diffusers/pr_12411/pt/_app/immutable/nodes/4.b2cbbc7d.js

import{s as mt,d as A,j as Da,u as R,g as Y,e as Q,o as Ws,b as Is,n as P,y as Ea,t as Fa,z as Gs}from"../chunks/scheduler.284fc092.js";import{S as dt,i as ft,e as w,a as M,f as z,d as r,k as v,m as c,l as D,B as Ls,t as h,o as _,D as Ca,E as Ua,x as Ka,s as f,b as p,y as E,w as X,c as q,j as G,n as N,p as Z,q as Xa,v as x,r as xa,u as Aa,z as Ns,A as Ra,h as Oa,g as k}from"../chunks/index.3707479a.js";import{aN as el,C as tl,H as ct,E as sl}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.b3d722ef.js";import{C as V}from"../chunks/CodeBlock.49e93ec9.js";import{e as Zs}from"../chunks/each.e59479a4.js";function al(n){let t,l,a,s,i,o;const d=n[7].default,m=A(d,n,n[6],null);return{c(){t=w("div"),l=w("ul"),m&&m.c(),this.h()},l(b){t=M(b,"DIV",{class:!0});var C=z(t);l=M(C,"UL",{class:!0});var I=z(l);m&&m.l(I),I.forEach(r),C.forEach(r),this.h()},h(){v(l,"class","min-w-full w-auto"),v(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(b,C){c(b,t,C),D(t,l),m&&m.m(l,null),n[8](t),s=!0,i||(o=Ls(t,"click",function(){Da(n[1])&&n[1].apply(this,arguments)}),i=!0)},p(b,[C]){n=b,m&&m.p&&(!s||C&64)&&R(m,d,n,n[6],s?Q(d,n[6],C,null):Y(n[6]),null),(!s||C&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]))&&v(t,"class",a)},i(b){s||(h(m,b),s=!0)},o(b){_(m,b),s=!1},d(b){b&&r(t),m&&m.d(b),n[8](null),i=!1,o()}}}function ll(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,b=d??"left",C;Ws(()=>{if(document.addEventListener("click",I),!d){const j=document.documentElement.clientWidth,g=C==null?void 0:C.getBoundingClientRect(),y=(g==null?void 0:g.left)??0,T=(g==null?void 0:g.width)??0;l(2,b=y+T>j?"right":"left")}return()=>{document.removeEventListener("click",I)}});function I(j){const g=j.target;g!==o&&!(o!=null&&o.contains(g))&&m(j)}function W(j){Is[j?"unshift":"push"](()=>{C=j,l(3,C)})}return n.$$set=j=>{"classNames"in j&&l(0,i=j.classNames),"dropdownElement"in j&&l(4,o=j.dropdownElement),"forceAlignement"in j&&l(5,d=j.forceAlignement),"onClose"in j&&l(1,m=j.onClose),"$$scope"in j&&l(6,s=j.$$scope)},[i,m,b,C,o,d,s,a,W]}class nl extends dt{constructor(t){super(),ft(this,t,ll,al,mt,{classNames:0,dropdownElement:4,forceAlignement:5,onClose:1})}}function ol(n){let t,l;return{c(){t=Ca("svg"),l=Ca("path"),this.h()},l(a){t=Ua(a,"svg",{class:!0,xmlns:!0,"xmlns:xlink":!0,"aria-hidden":!0,focusable:!0,role:!0,width:!0,height:!0,preserveAspectRatio:!0,viewBox:!0,style:!0});var s=z(t);l=Ua(s,"path",{d:!0,fill:!0}),z(l).forEach(r),s.forEach(r),this.h()},h(){v(l,"d","M7 10l5 5l5-5z"),v(l,"fill","currentColor"),v(t,"class",n[0]),v(t,"xmlns","http://www.w3.org/2000/svg"),v(t,"xmlns:xlink","http://www.w3.org/1999/xlink"),v(t,"aria-hidden","true"),v(t,"focusable","false"),v(t,"role","img"),v(t,"width","1em"),v(t,"height","1em"),v(t,"preserveAspectRatio","xMidYMid meet"),v(t,"viewBox","0 0 24 24"),Ka(t,"transform","rotate(360deg)")},m(a,s){c(a,t,s),D(t,l)},p(a,[s]){s&1&&v(t,"class",a[0])},i:P,o:P,d(a){a&&r(t)}}}function il(n,t,l){let{classNames:a=""}=t;return n.$$set=s=>{"classNames"in s&&l(0,a=s.classNames)},[a]}class rl extends dt{constructor(t){super(),ft(this,t,il,ol,mt,{classNames:0})}}const ul=n=>({}),Ta=n=>({}),cl=n=>({}),Ja=n=>({});function ml(n){let t,l,a,s,i,o=n[2]&&qa(n),d=n[9]&&Na();return{c(){o&&o.c(),t=f(),l=Xa(n[4]),a=f(),d&&d.c(),s=x()},l(m){o&&o.l(m),t=p(m),l=xa(m,n[4]),a=p(m),d&&d.l(m),s=x()},m(m,b){o&&o.m(m,b),c(m,t,b),c(m,l,b),c(m,a,b),d&&d.m(m,b),c(m,s,b),i=!0},p(m,b){m[2]?o?(o.p(m,b),b&4&&h(o,1)):(o=qa(m),o.c(),h(o,1),o.m(t.parentNode,t)):o&&(E(),_(o,1,1,()=>{o=null}),X()),(!i||b&16)&&Aa(l,m[4]),m[9]?d?b&512&&h(d,1):(d=Na(),d.c(),h(d,1),d.m(s.parentNode,s)):d&&(E(),_(d,1,1,()=>{d=null}),X())},i(m){i||(h(o),h(d),i=!0)},o(m){_(o),_(d),i=!1},d(m){m&&(r(t),r(l),r(a),r(s)),o&&o.d(m),d&&d.d(m)}}}function dl(n){let t;const l=n[15].button,a=A(l,n,n[18],Ja);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)&&R(a,l,s,s[18],t?Q(l,s[18],i,cl):Y(s[18]),Ja)},i(s){t||(h(a,s),t=!0)},o(s){_(a,s),t=!1},d(s){a&&a.d(s)}}}function qa(n){let t,l,a;var s=n[2];function i(o,d){return{props:{classNames:"mr-1.5 "+o[3]}}}return s&&(t=Ns(s,i(n))),{c(){t&&q(t.$$.fragment),l=x()},l(o){t&&G(t.$$.fragment,o),l=x()},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){E();const m=t;_(m.$$.fragment,1,0,()=>{Z(m,1)}),X()}s?(t=Ns(s,i(o)),q(t.$$.fragment),h(t.$$.fragment,1),N(t,l.parentNode,l)):t=null}else if(s){const m={};d&8&&(m.classNames="mr-1.5 "+o[3]),t.$set(m)}},i(o){a||(t&&h(t.$$.fragment,o),a=!0)},o(o){t&&_(t.$$.fragment,o),a=!1},d(o){o&&r(l),t&&Z(t,o)}}}function Na(n){let t,l;return t=new rl({props:{classNames:"-mr-1 text-gray-500"}}),{c(){q(t.$$.fragment)},l(a){G(t.$$.fragment,a)},m(a,s){N(t,a,s),l=!0},i(a){l||(h(t.$$.fragment,a),l=!0)},o(a){_(t.$$.fragment,a),l=!1},d(a){Z(t,a)}}}function Za(n){let t,l;return t=new nl({props:{classNames:n[6]+" "+(n[8]?"v2-dropdown-menu hidden":""),dropdownElement:n[10],forceAlignement:n[5],onClose:n[12],$$slots:{default:[fl]},$$scope:{ctx:n}}}),{c(){q(t.$$.fragment)},l(a){G(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||(h(t.$$.fragment,a),l=!0)},o(a){_(t.$$.fragment,a),l=!1},d(a){Z(t,a)}}}function fl(n){let t;const l=n[15].menu,a=A(l,n,n[18],Ta);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)&&R(a,l,s,s[18],t?Q(l,s[18],i,ul):Y(s[18]),Ta)},i(s){t||(h(a,s),t=!0)},o(s){_(a,s),t=!1},d(s){a&&a.d(s)}}}function pl(n){let t,l,a,s,i,o,d,m,b,C;const I=[dl,ml],W=[];function j(y,T){return y[13].button?0:1}a=j(n),s=W[a]=I[a](n);let g=(n[11]||n[8])&&Za(n);return{c(){t=w("div"),l=w("button"),s.c(),o=f(),g&&g.c(),this.h()},l(y){t=M(y,"DIV",{class:!0});var T=z(t);l=M(T,"BUTTON",{class:!0,type:!0});var $=z(l);s.l($),$.forEach(r),o=p(T),g&&g.l(T),T.forEach(r),this.h()},h(){v(l,"class",i=""+n[1]+" "+(n[7]?"":"cursor-pointer w-full btn text-sm")+" "+(n[8]?"v2-dropdown-button":"")),v(l,"type","button"),v(t,"class",d="relative "+n[0]+" "+(n[8]?"v2-dropdown":""))},m(y,T){c(y,t,T),D(t,l),W[a].m(l,null),D(t,o),g&&g.m(t,null),n[17](t),m=!0,b||(C=Ls(l,"click",n[16]),b=!0)},p(y,[T]){let $=a;a=j(y),a===$?W[a].p(y,T):(E(),_(W[$],1,1,()=>{W[$]=null}),X(),s=W[a],s?s.p(y,T):(s=W[a]=I[a](y),s.c()),h(s,1),s.m(l,null)),(!m||T&386&&i!==(i=""+y[1]+" "+(y[7]?"":"cursor-pointer w-full btn text-sm")+" "+(y[8]?"v2-dropdown-button":"")))&&v(l,"class",i),y[11]||y[8]?g?(g.p(y,T),T&2304&&h(g,1)):(g=Za(y),g.c(),h(g,1),g.m(t,null)):g&&(E(),_(g,1,1,()=>{g=null}),X()),(!m||T&257&&d!==(d="relative "+y[0]+" "+(y[8]?"v2-dropdown":"")))&&v(t,"class",d)},i(y){m||(h(s),h(g),m=!0)},o(y){_(s),_(g),m=!1},d(y){y&&r(t),W[a].d(),g&&g.d(),n[17](null),b=!1,C()}}}function gl(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:b=""}=t,{btnLabel:C=""}=t,{forceMenuAlignement:I=void 0}=t,{menuClassNames:W=""}=t,{noBtnClass:j=void 0}=t,{selectedValue:g=void 0}=t,{useDeprecatedJS:y=!0}=t,{withBtnCaret:T=!1}=t,$,S=!1;function U(L){var H;L.target&&(H=L.target)!=null&&H.className.includes("do-not-close-dropdown")||l(11,S=!1)}const J=()=>l(11,S=!S);function B(L){Is[L?"unshift":"push"](()=>{$=L,l(10,$)})}return n.$$set=L=>{"classNames"in L&&l(0,o=L.classNames),"btnClassNames"in L&&l(1,d=L.btnClassNames),"btnIcon"in L&&l(2,m=L.btnIcon),"btnIconClassNames"in L&&l(3,b=L.btnIconClassNames),"btnLabel"in L&&l(4,C=L.btnLabel),"forceMenuAlignement"in L&&l(5,I=L.forceMenuAlignement),"menuClassNames"in L&&l(6,W=L.menuClassNames),"noBtnClass"in L&&l(7,j=L.noBtnClass),"selectedValue"in L&&l(14,g=L.selectedValue),"useDeprecatedJS"in L&&l(8,y=L.useDeprecatedJS),"withBtnCaret"in L&&l(9,T=L.withBtnCaret),"$$scope"in L&&l(18,s=L.$$scope)},[o,d,m,b,C,I,W,j,y,T,$,S,U,i,g,a,J,B,s]}class Ya extends dt{constructor(t){super(),ft(this,t,gl,pl,mt,{classNames:0,btnClassNames:1,btnIcon:2,btnIconClassNames:3,btnLabel:4,forceMenuAlignement:5,menuClassNames:6,noBtnClass:7,selectedValue:14,useDeprecatedJS:8,withBtnCaret:9})}}function hl(n){let t,l,a,s=n[5]&&Ga(n);return{c(){s&&s.c(),t=f(),l=Xa(n[7])},l(i){s&&s.l(i),t=p(i),l=xa(i,n[7])},m(i,o){s&&s.m(i,o),c(i,t,o),c(i,l,o),a=!0},p(i,o){i[5]?s?(s.p(i,o),o&32&&h(s,1)):(s=Ga(i),s.c(),h(s,1),s.m(t.parentNode,t)):s&&(E(),_(s,1,1,()=>{s=null}),X()),(!a||o&128)&&Aa(l,i[7])},i(i){a||(h(s),a=!0)},o(i){_(s),a=!1},d(i){i&&(r(t),r(l)),s&&s.d(i)}}}function bl(n){let t;const l=n[15].default,a=A(l,n,n[14],null);return{c(){a&&a.c()},l(s){a&&a.l(s)},m(s,i){a&&a.m(s,i),t=!0},p(s,i){a&&a.p&&(!t||i&16384)&&R(a,l,s,s[14],t?Q(l,s[14],i,null):Y(s[14]),null)},i(s){t||(h(a,s),t=!0)},o(s){_(a,s),t=!1},d(s){a&&a.d(s)}}}function Ga(n){let t,l,a;var s=n[5];function i(o,d){return{props:{classNames:"mr-1.5 "+o[6]}}}return s&&(t=Ns(s,i(n))),{c(){t&&q(t.$$.fragment),l=x()},l(o){t&&G(t.$$.fragment,o),l=x()},m(o,d){t&&N(t,o,d),c(o,l,d),a=!0},p(o,d){if(d&32&&s!==(s=o[5])){if(t){E();const m=t;_(m.$$.fragment,1,0,()=>{Z(m,1)}),X()}s?(t=Ns(s,i(o)),q(t.$$.fragment),h(t.$$.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&&h(t.$$.fragment,o),a=!0)},o(o){t&&_(t.$$.fragment,o),a=!1},d(o){o&&r(l),t&&Z(t,o)}}}function _l(n){let t,l,a,s,i,o,d,m,b,C;const I=[bl,hl],W=[];function j(g,y){return g[13].default?0:1}return a=j(n),s=W[a]=I[a](n),{c(){t=w("li"),l=w("a"),s.c(),this.h()},l(g){t=M(g,"LI",{class:!0});var y=z(t);l=M(y,"A",{class:!0,"data-label":!0,"data-url":!0,"data-value":!0,href:!0,rel:!0,target:!0});var T=z(l);s.l(T),T.forEach(r),y.forEach(r),this.h()},h(){v(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":"")),v(l,"data-label",n[1]),v(l,"data-url",n[2]),v(l,"data-value",n[3]),v(l,"href",n[4]),v(l,"rel",o=n[8]?"nofollow":void 0),v(l,"target",d=n[11]?"_blank":void 0),v(t,"class","not-prose")},m(g,y){c(g,t,y),D(t,l),W[a].m(l,null),m=!0,b||(C=Ls(l,"click",function(){Da(n[10])&&n[10].apply(this,arguments)}),b=!0)},p(g,[y]){n=g;let T=a;a=j(n),a===T?W[a].p(n,y):(E(),_(W[T],1,1,()=>{W[T]=null}),X(),s=W[a],s?s.p(n,y):(s=W[a]=I[a](n),s.c()),h(s,1),s.m(l,null)),(!m||y&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":"")))&&v(l,"class",i),(!m||y&2)&&v(l,"data-label",n[1]),(!m||y&4)&&v(l,"data-url",n[2]),(!m||y&8)&&v(l,"data-value",n[3]),(!m||y&16)&&v(l,"href",n[4]),(!m||y&256&&o!==(o=n[8]?"nofollow":void 0))&&v(l,"rel",o),(!m||y&2048&&d!==(d=n[11]?"_blank":void 0))&&v(l,"target",d)},i(g){m||(h(s),m=!0)},o(g){_(s),m=!1},d(g){g&&r(t),W[a].d(),b=!1,C()}}}function wl(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:b=void 0}=t,{href:C=void 0}=t,{icon:I=void 0}=t,{iconClassNames:W=""}=t,{label:j=""}=t,{noFollow:g=!1}=t,{underline:y=!1}=t,{onClick:T=()=>{}}=t,{targetBlank:$=!1}=t,{useDeprecatedJS:S=!0}=t;return n.$$set=U=>{"classNames"in U&&l(0,o=U.classNames),"dataLabel"in U&&l(1,d=U.dataLabel),"dataUrl"in U&&l(2,m=U.dataUrl),"dataValue"in U&&l(3,b=U.dataValue),"href"in U&&l(4,C=U.href),"icon"in U&&l(5,I=U.icon),"iconClassNames"in U&&l(6,W=U.iconClassNames),"label"in U&&l(7,j=U.label),"noFollow"in U&&l(8,g=U.noFollow),"underline"in U&&l(9,y=U.underline),"onClick"in U&&l(10,T=U.onClick),"targetBlank"in U&&l(11,$=U.targetBlank),"useDeprecatedJS"in U&&l(12,S=U.useDeprecatedJS),"$$scope"in U&&l(14,s=U.$$scope)},[o,d,m,b,C,I,W,j,g,y,T,$,S,i,s,a]}class Qa extends dt{constructor(t){super(),ft(this,t,wl,_l,mt,{classNames:0,dataLabel:1,dataUrl:2,dataValue:3,href:4,icon:5,iconClassNames:6,label:7,noFollow:8,underline:9,onClick:10,targetBlank:11,useDeprecatedJS:12})}}const{window:Ml}=el,vl=n=>({}),La=n=>({slot:"button"});function Wa(n,t,l){const a=n.slice();return a[11]=t[l].label,a[12]=t[l].value,a}const yl=n=>({}),Ia=n=>({slot:"menu"}),jl=n=>({}),$a=n=>({slot:"button"});function Ba(n,t,l){const a=n.slice();return a[11]=t[l].label,a[12]=t[l].value,a}const kl=n=>({}),Va=n=>({slot:"menu"}),Cl=n=>({}),Sa=n=>({});function Ul(n){let t,l;return t=new Ya({props:{btnLabel:"",classNames:"colab-dropdown",noBtnClass:!0,useDeprecatedJS:!1,$$slots:{menu:[Zl],button:[ql]},$$scope:{ctx:n}}}),{c(){q(t.$$.fragment)},l(a){G(t.$$.fragment,a)},m(a,s){N(t,a,s),l=!0},p(a,s){const i={};s&1024&&(i.$$scope={dirty:s,ctx:a}),t.$set(i)},i(a){l||(h(t.$$.fragment,a),l=!0)},o(a){_(t.$$.fragment,a),l=!1},d(a){Z(t,a)}}}function Tl(n){let t,l,a;return{c(){t=w("a"),l=w("img"),this.h()},l(s){t=M(s,"A",{href:!0,target:!0});var i=z(t);l=M(i,"IMG",{alt:!0,class:!0,src:!0}),i.forEach(r),this.h()},h(){v(l,"alt","Open In Colab"),v(l,"class","!m-0"),Gs(l.src,a="https://colab.research.google.com/assets/colab-badge.svg")||v(l,"src",a),v(t,"href",n[2][0].value),v(t,"target","_blank")},m(s,i){c(s,t,i),D(t,l)},p:P,i:P,o:P,d(s){s&&r(t)}}}function Jl(n){let t,l;return{c(){t=w("img"),this.h()},l(a){t=M(a,"IMG",{alt:!0,class:!0,src:!0}),this.h()},h(){v(t,"alt","Open In Colab"),v(t,"class","!m-0"),Gs(t.src,l="https://colab.research.google.com/assets/colab-badge.svg")||v(t,"src",l)},m(a,s){c(a,t,s)},p:P,d(a){a&&r(t)}}}function ql(n){let t;const l=n[6].default,a=A(l,n,n[10],$a),s=a||Jl();return{c(){s&&s.c()},l(i){s&&s.l(i)},m(i,o){s&&s.m(i,o),t=!0},p(i,o){a&&a.p&&(!t||o&1024)&&R(a,l,i,i[10],t?Q(l,i[10],o,jl):Y(i[10]),$a)},i(i){t||(h(s,i),t=!0)},o(i){_(s,i),t=!1},d(i){s&&s.d(i)}}}function za(n){let t,l;function a(){return n[7](n[12])}return t=new Qa({props:{classNames:"text-sm !no-underline",iconClassNames:"text-gray-500",label:n[11],onClick:a,useDeprecatedJS:!1}}),{c(){q(t.$$.fragment)},l(s){G(t.$$.fragment,s)},m(s,i){N(t,s,i),l=!0},p(s,i){n=s},i(s){l||(h(t.$$.fragment,s),l=!0)},o(s){_(t.$$.fragment,s),l=!1},d(s){Z(t,s)}}}function Nl(n){let t,l,a=Zs(n[2]),s=[];for(let o=0;o<a.length;o+=1)s[o]=za(Ba(n,a,o));const i=o=>_(s[o],1,1,()=>{s[o]=null});return{c(){for(let o=0;o<s.length;o+=1)s[o].c();t=x()},l(o){for(let d=0;d<s.length;d+=1)s[d].l(o);t=x()},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=Zs(o[2]);let m;for(m=0;m<a.length;m+=1){const b=Ba(o,a,m);s[m]?(s[m].p(b,d),h(s[m],1)):(s[m]=za(b),s[m].c(),h(s[m],1),s[m].m(t.parentNode,t))}for(E(),m=a.length;m<s.length;m+=1)i(m);X()}},i(o){if(!l){for(let d=0;d<a.length;d+=1)h(s[d]);l=!0}},o(o){s=s.filter(Boolean);for(let d=0;d<s.length;d+=1)_(s[d]);l=!1},d(o){o&&r(t),Ra(s,o)}}}function Zl(n){let t;const l=n[6].default,a=A(l,n,n[10],Va),s=a||Nl(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&1024)&&R(a,l,i,i[10],t?Q(l,i[10],o,kl):Y(i[10]),Va)},i(i){t||(h(s,i),t=!0)},o(i){_(s,i),t=!1},d(i){s&&s.d(i)}}}function Gl(n){let t,l;return t=new Ya({props:{btnLabel:"",classNames:"colab-dropdown",noBtnClass:!0,useDeprecatedJS:!1,$$slots:{menu:[Bl],button:[Il]},$$scope:{ctx:n}}}),{c(){q(t.$$.fragment)},l(a){G(t.$$.fragment,a)},m(a,s){N(t,a,s),l=!0},p(a,s){const i={};s&1024&&(i.$$scope={dirty:s,ctx:a}),t.$set(i)},i(a){l||(h(t.$$.fragment,a),l=!0)},o(a){_(t.$$.fragment,a),l=!1},d(a){Z(t,a)}}}function Ll(n){let t,l,a;return{c(){t=w("a"),l=w("img"),this.h()},l(s){t=M(s,"A",{href:!0,target:!0});var i=z(t);l=M(i,"IMG",{alt:!0,class:!0,src:!0}),i.forEach(r),this.h()},h(){v(l,"alt","Open In Studio Lab"),v(l,"class","!m-0"),Gs(l.src,a="https://studiolab.sagemaker.aws/studiolab.svg")||v(l,"src",a),v(t,"href",n[3][0].value),v(t,"target","_blank")},m(s,i){c(s,t,i),D(t,l)},p:P,i:P,o:P,d(s){s&&r(t)}}}function Wl(n){let t,l;return{c(){t=w("img"),this.h()},l(a){t=M(a,"IMG",{alt:!0,class:!0,src:!0}),this.h()},h(){v(t,"alt","Open In Studio Lab"),v(t,"class","!m-0"),Gs(t.src,l="https://studiolab.sagemaker.aws/studiolab.svg")||v(t,"src",l)},m(a,s){c(a,t,s)},p:P,d(a){a&&r(t)}}}function Il(n){let t;const l=n[6].default,a=A(l,n,n[10],La),s=a||Wl();return{c(){s&&s.c()},l(i){s&&s.l(i)},m(i,o){s&&s.m(i,o),t=!0},p(i,o){a&&a.p&&(!t||o&1024)&&R(a,l,i,i[10],t?Q(l,i[10],o,vl):Y(i[10]),La)},i(i){t||(h(s,i),t=!0)},o(i){_(s,i),t=!1},d(i){s&&s.d(i)}}}function Ha(n){let t,l;function a(){return n[8](n[12])}return t=new Qa({props:{classNames:"text-sm !no-underline",iconClassNames:"text-gray-500",label:n[11],onClick:a,useDeprecatedJS:!1}}),{c(){q(t.$$.fragment)},l(s){G(t.$$.fragment,s)},m(s,i){N(t,s,i),l=!0},p(s,i){n=s},i(s){l||(h(t.$$.fragment,s),l=!0)},o(s){_(t.$$.fragment,s),l=!1},d(s){Z(t,s)}}}function $l(n){let t,l,a=Zs(n[3]),s=[];for(let o=0;o<a.length;o+=1)s[o]=Ha(Wa(n,a,o));const i=o=>_(s[o],1,1,()=>{s[o]=null});return{c(){for(let o=0;o<s.length;o+=1)s[o].c();t=x()},l(o){for(let d=0;d<s.length;d+=1)s[d].l(o);t=x()},m(o,d){for(let m=0;m<s.length;m+=1)s[m]&&s[m].m(o,d);c(o,t,d),l=!0},p(o,d){if(d&8){a=Zs(o[3]);let m;for(m=0;m<a.length;m+=1){const b=Wa(o,a,m);s[m]?(s[m].p(b,d),h(s[m],1)):(s[m]=Ha(b),s[m].c(),h(s[m],1),s[m].m(t.parentNode,t))}for(E(),m=a.length;m<s.length;m+=1)i(m);X()}},i(o){if(!l){for(let d=0;d<a.length;d+=1)h(s[d]);l=!0}},o(o){s=s.filter(Boolean);for(let d=0;d<s.length;d+=1)_(s[d]);l=!1},d(o){o&&r(t),Ra(s,o)}}}function Bl(n){let t;const l=n[6].default,a=A(l,n,n[10],Ia),s=a||$l(n);return{c(){s&&s.c()},l(i){s&&s.l(i)},m(i,o){s&&s.m(i,o),t=!0},p(i,o){a&&a.p&&(!t||o&1024)&&R(a,l,i,i[10],t?Q(l,i[10],o,yl):Y(i[10]),Ia)},i(i){t||(h(s,i),t=!0)},o(i){_(s,i),t=!1},d(i){s&&s.d(i)}}}function Vl(n){let t,l,a,s,i,o,d,m,b,C,I;const W=n[6].alwaysVisible,j=A(W,n,n[10],Sa),g=[Tl,Ul],y=[];function T(J,B){return J[2].length===1?0:J[2].length>1?1:-1}~(a=T(n))&&(s=y[a]=g[a](n));const $=[Ll,Gl],S=[];function U(J,B){return J[3].length===1?0:J[3].length>1?1:-1}return~(o=U(n))&&(d=S[o]=$[o](n)),{c(){t=w("div"),j&&j.c(),l=f(),s&&s.c(),i=f(),d&&d.c(),this.h()},l(J){t=M(J,"DIV",{class:!0});var B=z(t);j&&j.l(B),l=p(B),s&&s.l(B),i=p(B),d&&d.l(B),B.forEach(r),this.h()},h(){v(t,"class",m="flex space-x-1 "+n[0])},m(J,B){c(J,t,B),j&&j.m(t,null),D(t,l),~a&&y[a].m(t,null),D(t,i),~o&&S[o].m(t,null),n[9](t),b=!0,C||(I=Ls(Ml,"resize",n[4]),C=!0)},p(J,[B]){j&&j.p&&(!b||B&1024)&&R(j,W,J,J[10],b?Q(W,J[10],B,Cl):Y(J[10]),Sa),s&&s.p(J,B),d&&d.p(J,B),(!b||B&1&&m!==(m="flex space-x-1 "+J[0]))&&v(t,"class",m)},i(J){b||(h(j,J),h(s),h(d),b=!0)},o(J){_(j,J),_(s),_(d),b=!1},d(J){J&&r(t),j&&j.d(J),~a&&y[a].d(),~o&&S[o].d(),n[9](null),C=!1,I()}}}function Pa(n){window.open(n)}function Sl(n,t,l){let{$$slots:a={},$$scope:s}=t,{options:i=[]}=t,{classNames:o=""}=t,d;const m=i.filter(g=>g.value.includes("colab.research.google.com")),b=i.filter(g=>g.value.includes("studiolab.sagemaker.aws"));function C(){const g=document.querySelector(".prose-doc h1"),y=document.querySelector(".prose-doc h1 > span");if(g&&y){const{width:T}=g.getBoundingClientRect(),{width:$}=y.getBoundingClientRect();let S=0;for(let J=0;J<d.children.length;J++){const B=d.children.item(J);B&&(S+=B.clientWidth)}const U=20;T-$<S+U?d.classList.remove("absolute"):d.classList.add("absolute")}}Ws(()=>{(async()=>(await Fa(),C()))()});const I=g=>Pa(g),W=g=>Pa(g);function j(g){Is[g?"unshift":"push"](()=>{d=g,l(1,d)})}return n.$$set=g=>{"options"in g&&l(5,i=g.options),"classNames"in g&&l(0,o=g.classNames),"$$scope"in g&&l(10,s=g.$$scope)},[o,d,m,b,C,i,a,I,W,j,s]}class zl extends dt{constructor(t){super(),ft(this,t,Sl,Vl,mt,{options:5,classNames:0})}}function Hl(n){let t,l,a,s,i,o,d,m,b,C,I,W="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.",j,g,y="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:",T,$,S='<li>O <code>DiffusionPipeline</code> é uma classe de alto nível de ponta a ponta desenhada para gerar rapidamente amostras de modelos de difusão pré-treinados para inferência.