Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Apple Silicon (M1/M2)에서 Stable Diffusion을 사용하는 방법","local":"apple-silicon-m1m2에서-stable-diffusion을-사용하는-방법","sections":[{"title":"요구 사항","local":"요구-사항","sections":[],"depth":2},{"title":"추론 파이프라인","local":"추론-파이프라인","sections":[],"depth":2},{"title":"성능 추천","local":"성능-추천","sections":[],"depth":2},{"title":"Known Issues","local":"known-issues","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/diffusers/pr_10101/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/entry/start.1e8d474d.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/scheduler.94020406.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/singletons.8a3250a7.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/index.8b553f6b.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/paths.df81b2db.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/entry/app.af542977.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/index.a08c8d92.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/nodes/0.170498a3.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/nodes/13.d2d0b6c7.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/Tip.3b0aeee8.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/CodeBlock.b23cf525.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_10101/ko/_app/immutable/chunks/EditOnGithub.b1bceb47.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Apple Silicon (M1/M2)에서 Stable Diffusion을 사용하는 방법","local":"apple-silicon-m1m2에서-stable-diffusion을-사용하는-방법","sections":[{"title":"요구 사항","local":"요구-사항","sections":[],"depth":2},{"title":"추론 파이프라인","local":"추론-파이프라인","sections":[],"depth":2},{"title":"성능 추천","local":"성능-추천","sections":[],"depth":2},{"title":"Known Issues","local":"known-issues","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="apple-silicon-m1m2에서-stable-diffusion을-사용하는-방법" 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="#apple-silicon-m1m2에서-stable-diffusion을-사용하는-방법"><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>Apple Silicon (M1/M2)에서 Stable Diffusion을 사용하는 방법</span></h1> <p data-svelte-h="svelte-1cmhw56">Diffusers는 Stable Diffusion 추론을 위해 PyTorch <code>mps</code>를 사용해 Apple 실리콘과 호환됩니다. 다음은 Stable Diffusion이 있는 M1 또는 M2 컴퓨터를 사용하기 위해 따라야 하는 단계입니다.</p> <h2 class="relative group"><a id="요구-사항" 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="#요구-사항"><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>요구 사항</span></h2> <ul data-svelte-h="svelte-xmgm9h"><li>Apple silicon (M1/M2) 하드웨어의 Mac 컴퓨터.</li> <li>macOS 12.6 또는 이후 (13.0 또는 이후 추천).</li> <li>Python arm64 버전</li> <li>PyTorch 2.0(추천) 또는 1.13(<code>mps</code>를 지원하는 최소 버전). Y<a href="https://pytorch.org/get-started/locally/%EC%9D%98" rel="nofollow">https://pytorch.org/get-started/locally/의</a> 지침에 따라 <code>pip</code> 또는 <code>conda</code>로 설치할 수 있습니다.</li></ul> <h2 class="relative group"><a id="추론-파이프라인" 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="#추론-파이프라인"><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>추론 파이프라인</span></h2> <p data-svelte-h="svelte-26dp8q">아래 코도는 익숙한 <code>to()</code> 인터페이스를 사용하여 <code>mps</code> 백엔드로 Stable Diffusion 파이프라인을 M1 또는 M2 장치로 이동하는 방법을 보여줍니다.</p> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-1uj24v1"><strong>PyTorch 1.13을 사용 중일 때</strong> 추가 일회성 전달을 사용하여 파이프라인을 “프라이밍”하는 것을 추천합니다. 이것은 발견한 이상한 문제에 대한 임시 해결 방법입니다. 첫 번째 추론 전달은 후속 전달와 약간 다른 결과를 생성합니다. 이 전달은 한 번만 수행하면 되며 추론 단계를 한 번만 사용하고 결과를 폐기해도 됩니다.</p></div> <p data-svelte-h="svelte-d7ffo5">이전 팁에서 설명한 것들을 포함한 여러 문제를 해결하므로 PyTorch 2 이상을 사용하는 것이 좋습니다.</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-comment"># `huggingface-cli login`에 로그인되어 있음을 확인</span> | |
| <span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline | |
| pipe = DiffusionPipeline.from_pretrained(<span class="hljs-string">"stable-diffusion-v1-5/stable-diffusion-v1-5"</span>) | |
| pipe = pipe.to(<span class="hljs-string">"mps"</span>) | |
| <span class="hljs-comment"># 컴퓨터가 64GB 이하의 RAM 램일 때 추천</span> | |
| pipe.enable_attention_slicing() | |
| prompt = <span class="hljs-string">"a photo of an astronaut riding a horse on mars"</span> | |
| <span class="hljs-comment"># 처음 "워밍업" 전달 (위 설명을 보세요)</span> | |
| _ = pipe(prompt, num_inference_steps=<span class="hljs-number">1</span>) | |
| <span class="hljs-comment"># 결과는 워밍업 전달 후의 CPU 장치의 결과와 일치합니다.</span> | |
| image = pipe(prompt).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="성능-추천" 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="#성능-추천"><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>성능 추천</span></h2> <p data-svelte-h="svelte-1rzz618">M1/M2 성능은 메모리 압력에 매우 민감합니다. 시스템은 필요한 경우 자동으로 스왑되지만 스왑할 때 성능이 크게 저하됩니다.</p> <p data-svelte-h="svelte-1bz9ahf">특히 컴퓨터의 시스템 RAM이 64GB 미만이거나 512 × 512픽셀보다 큰 비표준 해상도에서 이미지를 생성하는 경우, 추론 중에 메모리 압력을 줄이고 스와핑을 방지하기 위해 <em>어텐션 슬라이싱</em>을 사용하는 것이 좋습니다. 어텐션 슬라이싱은 비용이 많이 드는 어텐션 작업을 한 번에 모두 수행하는 대신 여러 단계로 수행합니다. 일반적으로 범용 메모리가 없는 컴퓨터에서 ~20%의 성능 영향을 미치지만 64GB 이상이 아닌 경우 대부분의 Apple Silicon 컴퓨터에서 <em>더 나은 성능</em>이 관찰되었습니다.</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 -->pipeline.enable_attention_slicing()<!-- 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 data-svelte-h="svelte-1uyieu0"><li>여러 프롬프트를 배치로 생성하는 것은 <a href="https://github.com/huggingface/diffusers/issues/363" rel="nofollow">충돌이 발생하거나 안정적으로 작동하지 않습니다</a>. 우리는 이것이 <a href="https://github.com/pytorch/pytorch/issues/84039" rel="nofollow">PyTorch의 <code>mps</code> 백엔드</a>와 관련이 있다고 생각합니다. 이 문제는 해결되고 있지만 지금은 배치 대신 반복 방법을 사용하는 것이 좋습니다.</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/ko/optimization/mps.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_1qk4174 = { | |
| assets: "/docs/diffusers/pr_10101/ko", | |
| base: "/docs/diffusers/pr_10101/ko", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/pr_10101/ko/_app/immutable/entry/start.1e8d474d.js"), | |
| import("/docs/diffusers/pr_10101/ko/_app/immutable/entry/app.af542977.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 13], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 16.5 kB
- Xet hash:
- 2e836a46f54d803da36efacf94dcf15996544ce6b73e14fa2aa2dbdca7b0268e
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.