Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / diffusers /pr_12262 /zh /hybrid_inference /overview.html

rtrm

about 1 month ago

download

raw

13 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"混合推理","local":"混合推理","sections":[{"title":"为什么使用混合推理？","local":"为什么使用混合推理","sections":[],"depth":2},{"title":"可用模型","local":"可用模型","sections":[],"depth":2},{"title":"集成","local":"集成","sections":[],"depth":2},{"title":"更新日志","local":"更新日志","sections":[],"depth":2},{"title":"内容","local":"内容","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/diffusers/pr_12262/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/entry/start.51af38bc.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/scheduler.5c93273d.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/singletons.2f6324e8.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/index.6d7dc09e.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/paths.5bf4289e.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/entry/app.9a9887bb.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/index.e43dd92b.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/nodes/0.8f6c298a.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/nodes/8.08677044.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/Tip.1cbfe904.js">
	<link rel="modulepreload" href="/docs/diffusers/pr_12262/zh/_app/immutable/chunks/getInferenceSnippets.7d64e4c6.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"混合推理","local":"混合推理","sections":[{"title":"为什么使用混合推理？","local":"为什么使用混合推理","sections":[],"depth":2},{"title":"可用模型","local":"可用模型","sections":[],"depth":2},{"title":"集成","local":"集成","sections":[],"depth":2},{"title":"更新日志","local":"更新日志","sections":[],"depth":2},{"title":"内容","local":"内容","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="混合推理" 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="#混合推理"><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>混合推理</span></h1> <p data-svelte-h="svelte-1qp520s"><strong>通过混合推理赋能本地 AI 构建者</strong></p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-shhai2">混合推理是一项<a href="https://huggingface.co/blog/remote_vae" rel="nofollow">实验性功能</a>。
	可以在此处提供反馈<a href="https://github.com/huggingface/diffusers/issues/new?template=remote-vae-pilot-feedback.yml" rel="nofollow">此处</a>。</p></div> <h2 class="relative group"><a id="为什么使用混合推理" 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="#为什么使用混合推理"><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>为什么使用混合推理？</span></h2> <p data-svelte-h="svelte-pie3xf">混合推理提供了一种快速简单的方式来卸载本地生成需求。</p> <ul data-svelte-h="svelte-1icnlgm"><li>🚀 <strong>降低要求：</strong> 无需昂贵硬件即可访问强大模型。</li> <li>💎 <strong>无妥协：</strong> 在不牺牲性能的情况下实现最高质量。</li> <li>💰 <strong>成本效益高：</strong> 它是免费的！🤑</li> <li>🎯 <strong>多样化用例：</strong> 与 Diffusers � 和更广泛的社区完全兼容。</li> <li>🔧 <strong>开发者友好：</strong> 简单请求，快速响应。</li></ul> <hr> <h2 class="relative group"><a id="可用模型" 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="#可用模型"><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>可用模型</span></h2> <ul data-svelte-h="svelte-dmne87"><li><strong>VAE 解码 🖼️：</strong> 快速将潜在表示解码为高质量图像，不影响性能或工作流速度。</li> <li><strong>VAE 编码 🔢：</strong> 高效将图像编码为潜在表示，用于生成和训练。</li> <li><strong>文本编码器 📃（即将推出）：</strong> 快速准确地计算提示的文本嵌入，确保流畅高质量的工作流。</li></ul> <hr> <h2 class="relative group"><a id="集成" 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="#集成"><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>集成</span></h2> <ul data-svelte-h="svelte-n12d76"><li><strong><a href="https://github.com/vladmandic/sdnext" rel="nofollow">SD.Next</a>：</strong> 一体化 UI，直接支持混合推理。</li> <li><strong><a href="https://github.com/kijai/ComfyUI-HFRemoteVae" rel="nofollow">ComfyUI-HFRemoteVae</a>：</strong> 用于混合推理的 ComfyUI 节点。</li></ul> <h2 class="relative group"><a id="更新日志" 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="#更新日志"><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>更新日志</span></h2> <ul data-svelte-h="svelte-5ojv2r"><li>2025 年 3 月 10 日：添加了 VAE 编码</li> <li>2025 年 3 月 2 日：初始发布，包含 VAE 解码</li></ul> <h2 class="relative group"><a id="内容" 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="#内容"><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>内容</span></h2> <p data-svelte-h="svelte-7wavoz">文档分为三个部分：</p> <ul data-svelte-h="svelte-2isdzp"><li><strong>VAE 解码</strong> 学习如何使用混合推理进行 VAE 解码的基础知识。</li> <li><strong>VAE 编码</strong> 学习如何使用混合推理进行 VAE 编码的基础知识。</li> <li><strong>API 参考</strong> 深入了解任务特定设置和参数。</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/hybrid_inference/overview.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_179ljof = {
	assets: "/docs/diffusers/pr_12262/zh",
	base: "/docs/diffusers/pr_12262/zh",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/diffusers/pr_12262/zh/_app/immutable/entry/start.51af38bc.js"),
	import("/docs/diffusers/pr_12262/zh/_app/immutable/entry/app.9a9887bb.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 8],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 13 kB
Xet hash:: daab7437bcd994359cabf8eba0396a82ae22f9428cacf108f3da2bff517cf5e7

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