Move IP Adapter Face ID to core (#7186)

* Switch to peft and multi proj layers

* Move Face ID loading and inference to core

---------

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

docs/source/en/using-diffusers/ip_adapter.md

@@ -362,14 +362,12 @@ IP-Adapter's image prompting and compatibility with other adapters and models ma
 
 ### Face model
 
-Generating accurate faces is challenging because they are complex and nuanced. Diffusers supports two IP-Adapter checkpoints specifically trained to generate faces:
+Generating accurate faces is challenging because they are complex and nuanced. Diffusers supports two IP-Adapter checkpoints specifically trained to generate faces from the [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter) repository:
 
 * [ip-adapter-full-face_sd15.safetensors](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-full-face_sd15.safetensors) is conditioned with images of cropped faces and removed backgrounds
 * [ip-adapter-plus-face_sd15.safetensors](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-plus-face_sd15.safetensors) uses patch embeddings and is conditioned with images of cropped faces
 
-> [!TIP]
->
-> [IP-Adapter-FaceID](https://huggingface.co/h94/IP-Adapter-FaceID) is a face-specific IP-Adapter trained with face ID embeddings instead of CLIP image embeddings, allowing you to generate more consistent faces in different contexts and styles. Try out this popular [community pipeline](https://github.com/huggingface/diffusers/tree/main/examples/community#ip-adapter-face-id) and see how it compares to the other face IP-Adapters.
+Additionally, Diffusers supports all IP-Adapter checkpoints trained with face embeddings extracted by `insightface` face models. Supported models are from the [h94/IP-Adapter-FaceID](https://huggingface.co/h94/IP-Adapter-FaceID) repository.
 
 For face models, use the [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter) checkpoint. It is also recommended to use [`DDIMScheduler`] or [`EulerDiscreteScheduler`] for face models.
 
@@ -411,6 +409,56 @@ image
   </div>
 </div>
 
+To use IP-Adapter FaceID models, first extract face embeddings with `insightface`. Then pass the list of tensors to the pipeline as `ip_adapter_image_embeds`.
+
+```py
+import torch
+from diffusers import StableDiffusionPipeline, DDIMScheduler
+from diffusers.utils import load_image
+from insightface.app import FaceAnalysis
+
+pipeline = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    torch_dtype=torch.float16,
+).to("cuda")
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+pipeline.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder=None, weight_name="ip-adapter-faceid_sd15.bin", image_encoder_folder=None)
+pipeline.set_ip_adapter_scale(0.6)
+
+image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ip_mask_girl1.png")
+
+ref_images_embeds = []
+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)
+ref_images_embeds.append(image.unsqueeze(0))
+ref_images_embeds = torch.stack(ref_images_embeds, dim=0).unsqueeze(0)
+neg_ref_images_embeds = torch.zeros_like(ref_images_embeds)
+id_embeds = torch.cat([neg_ref_images_embeds, ref_images_embeds]).to(dtype=torch.float16, device="cuda"))
+
+generator = torch.Generator(device="cpu").manual_seed(42)
+
+images = pipeline(
+    prompt="A photo of a girl",
+    ip_adapter_image_embeds=[id_embeds], 
+    negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality", 
+    num_inference_steps=20, num_images_per_prompt=1,
+    generator=generator
+).images
+```
+
+Both IP-Adapter FaceID Plus and Plus v2 models require CLIP image embeddings. You can prepare face embeddings as shown previously, then you can extract and pass CLIP embeddings to the hidden image projection layers.
+
+```py
+clip_embeds = pipeline.prepare_ip_adapter_image_embeds([ip_adapter_images], None, torch.device("cuda"), num_images, True)[0]
+
+pipeline.unet.encoder_hid_proj.image_projection_layers[0].clip_embeds = clip_embeds.to(dtype=torch.float16)
+pipeline.unet.encoder_hid_proj.image_projection_layers[0].shortcut = False # True if Plus v2
+```
+
+
 ### Multi IP-Adapter
 
 More than one IP-Adapter can be used at the same time to generate specific images in more diverse styles. For example, you can use IP-Adapter-Face to generate consistent faces and characters, and IP-Adapter Plus to generate those faces in a specific style.

docs/source/en/using-diffusers/loading_adapters.md

@@ -320,3 +320,40 @@ pipeline = AutoPipelineForText2Image.from_pretrained(
 
 pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter-plus_sdxl_vit-h.safetensors")
 ```
+
+### IP-Adapter Face ID models
+
+The IP-Adapter FaceID models are experimental IP Adapters that use image embeddings generated by `insightface` instead of CLIP image embeddings. Some of these models also use LoRA to improve ID consistency.
+You need to install `insightface` and all its requirements to use these models.
+
+<Tip warning={true}>
+As InsightFace pretrained models are available for non-commercial research purposes, IP-Adapter-FaceID models are released exclusively for research purposes and are not intended for commercial use.
+</Tip>
+
+```py
+pipeline = AutoPipelineForText2Image.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    torch_dtype=torch.float16
+).to("cuda")
+
+pipeline.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder=None, weight_name="ip-adapter-faceid_sdxl.bin", image_encoder_folder=None)
+```
+
+If you want to use one of the two IP-Adapter FaceID Plus models, you must also load the CLIP image encoder, as this models use both `insightface` and CLIP image embeddings to achieve better photorealism.
+
+```py
+from transformers import CLIPVisionModelWithProjection
+
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(
+    "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+    torch_dtype=torch.float16,
+)
+
+pipeline = AutoPipelineForText2Image.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    image_encoder=image_encoder,
+    torch_dtype=torch.float16
+).to("cuda")
+
+pipeline.load_ip_adapter("h94/IP-Adapter-FaceID", subfolder=None, weight_name="ip-adapter-faceid-plus_sd15.bin")
+```

examples/community/README.md

@@ -3819,12 +3819,10 @@ export_to_gif(frames, "animation.gif")
 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.
 You can find more results [here](https://github.com/huggingface/diffusers/pull/6276).
 
 ```py
 import diffusers
-diffusers.utils.USE_PEFT_BACKEND = False
 import torch
 from diffusers.utils import load_image
 import cv2