Skip to main content
The SaveLoRA node saves LoRA (Low-Rank Adaptation) models to your output directory. It takes a LoRA model as input and creates a safetensors file with an automatically generated filename. You can customize the filename prefix and optionally include the training step count in the filename for better organization.

​
Inputs

ParameterDescriptionData TypeRequiredRange
loraThe LoRA model to save. Do not use the model with LoRA layers.LORA_MODELYes-
prefixThe prefix to use for the saved LoRA file (default: “loras/ComfyUI_trained_lora”).STRINGYes-
stepsOptional: The number of steps the LoRA has been trained for, used to name the saved file.INTNo-

​
Outputs

Output NameDescriptionData Type
NoneThis node does not return any outputs but saves the LoRA model to the output directory.-
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): 06a1067433aa4b720b51050b09fbad4870caf12c5e92f788d44ea022a39efef4