Skip to main content
The VideoTriangleCFGGuidance node applies a triangular classifier-free guidance scaling pattern to video models. It modifies the conditioning scale over time using a triangular wave function that oscillates between the minimum CFG value and the original conditioning scale. This creates a dynamic guidance pattern that can help improve video generation consistency and quality.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe video model to apply triangular CFG guidance toMODELYes-
min_cfgThe minimum CFG scale value for the triangular pattern (default: 1.0)FLOATYes0.0 - 100.0

Outputs

Output NameDescriptionData Type
modelThe modified model with triangular CFG guidance 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): 10b3ad8dcfe5e44f131b2e943e6645899102f406501418906cfe06ac2d21d433