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 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

ParameterData TypeRequiredRangeDescription
modelMODELYes-The diffusion model to apply renormalized CFG to
cfg_truncFLOATNo0.0 - 100.0Timestep threshold for applying CFG scaling (default: 100.0)
renorm_cfgFLOATNo0.0 - 100.0Renormalization factor for controlling conditional guidance strength (default: 1.0)

Outputs

Output NameData TypeDescription
modelMODELThe modified model with renormalized CFG function applied