diffusers/pr_10312/en/_app/immutable/nodes/29.d75106da.js

import{s as he,n as Pe,o as Ae}from"../chunks/scheduler.8c3d61f6.js";import{S as Te,i as we,g as d,s as t,r as m,A as be,h as a,f as o,c as r,j as I,u,x as X,k as U,y as c,a as n,v as p,d as _,t as g,w as h}from"../chunks/index.da70eac4.js";import{D as oe}from"../chunks/Docstring.6b390b9a.js";import{C as Me}from"../chunks/CodeBlock.00a903b3.js";import{H as ce,E as ve}from"../chunks/EditOnGithub.1e64e623.js";function Ce(fe){let f,Z,R,k,w,E,b,le='A Diffusion Transformer model for 2D data from <a href="https://github.com/THUDM/CogView3" rel="nofollow">CogView3Plus</a> was introduced in <a href="https://huggingface.co/papers/2403.05121" rel="nofollow">CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion</a> by Tsinghua University &amp; ZhipuAI.',J,M,me="The model can be loaded with the following code snippet.",N,v,j,C,W,i,D,te,L,ue=`The Transformer model introduced in <a href="https://huggingface.co/papers/2403.05121" rel="nofollow">CogView3: Finer and Faster Text-to-Image Generation via Relay
Diffusion</a>.`,re,P,y,ne,z,pe='The <a href="/docs/diffusers/pr_10312/en/api/models/cogview3plus_transformer2d#diffusers.CogView3PlusTransformer2DModel">CogView3PlusTransformer2DModel</a> forward method.',ie,A,x,de,S,_e="Sets the attention processor to use to compute attention.",K,$,O,l,V,ae,G,ge='The output of <a href="/docs/diffusers/pr_10312/en/api/models/transformer2d#diffusers.Transformer2DModel">Transformer2DModel</a>.',q,F,Y,H,B;return w=new ce({props:{title:"CogView3PlusTransformer2DModel",local:"cogview3plustransformer2dmodel",headingTag:"h1"}}),v=new Me({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMENvZ1ZpZXczUGx1c1RyYW5zZm9ybWVyMkRNb2RlbCUwQSUwQXZhZSUyMCUzRCUyMENvZ1ZpZXczUGx1c1RyYW5zZm9ybWVyMkRNb2RlbC5mcm9tX3ByZXRyYWluZWQoJTIyVEhVRE0lMkZDb2dWaWV3M1BsdXMtM2IlMjIlMkMlMjBzdWJmb2xkZXIlM0QlMjJ0cmFuc2Zvcm1lciUyMiUyQyUyMHRvcmNoX2R0eXBlJTNEdG9yY2guYmZsb2F0MTYpLnRvKCUyMmN1ZGElMjIp",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> CogView3PlusTransformer2DModel

vae = CogView3PlusTransformer2DModel.from_pretrained(<span class="hljs-string">&quot;THUDM/CogView3Plus-3b&quot;</span>, subfolder=<span class="hljs-string">&quot;transformer&quot;</span>, torch_dtype=torch.bfloat16).to(<span class="hljs-string">&quot;cuda&quot;</span>)`,wrap:!1}}),C=new ce({props:{title:"CogView3PlusTransformer2DModel",local:"diffusers.CogView3PlusTransformer2DModel",headingTag:"h2"}}),D=new oe({props:{name:"class diffusers.CogView3PlusTransformer2DModel",anchor:"diffusers.CogView3PlusTransformer2DModel",parameters:[{name:"patch_size",val:": int = 2"},{name:"in_channels",val:": int = 16"},{name:"num_layers",val:": int = 30"},{name:"attention_head_dim",val:": int = 40"},{name:"num_attention_heads",val:": int = 64"},{name:"out_channels",val:": int = 16"},{name:"text_embed_dim",val:": int = 4096"},{name:"time_embed_dim",val:": int = 512"},{name:"condition_dim",val:": int = 256"},{name:"pos_embed_max_size",val:": int = 128"},{name:"sample_size",val:": int = 128"}],parametersDescription:[{anchor:"diffusers.CogView3PlusTransformer2DModel.patch_size",description:`<strong>patch_size</strong> (<code>int</code>, defaults to <code>2</code>) &#x2014;
The size of the patches to use in the patch embedding layer.`,name:"patch_size"},{anchor:"diffusers.CogView3PlusTransformer2DModel.in_channels",description:`<strong>in_channels</strong> (<code>int</code>, defaults to <code>16</code>) &#x2014;
The number of channels in the input.`,name:"in_channels"},{anchor:"diffusers.CogView3PlusTransformer2DModel.num_layers",description:`<strong>num_layers</strong> (<code>int</code>, defaults to <code>30</code>) &#x2014;
