Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

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 TypeRequiredRangeDescription
modelMODELYes-The diffusion model to apply CFG normalization to
strengthFLOATYes0.0 to 100.0Controls the intensity of the normalization effect applied to the CFG scaling (default: 1.0)

Outputs

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

Source fingerprint (SHA-256): adbcea5c02277a7bd93866eaae75fe150b5b310dbc6e0a3a31c4e4ee0f71e57c