diffusers/v0.21.0/en/using-diffusers/inpaint.html

<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;textguided-imageinpainting&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;preserving-the-unmasked-area-of-the-image&quot;,&quot;title&quot;:&quot;Preserving the Unmasked Area of the Image&quot;}],&quot;title&quot;:&quot;Text-guided image-inpainting&quot;}" data-svelte="svelte-1phssyn">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/start-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/vendor-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/paths-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/pages/__layout.svelte-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/pages/using-diffusers/inpaint.mdx-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/Tip-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/CodeBlock-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.21.0/en/_app/chunks/DocNotebookDropdown-hf-doc-builder.js"> 






<h1 class="relative group"><a id="textguided-imageinpainting" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#textguided-imageinpainting"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>Text-guided image-inpainting
	</span></h1>



<div class="flex space-x-1 absolute z-10 right-0 top-0">
	<div class="relative colab-dropdown ">
	<button class="  " type="button">
		
				<img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg">
			</button>
	
	
	
	</div>
	<div class="relative colab-dropdown ">
	<button class="  " type="button">
		
				<img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg">
			</button>
	
	
	
	</div></div>
<p>The <a href="/docs/diffusers/v0.21.0/en/api/pipelines/stable_diffusion/inpaint#diffusers.StableDiffusionInpaintPipeline">StableDiffusionInpaintPipeline</a> allows you to edit specific parts of an image by providing a mask and a text prompt. It uses a version of Stable Diffusion, like <a href="https://huggingface.co/runwayml/stable-diffusion-inpainting" rel="nofollow"><code>runwayml/stable-diffusion-inpainting</code></a> specifically trained for inpainting tasks.</p>
<p>Get started by loading an instance of the <a href="/docs/diffusers/v0.21.0/en/api/pipelines/stable_diffusion/inpaint#diffusers.StableDiffusionInpaintPipeline">StableDiffusionInpaintPipeline</a>:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> PIL
<span class="hljs-keyword">import</span> requests
<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> io <span class="hljs-keyword">import</span> BytesIO

<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionInpaintPipeline

pipeline = StableDiffusionInpaintPipeline.from_pretrained(
    <span class="hljs-string">&quot;runwayml/stable-diffusion-inpainting&quot;</span>,
    torch_dtype=torch.float16,
    use_safetensors=<span class="hljs-literal">True</span>,
    variant=<span class="hljs-string">&quot;fp16&quot;</span>,
)
pipeline = pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>Download an image and a mask of a dog which you’ll eventually replace:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-keyword">def</span> <span class="hljs-title function_">download_image</span>(<span class="hljs-params">url</span>):
    response = requests.get(url)
    <span class="hljs-keyword">return</span> PIL.Image.<span class="hljs-built_in">open</span>(BytesIO(response.content)).convert(<span class="hljs-string">&quot;RGB&quot;</span>)


img_url = <span class="hljs-string">&quot;https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png&quot;</span>
mask_url = <span class="hljs-string">&quot;https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png&quot;</span>

init_image = download_image(img_url).resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))
mask_image = download_image(mask_url).resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))<!-- HTML_TAG_END --></pre></div>
<p>Now you can create a prompt to replace the mask with something else:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START -->prompt = <span class="hljs-string">&quot;Face of a yellow cat, high resolution, sitting on a park bench&quot;</span>
image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div>
<table><thead><tr><th align="center"><code>image</code></th>
<th align="center"><code>mask_image</code></th>
<th align="center"><code>prompt</code></th>
<th align="right">output</th></tr></thead>
<tbody><tr><td align="center"><img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" alt="drawing" width="250"></td>
<td align="center"><img src="https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" alt="drawing" width="250"></td>
<td align="center"><strong><em>Face of a yellow cat, high resolution, sitting on a park bench</em></strong></td>
<td align="right"><img src="https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/in_paint/yellow_cat_sitting_on_a_park_bench.png" alt="drawing" width="250"></td></tr></tbody></table>


