything and followed the instructions.. but seems like it can't load the model itself from the beginning .. I have 4080 12GB and 64GB ram.. does anyone have the same issue?
I tried with Bfloat16 also but got the same result

@APCOTech
Copy link
Author

Okay.. when I load it with the normal (Load Checkpoint) node. it works perfect and very fast. Seems there is an issue with your loader.

@MoreColors123
Copy link

what comfy workflow are you working with basically? the ones provided by comfyui (https://comfyanonymous.github.io/ComfyUI_examples/ltxv/), which are the only ones working for me ATM, or the ones provided here?

@APCOTech
Copy link
Author

what comfy workflow are you working with basically? the ones provided by comfyui (https://comfyanonymous.github.io/ComfyUI_examples/ltxv/), which are the only ones working for me ATM, or the ones provided here?

The workflows here do not work. The ModelLoader always stops with Allocation on Device error ... but the ComfyUI workflow is working fine and fast for me ..

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

2 participants