diffusers/main/pt/_app/immutable/nodes/4.38eb91a9.js

import{s as mt,c as A,i as Pa,u as Y,g as R,d as x,o as Gs,b as Ws,n as z,h as Da,t as Fa,j as Ns}from"../chunks/scheduler.d586627e.js";import{S as ct,i as ft,g as w,h as M,j as H,f as u,k as y,a as m,y as P,D as Zs,d as h,t as _,B as ka,C as Ca,l as Qa,s as d,c as p,p as D,b as E,r as C,u as J,v as U,w as T,m as Ea,e as X,n as Xa,o as Aa,q as Js,z as Ya,A as Ka,x as k}from"../chunks/index.8589a59c.js";import{g as Oa,T as $s,C as L}from"../chunks/CodeBlock.126e7335.js";import{e as qs}from"../chunks/each.e59479a4.js";import{H as ut,E as el}from"../chunks/EditOnGithub.073dfa26.js";function tl(n){let t,l,a,s,o,i;const f=n[7].default,c=A(f,n,n[6],null);return{c(){t=w("div"),l=w("ul"),c&&c.c(),this.h()},l(b){t=M(b,"DIV",{class:!0});var q=H(t);l=M(q,"UL",{class:!0});var V=H(l);c&&c.l(V),V.forEach(u),q.forEach(u),this.h()},h(){y(l,"class","min-w-full w-auto"),y(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,q){m(b,t,q),P(t,l),c&&c.m(l,null),n[8](t),s=!0,o||(i=Zs(t,"click",function(){Pa(n[1])&&n[1].apply(this,arguments)}),o=!0)},p(b,[q]){n=b,c&&c.p&&(!s||q&64)&&Y(c,f,n,n[6],s?x(f,n[6],q,null):R(n[6]),null),(!s||q&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]))&&y(t,"class",a)},i(b){s||(h(c,b),s=!0)},o(b){_(c,b),s=!1},d(b){b&&u(t),c&&c.d(b),n[8](null),o=!1,i()}}}function sl(n,t,l){let{$$slots:a={},$$scope:s}=t,{classNames:o=""}=t,{dropdownElement:i=void 0}=t,{forceAlignement:f=void 0}=t,{onClose:c}=t,b=f??"left",q;Gs(()=>{if(document.addEventListener("click",V),!f){const j=document.documentElement.clientWidth,g=q==null?void 0:q.getBoundingClientRect(),v=(g==null?void 0:g.left)??0,Z=(g==null?void 0:g.width)??0;l(2,b=v+Z>j?"right":"left")}return()=>{document.removeEventListener("click",V)}});function V(j){const g=j.target;g!==i&&!(i!=null&&i.contains(g))&&c()}function $(j){Ws[j?"unshift":"push"](()=>{q=j,l(3,q)})}return n.$$set=j=>{"classNames"in j&&l(0,o=j.classNames),"dropdownElement"in j&&l(4,i=j.dropdownElement),"forceAlignement"in j&&l(5,f=j.forceAlignement),"onClose"in j&&l(1,c=j.onClose),"$$scope"in j&&l(6,s=j.$$scope)},[o,c,b,q,i,f,s,a,$]}class al extends ct{constructor(t){super(),ft(this,t,sl,tl,mt,{classNames:0,dropdownElement:4,forceAlignement:5,onClose:1})}}function ll(n){let t,l;return{c(){t=ka("svg"),l=ka("path"),this.h()},l(a){t=Ca(a,"svg",{class:!0,xmlns:!0,"xmlns:xlink":!0,"aria-hidden":!0,focusable:!0,role:!0,width:!0,height:!0,preserveAspectRatio:!0,viewBox:!0,style:!0});var s=H(t);l=Ca(s,"path",{d:!0,fill:!0}),H(l).forEach(u),s.forEach(u),this.h()},h(){y(l,"d","M7 10l5 5l5-5z"),y(l,"fill","currentColor"),y(t,"class",n[0]),y(t,"xmlns","http://www.w3.org/2000/svg"),y(t,"xmlns:xlink","http://www.w3.org/1999/xlink"),y(t,"aria-hidden","true"),y(t,"focusable","false"),y(t,"role","img"),y(t,"width","1em"),y(t,"height","1em"),y(t,"preserveAspectRatio","xMidYMid meet"),y(t,"viewBox","0 0 24 24"),Qa(t,"transform","rotate(360deg)")},m(a,s){m(a,t,s),P(t,l)},p(a,[s]){s&1&&y(t,"class",a[0])},i:z,o:z,d(a){a&&u(t)}}}function nl(n,t,l){let{classNames:a=""}=t;return n.$$set=s=>{"classNames"in s&&l(0,a=s.classNames)},[a]}class ol extends ct{constructor(t){super(),ft(this,t,nl,ll,mt,{classNames:0})}}const il=n=>({}),Ua=n=>({}),rl=n=>({}),Ta=n=>({});function ul(n){let t,l,a,s,o,i=n[2]&&$a(n),f=n[9]&&Ja();return{c(){i&&i.c(),t=d(),l=Ea(n[4]),a=d(),f&&f.c(),s=X()},l(c){i&&i.l(c),t=p(c),l=Xa(c,n[4]),a=p(c),f&&f.l(c),s=X()},m(c,b){i&&i.m(c,b),m(c,t,b),m(c,l,b),m(c,a,b),f&&f.m(c,b),m(c,s,b),o=!0},p(c,b){c[2]?i?(i.p(c,b),b&4&&h(i,1)):(i=$a(c),i.c(),h(i,1),i.m(t.parentNode,t)):i&&(D(),_(i,1,1,()=>{i=null}),E()),(!o||b&16)&&Aa(l,c[4]),c[9]?f?b&512&&h(f,1):(f=Ja(),f.c(),h(f,1),f.m(s.parentNode,s)):f&&(D(),_(f,1,1,()=>{f=null}),E())},i(c){o||(h(i),h(f),o=!0)},o(c){_(i),_(f),o=!1},d(c){c&&(u(t),u(l),u(a),u(s)),i&&i.d(c),f&&f.d(c)}}}function ml(n){let t;const l=n[14].button,a=A(l,n,n[18],Ta);return{c(){a&&a.c()},l(s){a&&a.l(s)},m(s,o){a&&a.m(s,o),t=!0},p(s,o){a&&a.p&&(!t||o&262144)&&Y(a,l,s,s[18],t?x(l,s[18],o,rl):R(s[18]),Ta)},i(s){t||(h(a,s),t=!0)},o(s){_(a,s),t=!1},d(s){a&&a.d(s)}}}function $a(n){let t,l,a;var s=n[2];function o(i,f){return{props:{classNames:"mr-1.5 "+i[3]}}}return s&&(t=Js(s,o(n))),{c(){t&&C(t.$$.fragment),l=X()},l(i){t&&J(t.$$.fragment,i),l=X()},m(i,f){t&&U(t,i,f),m(i,l,f),a=!0},p(i,f){if(f&4&&s!==(s=i[2])){if(t){D();const c=t;_(c.$$.fragment,1,0,()=>{T(c,1)}),E()}s?(t=Js(s,o(i)),C(t.$$.fragment),h(t.$$.fragment,1),U(t,l.parentNode,l)):t=null}else if(s){const c={};f&8&&(c.classNames="mr-1.5 "+i[3]),t.$set(c)}},i(i){a||(t&&h(t.$$.fragment,i),a=!0)},o(i){t&&_(t.$$.fragment,i),a=!1},d(i){i&&u(l),t&&T(t,i)}}}function Ja(n){let t,l;return t=new ol({props:{classNames:"-mr-1 text-gray-500"}}),{c(){C(t.$$.fragment)},l(a){J(t.