diffusers/pr_7645/en/_app/immutable/nodes/4.91cd8d62.js

import{s as lo,o as mo,n as fo}from"../chunks/scheduler.8c3d61f6.js";import{S as po,i as uo,g as i,s as r,r as d,A as _o,h as a,f as o,c as n,j as g,u as c,x as $,k as h,y as u,a as s,v as l,d as m,t as f,w as p}from"../chunks/index.589a98e8.js";import{T as go}from"../chunks/Tip.42aa8582.js";import{D as b}from"../chunks/Docstring.27406313.js";import{H as A,E as ho}from"../chunks/EditOnGithub.e5a8d9cb.js";function $o(Xe){let _,q="This API is currently 🧪 experimental in nature and can change in future.";return{c(){_=i("p"),_.textContent=q},l(v){_=a(v,"P",{"data-svelte-h":!0}),$(_)!=="svelte-2dfli5"&&(_.textContent=q)},m(v,Ae){s(v,_,Ae)},p:fo,d(v){v&&o(_)}}}function Ao(Xe){let _,q,v,Ae,E,qe,I,Ht="An attention processor is a class for applying different types of attention mechanisms.",Ee,S,Ie,x,O,Lt,be,Mt="Default processor for performing attention-related computations.",Se,U,Oe,y,W,zt,ve,Gt="Processor for implementing scaled dot-product attention (enabled by default if you’re using PyTorch 2.0).",Ue,j,We,C,B,Vt,Pe,Jt=`Processor for performing attention-related computations with extra learnable key and value matrices for the text
encoder.`,je,H,Be,w,M,Kt,xe,Qt=`Processor for performing scaled dot-product attention (enabled by default if you’re using PyTorch 2.0), with extra
learnable key and value matrices for the text encoder.`,He,G,Me,D,J,Nt,ye,Yt="Cross frame attention processor. Each frame attends the first frame.",Ge,Q,Je,T,Y,Rt,Ce,Zt="Processor for implementing attention for the Custom Diffusion method.",Qe,Z,Ye,F,ee,Xt,we,eo=`Processor for implementing attention for the Custom Diffusion method using PyTorch 2.0’s memory-efficient scaled
dot-product attention.`,Ze,te,et,k,oe,qt,De,to="Processor for implementing memory efficient attention using xFormers for the Custom Diffusion method.",tt,se,ot,P,re,Et,Te,oo=`Processor for implementing scaled dot-product attention (enabled by default if you’re using PyTorch 2.0). It uses
fused projection layers. For self-attention modules, all projection matrices (i.e., query, key, value) are fused.
For cross-attention modules, key and value projection matrices are fused.`,It,X,st,ne,rt,L,ie,St,Fe,so=`Processor for implementing the LoRA attention mechanism with extra learnable key and value matrices for the text
encoder.`,nt,ae,it,z,de,Ot,ke,ro="Processor for implementing the LoRA attention mechanism with memory efficient attention using xFormers.",at,ce,dt,V,le,Ut,Le,no="Processor for implementing sliced attention.",ct,me,lt,K,fe,Wt,ze,io="Processor for implementing sliced attention with extra learnable key and value matrices for the text encoder.",mt,pe,ft,N,ue,jt,Ve,ao="Processor for implementing memory efficient attention using xFormers.",pt,_e,ut,R,ge,Bt,Ke,co=`Processor for implementing flash attention using torch_npu. Torch_npu supports only fp16 and bf16 data types. If
fp32 is used, F.scaled_dot_product_attention will be used for computation, but the acceleration effect on NPU is
