diffusers/main/en/_app/pages/api/attnprocessor.mdx-hf-doc-builder.js

import{S as Qr,i as Yr,s as Zr,e as s,k as c,w as p,t as f,M as en,c as r,d as o,m as l,a as n,x as u,h as m,b as i,G as t,g as d,y as h,L as on,q as _,o as v,B as A,v as tn}from"../../chunks/vendor-hf-doc-builder.js";import{D as P}from"../../chunks/Docstring-hf-doc-builder.js";import{I as g}from"../../chunks/IconCopyLink-hf-doc-builder.js";function sn(Os){let $,So,b,Q,He,me,Xt,We,qt,To,Ie,It,Vo,y,Y,Oe,pe,Ht,Be,Wt,zo,w,ue,Ot,Me,Bt,Fo,x,Z,Ue,he,Mt,Ge,Ut,Ko,k,_e,Gt,Je,Jt,Xo,E,ee,je,ve,jt,Qe,Qt,qo,L,Ae,Yt,Ye,Zt,Io,D,oe,Ze,ge,es,eo,os,Ho,R,Pe,ts,oo,ss,Wo,N,te,to,$e,rs,so,ns,Oo,C,be,is,ro,as,Bo,S,se,no,ye,ds,io,cs,Mo,T,we,ls,ao,fs,Uo,V,re,co,xe,ms,lo,ps,Go,z,ke,us,fo,hs,Jo,F,ne,mo,Ee,_s,po,vs,jo,K,Le,As,uo,gs,Qo,X,ie,ho,De,Ps,_o,$s,Yo,q,Re,bs,vo,ys,Zo,I,ae,Ao,Ne,ws,go,xs,et,H,Ce,ks,Po,Es,ot,W,de,$o,Se,Ls,bo,Ds,tt,O,Te,Rs,yo,Ns,st,B,ce,wo,Ve,Cs,xo,Ss,rt,M,ze,Ts,ko,Vs,nt,U,le,Eo,Fe,zs,Lo,Fs,it,G,Ke,Ks,Do,Xs,at,J,fe,Ro,Xe,qs,No,Is,dt,j,qe,Hs,Co,Ws,ct;return me=new g({}),pe=new g({}),ue=new P({props:{name:"class diffusers.models.attention_processor.AttnProcessor",anchor:"diffusers.models.attention_processor.AttnProcessor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L535"}}),he=new g({}),_e=new P({props:{name:"class diffusers.models.attention_processor.AttnProcessor2_0",anchor:"diffusers.models.attention_processor.AttnProcessor2_0",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L971"}}),ve=new g({}),Ae=new P({props:{name:"class diffusers.models.attention_processor.LoRAAttnProcessor",anchor:"diffusers.models.attention_processor.LoRAAttnProcessor",parameters:[{name:"hidden_size",val:""},{name:"cross_attention_dim",val:" = None"},{name:"rank",val:" = 4"},{name:"network_alpha",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.models.attention_processor.LoRAAttnProcessor.hidden_size",description:`<strong>hidden_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The hidden size of the attention layer.`,name:"hidden_size"},{anchor:"diffusers.models.attention_processor.LoRAAttnProcessor.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The number of channels in the <code>encoder_hidden_states</code>.`,name:"cross_attention_dim"},{anchor:"diffusers.models.attention_processor.LoRAAttnProcessor.rank",description:`<strong>rank</strong> (<code>int</code>, defaults to 4) &#x2014;
The dimension of the LoRA update matrices.`,name:"rank"},{anchor:"diffusers.models.attention_processor.LoRAAttnProcessor.network_alpha",description:`<strong>network_alpha</strong> (<code>int</code>, <em>optional</em>) &#x2014;
Equivalent to <code>alpha</code> but it&#x2019;s usage is specific to Kohya (A1111) style LoRAs.`,name:"network_alpha"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L1460"}}),ge=new g({}),Pe=new P({props:{name:"class diffusers.models.attention_processor.LoRAAttnProcessor2_0",anchor:"diffusers.models.attention_processor.LoRAAttnProcessor2_0",parameters:[{name:"hidden_size",val:""},{name:"cross_attention_dim",val:" = None"},{name:"rank",val:" = 4"},{name:"network_alpha",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.models.attention_processor.LoRAAttnProcessor2_0.hidden_size",description:`<strong>hidden_size</strong> (<code>int</code>) &#x2014;
The hidden size of the attention layer.`,name:"hidden_size"},{anchor:"diffusers.models.attention_processor.LoRAAttnProcessor2_0.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The number of channels in the <code>encoder_hidden_states</code>.`,name:"cross_attention_dim"},{anchor:"diffusers.models.attention_processor.LoRAAttnProcessor2_0.rank",description:`<strong>rank</strong> (<code>int</code>, defaults to 4) &#x2014;
The dimension of the LoRA update matrices.`,name:"rank"},{anchor:"diffusers.models.attention_processor.LoRAAttnProcessor2_0.network_alpha",description:`<strong>network_alpha</strong> (<code>int</code>, <em>optional</em>) &#x2014;
Equivalent to <code>alpha</code> but it&#x2019;s usage is specific to Kohya (A1111) style LoRAs.`,name:"network_alpha"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L1523"}}),$e=new g({}),be=new P({props:{name:"class diffusers.models.attention_processor.CustomDiffusionAttnProcessor",anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor",parameters:[{name:"train_kv",val:" = True"},{name:"train_q_out",val:" = True"},{name:"hidden_size",val:" = None"},{name:"cross_attention_dim",val:" = None"},{name:"out_bias",val:" = True"},{name:"dropout",val:" = 0.0"}],parametersDescription:[{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor.train_kv",description:`<strong>train_kv</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to newly train the key and value matrices corresponding to the text features.