$$.fragment,a)},m(a,s){U(t,a,s),l=!0},i(a){l||(h(t.$$.fragment,a),l=!0)},o(a){_(t.$$.fragment,a),l=!1},d(a){T(t,a)}}}function qa(n){let t,l;return t=new al({props:{classNames:n[6]+" "+(n[8]?"v2-dropdown-menu hidden":""),dropdownElement:n[10],forceAlignement:n[5],onClose:n[16],$$slots:{default:[cl]},$$scope:{ctx:n}}}),{c(){C(t.$$.fragment)},l(a){J(t.$$.fragment,a)},m(a,s){U(t,a,s),l=!0},p(a,s){const o={};s&320&&(o.classNames=a[6]+" "+(a[8]?"v2-dropdown-menu hidden":"")),s&1024&&(o.dropdownElement=a[10]),s&32&&(o.forceAlignement=a[5]),s&2048&&(o.onClose=a[16]),s&262144&&(o.$$scope={dirty:s,ctx:a}),t.$set(o)},i(a){l||(h(t.$$.fragment,a),l=!0)},o(a){_(t.$$.fragment,a),l=!1},d(a){T(t,a)}}}function cl(n){let t;const l=n[14].menu,a=A(l,n,n[18],Ua);return{c(){a&&a.c()},l(s){a&&a.l(s)},m(s,o){a&&a.m(s,o),t=!0},p(s,o){a&&a.p&&(!t||o&262144)&&Y(a,l,s,s[18],t?x(l,s[18],o,il):R(s[18]),Ua)},i(s){t||(h(a,s),t=!0)},o(s){_(a,s),t=!1},d(s){a&&a.d(s)}}}function fl(n){let t,l,a,s,o,i,f,c,b,q;const V=[ml,ul],$=[];function j(v,Z){return v[12].button?0:1}a=j(n),s=$[a]=V[a](n);let g=(n[11]||n[8])&&qa(n);return{c(){t=w("div"),l=w("button"),s.c(),i=d(),g&&g.c(),this.h()},l(v){t=M(v,"DIV",{class:!0});var Z=H(t);l=M(Z,"BUTTON",{class:!0,type:!0});var B=H(l);s.l(B),B.forEach(u),i=p(Z),g&&g.l(Z),Z.forEach(u),this.h()},h(){y(l,"class",o=""+n[1]+" "+(n[7]?"":"cursor-pointer w-full btn text-sm")+" "+(n[8]?"v2-dropdown-button":"")),y(l,"type","button"),y(t,"class",f="relative "+n[0]+" "+(n[8]?"v2-dropdown":""))},m(v,Z){m(v,t,Z),P(t,l),$[a].m(l,null),P(t,i),g&&g.m(t,null),n[17](t),c=!0,b||(q=Zs(l,"click",n[15]),b=!0)},p(v,[Z]){let B=a;a=j(v),a===B?$[a].p(v,Z):(D(),_($[B],1,1,()=>{$[B]=null}),E(),s=$[a],s?s.p(v,Z):(s=$[a]=V[a](v),s.c()),h(s,1),s.m(l,null)),(!c||Z&386&&o!==(o=""+v[1]+" "+(v[7]?"":"cursor-pointer w-full btn text-sm")+" "+(v[8]?"v2-dropdown-button":"")))&&y(l,"class",o),v[11]||v[8]?g?(g.p(v,Z),Z&2304&&h(g,1)):(g=qa(v),g.c(),h(g,1),g.m(t,null)):g&&(D(),_(g,1,1,()=>{g=null}),E()),(!c||Z&257&&f!==(f="relative "+v[0]+" "+(v[8]?"v2-dropdown":"")))&&y(t,"class",f)},i(v){c||(h(s),h(g),c=!0)},o(v){_(s),_(g),c=!1},d(v){v&&u(t),$[a].d(),g&&g.d(),n[17](null),b=!1,q()}}}function dl(n,t,l){let{$$slots:a={},$$scope:s}=t;const o=Da(a);let{classNames:i=""}=t,{btnClassNames:f=""}=t,{btnIcon:c=void 0}=t,{btnIconClassNames:b=""}=t,{btnLabel:q=""}=t,{forceMenuAlignement:V=void 0}=t,{menuClassNames:$=""}=t,{noBtnClass:j=void 0}=t,{selectedValue:g=void 0}=t,{useDeprecatedJS:v=!0}=t,{withBtnCaret:Z=!1}=t,B,S=!1;const N=()=>l(11,S=!S),G=()=>l(11,S=!1);function I(W){Ws[W?"unshift":"push"](()=>{B=W,l(10,B)})}return n.$$set=W=>{"classNames"in W&&l(0,i=W.classNames),"btnClassNames"in W&&l(1,f=W.btnClassNames),"btnIcon"in W&&l(2,c=W.btnIcon),"btnIconClassNames"in W&&l(3,b=W.btnIconClassNames),"btnLabel"in W&&l(4,q=W.btnLabel),"forceMenuAlignement"in W&&l(5,V=W.forceMenuAlignement),"menuClassNames"in W&&l(6,$=W.menuClassNames),"noBtnClass"in W&&l(7,j=W.noBtnClass),"selectedValue"in W&&l(13,g=W.selectedValue),"useDeprecatedJS"in W&&l(8,v=W.useDeprecatedJS),"withBtnCaret"in W&&l(9,Z=W.withBtnCaret),"$$scope"in W&&l(18,s=W.$$scope)},[i,f,c,b,q,V,$,j,v,Z,B,S,o,g,a,N,G,I,s]}class Ra extends ct{constructor(t){super(),ft(this,t,dl,fl,mt,{classNames:0,btnClassNames:1,btnIcon:2,btnIconClassNames:3,btnLabel:4,forceMenuAlignement:5,menuClassNames:6,noBtnClass:7,selectedValue:13,useDeprecatedJS:8,withBtnCaret:9})}}function pl(n){let t,l,a,s=n[5]&&Na(n);return{c(){s&&s.c(),t=d(),l=Ea(n[7])},l(o){s&&s.l(o),t=p(o),l=Xa(o,n[7])},m(o,i){s&&s.m(o,i),m(o,t,i),m(o,l,i),a=!0},p(o,i){o[5]?s?(s.p(o,i),i&32&&h(s,1)):(s=Na(o),s.c(),h(s,1),s.m(t.parentNode,t)):s&&(D(),_(s,1,1,()=>{s=null}),E()),(!a||i&128)&&Aa(l,o[7])},i(o){a||(h(s),a=!0)},o(o){_(s),a=!1},d(o){o&&(u(t),u(l)),s&&s.d(o)}}}function gl(n){let t;const l=n[15].default,a=A(l,n,n[14],null);return{c(){a&&a.c()},l(s){a&&a.l(s)},m(s,o){a&&a.m(s,o),t=!0},p(s,o){a&&a.p&&(!t||o&16384)&&Y(a,l,s,s[14],t?x(l,s[14],o,null):R(s[14]),null)},i(s){t||(h(a,s),t=!0)},o(s){_(a,s),t=!1},d(s){a&&a.d(s)}}}function Na(n){let t,l,a;var s=n[5];function o(i,f){return{props:{classNames:"mr-1.5 "+i[6]}}}return s&&(t=Js(s,o(n))),{c(){t&&C(t.$$.fragment),l=X()},l(i){t&&J(t.$$.fragment,i),l=X()},m(i,f){t&&U(t,i,f),m(i,l,f),a=!0},p(i,f){if(f&32&&s!==(s=i[5])){if(t){D();const c=t;_(c.$$.fragment,1,0,()=>{T(c,1)}),E()}s?(t=Js(s,o(i)),C(t.$$.fragment),h(t.$$.fragment,1),U(t,l.parentNode,l)):t=null}else if(s){const c={};f&64&&(c.classNames="mr-1.5 "+i[6]),t.$set(c)}},i(i){a||(t&&h(t.$$.fragment,i),a=!0)},o(i){t&&_(t.