diffusers/pr_12229/pt/_app/immutable/nodes/4.5aed51ff.js

import{s as ct,d as X,j as Ha,u as A,g as R,e as Y,o as Pa,b as Da,n as z,y as Ea,z as Gs}from"../chunks/scheduler.284fc092.js";import{S as mt,i as dt,e as M,a as w,f as V,d as r,k as _,m as c,l as H,B as Ls,t as g,o as b,D as ja,E as ka,x as Fa,s as f,b as p,y as P,w as D,c as Z,j as I,n as N,p as G,q as xa,v as E,r as Xa,u as Aa,z as Zs,A as Ra,h as Ka,g as C}from"../chunks/index.3707479a.js";import{C as Oa,H as ut,E as el}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.24bec0de.js";import{C as B}from"../chunks/CodeBlock.1184f70d.js";import{e as Ns}from"../chunks/each.e59479a4.js";function tl(n){let t,l,a,s,i,o;const d=n[7].default,m=X(d,n,n[6],null);return{c(){t=M("div"),l=M("ul"),m&&m.c(),this.h()},l(h){t=w(h,"DIV",{class:!0});var J=V(t);l=w(J,"UL",{class:!0});var U=V(l);m&&m.l(U),U.forEach(r),J.forEach(r),this.h()},h(){_(l,"class","min-w-full w-auto"),_(t,"class",a="absolute top-full mt-1 min-w-full w-auto bg-white rounded-xl overflow-hidden shadow-lg z-10 border border-gray-100 "+(n[2]==="right"?"right-0":"left-0")+" "+n[0])},m(h,J){c(h,t,J),H(t,l),m&&m.m(l,null),n[8](t),s=!0,i||(o=Ls(t,"click",function(){Ha(n[1])&&n[1].apply(this,arguments)}),i=!0)},p(h,[J]){n=h,m&&m.p&&(!s||J&64)&&A(m,d,n,n[6],s?Y(d,n[6],J,null):R(n[6]),null),(!s||J&5&&a!==(a="absolute top-full mt-1 min-w-full w-auto bg-white rounded-xl overflow-hidden shadow-lg z-10 border border-gray-100 "+(n[2]==="right"?"right-0":"left-0")+" "+n[0]))&&_(t,"class",a)},i(h){s||(g(m,h),s=!0)},o(h){b(m,h),s=!1},d(h){h&&r(t),m&&m.d(h),n[8](null),i=!1,o()}}}function sl(n,t,l){let{$$slots:a={},$$scope:s}=t,{classNames:i=""}=t,{dropdownElement:o=void 0}=t,{forceAlignement:d=void 0}=t,{onClose:m}=t,h=d??"left",J;Pa(()=>{if(document.addEventListener("click",U),!d){const T=document.documentElement.clientWidth,v=J==null?void 0:J.getBoundingClientRect(),j=(v==null?void 0:v.left)??0,q=(v==null?void 0:v.width)??0;l(2,h=j+q>T?"right":"left")}return()=>{document.removeEventListener("click",U)}});function U(T){const v=T.target;v!==o&&!(o!=null&&o.contains(v))&&m(T)}function k(T){Da[T?"unshift":"push"](()=>{J=T,l(3,J)})}return n.$$set=T=>{"classNames"in T&&l(0,i=T.classNames),"dropdownElement"in T&&l(4,o=T.dropdownElement),"forceAlignement"in T&&l(5,d=T.forceAlignement),"onClose"in T&&l(1,m=T.onClose),"$$scope"in T&&l(6,s=T.$$scope)},[i,m,h,J,o,d,s,a,k]}class al extends mt{constructor(t){super(),dt(this,t,sl,tl,ct,{classNames:0,dropdownElement:4,forceAlignement:5,onClose:1})}}function ll(n){let t,l;return{c(){t=ja("svg"),l=ja("path"),this.h()},l(a){t=ka(a,"svg",{class:!0,xmlns:!0,"xmlns:xlink":!0,"aria-hidden":!0,focusable:!0,role:!0,width:!0,height:!0,preserveAspectRatio:!0,viewBox:!0,style:!0});var s=V(t);l=ka(s,"path",{d:!0,fill:!0}),V(l).forEach(r),s.forEach(r),this.h()},h(){_(l,"d","M7 10l5 5l5-5z"),_(l,"fill","currentColor"),_(t,"class",n[0]),_(t,"xmlns","http://www.w3.org/2000/svg"),_(t,"xmlns:xlink","http://www.w3.org/1999/xlink"),_(t,"aria-hidden","true"),_(t,"focusable","false"),_(t,"role","img"),_(t,"width","1em"),_(t,"height","1em"),_(t,"preserveAspectRatio","xMidYMid meet"),_(t,"viewBox","0 0 24 24"),Fa(t,"transform","rotate(360deg)")},m(a,s){c(a,t,s),H(t,l)},p(a,[s]){s&1&&_(t,"class",a[0])},i:z,o:z,d(a){a&&r(t)}}}function nl(n,t,l){let{classNames:a=""}=t;return n.$$set=s=>{"classNames"in s&&l(0,a=s.classNames)},[a]}class ol extends mt{constructor(t){super(),dt(this,t,nl,ll,ct,{classNames:0})}}const il=n=>({}),Ca=n=>({}),rl=n=>({}),Ua=n=>({});function ul(n){let t,l,a,s,i,o=n[2]&&Ta(n),d=n[9]&&Ja();return{c(){o&&o.c(),t=f(),l=xa(n[4]),a=f(),d&&d.c(),s=E()},l(m){o&&o.l(m),t=p(m),l=Xa(m,n[4]),a=p(m),d&&d.l(m),s=E()},m(m,h){o&&o.m(m,h),c(m,t,h),c(m,l,h),c(m,a,h),d&&d.m(m,h),c(m,s,h),i=!0},p(m,h){m[2]?o?(o.p(m,h),h&4&&g(o,1)):(o=Ta(m),o.c(),g(o,1),o.m(t.parentNode,t)):o&&(P(),b(o,1,1,()=>{o=null}),D()),(!i||h&16)&&Aa(l,m[4]),m[9]?d?h&512&&g(d,1):(d=Ja(),d.c(),g(d,1),d.m(s.parentNode,s)):d&&(P(),b(d,1,1,()=>{d=null}),D())},i(m){i||(g(o),g(d),i=!0)},o(m){b(o),b(d),i=!1},d(m){m&&(r(t),r(l),r(a),r(s)),o&&o.d(m),d&&d.d(m)}}}function cl(n){let t;const l=n[15].button,a=X(l,n,n[18],Ua);return{c(){a&&a.c()},l(s){a&&a.l(s)},m(s,i){a&&a.m(s,i),t=!0},p(s,i){a&&a.p&&(!t||i&262144)&&A(a,l,s,s[18],t?Y(l,s[18],i,rl):R(s[18]),Ua)},i(s){t||(g(a,s),t=!0)},o(s){b(a,s),t=!1},d(s){a&&a.d(s)}}}function Ta(n){let t,l,a;var s=n[2];function i(o,d){return{props:{classNames:"mr-1.5 "+o[3]}}}return s&&(t=Zs(s,i(n))),{c(){t&&Z(t.$$.fragment),l=E()},l(o){t&&I(t.$$.fragment,o),l=E()},m(o,d){t&&N(t,o,d),c(o,l,d),a=!0},p(o,d){if(d&4&&s!==(s=o[2])){if(t){P();const m=t;b(m.$$.fragment,1,0,()=>{G(m,1)}),D()}s?(t=Zs(s,i(o)),Z(t.$$.fragment),g(t.$$.fragment,1),N(t,l.parentNode,l)):t=null}else if(s){const m={};d&8&&(m.classNames="mr-1.5 "+o[3]),t.$set(m)}},i(o){a||(t&&g(t.$$.fragment,o),a=!0)},o(o){t&&b(t.$$.fragment,o),a=!1},d(o){o&&r(l),t&&G(t,o)}}}function Ja(n){let t,l;return t=new ol({props:{classNames:"-mr-1 text-gray-500"}}),{c(){Z(t.$$.fragment)},l(a){I(t.$$.fragment,a)},m(a,s){N(t,a,s),l=!0},i(a){l||(g(t.$$.fragment,a),l=!0)},o(a){b(t.$$.fragment,a),l=!1},d(a){G(t,a)}}}function qa(n){let t,l;return t=new al({props:{classNames:n[6]+" "+(n[8]?"v2-dropdown-menu hidden":""),dropdownElement:n[10],forceAlignement:n[5],onClose:n[12],$$slots:{default:[ml]},$$scope:{ctx:n}}}),{c(){Z(t.$$.fragment)},l(a){I(t.$$.fragment,a)},m(a,s){N(t,a,s),l=!0},p(a,s){const i={};s&320&&(i.classNames=a[6]+" "+(a[8]?"v2-dropdown-menu hidden":"")),s&1024&&(i.dropdownElement=a[10]),s&32&&(i.forceAlignement=a[5]),s&262144&&(i.$$scope={dirty:s,ctx:a}),t.$set(i)},i(a){l||(g(t.$$.fragment,a),l=!0)},o(a){b(t.$$.fragment,a),l=!1},d(a){G(t,a)}}}function ml(n){let t;const l=n[15].menu,a=X(l,n,n[18],Ca);return{c(){a&&a.c()},l(s){a&&a.l(s)},m(s,i){a&&a.m(s,i),t=!0},p(s,i){a&&a.p&&(!t||i&262144)&&A(a,l,s,s[18],t?Y(l,s[18],i,il):R(s[18]),Ca)},i(s){t||(g(a,s),t=!0)},o(s){b(a,s),t=!1},d(s){a&&a.d(s)}}}function dl(n){let t,l,a,s,i,o,d,m,h,J;const U=[cl,ul],k=[];function T(j,q){return j[13].button?0:1}a=T(n),s=k[a]=U[a](n);let v=(n[11]||n[8])&&qa(n);return{c(){t=M("div"),l=M("button"),s.c(),o=f(),v&&v.c(),this.h()},l(j){t=w(j,"DIV",{class:!0});var q=V(t);l=w(q,"BUTTON",{class:!0,type:!0});var W=V(l);s.l(W),W.forEach(r),o=p(q),v&&v.l(q),q.forEach(r),this.h()},h(){_(l,"class",i=""+n[1]+" "+(n[7]?"":"cursor-pointer w-full btn text-sm")+" "+(n[8]?"v2-dropdown-button":"")),_(l,"type","button"),_(t,"class",d="relative "+n[0]+" "+(n[8]?"v2-dropdown":""))},m(j,q){c(j,t,q),H(t,l),k[a].m(l,null),H(t,o),v&&v.m(t,null),n[17](t),m=!0,h||(J=Ls(l,"click",n[16]),h=!0)},p(j,[q]){let W=a;a=T(j),a===W?k[a].p(j,q):(P(),b(k[W],1,1,()=>{k[W]=null}),D(),s=k[a],s?s.p(j,q):(s=k[a]=U[a](j),s.c()),g(s,1),s.m(l,null)),(!m||q&386&&i!==(i=""+j[1]+" "+(j[7]?"":"cursor-pointer w-full btn text-sm")+" "+(j[8]?"v2-dropdown-button":"")))&&_(l,"class",i),j[11]||j[8]?v?(v.p(j,q),q&2304&&g(v,1)):(v=qa(j),v.c(),g(v,1),v.m(t,null)):v&&(P(),b(v,1,1,()=>{v=null}),D()),(!m||q&257&&d!