TemporalScoreRescaling - ComfyUI Built-in Node Documentation

Complete documentation for the TemporalScoreRescaling node in ComfyUI. Learn its inputs, outputs, parameters and usage.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

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

Parameter	Data Type	Required	Range	Description
model	MODEL	Yes	-	The diffusion model to be patched with the TSR function.
tsr_k	FLOAT	No	0.01 - 100.0	Controls 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)
tsr_sigma	FLOAT	No	0.01 - 100.0	Controls how early rescaling takes effect. Larger values take effect earlier. (default: 1.0)

Outputs

Output Name	Data Type	Description
patched_model	MODEL	The input model, now patched with the Temporal Score Rescaling function applied to its sampling process.