$$.fragment,i),a=!1},d(i){i&&u(l),t&&T(t,i)}}}function hl(n){let t,l,a,s,o,i,f,c,b,q;const V=[gl,pl],$=[];function j(g,v){return g[13].default?0:1}return a=j(n),s=$[a]=V[a](n),{c(){t=w("li"),l=w("a"),s.c(),this.h()},l(g){t=M(g,"LI",{class:!0});var v=H(t);l=M(v,"A",{class:!0,"data-label":!0,"data-url":!0,"data-value":!0,href:!0,rel:!0,target:!0});var Z=H(l);s.l(Z),Z.forEach(u),v.forEach(u),this.h()},h(){y(l,"class",o="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":"")),y(l,"data-label",n[1]),y(l,"data-url",n[2]),y(l,"data-value",n[3]),y(l,"href",n[4]),y(l,"rel",i=n[8]?"nofollow":void 0),y(l,"target",f=n[11]?"_blank":void 0),y(t,"class","not-prose")},m(g,v){m(g,t,v),P(t,l),$[a].m(l,null),c=!0,b||(q=Zs(l,"click",function(){Pa(n[10])&&n[10].apply(this,arguments)}),b=!0)},p(g,[v]){n=g;let Z=a;a=j(n),a===Z?$[a].p(n,v):(D(),_($[Z],1,1,()=>{$[Z]=null}),E(),s=$[a],s?s.p(n,v):(s=$[a]=V[a](n),s.c()),h(s,1),s.m(l,null)),(!c||v&4609&&o!==(o="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":"")))&&y(l,"class",o),(!c||v&2)&&y(l,"data-label",n[1]),(!c||v&4)&&y(l,"data-url",n[2]),(!c||v&8)&&y(l,"data-value",n[3]),(!c||v&16)&&y(l,"href",n[4]),(!c||v&256&&i!==(i=n[8]?"nofollow":void 0))&&y(l,"rel",i),(!c||v&2048&&f!==(f=n[11]?"_blank":void 0))&&y(l,"target",f)},i(g){c||(h(s),c=!0)},o(g){_(s),c=!1},d(g){g&&u(t),$[a].d(),b=!1,q()}}}function _l(n,t,l){let{$$slots:a={},$$scope:s}=t;const o=Da(a);let{classNames:i=""}=t,{dataLabel:f=void 0}=t,{dataUrl:c=void 0}=t,{dataValue:b=void 0}=t,{href:q=void 0}=t,{icon:V=void 0}=t,{iconClassNames:$=""}=t,{label:j=""}=t,{noFollow:g=!1}=t,{underline:v=!1}=t,{onClick:Z=()=>{}}=t,{targetBlank:B=!1}=t,{useDeprecatedJS:S=!0}=t;return n.$$set=N=>{"classNames"in N&&l(0,i=N.classNames),"dataLabel"in N&&l(1,f=N.dataLabel),"dataUrl"in N&&l(2,c=N.dataUrl),"dataValue"in N&&l(3,b=N.dataValue),"href"in N&&l(4,q=N.href),"icon"in N&&l(5,V=N.icon),"iconClassNames"in N&&l(6,$=N.iconClassNames),"label"in N&&l(7,j=N.label),"noFollow"in N&&l(8,g=N.noFollow),"underline"in N&&l(9,v=N.underline),"onClick"in N&&l(10,Z=N.onClick),"targetBlank"in N&&l(11,B=N.targetBlank),"useDeprecatedJS"in N&&l(12,S=N.useDeprecatedJS),"$$scope"in N&&l(14,s=N.$$scope)},[i,f,c,b,q,V,$,j,g,v,Z,B,S,o,s,a]}class xa extends ct{constructor(t){super(),ft(this,t,_l,hl,mt,{classNames:0,dataLabel:1,dataUrl:2,dataValue:3,href:4,icon:5,iconClassNames:6,label:7,noFollow:8,underline:9,onClick:10,targetBlank:11,useDeprecatedJS:12})}}const{window:bl}=Oa,wl=n=>({}),Za=n=>({slot:"button"});function Ga(n,t,l){const a=n.slice();return a[11]=t[l].label,a[12]=t[l].value,a}const Ml=n=>({}),Wa=n=>({slot:"menu"}),vl=n=>({}),Ia=n=>({slot:"button"});function Va(n,t,l){const a=n.slice();return a[11]=t[l].label,a[12]=t[l].value,a}const yl=n=>({}),Ba=n=>({slot:"menu"}),jl=n=>({}),Sa=n=>({});function kl(n){let t,l;return t=new Ra({props:{btnLabel:"",classNames:"colab-dropdown",noBtnClass:!0,useDeprecatedJS:!1,$$slots:{menu:[Jl],button:[Tl]},$$scope:{ctx:n}}}),{c(){C(t.$$.fragment)},l(a){J(t.$$.fragment,a)},m(a,s){U(t,a,s),l=!0},p(a,s){const o={};s&1024&&(o.$$scope={dirty:s,ctx:a}),t.$set(o)},i(a){l||(h(t.$$.fragment,a),l=!0)},o(a){_(t.$$.fragment,a),l=!1},d(a){T(t,a)}}}function Cl(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 o=H(t);l=M(o,"IMG",{alt:!0,class:!0,src:!0}),o.forEach(u),this.h()},h(){y(l,"alt","Open In Colab"),y(l,"class","!m-0"),Ns(l.src,a="https://colab.research.google.com/assets/colab-badge.svg")||y(l,"src",a),y(t,"href",n[2][0].value),y(t,"target","_blank")},m(s,o){m(s,t,o),P(t,l)},p:z,i:z,o:z,d(s){s&&u(t)}}}function Ul(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(){y(t,"alt","Open In Colab"),y(t,"class","!m-0"),Ns(t.src,l="https://colab.research.google.com/assets/colab-badge.svg")||y(t,"src",l)},m(a,s){m(a,t,s)},p:z,d(a){a&&u(t)}}}function Tl(n){let t;const l=n[6].default,a=A(l,n,n[10],Ia),s=a||Ul();return{c(){s&&s.c()},l(o){s&&s.l(o)},m(o,i){s&&s.m(o,i),t=!0},p(o,i){a&&a.p&&(!t||i&1024)&&Y(a,l,o,o[10],t?x(l,o[10],i,vl):R(o[10]),Ia)},i(o){t||(h(s,o),t=!0)},o(o){_(s,o),t=!1},d(o){s&&s.d(o)}}}function La(n){let t,l;function a(){return n[7](n[12])}return t=new xa({props:{classNames:"text-sm !no-underline",iconClassNames:"text-gray-500",label:n[11],onClick:a,useDeprecatedJS:!1}}),{c(){C(t.$$.fragment)},l(s){J(t.$$.fragment,s)},m(s,o){U(t,s,o),l=!0},p(s,o){n=s},i(s){l||(h(t.$$.fragment,s),l=!0)},o(s){_(t.$$.fragment,s),l=!1},d(s){T(t,s)}}}function $l(n){let t,l,a=qs(n[2]),s=[];for(let i=0;i<a.length;i+=1)s[i]=La(Va(n,a,i));const o=i=>_(s[i],1,1,()=>{s[i]=null});return{c(){for(let i=0;i<s.length;i+=1)s[i].c();t=X()},l(i){for(let f=0;f<s.length;f+=1)s[f].l(i);t=X()},m(i,f){for(let c=0;c<s.length;c+=1)s[c]&&s[c].m(i,f);m(i,t,f),l=!0},p(i,f){if(f&4){a=qs(i[2]);let c;for(c=0;c<a.length;c+=1){const b=Va(i,a,c);s[c]?