Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Core ML로 Stable Diffusion을 실행하는 방법","local":"core-ml로-stable-diffusion을-실행하는-방법","sections":[{"title":"Stable Diffusion Core ML 체크포인트","local":"stable-diffusion-core-ml-체크포인트","sections":[],"depth":2},{"title":"사용할 Core ML 변형(Variant) 선택하기","local":"사용할-core-ml-변형variant-선택하기","sections":[],"depth":2},{"title":"Python에서 Core ML 추론","local":"python에서-core-ml-추론","sections":[{"title":"모델 체크포인트 다운로드하기","local":"모델-체크포인트-다운로드하기","sections":[],"depth":3},{"title":"추론","local":"python-inference","sections":[],"depth":3}],"depth":2},{"title":"Swift에서 Core ML 추론하기","local":"swift에서-core-ml-추론하기","sections":[{"title":"다운로드","local":"다운로드","sections":[],"depth":3},{"title":"추론","local":"swift-inference","sections":[],"depth":3}],"depth":2},{"title":"지원되는 Diffusers 기능","local":"지원되는-diffusers-기능","sections":[],"depth":2},{"title":"네이티브 Diffusers Swift 앱","local":"네이티브-diffusers-swift-앱","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/10.c17397a5.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":"Core ML로 Stable Diffusion을 실행하는 방법","local":"core-ml로-stable-diffusion을-실행하는-방법","sections":[{"title":"Stable Diffusion Core ML 체크포인트","local":"stable-diffusion-core-ml-체크포인트","sections":[],"depth":2},{"title":"사용할 Core ML 변형(Variant) 선택하기","local":"사용할-core-ml-변형variant-선택하기","sections":[],"depth":2},{"title":"Python에서 Core ML 추론","local":"python에서-core-ml-추론","sections":[{"title":"모델 체크포인트 다운로드하기","local":"모델-체크포인트-다운로드하기","sections":[],"depth":3},{"title":"추론","local":"python-inference","sections":[],"depth":3}],"depth":2},{"title":"Swift에서 Core ML 추론하기","local":"swift에서-core-ml-추론하기","sections":[{"title":"다운로드","local":"다운로드","sections":[],"depth":3},{"title":"추론","local":"swift-inference","sections":[],"depth":3}],"depth":2},{"title":"지원되는 Diffusers 기능","local":"지원되는-diffusers-기능","sections":[],"depth":2},{"title":"네이티브 Diffusers Swift 앱","local":"네이티브-diffusers-swift-앱","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="core-ml로-stable-diffusion을-실행하는-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="#core-ml로-stable-diffusion을-실행하는-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>Core ML로 Stable Diffusion을 실행하는 방법</span></h1> <p data-svelte-h="svelte-bbaeul"><a href="https://developer.apple.com/documentation/coreml" rel="nofollow">Core ML</a>은 Apple 프레임워크에서 지원하는 모델 형식 및 머신 러닝 라이브러리입니다. macOS 또는 iOS/iPadOS 앱 내에서 Stable Diffusion 모델을 실행하는 데 관심이 있는 경우, 이 가이드에서는 기존 PyTorch 체크포인트를 Core ML 형식으로 변환하고 이를 Python 또는 Swift로 추론에 사용하는 방법을 설명합니다.</p> <p data-svelte-h="svelte-25bb3r">Core ML 모델은 Apple 기기에서 사용할 수 있는 모든 컴퓨팅 엔진들, 즉 CPU, GPU, Apple Neural Engine(또는 Apple Silicon Mac 및 최신 iPhone/iPad에서 사용할 수 있는 텐서 최적화 가속기인 ANE)을 활용할 수 있습니다. 모델과 실행 중인 기기에 따라 Core ML은 컴퓨팅 엔진도 혼합하여 사용할 수 있으므로, 예를 들어 모델의 일부가 CPU에서 실행되는 반면 다른 부분은 GPU에서 실행될 수 있습니다.</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-2gy5p">PyTorch에 내장된 <code>mps</code> 가속기를 사용하여 Apple Silicon Macs에서 <code>diffusers</code> Python 코드베이스를 실행할 수도 있습니다. 이 방법은 [mps 가이드]에 자세히 설명되어 있지만 네이티브 앱과 호환되지 않습니다.