diffusers/pr_12762/ko/_app/immutable/nodes/48.97c4e262.js

import{s as Hl,n as Ol,o as Cl}from"../chunks/scheduler.23542ac5.js";import{S as Fl,i as Vl,e as n,s as a,c as m,h as Ll,a as p,d as t,b as i,f as Sl,g as o,j as u,k as wl,l as Dl,m as s,n as r,t as M,o as c,p as f}from"../chunks/index.9b1f405b.js";import{C as Al,H as D,E as Nl}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.d0f2fc78.js";import{C as F}from"../chunks/CodeBlock.debfd64c.js";import{D as zl}from"../chunks/DocNotebookDropdown.68a629d2.js";function ql($l){let d,A,V,N,U,z,T,q,h,P,y,Zl='SDXL Turbo는 adversarial time-distilled(적대적 시간 전이) <a href="https://huggingface.co/papers/2307.01952" rel="nofollow">Stable Diffusion XL</a>(SDXL) 모델로, 단 한 번의 스텝만으로 추론을 실행할 수 있습니다.',K,j,Rl="이 가이드에서는 text-to-image와 image-to-image를 위한 SDXL-Turbo를 사용하는 방법을 설명합니다.",ll,Q,kl="시작하기 전에 다음 라이브러리가 설치되어 있는지 확인하세요:",el,J,tl,w,sl,$,xl="모델 가중치는 Hub의 별도 하위 폴더 또는 로컬에 저장할 수 있으며, 이 경우 <code>from_pretrained()</code> 메서드를 사용해야 합니다:",al,Z,il,R,Gl="또한 <code>from_single_file()</code> 메서드를 사용하여 허브 또는 로컬에서 단일 파일 형식(<code>.ckpt</code> 또는 <code>.safetensors</code>)으로 저장된 모델 체크포인트를 불러올 수도 있습니다:",nl,k,pl,x,ml,G,Wl="Text-to-image의 경우 텍스트 프롬프트를 전달합니다. 기본적으로 SDXL Turbo는 512x512 이미지를 생성하며, 이 해상도에서 최상의 결과를 제공합니다. <code>height</code> 및 <code>width</code> 매개 변수를 768x768 또는 1024x1024로 설정할 수 있지만 이 경우 품질 저하를 예상할 수 있습니다.",ol,W,_l=`모델이 <code>guidance_scale</code> 없이 학습되었으므로 이를 0.0으로 설정해 비활성화해야 합니다. 단일 추론 스텝만으로도 고품질 이미지를 생성할 수 있습니다.
스텝 수를 2, 3 또는 4로 늘리면 이미지 품질이 향상됩니다.`,rl,_,Ml,g,Il='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/sdxl-turbo-text2img.png" alt="generated image of a racoon in a robe"/>',cl,I,fl,v,vl=`Image-to-image 생성의 경우 <code>num_inference_steps * strength</code>가 1보다 크거나 같은지 확인하세요.