(s[c].p(b,f),h(s[c],1)):(s[c]=La(b),s[c].c(),h(s[c],1),s[c].m(t.parentNode,t))}for(D(),c=a.length;c<s.length;c+=1)o(c);E()}},i(i){if(!l){for(let f=0;f<a.length;f+=1)h(s[f]);l=!0}},o(i){s=s.filter(Boolean);for(let f=0;f<s.length;f+=1)_(s[f]);l=!1},d(i){i&&u(t),Ya(s,i)}}}function Jl(n){let t;const l=n[6].default,a=A(l,n,n[10],Ba),s=a||$l(n);return{c(){s&&s.c()},l(o){s&&s.l(o)},m(o,i){s&&s.m(o,i),t=!0},p(o,i){a&&a.p&&(!t||i&1024)&&Y(a,l,o,o[10],t?x(l,o[10],i,yl):R(o[10]),Ba)},i(o){t||(h(s,o),t=!0)},o(o){_(s,o),t=!1},d(o){s&&s.d(o)}}}function ql(n){let t,l;return t=new Ra({props:{btnLabel:"",classNames:"colab-dropdown",noBtnClass:!0,useDeprecatedJS:!1,$$slots:{menu:[Il],button:[Gl]},$$scope:{ctx:n}}}),{c(){C(t.$$.fragment)},l(a){J(t.$$.fragment,a)},m(a,s){U(t,a,s),l=!0},p(a,s){const o={};s&1024&&(o.$$scope={dirty:s,ctx:a}),t.$set(o)},i(a){l||(h(t.$$.fragment,a),l=!0)},o(a){_(t.$$.fragment,a),l=!1},d(a){T(t,a)}}}function Nl(n){let t,l,a;return{c(){t=w("a"),l=w("img"),this.h()},l(s){t=M(s,"A",{href:!0,target:!0});var o=H(t);l=M(o,"IMG",{alt:!0,class:!0,src:!0}),o.forEach(u),this.h()},h(){y(l,"alt","Open In Studio Lab"),y(l,"class","!m-0"),Ns(l.src,a="https://studiolab.sagemaker.aws/studiolab.svg")||y(l,"src",a),y(t,"href",n[3][0].value),y(t,"target","_blank")},m(s,o){m(s,t,o),P(t,l)},p:z,i:z,o:z,d(s){s&&u(t)}}}function Zl(n){let t,l;return{c(){t=w("img"),this.h()},l(a){t=M(a,"IMG",{alt:!0,class:!0,src:!0}),this.h()},h(){y(t,"alt","Open In Studio Lab"),y(t,"class","!m-0"),Ns(t.src,l="https://studiolab.sagemaker.aws/studiolab.svg")||y(t,"src",l)},m(a,s){m(a,t,s)},p:z,d(a){a&&u(t)}}}function Gl(n){let t;const l=n[6].default,a=A(l,n,n[10],Za),s=a||Zl();return{c(){s&&s.c()},l(o){s&&s.l(o)},m(o,i){s&&s.m(o,i),t=!0},p(o,i){a&&a.p&&(!t||i&1024)&&Y(a,l,o,o[10],t?x(l,o[10],i,wl):R(o[10]),Za)},i(o){t||(h(s,o),t=!0)},o(o){_(s,o),t=!1},d(o){s&&s.d(o)}}}function za(n){let t,l;function a(){return n[8](n[12])}return t=new xa({props:{classNames:"text-sm !no-underline",iconClassNames:"text-gray-500",label:n[11],onClick:a,useDeprecatedJS:!1}}),{c(){C(t.$$.fragment)},l(s){J(t.$$.fragment,s)},m(s,o){U(t,s,o),l=!0},p(s,o){n=s},i(s){l||(h(t.$$.fragment,s),l=!0)},o(s){_(t.$$.fragment,s),l=!1},d(s){T(t,s)}}}function Wl(n){let t,l,a=qs(n[3]),s=[];for(let i=0;i<a.length;i+=1)s[i]=za(Ga(n,a,i));const o=i=>_(s[i],1,1,()=>{s[i]=null});return{c(){for(let i=0;i<s.length;i+=1)s[i].c();t=X()},l(i){for(let f=0;f<s.length;f+=1)s[f].l(i);t=X()},m(i,f){for(let c=0;c<s.length;c+=1)s[c]&&s[c].m(i,f);m(i,t,f),l=!0},p(i,f){if(f&8){a=qs(i[3]);let c;for(c=0;c<a.length;c+=1){const b=Ga(i,a,c);s[c]?(s[c].p(b,f),h(s[c],1)):(s[c]=za(b),s[c].c(),h(s[c],1),s[c].m(t.parentNode,t))}for(D(),c=a.length;c<s.length;c+=1)o(c);E()}},i(i){if(!l){for(let f=0;f<a.length;f+=1)h(s[f]);l=!0}},o(i){s=s.filter(Boolean);for(let f=0;f<s.length;f+=1)_(s[f]);l=!1},d(i){i&&u(t),Ya(s,i)}}}function Il(n){let t;const l=n[6].default,a=A(l,n,n[10],Wa),s=a||Wl(n);return{c(){s&&s.c()},l(o){s&&s.l(o)},m(o,i){s&&s.m(o,i),t=!0},p(o,i){a&&a.p&&(!t||i&1024)&&Y(a,l,o,o[10],t?x(l,o[10],i,Ml):R(o[10]),Wa)},i(o){t||(h(s,o),t=!0)},o(o){_(s,o),t=!1},d(o){s&&s.d(o)}}}function Vl(n){let t,l,a,s,o,i,f,c,b,q,V;const $=n[6].alwaysVisible,j=A($,n,n[10],Sa),g=[Cl,kl],v=[];function Z(G,I){return G[2].length===1?0:G[2].length>1?1:-1}~(a=Z(n))&&(s=v[a]=g[a](n));const B=[Nl,ql],S=[];function N(G,I){return G[3].length===1?0:G[3].length>1?1:-1}return~(i=N(n))&&(f=S[i]=B[i](n)),{c(){t=w("div"),j&&j.c(),l=d(),s&&s.c(),o=d(),f&&f.c(),this.h()},l(G){t=M(G,"DIV",{class:!0});var I=H(t);j&&j.l(I),l=p(I),s&&s.l(I),o=p(I),f&&f.l(I),I.forEach(u),this.h()},h(){y(t,"class",c="flex space-x-1 "+n[0])},m(G,I){m(G,t,I),j&&j.m(t,null),P(t,l),~a&&v[a].m(t,null),P(t,o),~i&&S[i].m(t,null),n[9](t),b=!0,q||(V=Zs(bl,"resize",n[4]),q=!0)},p(G,[I]){j&&j.p&&(!b||I&1024)&&Y(j,$,G,G[10],b?x($,G[10],I,jl):R(G[10]),Sa),s&&s.p(G,I),f&&f.p(G,I),(!b||I&1&&c!==(c="flex space-x-1 "+G[0]))&&y(t,"class",c)},i(G){b||(h(j,G),h(s),h(f),b=!0)},o(G){_(j,G),_(s),_(f),b=!1},d(G){G&&u(t),j&&j.d(G),~a&&v[a].d(),~i&&S[i].d(),n[9](null),q=!1,V()}}}function Ha(n){window.open(n)}function Bl(n,t,l){let{$$slots:a={},$$scope:s}=t,{options:o=[]}=t,{classNames:i=""}=t,f;const c=o.filter(g=>g.value.includes("colab.research.google.com")),b=o.filter(g=>g.value.includes("studiolab.sagemaker.aws"));function q(){const g=document.querySelector(".prose-doc h1"),v=document.querySelector(".prose-doc h1 > span");if(g&&v){const{width:Z}=g.getBoundingClientRect(),{width:B}=v.getBoundingClientRect();let S=0;for(let G=0;G<f.children.length;G++){const I=f.children.item(G);I&&(S+=I.clientWidth)}const N=20;Z-B<S+N?f.classList.remove("absolute"):f.classList.add("absolute")}}Gs(()=>{(async()=>(await Fa(),q()))()});const V=g=>Ha(g),$=g=>Ha(g);function j(g){Ws[g?"unshift":"push"](()=>{f=g,l(1,f)})}return n.$$set=g=>{"options"in g&&l(5,o=g.options),"classNames"in g&&l(0,i=g.classNames),"$$scope"in g&&l(10,s=g.$$scope)},[i,f,c,b,q,o,a,V,$,j,s]}class Sl extends ct{constructor(t){super(),ft(this,t,Bl,Vl,mt,{options:5,classNames:0})}}function Ll(n){let t,l='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!';return{c(){t=w("p"),t.innerHTML=l},l(a){t=M(a,"P",{"data-svelte-h":!0}),k(t)!=="svelte-vh1n7z"&&(t.innerHTML=l)},m(a,s){m(a,t,s)},p:z,d(a){a&&u(t)}}}function zl(n){let t,l='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.';return{c(){t=w("p"),t.innerHTML=l},l(a){t=M(a,"P",{"data-svelte-h":!0}),k(t)!=="svelte-15ggxls"&&(t.innerHTML=l)},m(a,s){m(a,t,s)},p:z,d(a){a&&u(t)}}}function Hl(n){let t,l="🧨 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.";return{c(){t=w("p"),t.innerHTML=l},l(a){t=M(a,"P",{"data-svelte-h":!0}),k(t)!=="svelte-qdtvqj"&&(t.innerHTML=l)},m(a,s){m(a,t,s)},p:z,d(a){a&&u(t)}}}function Pl(n){let t,l="💡 Perceba como o agendador é instanciado de uma configuração. Diferentemente de um modelo, um agendador não tem pesos treináveis e é livre de parâmetros!";return{c(){t=w("p"),t.textContent=l},l(a){t=M(a,"P",{"data-svelte-h":!0}),k(t)!=="svelte-15eqb5p"&&(t.textContent=l)},m(a,s){m(a,t,s)},p:z,d(a){a&&u(t)}}}function Dl(n){let t,l,a,s,o,i,f,c,b,q="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.",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:",g,v,Z='<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>',B,S,N="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>.",G,I,W,te,Is="Antes de começar, certifique-se de ter todas as bibliotecas necessárias instaladas:",pt,se,gt,ae,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>',ht,le,_t,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>.',bt,oe,Ss='<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>',wt,ie,Ls=`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/runwayml/stable-diffusion-v1-5" rel="nofollow"><code>stable-diffusion-v1-5</code></a> para geração de texto para imagem.`,Mt,F,vt,re,zs="Para carregar o modelo com o método <code>from_pretrained()</code>:",yt,ue,jt,me,Hs="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:",kt,ce,Ct,fe,Ps=`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:`,Ut,de,Tt,pe,Ds='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>.',$t,ge,Jt,Q,Es='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/image_of_squirrel_painting.png"/>',qt,he,Xs="Salve a imagem chamando o <code>save</code>:",Nt,_e,Zt,be,Gt,we,As="Você também pode utilizar o pipeline localmente. A única diferença é que você precisa baixar os pesos primeiro:",Wt,Me,It,ve,Ys="Assim carregue os pesos salvos no pipeline:",Vt,ye,Bt,je,Rs="Agora você pode rodar o pipeline como você faria na seção acima.",St,ke,Lt,Ce,xs="Agendadores diferentes tem diferentes velocidades de retirar o ruído e compensações de qualidade. A melhor forma de descobrir qual funciona melhor para você é testar eles! Uma das principais características do 🧨 Diffusers é permitir que você troque facilmente entre agendadores. Por exemplo, para substituir o <code>PNDMScheduler</code> padrão com o <code>EulerDiscreteScheduler</code>, carregue ele com o método <code>from_config()</code>:",zt,Ue,Ht,Te,Fs="Tente gerar uma imagem com o novo agendador e veja se você nota alguma diferença!",Pt,$e,Qs="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.",Dt,Je,Et,qe,Ks='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.',Xt,Ne,Os="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:",At,Ze,Yt,Ge,ea="Para acessar os parâmetros do modelo, chame <code>model.config</code>:",Rt,We,xt,Ie,ta="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.",Ft,Ve,sa="Um dos parâmetros mais importantes são:",Qt,Be,aa="<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>",Kt,Se,la="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:",Ot,Le,es,ze,na="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:",ts,He,ss,Pe,oa="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.",as,De,ls,Ee,ia="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>.",ns,K,os,Xe,ra="Para o tour rápido, você irá instanciar o <code>DDPMScheduler</code> com o método <code>from_config()</code>:",is,Ae,rs,O,us,Ye,ua="Um dos parâmetros mais importante são:",ms,Re,ma="<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>",cs,xe,ca="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>.",fs,Fe,ds,Qe,fa="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.",ps,Ke,da="Comece, criando a função que faça o pós-processamento e mostre a imagem sem ruído como uma <code>PIL.Image</code>:",gs,Oe,hs,et,pa="Para acelerar o processo de retirada de ruído, mova a entrada e o modelo para uma GPU:",_s,tt,bs,st,ga="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:",ws,at,Ms,lt,ha="Sente-se e assista o gato ser gerado do nada além de ruído! 