diffusers/pr_10083/en/_app/immutable/nodes/4.1c52508e.js

import{s as Bt,o as Ht,n as Mt}from"../chunks/scheduler.8c3d61f6.js";import{S as Gt,i as Rt,g as i,s as r,r as d,A as Jt,h as a,f as o,c as n,j as g,u as l,x as $,k as h,y as u,a as s,v as c,d as f,t as m,w as p}from"../chunks/index.da70eac4.js";import{T as Qt}from"../chunks/Tip.1d9b8c37.js";import{D as v}from"../chunks/Docstring.6b390b9a.js";import{H as b,E as Yt}from"../chunks/EditOnGithub.1e64e623.js";function Zt(ze){let _,X="This API is currently 🧪 experimental in nature and can change in future.";return{c(){_=i("p"),_.textContent=X},l(P){_=a(P,"P",{"data-svelte-h":!0}),$(_)!=="svelte-2dfli5"&&(_.textContent=X)},m(P,pe){s(P,_,pe)},p:Mt,d(P){P&&o(_)}}}function eo(ze){let _,X,P,pe,K,Fe,I,Vt="An attention processor is a class for applying different types of attention mechanisms.",Ve,S,qe,x,L,ht,ue,qt="Default processor for performing attention-related computations.",Ne,O,ke,C,U,$t,_e,Nt="Processor for implementing scaled dot-product attention (enabled by default if you’re using PyTorch 2.0).",Ee,W,Xe,y,j,bt,ge,kt=`Processor for performing attention-related computations with extra learnable key and value matrices for the text
encoder.`,Ke,B,Ie,D,H,vt,he,Et=`Processor for performing scaled dot-product attention (enabled by default if you’re using PyTorch 2.0), with extra
learnable key and value matrices for the text encoder.`,Se,M,Le,T,G,Pt,$e,Xt="Cross frame attention processor. Each frame attends the first frame.",Oe,R,Ue,w,J,At,be,Kt="Processor for implementing attention for the Custom Diffusion method.",We,Q,je,z,Y,xt,ve,It=`Processor for implementing attention for the Custom Diffusion method using PyTorch 2.0’s memory-efficient scaled
dot-product attention.`,Be,Z,He,F,ee,Ct,Pe,St="Processor for implementing memory efficient attention using xFormers for the Custom Diffusion method.",Me,te,Ge,A,oe,yt,Ae,Lt=`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.`,Dt,E,Re,se,Je,V,re,Tt,xe,Ot="Processor for implementing sliced attention.",Qe,ne,Ye,q,ie,wt,Ce,Ut="Processor for implementing sliced attention with extra learnable key and value matrices for the text encoder.",Ze,ae,et,N,de,zt,ye,Wt="Processor for implementing memory efficient attention using xFormers.",tt,le,ot,k,ce,Ft,De,jt=`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.`,st,fe,rt,we,nt;return K=new b({props:{title:"Attention Processor",local:"attention-processor",headingTag:"h1"}}),S=new b({props:{title:"AttnProcessor",local:"diffusers.models.attention_processor.AttnProcessor",headingTag:"h2"}}),L=new v({props:{name:"class diffusers.models.attention_processor.AttnProcessor",anchor:"diffusers.models.attention_processor.AttnProcessor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/models/attention_processor.py#L755"}}),O=new b({props:{title:"AttnProcessor2_0",local:"diffusers.models.attention_processor.AttnProcessor2_0",headingTag:"h2"}}),U=new v({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_10083/src/diffusers/models/attention_processor.py#L2660"}}),W=new b({props:{title:"AttnAddedKVProcessor",local:"diffusers.models.attention_processor.AttnAddedKVProcessor",headingTag:"h2"}}),j=new v({props:{name:"class diffusers.models.attention_processor.AttnAddedKVProcessor",anchor:"diffusers.models.attention_processor.AttnAddedKVProcessor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/models/attention_processor.py#L931"}}),B=new b({props:{title:"AttnAddedKVProcessor2_0",local:"diffusers.models.attention_processor.AttnAddedKVProcessor2_0",headingTag:"h2"}}),H=new v({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_10083/src/diffusers/models/attention_processor.py#L998"}}),M=new b({props:{title:"CrossFrameAttnProcessor",local:"diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor",headingTag:"h2"}}),G=new v({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"}],parametersDescription:[{anchor:"diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor.batch_size",description:`<strong>batch_size</strong> &#x2014; The number that represents actual batch size, other than the frames.