Image-to-image 파이프라인은 아래 예제에서 <code>0.5 * 2.0 = 1</code> 스텝과 같이 <code>int(num_inference_steps * strength)</code> 스텝으로 실행됩니다.`,ul,B,dl,b,Bl='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/sdxl-turbo-img2img.png" alt="Image-to-image generation sample using SDXL Turbo"/>',gl,X,bl,E,Xl="<li>PyTorch 버전 2 이상을 사용하는 경우 UNet을 컴파일합니다. 첫 번째 추론 실행은 매우 느리지만 이후 실행은 훨씬 빨라집니다.</li>",Ul,Y,Tl,S,El="<li>기본 VAE를 사용하는 경우, 각 생성 전후에 비용이 많이 드는 <code>dtype</code> 변환을 피하기 위해 <code>float32</code>로 유지하세요. 이 작업은 첫 생성 이전에 한 번만 수행하면 됩니다:</li>",hl,H,yl,O,Yl='또는, 커뮤니티 회원인 <a href="https://huggingface.co/madebyollin" rel="nofollow"><code>@madebyollin</code></a>이 만든 <a href="https://huggingface.co/madebyollin/sdxl-vae-fp16-fix" rel="nofollow">16비트 VAE</a>를 사용할 수도 있으며, 이는 <code>float32</code>로 업캐스트할 필요가 없습니다.',jl,C,Ql,L,Jl;return U=new Al({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),T=new zl({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;",options:[{label:"Mixed",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers_doc/ko/sdxl_turbo.ipynb"},{label:"PyTorch",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers_doc/ko/pytorch/sdxl_turbo.ipynb"},{label:"TensorFlow",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers_doc/ko/tensorflow/sdxl_turbo.ipynb"},{label:"Mixed",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/ko/sdxl_turbo.ipynb"},{label:"PyTorch",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/ko/pytorch/sdxl_turbo.ipynb"},{label:"TensorFlow",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/ko/tensorflow/sdxl_turbo.ipynb"}]}}),h=new D({props:{title:"Stable Diffusion XL Turbo",local:"stable-diffusion-xl-turbo",headingTag:"h1"}}),J=new F({props:{code:"JTIzJTIwQ29sYWIlRUMlOTclOTAlRUMlODQlOUMlMjAlRUQlOTUlODQlRUMlOUElOTQlRUQlOTUlOUMlMjAlRUIlOUQlQkMlRUMlOUQlQjQlRUIlQjglOEMlRUIlOUYlQUMlRUIlQTYlQUMlRUIlQTUlQkMlMjAlRUMlODQlQTQlRUMlQjklOTglRUQlOTUlOTglRUElQjglQjAlMjAlRUMlOUMlODQlRUQlOTUlQjQlMjAlRUMlQTMlQkMlRUMlODQlOUQlRUMlOUQlODQlMjAlRUMlQTAlOUMlRUMlOTklQjglRUQlOTUlOTglRUMlODQlQjglRUMlOUElOTQlMEElMjMhcGlwJTIwaW5zdGFsbCUyMC1xJTIwZGlmZnVzZXJzJTIwdHJhbnNmb3JtZXJzJTIwYWNjZWxlcmF0ZQ==",highlighted:`<span class="hljs-comment"># Colab에서 필요한 라이브러리를 설치하기 위해 주석을 제외하세요</span>
<span class="hljs-comment">#!pip install -q diffusers transformers accelerate</span>`,wrap:!1}}),w=new D({props:{title:"모델 체크포인트 불러오기",local:"모델-체크포인트-불러오기",headingTag:"h2"}}),Z=new F({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEF1dG9QaXBlbGluZUZvclRleHQySW1hZ2UlMkMlMjBBdXRvUGlwZWxpbmVGb3JJbWFnZTJJbWFnZSUwQWltcG9ydCUyMHRvcmNoJTBBJTBBcGlwZWxpbmUlMjAlM0QlMjBBdXRvUGlwZWxpbmVGb3JUZXh0MkltYWdlLmZyb21fcHJldHJhaW5lZCglMjJzdGFiaWxpdHlhaSUyRnNkeGwtdHVyYm8lMjIlMkMlMjB0b3JjaF9kdHlwZSUzRHRvcmNoLmZsb2F0MTYlMkMlMjB2YXJpYW50JTNEJTIyZnAxNiUyMiklMEFwaXBlbGluZSUyMCUzRCUyMHBpcGVsaW5lLnRvKCUyMmN1ZGElMjIp",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image, AutoPipelineForImage2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(<span class="hljs-string">&quot;stabilityai/sdxl-turbo&quot;</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>)