</li> <li><a href="./api/models">Modelos</a> pré-treinados populares e módulos que podem ser usados como blocos de construção para criar sistemas de difusão.</li> <li>Vários <a href="./api/schedulers/overview">Agendadores</a> diferentes - algoritmos que controlam como o ruído é adicionado para treinamento, e como gerar imagens sem o ruído durante a inferência.</li>',U,J,B="Esse tour rápido mostrará como usar o <code>DiffusionPipeline</code> para inferência, e então mostrará como combinar um modelo e um agendador para replicar o que está acontecendo dentro do <code>DiffusionPipeline</code>.",L,H,$s='<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,se,Bs="Antes de começar, certifique-se de ter todas as bibliotecas necessárias instaladas:",ht,ae,bt,le,Vs='<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,ne,wt,oe,Ss='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>.',Mt,ie,zs='<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,re,Hs=`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,F,Ps='<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,ue,Ds="Para carregar o modelo com o método <code>from_pretrained()</code>:",kt,ce,Ct,me,Es="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,de,Tt,fe,Xs=`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,pe,qt,ge,xs='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>.',Nt,he,Zt,K,As='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/image_of_squirrel_painting.png"/>',Gt,be,Rs="Salve a imagem chamando o <code>save</code>:",Lt,_e,Wt,we,It,Me,Ys="Você também pode utilizar o pipeline localmente. A única diferença é que você precisa baixar os pesos primeiro:",$t,ve,Bt,ye,Qs="Assim carregue os pesos salvos no pipeline:",Vt,je,St,ke,Fs="Agora você pode rodar o pipeline como você faria na seção acima.",zt,Ce,Ht,Ue,Ks="Agendadores diferentes tem diferentes velocidades de retirar o ruído e compensações de qualidade. A melhor forma de descobrir qual funciona melhor para você é testar eles! Uma das principais características do 🧨 Diffusers é permitir que você troque facilmente entre agendadores. Por exemplo, para substituir o <code>PNDMScheduler</code> padrão com o <code>EulerDiscreteScheduler</code>, carregue ele com o método <code>from_config()</code>:",Pt,Te,Dt,Je,Os="Tente gerar uma imagem com o novo agendador e veja se você nota alguma diferença!",Et,qe,ea="Na próxima seção, você irá dar uma olhada mais de perto nos componentes - o modelo e o agendador - que compõe o <code>DiffusionPipeline</code> e aprender como usar esses componentes para gerar uma imagem de um gato.",Xt,Ne,xt,Ze,ta='A maioria dos modelos recebe uma amostra de ruído, e em cada <em>timestep</em> ele prevê o <em>noise residual</em> (outros modelos aprendem a prever a amostra anterior diretamente ou a velocidade ou <a href="https://github.com/huggingface/diffusers/blob/5e5ce13e2f89ac45a0066cb3f369462a3cf1d9ef/src/diffusers/schedulers/scheduling_ddim.py#L110" rel="nofollow"><code>v-prediction</code></a>), a diferença entre uma imagem menos com ruído e a imagem de entrada. Você pode misturar e combinar modelos para criar outros sistemas de difusão.',At,Ge,sa="Modelos são inicializados com o método <code>from_pretrained()</code> que também armazena em cache localmente os pesos do modelo para que seja mais rápido na próxima vez que você carregar o modelo. Para o tour rápido, você irá carregar o <code>UNet2DModel</code>, um modelo básico de geração de imagem incondicional com um checkpoint treinado em imagens de gato:",Rt,Le,Yt,We,aa="Para acessar os parâmetros do modelo, chame <code>model.config</code>:",Qt,Ie,Ft,$e,la="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,Be,na="Um dos parâmetros mais importantes são:",Ot,Ve,oa="<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,Se,ia="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,ze,ss,He,ra="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,Pe,ls,De,ua="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,Ee,os,Xe,ca="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,O,ma="<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,da="Para o tour rápido, você irá instanciar o <code>DDPMScheduler</code> com o método <code>from_config()</code>:",us,Ae,cs,ee,fa="<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,Re,pa="Um dos parâmetros mais importante são:",ds,Ye,ga="<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,Qe,ha="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,Fe,gs,Ke,ba="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,Oe,_a="Comece, criando a função que faça o pós-processamento e mostre a imagem sem ruído como uma <code>PIL.Image</code>:",bs,et,_s,tt,wa="Para acelerar o processo de retirada de ruído, mova a entrada e o modelo para uma GPU:",ws,st,Ms,at,Ma="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,lt,ys,nt,va="Sente-se e assista o gato ser gerado do nada além de ruído! 