LazyCache - ComfyUI Built-in Node Documentation

LazyCache is an experimental, homebrew version of EasyCache that adds caching during sampling to reduce computation.

LazyCache is an experimental, homebrew version of EasyCache that adds caching during sampling to reduce computation. It is designed for universal compatibility with models in ComfyUI, though it generally performs worse than EasyCache and may work better only in rare cases.

Inputs

Parameter	Description	Data Type	Required	Range
model	The model to add LazyCache to.	MODEL	Yes	-
reuse_threshold	The threshold for reusing cached steps. Default: 0.2.	FLOAT	Yes	0.0 - 3.0 (step 0.01)
start_percent	The relative sampling step to begin use of LazyCache. Default: 0.15.	FLOAT	Yes	0.0 - 1.0 (step 0.01)
end_percent	The relative sampling step to end use of LazyCache. Default: 0.95.	FLOAT	Yes	0.0 - 1.0 (step 0.01)
verbose	Whether to log verbose information. Default: False.	BOOLEAN	Yes	-

Note: reuse_threshold, start_percent, end_percent, and verbose are marked as advanced inputs.

Outputs

Output Name	Description	Data Type
model	The model with LazyCache functionality added.	MODEL

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): 78f9c13473567e068fc2be35b2f8f5aa459d43d3f13300a6ea858af98d3e2a44