Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / diffusers /main /ko /training /adapt_a_model.html

rtrm

15 days ago

download

raw

12.9 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"새로운 작업에 대한 모델을 적용하기","local":"새로운-작업에-대한-모델을-적용하기","sections":[{"title":"UNet2DConditionModel 파라미터 구성","local":"unet2dconditionmodel-파라미터-구성","sections":[],"depth":2}],"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.df0b2e2f.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/scheduler.94020406.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/singletons.4482ca3c.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/index.8b553f6b.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/paths.1334326c.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/entry/app.4378a265.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/index.a08c8d92.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/nodes/0.96378992.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/21.7119b07b.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/CodeBlock.b23cf525.js">
	<link rel="modulepreload" href="/docs/diffusers/main/ko/_app/immutable/chunks/EditOnGithub.b1bceb47.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"새로운 작업에 대한 모델을 적용하기","local":"새로운-작업에-대한-모델을-적용하기","sections":[{"title":"UNet2DConditionModel 파라미터 구성","local":"unet2dconditionmodel-파라미터-구성","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="새로운-작업에-대한-모델을-적용하기" 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="#새로운-작업에-대한-모델을-적용하기"><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>새로운 작업에 대한 모델을 적용하기</span></h1> <p data-svelte-h="svelte-obt1bb">많은 diffusion 시스템은 같은 구성 요소들을 공유하므로 한 작업에 대해 사전학습된 모델을 완전히 다른 작업에 적용할 수 있습니다.</p> <p data-svelte-h="svelte-1bn5mvh">이 인페인팅을 위한 가이드는 사전학습된 <code>UNet2DConditionModel</code>의 아키텍처를 초기화하고 수정하여 사전학습된 text-to-image 모델을 어떻게 인페인팅에 적용하는지를 알려줄 것입니다.</p> <h2 class="relative group"><a id="unet2dconditionmodel-파라미터-구성" 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="#unet2dconditionmodel-파라미터-구성"><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>UNet2DConditionModel 파라미터 구성</span></h2> <p data-svelte-h="svelte-pq1ajp"><code>UNet2DConditionModel</code>은 <a href="https://huggingface.co/docs/diffusers/v0.16.0/en/api/models#diffusers.UNet2DConditionModel.in_channels" rel="nofollow">input sample</a>에서 4개의 채널을 기본적으로 허용합니다. 예를 들어, <a href="https://huggingface.co/runwayml/stable-diffusion-v1-5" rel="nofollow"><code>runwayml/stable-diffusion-v1-5</code></a>와 같은 사전학습된 text-to-image 모델을 불러오고 <code>in_channels</code>의 수를 확인합니다:</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> diffusers <span class="hljs-keyword">import</span> StableDiffusionPipeline

	pipeline = StableDiffusionPipeline.from_pretrained(<span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>)
	pipeline.unet.config[<span class="hljs-string">"in_channels"</span>]
	<span class="hljs-number">4</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-n1t961">인페인팅은 입력 샘플에 9개의 채널이 필요합니다. <a href="https://huggingface.co/runwayml/stable-diffusion-inpainting" rel="nofollow"><code>runwayml/stable-diffusion-inpainting</code></a>와 같은 사전학습된 인페인팅 모델에서 이 값을 확인할 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 --><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionPipeline

	pipeline = StableDiffusionPipeline.from_pretrained(<span class="hljs-string">"runwayml/stable-diffusion-inpainting"</span>)
	pipeline.unet.config[<span class="hljs-string">"in_channels"</span>]
	<span class="hljs-number">9</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1nkn0wh">인페인팅에 대한 text-to-image 모델을 적용하기 위해, <code>in_channels</code> 수를 4에서 9로 수정해야 할 것입니다.</p> <p data-svelte-h="svelte-oj0rfs">사전학습된 text-to-image 모델의 가중치와 <code>UNet2DConditionModel</code>을 초기화하고 <code>in_channels</code>를 9로 수정해 주세요. <code>in_channels</code>의 수를 수정하면 크기가 달라지기 때문에 크기가 안 맞는 오류를 피하기 위해 <code>ignore_mismatched_sizes=True</code> 및 <code>low_cpu_mem_usage=False</code>를 설정해야 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-keyword">from</span> diffusers <span class="hljs-keyword">import</span> UNet2DConditionModel

	model_id = <span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>
	unet = UNet2DConditionModel.from_pretrained(
	model_id, subfolder=<span class="hljs-string">"unet"</span>, in_channels=<span class="hljs-number">9</span>, low_cpu_mem_usage=<span class="hljs-literal">False</span>, ignore_mismatched_sizes=<span class="hljs-literal">True</span>
	)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-rfmg1f">Text-to-image 모델로부터 다른 구성 요소의 사전학습된 가중치는 체크포인트로부터 초기화되지만 <code>unet</code>의 입력 채널 가중치 (<code>conv_in.weight</code>)는 랜덤하게 초기화됩니다. 그렇지 않으면 모델이 노이즈를 리턴하기 때문에 인페인팅의 모델을 파인튜닝 할 때 중요합니다.</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/training/adapt_a_model.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_bmkzir = {
	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.df0b2e2f.js"),
	import("/docs/diffusers/main/ko/_app/immutable/entry/app.4378a265.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 21],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 12.9 kB
Xet hash:: 9cb8671992bb80db93339ed760e4720721166bdbdab1a4749c24048b6da16894

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