==(d="relative "+j[0]+" "+(j[8]?"v2-dropdown":"")))&&_(t,"class",d)},i(j){m||(g(s),g(v),m=!0)},o(j){b(s),b(v),m=!1},d(j){j&&r(t),k[a].d(),v&&v.d(),n[17](null),h=!1,J()}}}function fl(n,t,l){let{$$slots:a={},$$scope:s}=t;const i=Ea(a);let{classNames:o=""}=t,{btnClassNames:d=""}=t,{btnIcon:m=void 0}=t,{btnIconClassNames:h=""}=t,{btnLabel:J=""}=t,{forceMenuAlignement:U=void 0}=t,{menuClassNames:k=""}=t,{noBtnClass:T=void 0}=t,{selectedValue:v=void 0}=t,{useDeprecatedJS:j=!0}=t,{withBtnCaret:q=!1}=t,W,L=!1;function y(S){var $;S.target&&($=S.target)!=null&&$.className.includes("do-not-close-dropdown")||l(11,L=!1)}const x=()=>l(11,L=!L);function pt(S){Da[S?"unshift":"push"](()=>{W=S,l(10,W)})}return n.$$set=S=>{"classNames"in S&&l(0,o=S.classNames),"btnClassNames"in S&&l(1,d=S.btnClassNames),"btnIcon"in S&&l(2,m=S.btnIcon),"btnIconClassNames"in S&&l(3,h=S.btnIconClassNames),"btnLabel"in S&&l(4,J=S.btnLabel),"forceMenuAlignement"in S&&l(5,U=S.forceMenuAlignement),"menuClassNames"in S&&l(6,k=S.menuClassNames),"noBtnClass"in S&&l(7,T=S.noBtnClass),"selectedValue"in S&&l(14,v=S.selectedValue),"useDeprecatedJS"in S&&l(8,j=S.useDeprecatedJS),"withBtnCaret"in S&&l(9,q=S.withBtnCaret),"$$scope"in S&&l(18,s=S.$$scope)},[o,d,m,h,J,U,k,T,j,q,W,L,y,i,v,a,x,pt,s]}class Ya extends mt{constructor(t){super(),dt(this,t,fl,dl,ct,{classNames:0,btnClassNames:1,btnIcon:2,btnIconClassNames:3,btnLabel:4,forceMenuAlignement:5,menuClassNames:6,noBtnClass:7,selectedValue:14,useDeprecatedJS:8,withBtnCaret:9})}}function pl(n){let t,l,a,s=n[5]&&Za(n);return{c(){s&&s.c(),t=f(),l=xa(n[7])},l(i){s&&s.l(i),t=p(i),l=Xa(i,n[7])},m(i,o){s&&s.m(i,o),c(i,t,o),c(i,l,o),a=!0},p(i,o){i[5]?s?(s.p(i,o),o&32&&g(s,1)):(s=Za(i),s.c(),g(s,1),s.m(t.parentNode,t)):s&&(P(),b(s,1,1,()=>{s=null}),D()),(!a||o&128)&&Aa(l,i[7])},i(i){a||(g(s),a=!0)},o(i){b(s),a=!1},d(i){i&&(r(t),r(l)),s&&s.d(i)}}}function gl(n){let t;const l=n[15].default,a=X(l,n,n[14],null);return{c(){a&&a.c()},l(s){a&&a.l(s)},m(s,i){a&&a.m(s,i),t=!0},p(s,i){a&&a.p&&(!t||i&16384)&&A(a,l,s,s[14],t?Y(l,s[14],i,null):R(s[14]),null)},i(s){t||(g(a,s),t=!0)},o(s){b(a,s),t=!1},d(s){a&&a.d(s)}}}function Za(n){let t,l,a;var s=n[5];function i(o,d){return{props:{classNames:"mr-1.5 "+o[6]}}}return s&&(t=Zs(s,i(n))),{c(){t&&Z(t.$$.fragment),l=E()},l(o){t&&I(t.$$.fragment,o),l=E()},m(o,d){t&&N(t,o,d),c(o,l,d),a=!0},p(o,d){if(d&32&&s!==(s=o[5])){if(t){P();const m=t;b(m.$$.fragment,1,0,()=>{G(m,1)}),D()}s?(t=Zs(s,i(o)),Z(t.$$.fragment),g(t.$$.fragment,1),N(t,l.parentNode,l)):t=null}else if(s){const m={};d&64&&(m.classNames="mr-1.5 "+o[6]),t.$set(m)}},i(o){a||(t&&g(t.$$.fragment,o),a=!0)},o(o){t&&b(t.$$.fragment,o),a=!1},d(o){o&&r(l),t&&G(t,o)}}}function hl(n){let t,l,a,s,i,o,d,m,h,J;const U=[gl,pl],k=[];function T(v,j){return v[13].default?0:1}return a=T(n),s=k[a]=U[a](n),{c(){t=M("li"),l=M("a"),s.c(),this.h()},l(v){t=w(v,"LI",{class:!0});var j=V(t);l=w(j,"A",{class:!0,"data-label":!0,"data-url":!0,"data-value":!0,href:!0,rel:!0,target:!0});var q=V(l);s.l(q),q.forEach(r),j.forEach(r),this.h()},h(){_(l,"class",i="flex items-center hover:bg-gray-50 dark:hover:bg-gray-800 cursor-pointer px-3 py-1.5 whitespace-nowrap "+n[0]+" "+(n[9]?"hover:underline":"")+" "+(n[12]?"v2-dropdown-entry":"")),_(l,"data-label",n[1]),_(l,"data-url",n[2]),_(l,"data-value",n[3]),_(l,"href",n[4]),_(l,"rel",o=n[8]?"nofollow":void 0),_(l,"target",d=n[11]?"_blank":void 0),_(t,"class","not-prose")},m(v,j){c(v,t,j),H(t,l),k[a].m(l,null),m=!0,h||(J=Ls(l,"click",function(){Ha(n[10])&&n[10].apply(this,arguments)}),h=!0)},p(v,[j]){n=v;let q=a;a=T(n),a===q?k[a].p(n,j):(P(),b(k[q],1,1,()=>{k[q]=null}),D(),s=k[a],s?s.p(n,j):(s=k[a]=U[a](n),s.c()),g(s,1),s.m(l,null)),(!m||j&4609&&i!==(i="flex items-center hover:bg-gray-50 dark:hover:bg-gray-800 cursor-pointer px-3 py-1.5 whitespace-nowrap "+n[0]+" "+(n[9]?"hover:underline":"")+" "+(n[12]?"v2-dropdown-entry":"")))&&_(l,"class",i),(!m||j&2)&&_(l,"data-label",n[1]),(!m||j&4)&&_(l,"data-url",n[2]),(!m||j&8)&&_(l,"data-value",n[3]),(!m||j&16)&&_(l,"href",n[4]),(!m||j&256&&o!==(o=n[8]?"nofollow":void 0))&&_(l,"rel",o),(!m||j&2048&&d!==(d=n[11]?"_blank":void 0))&&_(l,"target",d)},i(v){m||(g(s),m=!0)},o(v){b(s),m=!1},d(v){v&&r(t),k[a].d(),h=!1,J()}}}function bl(n,t,l){let{$$slots:a={},$$scope:s}=t;const i=Ea(a);let{classNames:o=""}=t,{dataLabel:d=void 0}=t,{dataUrl:m=void 0}=t,{dataValue:h=void 0}=t,{href:J=void 0}=t,{icon:U=void 0}=t,{iconClassNames:k=""}=t,{label:T=""}=t,{noFollow:v=!1}=t,{underline:j=!1}=t,{onClick:q=()=>{}}=t,{targetBlank:W=!1}=t,{useDeprecatedJS:L=!0}=t;return n.$$set=y=>{"classNames"in y&&l(0,o=y.classNames),"dataLabel"in y&&l(1,d=y.dataLabel),"dataUrl"in y&&l(2,m=y.dataUrl),"dataValue"in y&&l(3,h=y.dataValue),"href"in y&&l(4,J=y.href),"icon"in y&&l(5,U=y.icon),"iconClassNames"in y&&l(6,k=y.iconClassNames),"label"in y&&l(7,T=y.label),"noFollow"in y&&l(8,v=y.noFollow),"underline"in y&&l(9,j=y.underline),"onClick"in y&&l(10,q=y.onClick),"targetBlank"in y&&l(11,W=y.targetBlank),"useDeprecatedJS"in y&&l(12,L=y.useDeprecatedJS),"$$scope"in y&&l(14,s=y.$$scope)},[o,d,m,h,J,U,k,T,v,j,q,W,L,i,s,a]}class Qa extends mt{constructor(t){super(),dt(this,t,bl,hl,ct,{classNames:0,dataLabel:1,dataUrl:2,dataValue:3,href:4,icon:5,iconClassNames:6,label:7,noFollow:8,underline:9,onClick:10,targetBlank:11,useDeprecatedJS:12})}}const _l=n=>({}),Na=n=>({slot:"button"});function Ga(n,t,l){const a=n.slice();return a[9]=t[l].label,a[10]=t[l].value,a}const Ml=n=>({}),La=n=>({slot:"menu"}),wl=n=>({}),Ia=n=>({slot:"button"});function Sa(n,t,l){const a=n.slice();return a[9]=t[l].label,a[10]=t[l].value,a}const vl=n=>({}),Wa=n=>({slot:"menu"}),yl=n=>({}),Ba=n=>({});function jl(n){let t,l;return t=new Ya({props:{btnLabel:"",classNames:"colab-dropdown",noBtnClass:!0,useDeprecatedJS:!1,$$slots:{menu:[Jl],button:[Ul]},$$scope:{ctx:n}}}),{c(){Z(t.$$.fragment)},l(a){I(t.$$.fragment,a)},m(a,s){N(t,a,s),l=!0},p(a,s){const i={};s&256&&(i.$$scope={dirty:s,ctx:a}),t.$set(i)},i(a){l||(g(t.$$.fragment,a),l=!0)},o(a){b(t.$$.fragment,a),l=!1},d(a){G(t,a)}}}function kl(n){let t,l,a;return{c(){t=M("a"),l=M("img"),this.h()},l(s){t=w(s,"A",{href:!0,target:!0});var i=V(t);l=w(i,"IMG",{alt:!0,class:!0,src:!0}),i.forEach(r),this.h()},h(){_(l,"alt","Open In Colab"),_(l,"class","!m-0"),Gs(l.src,a="https://colab.research.google.com/assets/colab-badge.svg")||_(l,"src",a),_(t,"href",n[2][0].value),_(t,"target","_blank")},m(s,i){c(s,t,i),H(t,l)},p:z,i:z,o:z,d(s){s&&r(t)}}}function Cl(n){let t,l;return{c(){t=M("img"),this.h()},l(a){t=w(a,"IMG",{alt:!0,class:!0,src:!0}),this.h()},h(){_(t,"alt","Open In Colab"),_(t,"class","!m-0"),Gs(t.src,l="https://colab.research.google.com/assets/colab-badge.svg")||_(t,"src",l)},m(a,s){c(a,t,s)},p:z,d(a){a&&r(t)}}}function Ul(n){let t;const l=n[5].default,a=X(l,n,n[8],Ia),s=a||Cl();return{c(){s&&s.c()},l(i){s&&s.l(i)},m(i,o){s&&s.m(i,o),t=!0},p(i,o){a&&a.p&&(!t||o&256)&&A(a,l,i,i[8],t?Y(l,i[8],o,wl):R(i[8]),Ia)},i(i){t||(g(s,i),t=!0)},o(i){b(s,i),t=!1},d(i){s&&s.d(i)}}}function Va(n){let t,l;function a(){return n[6](n[10])}return t=new Qa({props:{classNames:"text-sm !no-underline",iconClassNames:"text-gray-500",label:n[9],onClick:a,useDeprecatedJS:!1}}),{c(){Z(t.$$.fragment)},l(s){I(t.$$.fragment,s)},m(s,i){N(t,s,i),l=!0},p(s,i){n=s},i(s){l||(g(t.$$.fragment,s),l=!0)},o(s){b(t.$$.fragment,s),l=!1},d(s){G(t,s)}}}function Tl(n){let t,l,a=Ns(n[2]),s=[];for(let o=0;o<a.length;o+=1)s[o]=Va(Sa(n,a,o));const i=o=>b(s[o],1,1,()=>{s[o]=null});return{c(){for(let o=0;o<s.length;o+=1)s[o].c();t=E()},l(o){for(let d=0;d<s.length;d+=1)s[d].l(o);t=E()},m(o,d){for(let m=0;m<s.length;m+=1)s[m]&&s[m].m(o,d);c(o,t,d),l=!0},p(o,d){if(d&4){a=Ns(o[2]);let m;for(m=0;m<a.length;m+=1){const h=Sa(o,a,m);s[m]?(s[m].p(h,d),g(s[m],1)):(s[m]=Va(h),s[m].c(),g(s[m],1),s[m].m(t.parentNode,t))}for(P(),m=a.length;m<s.length;m+=1)i(m);D()}},i(o){if(!l){for(let d=0;d<a.length;d+=1)g(s[d]);l=!0}},o(o){s=s.filter(Boolean);for(let d=0;d<s.length;d+=1)b(s[d]);l=!1},d(o){o&&r(t),Ra(s,o)}}}function Jl(n){let t;const l=n[5].default,a=X(l,n,n[8],Wa),s=a||Tl(n);return{c(){s&&s.c()},l(i){s&&s.l(i)},m(i,o){s&&s.m(i,o),t=!0},p(i,o){a&&a.p&&(!t||o&256)&&A(a,l,i,i[8],t?Y(l,i[8],o,vl):R(i[8]),Wa)},i(i){t||(g(s,i),t=!0)},o(i){b(s,i),t=!1},d(i){s&&s.d(i)}}}function ql(n){let t,l;return t=new Ya({props:{btnLabel:"",classNames:"colab-dropdown",noBtnClass:!0,useDeprecatedJS:!1,$$slots:{menu:[Il],button:[Gl]},$$scope:{ctx:n}}}),{c(){Z(t.$$.fragment)},l(a){I(t.$$.fragment,a)},m(a,s){N(t,a,s),l=!0},p(a,s){const i={};s&256&&(i.$$scope={dirty:s,ctx:a}),t.$set(i)},i(a){l||(g(t.$$.fragment,a),l=!0)},o(a){b(t.$$.fragment,a),l=!1},d(a){G(t,a)}}}function Zl(n){let t,l,a;return{c(){t=M("a"),l=M("img"),this.h()},l(s){t=w(s,"A",{href:!0,target:!0});var i=V(t);l=w(i,"IMG",{alt:!0,class:!0,src:!0}),i.forEach(r),this.h()},h(){_(l,"alt","Open In Studio Lab"),_(l,"class","!m-0"),Gs(l.src,a="https://studiolab.sagemaker.aws/studiolab.svg")||_(l,"src",a),_(t,"href",n[3][0].value),_(t,"target","_blank")},m(s,i){c(s,t,i),H(t,l)},p:z,i:z,o:z,d(s){s&&r(t)}}}function Nl(n){let t,l;return{c(){t=M("img"),this.h()},l(a){t=w(a,"IMG",{alt:!0,class:!0,src:!0}),this.h()},h(){_(t,"alt","Open In Studio Lab"),_(t,"class","!m-0"),Gs(t.src,l="https://studiolab.sagemaker.aws/studiolab.svg")||_(t,"src",l)},m(a,s){c(a,t,s)},p:z,d(a){a&&r(t)}}}function Gl(n){let t;const l=n[5].default,a=X(l,n,n[8],Na),s=a||Nl();return{c(){s&&s.c()},l(i){s&&s.l(i)},m(i,o){s&&s.m(i,o),t=!0},p(i,o){a&&a.p&&(!t||o&256)&&A(a,l,i,i[8],t?Y(l,i[8],o,_l):R(i[8]),Na)},i(i){t||(g(s,i),t=!0)},o(i){b(s,i),t=!1},d(i){s&&s.d(i)}}}function $a(n){let t,l;function a(){return n[7](n[10])}return t=new Qa({props:{classNames:"text-sm !no-underline",iconClassNames:"text-gray-500",label:n[9],onClick:a,useDeprecatedJS:!1}}),{c(){Z(t.$$.fragment)},l(s){I(t.$$.fragment,s)},m(s,i){N(t,s,i),l=!0},p(s,i){n=s},i(s){l||(g(t.$$.fragment,s),l=!0)},o(s){b(t.$$.fragment,s),l=!1},d(s){G(t,s)}}}function Ll(n){let t,l,a=Ns(n[3]),s=[];for(let o=0;o<a.length;o+=1)s[o]=$a(Ga(n,a,o));const i=o=>b(s[o],1,1,()=>{s[o]=null});return{c(){for(let o=0;o<s.length;o+=1)s[o].c();t=E()},l(o){for(let d=0;d<s.length;d+=1)s[d].l(o);t=E()},m(o,d){for(let m=0;m<s.length;m+=1)s[m]&&s[m].m(o,d);c(o,t,d),l=!0},p(o,d){if(d&8){a=Ns(o[3]);let m;for(m=0;m<a.length;m+=1){const h=Ga(o,a,m);s[m]?(s[m].p(h,d),g(s[m],1)):(s[m]=$a(h),s[m].c(),g(s[m],1),s[m].m(t.parentNode,t))}for(P(),m=a.length;m<s.length;m+=1)i(m);D()}},i(o){if(!l){for(let d=0;d<a.length;d+=1)g(s[d]);l=!0}},o(o){s=s.filter(Boolean);for(let d=0;d<s.length;d+=1)b(s[d]);l=!1},d(o){o&&r(t),Ra(s,o)}}}function Il(n){let t;const l=n[5].default,a=X(l,n,n[8],La),s=a||Ll(n);return{c(){s&&s.c()},l(i){s&&s.l(i)},m(i,o){s&&s.m(i,o),t=!0},p(i,o){a&&a.p&&(!t||o&256)&&A(a,l,i,i[8],t?Y(l,i[8],o,Ml):R(i[8]),La)},i(i){t||(g(s,i),t=!0)},o(i){b(s,i),t=!1},d(i){s&&s.d(i)}}}function Sl(n){let t,l,a,s,i,o,d,m,h;const J=n[5].alwaysVisible,U=X(J,n,n[8],Ba),k=[kl,jl],T=[];function v(L,y){return L[2].length===1?0:L[2].length>1?1:-1}~(a=v(n))&&(s=T[a]=k[a](n));const j=[Zl,ql],q=[];function W(L,y){return L[3].length===1?0:L[3].length>1?1:-1}return~(o=W(n))&&(d=q[o]=j[o](n)),{c(){t=M("div"),U&&U.c(),l=f(),s&&s.c(),i=f(),d&&d.c(),this.h()},l(L){t=w(L,"DIV",{class:!0,style:!0});var y=V(t);U&&U.l(y),l=p(y),s&&s.l(y),i=p(y),d&&d.l(y),y.forEach(r),this.h()},h(){_(t,"class",m="flex space-x-1 "+n[0]),_(t,"style",n[1])},m(L,y){c(L,t,y),U&&U.m(t,null),H(t,l),~a&&T[a].m(t,null),H(t,i),~o&&q[o].m(t,null),h=!0},p(L,[y]){U&&U.p&&(!h||y&256)&&A(U,J,L,L[8],h?Y(J,L[8],y,yl):R(L[8]),Ba),s&&s.p(L,y),d&&d.p(L,y),(!h||y&1&&m!==(m="flex space-x-1 "+L[0]))&&_(t,"class",m),(!h||y&2)&&_(t,"style",L[1])},i(L){h||(g(U,L),g(s),g(d),h=!0)},o(L){b(U,L),b(s),b(d),h=!1},d(L){L&&r(t),U&&U.d(L),~a&&T[a].d(),~o&&q[o].d()}}}function za(n){window.open(n)}function Wl(n,t,l){let{$$slots:a={},$$scope:s}=t,{options:i=[]}=t,{classNames:o=""}=t,{containerStyle:d=""}=t;const m=i.filter(k=>k.value.includes("colab.research.google.com")),h=i.filter(k=>k.value.includes("studiolab.sagemaker.aws")),J=k=>za(k),U=k=>za(k);return n.$$set=k=>{"options"in k&&l(4,i=k.options),"classNames"in k&&l(0,o=k.classNames),"containerStyle"in k&&l(1,d=k.containerStyle),"$$scope"in k&&l(8,s=k.$$scope)},[o,d,m,h,i,a,J,U,s]}class Bl extends mt{constructor(t){super(),dt(this,t,Wl,Sl,ct,{options:4,classNames:0,containerStyle:1})}}function Vl(n){let t,l,a,s,i,o,d,m,h,J,U,k="Modelos de difusão são treinados para remover o ruído Gaussiano aleatório passo a passo para gerar uma amostra de interesse, como uma imagem ou áudio. Isso despertou um tremendo interesse em IA generativa, e você provavelmente já viu exemplos de imagens geradas por difusão na internet. 🧨 Diffusers é uma biblioteca que visa tornar os modelos de difusão amplamente acessíveis a todos.",T,v,j="Seja você um desenvolvedor ou um usuário, esse tour rápido irá introduzir você ao 🧨 Diffusers e ajudar você a começar a gerar rapidamente! Há três componentes principais da biblioteca para conhecer:",q,W,L='<li>O <code>DiffusionPipeline</code> é uma classe de alto nível de ponta a ponta desenhada para gerar rapidamente amostras de modelos de difusão pré-treinados para inferência.</li> <li><a href="./api/models">Modelos</a> pré-treinados populares e módulos que podem ser usados como blocos de construção para criar sistemas de difusão.</li> <li>Vários <a href="./api/schedulers/overview">Agendadores</a> diferentes - algoritmos que controlam como o ruído é adicionado para treinamento, e como gerar imagens sem o ruído durante a inferência.</li>',y,x,pt="Esse tour rápido mostrará como usar o <code>DiffusionPipeline</code> para inferência, e então mostrará como combinar um modelo e um agendador para replicar o que está acontecendo dentro do <code>DiffusionPipeline</code>.",S,$,Is='<p>Esse tour rápido é uma versão simplificada da introdução 🧨 Diffusers <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb" rel="nofollow">notebook</a> para ajudar você a começar rápido. Se você quer aprender mais sobre o objetivo do 🧨 Diffusers, filosofia de design, e detalhes adicionais sobre a API principal, veja o notebook!</p>',gt,te,Ss="Antes de começar, certifique-se de ter todas as bibliotecas necessárias instaladas:",ht,se,bt,ae,Ws='<li><a href="https://huggingface.co/docs/accelerate/index" rel="nofollow">🤗 Accelerate</a> acelera o carregamento do modelo para geração e treinamento.</li> <li><a href="https://huggingface.co/docs/transformers/index" rel="nofollow">🤗 Transformers</a> é necessário para executar os modelos mais populares de difusão, como o <a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview" rel="nofollow">Stable Diffusion</a>.</li>',_t,le,Mt,ne,Bs='O <code>DiffusionPipeline</code> é a forma mais fácil de usar um sistema de difusão pré-treinado para geração. É um sistema de ponta a ponta contendo o modelo e o agendador. Você pode usar o <code>DiffusionPipeline</code> pronto para muitas tarefas. Dê uma olhada na tabela abaixo para algumas tarefas suportadas, e para uma lista completa de tarefas suportadas, veja a tabela <a href="./api/pipelines/overview#diffusers-summary">Resumo do 🧨 Diffusers</a>.',wt,oe,Vs='<thead><tr><th><strong>Tarefa</strong></th> <th><strong>Descrição</strong></th> <th><strong>Pipeline</strong></th></tr></thead> <tbody><tr><td>Unconditional Image Generation</td> <td>gera uma imagem a partir do ruído Gaussiano</td> <td><a href="./using-diffusers/unconditional_image_generation">unconditional_image_generation</a></td></tr> <tr><td>Text-Guided Image Generation</td> <td>gera uma imagem a partir de um prompt de texto</td> <td><a href="./using-diffusers/conditional_image_generation">conditional_image_generation</a></td></tr> <tr><td>Text-Guided Image-to-Image Translation</td> <td>adapta uma imagem guiada por um prompt de texto</td> <td><a href="./using-diffusers/img2img">img2img</a></td></tr> <tr><td>Text-Guided Image-Inpainting</td> <td>preenche a parte da máscara da imagem, dado a imagem, a máscara e o prompt de texto</td> <td><a href="./using-diffusers/inpaint">inpaint</a></td></tr> <tr><td>Text-Guided Depth-to-Image Translation</td> <td>adapta as partes de uma imagem guiada por um prompt de texto enquanto preserva a estrutura por estimativa de profundidade</td> <td><a href="./using-diffusers/depth2img">depth2img</a></td></tr></tbody>',vt,ie,$s=`Comece criando uma instância do <code>DiffusionPipeline</code> e especifique qual checkpoint do pipeline você gostaria de baixar.
Você pode usar o <code>DiffusionPipeline</code> para qualquer <a href="https://huggingface.co/models?library=diffusers&amp;sort=downloads" rel="nofollow">checkpoint</a> armazenado no Hugging Face Hub.
Nesse quicktour, você carregará o checkpoint <a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow"><code>stable-diffusion-v1-5</code></a> para geração de texto para imagem.`,yt,Q,zs='<p>Para os modelos de <a href="https://huggingface.co/CompVis/stable-diffusion" rel="nofollow">Stable Diffusion</a>, por favor leia cuidadosamente a <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" rel="nofollow">licença</a> primeiro antes de rodar o modelo. 🧨 Diffusers implementa uma verificação de segurança: <a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py" rel="nofollow"><code>safety_checker</code></a> para prevenir conteúdo ofensivo ou nocivo, mas as capacidades de geração de imagem aprimorada do modelo podem ainda produzir conteúdo potencialmente nocivo.</p>',jt,re,Hs="Para carregar o modelo com o método <code>from_pretrained()</code>:",kt,ue,Ct,ce,Ps="O <code>DiffusionPipeline</code> baixa e armazena em cache todos os componentes de modelagem, tokenização, e agendamento. Você verá que o pipeline do Stable Diffusion é composto pelo <code>UNet2DConditionModel</code> e <code>PNDMScheduler</code> entre outras coisas:",Ut,me,Tt,de,Ds=`Nós fortemente recomendamos rodar o pipeline em uma placa de vídeo, pois o modelo consiste em aproximadamente 1.4 bilhões de parâmetros.
Você pode mover o objeto gerador para uma placa de vídeo, assim como você faria no PyTorch:`,Jt,fe,qt,pe,Es='Agora você pode passar o prompt de texto para o <code>pipeline</code> para gerar uma imagem, e então acessar a imagem sem ruído. Por padrão, a saída da imagem é embrulhada em um objeto <a href="https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class" rel="nofollow"><code>PIL.Image</code></a>.',Zt,ge,Nt,F,xs='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/image_of_squirrel_painting.png"/>',Gt,he,Xs="Salve a imagem chamando o <code>save</code>:",Lt,be,It,_e,St,Me,As="Você também pode utilizar o pipeline localmente. A única diferença é que você precisa baixar os pesos primeiro:",Wt,we,Bt,ve,Rs="Assim carregue os pesos salvos no pipeline:",Vt,ye,$t,je,Ys="Agora você pode rodar o pipeline como você faria na seção acima.",zt,ke,Ht,Ce,Qs="Agendadores diferentes tem diferentes velocidades de retirar o ruído e compensações de qualidade. A melhor forma de descobrir qual funciona melhor para você é testar eles! Uma das principais características do 🧨 Diffusers é permitir que você troque facilmente entre agendadores. Por exemplo, para substituir o <code>PNDMScheduler</code> padrão com o <code>EulerDiscreteScheduler</code>, carregue ele com o método <code>from_config()</code>:",Pt,Ue,Dt,Te,Fs="Tente gerar uma imagem com o novo agendador e veja se você nota alguma diferença!",Et,Je,Ks="Na próxima seção, você irá dar uma olhada mais de perto nos componentes - o modelo e o agendador - que compõe o <code>DiffusionPipeline</code> e aprender como usar esses componentes para gerar uma imagem de um gato.",xt,qe,Xt,Ze,Os='A maioria dos modelos recebe uma amostra de ruído, e em cada <em>timestep</em> ele prevê o <em>noise residual</em> (outros modelos aprendem a prever a amostra anterior diretamente ou a velocidade ou <a href="https://github.com/huggingface/diffusers/blob/5e5ce13e2f89ac45a0066cb3f369462a3cf1d9ef/src/diffusers/schedulers/scheduling_ddim.py#L110" rel="nofollow"><code>v-prediction</code></a>), a diferença entre uma imagem menos com ruído e a imagem de entrada. Você pode misturar e combinar modelos para criar outros sistemas de difusão.',At,Ne,ea="Modelos são inicializados com o método <code>from_pretrained()</code> que também armazena em cache localmente os pesos do modelo para que seja mais rápido na próxima vez que você carregar o modelo. Para o tour rápido, você irá carregar o <code>UNet2DModel</code>, um modelo básico de geração de imagem incondicional com um checkpoint treinado em imagens de gato:",Rt,Ge,Yt,Le,ta="Para acessar os parâmetros do modelo, chame <code>model.config</code>:",Qt,Ie,Ft,Se,sa="A configuração do modelo é um dicionário 🧊 congelado 🧊, o que significa que esses parâmetros não podem ser mudados depois que o modelo é criado. Isso é intencional e garante que os parâmetros usados para definir a arquitetura do modelo no início permaneçam os mesmos, enquanto outros parâmetros ainda podem ser ajustados durante a geração.",Kt,We,aa="Um dos parâmetros mais importantes são:",Ot,Be,la="<li><code>sample_size</code>: a dimensão da altura e largura da amostra de entrada.</li> <li><code>in_channels</code>: o número de canais de entrada da amostra de entrada.</li> <li><code>down_block_types</code> e <code>up_block_types</code>: o tipo de blocos de downsampling e upsampling usados para criar a arquitetura UNet.</li> <li><code>block_out_channels</code>: o número de canais de saída dos blocos de downsampling; também utilizado como uma order reversa do número de canais de entrada dos blocos de upsampling.</li> <li><code>layers_per_block</code>: o número de blocks ResNet presentes em cada block UNet.</li>",es,Ve,na="Para usar o modelo para geração, crie a forma da imagem com ruído Gaussiano aleatório. Deve ter um eixo <code>batch</code> porque o modelo pode receber múltiplos ruídos aleatórios, um eixo <code>channel</code> correspondente ao número de canais de entrada, e um eixo <code>sample_size</code> para a altura e largura da imagem:",ts,$e,ss,ze,oa="Para geração, passe a imagem com ruído para o modelo e um <code>timestep</code>. O <code>timestep</code> indica o quão ruidosa a imagem de entrada é, com mais ruído no início e menos no final. Isso ajuda o modelo a determinar sua posição no processo de difusão, se está mais perto do início ou do final. Use o método <code>sample</code> para obter a saída do modelo:",as,He,ls,Pe,ia="Para geração de exemplos reais, você precisará de um agendador para guiar o processo de retirada do ruído. Na próxima seção, você irá aprender como acoplar um modelo com um agendador.",ns,De,os,Ee,ra="Agendadores gerenciam a retirada do ruído de uma amostra ruidosa para uma amostra menos ruidosa dado a saída do modelo - nesse caso, é o <code>noisy_residual</code>.",is,K,ua="<p>🧨 Diffusers é uma caixa de ferramentas para construir sistemas de difusão. Enquanto o <code>DiffusionPipeline</code> é uma forma conveniente de começar com um sistema de difusão pré-construído, você também pode escolher seus próprios modelos e agendadores separadamente para construir um sistema de difusão personalizado.</p>",rs,xe,ca="Para o tour rápido, você irá instanciar o <code>DDPMScheduler</code> com o método <code>from_config()</code>:",us,Xe,cs,O,ma="<p>💡 Perceba como o agendador é instanciado de uma configuração. Diferentemente de um modelo, um agendador não tem pesos treináveis e é livre de parâmetros!</p>",ms,Ae,da="Um dos parâmetros mais importante são:",ds,Re,fa="<li><code>num_train_timesteps</code>: o tamanho do processo de retirar ruído ou em outras palavras, o número de <em>timesteps</em> necessários para o processo de ruídos Gausianos aleatórios dentro de uma amostra de dados.</li> <li><code>beta_schedule</code>: o tipo de agendados de ruído para o uso de geração e treinamento.</li> <li><code>beta_start</code> e <code>beta_end</code>: para começar e terminar os valores de ruído para o agendador de ruído.</li>",fs,Ye,pa="Para predizer uma imagem com um pouco menos de ruído, passe o seguinte para o método do agendador <code>step()</code>: saída do modelo, <code>timestep</code>, e a atual <code>amostra</code>.",ps,Qe,gs,Fe,ga="O <code>less_noisy_sample</code> pode ser passado para o próximo <code>timestep</code> onde ele ficará ainda com menos ruído! Vamos juntar tudo agora e visualizar o processo inteiro de retirada de ruído.",hs,Ke,ha="Comece, criando a função que faça o pós-processamento e mostre a imagem sem ruído como uma <code>PIL.Image</code>:",bs,Oe,_s,et,ba="Para acelerar o processo de retirada de ruído, mova a entrada e o modelo para uma GPU:",Ms,tt,ws,st,_a="Agora, crie um loop de retirada de ruído que prediz o residual da amostra menos ruidosa, e computa a amostra menos ruidosa com o agendador:",vs,at,ys,lt,Ma="Sente-se e assista o gato ser gerado do nada além de ruído! 😻",js,ee,wa='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/diffusion-quicktour.png"/>',ks,nt,Cs,ot,va="Esperamos que você tenha gerado algumas imagens legais com o 🧨 Diffusers neste tour rápido! Para suas próximas etapas, você pode",Us,it,ya='<li>Treine ou faça a configuração fina de um modelo para gerar suas próprias imagens no tutorial de <a href="./tutorials/basic_training">treinamento</a>.</li> <li>Veja exemplos oficiais e da comunidade de <a href="https://github.com/huggingface/diffusers/tree/main/examples#-diffusers-examples" rel="nofollow">scripts de treinamento ou configuração fina</a> para os mais variados casos de uso.</li> <li>Aprenda sobre como carregar, acessar, mudar e comparar agendadores no guia <a href="./using-diffusers/schedulers">Usando diferentes agendadores</a>.</li> <li>Explore engenharia de prompt, otimizações de velocidade e memória, e dicas e truques para gerar imagens de maior qualidade com o guia <a href="./stable_diffusion">Stable Diffusion</a>.</li> <li>Se aprofunde em acelerar 🧨 Diffusers com guias sobre <a href="./optimization/fp16">PyTorch otimizado em uma GPU</a>, e guias de inferência para rodar <a href="./optimization/mps">Stable Diffusion em Apple Silicon (M1/M2)</a> e <a href="./optimization/onnx">ONNX Runtime</a>.</li>',Ts,rt,Js,ft,qs;return i=new Oa({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),d=new Bl({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/pt/quicktour.ipynb"},{label:"PyTorch",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers_doc/pt/pytorch/quicktour.ipynb"},{label:"TensorFlow",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers_doc/pt/tensorflow/quicktour.ipynb"},{label:"Mixed",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/pt/quicktour.ipynb"},{label:"PyTorch",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/pt/pytorch/quicktour.ipynb"},{label:"TensorFlow",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/pt/tensorflow/quicktour.ipynb"}]}}),h=new ut({props:{title:"Tour rápido",local:"tour-rápido",headingTag:"h1"}}),se=new B({props:{code:"JTIzJTIwdW5jb21tZW50JTIwdG8lMjBpbnN0YWxsJTIwdGhlJTIwbmVjZXNzYXJ5JTIwbGlicmFyaWVzJTIwaW4lMjBDb2xhYiUwQSUyMyFwaXAlMjBpbnN0YWxsJTIwLS11cGdyYWRlJTIwZGlmZnVzZXJzJTIwYWNjZWxlcmF0ZSUyMHRyYW5zZm9ybWVycw==",highlighted:`<span class="hljs-comment"># uncomment to install the necessary libraries in Colab</span>
<span class="hljs-comment">#!pip install --upgrade diffusers accelerate transformers</span>`,wrap:!1}}),le=new ut({props:{title:"DiffusionPipeline",local:"diffusionpipeline",headingTag:"h2"}}),ue=new B({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMERpZmZ1c2lvblBpcGVsaW5lJTBBJTBBcGlwZWxpbmUlMjAlM0QlMjBEaWZmdXNpb25QaXBlbGluZS5mcm9tX3ByZXRyYWluZWQoJTIyc3RhYmxlLWRpZmZ1c2lvbi12MS01JTJGc3RhYmxlLWRpZmZ1c2lvbi12MS01JTIyJTJDJTIwdXNlX3NhZmV0ZW5zb3JzJTNEVHJ1ZSk=",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)`,wrap:!1}}),me=new B({props:{code:"cGlwZWxpbmU=",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline
StableDiffusionPipeline {
  <span class="hljs-string">&quot;_class_name&quot;</span>: <span class="hljs-string">&quot;StableDiffusionPipeline&quot;</span>,
  <span class="hljs-string">&quot;_diffusers_version&quot;</span>: <span class="hljs-string">&quot;0.13.1&quot;</span>,
  ...,
  <span class="hljs-string">&quot;scheduler&quot;</span>: [
    <span class="hljs-string">&quot;diffusers&quot;</span>,
    <span class="hljs-string">&quot;PNDMScheduler&quot;</span>
  ],
  ...,
  <span class="hljs-string">&quot;unet&quot;</span>: [
    <span class="hljs-string">&quot;diffusers&quot;</span>,
    <span class="hljs-string">&quot;UNet2DConditionModel&quot;</span>
  ],
  <span class="hljs-string">&quot;vae&quot;</span>: [
    <span class="hljs-string">&quot;diffusers&quot;</span>,
    <span class="hljs-string">&quot;AutoencoderKL&quot;</span>
  ]
}`,wrap:!1}}),fe=new B({props:{code:"cGlwZWxpbmUudG8oJTIyY3VkYSUyMik=",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)',wrap:!1}}),ge=new B({props:{code:"aW1hZ2UlMjAlM0QlMjBwaXBlbGluZSglMjJBbiUyMGltYWdlJTIwb2YlMjBhJTIwc3F1aXJyZWwlMjBpbiUyMFBpY2Fzc28lMjBzdHlsZSUyMikuaW1hZ2VzJTVCMCU1RCUwQWltYWdl",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span>image = pipeline(<span class="hljs-string">&quot;An image of a squirrel in Picasso style&quot;</span>).images[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>image`,wrap:!1}}),be=new B({props:{code:"aW1hZ2Uuc2F2ZSglMjJpbWFnZV9vZl9zcXVpcnJlbF9wYWludGluZy5wbmclMjIp",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;image_of_squirrel_painting.png&quot;</span>)',wrap:!1}}),_e=new ut({props:{title:"Pipeline local",local:"pipeline-local",headingTag:"h3"}}),we=new B({props:{code:"IWdpdCUyMGxmcyUyMGluc3RhbGwlMEEhZ2l0JTIwY2xvbmUlMjBodHRwcyUzQSUyRiUyRmh1Z2dpbmdmYWNlLmNvJTJGc3RhYmxlLWRpZmZ1c2lvbi12MS01JTJGc3RhYmxlLWRpZmZ1c2lvbi12MS01",highlighted:`!git lfs install
!git <span class="hljs-built_in">clone</span> https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5`,wrap:!1}}),ye=new B({props:{code:"cGlwZWxpbmUlMjAlM0QlMjBEaWZmdXNpb25QaXBlbGluZS5mcm9tX3ByZXRyYWluZWQoJTIyLiUyRnN0YWJsZS1kaWZmdXNpb24tdjEtNSUyMiUyQyUyMHVzZV9zYWZldGVuc29ycyUzRFRydWUp",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;./stable-diffusion-v1-5&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)',wrap:!1}}),ke=new ut({props:{title:"Troca dos agendadores",local:"troca-dos-agendadores",headingTag:"h3"}}),Ue=new B({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEV1bGVyRGlzY3JldGVTY2hlZHVsZXIlMEElMEFwaXBlbGluZSUyMCUzRCUyMERpZmZ1c2lvblBpcGVsaW5lLmZyb21fcHJldHJhaW5lZCglMjJzdGFibGUtZGlmZnVzaW9uLXYxLTUlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTUlMjIlMkMlMjB1c2Vfc2FmZXRlbnNvcnMlM0RUcnVlKSUwQXBpcGVsaW5lLnNjaGVkdWxlciUyMCUzRCUyMEV1bGVyRGlzY3JldGVTY2hlZHVsZXIuZnJvbV9jb25maWcocGlwZWxpbmUuc2NoZWR1bGVyLmNvbmZpZyk=",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> EulerDiscreteScheduler

<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)`,wrap:!1}}),qe=new ut({props:{title:"Modelos",local:"modelos",headingTag:"h2"}}),Ge=new B({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMFVOZXQyRE1vZGVsJTBBJTBBcmVwb19pZCUyMCUzRCUyMCUyMmdvb2dsZSUyRmRkcG0tY2F0LTI1NiUyMiUwQW1vZGVsJTIwJTNEJTIwVU5ldDJETW9kZWwuZnJvbV9wcmV0cmFpbmVkKHJlcG9faWQlMkMlMjB1c2Vfc2FmZXRlbnNvcnMlM0RUcnVlKQ==",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> UNet2DModel

<span class="hljs-meta">&gt;&gt;&gt; </span>repo_id = <span class="hljs-string">&quot;google/ddpm-cat-256&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>model = UNet2DModel.from_pretrained(repo_id, use_safetensors=<span class="hljs-literal">True</span>)`,wrap:!1}}),Ie=new B({props:{code:"bW9kZWwuY29uZmln",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span>model.config',wrap:!1}}),$e=new B({props:{code:"aW1wb3J0JTIwdG9yY2glMEElMEF0b3JjaC5tYW51YWxfc2VlZCgwKSUwQSUwQW5vaXN5X3NhbXBsZSUyMCUzRCUyMHRvcmNoLnJhbmRuKDElMkMlMjBtb2RlbC5jb25maWcuaW5fY2hhbm5lbHMlMkMlMjBtb2RlbC5jb25maWcuc2FtcGxlX3NpemUlMkMlMjBtb2RlbC5jb25maWcuc2FtcGxlX3NpemUpJTBBbm9pc3lfc2FtcGxlLnNoYXBl",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch

<span class="hljs-meta">&gt;&gt;&gt; </span>torch.manual_seed(<span class="hljs-number">0</span>)

<span class="hljs-meta">&gt;&gt;&gt; </span>noisy_sample = torch.randn(<span class="hljs-number">1</span>, model.config.in_channels, model.config.sample_size, model.config.sample_size)
<span class="hljs-meta">&gt;&gt;&gt; </span>noisy_sample.shape
torch.Size([<span class="hljs-number">1</span>, <span class="hljs-number">3</span>, <span class="hljs-number">256</span>, <span class="hljs-number">256</span>])`,wrap:!1}}),He=new B({props:{code:"d2l0aCUyMHRvcmNoLm5vX2dyYWQoKSUzQSUwQSUyMCUyMCUyMCUyMG5vaXN5X3Jlc2lkdWFsJTIwJTNEJTIwbW9kZWwoc2FtcGxlJTNEbm9pc3lfc2FtcGxlJTJDJTIwdGltZXN0ZXAlM0QyKS5zYW1wbGU=",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">with</span> torch.no_grad():
<span class="hljs-meta">... </span>    noisy_residual = model(sample=noisy_sample, timestep=<span class="hljs-number">2</span>).sample`,wrap:!1}}),De=new ut({props:{title:"Agendadores",local:"agendadores",headingTag:"h2"}}),Xe=new B({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEREUE1TY2hlZHVsZXIlMEElMEFzY2hlZHVsZXIlMjAlM0QlMjBERFBNU2NoZWR1bGVyLmZyb21fY29uZmlnKHJlcG9faWQpJTBBc2NoZWR1bGVy",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDPMScheduler

<span class="hljs-meta">&gt;&gt;&gt; </span>scheduler = DDPMScheduler.from_config(repo_id)
<span class="hljs-meta">&gt;&gt;&gt; </span>scheduler
DDPMScheduler {
  <span class="hljs-string">&quot;_class_name&quot;</span>: <span class="hljs-string">&quot;DDPMScheduler&quot;</span>,
  <span class="hljs-string">&quot;_diffusers_version&quot;</span>: <span class="hljs-string">&quot;0.13.1&quot;</span>,
  <span class="hljs-string">&quot;beta_end&quot;</span>: <span class="hljs-number">0.02</span>,
  <span class="hljs-string">&quot;beta_schedule&quot;</span>: <span class="hljs-string">&quot;linear&quot;</span>,
  <span class="hljs-string">&quot;beta_start&quot;</span>: <span class="hljs-number">0.0001</span>,
  <span class="hljs-string">&quot;clip_sample&quot;</span>: true,
  <span class="hljs-string">&quot;clip_sample_range&quot;</span>: <span class="hljs-number">1.0</span>,
  <span class="hljs-string">&quot;num_train_timesteps&quot;</span>: <span class="hljs-number">1000</span>,
  <span class="hljs-string">&quot;prediction_type&quot;</span>: <span class="hljs-string">&quot;epsilon&quot;</span>,
  <span class="hljs-string">&quot;trained_betas&quot;</span>: null,
  <span class="hljs-string">&quot;variance_type&quot;</span>: <span class="hljs-string">&quot;fixed_small&quot;</span>
}`,wrap:!1}}),Qe=new B({props:{code:"bGVzc19ub2lzeV9zYW1wbGUlMjAlM0QlMjBzY2hlZHVsZXIuc3RlcChtb2RlbF9vdXRwdXQlM0Rub2lzeV9yZXNpZHVhbCUyQyUyMHRpbWVzdGVwJTNEMiUyQyUyMHNhbXBsZSUzRG5vaXN5X3NhbXBsZSkucHJldl9zYW1wbGUlMEFsZXNzX25vaXN5X3NhbXBsZS5zaGFwZQ==",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span>less_noisy_sample = scheduler.step(model_output=noisy_residual, timestep=<span class="hljs-number">2</span>, sample=noisy_sample).prev_sample
<span class="hljs-meta">&gt;&gt;&gt; </span>less_noisy_sample.shape`,wrap:!1}}),Oe=new B({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> PIL.Image
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np


<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">display_sample</span>(<span class="hljs-params">sample, i</span>):
<span class="hljs-meta">... </span>    image_processed = sample.cpu().permute(<span class="hljs-number">0</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>, <span class="hljs-number">1</span>)
<span class="hljs-meta">... </span>    image_processed = (image_processed + <span class="hljs-number">1.0</span>) * <span class="hljs-number">127.5</span>
