diffusers/v0.28.2/en/_app/immutable/nodes/17.f0e09e83.js

import{s as at,o as lt,n as rt}from"../chunks/scheduler.182ea377.js";import{S as it,i as ct,g as i,s,r as f,A as dt,h as c,f as n,c as o,j as D,u as g,x as y,k as C,y as t,a as m,v as h,d as _,t as b,w as v}from"../chunks/index.abf12888.js";import{T as pt}from"../chunks/Tip.230e2334.js";import{D as V}from"../chunks/Docstring.b0ac41bc.js";import{C as mt}from"../chunks/CodeBlock.57fe6e13.js";import{E as ut}from"../chunks/ExampleCodeBlock.cf625607.js";import{H as ot,E as ft}from"../chunks/EditOnGithub.9b8e78e4.js";function gt(O){let d,E="Inference is only supported for 2 iterations as of now.";return{c(){d=i("p"),d.textContent=E},l(u){d=c(u,"P",{"data-svelte-h":!0}),y(d)!=="svelte-oxwnyv"&&(d.textContent=E)},m(u,$){m(u,d,$)},p:rt,d(u){u&&n(d)}}}function ht(O){let d,E="Examples:",u,$,w;return $=new mt({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionPipeline, ConsistencyDecoderVAE

<span class="hljs-meta">&gt;&gt;&gt; </span>vae = ConsistencyDecoderVAE.from_pretrained(<span class="hljs-string">&quot;openai/consistency-decoder&quot;</span>, torch_dtype=torch.float16)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = StableDiffusionPipeline.from_pretrained(
<span class="hljs-meta">... </span>    <span class="hljs-string">&quot;runwayml/stable-diffusion-v1-5&quot;</span>, vae=vae, torch_dtype=torch.float16
<span class="hljs-meta">... </span>).to(<span class="hljs-string">&quot;cuda&quot;</span>)

<span class="hljs-meta">&gt;&gt;&gt; </span>image = pipe(<span class="hljs-string">&quot;horse&quot;</span>, generator=torch.manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>image`,wrap:!1}}),{c(){d=i("p"),d.textContent=E,u=s(),f($.$$.fragment)},l(p){d=c(p,"P",{"data-svelte-h":!0}),y(d)!=="svelte-kvfsh7"&&(d.textContent=E),u=o(p),g($.$$.fragment,p)},m(p,x){m(p,d,x),m(p,u,x),h($,p,x),w=!0},p:rt,i(p){w||(_($.$$.fragment,p),w=!0)},o(p){b($.$$.fragment,p),w=!1},d(p){p&&(n(d),n(u)),v($,p)}}}function _t(O){let d,E,u,$,w,p,x,ze='Consistency decoder can be used to decode the latents from the denoising UNet in the <a href="/docs/diffusers/v0.28.2/en/api/pipelines/stable_diffusion/text2img#diffusers.StableDiffusionPipeline">StableDiffusionPipeline</a>. This decoder was introduced in the <a href="https://openai.com/dall-e-3" rel="nofollow">DALL-E 3 technical report</a>.',me,L,Ne='The original codebase can be found at <a href="https://github.com/openai/consistencydecoder" rel="nofollow">openai/consistencydecoder</a>.',ue,k,fe,R,Ge='The pipeline could not have been contributed without the help of <a href="https://github.com/madebyollin" rel="nofollow">madebyollin</a> and <a href="https://github.com/mrsteyk" rel="nofollow">mrsteyk</a> from <a href="https://github.com/openai/consistencydecoder/issues/1" rel="nofollow">this issue</a>.',ge,P,he,r,B,Ee,Q,Fe="The consistency decoder used with DALL-E 3.",Te,M,Ve,K,J,ke,A,H,Me,ee,Xe=`Disable sliced VAE decoding. If <code>enable_slicing</code> was previously enabled, this method will go back to computing
decoding in one step.`,Ae,U,S,Ue,te,qe=`Disable tiled VAE decoding. If <code>enable_tiling</code> was previously enabled, this method will go back to computing