pipeline = pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)`,wrap:!1}}),k=new F({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMFN0YWJsZURpZmZ1c2lvblhMUGlwZWxpbmUlMEFpbXBvcnQlMjB0b3JjaCUwQSUwQXBpcGVsaW5lJTIwJTNEJTIwU3RhYmxlRGlmZnVzaW9uWExQaXBlbGluZS5mcm9tX3NpbmdsZV9maWxlKCUwQSUyMCUyMCUyMCUyMCUyMmh0dHBzJTNBJTJGJTJGaHVnZ2luZ2ZhY2UuY28lMkZzdGFiaWxpdHlhaSUyRnNkeGwtdHVyYm8lMkZibG9iJTJGbWFpbiUyRnNkX3hsX3R1cmJvXzEuMF9mcDE2LnNhZmV0ZW5zb3JzJTIyJTJDJTIwdG9yY2hfZHR5cGUlM0R0b3JjaC5mbG9hdDE2KSUwQXBpcGVsaW5lJTIwJTNEJTIwcGlwZWxpbmUudG8oJTIyY3VkYSUyMik=",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionXLPipeline
<span class="hljs-keyword">import</span> torch

pipeline = StableDiffusionXLPipeline.from_single_file(
    <span class="hljs-string">&quot;https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0_fp16.safetensors&quot;</span>, torch_dtype=torch.float16)
pipeline = pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)`,wrap:!1}}),x=new D({props:{title:"Text-to-image",local:"text-to-image",headingTag:"h2"}}),_=new F({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline_text2image = AutoPipelineForText2Image.from_pretrained(<span class="hljs-string">&quot;stabilityai/sdxl-turbo&quot;</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>)
pipeline_text2image = pipeline_text2image.to(<span class="hljs-string">&quot;cuda&quot;</span>)

prompt = <span class="hljs-string">&quot;A cinematic shot of a baby racoon wearing an intricate italian priest robe.&quot;</span>

image = pipeline_text2image(prompt=prompt, guidance_scale=<span class="hljs-number">0.0</span>, num_inference_steps=<span class="hljs-number">1</span>).images[<span class="hljs-number">0</span>]
image`,wrap:!1}}),I=new D({props:{title:"Image-to-image",local:"image-to-image",headingTag:"h2"}}),B=new F({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForImage2Image
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, make_image_grid

<span class="hljs-comment"># 체크포인트를 불러올 때 추가 메모리 소모를 피하려면 from_pipe를 사용하세요.</span>
pipeline = AutoPipelineForImage2Image.from_pipe(pipeline_text2image).to(<span class="hljs-string">&quot;cuda&quot;</span>)

init_image = load_image(<span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png&quot;</span>)
init_image = init_image.resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))

prompt = <span class="hljs-string">&quot;cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k&quot;</span>

image = pipeline(prompt, image=init_image, strength=<span class="hljs-number">0.5</span>, guidance_scale=<span class="hljs-number">0.0</span>, num_inference_steps=<span class="hljs-number">2</span>).images[<span class="hljs-number">0</span>]