<span class="hljs-meta">... </span>    image_processed = image_processed.numpy().astype(np.uint8)

<span class="hljs-meta">... </span>    image_pil = PIL.Image.fromarray(image_processed[<span class="hljs-number">0</span>])
<span class="hljs-meta">... </span>    display(<span class="hljs-string">f&quot;Image at step <span class="hljs-subst">{i}</span>&quot;</span>)
<span class="hljs-meta">... </span>    display(image_pil)`,wrap:!1}}),tt=new B({props:{code:"bW9kZWwudG8oJTIyY3VkYSUyMiklMEFub2lzeV9zYW1wbGUlMjAlM0QlMjBub2lzeV9zYW1wbGUudG8oJTIyY3VkYSUyMik=",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span>model.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>noisy_sample = noisy_sample.to(<span class="hljs-string">&quot;cuda&quot;</span>)`,wrap:!1}}),at=new B({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> tqdm

<span class="hljs-meta">&gt;&gt;&gt; </span>sample = noisy_sample

<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">for</span> i, t <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(tqdm.tqdm(scheduler.timesteps)):
<span class="hljs-meta">... </span>    <span class="hljs-comment"># 1. predict noise residual</span>
<span class="hljs-meta">... </span>    <span class="hljs-keyword">with</span> torch.no_grad():
<span class="hljs-meta">... </span>        residual = model(sample, t).sample

<span class="hljs-meta">... </span>    <span class="hljs-comment"># 2. compute less noisy image and set x_t -&gt; x_t-1</span>
<span class="hljs-meta">... </span>    sample = scheduler.step(residual, t, sample).prev_sample

<span class="hljs-meta">... </span>    <span class="hljs-comment"># 3. optionally look at image</span>
<span class="hljs-meta">... </span>    <span class="hljs-keyword">if</span> (i + <span class="hljs-number">1</span>) % <span class="hljs-number">50</span> == <span class="hljs-number">0</span>:
<span class="hljs-meta">... </span>        display_sample(sample, i + <span class="hljs-number">1</span>)`,wrap:!1}}),nt=new ut({props:{title:"Próximos passos",local:"próximos-passos",headingTag:"h2"}}),rt=new el({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/pt/quicktour.md"}}),{c(){t=M("meta"),l=f(),a=M("p"),s=f(),Z(i.$$.fragment),o=f(),Z(d.$$.fragment),m=f(),Z(h.$$.fragment),J=f(),U=M("p"),U.textContent=k,T=f(),v=M("p"),v.textContent=j,q=f(),W=M("ul"),W.innerHTML=L,y=f(),x=M("p"),x.innerHTML=pt,S=f(),$=M("blockquote"),$.innerHTML=Is,gt=f(),te=M("p"),te.textContent=Ss,ht=f(),Z(se.$$.fragment),bt=f(),ae=M("ul"),ae.innerHTML=Ws,_t=f(),Z(le.$$.fragment),Mt=f(),ne=M("p"),ne.innerHTML=Bs,wt=f(),oe=M("table"),oe.innerHTML=Vs,vt=f(),ie=M("p"),ie.innerHTML=$s,yt=f(),Q=M("blockquote"),Q.innerHTML=zs,jt=f(),re=M("p"),re.innerHTML=Hs,kt=f(),Z(ue.$$.fragment),Ct=f(),ce=M("p"),ce.innerHTML=Ps,Ut=f(),Z(me.$$.fragment),Tt=f(),de=M("p"),de.textContent=Ds,Jt=f(),Z(fe.$$.fragment),qt=f(),pe=M("p"),pe.innerHTML=Es,Zt=f(),Z(ge.$$.fragment),Nt=f(),F=M("div"),F.innerHTML=xs,Gt=f(),he=M("p"),he.innerHTML=Xs,Lt=f(),Z(be.$$.fragment),It=f(),Z(_e.$$.fragment),St=f(),Me=M("p"),Me.textContent=As,Wt=f(),Z(we.$$.fragment),Bt=f(),ve=M("p"),ve.textContent=Rs,Vt=f(),Z(ye.$$.fragment),$t=f(),je=M("p"),je.textContent=Ys,zt=f(),Z(ke.$$.fragment),Ht=f(),Ce=M("p"),Ce.innerHTML=Qs,Pt=f(),Z(Ue.$$.fragment),Dt=f(),Te=M("p"),Te.textContent=Fs,Et=f(),Je=M("p"),Je.innerHTML=Ks,xt=f(),Z(qe.$$.fragment),Xt=f(),Ze=M("p"),Ze.innerHTML=Os,At=f(),Ne=M("p"),Ne.innerHTML=ea,Rt=f(),Z(Ge.$$.fragment),Yt=f(),Le=M("p"),Le.innerHTML=ta,Qt=f(),Z(Ie.$$.fragment),Ft=f(),Se=M("p"),Se.textContent=sa,Kt=f(),We=M("p"),We.textContent=aa,Ot=f(),Be=M("ul"),Be.innerHTML=la,es=f(),Ve=M("p"),Ve.innerHTML=na,ts=f(),Z($e.$$.fragment),ss=f(),ze=M("p"),ze.innerHTML=oa,as=f(),Z(He.$$.fragment),ls=f(),Pe=M("p"),Pe.textContent=ia,ns=f(),Z(De.$$.fragment),os=f(),Ee=M("p"),Ee.innerHTML=ra,is=f(),K=M("blockquote"),K.innerHTML=ua,rs=f(),xe=M("p"),xe.innerHTML=ca,us=f(),Z(Xe.$$.fragment),cs=f(),O=M("blockquote"),O.innerHTML=ma,ms=f(),Ae=M("p"),Ae.textContent=da,ds=f(),Re=M("ul"),Re.innerHTML=fa,fs=f(),Ye=M("p"),Ye.innerHTML=pa,ps=f(),Z(Qe.$$.fragment),gs=f(),Fe=M("p"),Fe.innerHTML=ga,hs=f(),Ke=M("p"),Ke.innerHTML=ha,bs=f(),Z(Oe.$$.fragment),_s=f(),et=M("p"),et.textContent=ba,Ms=f(),Z(tt.$$.fragment),ws=f(),st=M("p"),st.textContent=_a,vs=f(),Z(at.$$.fragment),ys=f(),lt=M("p"),lt.textContent=Ma,js=f(),ee=M("div"),ee.innerHTML=wa,ks=f(),Z(nt.$$.fragment),Cs=f(),ot=M("p"),ot.textContent=va,Us=f(),it=M("ul"),it.innerHTML=ya,Ts=f(),Z(rt.$$.fragment),Js=f(),ft=M("p"),this.h()},l(e){const u=Ka("svelte-u9bgzb",document.head);t=w(u,"META",{name:!0,content:!0}),u.forEach(r),l=p(e),a=w(e,"P",{}),V(a).forEach(r),s=p(e),I(i.$$.fragment,e),o=p(e),I(d.$$.fragment,e),m=p(e),I(h.$$.fragment,e),J=p(e),U=w(e,"P",{"data-svelte-h":!0}),C(U)!=="svelte-5d3hlg"&&(U.textContent=k),T=p(e),v=w(e,"P",{"data-svelte-h":!0}),C(v)!=="svelte-tkfmfk"&&(v.textContent=j),q=p(e),W=w(e,"UL",{"data-svelte-h":!0}),C(W)!=="svelte-1bp7yfw"&&(W.innerHTML=L),y=p(e),x=w(e,"P",{"data-svelte-h":!0}),C(x)!=="svelte-sqpmf8"&&(x.innerHTML=pt),S=p(e),$=w(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),C($)!=="svelte-mhj3h4"&&($.innerHTML=Is),gt=p(e),te=w(e,"P",{"data-svelte-h":!0}),C(te)!=="svelte-16jlltr"&&(te.textContent=Ss),ht=p(e),I(se.$$.fragment,e),bt=p(e),ae=w(e,"UL",{"data-svelte-h":!0}),C(ae)!=="svelte-l49o4a"&&(ae.innerHTML=Ws),_t=p(e),I(le.$$.fragment,e),Mt=p(e),ne=w(e,"P",{"data-svelte-h":!0}),C(ne)!=="svelte-1fm3zhc"&&(ne.innerHTML=Bs),wt=p(e),oe=w(e,"TABLE",{"data-svelte-h":!0}),C(oe)!=="svelte-1wldcuj"&&(oe.innerHTML=Vs),vt=p(e),ie=w(e,"P",{"data-svelte-h":!0}),C(ie)!=="svelte-1ywycy7"&&(ie.innerHTML=$s),yt=p(e),Q=w(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),C(Q)!=="svelte-eq1ac4"&&(Q.innerHTML=zs),jt=p(e),re=w(e,"P",{"data-svelte-h":!0}),C(re)!=="svelte-14st4zt"&&(re.innerHTML=Hs),kt=p(e),I(ue.$$.fragment,e),Ct=p(e),ce=w(e,"P",{"data-svelte-h":!0}),C(ce)!=="svelte-15d6klf"&&(ce.innerHTML=Ps),Ut=p(e),I(me.$$.fragment,e),Tt=p(e),de=w(e,"P",{"data-svelte-h":!0}),C(de)!=="svelte-1lh10u2"&&(de.textContent=Ds),Jt=p(e),I(fe.$$.fragment,e),qt=p(e),pe=w(e,"P",{"data-svelte-h":!0}),C(pe)!=="svelte-1fzeyvx"&&(pe.innerHTML=Es),Zt=p(e),I(ge.$$.fragment,e),Nt=p(e),F=w(e,"DIV",{class:!0,"data-svelte-h":!0}),C(F)!=="svelte-6cjtp1"&&(F.innerHTML=xs),Gt=p(e),he=w(e,"P",{"data-svelte-h":!0}),C(he)!=="svelte-1qpz3ys"&&(he.innerHTML=Xs),Lt=p(e),I(be.$$.fragment,e),It=p(e),I(_e.$$.fragment,e),St=p(e),Me=w(e,"P",{"data-svelte-h":!0}),C(Me)!=="svelte-11z96s9"&&(Me.textContent=As),Wt=p(e),I(we.$$.fragment,e),Bt=p(e),ve=w(e,"P",{"data-svelte-h":!0}),C(ve)!=="svelte-nca5xy"&&(ve.textContent=Rs),Vt=p(e),I(ye.$$.fragment,e),$t=p(e),je=w(e,"P",{"data-svelte-h":!0}),C(je)!=="svelte-18fxe39"&&(je.textContent=Ys),zt=p(e),I(ke.$$.fragment,e),Ht=p(e),Ce=w(e,"P",{"data-svelte-h":!0}),C(Ce)!=="svelte-1bdwzfu"&&(Ce.innerHTML=Qs),Pt=p(e),I(Ue.$$.fragment,e),Dt=p(e),Te=w(e,"P",{"data-svelte-h":!0}),C(Te)!=="svelte-rjqaf3"&&(Te.textContent=Fs),Et=p(e),Je=w(e,"P",{"data-svelte-h":!0}),C(Je)!=="svelte-yp9if5"&&(Je.innerHTML=Ks),xt=p(e),I(qe.