Buckets:

hf-doc-build
/

doc-dev

hf-doc-build/doc-dev / diffusers /pr_12652 /zh /quicktour.html

59.5 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"快速上手","local":"快速上手","sections":[{"title":"扩散模型管道","local":"扩散模型管道","sections":[{"title":"本地管道","local":"本地管道","sections":[],"depth":3},{"title":"更换调度器","local":"更换调度器","sections":[],"depth":3}],"depth":2},{"title":"模型","local":"模型","sections":[],"depth":2},{"title":"调度器","local":"调度器","sections":[],"depth":2},{"title":"下一步","local":"下一步","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/diffusers/pr_12652/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/entry/start.ca7a833f.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/scheduler.e4ff9b64.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/singletons.71526a34.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/index.f9be34a7.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/paths.0df57e7f.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/entry/app.746b83f3.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/preload-helper.bb94e341.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/index.09f1bca0.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/nodes/0.8237e20e.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/nodes/39.f6abb499.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.3bffcf96.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/CodeBlock.3dd9a65d.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12652/zh/_app/immutable/chunks/DocNotebookDropdown.02241b22.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"快速上手","local":"快速上手","sections":[{"title":"扩散模型管道","local":"扩散模型管道","sections":[{"title":"本地管道","local":"本地管道","sections":[],"depth":3},{"title":"更换调度器","local":"更换调度器","sections":[],"depth":3}],"depth":2},{"title":"模型","local":"模型","sections":[],"depth":2},{"title":"调度器","local":"调度器","sections":[],"depth":2},{"title":"下一步","local":"下一步","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div 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>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> </div> <div class="flex space-x-1 " style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"> <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> <h1 class="relative group"><a id="快速上手" 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="#快速上手"><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>快速上手</span></h1> <p data-svelte-h="svelte-cwrr0w">训练扩散模型，是为了对随机高斯噪声进行逐步去噪，以生成令人感兴趣的样本，比如图像或者语音。</p> <p data-svelte-h="svelte-wf7zan">扩散模型的发展引起了人们对生成式人工智能的极大兴趣，你可能已经在网上见过扩散生成的图像了。🧨 Diffusers库的目的是让大家更易上手扩散模型。</p> <p data-svelte-h="svelte-1p86fh9">无论你是开发人员还是普通用户，本文将向你介绍🧨 Diffusers 并帮助你快速开始生成内容！</p> <p data-svelte-h="svelte-iaz0x1">🧨 Diffusers 库的三个主要组件：</p> <p data-svelte-h="svelte-1gmty1c">无论你是开发者还是普通用户，这个快速指南将向你介绍🧨 Diffusers，并帮助你快速使用和生成！该库三个主要部分如下：</p> <ul data-svelte-h="svelte-6lqr76"><li><code>DiffusionPipeline</code>是一个高级的端到端类，旨在通过预训练的扩散模型快速生成样本进行推理。</li> <li>作为创建扩散系统做组件的流行的预训练<a href="./api/models">模型</a>框架和模块。</li> <li>许多不同的<a href="./api/schedulers/overview">调度器</a>：控制如何在训练过程中添加噪声的算法，以及如何在推理过程中生成去噪图像的算法。</li></ul> <p data-svelte-h="svelte-12lku06">快速入门将告诉你如何使用<code>DiffusionPipeline</code>进行推理，然后指导你如何结合模型和调度器以复现<code>DiffusionPipeline</code>内部发生的事情。</p> <blockquote class="tip" data-svelte-h="svelte-1ev33t"><p>快速入门是🧨<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb" rel="nofollow">Diffusers入门</a>的简化版，可以帮助你快速上手。