</p></div> <h2 class="relative group"><a id="stable-diffusion-core-ml-체크포인트" 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="#stable-diffusion-core-ml-체크포인트"><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>Stable Diffusion Core ML 체크포인트</span></h2> <p data-svelte-h="svelte-1n0wpaz">Stable Diffusion 가중치(또는 체크포인트)는 PyTorch 형식으로 저장되기 때문에 네이티브 앱에서 사용하기 위해서는 Core ML 형식으로 변환해야 합니다.</p> <p data-svelte-h="svelte-11ljk8w">다행히도 Apple 엔지니어들이 <code>diffusers</code>를 기반으로 한 <a href="https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml" rel="nofollow">변환 툴</a>을 개발하여 PyTorch 체크포인트를 Core ML로 변환할 수 있습니다.</p> <p data-svelte-h="svelte-1635zp">모델을 변환하기 전에 잠시 시간을 내어 Hugging Face Hub를 살펴보세요. 관심 있는 모델이 이미 Core ML 형식으로 제공되고 있을 가능성이 높습니다:</p> <ul data-svelte-h="svelte-q784xv"><li><a href="https://huggingface.co/apple" rel="nofollow">Apple</a> organization에는 Stable Diffusion 버전 1.4, 1.5, 2.0 base 및 2.1 base가 포함되어 있습니다.</li> <li><a href="https://huggingface.co/coreml" rel="nofollow">coreml</a> organization에는 커스텀 DreamBooth가 적용되거나, 파인튜닝된 모델이 포함되어 있습니다.</li> <li>이 <a href="https://huggingface.co/models?pipeline_tag=text-to-image&library=coreml&p=2&sort=likes" rel="nofollow">필터</a>를 사용하여 사용 가능한 모든 Core ML 체크포인트들을 반환합니다.</li></ul> <p data-svelte-h="svelte-b7xjel">원하는 모델을 찾을 수 없는 경우 Apple의 <a href="https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml" rel="nofollow">모델을 Core ML로 변환하기</a> 지침을 따르는 것이 좋습니다.</p> <h2 class="relative group"><a id="사용할-core-ml-변형variant-선택하기" 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="#사용할-core-ml-변형variant-선택하기"><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>사용할 Core ML 변형(Variant) 선택하기</span></h2> <p data-svelte-h="svelte-1t091it">Stable Diffusion 모델은 다양한 목적에 따라 다른 Core ML 변형으로 변환할 수 있습니다:</p> <ul data-svelte-h="svelte-1rrqib3"><li><p>사용되는 어텐션 블록 유형. 어텐션 연산은 이미지 표현의 여러 영역 간의 관계에 ‘주의를 기울이고’ 이미지와 텍스트 표현이 어떻게 연관되어 있는지 이해하는 데 사용됩니다. 어텐션 연산은 컴퓨팅 및 메모리 집약적이므로 다양한 장치의 하드웨어 특성을 고려한 다양한 구현이 존재합니다. Core ML Stable Diffusion 모델의 경우 두 가지 주의 변형이 있습니다:</p> <ul><li><code>split_einsum</code> (<a href="https://machinelearning.apple.com/research/neural-engine-transformers" rel="nofollow">Apple에서 도입</a>은 최신 iPhone, iPad 및 M 시리즈 컴퓨터에서 사용할 수 있는 ANE 장치에 최적화되어 있습니다.</li> <li>“원본” 어텐션(<code>diffusers</code>에 사용되는 기본 구현)는 CPU/GPU와만 호환되며 ANE와는 호환되지 않습니다. “원본” 어텐션을 사용하여 CPU + GPU에서 모델을 실행하는 것이 ANE보다 <em>더</em> 빠를 수 있습니다. 자세한 내용은 <a href="https://huggingface.co/blog/fast-mac-diffusers#performance-benchmarks" rel="nofollow">이 성능 벤치마크</a>와 커뮤니티에서 제공하는 일부 <a href="https://github.com/huggingface/swift-coreml-diffusers/issues/31" rel="nofollow">추가 측정</a>을 참조하십시오.</li></ul></li> <li><p>지원되는 추론 프레임워크</p> <ul><li><code>packages</code>는 Python 추론에 적합합니다. 네이티브 앱에 통합하기 전에 변환된 Core ML 모델을 테스트하거나, Core ML 성능을 알고 싶지만 네이티브 앱을 지원할 필요는 없는 경우에 사용할 수 있습니다. 예를 들어, 웹 UI가 있는 애플리케이션은 Python Core ML 백엔드를 완벽하게 사용할 수 있습니다.</li> <li>Swift 코드에는 <code>컴파일된</code> 모델이 필요합니다. Hub의 <code>컴파일된</code> 모델은 iOS 및 iPadOS 기기와의 호환성을 위해 큰 UNet 모델 가중치를 여러 파일로 분할합니다. 이는 <a href="https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml" rel="nofollow"><code>--chunk-unet</code> 변환 옵션</a>에 해당합니다. 네이티브 앱을 지원하려면 <code>컴파일된</code> 변형을 선택해야 합니다.</li></ul></li></ul> <p data-svelte-h="svelte-1itv6a4">공식 Core ML Stable Diffusion <a href="https://huggingface.co/apple/coreml-stable-diffusion-v1-4/tree/main" rel="nofollow">모델</a>에는 이러한 변형이 포함되어 있지만 커뮤니티 버전은 다를 수 있습니다:</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 -->coreml-stable-<span class="hljs-keyword">diffusion-v1-4 | |
