diffusers/v0.6.0/en/optimization/mps.html

<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;how-to-use-stable-diffusion-in-apple-silicon-m1m2&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;requirements&quot;,&quot;title&quot;:&quot;Requirements&quot;},{&quot;local&quot;:&quot;inference-pipeline&quot;,&quot;title&quot;:&quot;Inference Pipeline&quot;},{&quot;local&quot;:&quot;known-issues&quot;,&quot;title&quot;:&quot;Known Issues&quot;},{&quot;local&quot;:&quot;performance&quot;,&quot;title&quot;:&quot;Performance&quot;}],&quot;title&quot;:&quot;How to use Stable Diffusion in Apple Silicon (M1/M2)&quot;}" data-svelte="svelte-1phssyn">
	<link rel="modulepreload" href="/docs/diffusers/v0.6.0/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
	<link rel="modulepreload" href="/docs/diffusers/v0.6.0/en/_app/start-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.6.0/en/_app/chunks/vendor-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.6.0/en/_app/chunks/paths-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.6.0/en/_app/pages/__layout.svelte-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.6.0/en/_app/pages/optimization/mps.mdx-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.6.0/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.6.0/en/_app/chunks/CodeBlock-hf-doc-builder.js"> 






<h1 class="relative group"><a id="how-to-use-stable-diffusion-in-apple-silicon-m1m2" 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="#how-to-use-stable-diffusion-in-apple-silicon-m1m2"><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>How to use Stable Diffusion in Apple Silicon (M1/M2)
	</span></h1>

<p>🤗 Diffusers is compatible with Apple silicon for Stable Diffusion inference, using the PyTorch <code>mps</code> device. These are the steps you need to follow to use your M1 or M2 computer with Stable Diffusion.</p>
<h2 class="relative group"><a id="requirements" 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="#requirements"><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>Requirements
	</span></h2>

<ul><li>Mac computer with Apple silicon (M1/M2) hardware.</li>
<li>macOS 12.3 or later.</li>
<li>arm64 version of Python.</li>
<li>PyTorch <a href="https://pytorch.org/get-started/locally/" rel="nofollow">Preview (Nightly)</a>, version <code>1.14.0.dev20221007</code> or later.</li></ul>
<h2 class="relative group"><a id="inference-pipeline" 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="#inference-pipeline"><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>Inference Pipeline
	</span></h2>

<p>The snippet below demonstrates how to use the <code>mps</code> backend using the familiar <code>to()</code> interface to move the Stable Diffusion pipeline to your M1 or M2 device.</p>
<p>We recommend to “prime” the pipeline using an additional one-time pass through it. This is a temporary workaround for a weird issue we have detected: the first inference pass produces slightly different results than subsequent ones. You only need to do this pass once, and it’s ok to use just one inference step and discard the result.</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-comment"># make sure you&#x27;re logged in with `huggingface-cli login`</span>
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;CompVis/stable-diffusion-v1-4&quot;</span>)
pipe = pipe.to(<span class="hljs-string">&quot;mps&quot;</span>)

prompt = <span class="hljs-string">&quot;a photo of an astronaut riding a horse on mars&quot;</span>

<span class="hljs-comment"># First-time &quot;warmup&quot; pass (see explanation above)</span>
_ = pipe(prompt, num_inference_steps=<span class="hljs-number">1</span>)

<span class="hljs-comment"># Results match those from the CPU device after the warmup pass.</span>
image = pipe(prompt).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div>
<h2 class="relative group"><a id="known-issues" 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="#known-issues"><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>Known Issues
	</span></h2>

<ul><li>As mentioned above, we are investigating a strange <a href="https://github.com/huggingface/diffusers/issues/372" rel="nofollow">first-time inference issue</a>.</li>
<li>Generating multiple prompts in a batch <a href="https://github.com/huggingface/diffusers/issues/363" rel="nofollow">crashes or doesn’t work reliably</a>. We believe this might be related to the <a href="https://github.com/pytorch/pytorch/issues/84039#issuecomment-1237735249" rel="nofollow"><code>mps</code> backend in PyTorch</a>, but we need to investigate in more depth. For now, we recommend to iterate instead of batching.</li></ul>
<h2 class="relative group"><a id="performance" 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="#performance"><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>Performance
	</span></h2>

<p>These are the results we got on a M1 Max MacBook Pro with 64 GB of RAM, running macOS Ventura Version 13.0 Beta (22A5331f). We performed Stable Diffusion text-to-image generation of the same prompt for 50 inference steps, using a guidance scale of 7.5.</p>
<table><thead><tr><th>Device</th>
<th>Steps</th>
<th>Time</th></tr></thead>
<tbody><tr><td>CPU</td>
<td>50</td>
<td>213.46s</td></tr>
<tr><td>MPS</td>
<td>50</td>
<td>30.81s</td></tr></tbody></table>


		<script type="module" data-hydrate="rqiyck">
		import { start } from "/docs/diffusers/v0.6.0/en/_app/start-hf-doc-builder.js";
		start({
			target: document.querySelector('[data-hydrate="rqiyck"]').parentNode,
			paths: {"base":"/docs/diffusers/v0.6.0/en","assets":"/docs/diffusers/v0.6.0/en"},
			session: {},
			route: false,
			spa: false,
			trailing_slash: "never",
			hydrate: {
				status: 200,
				error: null,
				nodes: [
					import("/docs/diffusers/v0.6.0/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
						import("/docs/diffusers/v0.6.0/en/_app/pages/optimization/mps.mdx-hf-doc-builder.js")
				],
				params: {}
			}
		});
	</script>