Comfy-Org / Comfy-Org/ComfyUI

For models that take a long time to load

Open
#12,831 0 comments 0 reactions 0 assignees View on GitHub
Feature
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 7h
Merged PRs (30d)
158

Description

### Feature Idea

For models that take a long time to load, shouldn't they be retained separately when clearing GPU memory and RAM? For example, large language models loaded by DualCLIPLoader are very large and take a long time to load. Could an option be added at this node to specify the memory usage of the "remove model" setting? That's the gist of it. (Actually, I mainly want to be able to dynamically change this value at the code level so it doesn't fail to clear, but I don't want it to take a long time to load every time, especially with my limited 48GB of RAM.)

### Existing Solutions

_No response_

### Other

_No response_

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.