| </span>├── README.md | |
| ├── <span class="hljs-keyword">original | |
| </span>│ ├── compiled | |
| │ └── packages | |
| └── split_einsum | |
| ├── compiled | |
| └── packages<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1pm7gvi">아래와 같이 필요한 변형을 다운로드하여 사용할 수 있습니다.</p> <h2 class="relative group"><a id="python에서-core-ml-추론" 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="#python에서-core-ml-추론"><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>Python에서 Core ML 추론</span></h2> <p data-svelte-h="svelte-106wisv">Python에서 Core ML 추론을 실행하려면 다음 라이브러리를 설치하세요:</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 huggingface_hub | |
| pip install git+https://github.com/apple/ml-stable-diffusion<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="모델-체크포인트-다운로드하기" 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="#모델-체크포인트-다운로드하기"><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>모델 체크포인트 다운로드하기</span></h3> <p data-svelte-h="svelte-18035od"><code>컴파일된</code> 버전은 Swift와만 호환되므로 Python에서 추론을 실행하려면 <code>packages</code> 폴더에 저장된 버전 중 하나를 사용하세요. <code>원본</code> 또는 <code>split_einsum</code> 어텐션 중 어느 것을 사용할지 선택할 수 있습니다.</p> <p data-svelte-h="svelte-1li68th">다음은 Hub에서 ‘models’라는 디렉토리로 ‘original’ 어텐션 변형을 다운로드하는 방법입니다:</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-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> snapshot_download | |
| <span class="hljs-keyword">from</span> pathlib <span class="hljs-keyword">import</span> Path | |
| repo_id = <span class="hljs-string">"apple/coreml-stable-diffusion-v1-4"</span> | |
| variant = <span class="hljs-string">"original/packages"</span> | |
| model_path = Path(<span class="hljs-string">"./models"</span>) / (repo_id.split(<span class="hljs-string">"/"</span>)[-<span class="hljs-number">1</span>] + <span class="hljs-string">"_"</span> + variant.replace(<span class="hljs-string">"/"</span>, <span class="hljs-string">"_"</span>)) | |
| snapshot_download(repo_id, allow_patterns=<span class="hljs-string">f"<span class="hljs-subst">{variant}</span>/*"</span>, local_dir=model_path, local_dir_use_symlinks=<span class="hljs-literal">False</span>) | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">f"Model downloaded at <span class="hljs-subst">{model_path}</span>"</span>)<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="python-inference" 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="#python-inference"><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</span></h3> <p data-svelte-h="svelte-18ld88r">모델의 snapshot을 다운로드한 후에는 Apple의 Python 스크립트를 사용하여 테스트할 수 있습니다.</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 -->python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" -i models/coreml-stable-diffusion-v1-4_original_packages -o </path/to/output/image> --compute-unit CPU_AND_GPU --seed 93<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-mpzt9a"><code><output-mlpackages-directory></code>는 위 단계에서 다운로드한 체크포인트를 가리켜야 하며, <code>--compute-unit</code>은 추론을 허용할 하드웨어를 나타냅니다. 