Buckets:

hf-doc-build
/

doc

Files
xet
hf-doc-build/doc / diffusers /main /es /advanced_inference /outpaint.html
mishig
3 days ago
download
raw
32.8 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Outpainting&quot;,&quot;local&quot;:&quot;outpainting&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Preparación de imágenes&quot;,&quot;local&quot;:&quot;image-preparation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Outpaint&quot;,&quot;local&quot;:&quot;outpaint&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
		<link href="/docs/diffusers/main/en/_app/immutable/entry/start.0S0_iEoG.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/I9eooN77.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/Bupkjr9f.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/CyvZ3FS5.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/l0QnnOED.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DnVIJfC5.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/nodes/0.DteTvmQZ.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/CoSrdQax.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/nodes/2.CJ7qCPpK.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DSPDl1gz.js" rel="modulepreload">
		<!--w57hbo--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Outpainting&quot;,&quot;local&quot;:&quot;outpainting&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Image preparation&quot;,&quot;local&quot;:&quot;image-preparation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Outpaint&quot;,&quot;local&quot;:&quot;outpaint&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
		<link href="/docs/diffusers/main/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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><!----></span> <span dir="auto">Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="outpainting" 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="#outpainting"><span><svg 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><!---->Outpainting<!----></span></h1><!--]--><!----> <p>Outpainting extiende una imagen más allá de sus límites originales, lo que permite añadir, reemplazar o modificar elementos visuales en una imagen mientras se preserva la imagen original. Al igual que con <a href="../using-diffusers/inpaint">inpainting</a>, se desea rellenar el área blanca (en este caso, el área exterior de la imagen original) con nuevos elementos visuales manteniendo la imagen original (representada por una máscara de píxeles negros). Hay varias formas de realizar outpainting, como con <a href="https://hf.co/blog/OzzyGT/outpainting-controlnet" rel="nofollow">ControlNet</a> o con <a href="https://hf.co/blog/OzzyGT/outpainting-differential-diffusion" rel="nofollow">Differential Diffusion</a>.</p> <p>Esta guía te mostrará cómo hacer outpainting con un modelo de inpainting, ControlNet y un estimador de ZoeDepth.</p> <p>Antes de comenzar, asegúrate de tener instalada la biblioteca <a href="https://github.com/huggingface/controlnet_aux" rel="nofollow">controlnet_aux</a> para poder usar el estimador ZoeDepth.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->!pip install -q controlnet_aux<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="image-preparation" 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="#image-preparation"><span><svg 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><!---->Preparación de imágenes<!----></span></h2><!--]--><!----> <p>Comience seleccionando una imagen para ampliar y elimine el fondo con un Space como <a href="https://hf.co/spaces/briaai/BRIA-RMBG-1.4" rel="nofollow">BRIA-RMBG-1.4</a>.</p> <iframe src="https://briaai-bria-rmbg-1-4.hf.space" frameborder="0" width="850" height="450"></iframe> <p>Por ejemplo, elimina el fondo de esta imagen de un par de zapatos.</p> <div class="flex flex-row gap-4"><div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/original-jordan.png"/> <figcaption class="mt-2 text-center text-sm text-gray-500">imagen original</figcaption></div> <div class="flex-1"><img class="rounded-xl" src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/no-background-jordan.png"/> <figcaption class="mt-2 text-center text-sm text-gray-500">fondo eliminado</figcaption></div></div> <p>Los modelos de <a href="../api/pipelines/stable_diffusion/stable_diffusion_xl">Stable Diffusion XL (SDXL)</a> funcionan mejor con imágenes de 1024x1024, pero puedes redimensionar la imagen a cualquier tamaño siempre que tu hardware tenga suficiente memoria para soportarlo. El fondo transparente de la imagen también debe reemplazarse por un fondo blanco. Crea una función (como la siguiente) que escale la imagen y la pegue sobre un fondo blanco.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> random

<span class="hljs-keyword">import</span> requests
<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> controlnet_aux <span class="hljs-keyword">import</span> ZoeDetector
<span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image, ImageOps

<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> (
    AutoencoderKL,
    ControlNetModel,
    StableDiffusionXLControlNetPipeline,
    StableDiffusionXLInpaintPipeline,
)

<span class="hljs-keyword">def</span> <span class="hljs-title function_">scale_and_paste</span>(<span class="hljs-params">original_image</span>):
    aspect_ratio = original_image.width / original_image.height

    <span class="hljs-keyword">if</span> original_image.width &gt; original_image.height:
        new_width = <span class="hljs-number">1024</span>
        new_height = <span class="hljs-built_in">round</span>(new_width / aspect_ratio)
    <span class="hljs-keyword">else</span>:
        new_height = <span class="hljs-number">1024</span>
        new_width = <span class="hljs-built_in">round</span>(new_height * aspect_ratio)

    resized_original = original_image.resize((new_width, new_height), Image.LANCZOS)
    white_background = Image.new(<span class="hljs-string">&quot;RGBA&quot;</span>, (<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>), <span class="hljs-string">&quot;white&quot;</span>)
    x = (<span class="hljs-number">1024</span> - new_width) // <span class="hljs-number">2</span>
    y = (<span class="hljs-number">1024</span> - new_height) // <span class="hljs-number">2</span>
    white_background.paste(resized_original, (x, y), resized_original)

