Nodes/Skoogeer-Noise/Latent Channel Nonlinear Transform
ComfyUI Node

Latent Channel Nonlinear Transform

A ComfyUI node in latent/channel with 16 inputs and 1 output.

By ttulttul·Created 8 months ago·Updated 2 months ago· 14
Latent Channel Nonlinear Transform
  • latent
  • mask
  • latent
operation
seed0
gate_strength1.00
beta1.00
blur_radius0
quantize_step0.25
clip_threshold2.00
selection_modeall
selection_fraction1.00
selection_count0
selection_orderhighest
selection_indices
mix1.00
match_statsfalse
Categorylatent/channel

Inputs (16)

NameTypeDefaultDescription
latentLATENTLatent to transform in channel-space.
operationCOMBONonlinear channel-space transform to apply.
seedINT00–18446744073709550000Seed for deterministic gating/dropout patterns.
gate_strengthFLOAT1.000–10Slope for gate sigmoid (gate_* operations).
betaFLOAT1.00-4–4Gate strength for gate_* operations.
blur_radiusINT00–64Blur radius for gate maps (latent pixels).
quantize_stepFLOAT0.250–10Step size for quantize operation.
clip_thresholdFLOAT2.000–10Clip threshold for clip_* operations.
selection_modeCOMBOallHow to choose which channels are transformed.
selection_fractionFLOAT1.000–1Fraction of channels to select when selection_count is 0.
selection_countINT00–4096Exact number of channels to select (overrides selection_fraction when >0).
selection_orderCOMBOhighestWhether to pick high or low variance/roughness channels.
selection_indicesSTRINGComma-separated channel indices to select when selection_mode=indices.
mixFLOAT1.000–1Blend factor for the transformed channels (0=off, 1=full).
match_statsBOOLEANfalseMatch per-channel mean/std after the transform (stabilizes latent stats).
maskoptMASKOptional mask to limit the transform to masked areas.

Outputs (1)

NameTypeDescription
latentLATENT