not significant.`,_t,he,gt,Re,ht;return E=new A({props:{title:"Attention Processor",local:"attention-processor",headingTag:"h1"}}),S=new A({props:{title:"AttnProcessor",local:"diffusers.models.attention_processor.AttnProcessor",headingTag:"h2"}}),O=new b({props:{name:"class diffusers.models.attention_processor.AttnProcessor",anchor:"diffusers.models.attention_processor.AttnProcessor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/models/attention_processor.py#L766"}}),U=new A({props:{title:"AttnProcessor2_0",local:"diffusers.models.attention_processor.AttnProcessor2_0",headingTag:"h2"}}),W=new b({props:{name:"class diffusers.models.attention_processor.AttnProcessor2_0",anchor:"diffusers.models.attention_processor.AttnProcessor2_0",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/models/attention_processor.py#L1515"}}),j=new A({props:{title:"AttnAddedKVProcessor",local:"diffusers.models.attention_processor.AttnAddedKVProcessor",headingTag:"h2"}}),B=new b({props:{name:"class diffusers.models.attention_processor.AttnAddedKVProcessor",anchor:"diffusers.models.attention_processor.AttnAddedKVProcessor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/models/attention_processor.py#L942"}}),H=new A({props:{title:"AttnAddedKVProcessor2_0",local:"diffusers.models.attention_processor.AttnAddedKVProcessor2_0",headingTag:"h2"}}),M=new b({props:{name:"class diffusers.models.attention_processor.AttnAddedKVProcessor2_0",anchor:"diffusers.models.attention_processor.AttnAddedKVProcessor2_0",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/models/attention_processor.py#L1009"}}),G=new A({props:{title:"CrossFrameAttnProcessor",local:"diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor",headingTag:"h2"}}),J=new b({props:{name:"class diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor",anchor:"diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor",parameters:[{name:"batch_size",val:" = 2"}],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero.py#L48"}}),Q=new A({props:{title:"CustomDiffusionAttnProcessor",local:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor",headingTag:"h2"}}),Y=new b({props:{name:"class diffusers.models.attention_processor.CustomDiffusionAttnProcessor",anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor",parameters:[{name:"train_kv",val:": bool = True"},{name:"train_q_out",val:": bool = True"},{name:"hidden_size",val:": Optional = None"},{name:"cross_attention_dim",val:": Optional = None"},{name:"out_bias",val:": bool = True"},{name:"dropout",val:": float = 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/vr_7645/src/diffusers/models/attention_processor.py#L838"}}),Z=new A({props:{title:"CustomDiffusionAttnProcessor2_0",local:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0",headingTag:"h2"}}),ee=new b({props:{name:"class diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0",anchor:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0",parameters:[{name:"train_kv",val:": bool = True"},{name:"train_q_out",val:": bool = True"},{name:"hidden_size",val:": Optional = None"},{name:"cross_attention_dim",val:": Optional = None"},{name:"out_bias",val:": bool = True"},{name:"dropout",val:": float = 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/vr_7645/src/diffusers/models/attention_processor.py#L1919"}}),te=new A({props:{title:"CustomDiffusionXFormersAttnProcessor",local:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor",headingTag:"h2"}}),oe=new b({props:{name:"class diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor",anchor:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor",parameters:[{name:"train_kv",val:": bool = True"},{name:"train_q_out",val:": bool = False"},{name:"hidden_size",val:": Optional = None"},{name:"cross_attention_dim",val:": Optional = None"},{name:"out_bias",val:": bool = True"},{name:"dropout",val:": float = 0.0"},{name:"attention_op",val:": Optional = 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/vr_7645/src/diffusers/models/attention_processor.py#L1803"}}),se=new A({props:{title:"FusedAttnProcessor2_0",local:"diffusers.models.attention_processor.FusedAttnProcessor2_0",headingTag:"h2"}}),re=new b({props:{name:"class diffusers.models.attention_processor.FusedAttnProcessor2_0",anchor:"diffusers.models.attention_processor.FusedAttnProcessor2_0",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/models/attention_processor.py#L1702"}}),X=new go({props:{warning:!0,$$slots:{default:[$o]},$$scope:{ctx:Xe}}}),ne=new A({props:{title:"LoRAAttnAddedKVProcessor",local:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor",headingTag:"h2"}}),ie=new b({props:{name:"class diffusers.models.attention_processor.LoRAAttnAddedKVProcessor",anchor:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor",parameters:[{name:"hidden_size",val:": int"},{name:"cross_attention_dim",val:": Optional = None"},{name:"rank",val:": int = 4"},{name:"network_alpha",val:": Optional = 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"},{anchor:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor.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"},{anchor:"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>) &#x2014;
Additional keyword arguments to pass to the <code>LoRALinearLayer</code> layers.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/models/attention_processor.py#L2440"}}),ae=new A({props:{title:"LoRAXFormersAttnProcessor",local:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor",headingTag:"h2"}}),de=new b({props:{name:"class diffusers.models.attention_processor.LoRAXFormersAttnProcessor",anchor:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor",parameters:[{name:"hidden_size",val:": int"},{name:"cross_attention_dim",val:": int"},{name:"rank",val:": int = 4"},{name:"attention_op",val:": Optional = None"},{name:"network_alpha",val:": Optional = 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"},{anchor:"diffusers.models.attention_processor.LoRAXFormersAttnProcessor.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>) &#x2014;
