Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The CFGNorm node applies a normalization technique to the classifier-free guidance (CFG) process in diffusion models. It adjusts the scale of the denoised prediction by comparing the norms of the conditional and unconditional outputs, then applies a strength multiplier to control the effect. This helps stabilize the generation process by preventing extreme values in the guidance scaling.

Inputs

ParameterData TypeInput TypeDefaultRangeDescription
modelMODELrequired--The diffusion model to apply CFG normalization to
strengthFLOATrequired1.00.0 - 100.0Controls the intensity of the normalization effect applied to the CFG scaling

Outputs

Output NameData TypeDescription
patched_modelMODELReturns the modified model with CFG normalization applied to its sampling process