modifying requirements.txt

cogvideo_controlnet_pcd.py

@@ -237,11 +237,6 @@ class CogVideoXControlnetPCD(ModelMixin, ConfigMixin, PeftAdapterMixin):
                     temb=emb,
                     image_rotary_emb=image_rotary_emb,
                 )
-                
-            print("hidden_states shape:", hidden_states.shape)
-            print("out_projectors[i](hidden_states) shape:", self.out_projectors[i](hidden_states).shape)
-            print("controlnet_output_mask shape:", controlnet_output_mask.shape)
-
 
             if self.out_projectors is not None:
                 if controlnet_output_mask is not None:

inference/cli_demo_camera_i2v_pcd.py

@@ -368,6 +368,27 @@ def generate_video(
 
         # ++++++++++++++++++++++++++++++++++++++
         latents = video_generate_all # This is a latent
+        print(f"Type of latents: {type(latents)}")
+        print(f"Length of latents: {len(latents)}")
+
+        # Print detailed info about each item
+        for i, item in enumerate(latents):
+            print(f"\nItem {i}:")
+            print(f"  Type: {type(item)}")
+            if isinstance(item, torch.Tensor):
+                print(f"  Shape: {item.shape}")
+                print(f"  Dtype: {item.dtype}")
+                print(f"  Device: {item.device}")
+            elif isinstance(item, np.ndarray):
+                print(f"  Shape: {item.shape}")
+                print(f"  Dtype: {item.dtype}")
+            elif hasattr(item, 'size') and callable(item.size):  # For PIL images
+                print(f"  Size (WxH): {item.size}")
+                print(f"  Mode: {item.mode}")
+            else:
+                print(f"  Value: {item}")
+        # Only works if all elements are tensors of the same shape
+        latents = torch.stack(latents)
 
         scale_status = True
         rife_status = True
@@ -378,7 +399,7 @@ def generate_video(
 
         video_generate_all = latents
         # ++++++++++++++++++++++++++++++++++++++
-        
+
         video_generate = video_generate_all[0]
 
         # 6. Export the generated frames to a video file. fps must be 8 for original video.