Skip to main content
This node applies Temporal Score Rescaling (TSR) to a diffusion model. It modifies the model’s sampling behavior by rescaling the predicted noise or score during the denoising process, which can steer the diversity of the generated output. This is implemented as a post-CFG (Classifier-Free Guidance) function.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe diffusion model to be patched with the TSR function.MODELYes-
tsr_kControls the rescaling strength. Lower k produces more detailed results; higher k produces smoother results in image generation. Setting k = 1 disables rescaling. (default: 0.95)FLOATNo0.01 - 100.0
tsr_sigmaControls how early rescaling takes effect. Larger values take effect earlier. (default: 1.0)FLOATNo0.01 - 100.0

Outputs

Output NameDescriptionData Type
patched_modelThe input model, now patched with the Temporal Score Rescaling function applied to its sampling process.MODEL
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): c558da8dea80131f705f3217740c4f9df3c9a7a6695e2c089f5798a726730bb8