如果你想了解更多关于🧨 Diffusers的目标、设计理念以及关于它的核心API的更多细节，可以点击🧨<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb" rel="nofollow">Diffusers入门</a>查看。</p></blockquote> <p data-svelte-h="svelte-1lw160i">在开始之前，确认一下你已经安装好了所需要的库：</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 class=""><!-- HTML_TAG_START -->pip install --upgrade diffusers accelerate transformers<!-- HTML_TAG_END --></pre></div> <ul data-svelte-h="svelte-1yihngv"><li><a href="https://huggingface.co/docs/accelerate/index" rel="nofollow">🤗 Accelerate</a> 在推理和训练过程中加速模型加载。</li> <li><a href="https://huggingface.co/docs/transformers/index" rel="nofollow">🤗 Transformers</a> 是运行最流行的扩散模型所必须的库，比如<a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview" rel="nofollow">Stable Diffusion</a>.</li></ul> <h2 class="relative group"><a id="扩散模型管道" 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="#扩散模型管道"><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>扩散模型管道</span></h2> <p data-svelte-h="svelte-17wiug5"><code>DiffusionPipeline</code>是用预训练的扩散系统进行推理的最简单方法。它是一个包含模型和调度器的端到端系统。你可以直接使用<code>DiffusionPipeline</code>完成许多任务。请查看下面的表格以了解一些支持的任务，要获取完整的支持任务列表，请查看<a href="./api/pipelines/overview#diffusers-summary">🧨 Diffusers 总结</a> 。</p> <table data-svelte-h="svelte-17r70yk"><thead><tr><th><strong>任务</strong></th> <th><strong>描述</strong></th> <th><strong>管道</strong></th></tr></thead> <tbody><tr><td>Unconditional Image Generation</td> <td>从高斯噪声中生成图片</td> <td><a href="./using-diffusers/unconditional_image_generation">unconditional_image_generation</a></td></tr> <tr><td>Text-Guided Image Generation</td> <td>给定文本提示生成图像</td> <td><a href="./using-diffusers/conditional_image_generation">conditional_image_generation</a></td></tr> <tr><td>Text-Guided Image-to-Image Translation</td> <td>在文本提示的指导下调整图像</td> <td><a href="./using-diffusers/img2img">img2img</a></td></tr> <tr><td>Text-Guided Image-Inpainting</td> <td>给出图像、遮罩和文本提示，填充图像的遮罩部分</td> <td><a href="./using-diffusers/inpaint">inpaint</a></td></tr> <tr><td>Text-Guided Depth-to-Image Translation</td> <td>在文本提示的指导下调整图像的部分内容，同时通过深度估计保留其结构</td> <td><a href="./using-diffusers/depth2img">depth2img</a></td></tr></tbody></table> <p data-svelte-h="svelte-jd12jo">首先创建一个<code>DiffusionPipeline</code>的实例，并指定要下载的pipeline检查点。
	你可以使用存储在Hugging Face Hub上的任何<code>DiffusionPipeline</code><a href="https://huggingface.co/models?library=diffusers&sort=downloads" rel="nofollow">检查点</a>。
	在教程中，你将加载<a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow"><code>stable-diffusion-v1-5</code></a>检查点，用于文本到图像的生成。</p> <p data-svelte-h="svelte-1fmtl93">首先创建一个[DiffusionPipeline]实例，并指定要下载的管道检查点。
	您可以在Hugging Face Hub上使用[DiffusionPipeline]的任何检查点。
	在本快速入门中，您将加载stable-diffusion-v1-5检查点，用于文本到图像生成。</p> <blockquote class="warning" data-svelte-h="svelte-jvibq3"><p>。</p> <p>对于<a href="https://huggingface.co/CompVis/stable-diffusion" rel="nofollow">Stable Diffusion</a>模型，在运行该模型之前，请先仔细阅读<a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" rel="nofollow">许可证</a>。🧨 Diffusers实现了一个<a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py" rel="nofollow"><code>safety_checker</code></a>，以防止有攻击性的或有害的内容，但Stable Diffusion模型改进图像的生成能力仍有可能产生潜在的有害内容。</p></blockquote> <p data-svelte-h="svelte-ahj6oq">用<code>from_pretrained()</code>方法加载模型。</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