    <span class="hljs-keyword">return</span> resized_original, white_background

original_image = Image.<span class="hljs-built_in">open</span>(
    requests.get(
        <span class="hljs-string">&quot;https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/no-background-jordan.png&quot;</span>,
        stream=<span class="hljs-literal">True</span>,
    ).raw
).convert(<span class="hljs-string">&quot;RGBA&quot;</span>)
resized_img, white_bg_image = scale_and_paste(original_image)<!----></pre></div><!----> <p>Para evitar añadir detalles no deseados, utilice el estimador ZoeDepth para proporcionar orientación adicional durante la generación y garantizar que los zapatos se mantengan consistentes con la imagen original.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->zoe = ZoeDetector.from_pretrained(<span class="hljs-string">&quot;lllyasviel/Annotators&quot;</span>)
image_zoe = zoe(white_bg_image, detect_resolution=<span class="hljs-number">512</span>, image_resolution=<span class="hljs-number">1024</span>)
image_zoe<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/zoedepth-jordan.png"/></div> <!--[1--><h2 class="relative group"><a id="outpaint" 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="#outpaint"><span><svg 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><!---->Outpaint<!----></span></h2><!--]--><!----> <p>Una vez que tu imagen esté lista, puedes generar contenido en el área blanca alrededor de los zapatos con <a href="https://hf.co/destitech/controlnet-inpaint-dreamer-sdxl" rel="nofollow">controlnet-inpaint-dreamer-sdxl</a>, un ControlNet de SDXL entrenado para inpainting.</p> <p>Carga el ControlNet de inpainting, el modelo ZoeDepth y el VAE, y pásalos a <a href="/docs/diffusers/main/es/api/pipelines/controlnet_sdxl#diffusers.StableDiffusionXLControlNetPipeline">StableDiffusionXLControlNetPipeline</a>. Después, puedes crear una función opcional <code>generate_image</code> (por comodidad) para hacer outpainting de una imagen inicial.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->controlnets = [
    ControlNetModel.from_pretrained(
        <span class="hljs-string">&quot;destitech/controlnet-inpaint-dreamer-sdxl&quot;</span>, dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>
    ),
    ControlNetModel.from_pretrained(
        <span class="hljs-string">&quot;diffusers/controlnet-zoe-depth-sdxl-1.0&quot;</span>, dtype=torch.float16
    ),
]
vae = AutoencoderKL.from_pretrained(<span class="hljs-string">&quot;madebyollin/sdxl-vae-fp16-fix&quot;</span>, dtype=torch.float16).to(<span class="hljs-string">&quot;cuda&quot;</span>)  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
pipeline = StableDiffusionXLControlNetPipeline.from_pretrained(
    <span class="hljs-string">&quot;SG161222/RealVisXL_V4.0&quot;</span>, dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>, controlnet=controlnets, vae=vae
).to(<span class="hljs-string">&quot;cuda&quot;</span>)

<span class="hljs-keyword">def</span> <span class="hljs-title function_">generate_image</span>(<span class="hljs-params">prompt, negative_prompt, inpaint_image, zoe_image, seed: <span class="hljs-built_in">int</span> = <span class="hljs-literal">None</span></span>):
    <span class="hljs-keyword">if</span> seed <span class="hljs-keyword">is</span> <span class="hljs-literal">None</span>:
        seed = random.randint(<span class="hljs-number">0</span>, <span class="hljs-number">2</span>**<span class="hljs-number">32</span> - <span class="hljs-number">1</span>)

    generator = torch.Generator(device=<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(seed)

    image = pipeline(
        prompt,
        negative_prompt=negative_prompt,
        image=[inpaint_image, zoe_image],
        guidance_scale=<span class="hljs-number">6.5</span>,
        num_inference_steps=<span class="hljs-number">25</span>,
        generator=generator,
        controlnet_conditioning_scale=[<span class="hljs-number">0.5</span>, <span class="hljs-number">0.8</span>],
        control_guidance_end=[<span class="hljs-number">0.9</span>, <span class="hljs-number">0.6</span>],
    ).images[<span class="hljs-number">0</span>]