Additional keyword arguments to pass to the <code>LoRALinearLayer</code> layers.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/models/attention_processor.py#L2361"}}),ce=new A({props:{title:"SlicedAttnProcessor",local:"diffusers.models.attention_processor.SlicedAttnProcessor",headingTag:"h2"}}),le=new b({props:{name:"class diffusers.models.attention_processor.SlicedAttnProcessor",anchor:"diffusers.models.attention_processor.SlicedAttnProcessor",parameters:[{name:"slice_size",val:": int"}],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/vr_7645/src/diffusers/models/attention_processor.py#L2033"}}),me=new A({props:{title:"SlicedAttnAddedKVProcessor",local:"diffusers.models.attention_processor.SlicedAttnAddedKVProcessor",headingTag:"h2"}}),fe=new b({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/vr_7645/src/diffusers/models/attention_processor.py#L2120"}}),pe=new A({props:{title:"XFormersAttnProcessor",local:"diffusers.models.attention_processor.XFormersAttnProcessor",headingTag:"h2"}}),ue=new b({props:{name:"class diffusers.models.attention_processor.XFormersAttnProcessor",anchor:"diffusers.models.attention_processor.XFormersAttnProcessor",parameters:[{name:"attention_op",val:": Optional = 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/vr_7645/src/diffusers/models/attention_processor.py#L1312"}}),_e=new A({props:{title:"AttnProcessorNPU",local:"diffusers.models.attention_processor.AttnProcessorNPU",headingTag:"h2"}}),ge=new b({props:{name:"class diffusers.models.attention_processor.AttnProcessorNPU",anchor:"diffusers.models.attention_processor.AttnProcessorNPU",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_7645/src/diffusers/models/attention_processor.py#L1406"}}),he=new ho({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/attnprocessor.md"}}),{c(){_=i("meta"),q=r(),v=i("p"),Ae=r(),d(E.$$.fragment),qe=r(),I=i("p"),I.textContent=Ht,Ee=r(),d(S.$$.fragment),Ie=r(),x=i("div"),d(O.$$.fragment),Lt=r(),be=i("p"),be.textContent=Mt,Se=r(),d(U.$$.fragment),Oe=r(),y=i("div"),d(W.$$.fragment),zt=r(),ve=i("p"),ve.textContent=Gt,Ue=r(),d(j.$$.fragment),We=r(),C=i("div"),d(B.$$.fragment),Vt=r(),Pe=i("p"),Pe.textContent=Jt,je=r(),d(H.$$.fragment),Be=r(),w=i("div"),d(M.$$.fragment),Kt=r(),xe=i("p"),xe.textContent=Qt,He=r(),d(G.$$.fragment),Me=r(),D=i("div"),d(J.$$.fragment),Nt=r(),ye=i("p"),ye.textContent=Yt,Ge=r(),d(Q.$$.fragment),Je=r(),T=i("div"),d(Y.$$.fragment),Rt=r(),Ce=i("p"),Ce.textContent=Zt,Qe=r(),d(Z.$$.fragment),Ye=r(),F=i("div"),d(ee.$$.fragment),Xt=r(),we=i("p"),we.textContent=eo,Ze=r(),d(te.$$.fragment),et=r(),k=i("div"),d(oe.$$.fragment),qt=r(),De=i("p"),De.textContent=to,tt=r(),d(se.$$.fragment),ot=r(),P=i("div"),d(re.$$.fragment),Et=r(),Te=i("p"),Te.textContent=oo,It=r(),d(X.$$.fragment),st=r(),d(ne.$$.fragment),rt=r(),L=i("div"),d(ie.$$.fragment),St=r(),Fe=i("p"),Fe.textContent=so,nt=r(),d(ae.$$.fragment),it=r(),z=i("div"),d(de.$$.fragment),Ot=r(),ke=i("p"),ke.textContent=ro,at=r(),d(ce.$$.fragment),dt=r(),V=i("div"),d(le.$$.fragment),Ut=r(),Le=i("p"),Le.textContent=no,ct=r(),d(me.$$.fragment),lt=r(),K=i("div"),d(fe.$$.fragment),Wt=r(),ze=i("p"),ze.textContent=io,mt=r(),d(pe.$$.fragment),ft=r(),N=i("div"),d(ue.$$.fragment),jt=r(),Ve=i("p"),Ve.textContent=ao,pt=r(),d(_e.$$.fragment),ut=r(),R=i("div"),d(ge.$$.fragment),Bt=r(),Ke=i("p"),Ke.textContent=co,_t=r(),d(he.