😻",vs,ee,_a='<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/diffusion-quicktour.png"/>',ys,nt,js,ot,ba="Esperamos que você tenha gerado algumas imagens legais com o 🧨 Diffusers neste tour rápido! Para suas próximas etapas, você pode",ks,it,wa='<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>',Cs,rt,Us,dt,Ts;return o=new Sl({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"}]}}),f=new ut({props:{title:"Tour rápido",local:"tour-rápido",headingTag:"h1"}}),I=new $s({props:{$$slots:{default:[Ll]},$$scope:{ctx:n}}}),se=new L({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"}}),F=new $s({props:{warning:!0,$$slots:{default:[zl]},$$scope:{ctx:n}}}),ue=new L({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMERpZmZ1c2lvblBpcGVsaW5lJTBBJTBBcGlwZWxpbmUlMjAlM0QlMjBEaWZmdXNpb25QaXBlbGluZS5mcm9tX3ByZXRyYWluZWQoJTIycnVud2F5bWwlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTUlMjIlMkMlMjB1c2Vfc2FmZXRlbnNvcnMlM0RUcnVlKQ==",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;runwayml/stable-diffusion-v1-5&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)`,wrap:!1}}),ce=new L({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}}),de=new L({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 L({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 L({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}}),be=new ut({props:{title:"Pipeline local",local:"pipeline-local",headingTag:"h3"}}),Me=new L({props:{code:"IWdpdCUyMGxmcyUyMGluc3RhbGwlMEEhZ2l0JTIwY2xvbmUlMjBodHRwcyUzQSUyRiUyRmh1Z2dpbmdmYWNlLmNvJTJGcnVud2F5bWwlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTU=",highlighted:`!git lfs install
!git <span class="hljs-built_in">clone</span> https://huggingface.co/runwayml/stable-diffusion-v1-5`,wrap:!1}}),ye=new L({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 L({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEV1bGVyRGlzY3JldGVTY2hlZHVsZXIlMEElMEFwaXBlbGluZSUyMCUzRCUyMERpZmZ1c2lvblBpcGVsaW5lLmZyb21fcHJldHJhaW5lZCglMjJydW53YXltbCUyRnN0YWJsZS1kaWZmdXNpb24tdjEtNSUyMiUyQyUyMHVzZV9zYWZldGVuc29ycyUzRFRydWUpJTBBcGlwZWxpbmUuc2NoZWR1bGVyJTIwJTNEJTIwRXVsZXJEaXNjcmV0ZVNjaGVkdWxlci5mcm9tX2NvbmZpZyhwaXBlbGluZS5zY2hlZHVsZXIuY29uZmlnKQ==",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;runwayml/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}}),Je=new ut({props:{title:"Modelos",local:"modelos",headingTag:"h2"}}),Ze=new L({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}}),We=new L({props:{code:"bW9kZWwuY29uZmln",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span>model.config',wrap:!1}}),Le=new L({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 L({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"}}),K=new $s({props:{$$slots:{default:[Hl]},$$scope:{ctx:n}}}),Ae=new L({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}}),O=new $s({props:{$$slots:{default:[Pl]},$$scope:{ctx:n}}}),Fe=new L({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 L({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 L({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 L({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=w("meta"),l=d(),a=w("p"),s=d(),C(o.$$.fragment),i=d(),C(f.$$.fragment),c=d(),b=w("p"),b.textContent=q,V=d(),$=w("p"),$.textContent=j,g=d(),v=w("ul"),v.innerHTML=Z,B=d(),S=w("p"),S.innerHTML=N,G=d(),C(I.$$.fragment),W=d(),te=w("p"),te.textContent=Is,pt=d(),C(se.$$.fragment),gt=d(),ae=w("ul"),ae.innerHTML=Vs,ht=d(),C(le.$$.fragment),_t=d(),ne=w("p"),ne.innerHTML=Bs,bt=d(),oe=w("table"),oe.innerHTML=Ss,wt=d(),ie=w("p"),ie.innerHTML=Ls,Mt=d(),C(F.$$.fragment),vt=d(),re=w("p"),re.innerHTML=zs,yt=d(),C(ue.$$.fragment),jt=d(),me=w("p"),me.innerHTML=Hs,kt=d(),C(ce.$$.fragment),Ct=d(),fe=w("p"),fe.textContent=Ps,Ut=d(),C(de.$$.fragment),Tt=d(),pe=w("p"),pe.innerHTML=Ds,$t=d(),C(ge.$$.fragment),Jt=d(),Q=w("div"),Q.innerHTML=Es,qt=d(),he=w("p"),he.innerHTML=Xs,Nt=d(),C(_e.$$.fragment),Zt=d(),C(be.$$.fragment),Gt=d(),we=w("p"),we.textContent=As,Wt=d(),C(Me.$$.fragment),It=d(),ve=w("p"),ve.textContent=Ys,Vt=d(),C(ye.$$.fragment),Bt=d(),je=w("p"),je.textContent=Rs,St=d(),C(ke.$$.fragment),Lt=d(),Ce=w("p"),Ce.innerHTML=xs,zt=d(),C(Ue.$$.fragment),Ht=d(),Te=w("p"),Te.textContent=Fs,Pt=d(),$e=w("p"),$e.innerHTML=Qs,Dt=d(),C(Je.$$.fragment),Et=d(),qe=w("p"),qe.innerHTML=Ks,Xt=d(),Ne=w("p"),Ne.innerHTML=Os,At=d(),C(Ze.$$.fragment),Yt=d(),Ge=w("p"),Ge.innerHTML=ea,Rt=d(),C(We.$$.fragment),xt=d(),Ie=w("p"),Ie.textContent=ta,Ft=d(),Ve=w("p"),Ve.textContent=sa,Qt=d(),Be=w("ul"),Be.innerHTML=aa,Kt=d(),Se=w("p"),Se.innerHTML=la,Ot=d(),C(Le.$$.fragment),es=d(),ze=w("p"),ze.innerHTML=na,ts=d(),C(He.$$.fragment),ss=d(),Pe=w("p"),Pe.textContent=oa,as=d(),C(De.$$.fragment),ls=d(),Ee=w("p"),Ee.innerHTML=ia,ns=d(),C(K.$$.fragment),os=d(),Xe=w("p"),Xe.innerHTML=ra,is=d(),C(Ae.$$.fragment),rs=d(),C(O.$$.fragment),us=d(),Ye=w("p"),Ye.textContent=ua,ms=d(),Re=w("ul"),Re.innerHTML=ma,cs=d(),xe=w("p"),xe.innerHTML=ca,fs=d(),C(Fe.