Use FluxFillGP to better use memory management for faster BFL model performance?
Open
Feature
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 155
Description
### Feature Idea
Is this something comfy would need to implement or a node such as a the model loader or a sampler? https://github.com/deepbeepmeep/FluxFillGP
### Existing Solutions
_No response_
### Other
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.