Skip to main content

Overview

The VOIDSampler node provides a specialized DDIM sampling method designed specifically for VOID inpainting models. It implements the same denoising process used during VOID model training, without the noise scaling that standard KSamplers apply. This node is intended for use with SamplerCustom or SamplerCustomAdvanced nodes, and should be paired with RandomNoise or VOIDWarpedNoiseSource.

Inputs

This node has no configurable input parameters. It is a self-contained sampler that applies a fixed DDIM sampling algorithm.

Outputs

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): ca30211dc30975a1c6447afd3f6dcdb29d59d31effabe9b7fed5b90ee1cab540