$$.fragment),ds=d(),Qe=w("p"),Qe.innerHTML=fa,ps=d(),Ke=w("p"),Ke.innerHTML=da,gs=d(),C(Oe.$$.fragment),hs=d(),et=w("p"),et.textContent=pa,_s=d(),C(tt.$$.fragment),bs=d(),st=w("p"),st.textContent=ga,ws=d(),C(at.$$.fragment),Ms=d(),lt=w("p"),lt.textContent=ha,vs=d(),ee=w("div"),ee.innerHTML=_a,ys=d(),C(nt.$$.fragment),js=d(),ot=w("p"),ot.textContent=ba,ks=d(),it=w("ul"),it.innerHTML=wa,Cs=d(),C(rt.$$.fragment),Us=d(),dt=w("p"),this.h()},l(e){const r=Ka("svelte-u9bgzb",document.head);t=M(r,"META",{name:!0,content:!0}),r.forEach(u),l=p(e),a=M(e,"P",{}),H(a).forEach(u),s=p(e),J(o.$$.fragment,e),i=p(e),J(f.$$.fragment,e),c=p(e),b=M(e,"P",{"data-svelte-h":!0}),k(b)!=="svelte-5d3hlg"&&(b.textContent=q),V=p(e),$=M(e,"P",{"data-svelte-h":!0}),k($)!=="svelte-tkfmfk"&&($.textContent=j),g=p(e),v=M(e,"UL",{"data-svelte-h":!0}),k(v)!=="svelte-1bp7yfw"&&(v.innerHTML=Z),B=p(e),S=M(e,"P",{"data-svelte-h":!0}),k(S)!=="svelte-sqpmf8"&&(S.innerHTML=N),G=p(e),J(I.$$.fragment,e),W=p(e),te=M(e,"P",{"data-svelte-h":!0}),k(te)!=="svelte-16jlltr"&&(te.textContent=Is),pt=p(e),J(se.$$.fragment,e),gt=p(e),ae=M(e,"UL",{"data-svelte-h":!0}),k(ae)!=="svelte-l49o4a"&&(ae.innerHTML=Vs),ht=p(e),J(le.$$.fragment,e),_t=p(e),ne=M(e,"P",{"data-svelte-h":!0}),k(ne)!=="svelte-1fm3zhc"&&(ne.innerHTML=Bs),bt=p(e),oe=M(e,"TABLE",{"data-svelte-h":!0}),k(oe)!=="svelte-1wldcuj"&&(oe.innerHTML=Ss),wt=p(e),ie=M(e,"P",{"data-svelte-h":!0}),k(ie)!=="svelte-5t600l"&&(ie.innerHTML=Ls),Mt=p(e),J(F.$$.fragment,e),vt=p(e),re=M(e,"P",{"data-svelte-h":!0}),k(re)!=="svelte-14st4zt"&&(re.innerHTML=zs),yt=p(e),J(ue.$$.fragment,e),jt=p(e),me=M(e,"P",{"data-svelte-h":!0}),k(me)!=="svelte-15d6klf"&&(me.innerHTML=Hs),kt=p(e),J(ce.$$.fragment,e),Ct=p(e),fe=M(e,"P",{"data-svelte-h":!0}),k(fe)!=="svelte-1lh10u2"&&(fe.textContent=Ps),Ut=p(e),J(de.$$.fragment,e),Tt=p(e),pe=M(e,"P",{"data-svelte-h":!0}),k(pe)!=="svelte-1fzeyvx"&&(pe.innerHTML=Ds),$t=p(e),J(ge.$$.fragment,e),Jt=p(e),Q=M(e,"DIV",{class:!0,"data-svelte-h":!0}),k(Q)!=="svelte-6cjtp1"&&(Q.innerHTML=Es),qt=p(e),he=M(e,"P",{"data-svelte-h":!0}),k(he)!=="svelte-1qpz3ys"&&(he.innerHTML=Xs),Nt=p(e),J(_e.$$.fragment,e),Zt=p(e),J(be.$$.fragment,e),Gt=p(e),we=M(e,"P",{"data-svelte-h":!0}),k(we)!=="svelte-11z96s9"&&(we.textContent=As),Wt=p(e),J(Me.$$.fragment,e),It=p(e),ve=M(e,"P",{"data-svelte-h":!0}),k(ve)!=="svelte-nca5xy"&&(ve.textContent=Ys),Vt=p(e),J(ye.$$.fragment,e),Bt=p(e),je=M(e,"P",{"data-svelte-h":!0}),k(je)!=="svelte-18fxe39"&&(je.textContent=Rs),St=p(e),J(ke.$$.fragment,e),Lt=p(e),Ce=M(e,"P",{"data-svelte-h":!0}),k(Ce)!=="svelte-1bdwzfu"&&(Ce.innerHTML=xs),zt=p(e),J(Ue.$$.fragment,e),Ht=p(e),Te=M(e,"P",{"data-svelte-h":!0}),k(Te)!=="svelte-rjqaf3"&&(Te.textContent=Fs),Pt=p(e),$e=M(e,"P",{"data-svelte-h":!0}),k($e)!=="svelte-yp9if5"&&($e.innerHTML=Qs),Dt=p(e),J(Je.$$.fragment,e),Et=p(e),qe=M(e,"P",{"data-svelte-h":!0}),k(qe)!=="svelte-cl1ldd"&&(qe.innerHTML=Ks),Xt=p(e),Ne=M(e,"P",{"data-svelte-h":!0}),k(Ne)!=="svelte-onulph"&&(Ne.innerHTML=Os),At=p(e),J(Ze.$$.fragment,e),Yt=p(e),Ge=M(e,"P",{"data-svelte-h":!0}),k(Ge)!=="svelte-qcoyrg"&&(Ge.innerHTML=ea),Rt=p(e),J(We.$$.fragment,e),xt=p(e),Ie=M(e,"P",{"data-svelte-h":!0}),k(Ie)!=="svelte-i890oq"&&(Ie.textContent=ta),Ft=p(e),Ve=M(e,"P",{"data-svelte-h":!0}),k(Ve)!=="svelte-1wzn7ma"&&(Ve.textContent=sa),Qt=p(e),Be=M(e,"UL",{"data-svelte-h":!0}),k(Be)!=="svelte-o5msyb"&&(Be.innerHTML=aa),Kt=p(e),Se=M(e,"P",{"data-svelte-h":!0}),k(Se)!=="svelte-obxecp"&&(Se.innerHTML=la),Ot=p(e),J(Le.$$.fragment,e),es=p(e),ze=M(e,"P",{"data-svelte-h":!0}),k(ze)!=="svelte-1qo9t3f"&&(ze.innerHTML=na),ts=p(e),J(He.$$.fragment,e),ss=p(e),Pe=M(e,"P",{"data-svelte-h":!0}),k(Pe)!=="svelte-1ljqqs3"&&(Pe.textContent=oa),as=p(e),J(De.$$.fragment,e),ls=p(e),Ee=M(e,"P",{"data-svelte-h":!0}),k(Ee)!=="svelte-1c3rc74"&&(Ee.innerHTML=ia),ns=p(e),J(K.$$.fragment,e),os=p(e),Xe=M(e,"P",{"data-svelte-h":!0}),k(Xe)!=="svelte-7pekzf"&&(Xe.innerHTML=ra),is=p(e),J(Ae.$$.fragment,e),rs=p(e),J(O.$$.fragment,e),us=p(e),Ye=M(e,"P",{"data-svelte-h":!0}),k(Ye)!=="svelte-kydn7r"&&(Ye.textContent=ua),ms=p(e),Re=M(e,"UL",{"data-svelte-h":!0}),k(Re)!=="svelte-1xnw77s"&&(Re.innerHTML=ma),cs=p(e),xe=M(e,"P",{"data-svelte-h":!0}),k(xe)!=="svelte-3wttzd"&&(xe.innerHTML=ca),fs=p(e),J(Fe.$$.fragment,e),ds=p(e),Qe=M(e,"P",{"data-svelte-h":!0}),k(Qe)!=="svelte-1tpggdq"&&(Qe.innerHTML=fa),ps=p(e),Ke=M(e,"P",{"data-svelte-h":!0}),k(Ke)!=="svelte-1xrm0cs"&&(Ke.innerHTML=da),gs=p(e),J(Oe.$$.fragment,e),hs=p(e),et=M(e,"P",{"data-svelte-h":!0}),k(et)!=="svelte-19fphdr"&&(et.textContent=pa),_s=p(e),J(tt.$$.fragment,e),bs=p(e),st=M(e,"P",{"data-svelte-h":!0}),k(st)!=="svelte-1ff49gu"&&(st.textContent=ga),ws=p(e),J(at.$$.fragment,e),Ms=p(e),lt=M(e,"P",{"data-svelte-h":!0}),k(lt)!