-
Notifications
You must be signed in to change notification settings - Fork 15
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
feat: layer diffuse #272
feat: layer diffuse #272
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
As mentioned in discord, there needs to be handling to account for the model download and use supporting AIWORKER_CACHE_HOME
.
Further, I think that introducing 3gb+ of VRAM overhead with this feature presents potential problems, especially with making sure the new model introduced with this feature is getting unloaded at the correct times. I am only raising my concerns and am not vetoing the feature as a whole. I do think it is useful feature in theory but has the potential to introduce memory-related stability problems without further testing.
Adds support for Layer Diffuse via https://github.com/huchenlei/ComfyUI-layerdiffuse
Also pin numpy as v2 breaks us