Initial docs update for new in-painting pipeline (#910)

Docs update for new in-painting pipeline.
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

README.md

@@ -210,14 +210,16 @@ You can also run this example on colab [![Open In Colab](https://colab.research.
 
 ### In-painting using Stable Diffusion
 
-The `StableDiffusionInpaintPipeline` lets you edit specific parts of an image by providing a mask and text prompt.
+The `StableDiffusionInpaintPipeline` lets you edit specific parts of an image by providing a mask and a text prompt. It uses a model optimized for this particular task, whose license you need to accept before use.
 
-```python
-from io import BytesIO
+Please, visit the [model card](https://huggingface.co/runwayml/stable-diffusion-inpainting), read the license carefully and tick the checkbox if you agree. Note that this is an additional license, you need to accept it even if you accepted the text-to-image Stable Diffusion license in the past. You have to be a registered user in 🤗 Hugging Face Hub, and you'll also need to use an access token for the code to work. For more information on access tokens, please refer to [this section](https://huggingface.co/docs/hub/security-tokens) of the documentation.
 
-import torch
-import requests
+
+```python
 import PIL
+import requests
+import torch
+from io import BytesIO
 
 from diffusers import StableDiffusionInpaintPipeline
 
@@ -231,21 +233,15 @@ mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data
 init_image = download_image(img_url).resize((512, 512))
 mask_image = download_image(mask_url).resize((512, 512))
 
-device = "cuda"
-model_id_or_path = "CompVis/stable-diffusion-v1-4"
 pipe = StableDiffusionInpaintPipeline.from_pretrained(
-    model_id_or_path,
+    "runwayml/stable-diffusion-inpainting",
     revision="fp16",
     torch_dtype=torch.float16,
 )
-# or download via git clone https://huggingface.co/CompVis/stable-diffusion-v1-4
-# and pass `model_id_or_path="./stable-diffusion-v1-4"`.
-pipe = pipe.to(device)
-
-prompt = "a cat sitting on a bench"
-images = pipe(prompt=prompt, init_image=init_image, mask_image=mask_image, strength=0.75).images
+pipe = pipe.to("cuda")
 
-images[0].save("cat_on_bench.png")
+prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
+image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
 ```
 
 ### Tweak prompts reusing seeds and latents

docs/source/api/pipelines/overview.mdx

@@ -151,10 +151,10 @@ You can generate your own latents to reproduce results, or tweak your prompt on
 The `StableDiffusionInpaintPipeline` lets you edit specific parts of an image by providing a mask and text prompt.
 
 ```python
-from io import BytesIO
-
-import requests
 import PIL
+import requests
+import torch
+from io import BytesIO
 
 from diffusers import StableDiffusionInpaintPipeline
 
@@ -170,15 +170,15 @@ mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data
 init_image = download_image(img_url).resize((512, 512))
 mask_image = download_image(mask_url).resize((512, 512))
 
-device = "cuda"
 pipe = StableDiffusionInpaintPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4", revision="fp16", torch_dtype=torch.float16
-).to(device)
-
-prompt = "a cat sitting on a bench"
-images = pipe(prompt=prompt, init_image=init_image, mask_image=mask_image, strength=0.75).images
+    "runwayml/stable-diffusion-inpainting",
+    revision="fp16",
+    torch_dtype=torch.float16,
+)
+pipe = pipe.to("cuda")
 
-images[0].save("cat_on_bench.png")
+prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
+image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
 ```
 
 You can also run this example on colab [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb)

docs/source/using-diffusers/inpaint.mdx

@@ -12,13 +12,19 @@ specific language governing permissions and limitations under the License.
 
 # Text-Guided Image-Inpainting
 
-The [`StableDiffusionInpaintPipeline`] lets you edit specific parts of an image by providing a mask and text prompt.
+The [`StableDiffusionInpaintPipeline`] lets you edit specific parts of an image by providing a mask and a text prompt. It uses a version of Stable Diffusion specifically trained for in-painting tasks.
 
-```python
-from io import BytesIO
+<Tip warning={true}>
+Note that this model is distributed separately from the regular Stable Diffusion model, so you have to accept its license even if you accepted the Stable Diffusion one in the past.
 
-import requests
+Please, visit the [model card](https://huggingface.co/runwayml/stable-diffusion-inpainting), read the license carefully and tick the checkbox if you agree. You have to be a registered user in 🤗 Hugging Face Hub, and you'll also need to use an access token for the code to work. For more information on access tokens, please refer to [this section](https://huggingface.co/docs/hub/security-tokens) of the documentation.
+</Tip>
+
+```python
 import PIL
+import requests
+import torch
+from io import BytesIO
 
 from diffusers import StableDiffusionInpaintPipeline
 
@@ -34,15 +40,24 @@ mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data
 init_image = download_image(img_url).resize((512, 512))
 mask_image = download_image(mask_url).resize((512, 512))
 
-device = "cuda"
 pipe = StableDiffusionInpaintPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4", revision="fp16", torch_dtype=torch.float16
-).to(device)
+    "runwayml/stable-diffusion-inpainting",
+    revision="fp16",
+    torch_dtype=torch.float16,
+)
+pipe = pipe.to("cuda")
+
+prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
+image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
+```
 
-prompt = "a cat sitting on a bench"
-images = pipe(prompt=prompt, init_image=init_image, mask_image=mask_image, strength=0.75).images
+`image`          | `mask_image` | `prompt` | **Output** |
+:-------------------------:|:-------------------------:|:-------------------------:|-------------------------:|
+<img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" alt="drawing" width="250"/> | <img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" alt="drawing" width="250"/> | ***Face of a yellow cat, high resolution, sitting on a park bench*** | <img src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/test.png" alt="drawing" width="250"/> |
 
-images[0].save("cat_on_bench.png")
-```
 
 You can also run this example on colab [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb)
+
+<Tip warning={true}>
+A previous experimental implementation of in-painting used a different, lower-quality process. To ensure backwards compatibility, loading a pretrained pipeline that doesn't contain the new model will still apply the old in-painting method.
+</Tip>
\ No newline at end of file

src/diffusers/pipelines/README.md

@@ -141,10 +141,10 @@ You can generate your own latents to reproduce results, or tweak your prompt on
 The `StableDiffusionInpaintPipeline` lets you edit specific parts of an image by providing a mask and text prompt.
 
 ```python
-from io import BytesIO
-
-import requests
 import PIL
+import requests
+import torch
+from io import BytesIO
 
 from diffusers import StableDiffusionInpaintPipeline
 
@@ -158,17 +158,15 @@ mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data
 init_image = download_image(img_url).resize((512, 512))
 mask_image = download_image(mask_url).resize((512, 512))
 
-device = "cuda"
 pipe = StableDiffusionInpaintPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4",
+    "runwayml/stable-diffusion-inpainting",
     revision="fp16",
     torch_dtype=torch.float16,
-).to(device)
-
-prompt = "a cat sitting on a bench"
-images = pipe(prompt=prompt, init_image=init_image, mask_image=mask_image, strength=0.75).images
+)
+pipe = pipe.to("cuda")
 
-images[0].save("cat_on_bench.png")
+prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
+image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
 ```
 
 You can also run this example on colab [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb)