* Refactor noise generation
Try to make option passing and CPU/GPU noise selection work
Add advanced custom noise node that allows for parameter passing
Add wavelet noise type
* Add WaveletFilteredNoise node, other fixes
* Fix Brownian arg passing
* Generalized distribution noise for most torch.distributions
* Distro noise improvements, add SonarAdvancedDistroNoise node
* More distributions!
* Add SonarResizedNoise node
* Momentum sampler refactor/improvements (I hope)
* Better approach to integration with external nodes
Documentation updates
Other cleanups
* Internal cleanups and refactoring.
Some integration improvements.
Bump date in changelog
* Add round and step to node FLOAT inputs that did not have it
Add repeat_batch parameter to NoisyLatentLike node.
Add a node to convert SONAR_CUSTOM_NOISE to ComfyUI NOISE.
Various code cleanups and lint squashing.
Many new features, documentation reorganized.
* Add `SonarScheduledNoise`, `SonarCompositeNoise`, `SonarGuidedNoise`, `SonarRandomNoise` nodes.
* Add `SonarPowerFilterNoise`, `SonarPowerFilter`, `SonarPreviewFilter` nodes.
* Add `FreeUExtreme`, `FreeUExtremeConfig` nodes.
* Replace `pyramid` noise type with a (hopefully) more correct implementation. You can use `pyramid_old` for the previous behavior.
* Add more noise types and variations.
* The `NoisyLatentLike` node now allows using brownian noise if you connect a model and sigmas.
* Refactoring, cleanups, reorganization.
* Fixed issue when using Sonar samplers in normal sampling nodes/via stuff like `KSamplerSelect`.
* Add `pyramid` (non-high-res) noise type.
* Allow selecting `brownian` noise in custom noise nodes (but it won't work with `NoisyLatentLike`).
* Use `brownian` as the default noise type for `SamplerSonarDPMPP`.
* Make overriding the selected noise type in Sonar samplers a warning instead of a hard error.
* Improve noise scaling (may change seeds).
* Add `KRestartSamplerCustomNoise` if the user has a recent enough version of ComfyUI_restart_sampling installed.
* Improve NoisyLatentLike to allow calculating strength with sigmas and noise injection
* Update documentation for NoisyLatentLike changes + general improvements
* SonarPowerNoise: WIP
* don't allow highpass > lowpass
* fix filter unit gain
The filter was computed as an amplitude gain map. This change computes energy
gains instead. This makes easier to ensure unit-gain and makes the alpha values
more in line with literature where the power spectrum is obeying the power law.
new alpha = old alpha / 2
Also fixes the gain of common_mode.
* allow stretch < 1.0, paramter range fixes
* rename lowpass/highpass to min_freq/max_freq
* remove torch.no_grad wrappers
* add previews
* static seed for previews
* README: SonarPowerNoise documentation
blepping