`,name:"train_kv"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor.train_q_out",description:`<strong>train_q_out</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to newly train query matrices corresponding to the latent image features.`,name:"train_q_out"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor.hidden_size",description:`<strong>hidden_size</strong> (<code>int</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The hidden size of the attention layer.`,name:"hidden_size"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (<code>int</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The number of channels in the <code>encoder_hidden_states</code>.`,name:"cross_attention_dim"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor.out_bias",description:`<strong>out_bias</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to include the bias parameter in <code>train_q_out</code>.`,name:"out_bias"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor.dropout",description:`<strong>dropout</strong> (<code>float</code>, <em>optional</em>, defaults to 0.0) &#x2014;
The dropout probability to use.`,name:"dropout"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L602"}}),ye=new g({}),we=new P({props:{name:"class diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0",anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0",parameters:[{name:"train_kv",val:" = True"},{name:"train_q_out",val:" = True"},{name:"hidden_size",val:" = None"},{name:"cross_attention_dim",val:" = None"},{name:"out_bias",val:" = True"},{name:"dropout",val:" = 0.0"}],parametersDescription:[{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0.train_kv",description:`<strong>train_kv</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to newly train the key and value matrices corresponding to the text features.`,name:"train_kv"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0.train_q_out",description:`<strong>train_q_out</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to newly train query matrices corresponding to the latent image features.`,name:"train_q_out"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0.hidden_size",description:`<strong>hidden_size</strong> (<code>int</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The hidden size of the attention layer.`,name:"hidden_size"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (<code>int</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The number of channels in the <code>encoder_hidden_states</code>.`,name:"cross_attention_dim"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0.out_bias",description:`<strong>out_bias</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to include the bias parameter in <code>train_q_out</code>.`,name:"out_bias"},{anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0.dropout",description:`<strong>dropout</strong> (<code>float</code>, <em>optional</em>, defaults to 0.0) &#x2014;
The dropout probability to use.`,name:"dropout"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L1165"}}),xe=new g({}),ke=new P({props:{name:"class diffusers.models.attention_processor.AttnAddedKVProcessor",anchor:"diffusers.models.attention_processor.AttnAddedKVProcessor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L700"}}),Ee=new g({}),Le=new P({props:{name:"class diffusers.models.attention_processor.AttnAddedKVProcessor2_0",anchor:"diffusers.models.attention_processor.AttnAddedKVProcessor2_0",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L754"}}),De=new g({}),Re=new P({props:{name:"class diffusers.models.attention_processor.LoRAAttnAddedKVProcessor",anchor:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor",parameters:[{name:"hidden_size",val:""},{name:"cross_attention_dim",val:" = None"},{name:"rank",val:" = 4"},{name:"network_alpha",val:" = None"}],parametersDescription:[{anchor:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor.hidden_size",description:`<strong>hidden_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The hidden size of the attention layer.`,name:"hidden_size"},{anchor:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (<code>int</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The number of channels in the <code>encoder_hidden_states</code>.`,name:"cross_attention_dim"},{anchor:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor.rank",description:`<strong>rank</strong> (<code>int</code>, defaults to 4) &#x2014;
