CLIPAttentionMultiply - ComfyUI Built-in Node Documentation

The CLIPAttentionMultiply node allows you to adjust the attention mechanism in CLIP models by applying multiplication factors to different components of the self-attention layers. It works by modifying the query, key, value, and output projection weights and biases in the CLIP model’s attention mechanism. This experimental node creates a modified copy of the input CLIP model with the specified scaling factors applied.

Inputs

Parameter	Description	Data Type	Required	Range
`clip`	The CLIP model to modify	CLIP	Yes	-
`q`	Multiplication factor for query projection weights and biases (default: 1.0)	FLOAT	Yes	0.0 - 10.0
`k`	Multiplication factor for key projection weights and biases (default: 1.0)	FLOAT	Yes	0.0 - 10.0
`v`	Multiplication factor for value projection weights and biases (default: 1.0)	FLOAT	Yes	0.0 - 10.0
`out`	Multiplication factor for output projection weights and biases (default: 1.0)	FLOAT	Yes	0.0 - 10.0

Outputs

Output Name	Description	Data Type
`CLIP`	Returns a modified CLIP model with the specified attention scaling factors applied	CLIP

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): 1f5c437cb4a372dfd69ad3c10e2b8cfc68821e0fe82dcf37df5e6fd64aa0b436

​Inputs

​Outputs

Inputs

Outputs