Skip to main content
The ScaleROPE node allows you to modify the Rotary Position Embedding (ROPE) of a model by applying separate scaling and shifting factors to its X, Y, and T (time) components. This is an advanced, experimental node used to adjust the model’s positional encoding behavior.

Inputs

Outputs

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): 4899aaf380aefd7cb41593edb402f166c34e25029e82edddf718bb38e8c2339d