$$.fragment),gt=r(),Re=i("p"),this.h()},l(e){const t=_o("svelte-u9bgzb",document.head);_=a(t,"META",{name:!0,content:!0}),t.forEach(o),q=n(e),v=a(e,"P",{}),g(v).forEach(o),Ae=n(e),c(E.$$.fragment,e),qe=n(e),I=a(e,"P",{"data-svelte-h":!0}),$(I)!=="svelte-itqz7g"&&(I.textContent=Ht),Ee=n(e),c(S.$$.fragment,e),Ie=n(e),x=a(e,"DIV",{class:!0});var $e=g(x);c(O.$$.fragment,$e),Lt=n($e),be=a($e,"P",{"data-svelte-h":!0}),$(be)!=="svelte-12lirf9"&&(be.textContent=Mt),$e.forEach(o),Se=n(e),c(U.$$.fragment,e),Oe=n(e),y=a(e,"DIV",{class:!0});var $t=g(y);c(W.$$.fragment,$t),zt=n($t),ve=a($t,"P",{"data-svelte-h":!0}),$(ve)!=="svelte-zp073y"&&(ve.textContent=Gt),$t.forEach(o),Ue=n(e),c(j.$$.fragment,e),We=n(e),C=a(e,"DIV",{class:!0});var At=g(C);c(B.$$.fragment,At),Vt=n(At),Pe=a(At,"P",{"data-svelte-h":!0}),$(Pe)!=="svelte-yqqibm"&&(Pe.textContent=Jt),At.forEach(o),je=n(e),c(H.$$.fragment,e),Be=n(e),w=a(e,"DIV",{class:!0});var bt=g(w);c(M.$$.fragment,bt),Kt=n(bt),xe=a(bt,"P",{"data-svelte-h":!0}),$(xe)!=="svelte-hw86c4"&&(xe.textContent=Qt),bt.forEach(o),He=n(e),c(G.$$.fragment,e),Me=n(e),D=a(e,"DIV",{class:!0});var vt=g(D);c(J.$$.fragment,vt),Nt=n(vt),ye=a(vt,"P",{"data-svelte-h":!0}),$(ye)!=="svelte-1j63vyq"&&(ye.textContent=Yt),vt.forEach(o),Ge=n(e),c(Q.$$.fragment,e),Je=n(e),T=a(e,"DIV",{class:!0});var Pt=g(T);c(Y.$$.fragment,Pt),Rt=n(Pt),Ce=a(Pt,"P",{"data-svelte-h":!0}),$(Ce)!=="svelte-1gjwzkd"&&(Ce.textContent=Zt),Pt.forEach(o),Qe=n(e),c(Z.$$.fragment,e),Ye=n(e),F=a(e,"DIV",{class:!0});var xt=g(F);c(ee.$$.fragment,xt),Xt=n(xt),we=a(xt,"P",{"data-svelte-h":!0}),$(we)!=="svelte-pottg0"&&(we.textContent=eo),xt.forEach(o),Ze=n(e),c(te.$$.fragment,e),et=n(e),k=a(e,"DIV",{class:!0});var yt=g(k);c(oe.$$.fragment,yt),qt=n(yt),De=a(yt,"P",{"data-svelte-h":!0}),$(De)!=="svelte-10eh8wb"&&(De.textContent=to),yt.forEach(o),tt=n(e),c(se.$$.fragment,e),ot=n(e),P=a(e,"DIV",{class:!0});var Ne=g(P);c(re.$$.fragment,Ne),Et=n(Ne),Te=a(Ne,"P",{"data-svelte-h":!0}),$(Te)!=="svelte-cpmq6s"&&(Te.textContent=oo),It=n(Ne),c(X.$$.fragment,Ne),Ne.forEach(o),st=n(e),c(ne.$$.fragment,e),rt=n(e),L=a(e,"DIV",{class:!0});var Ct=g(L);c(ie.$$.fragment,Ct),St=n(Ct),Fe=a(Ct,"P",{"data-svelte-h":!0}),$(Fe)!=="svelte-zfgvyc"&&(Fe.textContent=so),Ct.forEach(o),nt=n(e),c(ae.$$.fragment,e),it=n(e),z=a(e,"DIV",{class:!0});var wt=g(z);c(de.$$.fragment,wt),Ot=n(wt),ke=a(wt,"P",{"data-svelte-h":!0}),$(ke)!=="svelte-yqwtom"&&(ke.textContent=ro),wt.forEach(o),at=n(e),c(ce.$$.fragment,e),dt=n(e),V=a(e,"DIV",{class:!0});var Dt=g(V);c(le.$$.fragment,Dt),Ut=n(Dt),Le=a(Dt,"P",{"data-svelte-h":!0}),$(Le)!=="svelte-16xjg0o"&&(Le.textContent=no),Dt.forEach(o),ct=n(e),c(me.$$.fragment,e),lt=n(e),K=a(e,"DIV",{class:!0});var Tt=g(K);c(fe.$$.fragment,Tt),Wt=n(Tt),ze=a(Tt,"P",{"data-svelte-h":!0}),$(ze)!=="svelte-15dojbg"&&(ze.textContent=io),Tt.forEach(o),mt=n(e),c(pe.$$.fragment,e),ft=n(e),N=a(e,"DIV",{class:!0});var Ft=g(N);c(ue.$$.fragment,Ft),jt=n(Ft),Ve=a(Ft,"P",{"data-svelte-h":!0}),$(Ve)!=="svelte-10td8ls"&&(Ve.textContent=ao),Ft.forEach(o),pt=n(e),c(_e.