Skip to main content
This node applies a LoRA (Low-Rank Adaptation) to a model to modify its behavior, but only affects the model component itself. It loads a specified LoRA file and adjusts the model’s weights by a given strength, leaving other components like the CLIP text encoder unchanged.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe base model to which the LoRA adjustments will be applied.MODELYes-
lora_nameThe name of the LoRA file to load and apply. The options are populated from the files in the loras directory.STRINGYes(List of available LoRA files)
strength_modelThe strength of the LoRA’s effect on the model’s weights. A positive value applies the LoRA, a negative value applies the inverse, and a value of 0 has no effect (default: 1.0).FLOATYes-100.0 to 100.0

Outputs

Output NameDescriptionData Type
modelThe modified model with the LoRA adjustments applied to its weights.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): e0e1ad2d6481a1b9771d7eae833ffab0737a967d4af6e57b946d1b2223fe45bf