Skip to main content
The RenormCFG node modifies the classifier-free guidance (CFG) process in diffusion models by applying conditional scaling and normalization. It adjusts the denoising process based on specified timestep thresholds and renormalization factors to control the influence of conditional versus unconditional predictions during image generation.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe diffusion model to apply renormalized CFG toMODELYes-
cfg_truncTimestep threshold for applying CFG scaling. When the current timestep is below this value, CFG scaling is applied; otherwise, only the conditional prediction is used (default: 100.0)FLOATNo0.0 - 100.0
renorm_cfgRenormalization factor that limits the maximum norm of the CFG-scaled prediction relative to the original conditional prediction. A value of 0.0 disables renormalization (default: 1.0)FLOATNo0.0 - 100.0

Outputs

Output NameDescriptionData Type
modelThe modified model with renormalized CFG function appliedMODEL
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): 1fb74c816d82d39e030a25e372c01f251a42c7fe6314cc6cefbad984acb262d3