fix cogvideox autoencoder decode (#9569)

Co-authored-by: Aryan <aryan@huggingface.co>

Author: Xiang-cd

src/diffusers/models/autoencoders/autoencoder_kl_cogvideox.py

@@ -1234,7 +1234,7 @@ def _decode(self, z: torch.Tensor, return_dict: bool = True) -> Union[DecoderOut
             return self.tiled_decode(z, return_dict=return_dict)
 
         frame_batch_size = self.num_latent_frames_batch_size
-        num_batches = num_frames // frame_batch_size
+        num_batches = max(num_frames // frame_batch_size, 1)
         conv_cache = None
         dec = []