This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe 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
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
lora | MODEL | Yes | N/A | The LoRA model to save. Do not use the model with LoRA layers. |
prefix | STRING | Yes | N/A | The prefix to use for the saved LoRA file (default: “loras/ComfyUI_trained_lora”). |
steps | INT | No | N/A | Optional: The number of steps the LoRA has been trained for, used to name the saved file. |
lora input must be a pure LoRA model. Do not provide a base model that has LoRA layers applied to it.
Outputs
| Output Name | Data Type | Description |
|---|---|---|
| None | N/A | This node does not output any data to the workflow. It is an output node that saves a file to disk. |