[docs] Add inpainting example for forcing the unmasked area to remain unchanged to the docs (#4536)

* Initial code to add force_unmasked_unchanged argument to StableDiffusionInpaintPipeline.__call__.

* Try to improve StableDiffusionInpaintPipelineFastTests.get_dummy_inputs.

* Use original mask to preserve unmasked pixels in pixel space rather than latent space.

* make style

* start working on note in docs to force unmasked area to be unchanged

* Add example of forcing the unmasked area to remain unchanged.

* Revert "make style"

This reverts commit fa7759293af916c665f683387a52fd789ed10531.

* Revert "Use original mask to preserve unmasked pixels in pixel space rather than latent space."

This reverts commit 092bd0e9e9628f02ff917aafb2a5c9252776b6e9.

* Revert "Try to improve StableDiffusionInpaintPipelineFastTests.get_dummy_inputs."

This reverts commit ff41cf43c5a820057289e0852fb41b3e2074d86d.

* Revert "Initial code to add force_unmasked_unchanged argument to StableDiffusionInpaintPipeline.__call__."

This reverts commit 989979752a1c9e6e16e92d8f1b3d14b70829fbb5.

---------
Co-authored-by: Will Berman <wlbberman@gmail.com>

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

@@ -76,3 +76,49 @@ Check out the Spaces below to try out image inpainting yourself!
 	width="850"
 	height="500"
 ></iframe>
+
+## Preserving the Unmasked Area of the Image
+
+Generally speaking, [`StableDiffusionInpaintPipeline`] (and other inpainting pipelines) will change the unmasked part of the image as well. If this behavior is undesirable, you can force the unmasked area to remain the same as follows:
+
+```python
+import PIL
+import numpy as np
+import torch
+
+from diffusers import StableDiffusionInpaintPipeline
+from diffusers.utils import load_image
+
+device = "cuda"
+pipeline = StableDiffusionInpaintPipeline.from_pretrained(
+    "runwayml/stable-diffusion-inpainting",
+    torch_dtype=torch.float16,
+)
+pipeline = pipeline.to(device)
+
+img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
+mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
+
+init_image = load_image(img_url).resize((512, 512))
+mask_image = load_image(mask_url).resize((512, 512))
+
+prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
+repainted_image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
+repainted_image.save("repainted_image.png")
+
+# Convert mask to grayscale NumPy array
+mask_image_arr = np.array(mask_image.convert("L"))
+# Add a channel dimension to the end of the grayscale mask
+mask_image_arr = mask_image_arr[:, :, None]
+# Binarize the mask: 1s correspond to the pixels which are repainted
+mask_image_arr = mask_image_arr.astype(np.float32) / 255.0
+mask_image_arr[mask_image_arr < 0.5] = 0
+mask_image_arr[mask_image_arr >= 0.5] = 1
+
+# Take the masked pixels from the repainted image and the unmasked pixels from the initial image
+unmasked_unchanged_image_arr = (1 - mask_image_arr) * init_image_arr + mask_image_arr * repainted_image_arr
+unmasked_unchanged_image = PIL.Image.fromarray(unmasked_unchanged_image_arr.round().astype("uint8"))
+unmasked_unchanged_image.save("force_unmasked_unchanged.png")
+```
+
+Forcing the unmasked portion of the image to remain the same might result in some weird transitions between the unmasked and masked areas, since the model will typically change the masked and unmasked areas to make the transition more natural.