modifying requirements.txt

inference/cli_demo_camera_i2v_pcd.py

@@ -369,12 +369,13 @@ def generate_video(
         # ++++++++++++++++++++++++++++++++++++++
         latents = video_generate_all # This is a latent
  
-        transform = T.ToTensor()
-
+        to_tensor = T.ToTensor()
         latents = [
-            torch.stack([transform(img) for img in sublist])  # [num_frames, C, H, W]
-            for sublist in latents
-        ]  # List of [T, C, H, W] tensors
+            torch.stack([to_tensor(img) for img in sublist])  # [T, C, H, W]
+            for sublist in latents  # original input
+        ]
+
+        latents = torch.stack(latents)  # [B, T, C, H, W]
 
         print(f"Type of latents: {type(latents)}")
         print(f"Length of latents: {len(latents)}")