Sigmas Nodes
Use this node to analyze the trends for the sigmas with various noise settings. The model input is required.
sigma = the noise level at each step.
sigma_next = the target noise level at the end of each step.
sigma_down = how far down the sampler really goes, when noise addition is being used.
sigma_up = how much noise is added after each step.
σ + sigma_up = the maximum noise level at each step.
Δt̂ = the full step size: how much noise is removed at each step after noise is added (sigma + sigma_up - sigma_down). Ultimately, the effect on the overall sampling process matches delta_t below.
Δt = the step size: how much noise is removed at each step (sigma - sigma_next).
alpha_ratio = how much the current latent is scaled by (as a multiplier) at each step prior to noise addition.
