[`Docs`] Fix typos (#7118)

Fix typos, formatting and remove trailing whitespace

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

@@ -362,6 +362,7 @@ image = pipeline(
     num_inference_steps=50, num_images_per_prompt=1,
     generator=generator,
 ).images[0]
+image
 ```
 
 <div class="flex justify-center">
@@ -386,7 +387,7 @@ pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16
 
 pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
 pipeline.load_lora_weights(lcm_lora_id)
-pipeline.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
 pipeline.enable_model_cpu_offload()
 ```
 
@@ -461,7 +462,7 @@ image = pipeline(
     negative_prompt="monochrome, lowres, bad anatomy, worst quality, low quality",
     num_inference_steps=50,
     generator=generator,
-).image[0]
+).images[0]
 image
 ```
 
@@ -511,8 +512,7 @@ If you have more than one IP-Adapter image, load them into a list, ensuring each
 face_image1 = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_girl1.png")
 face_image2 = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/ip_mask_girl2.png")
 
-ip_images =[[image1], [image2]]
-
+ip_images = [[face_image1], [face_image2]]
 ```
 
 <div class="flex flex-row gap-4">
@@ -529,11 +529,10 @@ ip_images =[[image1], [image2]]
 Pass preprocessed masks to the pipeline using `cross_attention_kwargs` as shown below:
 
 ```py
-
 pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name=["ip-adapter-plus-face_sdxl_vit-h.safetensors"] * 2)
 pipeline.set_ip_adapter_scale([0.7] * 2)
 generator = torch.Generator(device="cpu").manual_seed(0)
-num_images=1
+num_images = 1
 
 image = pipeline(
     prompt="2 girls",
@@ -542,6 +541,7 @@ image = pipeline(
     num_inference_steps=20, num_images_per_prompt=num_images,
     generator=generator, cross_attention_kwargs={"ip_adapter_masks": masks}
 ).images[0]
+image
 ```
 
 <div class="flex justify-center">

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

@@ -355,11 +355,13 @@ images
 
 ### IP-Adapter Plus
 
-IP-Adapter relies on an image encoder to generate image features. If the IP-Adapter repository contains a `image_encoder` subfolder, the image encoder is automatically loaded and registed to the pipeline. Otherwise, you'll need to explicitly load the image encoder with a [`~transformers.CLIPVisionModelWithProjection`] model and pass it to the pipeline.
+IP-Adapter relies on an image encoder to generate image features. If the IP-Adapter repository contains an `image_encoder` subfolder, the image encoder is automatically loaded and registered to the pipeline. Otherwise, you'll need to explicitly load the image encoder with a [`~transformers.CLIPVisionModelWithProjection`] model and pass it to the pipeline.
 
 This is the case for *IP-Adapter Plus* checkpoints which use the ViT-H image encoder.
 
 ```py
+from transformers import CLIPVisionModelWithProjection
+
 image_encoder = CLIPVisionModelWithProjection.from_pretrained(
     "h94/IP-Adapter",
     subfolder="models/image_encoder",