Buckets:

hf-doc-build/doc / diffusers /v0.19.2 /ko /quicktour.html
rtrm's picture
download
raw
22.8 kB
<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;diffusionpipeline&quot;,&quot;title&quot;:&quot;DiffusionPipeline&quot;}],&quot;title&quot;:&quot;훑어보기&quot;}" data-svelte="svelte-1phssyn">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/start-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/chunks/vendor-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/chunks/paths-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/pages/__layout.svelte-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/pages/quicktour.mdx-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/chunks/IconCopyLink-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/chunks/CodeBlock-hf-doc-builder.js">
<h1 id="">훑어보기</h1>
<p>🧨 Diffusers로 빠르게 시작하고 실행하세요!
이 훑어보기는 여러분이 개발자, 일반사용자 상관없이 시작하는 데 도움을 주며, 추론을 위해 <code>DiffusionPipeline</code> 사용하는 방법을 보여줍니다.</p>
<p>시작하기에 앞서서, 필요한 모든 라이브러리가 설치되어 있는지 확인하세요:</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 -->pip install --upgrade diffusers accelerate transformers<!-- HTML_TAG_END --></pre></div>
<ul><li><a href="https://huggingface.co/docs/accelerate/index" rel="nofollow"><code>accelerate</code></a>은 추론 및 학습을 위한 모델 불러오기 속도를 높입니다.</li>
<li><a href="https://huggingface.co/docs/transformers/index" rel="nofollow"><code>transformers</code></a><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview" rel="nofollow">Stable Diffusion</a>과 같이 가장 널리 사용되는 확산 모델을 실행하기 위해 필요합니다.</li></ul>
<h2 class="relative group"><a id="diffusionpipeline" 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="#diffusionpipeline"><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>DiffusionPipeline
</span></h2>
<p><code>DiffusionPipeline</code>은 추론을 위해 사전학습된 확산 시스템을 사용하는 가장 쉬운 방법입니다. 다양한 양식의 많은 작업에 <code>DiffusionPipeline</code>을 바로 사용할 수 있습니다. 지원되는 작업은 아래의 표를 참고하세요:</p>
<table><thead><tr><th><strong>Task</strong></th>
<th><strong>Description</strong></th>
<th><strong>Pipeline</strong></th></tr></thead>
<tbody><tr><td>Unconditional Image Generation</td>
<td>가우시안 노이즈에서 이미지 생성</td>
<td><a href="./using-diffusers/unconditional_image_generation%60">unconditional_image_generation</a></td></tr>
<tr><td>Text-Guided Image Generation</td>
<td>텍스트 프롬프트로 이미지 생성</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>텍스트 프롬프트에 따라 이미지 조정</td>
<td><a href="./using-diffusers/img2img">img2img</a></td></tr>
<tr><td>Text-Guided Image-Inpainting</td>
<td>마스크 및 텍스트 프롬프트가 주어진 이미지의 마스킹된 부분을 채우기</td>
<td><a href="./using-diffusers/inpaint">inpaint</a></td></tr>
<tr><td>Text-Guided Depth-to-Image Translation</td>
<td>깊이 추정을 통해 구조를 유지하면서 텍스트 프롬프트에 따라 이미지의 일부를 조정</td>
<td><a href="./using-diffusers/depth2image">depth2image</a></td></tr></tbody></table>
<p>확산 파이프라인이 다양한 작업에 대해 어떻게 작동하는지는 <a href="./using-diffusers/overview"><strong>Using Diffusers</strong></a>를 참고하세요.</p>
<p>예를들어, <code>DiffusionPipeline</code> 인스턴스를 생성하여 시작하고, 다운로드하려는 파이프라인 체크포인트를 지정합니다.
모든 <a href="https://huggingface.co/models?library=diffusers&sort=downloads" rel="nofollow">Diffusers’ checkpoint</a>에 대해 <code>DiffusionPipeline</code>을 사용할 수 있습니다.
하지만, 이 가이드에서는 <a href="https://huggingface.co/CompVis/stable-diffusion" rel="nofollow">Stable Diffusion</a>을 사용하여 text-to-image를 하는데 <code>DiffusionPipeline</code>을 사용합니다.</p>
<p><a href="https://huggingface.co/CompVis/stable-diffusion" rel="nofollow">Stable Diffusion</a> 기반 모델을 실행하기 전에 <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" rel="nofollow">license</a>를 주의 깊게 읽으세요.
이는 모델의 향상된 이미지 생성 기능과 이것으로 생성될 수 있는 유해한 콘텐츠 때문입니다. 선택한 Stable Diffusion 모델(<em></em>: <a href="https://huggingface.co/runwayml/stable-diffusion-v1-5" rel="nofollow"><code>runwayml/stable-diffusion-v1-5</code></a>)로 이동하여 라이센스를 읽으세요.</p>
<p>다음과 같이 모델을 로드할 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><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;runwayml/stable-diffusion-v1-5&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p><code>DiffusionPipeline</code>은 모든 모델링, 토큰화 및 스케줄링 구성요소를 다운로드하고 캐시합니다.
모델은 약 14억개의 매개변수로 구성되어 있으므로 GPU에서 실행하는 것이 좋습니다.