😻",js,te,ya='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/diffusion-quicktour.png"/>',ks,ot,Cs,it,ja="Esperamos que você tenha gerado algumas imagens legais com o 🧨 Diffusers neste tour rápido! Para suas próximas etapas, você pode",Us,rt,ka='<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,ut,Js,pt,qs;return i=new zl({props:{classNames:"absolute z-10 right-0 top-0",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"}]}}),d=new tl({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),b=new ct({props:{title:"Tour rápido",local:"tour-rápido",headingTag:"h1"}}),ae=new V({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}}),ne=new ct({props:{title:"DiffusionPipeline",local:"diffusionpipeline",headingTag:"h2"}}),ce=new V({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}}),de=new V({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}}),pe=new V({props:{code:"cGlwZWxpbmUudG8oJTIyY3VkYSUyMik=",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)',wrap:!1}}),he=new V({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}}),_e=new V({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}}),we=new ct({props:{title:"Pipeline local",local:"pipeline-local",headingTag:"h3"}}),ve=new V({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}}),je=new V({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}}),Ce=new ct({props:{title:"Troca dos agendadores",local:"troca-dos-agendadores",headingTag:"h3"}}),Te=new V({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}}),Ne=new ct({props:{title:"Modelos",local:"modelos",headingTag:"h2"}}),Le=new V({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 V({props:{code:"bW9kZWwuY29uZmln",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span>model.config',wrap:!1}}),ze=new V({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}}),Pe=new V({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}}),Ee=new ct({props:{title:"Agendadores",local:"agendadores",headingTag:"h2"}}),Ae=new V({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}}),Fe=new V({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}}),et=new V({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}}),st=new V({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}}),lt=new V({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}}),ot=new ct({props:{title:"Próximos passos",local:"próximos-passos",headingTag:"h2"}}),ut=new sl({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/pt/quicktour.md"}}),{c(){t=w("meta"),l=f(),a=w("p"),s=f(),q(i.$$.fragment),o=f(),q(d.$$.fragment),m=f(),q(b.$$.fragment),C=f(),I=w("p"),I.textContent=W,j=f(),g=w("p"),g.textContent=y,T=f(),$=w("ul"),$.innerHTML=S,U=f(),J=w("p"),J.innerHTML=B,L=f(),H=w("blockquote"),H.innerHTML=$s,gt=f(),se=w("p"),se.textContent=Bs,ht=f(),q(ae.$$.fragment),bt=f(),le=w("ul"),le.innerHTML=Vs,_t=f(),q(ne.$$.fragment),wt=f(),oe=w("p"),oe.innerHTML=Ss,Mt=f(),ie=w("table"),ie.innerHTML=zs,vt=f(),re=w("p"),re.innerHTML=Hs,yt=f(),F=w("blockquote"),F.innerHTML=Ps,jt=f(),ue=w("p"),ue.innerHTML=Ds,kt=f(),q(ce.$$.fragment),Ct=f(),me=w("p"),me.innerHTML=Es,Ut=f(),q(de.$$.fragment),Tt=f(),fe=w("p"),fe.textContent=Xs,Jt=f(),q(pe.$$.fragment),qt=f(),ge=w("p"),ge.innerHTML=xs,Nt=f(),q(he.$$.fragment),Zt=f(),K=w("div"),K.innerHTML=As,Gt=f(),be=w("p"),be.innerHTML=Rs,Lt=f(),q(_e.$$.fragment),Wt=f(),q(we.$$.fragment),It=f(),Me=w("p"),Me.textContent=Ys,$t=f(),q(ve.$$.fragment),Bt=f(),ye=w("p"),ye.textContent=Qs,Vt=f(),q(je.$$.fragment),St=f(),ke=w("p"),ke.textContent=Fs,zt=f(),q(Ce.$$.fragment),Ht=f(),Ue=w("p"),Ue.innerHTML=Ks,Pt=f(),q(Te.$$.fragment),Dt=f(),Je=w("p"),Je.textContent=Os,Et=f(),qe=w("p"),qe.innerHTML=ea,Xt=f(),q(Ne.$$.fragment),xt=f(),Ze=w("p"),Ze.innerHTML=ta,At=f(),Ge=w("p"),Ge.innerHTML=sa,Rt=f(),q(Le.$$.fragment),Yt=f(),We=w("p"),We.innerHTML=aa,Qt=f(),q(Ie.$$.fragment),Ft=f(),$e=w("p"),$e.textContent=la,Kt=f(),Be=w("p"),Be.textContent=na,Ot=f(),Ve=w("ul"),Ve.innerHTML=oa,es=f(),Se=w("p"),Se.innerHTML=ia,ts=f(),q(ze.$$.fragment),ss=f(),He=w("p"),He.innerHTML=ra,as=f(),q(Pe.$$.fragment),ls=f(),De=w("p"),De.textContent=ua,ns=f(),q(Ee.$$.fragment),os=f(),Xe=w("p"),Xe.innerHTML=ca,is=f(),O=w("blockquote"),O.innerHTML=ma,rs=f(),xe=w("p"),xe.innerHTML=da,us=f(),q(Ae.$$.fragment),cs=f(),ee=w("blockquote"),ee.innerHTML=fa,ms=f(),Re=w("p"),Re.textContent=pa,ds=f(),Ye=w("ul"),Ye.innerHTML=ga,fs=f(),Qe=w("p"),Qe.innerHTML=ha,ps=f(),q(Fe.$$.fragment),gs=f(),Ke=w("p"),Ke.innerHTML=ba,hs=f(),Oe=w("p"),Oe.innerHTML=_a,bs=f(),q(et.$$.fragment),_s=f(),tt=w("p"),tt.textContent=wa,ws=f(),q(st.$$.fragment),Ms=f(),at=w("p"),at.textContent=Ma,vs=f(),q(lt.$$.fragment),ys=f(),nt=w("p"),nt.textContent=va,js=f(),te=w("div"),te.innerHTML=ya,ks=f(),q(ot.$$.fragment),Cs=f(),it=w("p"),it.textContent=ja,Us=f(),rt=w("ul"),rt.innerHTML=ka,Ts=f(),q(ut.$$.fragment),Js=f(),pt=w("p"),this.h()},l(e){const u=Oa("svelte-u9bgzb",document.head);t=M(u,"META",{name:!0,content:!0}),u.forEach(r),l=p(e),a=M(e,"P",{}),z(a).forEach(r),s=p(e),G(i.$$.fragment,e),o=p(e),G(d.$$.fragment,e),m=p(e),G(b.$$.fragment,e),C=p(e),I=M(e,"P",{"data-svelte-h":!0}),k(I)!=="svelte-5d3hlg"&&(I.textContent=W),j=p(e),g=M(e,"P",{"data-svelte-h":!0}),k(g)!=="svelte-tkfmfk"&&(g.textContent=y),T=p(e),$=M(e,"UL",{"data-svelte-h":!0}),k($)!=="svelte-1bp7yfw"&&($.innerHTML=S),U=p(e),J=M(e,"P",{"data-svelte-h":!0}),k(J)!=="svelte-sqpmf8"&&(J.innerHTML=B),L=p(e),H=M(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),k(H)!=="svelte-mhj3h4"&&(H.innerHTML=$s),gt=p(e),se=M(e,"P",{"data-svelte-h":!0}),k(se)!=="svelte-16jlltr"&&(se.textContent=Bs),ht=p(e),G(ae.$$.fragment,e),bt=p(e),le=M(e,"UL",{"data-svelte-h":!0}),k(le)!=="svelte-l49o4a"&&(le.innerHTML=Vs),_t=p(e),G(ne.$$.fragment,e),wt=p(e),oe=M(e,"P",{"data-svelte-h":!0}),k(oe)!=="svelte-1fm3zhc"&&(oe.innerHTML=Ss),Mt=p(e),ie=M(e,"TABLE",{"data-svelte-h":!0}),k(ie)!=="svelte-1wldcuj"&&(ie.innerHTML=zs),vt=p(e),re=M(e,"P",{"data-svelte-h":!0}),k(re)!=="svelte-1ywycy7"&&(re.innerHTML=Hs),yt=p(e),F=M(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),k(F)!=="svelte-eq1ac4"&&(F.innerHTML=Ps),jt=p(e),ue=M(e,"P",{"data-svelte-h":!0}),k(ue)!=="svelte-14st4zt"&&(ue.innerHTML=Ds),kt=p(e),G(ce.$$.fragment,e),Ct=p(e),me=M(e,"P",{"data-svelte-h":!0}),k(me)!=="svelte-15d6klf"&&(me.innerHTML=Es),Ut=p(e),G(de.$$.fragment,e),Tt=p(e),fe=M(e,"P",{"data-svelte-h":!0}),k(fe)!=="svelte-1lh10u2"&&(fe.textContent=Xs),Jt=p(e),G(pe.$$.fragment,e),qt=p(e),ge=M(e,"P",{"data-svelte-h":!0}),k(ge)!=="svelte-1fzeyvx"&&(ge.innerHTML=xs),Nt=p(e),G(he.$$.fragment,e),Zt=p(e),K=M(e,"DIV",{class:!0,"data-svelte-h":!0}),k(K)!=="svelte-6cjtp1"&&(K.innerHTML=As),Gt=p(e),be=M(e,"P",{"data-svelte-h":!0}),k(be)!=="svelte-1qpz3ys"&&(be.innerHTML=Rs),Lt=p(e),G(_e.$$.fragment,e),Wt=p(e),G(we.$$.fragment,e),It=p(e),Me=M(e,"P",{"data-svelte-h":!0}),k(Me)!=="svelte-11z96s9"&&(Me.textContent=Ys),$t=p(e),G(ve.$$.fragment,e),Bt=p(e),ye=M(e,"P",{"data-svelte-h":!0}),k(ye)!=="svelte-nca5xy"&&(ye.textContent=Qs),Vt=p(e),G(je.$$.fragment,e),St=p(e),ke=M(e,"P",{"data-svelte-h":!0}),k(ke)!=="svelte-18fxe39"&&(ke.textContent=Fs),zt=p(e),G(Ce.$$.fragment,e),Ht=p(e),Ue=M(e,"P",{"data-svelte-h":!0}),k(Ue)!=="svelte-1bdwzfu"&&(Ue.innerHTML=Ks),Pt=p(e),G(Te.$$.fragment,e),Dt=p(e),Je=M(e,"P",{"data-svelte-h":!0}),k(Je)!=="svelte-rjqaf3"&&(Je.textContent=Os),Et=p(e),qe=M(e,"P",{"data-svelte-h":!0}),k(qe)!=="svelte-yp9if5"&&(qe.innerHTML=ea),Xt=p(e),G(Ne.$$.fragment,e),xt=p(e),Ze=M(e,"P",{"data-svelte-h":!0}),k(Ze)!=="svelte-cl1ldd"&&(Ze.innerHTML=ta),At=p(e),Ge=M(e,"P",{"data-svelte-h":!0}),k(Ge)!=="svelte-onulph"&&(Ge.innerHTML=sa),Rt=p(e),G(Le.$$.fragment,e),Yt=p(e),We=M(e,"P",{"data-svelte-h":!0}),k(We)!=="svelte-qcoyrg"&&(We.innerHTML=aa),Qt=p(e),G(Ie.$$.fragment,e),Ft=p(e),$e=M(e,"P",{"data-svelte-h":!0}),k($e)!=="svelte-i890oq"&&($e.textContent=la),Kt=p(e),Be=M(e,"P",{"data-svelte-h":!0}),k(Be)!=="svelte-1wzn7ma"&&(Be.textContent=na),Ot=p(e),Ve=M(e,"UL",{"data-svelte-h":!0}),k(Ve)!=="svelte-o5msyb"&&(Ve.innerHTML=oa),es=p(e),Se=M(e,"P",{"data-svelte-h":!0}),k(Se)!=="svelte-obxecp"&&(Se.innerHTML=ia),ts=p(e),G(ze.$$.fragment,e),ss=p(e),He=M(e,"P",{"data-svelte-h":!0}),k(He)!=="svelte-1qo9t3f"&&(He.innerHTML=ra),as=p(e),G(Pe.$$.fragment,e),ls=p(e),De=M(e,"P",{"data-svelte-h":!0}),k(De)!=="svelte-1ljqqs3"&&(De.textContent=ua),ns=p(e),G(Ee.$$.fragment,e),os=p(e),Xe=M(e,"P",{"data-svelte-h":!0}),k(Xe)!=="svelte-1c3rc74"&&(Xe.innerHTML=ca),is=p(e),O=M(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),k(O)!=="svelte-kw0jm4"&&(O.innerHTML=ma),rs=p(e),xe=M(e,"P",{"data-svelte-h":!0}),k(xe)!=="svelte-7pekzf"&&(xe.innerHTML=da),us=p(e),G(Ae.$$.fragment,e),cs=p(e),ee=M(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),k(ee)!=="svelte-1o3oicu"&&(ee.innerHTML=fa),ms=p(e),Re=M(e,"P",{"data-svelte-h":!0}),k(Re)!=="svelte-kydn7r"&&(Re.textContent=pa),ds=p(e),Ye=M(e,"UL",{"data-svelte-h":!0}),k(Ye)!=="svelte-1xnw77s"&&(Ye.innerHTML=ga),fs=p(e),Qe=M(e,"P",{"data-svelte-h":!0}),k(Qe)!=="svelte-3wttzd"&&(Qe.innerHTML=ha),ps=p(e),G(Fe.$$.fragment,e),gs=p(e),Ke=M(e,"P",{"data-svelte-h":!0}),k(Ke)!=="svelte-1tpggdq"&&(Ke.innerHTML=ba),hs=p(e),Oe=M(e,"P",{"data-svelte-h":!0}),k(Oe)!=="svelte-1xrm0cs"&&(Oe.innerHTML=_a),bs=p(e),G(et.$$.fragment,e),_s=p(e),tt=M(e,"P",{"data-svelte-h":!0}),k(tt)!=="svelte-19fphdr"&&(tt.textContent=wa),ws=p(e),G(st.$$.fragment,e),Ms=p(e),at=M(e,"P",{"data-svelte-h":!0}),k(at)!=="svelte-1ff49gu"&&(at.textContent=Ma),vs=p(e),G(lt.$$.fragment,e),ys=p(e),nt=M(e,"P",{"data-svelte-h":!0}),k(nt)!=="svelte-1tdl2pq"&&(nt.textContent=va),js=p(e),te=M(e,"DIV",{class:!0,"data-svelte-h":!0}),k(te)!=="svelte-1yzsrw6"&&(te.innerHTML=ya),ks=p(e),G(ot.$$.fragment,e),Cs=p(e),it=M(e,"P",{"data-svelte-h":!0}),k(it)!=="svelte-tfhhyg"&&(it.textContent=ja),Us=p(e),rt=M(e,"UL",{"data-svelte-h":!0}),k(rt)!=="svelte-1r1xmc2"&&(rt.innerHTML=ka),Ts=p(e),G(ut.$$.fragment,e),Js=p(e),pt=M(e,"P",{}),z(pt).forEach(r),this.h()},h(){v(t,"name","hf:doc:metadata"),v(t,"content",Pl),v(H,"class","tip"),v(F,"class","warning"),v(K,"class","flex justify-center"),v(O,"class","tip"),v(ee,"class","tip"),v(te,"class","flex justify-center")},m(e,u){D(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(b,e,u),c(e,C,u),c(e,I,u),c(e,j,u),c(e,g,u),c(e,T,u),c(e,$,u),c(e,U,u),c(e,J,u),c(e,L,u),c(e,H,u),c(e,gt,u),c(e,se,u),c(e,ht,u),N(ae,e,u),c(e,bt,u),c(e,le,u),c(e,_t,u),N(ne,e,u),c(e,wt,u),c(e,oe,u),c(e,Mt,u),c(e,ie,u),c(e,vt,u),c(e,re,u),c(e,yt,u),c(e,F,u),c(e,jt,u),c(e,ue,u),c(e,kt,u),N(ce,e,u),c(e,Ct,u),c(e,me,u),c(e,Ut,u),N(de,e,u),c(e,Tt,u),c(e,fe,u),c(e,Jt,u),N(pe,e,u),c(e,qt,u),c(e,ge,u),c(e,Nt,u),N(he,e,u),c(e,Zt,u),c(e,K,u),c(e,Gt,u),c(e,be,u),c(e,Lt,u),N(_e,e,u),c(e,Wt,u),N(we,e,u),c(e,It,u),c(e,Me,u),c(e,$t,u),N(ve,e,u),c(e,Bt,u),c(e,ye,u),c(e,Vt,u),N(je,e,u),c(e,St,u),c(e,ke,u),c(e,zt,u),N(Ce,e,u),c(e,Ht,u),c(e,Ue,u),c(e,Pt,u),N(Te,e,u),c(e,Dt,u),c(e,Je,u),c(e,Et,u),c(e,qe,u),c(e,Xt,u),N(Ne,e,u),c(e,xt,u),c(e,Ze,u),c(e,At,u),c(e,Ge,u),c(e,Rt,u),N(Le,e,u),c(e,Yt,u),c(e,We,u),c(e,Qt,u),N(Ie,e,u),c(e,Ft,u),c(e,$e,u),c(e,Kt,u),c(e,Be,u),c(e,Ot,u),c(e,Ve,u),c(e,es,u),c(e,Se,u),c(e,ts,u),N(ze,e,u),c(e,ss,u),c(e,He,u),c(e,as,u),N(Pe,e,u),c(e,ls,u),c(e,De,u),c(e,ns,u),N(Ee,e,u),c(e,os,u),c(e,Xe,u),c(e,is,u),c(e,O,u),c(e,rs,u),c(e,xe,u),c(e,us,u),N(Ae,e,u),c(e,cs,u),c(e,ee,u),c(e,ms,u),c(e,Re,u),c(e,ds,u),c(e,Ye,u),c(e,fs,u),c(e,Qe,u),c(e,ps,u),N(Fe,e,u),c(e,gs,u),c(e,Ke,u),c(e,hs,u),c(e,Oe,u),c(e,bs,u),N(et,e,u),c(e,_s,u),c(e,tt,u),c(e,ws,u),N(st,e,u),c(e,Ms,u),c(e,at,u),c(e,vs,u),N(lt,e,u),c(e,ys,u),c(e,nt,u),c(e,js,u),c(e,te,u),c(e,ks,u),N(ot,e,u),c(e,Cs,u),c(e,it,u),c(e,Us,u),c(e,rt,u),c(e,Ts,u),N(ut,e,u),c(e,Js,u),c(e,pt,u),qs=!0},p:P,i(e){qs||(h(i.$$.fragment,e),h(d.$$.fragment,e),h(b.$$.fragment,e),h(ae.$$.fragment,e),h(ne.$$.fragment,e),h(ce.$$.fragment,e),h(de.$$.fragment,e),h(pe.$$.fragment,e),h(he.$$.fragment,e),h(_e.$$.fragment,e),h(we.$$.fragment,e),h(ve.$$.fragment,e),h(je.$$.fragment,e),h(Ce.$$.fragment,e),h(Te.$$.fragment,e),h(Ne.$$.fragment,e),h(Le.$$.fragment,e),h(Ie.$$.fragment,e),h(ze.$$.fragment,e),h(Pe.$$.fragment,e),h(Ee.$$.fragment,e),h(Ae.$$.fragment,e),h(Fe.$$.fragment,e),h(et.$$.fragment,e),h(st.$$.fragment,e),h(lt.$$.fragment,e),h(ot.$$.fragment,e),h(ut.$$.fragment,e),qs=!0)},o(e){_(i.$$.fragment,e),_(d.$$.fragment,e),_(b.$$.fragment,e),_(ae.$$.fragment,e),_(ne.$$.fragment,e),_(ce.$$.fragment,e),_(de.$$.fragment,e),_(pe.$$.fragment,e),_(he.$$.fragment,e),_(_e.$$.fragment,e),_(we.$$.fragment,e),_(ve.$$.fragment,e),_(je.$$.fragment,e),_(Ce.$$.fragment,e),_(Te.$$.fragment,e),_(Ne.$$.fragment,e),_(Le.$$.fragment,e),_(Ie.$$.fragment,e),_(ze.$$.fragment,e),_(Pe.$$.fragment,e),_(Ee.$$.fragment,e),_(Ae.$$.fragment,e),_(Fe.$$.fragment,e),_(et.$$.fragment,e),_(st.$$.fragment,e),_(lt.$$.fragment,e),_(ot.$$.fragment,e),_(ut.$$.fragment,e),qs=!1},d(e){e&&(r(l),r(a),r(s),r(o),r(m),r(C),r(I),r(j),r(g),r(T),r($),r(U),r(J),r(L),r(H),r(gt),r(se),r(ht),r(bt),r(le),r(_t),r(wt),r(oe),r(Mt),r(ie),r(vt),r(re),r(yt),r(F),r(jt),r(ue),r(kt),r(Ct),r(me),r(Ut),r(Tt),r(fe),r(Jt),r(qt),r(ge),r(Nt),r(Zt),r(K),r(Gt),r(be),r(Lt),r(Wt),r(It),r(Me),r($t),r(Bt),r(ye),r(Vt),r(St),r(ke),r(zt),r(Ht),r(Ue),r(Pt),r(Dt),r(Je),r(Et),r(qe),r(Xt),r(xt),r(Ze),r(At),r(Ge),r(Rt),r(Yt),r(We),r(Qt),r(Ft),r($e),r(Kt),r(Be),r(Ot),r(Ve),r(es),r(Se),r(ts),r(ss),r(He),r(as),r(ls),r(De),r(ns),r(os),r(Xe),r(is),r(O),r(rs),r(xe),r(us),r(cs),r(ee),r(ms),r(Re),r(ds),r(Ye),r(fs),r(Qe),r(ps),r(gs),r(Ke),r(hs),r(Oe),r(bs),r(_s),r(tt),r(ws),r(Ms),r(at),r(vs),r(ys),r(nt),r(js),r(te),r(ks),r(Cs),r(it),r(Us),r(rt),r(Ts),r(Js),r(pt)),r(t),Z(i,e),Z(d,e),Z(b,e),Z(ae,e),Z(ne,e),Z(ce,e),Z(de,e),Z(pe,e),Z(he,e),Z(_e,e),Z(we,e),Z(ve,e),Z(je,e),Z(Ce,e),Z(Te,e),Z(Ne,e),Z(Le,e),Z(Ie,e),Z(ze,e),Z(Pe,e),Z(Ee,e),Z(Ae,e),Z(Fe,e),Z(et,e),Z(st,e),Z(lt,e),Z(ot,e),Z(ut,e)}}}const Pl='{"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 Dl(n){return Ws(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Yl extends dt{constructor(t){super(),ft(this,t,Dl,Hl,mt,{})}}export{Yl as component};