INNER CODE UNIT · Python

get_denoised_ranges

Extraltodeus/ComfyUI-AutomaticCFG · nodes.py:114

def get_denoised_ranges(latent, measure="hard", top_k=0.25):
    chans = []
    for x in range(len(latent)):
        max_values = torch.topk(latent[x] - latent[x].mean() if measure == "range" else latent[x], k=int(len(latent[x])*top_k), largest=True).values
        min_values = torch.topk(latent[x] - latent[x].mean() if measure == "range" else latent[x], k=int(len(latent[x])*top_k), largest=False).values
        max_val = torch.mean(max_values).item()
        min_val = abs(torch.mean(min_values).item()) if measure == "soft" else torch.mean(torch.abs(min_values)).item()
        denoised_range = (max_val + min_val) / 2
        chans.append(denoised_range**2 if measure == "hard_squared" else denoised_range)
    return chans

def get_sigmin_sigmax(model):
    model_sampling = model.model.model_sampling
    sigmin = model_sampling.sigma(model_sampling.timestep(model_sampling.sigma_min))
    sigmax = model_sampling.sigma(model_sampling.timestep(model_sampling.sigma_max))
    return sigmin, sigmax

def gaussian_similarity(x, y, sigma=1.0):

View source record →