The dimension of the LoRA update matrices.`,name:"rank"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L1667"}}),Ne=new g({}),Ce=new P({props:{name:"class diffusers.models.attention_processor.XFormersAttnProcessor",anchor:"diffusers.models.attention_processor.XFormersAttnProcessor",parameters:[{name:"attention_op",val:": typing.Optional[typing.Callable] = None"}],parametersDescription:[{anchor:"diffusers.models.attention_processor.XFormersAttnProcessor.attention_op",description:`<strong>attention_op</strong> (<code>Callable</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The base
<a href="https://facebookresearch.github.io/xformers/components/ops.html#xformers.ops.AttentionOpBase" rel="nofollow">operator</a> to
use as the attention operator. It is recommended to set to <code>None</code>, and allow xFormers to choose the best
operator.`,name:"attention_op"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L882"}}),Se=new g({}),Te=new P({props:{name:"class diffusers.models.attention_processor.LoRAXFormersAttnProcessor",anchor:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor",parameters:[{name:"hidden_size",val:""},{name:"cross_attention_dim",val:""},{name:"rank",val:" = 4"},{name:"attention_op",val:": typing.Optional[typing.Callable] = None"},{name:"network_alpha",val:" = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor.hidden_size",description:`<strong>hidden_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The hidden size of the attention layer.`,name:"hidden_size"},{anchor:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The number of channels in the <code>encoder_hidden_states</code>.`,name:"cross_attention_dim"},{anchor:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor.rank",description:`<strong>rank</strong> (<code>int</code>, defaults to 4) &#x2014;
The dimension of the LoRA update matrices.`,name:"rank"},{anchor:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor.attention_op",description:`<strong>attention_op</strong> (<code>Callable</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The base
<a href="https://facebookresearch.github.io/xformers/components/ops.html#xformers.ops.AttentionOpBase" rel="nofollow">operator</a> to
use as the attention operator. It is recommended to set to <code>None</code>, and allow xFormers to choose the best
operator.`,name:"attention_op"},{anchor:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor.network_alpha",description:`<strong>network_alpha</strong> (<code>int</code>, <em>optional</em>) &#x2014;
Equivalent to <code>alpha</code> but it&#x2019;s usage is specific to Kohya (A1111) style LoRAs.`,name:"network_alpha"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L1589"}}),Ve=new g({}),ze=new P({props:{name:"class diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor",anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor",parameters:[{name:"train_kv",val:" = True"},{name:"train_q_out",val:" = False"},{name:"hidden_size",val:" = None"},{name:"cross_attention_dim",val:" = None"},{name:"out_bias",val:" = True"},{name:"dropout",val:" = 0.0"},{name:"attention_op",val:": typing.Optional[typing.Callable] = None"}],parametersDescription:[{anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor.train_kv",description:`<strong>train_kv</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to newly train the key and value matrices corresponding to the text features.`,name:"train_kv"},{anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor.train_q_out",description:`<strong>train_q_out</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to newly train query matrices corresponding to the latent image features.`,name:"train_q_out"},{anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor.hidden_size",description:`<strong>hidden_size</strong> (<code>int</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The hidden size of the attention layer.`,name:"hidden_size"},{anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (<code>int</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The number of channels in the <code>encoder_hidden_states</code>.`,name:"cross_attention_dim"},{anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor.out_bias",description:`<strong>out_bias</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to include the bias parameter in <code>train_q_out</code>.`,name:"out_bias"},{anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor.dropout",description:`<strong>dropout</strong> (<code>float</code>, <em>optional</em>, defaults to 0.0) &#x2014;
The dropout probability to use.`,name:"dropout"},{anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor.attention_op",description:`<strong>attention_op</strong> (<code>Callable</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The base
