SamplerCustomAdvanced - ComfyUI Built-in Node Documentation

Complete documentation for the SamplerCustomAdvanced 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

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

Parameter	Data Type	Required	Range	Description
noise	NOISE	Yes	-	The noise generator that provides the initial noise pattern and seed for the sampling process
guider	GUIDER	Yes	-	The guidance model that directs the sampling process toward desired outputs
sampler	SAMPLER	Yes	-	The sampling algorithm that defines how the latent space is traversed during generation
sigmas	SIGMAS	Yes	-	The sigma schedule that controls the noise levels throughout the sampling steps
latent_image	LATENT	Yes	-	The initial latent representation that serves as the starting point for sampling. Supports optional noise_mask for selective denoising, and optional downscale_ratio_spacial and downscale_ratio_temporal keys for advanced latent handling

Outputs

Output Name	Data Type	Description
output	LATENT	The final sampled latent representation after completing the sampling process. Any downscale_ratio_spacial or downscale_ratio_temporal keys from the input latent are removed from this output
denoised_output	LATENT	A denoised version of the output when the sampling process produces an intermediate clean prediction (x0), otherwise returns the same as the output. When available, this represents the model’s best estimate of the clean latent at each step

---

Source fingerprint (SHA-256): c6217a2b89009237366109e2156e279c3a1077f28c9e8bf9808b1f04788c5370