For example, calling unet with a single prompt and num_images_per_prompt=1, batch_size should be equal to
2, due to classifier-free guidance.`,name:"batch_size"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_zero.py#L48"}}),R=new b({props:{title:"CustomDiffusionAttnProcessor",local:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor",headingTag:"h2"}}),J=new v({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:": typing.Optional[int] = None"},{name:"cross_attention_dim",val:": typing.Optional[int] = 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_10083/src/diffusers/models/attention_processor.py#L827"}}),Q=new b({props:{title:"CustomDiffusionAttnProcessor2_0",local:"diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0",headingTag:"h2"}}),Y=new v({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:": typing.Optional[int] = None"},{name:"cross_attention_dim",val:": typing.Optional[int] = 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_10083/src/diffusers/models/attention_processor.py#L3824"}}),Z=new b({props:{title:"CustomDiffusionXFormersAttnProcessor",local:"diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor",headingTag:"h2"}}),ee=new v({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:": typing.Optional[int] = None"},{name:"cross_attention_dim",val:": typing.Optional[int] = None"},{name:"out_bias",val:": bool = True"},{name:"dropout",val:": float = 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/vr_10083/src/diffusers/models/attention_processor.py#L3708"}}),te=new b({props:{title:"FusedAttnProcessor2_0",local:"diffusers.models.attention_processor.FusedAttnProcessor2_0",headingTag:"h2"}}),oe=new v({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_10083/src/diffusers/models/attention_processor.py#L3602"}}),E=new Qt({props:{warning:!0,$$slots:{default:[Zt]},$$scope:{ctx:ze}}}),se=new b({props:{title:"SlicedAttnProcessor",local:"diffusers.models.attention_processor.SlicedAttnProcessor",headingTag:"h2"}}),re=new v({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_10083/src/diffusers/models/attention_processor.py#L3938"}}),ne=new b({props:{title:"SlicedAttnAddedKVProcessor",local:"diffusers.models.attention_processor.SlicedAttnAddedKVProcessor",headingTag:"h2"}}),ie=new v({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_10083/src/diffusers/models/attention_processor.py#L4025"}}),ae=new b({props:{title:"XFormersAttnProcessor",local:"diffusers.models.attention_processor.XFormersAttnProcessor",headingTag:"h2"}}),de=new v({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/vr_10083/src/diffusers/models/attention_processor.py#L2457"}}),le=new