Nodes/ComfyUI-sonar/SonarLatentOperationQuantileFilter
ComfyUI Node

SonarLatentOperationQuantileFilter

Allows applying a quantile normalization function to the latent during sampling. Can be used with Sonar SonarApplyLatentOperationCFG. The just copies most of the parameters from the other quantile normalization node where it talks to 'noise', this will apply to whatever you're applying the latent operation to (denoised, uncond, etc).

By blepping·Created 3 years ago·Updated 4 days ago· 49
SonarLatentOperationQuantileFilter
    • LATENT_OPERATION
    quantile0.850
    dim1
    flattentrue
    norm_factor1.000
    norm_power0.500
    strategyclamp
    Categorylatent/advanced/operations

    Inputs (6)

    NameTypeDefaultDescription
    quantileFLOAT0.850-1–1When enabled, will normalize generated noise to this quantile (i.e. 0.75 means outliers >75% will be clipped). Set to 1.0 or 0.0 to disable quantile normalization. A value like 0.75 or 0.85 should be reasonable, it really depends on the input and how many of the values are extreme. (Experimental) You can also use a negative quantile to consider values closest to 0 to be 'extreme'.
    dimCOMBO1Controls what dimensions quantile normalization uses. Dimensions start from 0. Image latents have dimensions: batch, channel, row, column. Video latents have dimensions: batch, channel, frame, row, column.
    flattenBOOLEANtrueControls whether the noise is flattened before quantile normalization. You can try disabling it but they may have a very strong row/column influence.
    norm_factorFLOAT1.0000.00001–10000Multiplier on the input noise just before it is clipped to the quantile min/max. Generally should be left at the default.
    norm_powerFLOAT0.500-10000–10000The absolute value of the noise is raised to this power after it is clipped to the quantile min/max. You can use negative values here, but anything below -0.3 will probably produce pretty strange effects. Generally should be left at the default.
    strategyCOMBOclampDetermines how to treat outliers. zero and reverse_zero modes are only useful if you're going to do something like add the result to some other noise. zero will return zero for anything outside the quantile range, reverse_zero only _keeps_ the outliers and zeros everything else.

    Outputs (1)

    NameTypeDescription
    LATENT_OPERATIONLATENT_OPERATIONA custom noise chain.