Added vae_slicing option

pipeline.py

@@ -542,6 +542,21 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
         # set slice_size = `None` to disable `attention slicing`
         self.enable_attention_slicing(None)
 
+    def enable_vae_slicing(self):
+        r"""
+        Enable sliced VAE decoding.
+        When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several
+        steps. This is useful to save some memory and allow larger batch sizes.
+        """
+        self.vae.enable_slicing()
+
+    def disable_vae_slicing(self):
+        r"""
+        Disable sliced VAE decoding. If `enable_vae_slicing` was previously invoked, this method will go back to
+        computing decoding in one step.
+        """
+        self.vae.disable_slicing()
+
     def enable_sequential_cpu_offload(self):
         r"""
         Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet,