diffusers/main/ko/_app/immutable/nodes/16.3f54152b.js

import{s as Yt,n as Qt,o as Rt}from"../chunks/scheduler.94020406.js";import{S as Kt,i as te,g as n,s as i,r as f,E as ee,h as r,f as d,c as o,j as Xt,u as p,x as a,k as qt,y as de,a as l,v as m,d as M,t as u,w as h}from"../chunks/index.a08c8d92.js";import{C as At}from"../chunks/CodeBlock.b23cf525.js";import{H as N,E as le}from"../chunks/EditOnGithub.b1bceb47.js";function ie(xt){let s,q,W,A,T,Y,c,Lt='Token Merging (introduced in <a href="https://arxiv.org/abs/2210.09461" rel="nofollow">Token Merging: Your ViT But Faster</a>)은 트랜스포머 기반 네트워크의 forward pass에서 중복 토큰이나 패치를 점진적으로 병합하는 방식으로 작동합니다. 이를 통해 기반 네트워크의 추론 지연 시간을 단축할 수 있습니다.',Q,b,Pt='Token Merging(ToMe)이 출시된 후, 저자들은 <a href="https://arxiv.org/abs/2303.17604" rel="nofollow">Fast Stable Diffusion을 위한 토큰 병합</a>을 발표하여 Stable Diffusion과 더 잘 호환되는 ToMe 버전을 소개했습니다. ToMe를 사용하면 <code>DiffusionPipeline</code>의 추론 지연 시간을 부드럽게 단축할 수 있습니다. 이 문서에서는 ToMe를 <code>StableDiffusionPipeline</code>에 적용하는 방법, 예상되는 속도 향상, <code>StableDiffusionPipeline</code>에서 ToMe를 사용할 때의 질적 측면에 대해 설명합니다.',R,w,K,v,Ht='ToMe의 저자들은 <a href="https://github.com/dbolya/tomesd" rel="nofollow"><code>tomesd</code></a>라는 편리한 Python 라이브러리를 공개했는데, 이 라이브러리를 이용하면 <code>DiffusionPipeline</code>에 ToMe를 다음과 같이 적용할 수 있습니다:',tt,g,et,$,Bt="이것이 다입니다!",dt,y,_t='<code>tomesd.apply_patch()</code>는 파이프라인 추론 속도와 생성된 토큰의 품질 사이의 균형을 맞출 수 있도록 <a href="https://github.com/dbolya/tomesd#usage" rel="nofollow">여러 개의 인자</a>를 노출합니다. 이러한 인수 중 가장 중요한 것은 <code>ratio(비율)</code>입니다. <code>ratio</code>은 forward pass 중에 병합될 토큰의 수를 제어합니다. <code>tomesd</code>에 대한 자세한 내용은 해당 리포지토리(<a href="https://github.com/dbolya/tomesd" rel="nofollow">https://github.com/dbolya/tomesd</a>) 및 <a href="https://arxiv.org/abs/2303.17604" rel="nofollow">논문</a>을 참고하시기 바랍니다.',lt,O,it,J,Ut=`We benchmarked the impact of using <code>tomesd</code> on <code>StableDiffusionPipeline</code> along with <a href="https://huggingface.co/docs/diffusers/optimization/xformers" rel="nofollow">xformers</a> across different image resolutions. We used A100 and V100 as our test GPU devices with the following development environment (with Python 3.8.5):
다양한 이미지 해상도에서 <a href="https://huggingface.co/docs/diffusers/optimization/xformers" rel="nofollow">xformers</a>를 적용한 상태에서, <code>StableDiffusionPipeline</code>에 <code>tomesd</code>를 사용했을 때의 영향을 벤치마킹했습니다. 테스트 GPU 장치로 A100과 V100을 사용했으며 개발 환경은 다음과 같습니다(Python 3.8.5 사용):`,ot,x,nt,L,Ct='벤치마킹에는 다음 스크립트를 사용했습니다: <a href="https://gist.github.com/sayakpaul/27aec6bca7eb7b0e0aa4112205850335" rel="nofollow">https://gist.github.com/sayakpaul/27aec6bca7eb7b0e0aa4112205850335</a>. 결과는 다음과 같습니다:',rt,P,at,H,St="<thead><tr><th>해상도</th> <th>배치 크기</th> <th>Vanilla</th> <th>ToMe</th> <th>ToMe + xFormers</th> <th>ToMe 속도 향상 (%)</th> <th>ToMe + xFormers 속도 향상 (%)</th></tr></thead> <tbody><tr><td>512</td> <td>10</td> <td>6.88</td> <td>5.26</td> <td>4.69</td> <td>23.54651163</td> <td>31.83139535</td></tr> <tr><td></td> <td></td> <td></td> <td></td> <td></td> <td></td> <td></td></tr> <tr><td>768</td> <td>10</td> <td>OOM</td> <td>14.71</td> <td>11</td> <td></td> <td></td></tr> <tr><td></td> <td>8</td> <td>OOM</td> <td>11.56</td> <td>8.84</td> <td></td> <td></td></tr> <tr><td></td> <td>4</td> <td>OOM</td> <td>5.98</td> <td>4.66</td> <td></td> <td></td></tr> <tr><td></td> <td>2</td> <td>4.99</td> <td>3.24</td> <td>3.1</td> <td>35.07014028</td> <td>37.8757515</td></tr> <tr><td></td> <td>1</td> <td>3.29</td> <td>2.24</td> <td>2.03</td> <td>31.91489362</td> <td>38.29787234</td></tr> <tr><td></td> <td></td> <td></td> <td></td> <td></td> <td></td> <td></td></tr> <tr><td>1024</td> <td>10</td> <td>OOM</td> <td>OOM</td> <td>OOM</td> <td></td> <td></td></tr> <tr><td></td> <td>8</td> <td>OOM</td> <td>OOM</td> <td>OOM</td> <td></td> <td></td></tr> <tr><td></td> <td>4</td> <td>OOM</td> <td>12.51</td> <td>9.09</td> <td></td> <td></td></tr> <tr><td></td> <td>2</td> <td>OOM</td> <td>6.52</td> <td>4.96</td> <td></td> <td></td></tr> <tr><td></td> <td>1</td> <td>6.4</td> <td>3.61</td> <td>2.81</td> <td>43.59375</td> <td>56.09375</td></tr></tbody>",st,B,Zt="<strong><em>결과는 초 단위입니다. 속도 향상은 <code>Vanilla</code>과 비교해 계산됩니다.</em></strong>",ft,_,pt,U,jt="<thead><tr><th>해상도</th> <th>배치 크기</th> <th>Vanilla</th> <th>ToMe</th> <th>ToMe + xFormers</th> <th>ToMe 속도 향상 (%)</th> <th>ToMe + xFormers 속도 향상 (%)</th></tr></thead> <tbody><tr><td>512</td> <td>10</td> <td>OOM</td> <td>10.03</td> <td>9.29</td> <td></td> <td></td></tr> <tr><td></td> <td>8</td> <td>OOM</td> <td>8.05</td> <td>7.47</td> <td></td> <td></td></tr> <tr><td></td> <td>4</td> <td>5.7</td> <td>4.3</td> <td>3.98</td> <td>24.56140351</td> <td>30.1754386</td></tr> <tr><td></td> <td>2</td> <td>3.14</td> <td>2.43</td> <td>2.27</td> <td>22.61146497</td> <td>27.70700637</td></tr> <tr><td></td> <td>1</td> <td>1.88</td> <td>1.57</td> <td>1.57</td> <td>16.4893617</td> <td>16.4893617</td></tr> <tr><td></td> <td></td> <td></td> <td></td> <td></td> <td></td> <td></td></tr> <tr><td>768</td> <td>10</td> <td>OOM</td> <td>OOM</td> <td>23.67</td> <td></td> <td></td></tr> <tr><td></td> <td>8</td> <td>OOM</td> <td>OOM</td> <td>18.81</td> <td></td> <td></td></tr> <tr><td></td> <td>4</td> <td>OOM</td> <td>11.81</td> <td>9.7</td> <td></td> <td></td></tr> <tr><td></td> <td>2</td> <td>OOM</td> <td>6.27</td> <td>5.2</td> <td></td> <td></td></tr> <tr><td></td> <td>1</td> <td>5.43</td> <td>3.38</td> <td>2.82</td> <td>37.75322284</td> <td>48.06629834</td></tr> <tr><td></td> <td></td> <td></td> <td></td> <td></td> <td></td> <td></td></tr> <tr><td>1024</td> <td>10</td> <td>OOM</td> <td>OOM</td> <td>OOM</td> <td></td> <td></td></tr> <tr><td></td> <td>8</td> <td>OOM</td> <td>OOM</td> <td>OOM</td> <td></td> <td></td></tr> <tr><td></td> <td>4</td> <td>OOM</td> <td>OOM</td> <td>19.35</td> <td></td> <td></td></tr> <tr><td></td> <td>2</td> <td>OOM</td> <td>13</td> <td>10.78</td> <td></td> <td></td></tr> <tr><td></td> <td>1</td> <td>OOM</td> <td>6.66</td> <td>5.54</td> <td></td> <td></td></tr></tbody>",mt,C,kt="위의 표에서 볼 수 있듯이, 이미지 해상도가 높을수록 <code>tomesd</code>를 사용한 속도 향상이 더욱 두드러집니다. 또한 <code>tomesd</code>를 사용하면 1024x1024와 같은 더 높은 해상도에서 파이프라인을 실행할 수 있다는 점도 흥미롭습니다.",Mt,S,Gt='<a href="https://huggingface.co/docs/diffusers/optimization/torch2.0" rel="nofollow"><code>torch.compile()</code></a>을 사용하면 추론 속도를 더욱 높일 수 있습니다.',ut,Z,ht,j,It='As reported in <a href="https://arxiv.org/abs/2303.17604" rel="nofollow">the paper</a>, ToMe can preserve the quality of the generated images to a great extent while speeding up inference. By increasing the <code>ratio</code>, it is possible to further speed up inference, but that might come at the cost of a deterioration in the image quality.',Tt,k,Vt='To test the quality of the generated samples using our setup, we sampled a few prompts from the “Parti Prompts” (introduced in <a href="https://parti.research.google/" rel="nofollow">Parti</a>) and performed inference with the <code>StableDiffusionPipeline</code> in the following settings:',ct,G,Et='<a href="https://arxiv.org/abs/2303.17604" rel="nofollow">논문</a>에 보고된 바와 같이, ToMe는 생성된 이미지의 품질을 상당 부분 보존하면서 추론 속도를 높일 수 있습니다. <code>ratio</code>을 높이면 추론 속도를 더 높일 수 있지만, 이미지 품질이 저하될 수 있습니다.',bt,I,zt='해당 설정을 사용하여 생성된 샘플의 품질을 테스트하기 위해, “Parti 프롬프트”(<a href="https://parti.research.google/" rel="nofollow">Parti</a>에서 소개)에서 몇 가지 프롬프트를 샘플링하고 다음 설정에서 <code>StableDiffusionPipeline</code>을 사용하여 추론을 수행했습니다:',wt,V,Dt="<li>Vanilla <code>StableDiffusionPipeline</code></li> <li><code>StableDiffusionPipeline</code> + ToMe</li> <li><code>StableDiffusionPipeline</code> + ToMe + xformers</li>",vt,E,Ft="생성된 샘플의 품질이 크게 저하되는 것을 발견하지 못했습니다. 다음은 샘플입니다:",gt,z,Nt='<img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/tome/tome_samples.png" alt="tome-samples"/>',$t,D,Wt='생성된 샘플은 <a href="https://wandb.ai/sayakpaul/tomesd-results/runs/23j4bj3i?workspace=" rel="nofollow">여기</a>에서 확인할 수 있습니다. 이 실험을 수행하기 위해 <a href="https://gist.github.com/sayakpaul/8cac98d7f22399085a060992f411ecbd" rel="nofollow">이 스크립트</a>를 사용했습니다.',yt,F,Ot,X,Jt;return T=new N({props:{title:"Token Merging (토큰 병합)",local:"token-merging-토큰-병합",headingTag:"h1"}}),w=new N({props:{title:"ToMe 사용하기",local:"tome-사용하기",headingTag:"h2"}}),g=new At({props:{code:"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",highlighted:`from diffusers import StableDiffusionPipeline
import tomesd

pipeline = StableDiffusionPipeline.from_pretrained(
      &quot;runwayml/stable-diffusion-v1-5&quot;, torch_dtype=torch.float16
).to(&quot;cuda&quot;)
<span class="hljs-addition">+ tomesd.apply_patch(pipeline, ratio=0.5)</span>

image = pipeline(&quot;a photo of an astronaut riding a horse on mars&quot;).images[0]`,wrap:!1}}),O=new N({props:{title:"StableDiffusionPipeline 으로 tomesd 벤치마킹하기",local:"stablediffusionpipeline-으로-tomesd-벤치마킹하기",headingTag:"h2"}}),x=new At({props:{code:"LSUyMCU2MGRpZmZ1c2VycyU2MCUyMHZlcnNpb24lM0ElMjAwLjE1LjElMEEtJTIwUHl0aG9uJTIwdmVyc2lvbiUzQSUyMDMuOC4xNiUwQS0lMjBQeVRvcmNoJTIwdmVyc2lvbiUyMChHUFUlM0YpJTNBJTIwMS4xMy4xJTJCY3UxMTYlMjAoVHJ1ZSklMEEtJTIwSHVnZ2luZ2ZhY2VfaHViJTIwdmVyc2lvbiUzQSUyMDAuMTMuMiUwQS0lMjBUcmFuc2Zvcm1lcnMlMjB2ZXJzaW9uJTNBJTIwNC4yNy4yJTBBLSUyMEFjY2VsZXJhdGUlMjB2ZXJzaW9uJTNBJTIwMC4xOC4wJTBBLSUyMHhGb3JtZXJzJTIwdmVyc2lvbiUzQSUyMDAuMC4xNiUwQS0lMjB0b21lc2QlMjB2ZXJzaW9uJTNBJTIwMC4xLjI=",highlighted:`- \`diffusers\` version: 0.15.1
- Python version: 3.8.16
- PyTorch version (GPU?): 1.13.1+cu116 (True)
- Huggingface_hub version: 0.13.2
- Transformers version: 4.27.2
- Accelerate version: 0.18.0
- xFormers version: 0.0.16
- tomesd version: 0.1.2`,wrap:!1}}),P=new N({props:{title:"A100",local:"a100",headingTag:"h3"}}),_=new N({props:{title:"V100",local:"v100",headingTag:"h3"}}),Z=new N({props:{title:"품질",local:"품질",headingTag:"h2"}}),F=new le({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/ko/optimization/tome.md"}}),{c(){s=n("meta"),q=i(),W=n("p"),A=i(),f(T.$$.fragment),Y=i(),c=n("p"),c.innerHTML=Lt,Q=i(),b=n("p"),b.innerHTML=Pt,R=i(),f(w.$$.fragment),K=i(),v=n("p"),v.innerHTML=Ht,tt=i(),f(g.$$.fragment),et=i(),$=n("p"),$.textContent=Bt,dt=i(),y=n("p"),y.innerHTML=_t,lt=i(),f(O.$$.fragment),it=i(),J=n("p"),J.innerHTML=Ut,ot=i(),f(x.$$.fragment),nt=i(),L=n("p"),L.innerHTML=Ct,rt=i(),f(P.$$.fragment),at=i(),H=n("table"),H.innerHTML=St,st=i(),B=n("p"),B.innerHTML=Zt,ft=i(),f(_.$$.fragment),pt=i(),U=n("table"),U.innerHTML=jt,mt=i(),C=n("p"),C.innerHTML=kt,Mt=i(),S=n("p"),S.innerHTML=Gt,ut=i(),f(Z.$$.fragment),ht=i(),j=n("p"),j.innerHTML=It,Tt=i(),k=n("p"),k.innerHTML=Vt,ct=i(),G=n("p"),G.innerHTML=Et,bt=i(),I=n("p"),I.innerHTML=zt,wt=i(),V=n("ul"),V.innerHTML=Dt,vt=i(),E=n("p"),E.textContent=Ft,gt=i(),z=n("p"),z.innerHTML=Nt,$t=i(),D=n("p"),D.innerHTML=Wt,yt=i(),f(F.$$.fragment),Ot=i(),X=n("p"),this.h()},l(t){const e=ee("svelte-u9bgzb",document.head);s=r(e,"META",{name:!0,content:!0}),e.forEach(d),q=o(t),W=r(t,"P",{}),Xt(W).forEach(d),A=o(t),p(T.$$.fragment,t),Y=o(t),c=r(t,"P",{"data-svelte-h":!0}),a(c)!=="svelte-t5sgvz"&&(c.innerHTML=Lt),Q=o(t),b=r(t,"P",{"data-svelte-h":!0}),a(b)!=="svelte-hk2hfi"&&(b.innerHTML=Pt),R=o(t),p(w.$$.fragment,t),K=o(t),v=r(t,"P",{"data-svelte-h":!0}),a(v)!=="svelte-12otzto"&&(v.innerHTML=Ht),tt=o(t),p(g.$$.fragment,t),et=o(t),$=r(t,"P",{"data-svelte-h":!0}),a($)!=="svelte-1k8jadh"&&($.textContent=Bt),dt=o(t),y=r(t,"P",{"data-svelte-h":!0}),a(y)!=="svelte-1cys8id"&&(y.innerHTML=_t),lt=o(t),p(O.$$.fragment,t),it=o(t),J=r(t,"P",{"data-svelte-h":!0}),a(J)!=="svelte-11ikqbb"&&(J.innerHTML=Ut),ot=o(t),p(x.$$.fragment,t),nt=o(t),L=r(t,"P",{"data-svelte-h":!0}),a(L)!=="svelte-7462bd"&&(L.innerHTML=Ct),rt=o(t),p(P.$$.fragment,t),at=o(t),H=r(t,"TABLE",{"data-svelte-h":!0}),a(H)!=="svelte-1sq5eqd"&&(H.innerHTML=St),st=o(t),B=r(t,"P",{"data-svelte-h":!0}),a(B)!=="svelte-wj7mc7"&&(B.innerHTML=Zt),ft=o(t),p(_.$$.fragment,t),pt=o(t),U=r(t,"TABLE",{"data-svelte-h":!0}),a(U)!=="svelte-db49ae"&&(U.innerHTML=jt),mt=o(t),C=r(t,"P",{"data-svelte-h":!0}),a(C)!=="svelte-1g345nk"&&(C.innerHTML=kt),Mt=o(t),S=r(t,"P",{"data-svelte-h":!0}),a(S)!=="svelte-130oxzi"&&(S.innerHTML=Gt),ut=o(t),p(Z.$$.fragment,t),ht=o(t),j=r(t,"P",{"data-svelte-h":!0}),a(j)!=="svelte-171kjds"&&(j.innerHTML=It),Tt=o(t),k=r(t,"P",{"data-svelte-h":!0}),a(k)!=="svelte-xb1okv"&&(k.innerHTML=Vt),ct=o(t),G=r(t,"P",{"data-svelte-h":!0}),a(G)!=="svelte-48gifm"&&(G.innerHTML=Et),bt=o(t),I=r(t,"P",{"data-svelte-h":!0}),a(I)!