Add sdxl controlnet reference community pipeline (#9893)

* Add reference_attn & reference_adain support for sdxl with other controlnet

* Update README.md

* Update README.md by replacing human example with a cat one

Replace human example with a cat one

* Replace default human example with a cat one

* Use example images from huggingface documentation-images repository

---------

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

Author: dimitribarbot

examples/community/README.md

@@ -2684,6 +2684,88 @@ Output Image
 `reference_attn=True, reference_adain=True, num_inference_steps=20`
 ![output_image](https://github.com/huggingface/diffusers/assets/34944964/9b2f1aca-886f-49c3-89ec-d2031c8e3670)
 
+### Stable Diffusion XL ControlNet Reference
+
+This pipeline uses the Reference Control and with ControlNet. Refer to the [Stable Diffusion ControlNet Reference](https://github.com/huggingface/diffusers/blob/main/examples/community/README.md#stable-diffusion-controlnet-reference) and [Stable Diffusion XL Reference](https://github.com/huggingface/diffusers/blob/main/examples/community/README.md#stable-diffusion-xl-reference) sections for more information.
+
+```py
+from diffusers import ControlNetModel, AutoencoderKL
+from diffusers.schedulers import UniPCMultistepScheduler
+from diffusers.utils import load_image
+import numpy as np
+import torch
+
+import cv2
+from PIL import Image
+
+from .stable_diffusion_xl_controlnet_reference import StableDiffusionXLControlNetReferencePipeline
+
+# download an image
+canny_image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_reference_input_cat.jpg"
+)
+
+ref_image = load_image(
+    "https://hf.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png"
+)
+
+# initialize the models and pipeline
+controlnet_conditioning_scale = 0.5  # recommended for good generalization
+controlnet = ControlNetModel.from_pretrained(
+    "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
+)
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+pipe = StableDiffusionXLControlNetReferencePipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet, vae=vae, torch_dtype=torch.float16
+).to("cuda:0")
+
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+
+# get canny image
+image = np.array(canny_image)
+image = cv2.Canny(image, 100, 200)
+image = image[:, :, None]
+image = np.concatenate([image, image, image], axis=2)
+canny_image = Image.fromarray(image)
+
+# generate image
+image = pipe(
+    prompt="a cat",
+    num_inference_steps=20,
+    controlnet_conditioning_scale=controlnet_conditioning_scale,
+    image=canny_image,
+    ref_image=ref_image,
+    reference_attn=False,
+    reference_adain=True,
+    style_fidelity=1.0,
+    generator=torch.Generator("cuda").manual_seed(42)
+).images[0]
+```
+
+Canny ControlNet Image
+
+![canny_image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_reference_input_cat.jpg)
+
+Reference Image
+
+![ref_image](https://hf.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png)
+
+Output Image
+
+`prompt: a cat`
+
+`reference_attn=True, reference_adain=True, num_inference_steps=20, style_fidelity=1.0`
+
+![Output_image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_reference_attn_adain_canny_cat.png)
+
+`reference_attn=False, reference_adain=True, num_inference_steps=20, style_fidelity=1.0`
+
+![Output_image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_reference_adain_canny_cat.png)
+
+`reference_attn=True, reference_adain=False, num_inference_steps=20, style_fidelity=1.0`
+
+![Output_image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_reference_attn_canny_cat.png)
+
 ### Stable diffusion fabric pipeline
 
 FABRIC approach applicable to a wide range of popular diffusion models, which exploits