<a href="https://facebookresearch.github.io/xformers/components/ops.html#xformers.ops.AttentionOpBase" rel="nofollow">operator</a> to use
as the attention operator. It is recommended to set to <code>None</code>, and allow xFormers to choose the best operator.`,name:"attention_op"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L1056"}}),Fe=new g({}),Ke=new P({props:{name:"class diffusers.models.attention_processor.SlicedAttnProcessor",anchor:"diffusers.models.attention_processor.SlicedAttnProcessor",parameters:[{name:"slice_size",val:""}],parametersDescription:[{anchor:"diffusers.models.attention_processor.SlicedAttnProcessor.slice_size",description:`<strong>slice_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The number of steps to compute attention. Uses as many slices as <code>attention_head_dim // slice_size</code>, and
<code>attention_head_dim</code> must be a multiple of the <code>slice_size</code>.`,name:"slice_size"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L1270"}}),Xe=new g({}),qe=new P({props:{name:"class diffusers.models.attention_processor.SlicedAttnAddedKVProcessor",anchor:"diffusers.models.attention_processor.SlicedAttnAddedKVProcessor",parameters:[{name:"slice_size",val:""}],parametersDescription:[{anchor:"diffusers.models.attention_processor.SlicedAttnAddedKVProcessor.slice_size",description:`<strong>slice_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The number of steps to compute attention. Uses as many slices as <code>attention_head_dim // slice_size</code>, and
<code>attention_head_dim</code> must be a multiple of the <code>slice_size</code>.`,name:"slice_size"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py#L1351"}}),{c(){$=s("meta"),So=c(),b=s("h1"),Q=s("a"),He=s("span"),p(me.$$.fragment),Xt=c(),We=s("span"),qt=f("Attention Processor"),To=c(),Ie=s("p"),It=f("An attention processor is a class for applying different types of attention mechanisms."),Vo=c(),y=s("h2"),Y=s("a"),Oe=s("span"),p(pe.$$.fragment),Ht=c(),Be=s("span"),Wt=f("AttnProcessor"),zo=c(),w=s("div"),p(ue.$$.fragment),Ot=c(),Me=s("p"),Bt=f("Default processor for performing attention-related computations."),Fo=c(),x=s("h2"),Z=s("a"),Ue=s("span"),p(he.$$.fragment),Mt=c(),Ge=s("span"),Ut=f("AttnProcessor2_0"),Ko=c(),k=s("div"),p(_e.$$.fragment),Gt=c(),Je=s("p"),Jt=f("Processor for implementing scaled dot-product attention (enabled by default if you\u2019re using PyTorch 2.0)."),Xo=c(),E=s("h2"),ee=s("a"),je=s("span"),p(ve.$$.fragment),jt=c(),Qe=s("span"),Qt=f("LoRAAttnProcessor"),qo=c(),L=s("div"),p(Ae.$$.fragment),Yt=c(),Ye=s("p"),Zt=f("Processor for implementing the LoRA attention mechanism."),Io=c(),D=s("h2"),oe=s("a"),Ze=s("span"),p(ge.$$.fragment),es=c(),eo=s("span"),os=f("LoRAAttnProcessor2_0"),Ho=c(),R=s("div"),p(Pe.$$.fragment),ts=c(),oo=s("p"),ss=f(`Processor for implementing the LoRA attention mechanism using PyTorch 2.0\u2019s memory-efficient scaled dot-product
attention.`),Wo=c(),N=s("h2"),te=s("a"),to=s("span"),p($e.$$.fragment),rs=c(),so=s("span"),ns=f("CustomDiffusionAttnProcessor"),Oo=c(),C=s("div"),p(be.$$.fragment),is=c(),ro=s("p"),as=f("Processor for implementing attention for the Custom Diffusion method."),Bo=c(),S=s("h2"),se=s("a"),no=s("span"),p(ye.$$.fragment),ds=c(),io=s("span"),cs=f("CustomDiffusionAttnProcessor2_0"),Mo=c(),T=s("div"),p(we.$$.fragment),ls=c(),ao=s("p"),fs=f(`Processor for implementing attention for the Custom Diffusion method using PyTorch 2.0\u2019s memory-efficient scaled
dot-product attention.`),Uo=c(),V=s("h2"),re=s("a"),co=s("span"),p(xe.$$.fragment),ms=c(),lo=s("span"),ps=f("AttnAddedKVProcessor"),Go=c(),z=s("div"),p(ke.$$.fragment),us=c(),fo=s("p"),hs=f(`Processor for performing attention-related computations with extra learnable key and value matrices for the text
encoder.`),Jo=c(),F=s("h2"),ne=s("a"),mo=s("span"),p(Ee.$$.fragment),_s=c(),po=s("span"),vs=f("AttnAddedKVProcessor2_0"),jo=c(),K=s("div"),p(Le.$$.fragment),As=c(),uo=s("p"),gs=f(`Processor for performing scaled dot-product attention (enabled by default if you\u2019re using PyTorch 2.0), with extra
learnable key and value matrices for the text encoder.`),Qo=c(),X=s("h2"),ie=s("a"),ho=s("span"),p(De.$$.fragment),Ps=c(),_o=s("span"),$s=f("LoRAAttnAddedKVProcessor"),Yo=c(),q=s("div"),p(Re.$$.fragment),bs=c(),vo=s("p"),ys=f(`Processor for implementing the LoRA attention mechanism with extra learnable key and value matrices for the text
encoder.`),Zo=c(),I=s("h2"),ae=s("a"),Ao=s("span"),p(Ne.$$.fragment),ws=c(),go=s("span"),xs=f("XFormersAttnProcessor"),et=c(),H=s("div"),p(Ce.$$.fragment),ks=c(),Po=s("p"),Es=f("Processor for implementing memory efficient attention using xFormers."),ot=c(),W=s("h2"),de=s("a"),$o=s("span"),p(Se.$$.fragment),Ls=c(),bo=s("span"),Ds=f("LoRAXFormersAttnProcessor"),tt=c(),O=s("div"),p(Te.$$.fragment),Rs=c(),yo=s("p"),Ns=f("Processor for implementing the LoRA attention mechanism with memory efficient attention using xFormers."),st=c(),B=s("h2"),ce=s("a"),wo=s("span"),p(Ve.$$.fragment),Cs=c(),xo=s("span"),Ss=f("CustomDiffusionXFormersAttnProcessor"),rt=c(),M=s("div"),p(ze.$$.fragment),Ts=c(),ko=s("p"),Vs=f("Processor for implementing memory efficient attention using xFormers for the Custom Diffusion method."),nt=c(),U=s("h2"),le=s("a"),Eo=s("span"),p(Fe.$$.fragment),zs=c(),Lo=s("span"),Fs=f("SlicedAttnProcessor"),it=c(),G=s("div"),p(Ke.$$.fragment),Ks=c(),Do=s("p"),Xs=f("Processor for implementing sliced attention."),at=c(),J=s("h2"),fe=s("a"),Ro=s("span"),p(Xe.$$.fragment),qs=c(),No=s("span"),Is=f("SlicedAttnAddedKVProcessor"),dt=c(),j=s("div"),p(qe.$$.fragment),Hs=c(),Co=s("p"),Ws=f("Processor for implementing sliced attention with extra learnable key and value matrices for the text encoder."),this.h()},l(e){const a=en('[data-svelte="svelte-1phssyn"]',document.head);$=r(a,"META",{name:!0,content:!0}),a.forEach(o),So=l(e),b=r(e,"H1",{class:!0});var lt=n(b);Q=r(lt,"A",{id:!0,class:!0,href:!0});var Bs=n(Q);He=r(Bs,"SPAN",{});var Ms=n(He);u(me.$$.fragment,Ms),Ms.forEach(o),Bs.forEach(o),Xt=l(lt),We=r(lt,"SPAN",{});var Us=n(We);qt=m(Us,"Attention Processor"),Us.forEach(o),lt.forEach(o),To=l(e),Ie=r(e,"P",{});var Gs=n(Ie);It=m(Gs,"An attention processor is a class for applying different types of attention mechanisms."),Gs.forEach(o),Vo=l(e),y=r(e,"H2",{class:!0});var ft=n(y);Y=r(ft,"A",{id:!0,class:!0,href:!0});var Js=n(Y);Oe=r(Js,"SPAN",{});var js=n(Oe);u(pe.$$.fragment,js),js.forEach(o),Js.forEach(o),Ht=l(ft),Be=r(ft,"SPAN",{});var Qs=n(Be);Wt=m(Qs,"AttnProcessor"),Qs.forEach(o),ft.forEach(o),zo=l(e),w=r(e,"DIV",{class:!0});var mt=n(w);u(ue.$$.fragment,mt),Ot=l(mt),Me=r(mt,"P",{});var Ys=n(Me);Bt=m(Ys,"Default processor for performing attention-related computations."),Ys.forEach(o),mt.forEach(o),Fo=l(e),x=r(e,"H2",{class:!0});var pt=n(x);Z=r(pt,"A",{id:!0,class:!0,href:!0});var Zs=n(Z);Ue=r(Zs,"SPAN",{});var er=n(Ue);u(he.$$.fragment,er),er.forEach(o),Zs.forEach(o),Mt=l(pt),Ge=r(pt,"SPAN",{});var or=n(Ge);Ut=m(or,"AttnProcessor2_0"),or.forEach(o),pt.forEach(o),Ko=l(e),k=r(e,"DIV",{class:!0});var ut=n(k);u(_e.$$.fragment,ut),Gt=l(ut),Je=r(ut,"P",{});var tr=n(Je);Jt=m(tr,"Processor for implementing scaled dot-product attention (enabled by default if you\u2019re using PyTorch 2.0)."),tr.forEach(o),ut.forEach(o),Xo=l(e),E=r(e,"H2",{class:!0});var ht=n(E);ee=r(ht,"A",{id:!0,class:!0,href:!0});var sr=n(ee);je=r(sr,"SPAN",{});var rr=n(je);u(ve.$$.fragment,rr),rr.forEach(o),sr.forEach(o),jt=l(ht),Qe=r(ht,"SPAN",{});var nr=n(Qe);Qt=m(nr,"LoRAAttnProcessor"),nr.forEach(o),ht.forEach(o),qo=l(e),L=r(e,"DIV",{class:!0});var _t=n(L);u(Ae.$$.fragment,_t),Yt=l(_t),Ye=r(_t,"P",{});var ir=n(Ye);Zt=m(ir,"Processor for implementing the LoRA attention mechanism."),ir.forEach(o),_t.forEach(o),Io=l(e),D=r(e,"H2",{class:!0});var vt=n(D);oe=r(vt,"A",{id:!0,class:!0,href:!0});var ar=n(oe);Ze=r(ar,"SPAN",{});var dr=n(Ze);u(ge.$$.fragment,dr),dr.forEach(o),ar.forEach(o),es=l(vt),eo=r(vt,"SPAN",{});var cr=n(eo);os=m(cr,"LoRAAttnProcessor2_0"),cr.forEach(o),vt.forEach(o),Ho=l(e),R=r(e,"DIV",{class:!0});var At=n(R);u(Pe.$$.fragment,At),ts=l(At),oo=r(At,"P",{});var lr=n(oo);ss=m(lr,`Processor for implementing the LoRA attention mechanism using PyTorch 2.0\u2019s memory-efficient scaled dot-product
attention.`),lr.forEach(o),At.forEach(o),Wo=l(e),N=r(e,"H2",{class:!0});var gt=n(N);te=r(gt,"A",{id:!0,class:!0,href:!0});var fr=n(te);to=r(fr,"SPAN",{});var mr=n(to);u($e.$$.fragment,mr),mr.forEach(o),fr.forEach(o),rs=l(gt),so=r(gt,"SPAN",{});var pr=n(so);ns=m(pr,"CustomDiffusionAttnProcessor"),pr.forEach(o),gt.forEach(o),Oo=l(e),C=r(e,"DIV",{class:!0});var Pt=n(C);u(be.$$.fragment,Pt),is=l(Pt),ro=r(Pt,"P",{});var ur=n(ro);as=m(ur,"Processor for implementing attention for the Custom Diffusion method."),ur.forEach(o),Pt.forEach(o),Bo=l(e),S=r(e,"H2",{class:!0});var $t=n(S);se=r($t,"A",{id:!0,class:!0,href:!0});var hr=n(se);no=r(hr,"SPAN",{});var _r=n(no);u(ye.$$.fragment,_r),_r.forEach(o),hr.forEach(o),ds=l($t),io=r($t,"SPAN",{});var vr=n(io);cs=m(vr,"CustomDiffusionAttnProcessor2_0"),vr.forEach(o),$t.forEach(o),Mo=l(e),T=r(e,"DIV",{class:!0});var bt=n(T);u(we.$$.fragment,bt),ls=l(bt),ao=r(bt,"P",{});var Ar=n(ao);fs=m(Ar,`Processor for implementing attention for the Custom Diffusion method using PyTorch 2.0\u2019s memory-efficient scaled
