Calibrated Spectrum Adaptive Forecaster (SDXL) [LEGACY]

A ComfyUI node in sampling with 12 inputs and 1 output.

By ruwwww·Created 5 months ago·Updated 3 months ago· 56

◄w0.30►

◄m3►

◄lam0.10►

◄window_size2►

◄flex_window0.00►

◄warmup_steps5►

◄stop_caching_step-1►

◄steps30►

◄enable_calibrationtrue►

◄calibration_strength0.50►

◄debugfalse►

Categorysampling

Inputs (12)

Name	Type	Default	Description
model	MODEL		LEGACY: This node is non-faithful and uses 'vibe-coded' logic. Please use the 'SpectrumSDXL' if you want a faithful implementation.
w	FLOAT	0.300–1	Blending weight between predicted (Chebyshev) and local (Taylor) features. Lower (0.3-0.5) preserves sharpness, higher relies on global smoothing.
m	INT	31–8	Number of Chebyshev basis functions (forecast complexity). Lower values (3-4) are more stable for SDXL.
lam	FLOAT	0.100–2	Ridge regularization strength. Prevents latent explosions and rainbow artifacts in low-precision modes.
window_size	INT	21–10	Initial forecasting window size (number of skipped steps).
flex_window	FLOAT	0.000–2	Increment added to window size after each actual UNet pass. Higher = aggressive acceleration.
warmup_steps	INT	50–20	Initial full-model steps before forecasting begins. Gives the model time to establish composition.
stop_caching_step	INT	-1-1–100	The exact step where Spectrum stops and returns to native UNet. Essential for final detail recovery. Set to Total Steps - 3.
steps	INT	3010–500	Match this value with your KSampler total steps for stable forecast accuracy and drift reduction.
enable_calibration	BOOLEAN	true	LEGACY: Applies residual correction to forecasts. Not part of the official algorithm.
calibration_strength	FLOAT	0.500–1	LEGACY: Strength of the residual blending.
debug	BOOLEAN	false	Print detailed stats to the console for debugging.

Name	Type	Description
MODEL	MODEL	—