ComfyUI Nodes
advanced
model
Model Sampling Discrete

Model Sampling Discrete

comfyUI节点-ModelSamplingDiscrete|模型离散采样算法

Documentation

  • Class name: ModelSamplingDiscrete
  • Category: advanced/model
  • Output node: False

This node is designed to modify the sampling behavior of a model by applying a discrete sampling strategy. It allows for the selection of different sampling methods, such as epsilon, v_prediction, lcm, or x0, and optionally adjusts the model's noise reduction strategy based on the zero-shot noise ratio (zsnr) setting.

Input types

ParameterComfy dtypePython dtypeDescription
modelMODELtorch.nn.ModuleThe model to which the discrete sampling strategy will be applied. This parameter is crucial as it defines the base model that will undergo modification.
samplingCOMBO[STRING]strSpecifies the discrete sampling method to be applied to the model. The choice of method affects how the model generates samples, offering different strategies for sampling.
zsnrBOOLEANboolA boolean flag that, when enabled, adjusts the model's noise reduction strategy based on the zero-shot noise ratio. This can influence the quality and characteristics of the generated samples.

Output types

ParameterComfy dtypePython dtypeDescription
modelMODELtorch.nn.ModuleThe modified model with the applied discrete sampling strategy. This model is now equipped to generate samples using the specified method and adjustments.