Skip to main content
The SaveLoRA node saves a LoRA (Low-Rank Adaptation) model to a file. It takes a LoRA model as input and writes it to a .safetensors file in the output directory. You can specify a filename prefix and an optional step count to be included in the final filename.

Inputs

ParameterDescriptionData TypeRequiredRange
loraThe LoRA model to save. Do not use the model with LoRA layers.LORA_MODELYesN/A
prefixThe prefix to use for the saved LoRA file (default: “loras/ComfyUI_trained_lora”).STRINGYesN/A
stepsOptional: The number of steps the LoRA has been trained for, used to name the saved file.INTNoN/A
Note: The lora input must be a pure LoRA model. Do not provide a base model that has LoRA layers applied to it.

Outputs

Output NameDescriptionData Type
NoneThis node does not output any data to the workflow. It is an output node that saves a file to disk.N/A
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): 0d9bb1adef75214e3ecf5a16f046761d547d21bea41488b0ce80cdc05ed2e81b