	<span class="hljs-meta">>>> </span>pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-v8l6xu"><code>DiffusionPipeline</code>会下载并缓存所有的建模、标记化和调度组件。你可以看到Stable Diffusion的pipeline是由<code>UNet2DConditionModel</code>和<code>PNDMScheduler</code>等组件组成的：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>pipeline
	StableDiffusionPipeline {
	<span class="hljs-string">"_class_name"</span>: <span class="hljs-string">"StableDiffusionPipeline"</span>,
	<span class="hljs-string">"_diffusers_version"</span>: <span class="hljs-string">"0.13.1"</span>,
	...,
	<span class="hljs-string">"scheduler"</span>: [
	<span class="hljs-string">"diffusers"</span>,
	<span class="hljs-string">"PNDMScheduler"</span>
	],
	...,
	<span class="hljs-string">"unet"</span>: [
	<span class="hljs-string">"diffusers"</span>,
	<span class="hljs-string">"UNet2DConditionModel"</span>
	],
	<span class="hljs-string">"vae"</span>: [
	<span class="hljs-string">"diffusers"</span>,
	<span class="hljs-string">"AutoencoderKL"</span>
	]
	}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-boqazn">我们强烈建议你在GPU上运行这个pipeline，因为该模型由大约14亿个参数组成。</p> <p data-svelte-h="svelte-c79z70">你可以像在Pytorch里那样把生成器对象移到GPU上：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>pipeline.to(<span class="hljs-string">"cuda"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-dap4va">现在你可以向<code>pipeline</code>传递一个文本提示来生成图像，然后获得去噪的图像。默认情况下，图像输出被放在一个<a href="https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class" rel="nofollow"><code>PIL.Image</code></a>对象中。</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>image = pipeline(<span class="hljs-string">"An image of a squirrel in Picasso style"</span>).images[<span class="hljs-number">0</span>]
	<span class="hljs-meta">>>> </span>image<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-6cjtp1"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/image_of_squirrel_painting.png"></div> <p data-svelte-h="svelte-l4v8b">调用<code>save</code>保存图像:</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>image.save(<span class="hljs-string">"image_of_squirrel_painting.png"</span>)<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="本地管道" 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="#本地管道"><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>本地管道</span></h3> <p data-svelte-h="svelte-mt9jjc">你也可以在本地使用管道。唯一的区别是你需提前下载权重：</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 class=""><!-- HTML_TAG_START -->git lfs install
	git clone https:<span class="hljs-regexp">//</span>huggingface.co<span class="hljs-regexp">/stable-diffusion-v1-5/</span>stable-diffusion-v1-<span class="hljs-number">5</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1i6uowx">将下载好的权重加载到管道中:</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">"./stable-diffusion-v1-5"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-q2xnew">现在你可以像上一节中那样运行管道了。</p> <h3 class="relative group"><a id="更换调度器" 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="#更换调度器"><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>更换调度器</span></h3> <p data-svelte-h="svelte-1cbwvt6">不同的调度器对去噪速度和质量的权衡是不同的。要想知道哪种调度器最适合你，最好的办法就是试用一下。🧨 Diffusers的主要特点之一是允许你轻松切换不同的调度器。例如，要用<code>EulerDiscreteScheduler</code>替换默认的<code>PNDMScheduler</code>，用<code>from_config()</code>方法加载即可：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> EulerDiscreteScheduler

