Buckets:

hf-doc-build/doc / diffusers /v0.19.2 /ko /using-diffusers /unconditional_image_generation.html
rtrm's picture
download
raw
7.51 kB
<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;unconditional&quot;,&quot;title&quot;:&quot;Unconditional 이미지 생성&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/using-diffusers/unconditional_image_generation.mdx-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.19.2/ko/_app/chunks/Tip-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 class="relative group"><a id="unconditional" 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="#unconditional"><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>Unconditional 이미지 생성
</span></h1>
<p>[[Colab에서 열기]]</p>
<p>Unconditional 이미지 생성은 비교적 간단한 작업입니다. 모델이 텍스트나 이미지와 같은 추가 조건 없이 이미 학습된 학습 데이터와 유사한 이미지만 생성합니다.</p>
<p>[‘DiffusionPipeline’]은 추론을 위해 미리 학습된 diffusion 시스템을 사용하는 가장 쉬운 방법입니다.</p>
<p>먼저 [‘DiffusionPipeline’]의 인스턴스를 생성하고 다운로드할 파이프라인의 <a href="https://huggingface.co/models?library=diffusers&sort=downloads" rel="nofollow">체크포인트</a>를 지정합니다. 허브의 🧨 diffusion 체크포인트 중 하나를 사용할 수 있습니다(사용할 체크포인트는 나비 이미지를 생성합니다).</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>💡 나만의 unconditional 이미지 생성 모델을 학습시키고 싶으신가요? 학습 가이드를 살펴보고 나만의 이미지를 생성하는 방법을 알아보세요.</p></div>
<p>이 가이드에서는 unconditional 이미지 생성에 [‘DiffusionPipeline’]과 <a href="https://arxiv.org/abs/2006.11239" rel="nofollow">DDPM</a>을 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><!-- 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>generator = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;anton-l/ddpm-butterflies-128&quot;</span>)
```
[diffusion 파이프라인]은 모든 모델링, 토큰화, 스케줄링 구성 요소를 다운로드하고 캐시합니다. 이 모델은 약 <span class="hljs-number">14</span>억 개의 파라미터로 구성되어 있기 때문에 GPU에서 실행할 것을 강력히 권장합니다. PyTorch에서와 마찬가지로 제너레이터 객체를 GPU로 옮길 수 있습니다:
```python
<span class="hljs-meta">&gt;&gt;&gt; </span>generator.to(<span class="hljs-string">&quot;cuda&quot;</span>)
```
이제 제너레이터를 사용하여 이미지를 생성할 수 있습니다:
```python
<span class="hljs-meta">&gt;&gt;&gt; </span>image = generator().images[<span class="hljs-number">0</span>]
```
출력은 기본적으로 [PIL.Image](https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image<span class="hljs-comment">#the-image-class) 객체로 감싸집니다.</span>
다음을 호출하여 이미지를 저장할 수 있습니다:
```python
<span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;generated_image.png&quot;</span>)
```
아래 스페이스(데모 링크)를 이용해 보고, 추론 단계의 매개변수를 자유롭게 조절하여 이미지 품질에 어떤 영향을 미치는지 확인해 보세요!
&lt;iframe src=<span class="hljs-string">&quot;https://stevhliu-ddpm-butterflies-128.hf.space&quot;</span> frameborder=<span class="hljs-string">&quot;0&quot;</span> width=<span class="hljs-string">&quot;850&quot;</span> height=<span class="hljs-string">&quot;500&quot;</span>&gt;&lt;/iframe&gt;<!-- HTML_TAG_END --></pre></div>
<script type="module" data-hydrate="1r3dlkx">
import { start } from "/docs/diffusers/v0.19.2/ko/_app/start-hf-doc-builder.js";
start({
target: document.querySelector('[data-hydrate="1r3dlkx"]').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/using-diffusers/unconditional_image_generation.mdx-hf-doc-builder.js")
],
params: {}
}
});
</script>

Xet Storage Details

Size:
7.51 kB
·
Xet hash:
37cb37854ca92e38648013255ed36c8cad3272c98150d5d9295580dd5d7ceae3

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