LoraLoaderBypass - ComfyUI Built-in Node Documentation

Complete documentation for the LoraLoaderBypass node in ComfyUI. Learn its inputs, outputs, parameters and usage.

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

The LoraLoaderBypass node applies a LoRA (Low-Rank Adaptation) to a diffusion model and a CLIP model in a special “bypass” mode. Unlike a standard LoRA loader, this method does not permanently modify the base model’s weights. Instead, it computes the output by adding the LoRA’s effect to the model’s normal forward pass, which is useful for training or when working with models that have their weights offloaded.

Inputs

Parameter	Data Type	Required	Range	Description
model	MODEL	Yes	-	The diffusion model the LoRA will be applied to.
clip	CLIP	Yes	-	The CLIP model the LoRA will be applied to.
lora_name	COMBO	Yes	List of available LoRA files	The name of the LoRA file to apply. The options are loaded from the loras folder.
strength_model	FLOAT	Yes	-100.0 to 100.0	How strongly to modify the diffusion model. This value can be negative (default: 1.0).
strength_clip	FLOAT	Yes	-100.0 to 100.0	How strongly to modify the CLIP model. This value can be negative (default: 1.0).

Note: If both strength_model and strength_clip are set to 0, the node will return the original, unmodified model and clip inputs without processing.

Outputs

Output Name	Data Type	Description
MODEL	MODEL	The diffusion model with the LoRA applied in bypass mode.
CLIP	CLIP	The CLIP model with the LoRA applied in bypass mode.