PyTorch에서와 마찬가지로 생성기 객체를 GPU로 옮길 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><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>이제 <code>pipeline</code>을 사용할 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><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span>image = pipeline(<span class="hljs-string">&quot;An image of a squirrel in Picasso style&quot;</span>).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div>
<p>출력은 기본적으로 <a href="https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class" rel="nofollow">PIL Image object</a>로 래핑됩니다.</p>
<p>다음과 같이 함수를 호출하여 이미지를 저장할 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><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;image_of_squirrel_painting.png&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p><strong>참고</strong>: 다음을 통해 가중치를 다운로드하여 로컬에서 파이프라인을 사용할 수도 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><!-- HTML_TAG_START -->git lfs install
git clone https:<span class="hljs-regexp">//</span>huggingface.co<span class="hljs-regexp">/runwayml/</span>stable-diffusion-v1-<span class="hljs-number">5</span><!-- HTML_TAG_END --></pre></div>
<p>그리고 저장된 가중치를 파이프라인에 불러옵니다.</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-meta">&gt;&gt;&gt; </span>pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;./stable-diffusion-v1-5&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>파이프라인 실행은 동일한 모델 아키텍처이므로 위의 코드와 동일합니다.</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-meta">&gt;&gt;&gt; </span>generator.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>image = generator(<span class="hljs-string">&quot;An image of a squirrel in Picasso style&quot;</span>).images[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;image_of_squirrel_painting.png&quot;</span>)<!-- HTML_TAG_END --></pre></div>
<p>확산 시스템은 각각 장점이 있는 여러 다른 <a href="./api/schedulers/overview">schedulers</a>와 함께 사용할 수 있습니다. 기본적으로 Stable Diffusion은 <code>PNDMScheduler</code>로 실행되지만 다른 스케줄러를 사용하는 방법은 매우 간단합니다. <em></em> <code>EulerDiscreteScheduler</code> 스케줄러를 사용하려는 경우, 다음과 같이 사용할 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><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> EulerDiscreteScheduler
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline = StableDiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;runwayml/stable-diffusion-v1-5&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># change scheduler to Euler</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)<!-- HTML_TAG_END --></pre></div>
<p>스케줄러 변경 방법에 대한 자세한 내용은 <a href="./using-diffusers/schedulers">Using Schedulers</a> 가이드를 참고하세요.</p>
<p><a href="https://stability.ai/" rel="nofollow">Stability AI’s</a>의 Stable Diffusion 모델은 인상적인 이미지 생성 모델이며 텍스트에서 이미지를 생성하는 것보다 훨씬 더 많은 작업을 수행할 수 있습니다. 우리는 Stable Diffusion만을 위한 전체 문서 페이지를 제공합니다 <a href="./conceptual/stable_diffusion">link</a>.</p>
<p>만약 더 적은 메모리, 더 높은 추론 속도, Mac과 같은 특정 하드웨어 또는 ONNX 런타임에서 실행되도록 Stable Diffusion을 최적화하는 방법을 알고 싶다면 최적화 페이지를 살펴보세요:</p>
<ul><li><a href="./optimization/fp16">Optimized PyTorch on GPU</a></li>
<li><a href="./optimization/mps">Mac OS with PyTorch</a></li>
<li><a href="./optimization/onnx">ONNX</a></li>
<li><a href="./optimization/open_vino">OpenVINO</a></li></ul>
<p>확산 모델을 미세조정하거나 학습시키려면, <a href="./training/overview"><strong>training section</strong></a>을 살펴보세요.</p>
<p>마지막으로, 생성된 이미지를 공개적으로 배포할 때 신중을 기해 주세요 🤗.</p>
<script type="module" data-hydrate="zsn1k6">
import { start } from "/docs/diffusers/v0.19.2/ko/_app/start-hf-doc-builder.js";
start({
target: document.querySelector('[data-hydrate="zsn1k6"]').parentNode,
paths: {"base":"/docs/diffusers/v0.19.2/ko","assets":"/docs/diffusers/v0.19.2/ko"},
session: {},
route: false,
spa: false,
trailing_slash: "never",
hydrate: {
status: 200,
error: null,
nodes: [
import("/docs/diffusers/v0.19.2/ko/_app/pages/__layout.svelte-hf-doc-builder.js"),
import("/docs/diffusers/v0.19.2/ko/_app/pages/quicktour.mdx-hf-doc-builder.js")
],
params: {}
}
});
</script>

Xet Storage Details

Size:
22.8 kB
·
Xet hash:
598de1837fdb349b6fd35faa3ad6597fb520cd4e2860656fe08e112d7ba6dc6a

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