dot-product attention.`),Ar.forEach(o),bt.forEach(o),Uo=l(e),V=r(e,"H2",{class:!0});var yt=n(V);re=r(yt,"A",{id:!0,class:!0,href:!0});var gr=n(re);co=r(gr,"SPAN",{});var Pr=n(co);u(xe.$$.fragment,Pr),Pr.forEach(o),gr.forEach(o),ms=l(yt),lo=r(yt,"SPAN",{});var $r=n(lo);ps=m($r,"AttnAddedKVProcessor"),$r.forEach(o),yt.forEach(o),Go=l(e),z=r(e,"DIV",{class:!0});var wt=n(z);u(ke.$$.fragment,wt),us=l(wt),fo=r(wt,"P",{});var br=n(fo);hs=m(br,`Processor for performing attention-related computations with extra learnable key and value matrices for the text
encoder.`),br.forEach(o),wt.forEach(o),Jo=l(e),F=r(e,"H2",{class:!0});var xt=n(F);ne=r(xt,"A",{id:!0,class:!0,href:!0});var yr=n(ne);mo=r(yr,"SPAN",{});var wr=n(mo);u(Ee.$$.fragment,wr),wr.forEach(o),yr.forEach(o),_s=l(xt),po=r(xt,"SPAN",{});var xr=n(po);vs=m(xr,"AttnAddedKVProcessor2_0"),xr.forEach(o),xt.forEach(o),jo=l(e),K=r(e,"DIV",{class:!0});var kt=n(K);u(Le.$$.fragment,kt),As=l(kt),uo=r(kt,"P",{});var kr=n(uo);gs=m(kr,`Processor for performing scaled dot-product attention (enabled by default if you\u2019re using PyTorch 2.0), with extra
learnable key and value matrices for the text encoder.`),kr.forEach(o),kt.forEach(o),Qo=l(e),X=r(e,"H2",{class:!0});var Et=n(X);ie=r(Et,"A",{id:!0,class:!0,href:!0});var Er=n(ie);ho=r(Er,"SPAN",{});var Lr=n(ho);u(De.$$.fragment,Lr),Lr.forEach(o),Er.forEach(o),Ps=l(Et),_o=r(Et,"SPAN",{});var Dr=n(_o);$s=m(Dr,"LoRAAttnAddedKVProcessor"),Dr.forEach(o),Et.forEach(o),Yo=l(e),q=r(e,"DIV",{class:!0});var Lt=n(q);u(Re.$$.fragment,Lt),bs=l(Lt),vo=r(Lt,"P",{});var Rr=n(vo);ys=m(Rr,`Processor for implementing the LoRA attention mechanism with extra learnable key and value matrices for the text
encoder.`),Rr.forEach(o),Lt.forEach(o),Zo=l(e),I=r(e,"H2",{class:!0});var Dt=n(I);ae=r(Dt,"A",{id:!0,class:!0,href:!0});var Nr=n(ae);Ao=r(Nr,"SPAN",{});var Cr=n(Ao);u(Ne.$$.fragment,Cr),Cr.forEach(o),Nr.forEach(o),ws=l(Dt),go=r(Dt,"SPAN",{});var Sr=n(go);xs=m(Sr,"XFormersAttnProcessor"),Sr.forEach(o),Dt.forEach(o),et=l(e),H=r(e,"DIV",{class:!0});var Rt=n(H);u(Ce.$$.fragment,Rt),ks=l(Rt),Po=r(Rt,"P",{});var Tr=n(Po);Es=m(Tr,"Processor for implementing memory efficient attention using xFormers."),Tr.forEach(o),Rt.forEach(o),ot=l(e),W=r(e,"H2",{class:!0});var Nt=n(W);de=r(Nt,"A",{id:!0,class:!0,href:!0});var Vr=n(de);$o=r(Vr,"SPAN",{});var zr=n($o);u(Se.$$.fragment,zr),zr.forEach(o),Vr.forEach(o),Ls=l(Nt),bo=r(Nt,"SPAN",{});var Fr=n(bo);Ds=m(Fr,"LoRAXFormersAttnProcessor"),Fr.forEach(o),Nt.forEach(o),tt=l(e),O=r(e,"DIV",{class:!0});var Ct=n(O);u(Te.$$.fragment,Ct),Rs=l(Ct),yo=r(Ct,"P",{});var Kr=n(yo);Ns=m(Kr,"Processor for implementing the LoRA attention mechanism with memory efficient attention using xFormers."),Kr.forEach(o),Ct.forEach(o),st=l(e),B=r(e,"H2",{class:!0});var St=n(B);ce=r(St,"A",{id:!0,class:!0,href:!0});var Xr=n(ce);wo=r(Xr,"SPAN",{});var qr=n(wo);u(Ve.$$.fragment,qr),qr.forEach(o),Xr.forEach(o),Cs=l(St),xo=r(St,"SPAN",{});var Ir=n(xo);Ss=m(Ir,"CustomDiffusionXFormersAttnProcessor"),Ir.forEach(o),St.forEach(o),rt=l(e),M=r(e,"DIV",{class:!0});var Tt=n(M);u(ze.$$.fragment,Tt),Ts=l(Tt),ko=r(Tt,"P",{});var Hr=n(ko);Vs=m(Hr,"Processor for implementing memory efficient attention using xFormers for the Custom Diffusion method."),Hr.forEach(o),Tt.forEach(o),nt=l(e),U=r(e,"H2",{class:!0});var Vt=n(U);le=r(Vt,"A",{id:!0,class:!0,href:!0});var Wr=n(le);Eo=r(Wr,"SPAN",{});var Or=n(Eo);u(Fe.$$.fragment,Or),Or.forEach(o),Wr.forEach(o),zs=l(Vt),Lo=r(Vt,"SPAN",{});var Br=n(Lo);Fs=m(Br,"SlicedAttnProcessor"),Br.forEach(o),Vt.forEach(o),it=l(e),G=r(e,"DIV",{class:!0});var zt=n(G);u(Ke.$$.fragment,zt),Ks=l(zt),Do=r(zt,"P",{});var Mr=n(Do);Xs=m(Mr,"Processor for implementing sliced attention."),Mr.forEach(o),zt.forEach(o),at=l(e),J=r(e,"H2",{class:!0});var Ft=n(J);fe=r(Ft,"A",{id:!0,class:!0,href:!0});var Ur=n(fe);Ro=r(Ur,"SPAN",{});var Gr=n(Ro);u(Xe.$$.fragment,Gr),Gr.forEach(o),Ur.forEach(o),qs=l(Ft),No=r(Ft,"SPAN",{});var Jr=n(No);Is=m(Jr,"SlicedAttnAddedKVProcessor"),Jr.forEach(o),Ft.forEach(o),dt=l(e),j=r(e,"DIV",{class:!0});var Kt=n(j);u(qe.