[Pipeline] Fix error of SVD pipeline when num_videos_per_prompt > 1 (#7786)

swap the order for do_classifier_free_guidance concat with repeat

Co-authored-by: Sayak Paul <[email protected]>
Co-authored-by: Dhruv Nair <[email protected]>

Author: 3 people

src/diffusers/pipelines/stable_video_diffusion/pipeline_stable_video_diffusion.py

@@ -199,6 +199,9 @@ def _encode_vae_image(
         image = image.to(device=device)
         image_latents = self.vae.encode(image).latent_dist.mode()
 
+        # duplicate image_latents for each generation per prompt, using mps friendly method
+        image_latents = image_latents.repeat(num_videos_per_prompt, 1, 1, 1)
+
         if do_classifier_free_guidance:
             negative_image_latents = torch.zeros_like(image_latents)
 
@@ -207,9 +210,6 @@ def _encode_vae_image(
             # to avoid doing two forward passes
             image_latents = torch.cat([negative_image_latents, image_latents])
 
-        # duplicate image_latents for each generation per prompt, using mps friendly method
-        image_latents = image_latents.repeat(num_videos_per_prompt, 1, 1, 1)
-
         return image_latents
 
     def _get_add_time_ids(