ComfyUI Node
SonarAdvancedDistroNoise
Custom noise type that allows specifying parameters for Distro variants. See: https://pytorch.org/docs/stable/distributions.html
SonarAdvancedDistroNoise
- sonar_custom_noise_opt
- SONAR_CUSTOM_NOISE
◄factor1.000►
◄rescale0.000►
◄distributionuniform►
◄quantile_norm0.850►
◄quantile_norm_modebatch►
◄result_index-1►
◄exponential_lambd1.00►
◄cauchy_median0.0►
◄cauchy_sigma1.00►
◄geometric_p0.25►
◄log_normal_mean1.00►
◄log_normal_std2.00►
◄normal_mean0.00►
◄normal_std1.00►
◄beta_concentration00.5►
◄beta_concentration10.5►
◄continuous_bernoulli_probs0.5►
◄dirichlet_concentration0.5 0.5►
◄fisher_snedecor_df11.0►
◄fisher_snedecor_df22.0►
◄gamma_concentration1.0►
◄gamma_rate1.0►
◄gumbel_loc1.0►
◄gumbel_scale2.0►
◄inverse_gamma_concentration1.0►
◄inverse_gamma_rate1.0►
◄kumaraswamy_concentration01.0►
◄kumaraswamy_concentration11.0►
◄laplacian_loc0.0►
◄laplacian_scale1.0►
◄lkjcholesky_dim3►
◄lkjcholesky_concentration1.0►
◄lrmvariate_normal_loc0.0 0.0►
◄lrmvariate_normal_cov_factor1.0 0.0►
◄lrmvariate_normal_cov_diag1.0 1.0►
◄mvariate_normal_loc0.0 0.0►
◄mvariate_normal_cov_multiplier1.00►
◄pareto_scale1.0►
◄pareto_alpha1.0►
◄poisson_rate1.5►
◄relaxed_bernoulli_temperature0.75►
◄relaxed_bernoulli_probs0.66►
◄relaxed_onehotcategorical_temperature1.50►
◄relaxed_onehotcategorical_probs0.33 0.66►
◄studentt_loc0.0►
◄studentt_scale1.0►
◄studentt_df1.0►
◄uniform_low0.00►
◄uniform_high1.00►
◄vonmises_loc1.0►
◄vonmises_concentration1.0►
◄weibull_scale1.0►
◄weibull_concentration1.0►
◄wishart_df2.0►
◄wishart_cov_size2►
◄wishart_cov_multiplier1.00►
Categoryadvanced/noise
Inputs (57)
| Name | Type | Default | Description |
|---|---|---|---|
| factor | FLOAT | 1.000-10000–10000 | Scaling factor for the generated noise of this type. |
| rescale | FLOAT | 0.0000–10000 | When non-zero, this custom noise item and other custom noise items items connected to it will have their factor scaled to add up to the specified rescale value. When set to 0, rescaling is disabled. |
| distribution | COMBO | uniform | Sets the distribution used for noise generation. See: https://pytorch.org/docs/stable/distributions.html |
| quantile_norm | FLOAT | 0.850-1–1 | When 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 distribution and how many of the values are extreme. (Experimental) You can use a negative quantile to consider the values closest to zero as extreme. |
| quantile_norm_mode | COMBO | batch | Controls what dimensions quantile normalization uses. By default, the noise is flattened first. You can try the nonflat versions but they may have a very strong row/column influence. Only applies when quantile_norm is active. |
| result_index | STRING | -1 | When noise generation returns a batch of items, it will select the specified index. Negative indexes count from the end. Values outside the valid range will be automatically adjusted. You may enter a space-separated list of values for the case where there might be multiple added batch dimensions. Excess batch dimensions are removed from the end, indexe from result_index are used in order so you may want to enter the indexes in reverse order. Example: If your noise has shape (1, 4, 3, 3) and two 2-sized batch dims are added resulting in (1, 4, 3, 3, 2, 2) and you wanted index 0 from the first additional batch dimension and 1 from the second you would use result_index: 1 0 |
| exponential_lambd | FLOAT | 1.00 | — |
| cauchy_median | STRING | 0.0 | — |
| cauchy_sigma | FLOAT | 1.00 | — |
| geometric_p | FLOAT | 0.25 | — |
| log_normal_mean | FLOAT | 1.00 | — |
| log_normal_std | FLOAT | 2.00 | — |
| normal_mean | FLOAT | 0.00 | — |
| normal_std | FLOAT | 1.00 | — |
| beta_concentration0 | STRING | 0.5 | — |
| beta_concentration1 | STRING | 0.5 | — |
| continuous_bernoulli_probs | STRING | 0.5 | — |
| dirichlet_concentration | STRING | 0.5 0.5 | — |
| fisher_snedecor_df1 | STRING | 1.0 | — |
| fisher_snedecor_df2 | STRING | 2.0 | — |
| gamma_concentration | STRING | 1.0 | — |
| gamma_rate | STRING | 1.0 | — |
| gumbel_loc | STRING | 1.0 | — |
| gumbel_scale | STRING | 2.0 | — |
| inverse_gamma_concentration | STRING | 1.0 | — |
| inverse_gamma_rate | STRING | 1.0 | — |
| kumaraswamy_concentration0 | STRING | 1.0 | — |
| kumaraswamy_concentration1 | STRING | 1.0 | — |
| laplacian_loc | STRING | 0.0 | — |
| laplacian_scale | STRING | 1.0 | — |
| lkjcholesky_dim | INT | 3 | — |
| lkjcholesky_concentration | STRING | 1.0 | — |
| lrmvariate_normal_loc | STRING | 0.0 0.0 | — |
| lrmvariate_normal_cov_factor | STRING | 1.0 0.0 | — |
| lrmvariate_normal_cov_diag | STRING | 1.0 1.0 | — |
| mvariate_normal_loc | STRING | 0.0 0.0 | — |
| mvariate_normal_cov_multiplier | FLOAT | 1.00 | — |
| pareto_scale | STRING | 1.0 | — |
| pareto_alpha | STRING | 1.0 | — |
| poisson_rate | STRING | 1.5 | — |
| relaxed_bernoulli_temperature | FLOAT | 0.75 | — |
| relaxed_bernoulli_probs | STRING | 0.66 | — |
| relaxed_onehotcategorical_temperature | FLOAT | 1.50 | — |
| relaxed_onehotcategorical_probs | STRING | 0.33 0.66 | — |
| studentt_loc | STRING | 0.0 | — |
| studentt_scale | STRING | 1.0 | — |
| studentt_df | STRING | 1.0 | — |
| uniform_low | FLOAT | 0.00 | — |
| uniform_high | FLOAT | 1.00 | — |
| vonmises_loc | STRING | 1.0 | — |
| vonmises_concentration | STRING | 1.0 | — |
| weibull_scale | STRING | 1.0 | — |
| weibull_concentration | STRING | 1.0 | — |
| wishart_df | STRING | 2.0 | — |
| wishart_cov_size | INT | 2 | — |
| wishart_cov_multiplier | FLOAT | 1.00 | — |
| sonar_custom_noise_optopt | SONAR_CUSTOM_NOISE,OCS_NOISE | Optional input for more custom noise items. The following input types are supported: SONAR_CUSTOM_NOISE, OCS_NOISE |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| SONAR_CUSTOM_NOISE | SONAR_CUSTOM_NOISE | A custom noise chain. |