이는 다음 옵션 중 하나이어야 합니다: <code>ALL</code>, <code>CPU_AND_GPU</code>, <code>CPU_ONLY</code>, <code>CPU_AND_NE</code>. 선택적 출력 경로와 재현성을 위한 시드를 제공할 수도 있습니다.</p> <p data-svelte-h="svelte-lf923q">추론 스크립트에서는 Stable Diffusion 모델의 원래 버전인 <code>CompVis/stable-diffusion-v1-4</code>를 사용한다고 가정합니다. 다른 모델을 사용하는 경우 추론 명령줄에서 <code>--model-version</code> 옵션을 사용하여 해당 허브 ID를 <em>지정</em>해야 합니다. 이는 이미 지원되는 모델과 사용자가 직접 학습하거나 파인튜닝한 사용자 지정 모델에 적용됩니다.</p> <p data-svelte-h="svelte-1rdfmyj">예를 들어, <a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow"><code>stable-diffusion-v1-5/stable-diffusion-v1-5</code></a>를 사용하려는 경우입니다:</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 -->python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" --compute-unit ALL -o output --seed 93 -i models/coreml-stable-diffusion-v1-5_original_packages --model-version stable-diffusion-v1-5/stable-diffusion-v1-5<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="swift에서-core-ml-추론하기" 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="#swift에서-core-ml-추론하기"><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>Swift에서 Core ML 추론하기</span></h2> <p data-svelte-h="svelte-ker45t">Swift에서 추론을 실행하는 것은 모델이 이미 <code>mlmodelc</code> 형식으로 컴파일되어 있기 때문에 Python보다 약간 빠릅니다. 이는 앱이 시작될 때 모델이 불러와지는 것이 눈에 띄지만, 이후 여러 번 실행하면 눈에 띄지 않을 것입니다.</p> <h3 class="relative group"><a id="다운로드" 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="#다운로드"><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>다운로드</span></h3> <p data-svelte-h="svelte-3a5qkr">Mac에서 Swift에서 추론을 실행하려면 <code>컴파일된</code> 체크포인트 버전 중 하나가 필요합니다. 이전 예제와 유사하지만 <code>컴파일된</code> 변형 중 하나를 사용하여 Python 코드를 로컬로 다운로드하는 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-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> snapshot_download | |
| <span class="hljs-keyword">from</span> pathlib <span class="hljs-keyword">import</span> Path | |
| repo_id = <span class="hljs-string">"apple/coreml-stable-diffusion-v1-4"</span> | |
| variant = <span class="hljs-string">"original/compiled"</span> | |
| model_path = Path(<span class="hljs-string">"./models"</span>) / (repo_id.split(<span class="hljs-string">"/"</span>)[-<span class="hljs-number">1</span>] + <span class="hljs-string">"_"</span> + variant.replace(<span class="hljs-string">"/"</span>, <span class="hljs-string">"_"</span>)) | |
| snapshot_download(repo_id, allow_patterns=<span class="hljs-string">f"<span class="hljs-subst">{variant}</span>/*"</span>, local_dir=model_path, local_dir_use_symlinks=<span class="hljs-literal">False</span>) | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">f"Model downloaded at <span class="hljs-subst">{model_path}</span>"</span>)<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="swift-inference" 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="#swift-inference"><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</span></h3> <p data-svelte-h="svelte-2e0s68">추론을 실행하기 위해서, Apple의 리포지토리를 복제하세요:</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 <span class="hljs-built_in">clone</span> https://github.com/apple/ml-stable-diffusion | |
