diffusers/pr_11686/ko/using-diffusers/depth2img.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Text-guided depth-to-image 생성&quot;,&quot;local&quot;:&quot;text-guided-depth-to-image-생성&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/diffusers/pr_11686/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/entry/start.9aef4fd8.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/scheduler.94020406.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/singletons.4a7d5fdc.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/index.8b553f6b.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/paths.c0f6af24.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/entry/app.90f3fbbd.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/index.a08c8d92.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/nodes/0.c5e60128.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/nodes/38.912e9301.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/CodeBlock.f1fae7de.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/DocNotebookDropdown.a1753374.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/globals.7f7f1b26.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_11686/ko/_app/immutable/chunks/getInferenceSnippets.f4caff04.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Text-guided depth-to-image 생성&quot;,&quot;local&quot;:&quot;text-guided-depth-to-image-생성&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <h1 class="relative group"><a id="text-guided-depth-to-image-생성" 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="#text-guided-depth-to-image-생성"><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>Text-guided depth-to-image 생성</span></h1>  <div class="flex space-x-1 absolute z-10 right-0 top-0"> <div class="relative colab-dropdown "> <button class="  " type="button">  <img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"> </button>    </div> <div class="relative colab-dropdown "> <button class="  " type="button">  <img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"> </button>    </div></div> <p data-svelte-h="svelte-1nwb6xh"><code>StableDiffusionDepth2ImgPipeline</code>을 사용하면 텍스트 프롬프트와 초기 이미지를 전달하여 새 이미지의 생성을 조절할 수 있습니다. 또한 이미지 구조를 보존하기 위해 <code>depth_map</code>을 전달할 수도 있습니다. <code>depth_map</code>이 제공되지 않으면 파이프라인은 통합된 <a href="https://github.com/isl-org/MiDaS" rel="nofollow">depth-estimation model</a>을 통해 자동으로 깊이를 예측합니다.</p> <p data-svelte-h="svelte-b7rzk">먼저 <code>StableDiffusionDepth2ImgPipeline</code>의 인스턴스를 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-keyword">import</span> torch
<span class="hljs-keyword">import</span> requests
<span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image

<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionDepth2ImgPipeline

pipe = StableDiffusionDepth2ImgPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-2-depth&quot;</span>,
    torch_dtype=torch.float16,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ospw27">이제 프롬프트를 파이프라인에 전달합니다. 특정 단어가 이미지 생성을 가이드 하는것을 방지하기 위해 <code>negative_prompt</code>를 전달할 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 class=""><!-- HTML_TAG_START -->url = <span class="hljs-string">&quot;http://images.cocodataset.org/val2017/000000039769.jpg&quot;</span>
init_image = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw)
prompt = <span class="hljs-string">&quot;two tigers&quot;</span>
n_prompt = <span class="hljs-string">&quot;bad, deformed, ugly, bad anatomy&quot;</span>
image = pipe(prompt=prompt, image=init_image, negative_prompt=n_prompt, strength=<span class="hljs-number">0.7</span>).images[<span class="hljs-number">0</span>]
image<!-- HTML_TAG_END --></pre></div> <table data-svelte-h="svelte-175x2as"><thead><tr><th>Input</th> <th>Output</th></tr></thead> <tbody><tr><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/coco-cats.png" width="500"></td> <td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/depth2img-tigers.png" width="500"></td></tr></tbody></table> <p data-svelte-h="svelte-1vexnbo">아래의 Spaces를 가지고 놀며 depth map이 있는 이미지와 없는 이미지의 차이가 있는지 확인해 보세요!</p> <iframe src="https://radames-stable-diffusion-depth2img.hf.space" frameborder="0" width="850" height="500"></iframe> <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/depth2img.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_c1nis = {
						assets: "/docs/diffusers/pr_11686/ko",
						base: "/docs/diffusers/pr_11686/ko",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/diffusers/pr_11686/ko/_app/immutable/entry/start.9aef4fd8.js"),
						import("/docs/diffusers/pr_11686/ko/_app/immutable/entry/app.90f3fbbd.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 38],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>