	<span class="hljs-meta">>>> </span>pipeline = StableDiffusionPipeline.from_pretrained(<span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>)
	<span class="hljs-meta">>>> </span>pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ipe7mg">试着用新的调度器生成一个图像，看看你能否发现不同之处。</p> <p data-svelte-h="svelte-1bnbirw">在下一节中，你将仔细观察组成<code>DiffusionPipeline</code>的组件——模型和调度器，并学习如何使用这些组件来生成猫咪的图像。</p> <h2 class="relative group"><a id="模型" 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="#模型"><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>模型</span></h2> <p data-svelte-h="svelte-yv28ui">大多数模型取一个噪声样本，在每个时间点预测<em>噪声残差</em>（其他模型则直接学习预测前一个样本或速度或<a href="https://github.com/huggingface/diffusers/blob/5e5ce13e2f89ac45a0066cb3f369462a3cf1d9ef/src/diffusers/schedulers/scheduling_ddim.py#L110" rel="nofollow"><code>v-prediction</code></a>），即噪声较小的图像与输入图像的差异。你可以混搭模型创建其他扩散系统。</p> <p data-svelte-h="svelte-15d6qex">模型是用<code>from_pretrained()</code>方法启动的，该方法还在本地缓存了模型权重，所以下次加载模型时更快。对于快速入门，你默认加载的是<code>UNet2DModel</code>，这是一个基础的无条件图像生成模型，该模型有一个在猫咪图像上训练的检查点：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> UNet2DModel

	<span class="hljs-meta">>>> </span>repo_id = <span class="hljs-string">"google/ddpm-cat-256"</span>
	<span class="hljs-meta">>>> </span>model = UNet2DModel.from_pretrained(repo_id)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-abj9qe">想知道模型的参数，调用 <code>model.config</code>:</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>model.config<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-19gbp7r">模型配置是一个🧊冻结的🧊字典，意思是这些参数在模型创建后就不变了。这是特意设置的，确保在开始时用于定义模型架构的参数保持不变，其他参数仍然可以在推理过程中进行调整。</p> <p data-svelte-h="svelte-mr6snl">一些最重要的参数：</p> <ul data-svelte-h="svelte-1bmadu3"><li><code>sample_size</code>：输入样本的高度和宽度尺寸。</li> <li><code>in_channels</code>：输入样本的输入通道数。</li> <li><code>down_block_types</code>和<code>up_block_types</code>：用于创建U-Net架构的下采样和上采样块的类型。</li> <li><code>block_out_channels</code>：下采样块的输出通道数；也以相反的顺序用于上采样块的输入通道数。</li> <li><code>layers_per_block</code>：每个U-Net块中存在的ResNet块的数量。</li></ul> <p data-svelte-h="svelte-kl1n6d">为了使用该模型进行推理，用随机高斯噪声生成图像形状。它应该有一个<code>batch</code>轴，因为模型可以接收多个随机噪声，一个<code>channel</code>轴，对应于输入通道的数量，以及一个<code>sample_size</code>轴，对应图像的高度和宽度。</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch

	<span class="hljs-meta">>>> </span>torch.manual_seed(<span class="hljs-number">0</span>)

	<span class="hljs-meta">>>> </span>noisy_sample = torch.randn(<span class="hljs-number">1</span>, model.config.in_channels, model.config.sample_size, model.config.sample_size)
	<span class="hljs-meta">>>> </span>noisy_sample.shape
	torch.Size([<span class="hljs-number">1</span>, <span class="hljs-number">3</span>, <span class="hljs-number">256</span>, <span class="hljs-number">256</span>])<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-54yfeg">对于推理，将噪声图像和一个<code>timestep</code>传递给模型。<code>timestep</code> 表示输入图像的噪声程度，开始时噪声更多，结束时噪声更少。这有助于模型确定其在扩散过程中的位置，是更接近开始还是结束。使用 <code>sample</code> 获得模型输出：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">with</span> torch.no_grad():
	<span class="hljs-meta">... </span> noisy_residual = model(sample=noisy_sample, timestep=<span class="hljs-number">2</span>).sample<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1a1a7pz">想生成实际的样本，你需要一个调度器指导去噪过程。在下一节中，你将学习如何把模型与调度器结合起来。</p> <h2 class="relative group"><a id="调度器" 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="#调度器"><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>调度器</span></h2> <p data-svelte-h="svelte-79pc64">调度器管理一个噪声样本到一个噪声较小的样本的处理过程，给出模型输出 —— 在这种情况下，它是<code>noisy_residual</code>。</p> <blockquote class="tip" data-svelte-h="svelte-1e9wl6d"><p>🧨 Diffusers是一个用于构建扩散系统的工具箱。预定义好的扩散系统<code>DiffusionPipeline</code>能方便你快速试用，你也可以单独选择自己的模型和调度器组件来建立一个自定义的扩散系统。</p></blockquote> <p data-svelte-h="svelte-l4n2hw">在快速入门教程中，你将用它的<code>from_config()</code>方法实例化<code>DDPMScheduler</code>：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDPMScheduler

	<span class="hljs-meta">>>> </span>scheduler = DDPMScheduler.from_config(repo_id)
	<span class="hljs-meta">>>> </span>scheduler
	DDPMScheduler {
	<span class="hljs-string">"_class_name"</span>: <span class="hljs-string">"DDPMScheduler"</span>,
	<span class="hljs-string">"_diffusers_version"</span>: <span class="hljs-string">"0.13.1"</span>,
	<span class="hljs-string">"beta_end"</span>: <span class="hljs-number">0.02</span>,
	<span class="hljs-string">"beta_schedule"</span>: <span class="hljs-string">"linear"</span>,
	<span class="hljs-string">"beta_start"</span>: <span class="hljs-number">0.0001</span>,
	<span class="hljs-string">"clip_sample"</span>: true,
	<span class="hljs-string">"clip_sample_range"</span>: <span class="hljs-number">1.0</span>,
	<span class="hljs-string">"num_train_timesteps"</span>: <span class="hljs-number">1000</span>,
	<span class="hljs-string">"prediction_type"</span>: <span class="hljs-string">"epsilon"</span>,
	<span class="hljs-string">"trained_betas"</span>: null,
	<span class="hljs-string">"variance_type"</span>: <span class="hljs-string">"fixed_small"</span>
	}<!-- HTML_TAG_END --></pre></div> <blockquote class="tip" data-svelte-h="svelte-1vb1pte"><p>💡 注意调度器是如何从配置中实例化的。与模型不同，调度器没有可训练的权重，而且是无参数的。</p></blockquote> <ul data-svelte-h="svelte-1eztqv6"><li><code>num_train_timesteps</code>：去噪过程的长度，或者换句话说，将随机高斯噪声处理成数据样本所需的时间步数。</li> <li><code>beta_schedule</code>：用于推理和训练的噪声表。</li> <li><code>beta_start</code>和<code>beta_end</code>：噪声表的开始和结束噪声值。</li></ul> <p data-svelte-h="svelte-x6lwt8">要预测一个噪音稍小的图像，请将模型输出、<code>timestep</code>和当前<code>sample</code> 传递给调度器的<code>step()</code>方法：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>less_noisy_sample = scheduler.step(model_output=noisy_residual, timestep=<span class="hljs-number">2</span>, sample=noisy_sample).prev_sample
	<span class="hljs-meta">>>> </span>less_noisy_sample.shape<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-e5o0yl">这个 <code>less_noisy_sample</code> 去噪样本可以被传递到下一个<code>timestep</code> ，处理后会将变得噪声更小。现在让我们把所有步骤合起来，可视化整个去噪过程。</p> <p data-svelte-h="svelte-h02hkp">首先，创建一个函数，对去噪后的图像进行后处理并显示为<code>PIL.Image</code>：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> PIL.Image
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np


	<span class="hljs-meta">>>> </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">display_sample</span>(<span class="hljs-params">sample, i</span>):
	<span class="hljs-meta">... </span> image_processed = sample.cpu().permute(<span class="hljs-number">0</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>, <span class="hljs-number">1</span>)
	<span class="hljs-meta">... </span> image_processed = (image_processed + <span class="hljs-number">1.0</span>) * <span class="hljs-number">127.5</span>
	<span class="hljs-meta">... </span> image_processed = image_processed.numpy().astype(np.uint8)