b({props:{title:"AttnProcessorNPU",local:"diffusers.models.attention_processor.AttnProcessorNPU",headingTag:"h2"}}),ce=new v({props:{name:"class diffusers.models.attention_processor.AttnProcessorNPU",anchor:"diffusers.models.attention_processor.AttnProcessorNPU",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/models/attention_processor.py#L2551"}}),fe=new Yt({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/attnprocessor.md"}}),{c(){_=i("meta"),X=r(),P=i("p"),pe=r(),d(K.$$.fragment),Fe=r(),I=i("p"),I.textContent=Vt,Ve=r(),d(S.$$.fragment),qe=r(),x=i("div"),d(L.$$.fragment),ht=r(),ue=i("p"),ue.textContent=qt,Ne=r(),d(O.$$.fragment),ke=r(),C=i("div"),d(U.$$.fragment),$t=r(),_e=i("p"),_e.textContent=Nt,Ee=r(),d(W.$$.fragment),Xe=r(),y=i("div"),d(j.$$.fragment),bt=r(),ge=i("p"),ge.textContent=kt,Ke=r(),d(B.$$.fragment),Ie=r(),D=i("div"),d(H.$$.fragment),vt=r(),he=i("p"),he.textContent=Et,Se=r(),d(M.$$.fragment),Le=r(),T=i("div"),d(G.$$.fragment),Pt=r(),$e=i("p"),$e.textContent=Xt,Oe=r(),d(R.$$.fragment),Ue=r(),w=i("div"),d(J.$$.fragment),At=r(),be=i("p"),be.textContent=Kt,We=r(),d(Q.$$.fragment),je=r(),z=i("div"),d(Y.$$.fragment),xt=r(),ve=i("p"),ve.textContent=It,Be=r(),d(Z.$$.fragment),He=r(),F=i("div"),d(ee.$$.fragment),Ct=r(),Pe=i("p"),Pe.textContent=St,Me=r(),d(te.$$.fragment),Ge=r(),A=i("div"),d(oe.$$.fragment),yt=r(),Ae=i("p"),Ae.textContent=Lt,Dt=r(),d(E.$$.fragment),Re=r(),d(se.$$.fragment),Je=r(),V=i("div"),d(re.$$.fragment),Tt=r(),xe=i("p"),xe.textContent=Ot,Qe=r(),d(ne.$$.fragment),Ye=r(),q=i("div"),d(ie.$$.fragment),wt=r(),Ce=i("p"),Ce.textContent=Ut,Ze=r(),d(ae.$$.fragment),et=r(),N=i("div"),d(de.$$.fragment),zt=r(),ye=i("p"),ye.textContent=Wt,tt=r(),d(le.$$.fragment),ot=r(),k=i("div"),d(ce.$$.fragment),Ft=r(),De=i("p"),De.textContent=jt,st=r(),d(fe.$$.fragment),rt=r(),we=i("p"),this.h()},l(e){const t=Jt("svelte-u9bgzb",document.head);_=a(t,"META",{name:!0,content:!0}),t.forEach(o),X=n(e),P=a(e,"P",{}),g(P).forEach(o),pe=n(e),l(K.$$.fragment,e),Fe=n(e),I=a(e,"P",{"data-svelte-h":!0}),$(I)!=="svelte-itqz7g"&&(I.textContent=Vt),Ve=n(e),l(S.$$.fragment,e),qe=n(e),x=a(e,"DIV",{class:!0});var me=g(x);l(L.$$.fragment,me),ht=n(me),ue=a(me,"P",{"data-svelte-h":!0}),$(ue)!=="svelte-12lirf9"&&(ue.textContent=qt),me.forEach(o),Ne=n(e),l(O.$$.fragment,e),ke=n(e),C=a(e,"DIV",{class:!0});var it=g(C);l(U.$$.fragment,it),$t=n(it),_e=a(it,"P",{"data-svelte-h":!0}),$(_e)!=="svelte-zp073y"&&(_e.textContent=Nt),it.forEach(o),Ee=n(e),l(W.$$.fragment,e),Xe=n(e),y=a(e,"DIV",{class:!0});var at=g(y);l(j.$$.fragment,at),bt=n(at),ge=a(at,"P",{"data-svelte-h":!0}),$(ge)!=="svelte-yqqibm"&&(ge.textContent=kt),at.forEach(o),Ke=n(e),l(B.$$.fragment,e),Ie=n(e),D=a(e,"DIV",{class:!0});var dt=g(D);l(H.$$.fragment,dt),vt=n(dt),he=a(dt,"P",{"data-svelte-h":!0}),$(he)!=="svelte-hw86c4"&&(he.textContent=Et),dt.forEach(o),Se=n(e),l(M.$$.fragment,e),Le=n(e),T=a(e,"DIV",{class:!0});var lt=g(T);l(G.$$.fragment,lt),Pt=n(lt),$e=a(lt,"P",{"data-svelte-h":!0}),$($e)!=="svelte-1j63vyq"&&($e.textContent=Xt),lt.forEach(o),Oe=n(e),l(R.$$.fragment,e),Ue=n(e),w=a(e,"DIV",{class:!0});var ct=g(w);l(J.$$.fragment,ct),At=n(ct),be=a(ct,"P",{"data-svelte-h":!0}),$(be)!=="svelte-1gjwzkd"&&(be.textContent=Kt),ct.forEach(o),We=n(e),l(Q.$$.fragment,e),je=n(e),z=a(e,"DIV",{class:!0});var ft=g(z);l(Y.$$.fragment,ft),xt=n(ft),ve=a(ft,"P",{"data-svelte-h":!0}),$(ve)!=="svelte-pottg0"&&(ve.textContent=It),ft.forEach(o),Be=n(e),l(Z.$$.fragment,e),He=n(e),F=a(e,"DIV",{class:!0});var mt=g(F);l(ee.$$.fragment,mt),Ct=n(mt),Pe=a(mt,"P",{"data-svelte-h":!0}),$(Pe)!=="svelte-10eh8wb"&&(Pe.textContent=St),mt.forEach(o),Me=n(e),l(te.$$.fragment,e),Ge=n(e),A=a(e,"DIV",{class:!0});var Te=g(A);l(oe.$$.fragment,Te),yt=n(Te),Ae=a(Te,"P",{"data-svelte-h":!0}),$(Ae)!=="svelte-cpmq6s"&&(Ae.textContent=Lt),Dt=n(Te),l(E.$$.fragment,Te),Te.forEach(o),Re=n(e),l(se.$$.fragment,e),Je=n(e),V=a(e,"DIV",{class:!0});var pt=g(V);l(re.$$.fragment,pt),Tt=n(pt),xe=a(pt,"P",{"data-svelte-h":!0}),$(xe)!=="svelte-16xjg0o"&&(xe.textContent=Ot),pt.forEach(o),Qe=n(e),l(ne.$$.fragment,e),Ye=n(e),q=a(e,"DIV",{class:!0});var ut=g(q);l(ie.$$.fragment,ut),wt=n(ut),Ce=a(ut,"P",{"data-svelte-h":!0}),$(Ce)!=="svelte-15dojbg"&&(Ce.textContent=Ut),ut.forEach(o),Ze=n(e),l(ae.$$.fragment,e),et=n(e),N=a(e,"DIV",{class:!0});var _t=g(N);l(de.$$.fragment,_t),zt=n(_t),ye=a(_t,"P",{"data-svelte-h":!0}),$(ye)!=="svelte-10td8ls"&&(ye.textContent=Wt),_t.forEach(o),tt=n(e),l(le.$$.fragment,e),ot=n(e),k=a(e,"DIV",{class:!0});var gt=g(k);l(ce.$$.fragment,gt),Ft=n(gt),De=a(gt,"P",{"data-svelte-h":!0}),$(De)!=="svelte-1t62rbf"&&(De.textContent=jt),gt.forEach(o),st=n(e),l(fe.$$.fragment,e),rt=n(e),we=a(e,"P",{}),g(we).forEach(o),this.h()},h(){h(_,"name","hf:doc:metadata"),h(_,"content",to),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(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(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(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(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(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(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(A,"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(q,"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(k,"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