=="svelte-1tdl2pq"&&(lt.textContent=ha),vs=p(e),ee=M(e,"DIV",{class:!0,"data-svelte-h":!0}),k(ee)!=="svelte-1yzsrw6"&&(ee.innerHTML=_a),ys=p(e),J(nt.$$.fragment,e),js=p(e),ot=M(e,"P",{"data-svelte-h":!0}),k(ot)!=="svelte-tfhhyg"&&(ot.textContent=ba),ks=p(e),it=M(e,"UL",{"data-svelte-h":!0}),k(it)!=="svelte-1r1xmc2"&&(it.innerHTML=wa),Cs=p(e),J(rt.$$.fragment,e),Us=p(e),dt=M(e,"P",{}),H(dt).forEach(u),this.h()},h(){y(t,"name","hf:doc:metadata"),y(t,"content",El),y(Q,"class","flex justify-center"),y(ee,"class","flex justify-center")},m(e,r){P(document.head,t),m(e,l,r),m(e,a,r),m(e,s,r),U(o,e,r),m(e,i,r),U(f,e,r),m(e,c,r),m(e,b,r),m(e,V,r),m(e,$,r),m(e,g,r),m(e,v,r),m(e,B,r),m(e,S,r),m(e,G,r),U(I,e,r),m(e,W,r),m(e,te,r),m(e,pt,r),U(se,e,r),m(e,gt,r),m(e,ae,r),m(e,ht,r),U(le,e,r),m(e,_t,r),m(e,ne,r),m(e,bt,r),m(e,oe,r),m(e,wt,r),m(e,ie,r),m(e,Mt,r),U(F,e,r),m(e,vt,r),m(e,re,r),m(e,yt,r),U(ue,e,r),m(e,jt,r),m(e,me,r),m(e,kt,r),U(ce,e,r),m(e,Ct,r),m(e,fe,r),m(e,Ut,r),U(de,e,r),m(e,Tt,r),m(e,pe,r),m(e,$t,r),U(ge,e,r),m(e,Jt,r),m(e,Q,r),m(e,qt,r),m(e,he,r),m(e,Nt,r),U(_e,e,r),m(e,Zt,r),U(be,e,r),m(e,Gt,r),m(e,we,r),m(e,Wt,r),U(Me,e,r),m(e,It,r),m(e,ve,r),m(e,Vt,r),U(ye,e,r),m(e,Bt,r),m(e,je,r),m(e,St,r),U(ke,e,r),m(e,Lt,r),m(e,Ce,r),m(e,zt,r),U(Ue,e,r),m(e,Ht,r),m(e,Te,r),m(e,Pt,r),m(e,$e,r),m(e,Dt,r),U(Je,e,r),m(e,Et,r),m(e,qe,r),m(e,Xt,r),m(e,Ne,r),m(e,At,r),U(Ze,e,r),m(e,Yt,r),m(e,Ge,r),m(e,Rt,r),U(We,e,r),m(e,xt,r),m(e,Ie,r),m(e,Ft,r),m(e,Ve,r),m(e,Qt,r),m(e,Be,r),m(e,Kt,r),m(e,Se,r),m(e,Ot,r),U(Le,e,r),m(e,es,r),m(e,ze,r),m(e,ts,r),U(He,e,r),m(e,ss,r),m(e,Pe,r),m(e,as,r),U(De,e,r),m(e,ls,r),m(e,Ee,r),m(e,ns,r),U(K,e,r),m(e,os,r),m(e,Xe,r),m(e,is,r),U(Ae,e,r),m(e,rs,r),U(O,e,r),m(e,us,r),m(e,Ye,r),m(e,ms,r),m(e,Re,r),m(e,cs,r),m(e,xe,r),m(e,fs,r),U(Fe,e,r),m(e,ds,r),m(e,Qe,r),m(e,ps,r),m(e,Ke,r),m(e,gs,r),U(Oe,e,r),m(e,hs,r),m(e,et,r),m(e,_s,r),U(tt,e,r),m(e,bs,r),m(e,st,r),m(e,ws,r),U(at,e,r),m(e,Ms,r),m(e,lt,r),m(e,vs,r),m(e,ee,r),m(e,ys,r),U(nt,e,r),m(e,js,r),m(e,ot,r),m(e,ks,r),m(e,it,r),m(e,Cs,r),U(rt,e,r),m(e,Us,r),m(e,dt,r),Ts=!0},p(e,[r]){const Ma={};r&2&&(Ma.$$scope={dirty:r,ctx:e}),I.$set(Ma);const va={};r&2&&(va.$$scope={dirty:r,ctx:e}),F.$set(va);const ya={};r&2&&(ya.$$scope={dirty:r,ctx:e}),K.$set(ya);const ja={};r&2&&(ja.$$scope={dirty:r,ctx:e}),O.$set(ja)},i(e){Ts||(h(o.$$.fragment,e),h(f.$$.fragment,e),h(I.$$.fragment,e),h(se.$$.fragment,e),h(le.$$.fragment,e),h(F.$$.fragment,e),h(ue.$$.fragment,e),h(ce.$$.fragment,e),h(de.$$.fragment,e),h(ge.$$.fragment,e),h(_e.$$.fragment,e),h(be.$$.fragment,e),h(Me.$$.fragment,e),h(ye.$$.fragment,e),h(ke.$$.fragment,e),h(Ue.$$.fragment,e),h(Je.$$.fragment,e),h(Ze.$$.fragment,e),h(We.$$.fragment,e),h(Le.$$.fragment,e),h(He.$$.fragment,e),h(De.$$.fragment,e),h(K.$$.fragment,e),h(Ae.$$.fragment,e),h(O.$$.fragment,e),h(Fe.$$.fragment,e),h(Oe.$$.fragment,e),h(tt.$$.fragment,e),h(at.$$.fragment,e),h(nt.$$.fragment,e),h(rt.$$.fragment,e),Ts=!0)},o(e){_(o.$$.fragment,e),_(f.$$.fragment,e),_(I.$$.fragment,e),_(se.$$.fragment,e),_(le.$$.fragment,e),_(F.$$.fragment,e),_(ue.$$.fragment,e),_(ce.$$.fragment,e),_(de.$$.fragment,e),_(ge.$$.fragment,e),_(_e.$$.fragment,e),_(be.$$.fragment,e),_(Me.$$.fragment,e),_(ye.$$.fragment,e),_(ke.$$.fragment,e),_(Ue.$$.fragment,e),_(Je.$$.fragment,e),_(Ze.$$.fragment,e),_(We.$$.fragment,e),_(Le.$$.fragment,e),_(He.$$.fragment,e),_(De.$$.fragment,e),_(K.$$.fragment,e),_(Ae.$$.fragment,e),_(O.$$.fragment,e),_(Fe.$$.fragment,e),_(Oe.$$.fragment,e),_(tt.$$.fragment,e),_(at.$$.fragment,e),_(nt.$$.fragment,e),_(rt.$$.fragment,e),Ts=!1},d(e){e&&(u(l),u(a),u(s),u(i),u(c),u(b),u(V),u($),u(g),u(v),u(B),u(S),u(G),u(W),u(te),u(pt),u(gt),u(ae),u(ht),u(_t),u(ne),u(bt),u(oe),u(wt),u(ie),u(Mt),u(vt),u(re),u(yt),u(jt),u(me),u(kt),u(Ct),u(fe),u(Ut),u(Tt),u(pe),u($t),u(Jt),u(Q),u(qt),u(he),u(Nt),u(Zt),u(Gt),u(we),u(Wt),u(It),u(ve),u(Vt),u(Bt),u(je),u(St),u(Lt),u(Ce),u(zt),u(Ht),u(Te),u(Pt),u($e),u(Dt),u(Et),u(qe),u(Xt),u(Ne),u(At),u(Yt),u(Ge),u(Rt),u(xt),u(Ie),u(Ft),u(Ve),u(Qt),u(Be),u(Kt),u(Se),u(Ot),u(es),u(ze),u(ts),u(ss),u(Pe),u(as),u(ls),u(Ee),u(ns),u(os),u(Xe),u(is),u(rs),u(us),u(Ye),u(ms),u(Re),u(cs),u(xe),u(fs),u(ds),u(Qe),u(ps),u(Ke),u(gs),u(hs),u(et),u(_s),u(bs),u(st),u(ws),u(Ms),u(lt),u(vs),u(ee),u(ys),u(js),u(ot),u(ks),u(it),u(Cs),u(Us),u(dt)),u(t),T(o,e),T(f,e),T(I,e),T(se,e),T(le,e),T(F,e),T(ue,e),T(ce,e),T(de,e),T(ge,e),T(_e,e),T(be,e),T(Me,e),T(ye,e),T(ke,e),T(Ue,e),T(Je,e),T(Ze,e),T(We,e),T(Le,e),T(He,e),T(De,e),T(K,e),T(Ae,e),T(O,e),T(Fe,e),T(Oe,e),T(tt,e),T(at,e),T(nt,e),T(rt,e)}}}const El='{"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 Xl(n){return Gs(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Ql extends ct{constructor(t){super(),ft(this,t,Xl,Dl,mt,{})}}export{Ql as component};