make_image_grid([init_image, image], rows=<span class="hljs-number">1</span>, cols=<span class="hljs-number">2</span>)`,wrap:!1}}),X=new D({props:{title:"SDXL Turbo 속도 훨씬 더 빠르게 하기",local:"sdxl-turbo-속도-훨씬-더-빠르게-하기",headingTag:"h2"}}),Y=new F({props:{code:"cGlwZS51bmV0JTIwJTNEJTIwdG9yY2guY29tcGlsZShwaXBlLnVuZXQlMkMlMjBtb2RlJTNEJTIycmVkdWNlLW92ZXJoZWFkJTIyJTJDJTIwZnVsbGdyYXBoJTNEVHJ1ZSk=",highlighted:'pipe.unet = torch.<span class="hljs-built_in">compile</span>(pipe.unet, mode=<span class="hljs-string">&quot;reduce-overhead&quot;</span>, fullgraph=<span class="hljs-literal">True</span>)',wrap:!1}}),H=new F({props:{code:"cGlwZS51cGNhc3RfdmFlKCk=",highlighted:"pipe.upcast_vae()",wrap:!1}}),C=new Nl({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/ko/using-diffusers/sdxl_turbo.md"}}),{c(){d=n("meta"),A=a(),V=n("p"),N=a(),m(U.$$.fragment),z=a(),m(T.$$.fragment),q=a(),m(h.$$.fragment),P=a(),y=n("p"),y.innerHTML=Zl,K=a(),j=n("p"),j.textContent=Rl,ll=a(),Q=n("p"),Q.textContent=kl,el=a(),m(J.$$.fragment),tl=a(),m(w.$$.fragment),sl=a(),$=n("p"),$.innerHTML=xl,al=a(),m(Z.$$.fragment),il=a(),R=n("p"),R.innerHTML=Gl,nl=a(),m(k.$$.fragment),pl=a(),m(x.$$.fragment),ml=a(),G=n("p"),G.innerHTML=Wl,ol=a(),W=n("p"),W.innerHTML=_l,rl=a(),m(_.$$.fragment),Ml=a(),g=n("div"),g.innerHTML=Il,cl=a(),m(I.$$.fragment),fl=a(),v=n("p"),v.innerHTML=vl,ul=a(),m(B.$$.fragment),dl=a(),b=n("div"),b.innerHTML=Bl,gl=a(),m(X.$$.fragment),bl=a(),E=n("ul"),E.innerHTML=Xl,Ul=a(),m(Y.$$.fragment),Tl=a(),S=n("ul"),S.innerHTML=El,hl=a(),m(H.$$.fragment),yl=a(),O=n("p"),O.innerHTML=Yl,jl=a(),m(C.$$.fragment),Ql=a(),L=n("p"),this.h()},l(l){const e=Ll("svelte-u9bgzb",document.head);d=p(e,"META",{name:!0,content:!0}),e.forEach(t),A=i(l),V=p(l,"P",{}),Sl(V).forEach(t),N=i(l),o(U.$$.fragment,l),z=i(l),o(T.$$.fragment,l),q=i(l),o(h.$$.fragment,l),P=i(l),y=p(l,"P",{"data-svelte-h":!0}),u(y)!=="svelte-1ufuzv5"&&(y.innerHTML=Zl),K=i(l),j=p(l,"P",{"data-svelte-h":!0}),u(j)!=="svelte-b6e8o9"&&(j.textContent=Rl),ll=i(l),Q=p(l,"P",{"data-svelte-h":!0}),u(Q)!=="svelte-1dydg7a"&&(Q.textContent=kl),el=i(l),o(J.$$.fragment,l),tl=i(l),o(w.$$.fragment,l),sl=i(l),$=p(l,"P",{"data-svelte-h":!0}),u($)!=="svelte-1002t17"&&($.innerHTML=xl),al=i(l),o(Z.$$.fragment,l),il=i(l),R=p(l,"P",{"data-svelte-h":!0}),u(R)!=="svelte-1sxulob"&&(R.innerHTML=Gl),nl=i(l),o(k.$$.fragment,l),pl=i(l),o(x.$$.fragment,l),ml=i(l),G=p(l,"P",{"data-svelte-h":!0}),u(G)!=="svelte-578px2"&&(G.innerHTML=Wl),ol=i(l),W=p(l,"P",{"data-svelte-h":!0}),u(W)!=="svelte-19as9ic"&&(W.innerHTML=_l),rl=i(l),o(_.$$.fragment,l),Ml=i(l),g=p(l,"DIV",{class:!0,"data-svelte-h":!0}),u(g)!=="svelte-1lx4ppg"&&(g.innerHTML=Il),cl=i(l),o(I.$$.fragment,l),fl=i(l),v=p(l,"P",{"data-svelte-h":!0}),u(v)!