decoding in one step.`,je,j,Y,Ze,ne,Oe=`Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.`,We,Z,z,Ie,se,Qe=`Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
processing larger images.`,Le,oe,N,Re,W,G,Pe,re,Ke="Sets the attention processor to use to compute attention.",Be,I,F,Je,ae,et="Disables custom attention processors and sets the default attention implementation.",He,T,X,Se,le,tt="Encode a batch of images using a tiled encoder.",Ye,ie,nt=`When this option is enabled, the VAE will split the input tensor into tiles to compute encoding in several
steps. This is useful to keep memory use constant regardless of image size. The end result of tiled encoding is
different from non-tiled encoding because each tile uses a different encoder. To avoid tiling artifacts, the
tiles overlap and are blended together to form a smooth output. You may still see tile-sized changes in the
output, but they should be much less noticeable.`,_e,q,be,de,ve;return w=new ot({props:{title:"Consistency Decoder",local:"consistency-decoder",headingTag:"h1"}}),k=new pt({props:{warning:!0,$$slots:{default:[gt]},$$scope:{ctx:O}}}),P=new ot({props:{title:"ConsistencyDecoderVAE",local:"diffusers.ConsistencyDecoderVAE",headingTag:"h2"}}),B=new V({props:{name:"class diffusers.ConsistencyDecoderVAE",anchor:"diffusers.ConsistencyDecoderVAE",parameters:[{name:"scaling_factor",val:": float = 0.18215"},{name:"latent_channels",val:": int = 4"},{name:"sample_size",val:": int = 32"},{name:"encoder_act_fn",val:": str = 'silu'"},{name:"encoder_block_out_channels",val:": Tuple = (128, 256, 512, 512)"},{name:"encoder_double_z",val:": bool = True"},{name:"encoder_down_block_types",val:": Tuple = ('DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D')"},{name:"encoder_in_channels",val:": int = 3"},{name:"encoder_layers_per_block",val:": int = 2"},{name:"encoder_norm_num_groups",val:": int = 32"},{name:"encoder_out_channels",val:": int = 4"},{name:"decoder_add_attention",val:": bool = False"},{name:"decoder_block_out_channels",val:": Tuple = (320, 640, 1024, 1024)"},{name:"decoder_down_block_types",val:": Tuple = ('ResnetDownsampleBlock2D', 'ResnetDownsampleBlock2D', 'ResnetDownsampleBlock2D', 'ResnetDownsampleBlock2D')"},{name:"decoder_downsample_padding",val:": int = 1"},{name:"decoder_in_channels",val:": int = 7"},{name:"decoder_layers_per_block",val:": int = 3"},{name:"decoder_norm_eps",val:": float = 1e-05"},{name:"decoder_norm_num_groups",val:": int = 32"},{name:"decoder_num_train_timesteps",val:": int = 1024"},{name:"decoder_out_channels",val:": int = 6"},{name:"decoder_resnet_time_scale_shift",val:": str = 'scale_shift'"},{name:"decoder_time_embedding_type",val:": str = 'learned'"},{name:"decoder_up_block_types",val:": Tuple = ('ResnetUpsampleBlock2D', 'ResnetUpsampleBlock2D', 'ResnetUpsampleBlock2D', 'ResnetUpsampleBlock2D')"}],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L52"}}),M=new ut({props:{anchor:"diffusers.ConsistencyDecoderVAE.example",$$slots:{default:[ht]},$$scope:{ctx:O}}}),J=new V({props:{name:"wrapper",anchor:"diffusers.ConsistencyDecoderVAE.decode",parameters:[{name:"*args",val:""},{name:"**kwargs",val:""}],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/utils/accelerate_utils.py#L43"}}),H=new