Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The SamplerCustomAdvanced node performs advanced latent space sampling using custom noise, guidance, and sampling configurations. It processes a latent image through a guided sampling process with customizable noise generation and sigma schedules, producing both the final sampled output and a denoised version when available.

Inputs

ParameterData TypeRequiredRangeDescription
noiseNOISEYes-The noise generator that provides the initial noise pattern and seed for the sampling process
guiderGUIDERYes-The guidance model that directs the sampling process toward desired outputs
samplerSAMPLERYes-The sampling algorithm that defines how the latent space is traversed during generation
sigmasSIGMASYes-The sigma schedule that controls the noise levels throughout the sampling steps
latent_imageLATENTYes-The initial latent representation that serves as the starting point for sampling

Outputs

Output NameData TypeDescription
outputLATENTThe final sampled latent representation after completing the sampling process
denoised_outputLATENTA denoised version of the output when available, otherwise returns the same as the output