=="svelte-plguoj"&&(v.innerHTML=vl),ul=i(l),o(B.$$.fragment,l),dl=i(l),b=p(l,"DIV",{class:!0,"data-svelte-h":!0}),u(b)!=="svelte-ovbosa"&&(b.innerHTML=Bl),gl=i(l),o(X.$$.fragment,l),bl=i(l),E=p(l,"UL",{"data-svelte-h":!0}),u(E)!=="svelte-d9vh8a"&&(E.innerHTML=Xl),Ul=i(l),o(Y.$$.fragment,l),Tl=i(l),S=p(l,"UL",{"data-svelte-h":!0}),u(S)!=="svelte-13u9mbf"&&(S.innerHTML=El),hl=i(l),o(H.$$.fragment,l),yl=i(l),O=p(l,"P",{"data-svelte-h":!0}),u(O)!=="svelte-6q79hw"&&(O.innerHTML=Yl),jl=i(l),o(C.$$.fragment,l),Ql=i(l),L=p(l,"P",{}),Sl(L).forEach(t),this.h()},h(){wl(d,"name","hf:doc:metadata"),wl(d,"content",Pl),wl(g,"class","flex justify-center"),wl(b,"class","flex justify-center")},m(l,e){Dl(document.head,d),s(l,A,e),s(l,V,e),s(l,N,e),r(U,l,e),s(l,z,e),r(T,l,e),s(l,q,e),r(h,l,e),s(l,P,e),s(l,y,e),s(l,K,e),s(l,j,e),s(l,ll,e),s(l,Q,e),s(l,el,e),r(J,l,e),s(l,tl,e),r(w,l,e),s(l,sl,e),s(l,$,e),s(l,al,e),r(Z,l,e),s(l,il,e),s(l,R,e),s(l,nl,e),r(k,l,e),s(l,pl,e),r(x,l,e),s(l,ml,e),s(l,G,e),s(l,ol,e),s(l,W,e),s(l,rl,e),r(_,l,e),s(l,Ml,e),s(l,g,e),s(l,cl,e),r(I,l,e),s(l,fl,e),s(l,v,e),s(l,ul,e),r(B,l,e),s(l,dl,e),s(l,b,e),s(l,gl,e),r(X,l,e),s(l,bl,e),s(l,E,e),s(l,Ul,e),r(Y,l,e),s(l,Tl,e),s(l,S,e),s(l,hl,e),r(H,l,e),s(l,yl,e),s(l,O,e),s(l,jl,e),r(C,l,e),s(l,Ql,e),s(l,L,e),Jl=!0},p:Ol,i(l){Jl||(M(U.$$.fragment,l),M(T.$$.fragment,l),M(h.$$.fragment,l),M(J.$$.fragment,l),M(w.$$.fragment,l),M(Z.$$.fragment,l),M(k.$$.fragment,l),M(x.$$.fragment,l),M(_.$$.fragment,l),M(I.$$.fragment,l),M(B.$$.fragment,l),M(X.$$.fragment,l),M(Y.$$.fragment,l),M(H.$$.fragment,l),M(C.$$.fragment,l),Jl=!0)},o(l){c(U.$$.fragment,l),c(T.$$.fragment,l),c(h.$$.fragment,l),c(J.$$.fragment,l),c(w.$$.fragment,l),c(Z.$$.fragment,l),c(k.$$.fragment,l),c(x.$$.fragment,l),c(_.$$.fragment,l),c(I.$$.fragment,l),c(B.$$.fragment,l),c(X.$$.fragment,l),c(Y.$$.fragment,l),c(H.$$.fragment,l),c(C.$$.fragment,l),Jl=!1},d(l){l&&(t(A),t(V),t(N),t(z),t(q),t(P),t(y),t(K),t(j),t(ll),t(Q),t(el),t(tl),t(sl),t($),t(al),t(il),t(R),t(nl),t(pl),t(ml),t(G),t(ol),t(W),t(rl),t(Ml),t(g),t(cl),t(fl),t(v),t(ul),t(dl),t(b),t(gl),t(bl),t(E),t(Ul),t(Tl),t(S),t(hl),t(yl),t(O),t(jl),t(Ql),t(L)),t(d),f(U,l),f(T,l),f(h,l),f(J,l),f(w,l),f(Z,l),f(k,l),f(x,l),f(_,l),f(I,l),f(B,l),f(X,l),f(Y,l),f(H,l),f(C,l)}}}const Pl='{"title":"Stable Diffusion XL Turbo","local":"stable-diffusion-xl-turbo","sections":[{"title":"모델 체크포인트 불러오기","local":"모델-체크포인트-불러오기","sections":[],"depth":2},{"title":"Text-to-image","local":"text-to-image","sections":[],"depth":2},{"title":"Image-to-image","local":"image-to-image","sections":[],"depth":2},{"title":"SDXL Turbo 속도 훨씬 더 빠르게 하기","local":"sdxl-turbo-속도-훨씬-더-빠르게-하기","sections":[],"depth":2}],"depth":1}';function Kl($l){return Cl(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ie extends Fl{constructor(d){super(),Vl(this,d,Kl,ql,Hl,{})}}export{ie as component};