Set upscale algorithm to bilinear for stable cascade controlnet.

comfy/controlnet.py

@@ -39,6 +39,7 @@ def __init__(self, device=None):
         self.global_average_pooling = False
         self.timestep_range = None
         self.compression_ratio = 8
+        self.upscale_algorithm = 'nearest-exact'
 
         if device is None:
             device = comfy.model_management.get_torch_device()
@@ -80,6 +81,7 @@ def copy_to(self, c):
         c.timestep_percent_range = self.timestep_percent_range
         c.global_average_pooling = self.global_average_pooling
         c.compression_ratio = self.compression_ratio
+        c.upscale_algorithm = self.upscale_algorithm
 
     def inference_memory_requirements(self, dtype):
         if self.previous_controlnet is not None:
@@ -165,7 +167,7 @@ def get_control(self, x_noisy, t, cond, batched_number):
             if self.cond_hint is not None:
                 del self.cond_hint
             self.cond_hint = None
-            self.cond_hint = comfy.utils.common_upscale(self.cond_hint_original, x_noisy.shape[3] * self.compression_ratio, x_noisy.shape[2] * self.compression_ratio, 'nearest-exact', "center").to(dtype).to(self.device)
+            self.cond_hint = comfy.utils.common_upscale(self.cond_hint_original, x_noisy.shape[3] * self.compression_ratio, x_noisy.shape[2] * self.compression_ratio, self.upscale_algorithm, "center").to(dtype).to(self.device)
         if x_noisy.shape[0] != self.cond_hint.shape[0]:
             self.cond_hint = broadcast_image_to(self.cond_hint, x_noisy.shape[0], batched_number)
 
@@ -435,12 +437,13 @@ class WeightsLoader(torch.nn.Module):
     return control
 
 class T2IAdapter(ControlBase):
-    def __init__(self, t2i_model, channels_in, compression_ratio, device=None):
+    def __init__(self, t2i_model, channels_in, compression_ratio, upscale_algorithm, device=None):
         super().__init__(device)
         self.t2i_model = t2i_model
         self.channels_in = channels_in
         self.control_input = None
         self.compression_ratio = compression_ratio
+        self.upscale_algorithm = upscale_algorithm
 
     def scale_image_to(self, width, height):
         unshuffle_amount = self.t2i_model.unshuffle_amount
@@ -466,7 +469,7 @@ def get_control(self, x_noisy, t, cond, batched_number):
             self.control_input = None
             self.cond_hint = None
             width, height = self.scale_image_to(x_noisy.shape[3] * self.compression_ratio, x_noisy.shape[2] * self.compression_ratio)
-            self.cond_hint = comfy.utils.common_upscale(self.cond_hint_original, width, height, 'nearest-exact', "center").float().to(self.device)
+            self.cond_hint = comfy.utils.common_upscale(self.cond_hint_original, width, height, self.upscale_algorithm, "center").float().to(self.device)
             if self.channels_in == 1 and self.cond_hint.shape[1] > 1:
                 self.cond_hint = torch.mean(self.cond_hint, 1, keepdim=True)
         if x_noisy.shape[0] != self.cond_hint.shape[0]:
@@ -485,12 +488,13 @@ def get_control(self, x_noisy, t, cond, batched_number):
         return self.control_merge(control_input, mid, control_prev, x_noisy.dtype)
 
     def copy(self):
-        c = T2IAdapter(self.t2i_model, self.channels_in, self.compression_ratio)
+        c = T2IAdapter(self.t2i_model, self.channels_in, self.compression_ratio, self.upscale_algorithm)
         self.copy_to(c)
         return c
 
 def load_t2i_adapter(t2i_data):
     compression_ratio = 8
+    upscale_algorithm = 'nearest-exact'
 
     if 'adapter' in t2i_data:
         t2i_data = t2i_data['adapter']
@@ -522,6 +526,7 @@ def load_t2i_adapter(t2i_data):
     elif "backbone.0.0.weight" in keys:
         model_ad = comfy.ldm.cascade.controlnet.ControlNet(c_in=t2i_data['backbone.0.0.weight'].shape[1], proj_blocks=[0, 4, 8, 12, 51, 55, 59, 63])
         compression_ratio = 32
+        upscale_algorithm = 'bilinear'
     else:
         return None
 
@@ -532,4 +537,4 @@ def load_t2i_adapter(t2i_data):
     if len(unexpected) > 0:
         print("t2i unexpected", unexpected)
 
-    return T2IAdapter(model_ad, model_ad.input_channels, compression_ratio)
+    return T2IAdapter(model_ad, model_ad.input_channels, compression_ratio, upscale_algorithm)

comfy/ldm/cascade/controlnet.py

@@ -86,7 +86,6 @@ def __init__(self, c_in=3, c_proj=2048, proj_blocks=None, bottleneck_mode=None,
         self.unshuffle_amount = 8
 
     def forward(self, x):
-        print(x)
         x = self.backbone(x)
         proj_outputs = [None for _ in range(max(self.proj_blocks) + 1)]
         for i, idx in enumerate(self.proj_blocks):