=="svelte-q8pz6p"&&(I.innerHTML=zt),wt=o(t),V=r(t,"UL",{"data-svelte-h":!0}),a(V)!=="svelte-nt18e6"&&(V.innerHTML=Dt),vt=o(t),E=r(t,"P",{"data-svelte-h":!0}),a(E)!=="svelte-13iqe5c"&&(E.textContent=Ft),gt=o(t),z=r(t,"P",{"data-svelte-h":!0}),a(z)!=="svelte-121uzx9"&&(z.innerHTML=Nt),$t=o(t),D=r(t,"P",{"data-svelte-h":!0}),a(D)!=="svelte-4mouq"&&(D.innerHTML=Wt),yt=o(t),p(F.$$.fragment,t),Ot=o(t),X=r(t,"P",{}),Xt(X).forEach(d),this.h()},h(){qt(s,"name","hf:doc:metadata"),qt(s,"content",oe)},m(t,e){de(document.head,s),l(t,q,e),l(t,W,e),l(t,A,e),m(T,t,e),l(t,Y,e),l(t,c,e),l(t,Q,e),l(t,b,e),l(t,R,e),m(w,t,e),l(t,K,e),l(t,v,e),l(t,tt,e),m(g,t,e),l(t,et,e),l(t,$,e),l(t,dt,e),l(t,y,e),l(t,lt,e),m(O,t,e),l(t,it,e),l(t,J,e),l(t,ot,e),m(x,t,e),l(t,nt,e),l(t,L,e),l(t,rt,e),m(P,t,e),l(t,at,e),l(t,H,e),l(t,st,e),l(t,B,e),l(t,ft,e),m(_,t,e),l(t,pt,e),l(t,U,e),l(t,mt,e),l(t,C,e),l(t,Mt,e),l(t,S,e),l(t,ut,e),m(Z,t,e),l(t,ht,e),l(t,j,e),l(t,Tt,e),l(t,k,e),l(t,ct,e),l(t,G,e),l(t,bt,e),l(t,I,e),l(t,wt,e),l(t,V,e),l(t,vt,e),l(t,E,e),l(t,gt,e),l(t,z,e),l(t,$t,e),l(t,D,e),l(t,yt,e),m(F,t,e),l(t,Ot,e),l(t,X,e),Jt=!0},p:Qt,i(t){Jt||(M(T.$$.fragment,t),M(w.$$.fragment,t),M(g.$$.fragment,t),M(O.$$.fragment,t),M(x.$$.fragment,t),M(P.$$.fragment,t),M(_.$$.fragment,t),M(Z.$$.fragment,t),M(F.$$.fragment,t),Jt=!0)},o(t){u(T.$$.fragment,t),u(w.$$.fragment,t),u(g.$$.fragment,t),u(O.$$.fragment,t),u(x.$$.fragment,t),u(P.$$.fragment,t),u(_.$$.fragment,t),u(Z.$$.fragment,t),u(F.$$.fragment,t),Jt=!1},d(t){t&&(d(q),d(W),d(A),d(Y),d(c),d(Q),d(b),d(R),d(K),d(v),d(tt),d(et),d($),d(dt),d(y),d(lt),d(it),d(J),d(ot),d(nt),d(L),d(rt),d(at),d(H),d(st),d(B),d(ft),d(pt),d(U),d(mt),d(C),d(Mt),d(S),d(ut),d(ht),d(j),d(Tt),d(k),d(ct),d(G),d(bt),d(I),d(wt),d(V),d(vt),d(E),d(gt),d(z),d($t),d(D),d(yt),d(Ot),d(X)),d(s),h(T,t),h(w,t),h(g,t),h(O,t),h(x,t),h(P,t),h(_,t),h(Z,t),h(F,t)}}}const oe='{"title":"Token Merging (토큰 병합)","local":"token-merging-토큰-병합","sections":[{"title":"ToMe 사용하기","local":"tome-사용하기","sections":[],"depth":2},{"title":"StableDiffusionPipeline 으로 tomesd 벤치마킹하기","local":"stablediffusionpipeline-으로-tomesd-벤치마킹하기","sections":[{"title":"A100","local":"a100","sections":[],"depth":3},{"title":"V100","local":"v100","sections":[],"depth":3}],"depth":2},{"title":"품질","local":"품질","sections":[],"depth":2}],"depth":1}';function ne(xt){return Rt(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class pe extends Kt{constructor(s){super(),te(this,s,ne,ie,Yt,{})}}export{pe as component};