$$.fragment,e),Xt=p(e),Ze=w(e,"P",{"data-svelte-h":!0}),C(Ze)!=="svelte-cl1ldd"&&(Ze.innerHTML=Os),At=p(e),Ne=w(e,"P",{"data-svelte-h":!0}),C(Ne)!=="svelte-onulph"&&(Ne.innerHTML=ea),Rt=p(e),I(Ge.$$.fragment,e),Yt=p(e),Le=w(e,"P",{"data-svelte-h":!0}),C(Le)!=="svelte-qcoyrg"&&(Le.innerHTML=ta),Qt=p(e),I(Ie.$$.fragment,e),Ft=p(e),Se=w(e,"P",{"data-svelte-h":!0}),C(Se)!=="svelte-i890oq"&&(Se.textContent=sa),Kt=p(e),We=w(e,"P",{"data-svelte-h":!0}),C(We)!=="svelte-1wzn7ma"&&(We.textContent=aa),Ot=p(e),Be=w(e,"UL",{"data-svelte-h":!0}),C(Be)!=="svelte-o5msyb"&&(Be.innerHTML=la),es=p(e),Ve=w(e,"P",{"data-svelte-h":!0}),C(Ve)!=="svelte-obxecp"&&(Ve.innerHTML=na),ts=p(e),I($e.$$.fragment,e),ss=p(e),ze=w(e,"P",{"data-svelte-h":!0}),C(ze)!=="svelte-1qo9t3f"&&(ze.innerHTML=oa),as=p(e),I(He.$$.fragment,e),ls=p(e),Pe=w(e,"P",{"data-svelte-h":!0}),C(Pe)!=="svelte-1ljqqs3"&&(Pe.textContent=ia),ns=p(e),I(De.$$.fragment,e),os=p(e),Ee=w(e,"P",{"data-svelte-h":!0}),C(Ee)!=="svelte-1c3rc74"&&(Ee.innerHTML=ra),is=p(e),K=w(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),C(K)!=="svelte-kw0jm4"&&(K.innerHTML=ua),rs=p(e),xe=w(e,"P",{"data-svelte-h":!0}),C(xe)!=="svelte-7pekzf"&&(xe.innerHTML=ca),us=p(e),I(Xe.$$.fragment,e),cs=p(e),O=w(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),C(O)!=="svelte-1o3oicu"&&(O.innerHTML=ma),ms=p(e),Ae=w(e,"P",{"data-svelte-h":!0}),C(Ae)!=="svelte-kydn7r"&&(Ae.textContent=da),ds=p(e),Re=w(e,"UL",{"data-svelte-h":!0}),C(Re)!=="svelte-1xnw77s"&&(Re.innerHTML=fa),fs=p(e),Ye=w(e,"P",{"data-svelte-h":!0}),C(Ye)!=="svelte-3wttzd"&&(Ye.innerHTML=pa),ps=p(e),I(Qe.$$.fragment,e),gs=p(e),Fe=w(e,"P",{"data-svelte-h":!0}),C(Fe)!=="svelte-1tpggdq"&&(Fe.innerHTML=ga),hs=p(e),Ke=w(e,"P",{"data-svelte-h":!0}),C(Ke)!=="svelte-1xrm0cs"&&(Ke.innerHTML=ha),bs=p(e),I(Oe.$$.fragment,e),_s=p(e),et=w(e,"P",{"data-svelte-h":!0}),C(et)!=="svelte-19fphdr"&&(et.textContent=ba),Ms=p(e),I(tt.$$.fragment,e),ws=p(e),st=w(e,"P",{"data-svelte-h":!0}),C(st)!=="svelte-1ff49gu"&&(st.textContent=_a),vs=p(e),I(at.$$.fragment,e),ys=p(e),lt=w(e,"P",{"data-svelte-h":!0}),C(lt)!=="svelte-1tdl2pq"&&(lt.textContent=Ma),js=p(e),ee=w(e,"DIV",{class:!0,"data-svelte-h":!0}),C(ee)!=="svelte-1yzsrw6"&&(ee.innerHTML=wa),ks=p(e),I(nt.$$.fragment,e),Cs=p(e),ot=w(e,"P",{"data-svelte-h":!0}),C(ot)!=="svelte-tfhhyg"&&(ot.textContent=va),Us=p(e),it=w(e,"UL",{"data-svelte-h":!0}),C(it)!=="svelte-1r1xmc2"&&(it.innerHTML=ya),Ts=p(e),I(rt.$$.fragment,e),Js=p(e),ft=w(e,"P",{}),V(ft).forEach(r),this.h()},h(){_(t,"name","hf:doc:metadata"),_(t,"content",$l),_($,"class","tip"),_(Q,"class","warning"),_(F,"class","flex justify-center"),_(K,"class","tip"),_(O,"class","tip"),_(ee,"class","flex justify-center")},m(e,u){H(document.head,t),c(e,l,u),c(e,a,u),c(e,s,u),N(i,e,u),c(e,o,u),N(d,e,u),c(e,m,u),N(h,e,u),c(e,J,u),c(e,U,u),c(e,T,u),c(e,v,u),c(e,q,u),c(e,W,u),c(e,y,u),c(e,x,u),c(e,S,u),c(e,$,u),c(e,gt,u),c(e,te,u),c(e,ht,u),N(se,e,u),c(e,bt,u),c(e,ae,u),c(e,_t,u),N(le,e,u),c(e,Mt,u),c(e,ne,u),c(e,wt,u),c(e,oe,u),c(e,vt,u),c(e,ie,u),c(e,yt,u),c(e,Q,u),c(e,jt,u),c(e,re,u),c(e,kt,u),N(ue,e,u),c(e,Ct,u),c(e,ce,u),c(e,Ut,u),N(me,e,u),c(e,Tt,u),c(e,de,u),c(e,Jt,u),N(fe,e,u),c(e,qt,u),c(e,pe,u),c(e,Zt,u),N(ge,e,u),c(e,Nt,u),c(e,F,u),c(e,Gt,u),c(e,he,u),c(e,Lt,u),N(be,e,u),c(e,It,u),N(_e,e,u),c(e,St,u),c(e,Me,u),c(e,Wt,u),N(we,e,u),c(e,Bt,u),c(e,ve,u),c(e,Vt,u),N(ye,e,u),c(e,$t,u),c(e,je,u),c(e,zt,u),N(ke,e,u),c(e,Ht,u),c(e,Ce,u),c(e,Pt,u),N(Ue,e,u),c(e,Dt,u),c(e,Te,u),c(e,Et,u),c(e,Je,u),c(e,xt,u),N(qe,e,u),c(e,Xt,u),c(e,Ze,u),c(e,At,u),c(e,Ne,u),c(e,Rt,u),N(Ge,e,u),c(e,Yt,u),c(e,Le,u),c(e,Qt,u),N(Ie,e,u),c(e,Ft,u),c(e,Se,u),c(e,Kt,u),c(e,We,u),c(e,Ot,u),c(e,Be,u),c(e,es,u),c(e,Ve,u),c(e,ts,u),N($e,e,u),c(e,ss,u),c(e,ze,u),c(e,as,u),N(He,e,u),c(e,ls,u),c(e,Pe,u),c(e,ns,u),N(De,e,u),c(e,os,u),c(e,Ee,u),c(e,is,u),c(e,K,u),c(e,rs,u),c(e,xe,u),c(e,us,u),N(Xe,e,u),c(e,cs,u),c(e,O,u),c(e,ms,u),c(e,Ae,u),c(e,ds,u),c(e,Re,u),c(e,fs,u),c(e,Ye,u),c(e,ps,u),N(Qe,e,u),c(e,gs,u),c(e,Fe,u),c(e,hs,u),c(e,Ke,u),c(e,bs,u),N(Oe,e,u),c(e,_s,u),c(e,et,u),c(e,Ms,u),N(tt,e,u),c(e,ws,u),c(e,st,u),c(e,vs,u),N(at,e,u),c(e,ys,u),c(e,lt,u),c(e,js,u),c(e,ee,u),c(e,ks,u),N(nt,e,u),c(e,Cs,u),c(e,ot,u),c(e,Us,u),c(e,it,u),c(e,Ts,u),N(rt,e,u),c(e,Js,u),c(e,ft,u),qs=!0},p:z,i(e){qs||(g(i.$$.fragment,e),g(d.$$.fragment,e),g(h.$$.fragment,e),g(se.$$.fragment,e),g(le.$$.fragment,e),g(ue.$$.fragment,e),g(me.$$.fragment,e),g(fe.$$.fragment,e),g(ge.$$.fragment,e),g(be.$$.fragment,e),g(_e.$$.fragment,e),g(we.$$.fragment,e),g(ye.$$.fragment,e),g(ke.$$.fragment,e),g(Ue.$$.fragment,e),g(qe.$$.fragment,e),g(Ge.$$.fragment,e),g(Ie.$$.fragment,e),g($e.$$.fragment,e),g(He.$$.fragment,e),g(De.$$.fragment,e),g(Xe.$$.fragment,e),g(Qe.$$.fragment,e),g(Oe.$$.fragment,e),g(tt.$$.fragment,e),g(at.$$.fragment,e),g(nt.$$.fragment,e),g(rt.$$.fragment,e),qs=!0)},o(e){b(i.$$.fragment,e),b(d.$$.fragment,e),b(h.$$.fragment,e),b(se.$$.fragment,e),b(le.$$.fragment,e),b(ue.$$.fragment,e),b(me.$$.fragment,e),b(fe.$$.fragment,e),b(ge.$$.fragment,e),b(be.$$.fragment,e),b(_e.$$.fragment,e),b(we.$$.fragment,e),b(ye.$$.fragment,e),b(ke.$$.fragment,e),b(Ue.$$.fragment,e),b(qe.$$.fragment,e),b(Ge.$$.fragment,e),b(Ie.$$.fragment,e),b($e.$$.fragment,e),b(He.$$.fragment,e),b(De.$$.fragment,e),b(Xe.$$.fragment,e),b(Qe.$$.fragment,e),b(Oe.$$.fragment,e),b(tt.$$.fragment,e),b(at.$$.fragment,e),b(nt.$$.fragment,e),b(rt.$$.fragment,e),qs=!1},d(e){e&&(r(l),r(a),r(s),r(o),r(m),r(J),r(U),r(T),r(v),r(q),r(W),r(y),r(x),r(S),r($),r(gt),r(te),r(ht),r(bt),r(ae),r(_t),r(Mt),r(ne),r(wt),r(oe),r(vt),r(ie),r(yt),r(Q),r(jt),r(re),r(kt),r(Ct),r(ce),r(Ut),r(Tt),r(de),r(Jt),r(qt),r(pe),r(Zt),r(Nt),r(F),r(Gt),r(he),r(Lt),r(It),r(St),r(Me),r(Wt),r(Bt),r(ve),r(Vt),r($t),r(je),r(zt),r(Ht),r(Ce),r(Pt),r(Dt),r(Te),r(Et),r(Je),r(xt),r(Xt),r(Ze),r(At),r(Ne),r(Rt),r(Yt),r(Le),r(Qt),r(Ft),r(Se),r(Kt),r(We),r(Ot),r(Be),r(es),r(Ve),r(ts),r(ss),r(ze),r(as),r(ls),r(Pe),r(ns),r(os),r(Ee),r(is),r(K),r(rs),r(xe),r(us),r(cs),r(O),r(ms),r(Ae),r(ds),r(Re),r(fs),r(Ye),r(ps),r(gs),r(Fe),r(hs),r(Ke),r(bs),r(_s),r(et),r(Ms),r(ws),r(st),r(vs),r(ys),r(lt),r(js),r(ee),r(ks),r(Cs),r(ot),r(Us),r(it),r(Ts),r(Js),r(ft)),r(t),G(i,e),G(d,e),G(h,e),G(se,e),G(le,e),G(ue,e),G(me,e),G(fe,e),G(ge,e),G(be,e),G(_e,e),G(we,e),G(ye,e),G(ke,e),G(Ue,e),G(qe,e),G(Ge,e),G(Ie,e),G($e,e),G(He,e),G(De,e),G(Xe,e),G(Qe,e),G(Oe,e),G(tt,e),G(at,e),G(nt,e),G(rt,e)}}}const $l='{"title":"Tour rápido","local":"tour-rápido","sections":[{"title":"DiffusionPipeline","local":"diffusionpipeline","sections":[{"title":"Pipeline local","local":"pipeline-local","sections":[],"depth":3},{"title":"Troca dos agendadores","local":"troca-dos-agendadores","sections":[],"depth":3}],"depth":2},{"title":"Modelos","local":"modelos","sections":[],"depth":2},{"title":"Agendadores","local":"agendadores","sections":[],"depth":2},{"title":"Próximos passos","local":"próximos-passos","sections":[],"depth":2}],"depth":1}';function zl(n){return Pa(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Xl extends mt{constructor(t){super(),dt(this,t,zl,Vl,ct,{})}}export{Xl as component};