,X,t),s(e,P,t),s(e,pe,t),c(K,e,t),s(e,Fe,t),s(e,I,t),s(e,Ve,t),c(S,e,t),s(e,qe,t),s(e,x,t),c(L,x,null),u(x,ht),u(x,ue),s(e,Ne,t),c(O,e,t),s(e,ke,t),s(e,C,t),c(U,C,null),u(C,$t),u(C,_e),s(e,Ee,t),c(W,e,t),s(e,Xe,t),s(e,y,t),c(j,y,null),u(y,bt),u(y,ge),s(e,Ke,t),c(B,e,t),s(e,Ie,t),s(e,D,t),c(H,D,null),u(D,vt),u(D,he),s(e,Se,t),c(M,e,t),s(e,Le,t),s(e,T,t),c(G,T,null),u(T,Pt),u(T,$e),s(e,Oe,t),c(R,e,t),s(e,Ue,t),s(e,w,t),c(J,w,null),u(w,At),u(w,be),s(e,We,t),c(Q,e,t),s(e,je,t),s(e,z,t),c(Y,z,null),u(z,xt),u(z,ve),s(e,Be,t),c(Z,e,t),s(e,He,t),s(e,F,t),c(ee,F,null),u(F,Ct),u(F,Pe),s(e,Me,t),c(te,e,t),s(e,Ge,t),s(e,A,t),c(oe,A,null),u(A,yt),u(A,Ae),u(A,Dt),c(E,A,null),s(e,Re,t),c(se,e,t),s(e,Je,t),s(e,V,t),c(re,V,null),u(V,Tt),u(V,xe),s(e,Qe,t),c(ne,e,t),s(e,Ye,t),s(e,q,t),c(ie,q,null),u(q,wt),u(q,Ce),s(e,Ze,t),c(ae,e,t),s(e,et,t),s(e,N,t),c(de,N,null),u(N,zt),u(N,ye),s(e,tt,t),c(le,e,t),s(e,ot,t),s(e,k,t),c(ce,k,null),u(k,Ft),u(k,De),s(e,st,t),c(fe,e,t),s(e,rt,t),s(e,we,t),nt=!0},p(e,[t]){const me={};t&2&&(me.$$scope={dirty:t,ctx:e}),E.$set(me)},i(e){nt||(f(K.$$.fragment,e),f(S.$$.fragment,e),f(L.$$.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(R.$$.fragment,e),f(J.$$.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(E.$$.fragment,e),f(se.$$.fragment,e),f(re.$$.fragment,e),f(ne.$$.fragment,e),f(ie.$$.fragment,e),f(ae.$$.fragment,e),f(de.$$.fragment,e),f(le.$$.fragment,e),f(ce.$$.fragment,e),f(fe.$$.fragment,e),nt=!0)},o(e){m(K.$$.fragment,e),m(S.$$.fragment,e),m(L.$$.fragment,e),m(O.$$.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.$$.fragment,e),m(R.$$.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.$$.fragment,e),m(E.$$.fragment,e),m(se.$$.fragment,e),m(re.$$.fragment,e),m(ne.$$.fragment,e),m(ie.$$.fragment,e),m(ae.$$.fragment,e),m(de.$$.fragment,e),m(le.$$.fragment,e),m(ce.$$.fragment,e),m(fe.$$.fragment,e),nt=!1},d(e){e&&(o(X),o(P),o(pe),o(Fe),o(I),o(Ve),o(qe),o(x),o(Ne),o(ke),o(C),o(Ee),o(Xe),o(y),o(Ke),o(Ie),o(D),o(Se),o(Le),o(T),o(Oe),o(Ue),o(w),o(We),o(je),o(z),o(Be),o(He),o(F),o(Me),o(Ge),o(A),o(Re),o(Je),o(V),o(Qe),o(Ye),o(q),o(Ze),o(et),o(N),o(tt),o(ot),o(k),o(st),o(rt),o(we)),o(_),p(K,e),p(S,e),p(L),p(O,e),p(U),p(W,e),p(j),p(B,e),p(H),p(M,e),p(G),p(R,e),p(J),p(Q,e),p(Y),p(Z,e),p(ee),p(te,e),p(oe),p(E),p(se,e),p(re),p(ne,e),p(ie),p(ae,e),p(de),p(le,e),p(ce),p(fe,e)}}}const to='{"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":"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 oo(ze){return Ht(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class lo extends Gt{constructor(_){super(),Rt(this,_,oo,eo,Bt,{})}}export{lo as component};