The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
FreSca: 5D+ (ex. Anima) fix, model-agnostic iteration (#15007)
TheToxin-git593786e48987
diff --git a/comfy_extras/nodes_fresca.py b/comfy_extras/nodes_fresca.pyindex 173f42154..a7d181bdf 100644--- a/comfy_extras/nodes_fresca.py+++ b/comfy_extras/nodes_fresca.py@@ -10,7 +10,7 @@ def Fourier_filter(x, scale_low=1.0, scale_high=1.5, freq_cutoff=20):Apply frequency-dependent scaling to an image tensor using Fourier transforms.Parameters:- x: Input tensor of shape (B, C, H, W)+ x: Input tensor of shape (..., H, W)scale_low: Scaling factor for low-frequency components (default: 1.0)scale_high: Scaling factor for high-frequency components (default: 1.5)freq_cutoff: Number of frequency indices around center to consider as low-frequency (default: 20)@@ -31,8 +31,8 @@ def Fourier_filter(x, scale_low=1.0, scale_high=1.5, freq_cutoff=20):# Initialize mask with high-frequency scaling factormask = torch.ones(x_freq.shape, device=device) * scale_highm = mask- for d in range(len(x_freq.shape) - 2):- dim = d + 2+ for d in range(2):+ dim = len(x_freq.shape) - 2 + dcc = x_freq.shape[dim] // 2f_c = min(freq_cutoff, cc)m = m.narrow(dim, cc - f_c, f_c * 2)