$$.fragment,e),ut=n(e),R=a(e,"DIV",{class:!0});var kt=g(R);c(ge.$$.fragment,kt),Bt=n(kt),Ke=a(kt,"P",{"data-svelte-h":!0}),$(Ke)!=="svelte-1t62rbf"&&(Ke.textContent=co),kt.forEach(o),_t=n(e),c(he.$$.fragment,e),gt=n(e),Re=a(e,"P",{}),g(Re).forEach(o),this.h()},h(){h(_,"name","hf:doc:metadata"),h(_,"content",bo),h(x,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(y,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(C,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(w,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(D,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(F,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(P,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(L,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(V,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(K,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(N,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),h(R,"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,t){u(document.head,_),s(e,q,t),s(e,v,t),s(e,Ae,t),l(E,e,t),s(e,qe,t),s(e,I,t),s(e,Ee,t),l(S,e,t),s(e,Ie,t),s(e,x,t),l(O,x,null),u(x,Lt),u(x,be),s(e,Se,t),l(U,e,t),s(e,Oe,t),s(e,y,t),l(W,y,null),u(y,zt),u(y,ve),s(e,Ue,t),l(j,e,t),s(e,We,t),s(e,C,t),l(B,C,null),u(C,Vt),u(C,Pe),s(e,je,t),l(H,e,t),s(e,Be,t),s(e,w,t),l(M,w,null),u(w,Kt),u(w,xe),s(e,He,t),l(G,e,t),s(e,Me,t),s(e,D,t),l(J,D,null),u(D,Nt),u(D,ye),s(e,Ge,t),l(Q,e,t),s(e,Je,t),s(e,T,t),l(Y,T,null),u(T,Rt),u(T,Ce),s(e,Qe,t),l(Z,e,t),s(e,Ye,t),s(e,F,t),l(ee,F,null),u(F,Xt),u(F,we),s(e,Ze,t),l(te,e,t),s(e,et,t),s(e,k,t),l(oe,k,null),u(k,qt),u(k,De),s(e,tt,t),l(se,e,t),s(e,ot,t),s(e,P,t),l(re,P,null),u(P,Et),u(P,Te),u(P,It),l(X,P,null),s(e,st,t),l(ne,e,t),s(e,rt,t),s(e,L,t),l(ie,L,null),u(L,St),u(L,Fe),s(e,nt,t),l(ae,e,t),s(e,it,t),s(e,z,t),l(de,z,null),u(z,Ot),u(z,ke),s(e,at,t),l(ce,e,t),s(e,dt,t),s(e,V,t),l(le,V,null),u(V,Ut),u(V,Le),s(e,ct,t),l(me,e,t),s(e,lt,t),s(e,K,t),l(fe,K,null),u(K,Wt),u(K,ze),s(e,mt,t),l(pe,e,t),s(e,ft,t),s(e,N,t),l(ue,N,null),u(N,jt),u(N,Ve),s(e,pt,t),l(_e,e,t),s(e,ut,t),s(e,R,t),l(ge,R,null),u(R,Bt),u(R,Ke),s(e,_t,t),l(he,e,t),s(e,gt,t),s(e,Re,t),ht=!0},p(e,[t]){const $e={};t&2&&($e.$$scope={dirty:t,ctx:e}),X.$set($e)},i(e){ht||(m(E.$$.fragment,e),m(S.$$.fragment,e),m(O.$$.fragment,e),m(U.$$.fragment,e),m(W.$$.fragment,e),m(j.$$.fragment,e),m(B.$$.fragment,e),m(H.$$.fragment,e),m(M.$$.fragment,e),m(G.$$.fragment,e),m(J.$$.fragment,e),m(Q.$$.fragment,e),m(Y.$$.fragment,e),m(Z.$$.fragment,e),m(ee.$$.fragment,e),m(te.$$.fragment,e),m(oe.$$.fragment,e),m(se.$$.fragment,e),m(re.$$.fragment,e),m(X.$$.fragment,e),m(ne.$$.fragment,e),m(ie.$$.fragment,e),m(ae.$$.fragment,e),m(de.$$.fragment,e),m(ce.$$.fragment,e),m(le.$$.fragment,e),m(me.$$.fragment,e),m(fe.$$.fragment,e),m(pe.$$.fragment,e),m(ue.$$.fragment,e),m(_e.$$.fragment,e),m(ge.$$.fragment,e),m(he.$$.fragment,e),ht=!0)},o(e){f(E.$$.fragment,e),f(S.$$.fragment,e),f(O.$$.fragment,e),f(U.$$.fragment,e),f(W.$$.fragment,e),f(j.$$.fragment,e),f(B.$$.fragment,e),f(H.$$.fragment,e),f(M.$$.fragment,e),f(G.$$.fragment,e),f(J.$$.fragment,e),f(Q.$$.fragment,e),f(Y.$$.fragment,e),f(Z.$$.fragment,e),f(ee.