The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Mask strength should be separate from area strength.
comfyanonymous071011aebed2
diff --git a/comfy/samplers.py b/comfy/samplers.pyindex f8701c879..10527fb1c 100644--- a/comfy/samplers.py+++ b/comfy/samplers.py@@ -26,10 +26,13 @@ def sampling_function(model_function, x, timestep, uncond, cond, cond_scale, conif 'mask' in cond[1]:# Scale the mask to the size of the input# The mask should have been resized as we began the sampling process+ mask_strength = 1.0+ if "mask_strength" in cond[1]:+ mask_strength = cond[1]["mask_strength"]mask = cond[1]['mask']assert(mask.shape[1] == x_in.shape[2])assert(mask.shape[2] == x_in.shape[3])- mask = mask[:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]]+ mask = mask[:,area[2]:area[0] + area[2],area[3]:area[1] + area[3]] * mask_strengthmask = mask.unsqueeze(1).repeat(input_x.shape[0] // mask.shape[0], input_x.shape[1], 1, 1)else:mask = torch.ones_like(input_x)diff --git a/nodes.py b/nodes.pyindex 12fa7e5a3..b4069c836 100644--- a/nodes.py+++ b/nodes.py@@ -98,7 +98,7 @@ class ConditioningSetMask:CATEGORY = "conditioning"- def append(self, conditioning, mask, set_area_to_bounds, strength, min_sigma=0.0, max_sigma=99.0):+ def append(self, conditioning, mask, set_area_to_bounds, strength):c = []if len(mask.shape) < 3:mask = mask.unsqueeze(0)@@ -107,9 +107,7 @@ class ConditioningSetMask:_, h, w = mask.shapen[1]['mask'] = maskn[1]['set_area_to_bounds'] = set_area_to_bounds- n[1]['strength'] = strength- n[1]['min_sigma'] = min_sigma- n[1]['max_sigma'] = max_sigma+ n[1]['mask_strength'] = strengthc.append(n)return (c, )