NAGuidance - ComfyUI Built-in Node Documentation

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

The NAGuidance node applies Normalized Attention Guidance to a model. This technique enables the use of negative prompts with distilled or schnell models by modifying the model’s attention mechanism during the sampling process to steer the generation away from undesired concepts.

Inputs

Parameter	Description	Data Type	Required	Range
model	The model to apply Normalized Attention Guidance to.	MODEL	Yes	-
nag_scale	The guidance scale factor. Higher values push the generation further from the negative prompt. (default: 5.0)	FLOAT	Yes	0.0 - 50.0
nag_alpha	The blending factor for the normalized attention. A value of 1.0 fully replaces the original attention, while 0.0 has no effect. (default: 0.5)	FLOAT	Yes	0.0 - 1.0
nag_tau	A scaling factor used to limit the normalization ratio. (default: 1.5)	FLOAT	Yes	1.0 - 10.0

Outputs

Output Name	Description	Data Type
model	The patched model with Normalized Attention Guidance enabled.	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): 42b4d601312dcbb1c934c6a79bbb5e9fd6598fa5f32b18f5c0affcb596672cba