$$.fragment,e),f(te.$$.fragment,e),f(oe.$$.fragment,e),f(se.$$.fragment,e),f(re.$$.fragment,e),f(X.$$.fragment,e),f(ne.$$.fragment,e),f(ie.$$.fragment,e),f(ae.$$.fragment,e),f(de.$$.fragment,e),f(ce.$$.fragment,e),f(le.$$.fragment,e),f(me.$$.fragment,e),f(fe.$$.fragment,e),f(pe.$$.fragment,e),f(ue.$$.fragment,e),f(_e.$$.fragment,e),f(ge.$$.fragment,e),f(he.$$.fragment,e),ht=!1},d(e){e&&(o(q),o(v),o(Ae),o(qe),o(I),o(Ee),o(Ie),o(x),o(Se),o(Oe),o(y),o(Ue),o(We),o(C),o(je),o(Be),o(w),o(He),o(Me),o(D),o(Ge),o(Je),o(T),o(Qe),o(Ye),o(F),o(Ze),o(et),o(k),o(tt),o(ot),o(P),o(st),o(rt),o(L),o(nt),o(it),o(z),o(at),o(dt),o(V),o(ct),o(lt),o(K),o(mt),o(ft),o(N),o(pt),o(ut),o(R),o(_t),o(gt),o(Re)),o(_),p(E,e),p(S,e),p(O),p(U,e),p(W),p(j,e),p(B),p(H,e),p(M),p(G,e),p(J),p(Q,e),p(Y),p(Z,e),p(ee),p(te,e),p(oe),p(se,e),p(re),p(X),p(ne,e),p(ie),p(ae,e),p(de),p(ce,e),p(le),p(me,e),p(fe),p(pe,e),p(ue),p(_e,e),p(ge),p(he,e)}}}const bo='{"title":"Attention Processor","local":"attention-processor","sections":[{"title":"AttnProcessor","local":"diffusers.models.attention_processor.AttnProcessor","sections":[],"depth":2},{"title":"AttnProcessor2_0","local":"diffusers.models.attention_processor.AttnProcessor2_0","sections":[],"depth":2},{"title":"AttnAddedKVProcessor","local":"diffusers.models.attention_processor.AttnAddedKVProcessor","sections":[],"depth":2},{"title":"AttnAddedKVProcessor2_0","local":"diffusers.models.attention_processor.AttnAddedKVProcessor2_0","sections":[],"depth":2},{"title":"CrossFrameAttnProcessor","local":"diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor","sections":[],"depth":2},{"title":"CustomDiffusionAttnProcessor","local":"diffusers.models.attention_processor.CustomDiffusionAttnProcessor","sections":[],"depth":2},{"title":"CustomDiffusionAttnProcessor2_0","local":"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0","sections":[],"depth":2},{"title":"CustomDiffusionXFormersAttnProcessor","local":"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor","sections":[],"depth":2},{"title":"FusedAttnProcessor2_0","local":"diffusers.models.attention_processor.FusedAttnProcessor2_0","sections":[],"depth":2},{"title":"LoRAAttnAddedKVProcessor","local":"diffusers.models.attention_processor.LoRAAttnAddedKVProcessor","sections":[],"depth":2},{"title":"LoRAXFormersAttnProcessor","local":"diffusers.models.attention_processor.LoRAXFormersAttnProcessor","sections":[],"depth":2},{"title":"SlicedAttnProcessor","local":"diffusers.models.attention_processor.SlicedAttnProcessor","sections":[],"depth":2},{"title":"SlicedAttnAddedKVProcessor","local":"diffusers.models.attention_processor.SlicedAttnAddedKVProcessor","sections":[],"depth":2},{"title":"XFormersAttnProcessor","local":"diffusers.models.attention_processor.XFormersAttnProcessor","sections":[],"depth":2},{"title":"AttnProcessorNPU","local":"diffusers.models.attention_processor.AttnProcessorNPU","sections":[],"depth":2}],"depth":1}';function vo(Xe){return mo(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Do extends po{constructor(_){super(),uo(this,_,vo,Ao,lo,{})}}export{Do as component};