V({props:{name:"disable_slicing",anchor:"diffusers.ConsistencyDecoderVAE.disable_slicing",parameters:[],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L194"}}),S=new V({props:{name:"disable_tiling",anchor:"diffusers.ConsistencyDecoderVAE.disable_tiling",parameters:[],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L178"}}),Y=new V({props:{name:"enable_slicing",anchor:"diffusers.ConsistencyDecoderVAE.enable_slicing",parameters:[],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L186"}}),z=new V({props:{name:"enable_tiling",anchor:"diffusers.ConsistencyDecoderVAE.enable_tiling",parameters:[{name:"use_tiling",val:": bool = True"}],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L169"}}),N=new V({props:{name:"forward",anchor:"diffusers.ConsistencyDecoderVAE.forward",parameters:[{name:"sample",val:": Tensor"},{name:"sample_posterior",val:": bool = False"},{name:"return_dict",val:": bool = True"},{name:"generator",val:": Optional = None"}],parametersDescription:[{anchor:"diffusers.ConsistencyDecoderVAE.forward.sample",description:"<strong>sample</strong> (<code>torch.Tensor</code>) &#x2014; Input sample.",name:"sample"},{anchor:"diffusers.ConsistencyDecoderVAE.forward.sample_posterior",description:`<strong>sample_posterior</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to sample from the posterior.`,name:"sample_posterior"},{anchor:"diffusers.ConsistencyDecoderVAE.forward.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether or not to return a <code>DecoderOutput</code> instead of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.ConsistencyDecoderVAE.forward.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
Generator to use for sampling.`,name:"generator"}],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L428",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>If return_dict is True, a <code>DecoderOutput</code> is returned, otherwise a plain <code>tuple</code> is returned.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>DecoderOutput</code> or <code>tuple</code></p>
`}}),G=new V({props:{name:"set_attn_processor",anchor:"diffusers.ConsistencyDecoderVAE.set_attn_processor",parameters:[{name:"processor",val:": Union"}],parametersDescription:[{anchor:"diffusers.ConsistencyDecoderVAE.set_attn_processor.processor",description:`<strong>processor</strong> (<code>dict</code> of <code>AttentionProcessor</code> or only <code>AttentionProcessor</code>) &#x2014;
The instantiated processor class or a dictionary of processor classes that will be set as the processor
for <strong>all</strong> <code>Attention</code> layers.</p>
<p>If <code>processor</code> is a dict, the key needs to define the path to the corresponding cross attention
processor. This is strongly recommended when setting trainable attention processors.`,name:"processor"}],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L227"}}),F=new V({props:{name:"set_default_attn_processor",anchor:"diffusers.ConsistencyDecoderVAE.set_default_attn_processor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L262"}}),X=new V({props:{name:"tiled_encode",anchor:"diffusers.ConsistencyDecoderVAE.tiled_encode",parameters:[{name:"x",val:": Tensor"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.ConsistencyDecoderVAE.tiled_encode.x",description:"<strong>x</strong> (<code>torch.Tensor</code>) &#x2014; Input batch of images.",name:"x"},{anchor:"diffusers.ConsistencyDecoderVAE.tiled_encode.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether or not to return a <code>~models.consistency_decoder_vae.ConsistencyDecoderVAEOutput</code> instead of a
plain tuple.`,name:"return_dict"}],source:"https://github.com/huggingface/diffusers/blob/v0.28.2/src/diffusers/models/autoencoders/consistency_decoder_vae.py#L373",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>If return_dict is True, a <code>~models.consistency_decoder_vae.ConsistencyDecoderVAEOutput</code> is returned,
otherwise a plain <code>tuple</code> is returned.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~models.consistency_decoder_vae.ConsistencyDecoderVAEOutput</code> or <code>tuple</code></p>
`}}),q=new ft({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/models/consistency_decoder_vae.md"}}),{c(){d=i("meta"),E=s(),u=i("p"),$=s(),f(w.$$.fragment),p=s(),x=i("p"),x.innerHTML=ze,me=s(),L=i("p"),L.innerHTML=Ne,ue=s(),f(k.$$.fragment),fe=s(),R=i("p"),R.innerHTML=Ge,ge=s(),f(P.$$.fragment),he=s(),r=i("div"),f(B.$$.fragment),Ee=s(),Q=i("p"),Q.textContent=Fe,Te=s(),f(M.$$.fragment),Ve=s(),K=i("div"),f(J.$$.fragment),ke=s(),A=i("div"),f(H.$$.fragment),Me=s(),ee=i("p"),ee.innerHTML=Xe,Ae=s(),U=i("div"),f(S.$$.fragment),Ue=s(),te=i("p"),te.innerHTML=qe,je=s(),j=i("div"),f(Y.$$.fragment),Ze=s(),ne=i("p"),ne.textContent=Oe,We=s(),Z=i("div"),f(z.$$.fragment),Ie=s(),se=i("p"),se.textContent=Qe,Le=s(),oe=i("div"),f(N.$$.fragment),Re=s(),W=i("div"),f(G.$$.fragment),Pe=s(),re=i("p"),re.textContent=Ke,Be=s(),I=i("div"),f(F.$$.fragment),Je=s(),ae=i("p"),ae.textContent=et,He=s(),T=i("div"),f(X.$$.fragment),Se=s(),le=i("p"),le.textContent=tt,Ye=s(),ie=i("p"),ie.textContent=nt,_e=s(),f(q.$$.fragment),be=s(),de=i("p"),this.h()},l(e){const a=dt("svelte-u9bgzb",document.head);d=c(a,"META",{name:!0,content:!0}),a.forEach(n),E=o(e),u=c(e,"P",{}),D(u).forEach(n),$=o(e),g(w.$$.fragment,e),p=o(e),x=c(e,"P",{"data-svelte-h":!0}),y(x)!=="svelte-1e6231i"&&(x.innerHTML=ze),me=o(e),L=c(e,"P",{"data-svelte-h":!0}),y(L)!=="svelte-uyyo7l"&&(L.innerHTML=Ne),ue=o(e),g(k.$$.fragment,e),fe=o(e),R=c(e,"P",{"data-svelte-h":!0}),y(R)!=="svelte-1ln42ze"&&(R.innerHTML=Ge),ge=o(e),g(P.$$.fragment,e),he=o(e),r=c(e,"DIV",{class:!0});var l=D(r);g(B.$$.fragment,l),Ee=o(l),Q=c(l,"P",{"data-svelte-h":!0}),y(Q)!=="svelte-1fvfwaa"&&(Q.textContent=Fe),Te=o(l),g(M.$$.fragment,l),Ve=o(l),K=c(l,"DIV",{class:!0});var pe=D(K);g(J.$$.fragment,pe),pe.forEach(n),ke=o(l),A=c(l,"DIV",{class:!0});var $e=D(A);g(H.$$.fragment,$e),Me=o($e),ee=c($e,"P",{"data-svelte-h":!0}),y(ee)!=="svelte-189cc7b"&&(ee.innerHTML=Xe),$e.forEach(n),Ae=o(l),U=c(l,"DIV",{class:!0});var ye=D(U);g(S.$$.fragment,ye),Ue=o(ye),te=c(ye,"P",{"data-svelte-h":!0}),y(te)!=="svelte-1f366pl"&&(te.innerHTML=qe),ye.forEach(n),je=o(l),j=c(l,"DIV",{class:!0});var we=D(j);g(Y.$$.fragment,we),Ze=o(we),ne=c(we,"P",{"data-svelte-h":!0}),y(ne)!=="svelte-14bnrb6"&&(ne.textContent=Oe),we.forEach(n),We=o(l),Z=c(l,"DIV",{class:!0});var De=D(Z);g(z.$$.fragment,De),Ie=o(De),se=c(De,"P",{"data-svelte-h":!0}),y(se)!