Fix AutoencoderTiny with use_slicing (huggingface#6850)

* Fix `AutoencoderTiny` with `use_slicing`

When using slicing with AutoencoderTiny, the encoder mistakenly encodes the entire batch for every image in the batch.

* Fixed formatting issue

Author: edwardwli

src/diffusers/models/autoencoders/autoencoder_tiny.py

@@ -292,7 +292,9 @@ def encode(
         self, x: torch.FloatTensor, return_dict: bool = True
     ) -> Union[AutoencoderTinyOutput, Tuple[torch.FloatTensor]]:
         if self.use_slicing and x.shape[0] > 1:
-            output = [self._tiled_encode(x_slice) if self.use_tiling else self.encoder(x) for x_slice in x.split(1)]
+            output = [
+                self._tiled_encode(x_slice) if self.use_tiling else self.encoder(x_slice) for x_slice in x.split(1)
+            ]
             output = torch.cat(output)
         else:
             output = self._tiled_encode(x) if self.use_tiling else self.encoder(x)