sampling
custom-sampling
schedulers
Sd Turbo Scheduler

SD Turbo Scheduler

comfyUI节点-SDTurboScheduler|SDTurbo调度器

Documentation

  • Class name: SDTurboScheduler
  • Category: sampling/custom_sampling/schedulers
  • Output node: False

SDTurboScheduler is designed to generate a sequence of sigma values for image sampling, adjusting the sequence based on the denoise level and the number of steps specified. It leverages a specific model's sampling capabilities to produce these sigma values, which are crucial for controlling the denoising process during image generation.

Input types

ParameterComfy dtypeDescription
modelMODELThe model parameter specifies the generative model to be used for sigma value generation. It is crucial for determining the specific sampling behavior and capabilities of the scheduler.
stepsINTThe steps parameter determines the length of the sigma sequence to be generated, directly influencing the granularity of the denoising process.
denoiseFLOATThe denoise parameter adjusts the starting point of the sigma sequence, allowing for finer control over the denoising level applied during image generation.

Output types

ParameterComfy dtypeDescription
sigmasSIGMASA sequence of sigma values generated based on the specified model, steps, and denoise level. These values are essential for controlling the denoising process in image generation.