	<span class="hljs-meta">... </span> image_pil = PIL.Image.fromarray(image_processed[<span class="hljs-number">0</span>])
	<span class="hljs-meta">... </span> display(<span class="hljs-string">f"Image at step <span class="hljs-subst">{i}</span>"</span>)
	<span class="hljs-meta">... </span> display(image_pil)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-25mu3n">将输入和模型移到GPU上加速去噪过程：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>model.to(<span class="hljs-string">"cuda"</span>)
	<span class="hljs-meta">>>> </span>noisy_sample = noisy_sample.to(<span class="hljs-string">"cuda"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1cml9g9">现在创建一个去噪循环，该循环预测噪声较少样本的残差，并使用调度程序计算噪声较少的样本：</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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> tqdm

	<span class="hljs-meta">>>> </span>sample = noisy_sample

	<span class="hljs-meta">>>> </span><span class="hljs-keyword">for</span> i, t <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(tqdm.tqdm(scheduler.timesteps)):
	<span class="hljs-meta">... </span> <span class="hljs-comment"># 1. predict noise residual</span>
	<span class="hljs-meta">... </span> <span class="hljs-keyword">with</span> torch.no_grad():
	<span class="hljs-meta">... </span> residual = model(sample, t).sample

	<span class="hljs-meta">... </span> <span class="hljs-comment"># 2. compute less noisy image and set x_t -> x_t-1</span>
	<span class="hljs-meta">... </span> sample = scheduler.step(residual, t, sample).prev_sample

	<span class="hljs-meta">... </span> <span class="hljs-comment"># 3. optionally look at image</span>
	<span class="hljs-meta">... </span> <span class="hljs-keyword">if</span> (i + <span class="hljs-number">1</span>) % <span class="hljs-number">50</span> == <span class="hljs-number">0</span>:
	<span class="hljs-meta">... </span> display_sample(sample, i + <span class="hljs-number">1</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-844bxv">看！这样就从噪声中生成出一只猫了！😻</p> <div class="flex justify-center" data-svelte-h="svelte-1yzsrw6"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/diffusion-quicktour.png"></div> <h2 class="relative group"><a id="下一步" 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="#下一步"><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>下一步</span></h2> <p data-svelte-h="svelte-4d94hq">希望你在这次快速入门教程中用🧨Diffuser 生成了一些很酷的图像! 下一步你可以:</p> <ul data-svelte-h="svelte-g8q2e0"><li>在<a href="./tutorials/basic_training">训练</a>教程中训练或微调一个模型来生成你自己的图像。</li> <li>查看官方和社区的<a href="https://github.com/huggingface/diffusers/tree/main/examples#-diffusers-examples" rel="nofollow">训练或微调脚本</a>的例子，了解更多使用情况。</li> <li>在<a href="./using-diffusers/schedulers">使用不同的调度器</a>指南中了解更多关于加载、访问、更改和比较调度器的信息。</li> <li>在<a href="./stable_diffusion">Stable Diffusion</a>教程中探索提示工程、速度和内存优化，以及生成更高质量图像的技巧。</li> <li>通过<a href="./optimization/fp16">在GPU上优化PyTorch</a>指南，以及运行<a href="./optimization/mps">Apple (M1/M2)上的Stable Diffusion</a>和<a href="./optimization/onnx">ONNX Runtime</a>的教程，更深入地了解如何加速🧨Diffuser。</li></ul> <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/zh/quicktour.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 data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_oaf0l2 = {
	assets: "/docs/diffusers/pr_12652/zh",
	base: "/docs/diffusers/pr_12652/zh",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/diffusers/pr_12652/zh/_app/immutable/entry/start.ca7a833f.js"),
	import("/docs/diffusers/pr_12652/zh/_app/immutable/entry/app.746b83f3.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 39],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 59.5 kB
Xet hash:: 0eddb9374a6d2bf0a9edc69b48085de22b5c8e0d10a7a043d108d548f005006f

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.