Unable to Free Up Memory in a ComfyUI workflow
Open
Feature
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 155
Description
### Feature Idea
I am currently working on a workflow in ComfyUI that involves loading large models, such as FluxDev. The workflow performs generation tasks where the output of one model serves as the input for another. However, I encounter an issue when attempting to load a third model; my system's memory (not VRAM) becomes fully utilized.
I would like to know if there is a way to clear memory and unload models that I no longer need within the same workflow. I have 64 GB of RAM, yet loading just the FluxDev model consumes 16 GB of it.
### Existing Solutions
_No response_
### Other
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.