UNetSelfAttentionMultiply - ComfyUI Built-in Node Documentation

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

The UNetSelfAttentionMultiply node applies multiplication factors to the query, key, value, and output components of the self-attention mechanism in a UNet model. It allows you to scale different parts of the attention computation to experiment with how attention weights affect the model’s behavior.

Inputs

Parameter	Description	Data Type	Required	Range
model	The UNet model to modify with attention scaling factors	MODEL	Yes	-
q	Multiplication factor for query component (default: 1.0)	FLOAT	No	0.0 - 10.0
k	Multiplication factor for key component (default: 1.0)	FLOAT	No	0.0 - 10.0
v	Multiplication factor for value component (default: 1.0)	FLOAT	No	0.0 - 10.0
out	Multiplication factor for output component (default: 1.0)	FLOAT	No	0.0 - 10.0

Outputs

Output Name	Description	Data Type
MODEL	The modified UNet model with scaled attention components	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): 7a6039eb2faae56437a5eb6fe01be6d38e53c0632175a3405a1e24a476d4da82