update

Author: a-r-r-o-w

src/diffusers/models/autoencoders/autoencoder_kl_cogvideox.py

@@ -1182,7 +1182,8 @@ def _encode(self, x: torch.Tensor) -> torch.Tensor:
 
         frame_batch_size = self.num_sample_frames_batch_size
         # Note: We expect the number of frames to be either `1` or `frame_batch_size * k` or `frame_batch_size * k + 1` for some k.
-        num_batches = num_frames // frame_batch_size if num_frames > 1 else 1
+        # So, it is okay to not round up as the extra remaining frame is handled in the loop
+        num_batches = max(num_frames // frame_batch_size, 1)
         conv_cache = None
         enc = []
 
@@ -1330,7 +1331,8 @@ def tiled_encode(self, x: torch.Tensor) -> torch.Tensor:
             row = []
             for j in range(0, width, overlap_width):
                 # Note: We expect the number of frames to be either `1` or `frame_batch_size * k` or `frame_batch_size * k + 1` for some k.
-                num_batches = num_frames // frame_batch_size if num_frames > 1 else 1
+                # So, it is okay to not round up as the extra remaining frame is handled in the loop
+                num_batches = max(num_frames // frame_batch_size, 1)
                 conv_cache = None
                 time = []
 
@@ -1409,7 +1411,7 @@ def tiled_decode(self, z: torch.Tensor, return_dict: bool = True) -> Union[Decod
         for i in range(0, height, overlap_height):
             row = []
             for j in range(0, width, overlap_width):
-                num_batches = num_frames // frame_batch_size
+                num_batches = max(num_frames // frame_batch_size, 1)
                 conv_cache = None
                 time = []