| <span class="hljs-built_in">cd</span> ml-stable-diffusion<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1hqru1i">그 다음 Apple의 명령어 도구인 <a href="https://www.swift.org/package-manager/#" rel="nofollow">Swift 패키지 관리자</a>를 사용합니다:</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 -->swift run StableDiffusionSample --resource-path models/coreml-stable-diffusion-v1-4_original_compiled --compute-units all <span class="hljs-string">"a photo of an astronaut riding a horse on mars"</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1rrvko7"><code>--resource-path</code>에 이전 단계에서 다운로드한 체크포인트 중 하나를 지정해야 하므로 확장자가 <code>.mlmodelc</code>인 컴파일된 Core ML 번들이 포함되어 있는지 확인하시기 바랍니다. <code>--compute-units</code>는 다음 값 중 하나이어야 합니다: <code>all</code>, <code>cpuOnly</code>, <code>cpuAndGPU</code>, <code>cpuAndNeuralEngine</code>.</p> <p data-svelte-h="svelte-2n9wsh">자세한 내용은 <a href="https://github.com/apple/ml-stable-diffusion" rel="nofollow">Apple의 리포지토리 안의 지침</a>을 참고하시기 바랍니다.</p> <h2 class="relative group"><a id="지원되는-diffusers-기능" 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="#지원되는-diffusers-기능"><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>지원되는 Diffusers 기능</span></h2> <p data-svelte-h="svelte-1svsy93">Core ML 모델과 추론 코드는 🧨 Diffusers의 많은 기능, 옵션 및 유연성을 지원하지 않습니다. 다음은 유의해야 할 몇 가지 제한 사항입니다:</p> <ul data-svelte-h="svelte-upf8t6"><li>Core ML 모델은 추론에만 적합합니다. 학습이나 파인튜닝에는 사용할 수 없습니다.</li> <li>Swift에 포팅된 스케줄러는 Stable Diffusion에서 사용하는 기본 스케줄러와 <code>diffusers</code> 구현에서 Swift로 포팅한 <code>DPMSolverMultistepScheduler</code> 두 개뿐입니다. 이들 중 약 절반의 스텝으로 동일한 품질을 생성하는 <code>DPMSolverMultistepScheduler</code>를 사용하는 것이 좋습니다.</li> <li>추론 코드에서 네거티브 프롬프트, classifier-free guidance scale 및 image-to-image 작업을 사용할 수 있습니다. depth guidance, ControlNet, latent upscalers와 같은 고급 기능은 아직 사용할 수 없습니다.</li></ul> <p data-svelte-h="svelte-vgqart">Apple의 <a href="https://github.com/apple/ml-stable-diffusion" rel="nofollow">변환 및 추론 리포지토리</a>와 자체 <a href="https://github.com/huggingface/swift-coreml-diffusers" rel="nofollow">swift-coreml-diffusers</a> 리포지토리는 다른 개발자들이 구축할 수 있는 기술적인 데모입니다.</p> <p data-svelte-h="svelte-e71cas">누락된 기능이 있다고 생각되면 언제든지 기능을 요청하거나, 더 좋은 방법은 기여 PR을 열어주세요. :)</p> <h2 class="relative group"><a id="네이티브-diffusers-swift-앱" 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="#네이티브-diffusers-swift-앱"><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>네이티브 Diffusers Swift 앱</span></h2> <p data-svelte-h="svelte-1e0lp79">자체 Apple 하드웨어에서 Stable Diffusion을 실행하는 쉬운 방법 중 하나는 <code>diffusers</code>와 Apple의 변환 및 추론 리포지토리를 기반으로 하는 <a href="https://github.com/huggingface/swift-coreml-diffusers" rel="nofollow">자체 오픈 소스 Swift 리포지토리</a>를 사용하는 것입니다. 코드를 공부하고 <a href="https://developer.apple.com/xcode/" rel="nofollow">Xcode</a>로 컴파일하여 필요에 맞게 조정할 수 있습니다. 편의를 위해 앱스토어에 <a href="https://apps.apple.com/app/diffusers/id1666309574" rel="nofollow">독립형 Mac 앱</a>도 있으므로 코드나 IDE를 다루지 않고도 사용할 수 있습니다. 개발자로서 Core ML이 Stable Diffusion 앱을 구축하는 데 가장 적합한 솔루션이라고 판단했다면, 이 가이드의 나머지 부분을 사용하여 프로젝트를 시작할 수 있습니다. 여러분이 무엇을 빌드할지 기대됩니다. :)</p> <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/coreml.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, 10], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 44.1 kB
- Xet hash:
- bf6033c2f28746c51f9a4ba873eeb3459d621b6ad0c5035c3bf9960c5f10697d
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.