Update sdxl reference pipeline to latest sdxl pipeline (#9938)

* Update sdxl reference community pipeline

* Update README.md

Add example images.

* Style & quality

* Use example images from huggingface documentation-images repository

---------

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

Author: dimitribarbot

examples/community/README.md

@@ -2619,16 +2619,17 @@ for obj in range(bs):
 
 ### Stable Diffusion XL Reference
 
-This pipeline uses the Reference. Refer to the [stable_diffusion_reference](https://github.com/huggingface/diffusers/blob/main/examples/community/README.md#stable-diffusion-reference).
+This pipeline uses the Reference. Refer to the [Stable Diffusion Reference](https://github.com/huggingface/diffusers/blob/main/examples/community/README.md#stable-diffusion-reference) section for more information.
 
 ```py
 import torch
-from PIL import Image
+# from diffusers import DiffusionPipeline
 from diffusers.utils import load_image
-from diffusers import DiffusionPipeline
 from diffusers.schedulers import UniPCMultistepScheduler
 
-input_image = load_image("https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png")
+from .stable_diffusion_xl_reference import StableDiffusionXLReferencePipeline
+
+input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_reference_input_cat.jpg")
 
 # pipe = DiffusionPipeline.from_pretrained(
 #     "stabilityai/stable-diffusion-xl-base-1.0",
@@ -2646,22 +2647,22 @@ pipe = StableDiffusionXLReferencePipeline.from_pretrained(
 pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
 
 result_img = pipe(ref_image=input_image,
-      prompt="1girl",
+      prompt="a dog",
       num_inference_steps=20,
       reference_attn=True,
       reference_adain=True).images[0]
 ```
 
 Reference Image
 
-![reference_image](https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png)
+![reference_image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_reference_input_cat.jpg)
 
 Output Image
 
-`prompt: 1 girl`
+`prompt: a dog`
 
-`reference_attn=True, reference_adain=True, num_inference_steps=20`
-![Output_image](https://github.com/zideliu/diffusers/assets/34944964/743848da-a215-48f9-ae39-b5e2ae49fb13)
+`reference_attn=False, reference_adain=True, num_inference_steps=20`
+![Output_image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_reference_adain_dog.png)
 
 Reference Image
 ![reference_image](https://github.com/huggingface/diffusers/assets/34944964/449bdab6-e744-4fb2-9620-d4068d9a741b)
@@ -4696,4 +4697,4 @@ with torch.no_grad():
 ```
 
 In the folder examples/pixart there is also a script that can be used to train new models.
-Please check the script `train_controlnet_hf_diffusers.sh` on how to start the training.
+Please check the script `train_controlnet_hf_diffusers.sh` on how to start the training.