$$.fragment,Kt),Hs=l(Kt),Co=r(Kt,"P",{});var jr=n(Co);Ws=m(jr,"Processor for implementing sliced attention with extra learnable key and value matrices for the text encoder."),jr.forEach(o),Kt.forEach(o),this.h()},h(){i($,"name","hf:doc:metadata"),i($,"content",JSON.stringify(rn)),i(Q,"id","attention-processor"),i(Q,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(Q,"href","#attention-processor"),i(b,"class","relative group"),i(Y,"id","diffusers.models.attention_processor.AttnProcessor"),i(Y,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(Y,"href","#diffusers.models.attention_processor.AttnProcessor"),i(y,"class","relative group"),i(w,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(Z,"id","diffusers.models.attention_processor.AttnProcessor2_0"),i(Z,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(Z,"href","#diffusers.models.attention_processor.AttnProcessor2_0"),i(x,"class","relative group"),i(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(ee,"id","diffusers.models.attention_processor.LoRAAttnProcessor"),i(ee,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(ee,"href","#diffusers.models.attention_processor.LoRAAttnProcessor"),i(E,"class","relative group"),i(L,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(oe,"id","diffusers.models.attention_processor.LoRAAttnProcessor2_0"),i(oe,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(oe,"href","#diffusers.models.attention_processor.LoRAAttnProcessor2_0"),i(D,"class","relative group"),i(R,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(te,"id","diffusers.models.attention_processor.CustomDiffusionAttnProcessor"),i(te,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(te,"href","#diffusers.models.attention_processor.CustomDiffusionAttnProcessor"),i(N,"class","relative group"),i(C,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(se,"id","diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0"),i(se,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(se,"href","#diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0"),i(S,"class","relative group"),i(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(re,"id","diffusers.models.attention_processor.AttnAddedKVProcessor"),i(re,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(re,"href","#diffusers.models.attention_processor.AttnAddedKVProcessor"),i(V,"class","relative group"),i(z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(ne,"id","diffusers.models.attention_processor.AttnAddedKVProcessor2_0"),i(ne,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(ne,"href","#diffusers.models.attention_processor.AttnAddedKVProcessor2_0"),i(F,"class","relative group"),i(K,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(ie,"id","diffusers.models.attention_processor.LoRAAttnAddedKVProcessor"),i(ie,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(ie,"href","#diffusers.models.attention_processor.LoRAAttnAddedKVProcessor"),i(X,"class","relative group"),i(q,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(ae,"id","diffusers.models.attention_processor.XFormersAttnProcessor"),i(ae,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(ae,"href","#diffusers.models.attention_processor.XFormersAttnProcessor"),i(I,"class","relative group"),i(H,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(de,"id","diffusers.models.attention_processor.LoRAXFormersAttnProcessor"),i(de,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(de,"href","#diffusers.models.attention_processor.LoRAXFormersAttnProcessor"),i(W,"class","relative group"),i(O,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(ce,"id","diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor"),i(ce,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(ce,"href","#diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor"),i(B,"class","relative group"),i(M,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(le,"id","diffusers.models.attention_processor.SlicedAttnProcessor"),i(le,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(le,"href","#diffusers.models.attention_processor.SlicedAttnProcessor"),i(U,"class","relative group"),i(G,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),i(fe,"id","diffusers.models.attention_processor.SlicedAttnAddedKVProcessor"),i(fe,"class","header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full"),i(fe,"href","#diffusers.models.attention_processor.SlicedAttnAddedKVProcessor"),i(J,"class","relative group"),i(j,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(e,a){t(document.head,$),d(e,So,a),d(e,b,a),t(b,Q),t(Q,He),h(me,He,null),t(b,Xt),t(b,We),t(We,qt),d(e,To,a),d(e,Ie,a),t(Ie,It),d(e,Vo,a),d(e,y,a),t(y,Y),t(Y,Oe),h(pe,Oe,null),t(y,Ht),t(y,Be),t(Be,Wt),d(e,zo,a),d(e,w,a),h(ue,w,null),t(w,Ot),t(w,Me),t(Me,Bt),d(e,Fo,a),d(e,x,a),t(x,Z),t(Z,Ue),h(he,Ue,null),t(x,Mt),t(x,Ge),t(Ge,Ut),d(e,Ko,a),d(e,k,a),h(_e,k,null),t(k,Gt),t(k,Je),t(Je,Jt),d(e,Xo,a),d(e,E,a),t(E,ee),t(ee,je),h(ve,je,null),t(E,jt),t(E,Qe),t(Qe,Qt),d(e,qo,a),d(e,L,a),h(Ae,L,null),t(L,Yt),t(L,Ye),t(Ye,Zt),d(e,Io,a),d(e,D,a),t(D,oe),t(oe,Ze),h(ge,Ze,null),t(D,es),t(D,eo),t(eo,os),d(e,Ho,a),d(e,R,a),h(Pe,R,null),t(R,ts),t(R,oo),t(oo,ss),d(e,Wo,a),d(e,N,a),t(N,te),t(te,to),h($e,to,null),t(N,rs),t(N,so),t(so,ns),d(e,Oo,a),d(e,C,a),h(be,C,null),t(C,is),t(C,ro),t(ro,as),d(e,Bo,a),d(e,S,a),t(S,se),t(se,no),h(ye,no