The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Start is now 0.0 and end is now 1.0 for the timestep ranges.
comfyanonymous5f75d784a177
diff --git a/comfy/sd.py b/comfy/sd.pyindex aaeed0561..64ab7cc63 100644--- a/comfy/sd.py+++ b/comfy/sd.py@@ -713,7 +713,6 @@ class ControlBase:out = []if self.previous_controlnet is not None:out += self.previous_controlnet.get_models()- out.append(self.control_model)return outdef copy_to(self, c):@@ -791,6 +790,12 @@ class ControlNet(ControlBase):self.copy_to(c)return c+ def get_models(self):+ out = super().get_models()+ out.append(self.control_model)+ return out++def load_controlnet(ckpt_path, model=None):controlnet_data = utils.load_torch_file(ckpt_path, safe_load=True)diff --git a/nodes.py b/nodes.pyindex ac2ca1197..b0d05f0d7 100644--- a/nodes.py+++ b/nodes.py@@ -208,8 +208,8 @@ class ConditioningSetTimestepRange:@classmethoddef INPUT_TYPES(s):return {"required": {"conditioning": ("CONDITIONING", ),- "start": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001}),- "end": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001})+ "start": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001}),+ "end": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001})}}RETURN_TYPES = ("CONDITIONING",)FUNCTION = "set_range"@@ -220,8 +220,8 @@ class ConditioningSetTimestepRange:c = []for t in conditioning:d = t[1].copy()- d['start_percent'] = start- d['end_percent'] = end+ d['start_percent'] = 1.0 - start+ d['end_percent'] = 1.0 - endn = [t[0], d]c.append(n)return (c, )@@ -615,8 +615,8 @@ class ControlNetApplyAdvanced:"control_net": ("CONTROL_NET", ),"image": ("IMAGE", ),"strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),- "start": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001}),- "end": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001})+ "start_percent": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001}),+ "end_percent": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001})}}RETURN_TYPES = ("CONDITIONING","CONDITIONING")@@ -625,7 +625,7 @@ class ControlNetApplyAdvanced:CATEGORY = "conditioning"- def apply_controlnet(self, positive, negative, control_net, image, strength, start, end):+ def apply_controlnet(self, positive, negative, control_net, image, strength, start_percent, end_percent):if strength == 0:return (positive, negative)@@ -642,7 +642,7 @@ class ControlNetApplyAdvanced:if prev_cnet in cnets:c_net = cnets[prev_cnet]else:- c_net = control_net.copy().set_cond_hint(control_hint, strength, (start, end))+ c_net = control_net.copy().set_cond_hint(control_hint, strength, (1.0 - start_percent, 1.0 - end_percent))c_net.set_previous_controlnet(prev_cnet)cnets[prev_cnet] = c_net