=="svelte-1xwrf7t"&&(se.textContent=Qe),De.forEach(n),Le=o(l),oe=c(l,"DIV",{class:!0});var st=D(oe);g(N.$$.fragment,st),st.forEach(n),Re=o(l),W=c(l,"DIV",{class:!0});var Ce=D(W);g(G.$$.fragment,Ce),Pe=o(Ce),re=c(Ce,"P",{"data-svelte-h":!0}),y(re)!=="svelte-1o77hl2"&&(re.textContent=Ke),Ce.forEach(n),Be=o(l),I=c(l,"DIV",{class:!0});var xe=D(I);g(F.$$.fragment,xe),Je=o(xe),ae=c(xe,"P",{"data-svelte-h":!0}),y(ae)!=="svelte-1lxcwhv"&&(ae.textContent=et),xe.forEach(n),He=o(l),T=c(l,"DIV",{class:!0});var ce=D(T);g(X.$$.fragment,ce),Se=o(ce),le=c(ce,"P",{"data-svelte-h":!0}),y(le)!=="svelte-1un5fcn"&&(le.textContent=tt),Ye=o(ce),ie=c(ce,"P",{"data-svelte-h":!0}),y(ie)!=="svelte-lbfkqr"&&(ie.textContent=nt),ce.forEach(n),l.forEach(n),_e=o(e),g(q.$$.fragment,e),be=o(e),de=c(e,"P",{}),D(de).forEach(n),this.h()},h(){C(d,"name","hf:doc:metadata"),C(d,"content",bt),C(K,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(A,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(U,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(j,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(Z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(oe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(W,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(I,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(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,a){t(document.head,d),m(e,E,a),m(e,u,a),m(e,$,a),h(w,e,a),m(e,p,a),m(e,x,a),m(e,me,a),m(e,L,a),m(e,ue,a),h(k,e,a),m(e,fe,a),m(e,R,a),m(e,ge,a),h(P,e,a),m(e,he,a),m(e,r,a),h(B,r,null),t(r,Ee),t(r,Q),t(r,Te),h(M,r,null),t(r,Ve),t(r,K),h(J,K,null),t(r,ke),t(r,A),h(H,A,null),t(A,Me),t(A,ee),t(r,Ae),t(r,U),h(S,U,null),t(U,Ue),t(U,te),t(r,je),t(r,j),h(Y,j,null),t(j,Ze),t(j,ne),t(r,We),t(r,Z),h(z,Z,null),t(Z,Ie),t(Z,se),t(r,Le),t(r,oe),h(N,oe,null),t(r,Re),t(r,W),h(G,W,null),t(W,Pe),t(W,re),t(r,Be),t(r,I),h(F,I,null),t(I,Je),t(I,ae),t(r,He),t(r,T),h(X,T,null),t(T,Se),t(T,le),t(T,Ye),t(T,ie),m(e,_e,a),h(q,e,a),m(e,be,a),m(e,de,a),ve=!0},p(e,[a]){const l={};a&2&&(l.$$scope={dirty:a,ctx:e}),k.$set(l);const pe={};a&2&&(pe.$$scope={dirty:a,ctx:e}),M.$set(pe)},i(e){ve||(_(w.$$.fragment,e),_(k.$$.fragment,e),_(P.$$.fragment,e),_(B.$$.fragment,e),_(M.$$.fragment,e),_(J.$$.fragment,e),_(H.$$.fragment,e),_(S.$$.fragment,e),_(Y.$$.fragment,e),_(z.$$.fragment,e),_(N.$$.fragment,e),_(G.$$.fragment,e),_(F.$$.fragment,e),_(X.$$.fragment,e),_(q.$$.fragment,e),ve=!0)},o(e){b(w.$$.fragment,e),b(k.$$.fragment,e),b(P.$$.fragment,e),b(B.$$.fragment,e),b(M.$$.fragment,e),b(J.$$.fragment,e),b(H.$$.fragment,e),b(S.$$.fragment,e),b(Y.$$.fragment,e),b(z.$$.fragment,e),b(N.$$.fragment,e),b(G.$$.fragment,e),b(F.$$.fragment,e),b(X.$$.fragment,e),b(q.$$.fragment,e),ve=!1},d(e){e&&(n(E),n(u),n($),n(p),n(x),n(me),n(L),n(ue),n(fe),n(R),n(ge),n(he),n(r),n(_e),n(be),n(de)),n(d),v(w,e),v(k,e),v(P,e),v(B),v(M),v(J),v(H),v(S),v(Y),v(z),v(N),v(G),v(F),v(X),v(q,e)}}}const bt='{"title":"Consistency Decoder","local":"consistency-decoder","sections":[{"title":"ConsistencyDecoderVAE","local":"diffusers.ConsistencyDecoderVAE","sections":[],"depth":2}],"depth":1}';function vt(O){return lt(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Tt extends it{constructor(d){super(),ct(this,d,vt,_t,at,{})}}export{Tt as component};