    <span class="hljs-keyword">return</span> image

prompt = <span class="hljs-string">&quot;nike air jordans on a basketball court&quot;</span>
negative_prompt = <span class="hljs-string">&quot;&quot;</span>

temp_image = generate_image(prompt, negative_prompt, white_bg_image, image_zoe, <span class="hljs-number">908097</span>)<!----></pre></div><!----> <p>Pega la imagen original sobre la imagen inicial extendida. Mejorarás el fondo extendido en un paso posterior.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->x = (<span class="hljs-number">1024</span> - resized_img.width) // <span class="hljs-number">2</span>
y = (<span class="hljs-number">1024</span> - resized_img.height) // <span class="hljs-number">2</span>
temp_image.paste(resized_img, (x, y), resized_img)
temp_image<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/initial-outpaint.png"/></div> <blockquote class="tip"><p>Ahora es un buen momento para liberar algo de memoria si te estás quedando sin espacio.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->pipeline=<span class="hljs-literal">None</span>
torch.cuda.empty_cache()<!----></pre></div><!----></blockquote> <p>Ahora que tienes una imagen inicial extendida, carga el <a href="/docs/diffusers/main/es/api/pipelines/stable_diffusion/stable_diffusion_xl#diffusers.StableDiffusionXLInpaintPipeline">StableDiffusionXLInpaintPipeline</a> con el modelo <a href="https://hf.co/SG161222/RealVisXL_V4.0" rel="nofollow">RealVisXL</a> para generar la imagen final extendida con una mejor calidad.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->pipeline = StableDiffusionXLInpaintPipeline.from_pretrained(
    <span class="hljs-string">&quot;OzzyGT/RealVisXL_V4.0_inpainting&quot;</span>,
    dtype=torch.float16,
    variant=<span class="hljs-string">&quot;fp16&quot;</span>,
    vae=vae,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span><!----></pre></div><!----> <p>Prepara una máscara para la imagen final generada por outpainting. Para crear una transición más natural entre la imagen original y el fondo generado, difumina la máscara para que se integre mejor.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->mask = Image.new(<span class="hljs-string">&quot;L&quot;</span>, temp_image.size)
mask.paste(resized_img.split()[<span class="hljs-number">3</span>], (x, y))
mask = ImageOps.invert(mask)
final_mask = mask.point(<span class="hljs-keyword">lambda</span> p: p &gt; <span class="hljs-number">128</span> <span class="hljs-keyword">and</span> <span class="hljs-number">255</span>)
mask_blurred = pipeline.mask_processor.blur(final_mask, blur_factor=<span class="hljs-number">20</span>)
mask_blurred<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/blurred-mask.png"/></div> <p>Cree un mejor prompt y páselo a la función <code>generate_outpaint</code> para generar la imagen final outpainted. Vuelva a pegar la imagen original sobre el fondo outpainted final.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">def</span> <span class="hljs-title function_">generate_outpaint</span>(<span class="hljs-params">prompt, negative_prompt, image, mask, seed: <span class="hljs-built_in">int</span> = <span class="hljs-literal">None</span></span>):
    <span class="hljs-keyword">if</span> seed <span class="hljs-keyword">is</span> <span class="hljs-literal">None</span>:
        seed = random.randint(<span class="hljs-number">0</span>, <span class="hljs-number">2</span>**<span class="hljs-number">32</span> - <span class="hljs-number">1</span>)

    generator = torch.Generator(device=<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(seed)

    image = pipeline(
        prompt,
        negative_prompt=negative_prompt,
        image=image,
        mask_image=mask,
        guidance_scale=<span class="hljs-number">10.0</span>,
        strength=<span class="hljs-number">0.8</span>,
        num_inference_steps=<span class="hljs-number">30</span>,
        generator=generator,
    ).images[<span class="hljs-number">0</span>]

    <span class="hljs-keyword">return</span> image

prompt = <span class="hljs-string">&quot;high quality photo of nike air jordans on a basketball court, highly detailed&quot;</span>
negative_prompt = <span class="hljs-string">&quot;&quot;</span>

final_image = generate_outpaint(prompt, negative_prompt, temp_image, mask_blurred, <span class="hljs-number">7688778</span>)
x = (<span class="hljs-number">1024</span> - resized_img.width) // <span class="hljs-number">2</span>
y = (<span class="hljs-number">1024</span> - resized_img.height) // <span class="hljs-number">2</span>
final_image.paste(resized_img, (x, y), resized_img)
final_image<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/stevhliu/testing-images/resolve/main/final-outpaint.png"/></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/diffusers/blob/main/docs/source/en/advanced_inference/outpaint.md" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
			
			<script>
				{
					__sveltekit_1qsdbwf = {
						base: "/docs/diffusers/main/en",
						assets: "/docs/diffusers/main/en"
					};
					const element = document.currentScript.parentElement;
					Promise.all([
						import("/docs/diffusers/main/en/_app/immutable/entry/start.0S0_iEoG.js"),
						import("/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 2],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>
		
Xet Storage Details

Size:: 32.8 kB
Xet hash:: 87356d9539fca240393ebba7c14d677ae7e7b912a49241da5aa3c29fffaa7544
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.