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 DualCFGGuider node creates a guidance system for dual classifier-free guidance sampling. It combines two positive conditioning inputs with one negative conditioning input, applying different guidance scales to each conditioning pair to control the influence of each prompt on the generated output.

Inputs

ParameterData TypeRequiredRangeDescription
modelMODELYes-The model to use for guidance
cond1CONDITIONINGYes-The first positive conditioning input
cond2CONDITIONINGYes-The second positive conditioning input
negativeCONDITIONINGYes-The negative conditioning input
cfg_condsFLOATYes0.0 - 100.0Guidance scale for the first positive conditioning (default: 8.0)
cfg_cond2_negativeFLOATYes0.0 - 100.0Guidance scale for the second positive and negative conditioning (default: 8.0)
styleCOMBOYes”regular"
"nested”
The guidance style to apply (default: “regular”)

Outputs

Output NameData TypeDescription
GUIDERGUIDERA configured guidance system ready for use with sampling