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 CFGGuider node creates a guidance system for controlling the sampling process in image generation. It takes a model along with positive and negative conditioning inputs, then applies a classifier-free guidance scale to steer the generation toward desired content while avoiding unwanted elements. This node outputs a guider object that can be used by sampling nodes to control the image generation direction.

Inputs

ParameterData TypeInput TypeDefaultRangeDescription
modelMODELRequired--The model to be used for guidance
positiveCONDITIONINGRequired--The positive conditioning that guides the generation toward desired content
negativeCONDITIONINGRequired--The negative conditioning that steers the generation away from unwanted content
cfgFLOATRequired8.00.0 - 100.0The classifier-free guidance scale that controls how strongly the conditioning influences the generation

Outputs

Output NameData TypeDescription
GUIDERGUIDERA guider object that can be passed to sampling nodes to control the generation process