Update pipeline.py

pipeline.py

@@ -378,13 +378,24 @@ class AnimateDiffControlNetPipeline(
 
             if not isinstance(image, torch.Tensor):
                 image = self.feature_extractor(image, return_tensors="pt").pixel_values
-
+    
             image = image.to(device=device, dtype=dtype)
-            image_embeds = self.image_encoder(image).image_embeds
-            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-
-            uncond_image_embeds = torch.zeros_like(image_embeds)
-            return image_embeds, uncond_image_embeds
+            if output_hidden_states:
+                image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
+                image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
+                uncond_image_enc_hidden_states = self.image_encoder(
+                    torch.zeros_like(image), output_hidden_states=True
+                ).hidden_states[-2]
+                uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
+                    num_images_per_prompt, dim=0
+                )
+                return image_enc_hidden_states, uncond_image_enc_hidden_states
+            else:
+                image_embeds = self.image_encoder(image).image_embeds
+                image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
+                uncond_image_embeds = torch.zeros_like(image_embeds)
+    
+                return image_embeds, uncond_image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
     def prepare_ip_adapter_image_embeds(