,null),t(S,ds),t(S,io),t(io,cs),d(e,Mo,a),d(e,T,a),h(we,T,null),t(T,ls),t(T,ao),t(ao,fs),d(e,Uo,a),d(e,V,a),t(V,re),t(re,co),h(xe,co,null),t(V,ms),t(V,lo),t(lo,ps),d(e,Go,a),d(e,z,a),h(ke,z,null),t(z,us),t(z,fo),t(fo,hs),d(e,Jo,a),d(e,F,a),t(F,ne),t(ne,mo),h(Ee,mo,null),t(F,_s),t(F,po),t(po,vs),d(e,jo,a),d(e,K,a),h(Le,K,null),t(K,As),t(K,uo),t(uo,gs),d(e,Qo,a),d(e,X,a),t(X,ie),t(ie,ho),h(De,ho,null),t(X,Ps),t(X,_o),t(_o,$s),d(e,Yo,a),d(e,q,a),h(Re,q,null),t(q,bs),t(q,vo),t(vo,ys),d(e,Zo,a),d(e,I,a),t(I,ae),t(ae,Ao),h(Ne,Ao,null),t(I,ws),t(I,go),t(go,xs),d(e,et,a),d(e,H,a),h(Ce,H,null),t(H,ks),t(H,Po),t(Po,Es),d(e,ot,a),d(e,W,a),t(W,de),t(de,$o),h(Se,$o,null),t(W,Ls),t(W,bo),t(bo,Ds),d(e,tt,a),d(e,O,a),h(Te,O,null),t(O,Rs),t(O,yo),t(yo,Ns),d(e,st,a),d(e,B,a),t(B,ce),t(ce,wo),h(Ve,wo,null),t(B,Cs),t(B,xo),t(xo,Ss),d(e,rt,a),d(e,M,a),h(ze,M,null),t(M,Ts),t(M,ko),t(ko,Vs),d(e,nt,a),d(e,U,a),t(U,le),t(le,Eo),h(Fe,Eo,null),t(U,zs),t(U,Lo),t(Lo,Fs),d(e,it,a),d(e,G,a),h(Ke,G,null),t(G,Ks),t(G,Do),t(Do,Xs),d(e,at,a),d(e,J,a),t(J,fe),t(fe,Ro),h(Xe,Ro,null),t(J,qs),t(J,No),t(No,Is),d(e,dt,a),d(e,j,a),h(qe,j,null),t(j,Hs),t(j,Co),t(Co,Ws),ct=!0},p:on,i(e){ct||(_(me.$$.fragment,e),_(pe.$$.fragment,e),_(ue.$$.fragment,e),_(he.$$.fragment,e),_(_e.$$.fragment,e),_(ve.$$.fragment,e),_(Ae.$$.fragment,e),_(ge.$$.fragment,e),_(Pe.$$.fragment,e),_($e.$$.fragment,e),_(be.$$.fragment,e),_(ye.$$.fragment,e),_(we.$$.fragment,e),_(xe.$$.fragment,e),_(ke.$$.fragment,e),_(Ee.$$.fragment,e),_(Le.$$.fragment,e),_(De.$$.fragment,e),_(Re.$$.fragment,e),_(Ne.$$.fragment,e),_(Ce.$$.fragment,e),_(Se.$$.fragment,e),_(Te.$$.fragment,e),_(Ve.$$.fragment,e),_(ze.$$.fragment,e),_(Fe.$$.fragment,e),_(Ke.$$.fragment,e),_(Xe.$$.fragment,e),_(qe.$$.fragment,e),ct=!0)},o(e){v(me.$$.fragment,e),v(pe.$$.fragment,e),v(ue.$$.fragment,e),v(he.$$.fragment,e),v(_e.$$.fragment,e),v(ve.$$.fragment,e),v(Ae.$$.fragment,e),v(ge.$$.fragment,e),v(Pe.$$.fragment,e),v($e.$$.fragment,e),v(be.$$.fragment,e),v(ye.$$.fragment,e),v(we.$$.fragment,e),v(xe.$$.fragment,e),v(ke.$$.fragment,e),v(Ee.$$.fragment,e),v(Le.$$.fragment,e),v(De.$$.fragment,e),v(Re.$$.fragment,e),v(Ne.$$.fragment,e),v(Ce.$$.fragment,e),v(Se.$$.fragment,e),v(Te.$$.fragment,e),v(Ve.$$.fragment,e),v(ze.$$.fragment,e),v(Fe.$$.fragment,e),v(Ke.$$.fragment,e),v(Xe.$$.fragment,e),v(qe.$$.fragment,e),ct=!1},d(e){o($),e&&o(So),e&&o(b),A(me),e&&o(To),e&&o(Ie),e&&o(Vo),e&&o(y),A(pe),e&&o(zo),e&&o(w),A(ue),e&&o(Fo),e&&o(x),A(he),e&&o(Ko),e&&o(k),A(_e),e&&o(Xo),e&&o(E),A(ve),e&&o(qo),e&&o(L),A(Ae),e&&o(Io),e&&o(D),A(ge),e&&o(Ho),e&&o(R),A(Pe),e&&o(Wo),e&&o(N),A($e),e&&o(Oo),e&&o(C),A(be),e&&o(Bo),e&&o(S),A(ye),e&&o(Mo),e&&o(T),A(we),e&&o(Uo),e&&o(V),A(xe),e&&o(Go),e&&o(z),A(ke),e&&o(Jo),e&&o(F),A(Ee),e&&o(jo),e&&o(K),A(Le),e&&o(Qo),e&&o(X),A(De),e&&o(Yo),e&&o(q),A(Re),e&&o(Zo),e&&o(I),A(Ne),e&&o(et),e&&o(H),A(Ce),e&&o(ot),e&&o(W),A(Se),e&&o(tt),e&&o(O),A(Te),e&&o(st),e&&o(B),A(Ve),e&&o(rt),e&&o(M),A(ze),e&&o(nt),e&&o(U),A(Fe),e&&o(it),e&&o(G),A(Ke),e&&o(at),e&&o(J),A(Xe),e&&o(dt),e&&o(j),A(qe)}}}const rn={local:"attention-processor",sections:[{local:"diffusers.models.attention_processor.AttnProcessor",title:"AttnProcessor"},{local:"diffusers.models.attention_processor.AttnProcessor2_0",title:"AttnProcessor2_0"},{local:"diffusers.models.attention_processor.LoRAAttnProcessor",title:"LoRAAttnProcessor"},{local:"diffusers.models.attention_processor.LoRAAttnProcessor2_0",title:"LoRAAttnProcessor2_0"},{local:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor",title:"CustomDiffusionAttnProcessor"},{local:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0",title:"CustomDiffusionAttnProcessor2_0"},{local:"diffusers.models.attention_processor.AttnAddedKVProcessor",title:"AttnAddedKVProcessor"},{local:"diffusers.models.attention_processor.AttnAddedKVProcessor2_0",title:"AttnAddedKVProcessor2_0"},{local:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor",title:"LoRAAttnAddedKVProcessor"},{local:"diffusers.models.attention_processor.XFormersAttnProcessor",title:"XFormersAttnProcessor"},{local:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor",title:"LoRAXFormersAttnProcessor"},{local:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor",title:"CustomDiffusionXFormersAttnProcessor"},{local:"diffusers.models.attention_processor.SlicedAttnProcessor",title:"SlicedAttnProcessor"},{local:"diffusers.models.attention_processor.SlicedAttnAddedKVProcessor",title:"SlicedAttnAddedKVProcessor"}],title:"Attention Processor"};function nn(Os){return tn(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ln extends Qr{constructor($){super();Yr(this,$,nn,sn,Zr,{})}}export{ln as default,rn as metadata};