Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Deterministic(결정적) 생성을 통한 이미지 품질 개선","local":"deterministic결정적-생성을-통한-이미지-품질-개선","sections":[],"depth":1}"> | |
| <link href="/docs/diffusers/main/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/entry/start.0574fe93.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/scheduler.e3739aa0.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/singletons.6c595ea8.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/index.02f4400c.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/paths.b2b36d06.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/entry/app.f5608ddb.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/index.13f5b837.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/nodes/0.a357fdeb.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/nodes/50.c5d825a8.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/CodeBlock.de02009a.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/EditOnGithub.72bac8d8.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Deterministic(결정적) 생성을 통한 이미지 품질 개선","local":"deterministic결정적-생성을-통한-이미지-품질-개선","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="deterministic결정적-생성을-통한-이미지-품질-개선" 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="#deterministic결정적-생성을-통한-이미지-품질-개선"><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>Deterministic(결정적) 생성을 통한 이미지 품질 개선</span></h1> <p data-svelte-h="svelte-1vonp5w">생성된 이미지의 품질을 개선하는 일반적인 방법은 <em>결정적 batch(배치) 생성</em>을 사용하는 것입니다. 이 방법은 이미지 batch(배치)를 생성하고 두 번째 추론 라운드에서 더 자세한 프롬프트와 함께 개선할 이미지 하나를 선택하는 것입니다. 핵심은 일괄 이미지 생성을 위해 파이프라인에 <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html#generator" rel="nofollow"><code>torch.Generator</code></a> 목록을 전달하고, 각 <code>Generator</code>를 시드에 연결하여 이미지에 재사용할 수 있도록 하는 것입니다.</p> <p data-svelte-h="svelte-gvc3qa">예를 들어 <a href="runwayml/stable-diffusion-v1-5"><code>runwayml/stable-diffusion-v1-5</code></a>를 사용하여 다음 프롬프트의 여러 버전을 생성해 봅시다.</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 -->prompt = <span class="hljs-string">"Labrador in the style of Vermeer"</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-16ygecj">(가능하다면) 파이프라인을 <code>DiffusionPipeline.from_pretrained()</code>로 인스턴스화하여 GPU에 배치합니다.</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-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline | |
| <span class="hljs-meta">>>> </span>pipe = DiffusionPipeline.from_pretrained(<span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>, torch_dtype=torch.float16) | |
| <span class="hljs-meta">>>> </span>pipe = pipe.to(<span class="hljs-string">"cuda"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1dutbmp">이제 네 개의 서로 다른 <code>Generator</code>를 정의하고 각 <code>Generator</code>에 시드(<code>0</code> ~ <code>3</code>)를 할당하여 나중에 특정 이미지에 대해 <code>Generator</code>를 재사용할 수 있도록 합니다.</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-meta">>>> </span><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-meta">>>> </span>generator = [torch.Generator(device=<span class="hljs-string">"cuda"</span>).manual_seed(i) <span class="hljs-keyword">for</span> i <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(<span class="hljs-number">4</span>)]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1k0bpz">이미지를 생성하고 살펴봅니다.</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-meta">>>> </span>images = pipe(prompt, generator=generator, num_images_per_prompt=<span class="hljs-number">4</span>).images | |
| <span class="hljs-meta">>>> </span>images<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ohfhuy"><img src="https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/reusabe_seeds.jpg" alt="img"></p> <p data-svelte-h="svelte-13620rq">이 예제에서는 첫 번째 이미지를 개선했지만 실제로는 원하는 모든 이미지를 사용할 수 있습니다(심지어 두 개의 눈이 있는 이미지도!). 첫 번째 이미지에서는 시드가 ‘0’인 ‘생성기’를 사용했기 때문에 두 번째 추론 라운드에서는 이 ‘생성기’를 재사용할 것입니다. 이미지의 품질을 개선하려면 프롬프트에 몇 가지 텍스트를 추가합니다:</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 -->prompt = [prompt + t <span class="hljs-keyword">for</span> t <span class="hljs-keyword">in</span> [<span class="hljs-string">", highly realistic"</span>, <span class="hljs-string">", artsy"</span>, <span class="hljs-string">", trending"</span>, <span class="hljs-string">", colorful"</span>]] | |
| generator = [torch.Generator(device=<span class="hljs-string">"cuda"</span>).manual_seed(<span class="hljs-number">0</span>) <span class="hljs-keyword">for</span> i <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(<span class="hljs-number">4</span>)]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-mermk5">시드가 <code>0</code>인 제너레이터 4개를 생성하고, 이전 라운드의 첫 번째 이미지처럼 보이는 다른 이미지 batch(배치)를 생성합니다!</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-meta">>>> </span>images = pipe(prompt, generator=generator).images | |
| <span class="hljs-meta">>>> </span>images<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ufx7w5"><img src="https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/reusabe_seeds_2.jpg" alt="img"></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/using-diffusers/reusing_seeds.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_198thv9 = { | |
| assets: "/docs/diffusers/main/ko", | |
| base: "/docs/diffusers/main/ko", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/main/ko/_app/immutable/entry/start.0574fe93.js"), | |
| import("/docs/diffusers/main/ko/_app/immutable/entry/app.f5608ddb.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 50], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 16 kB
- Xet hash:
- 406cf3eadfe5a01682e88d5dfd4af375d3577ded6533f4353a231a69e36dfec2
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.