apply `repeat_interleave` fix for `mps` to stable diffusion image2image pipeline (#1135)

copy from other pipeline

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py

@@ -337,8 +337,10 @@ class StableDiffusionImg2ImgPipeline(DiffusionPipeline):
             text_input_ids = text_input_ids[:, : self.tokenizer.model_max_length]
         text_embeddings = self.text_encoder(text_input_ids.to(device))[0]
 
-        # duplicate text embeddings for each generation per prompt
-        text_embeddings = text_embeddings.repeat_interleave(num_images_per_prompt, dim=0)
+        # duplicate text embeddings for each generation per prompt, using mps friendly method
+        bs_embed, seq_len, _ = text_embeddings.shape
+        text_embeddings = text_embeddings.repeat(1, num_images_per_prompt, 1)
+        text_embeddings = text_embeddings.view(bs_embed * num_images_per_prompt, seq_len, -1)
 
         # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
         # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`