[Community Pipeline] IPAdapter FaceID (#6276)

* Add support for IPAdapter FaceID

* Add docs

* Move subfolder to kwargs

* Fix quality

* Fix image encoder loading

* Fix loading + add test

* Move to community folder

* Fix style

* Revert constant update

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

examples/community/README.md

@@ -58,6 +58,7 @@ prompt-to-prompt | change parts of a prompt and retain image structure (see [pap
 |   Null-Text Inversion Pipeline  | Implement [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://arxiv.org/abs/2211.09794) as a pipeline.                                                                                                                                                                                                                                                                                                                                                                                                                                      | [Null-Text Inversion](https://github.com/google/prompt-to-prompt/)      | - |              [Junsheng Luan](https://github.com/Junsheng121) |
 |   Rerender A Video Pipeline                                                                                                    | Implementation of [[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation](https://arxiv.org/abs/2306.07954)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [Rerender A Video Pipeline](#Rerender_A_Video)      | - |              [Yifan Zhou](https://github.com/SingleZombie) |
 | StyleAligned Pipeline                                                                                                    | Implementation of [Style Aligned Image Generation via Shared Attention](https://arxiv.org/abs/2312.02133)                                                                                                                                                                                                                                                                                                                                                                                                                                   | [StyleAligned Pipeline](#stylealigned-pipeline) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://drive.google.com/file/d/15X2E0jFPTajUIjS0FzX50OaHsCbP2lQ0/view?usp=sharing) | [Aryan V S](https://github.com/a-r-r-o-w) |
+|   IP Adapter FaceID Stable Diffusion                                                                                               | Stable Diffusion Pipeline that supports IP Adapter Face ID                                                                                                                                                                                                                                                                                                                                                  |  [IP Adapter Face ID](#ip-adapter-face-id) | - | [Fabio Rigano](https://github.com/fabiorigano) |
 
 To load a custom pipeline you just need to pass the `custom_pipeline` argument to `DiffusionPipeline`, as one of the files in `diffusers/examples/community`. Feel free to send a PR with your own pipelines, we will merge them quickly.
 ```py
@@ -3407,3 +3408,62 @@ images = pipe(
 # Disable StyleAligned if you do not wish to use it anymore
 pipe.disable_style_aligned()
 ```
+
+### IP Adapter Face ID
+IP Adapter FaceID is an experimental IP Adapter model that uses image embeddings generated by `insightface`, so no image encoder needs to be loaded.
+You need to install `insightface` and all its requirements to use this model.
+You must pass the image embedding tensor as `image_embeds` to the StableDiffusionPipeline instead of `ip_adapter_image`.
+You have to disable PEFT BACKEND in order to load weights.
+
+```py
+import diffusers
+diffusers.utils.USE_PEFT_BACKEND = False
+import torch
+from diffusers.utils import load_image
+import cv2
+import numpy as np
+from diffusers import DiffusionPipeline, AutoencoderKL, DDIMScheduler
+from insightface.app import FaceAnalysis
+
+
+noise_scheduler = DDIMScheduler(
+    num_train_timesteps=1000,
+    beta_start=0.00085,
+    beta_end=0.012,
+    beta_schedule="scaled_linear",
+    clip_sample=False,
+    set_alpha_to_one=False,
+    steps_offset=1,
+)
+vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse").to(dtype=torch.float16)
+pipeline = DiffusionPipeline.from_pretrained(
+    "SG161222/Realistic_Vision_V4.0_noVAE",
+    torch_dtype=torch.float16,
+    scheduler=noise_scheduler,
+    vae=vae,
+    custom_pipeline="ip_adapter_face_id"
+)
+pipeline.load_ip_adapter_face_id("h94/IP-Adapter-FaceID", "ip-adapter-faceid_sd15.bin")
+pipeline.to("cuda")
+
+generator = torch.Generator(device="cpu").manual_seed(42)
+num_images=2
+
+image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ai_face2.png")
+
+app = FaceAnalysis(name="buffalo_l", providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
+app.prepare(ctx_id=0, det_size=(640, 640))
+image = cv2.cvtColor(np.asarray(image), cv2.COLOR_BGR2RGB)
+faces = app.get(image)
+image = torch.from_numpy(faces[0].normed_embedding).unsqueeze(0)
+images = pipeline(
+    prompt="A photo of a girl wearing a black dress, holding red roses in hand, upper body, behind is the Eiffel Tower",
+    image_embeds=image,
+    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality", 
+    num_inference_steps=20, num_images_per_prompt=num_images, width=512, height=704, 
+    generator=generator
+).images
+
+for i in range(num_images):
+    images[i].save(f"c{i}.png")
+```