<div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p>A previous experimental implementation of inpainting 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 inpainting method.</p></div>
<p>Check out the Spaces below to try out image inpainting yourself!</p>
<iframe src="https://runwayml-stable-diffusion-inpainting.hf.space" frameborder="0" width="850" height="500"></iframe>
<h2 class="relative group"><a id="preserving-the-unmasked-area-of-the-image" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#preserving-the-unmasked-area-of-the-image"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>Preserving the Unmasked Area of the Image
	</span></h2>

<p>Generally speaking, <a href="/docs/diffusers/v0.21.0/en/api/pipelines/stable_diffusion/inpaint#diffusers.StableDiffusionInpaintPipeline">StableDiffusionInpaintPipeline</a> (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:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> PIL
<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np
<span class="hljs-keyword">import</span> torch

<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionInpaintPipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

device = <span class="hljs-string">&quot;cuda&quot;</span>
pipeline = StableDiffusionInpaintPipeline.from_pretrained(
    <span class="hljs-string">&quot;runwayml/stable-diffusion-inpainting&quot;</span>,
    torch_dtype=torch.float16,
)
pipeline = pipeline.to(device)

img_url = <span class="hljs-string">&quot;https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png&quot;</span>
mask_url = <span class="hljs-string">&quot;https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png&quot;</span>

init_image = load_image(img_url).resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))
mask_image = load_image(mask_url).resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))

prompt = <span class="hljs-string">&quot;Face of a yellow cat, high resolution, sitting on a park bench&quot;</span>
repainted_image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image).images[<span class="hljs-number">0</span>]
repainted_image.save(<span class="hljs-string">&quot;repainted_image.png&quot;</span>)

<span class="hljs-comment"># Convert mask to grayscale NumPy array</span>
mask_image_arr = np.array(mask_image.convert(<span class="hljs-string">&quot;L&quot;</span>))
<span class="hljs-comment"># Add a channel dimension to the end of the grayscale mask</span>
mask_image_arr = mask_image_arr[:, :, <span class="hljs-literal">None</span>]
<span class="hljs-comment"># Binarize the mask: 1s correspond to the pixels which are repainted</span>
mask_image_arr = mask_image_arr.astype(np.float32) / <span class="hljs-number">255.0</span>
mask_image_arr[mask_image_arr &lt; <span class="hljs-number">0.5</span>] = <span class="hljs-number">0</span>
mask_image_arr[mask_image_arr &gt;= <span class="hljs-number">0.5</span>] = <span class="hljs-number">1</span>

<span class="hljs-comment"># Take the masked pixels from the repainted image and the unmasked pixels from the initial image</span>
unmasked_unchanged_image_arr = (<span class="hljs-number">1</span> - mask_image_arr) * init_image + mask_image_arr * repainted_image
unmasked_unchanged_image = PIL.Image.fromarray(unmasked_unchanged_image_arr.<span class="hljs-built_in">round</span>().astype(<span class="hljs-string">&quot;uint8&quot;</span>))
unmasked_unchanged_image.save(<span class="hljs-string">&quot;force_unmasked_unchanged.png&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>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.</p>


		<script type="module" data-hydrate="1jvq2pc">
		import { start } from "/docs/diffusers/v0.21.0/en/_app/start-hf-doc-builder.js";
		start({
			target: document.querySelector('[data-hydrate="1jvq2pc"]').parentNode,
			paths: {"base":"/docs/diffusers/v0.21.0/en","assets":"/docs/diffusers/v0.21.0/en"},
			session: {},
			route: false,
			spa: false,
			trailing_slash: "never",
			hydrate: {
				status: 200,
				error: null,
				nodes: [
					import("/docs/diffusers/v0.21.0/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
						import("/docs/diffusers/v0.21.0/en/_app/pages/using-diffusers/inpaint.mdx-hf-doc-builder.js")
				],
				params: {}
			}
		});
	</script>