CFGNorm - ComfyUI Built-in Node Documentation

CFGNorm adjusts how classifier-free guidance (CFG) is applied in diffusion models by comparing the size (norm) of the conditional prediction with the guided prediction and rescalin

CFGNorm adjusts how classifier-free guidance (CFG) is applied in diffusion models by comparing the size (norm) of the conditional prediction with the guided prediction and rescaling the result. A strength value controls how much of the adjustment is applied. By default the scaling only attenuates the guidance output, while enabling pre_cfg rescales the combined noise before the sampler’s CFG combine without clamping, which can amplify the result.

Inputs

Parameter	Description	Data Type	Required	Range
model	The diffusion model to apply CFG normalization to	MODEL	Yes	-
strength	Controls the intensity of the normalization effect applied to the CFG scaling (default: 1.0)	FLOAT	Yes	0.0 to 100.0 (step 0.01)
pre_cfg	If true, rescale the combined noise BEFORE the sampler’s CFG combine, without clamping (can amplify). Matches the norm-scaled CFG used by models like Lens. Default false keeps the original post-CFG x0-space attenuate-only behavior. (default: False)	BOOLEAN	No	true / false

Note: This node is marked as experimental.

Outputs

Output Name	Description	Data Type
patched_model	Returns the modified model with CFG normalization applied to its sampling process	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): 427dda498ebda2642489aa2591f063355a77b1e064e0dc7fa8570ed8200c2734