The number of layers of Transformer blocks to use.`,name:"num_layers"},{anchor:"diffusers.CogView3PlusTransformer2DModel.attention_head_dim",description:`<strong>attention_head_dim</strong> (<code>int</code>, defaults to <code>40</code>) &#x2014;
The number of channels in each head.`,name:"attention_head_dim"},{anchor:"diffusers.CogView3PlusTransformer2DModel.num_attention_heads",description:`<strong>num_attention_heads</strong> (<code>int</code>, defaults to <code>64</code>) &#x2014;
The number of heads to use for multi-head attention.`,name:"num_attention_heads"},{anchor:"diffusers.CogView3PlusTransformer2DModel.out_channels",description:`<strong>out_channels</strong> (<code>int</code>, defaults to <code>16</code>) &#x2014;
The number of channels in the output.`,name:"out_channels"},{anchor:"diffusers.CogView3PlusTransformer2DModel.text_embed_dim",description:`<strong>text_embed_dim</strong> (<code>int</code>, defaults to <code>4096</code>) &#x2014;
Input dimension of text embeddings from the text encoder.`,name:"text_embed_dim"},{anchor:"diffusers.CogView3PlusTransformer2DModel.time_embed_dim",description:`<strong>time_embed_dim</strong> (<code>int</code>, defaults to <code>512</code>) &#x2014;
Output dimension of timestep embeddings.`,name:"time_embed_dim"},{anchor:"diffusers.CogView3PlusTransformer2DModel.condition_dim",description:`<strong>condition_dim</strong> (<code>int</code>, defaults to <code>256</code>) &#x2014;
The embedding dimension of the input SDXL-style resolution conditions (original_size, target_size,
crop_coords).`,name:"condition_dim"},{anchor:"diffusers.CogView3PlusTransformer2DModel.pos_embed_max_size",description:`<strong>pos_embed_max_size</strong> (<code>int</code>, defaults to <code>128</code>) &#x2014;
The maximum resolution of the positional embeddings, from which slices of shape <code>H x W</code> are taken and added
to input patched latents, where <code>H</code> and <code>W</code> are the latent height and width respectively. A value of 128
means that the maximum supported height and width for image generation is <code>128 * vae_scale_factor * patch_size =&gt; 128 * 8 * 2 =&gt; 2048</code>.`,name:"pos_embed_max_size"},{anchor:"diffusers.CogView3PlusTransformer2DModel.sample_size",description:`<strong>sample_size</strong> (<code>int</code>, defaults to <code>128</code>) &#x2014;
The base resolution of input latents. If height/width is not provided during generation, this value is used
to determine the resolution as <code>sample_size * vae_scale_factor =&gt; 128 * 8 =&gt; 1024</code>`,name:"sample_size"}],source:"https://github.com/huggingface/diffusers/blob/vr_10312/src/diffusers/models/transformers/transformer_cogview3plus.py#L133"}}),y=new oe({props:{name:"forward",anchor:"diffusers.CogView3PlusTransformer2DModel.forward",parameters:[{name:"hidden_states",val:": Tensor"},{name:"encoder_hidden_states",val:": Tensor"},{name:"timestep",val:": LongTensor"},{name:"original_size",val:": Tensor"},{name:"target_size",val:": Tensor"},{name:"crop_coords",val:": Tensor"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.CogView3PlusTransformer2DModel.forward.hidden_states",description:`<strong>hidden_states</strong> (<code>torch.Tensor</code>) &#x2014;
Input <code>hidden_states</code> of shape <code>(batch size, channel, height, width)</code>.`,name:"hidden_states"},{anchor:"diffusers.CogView3PlusTransformer2DModel.forward.encoder_hidden_states",description:`<strong>encoder_hidden_states</strong> (<code>torch.Tensor</code>) &#x2014;
Conditional embeddings (embeddings computed from the input conditions such as prompts) of shape
<code>(batch_size, sequence_len, text_embed_dim)</code>`,name:"encoder_hidden_states"},{anchor:"diffusers.CogView3PlusTransformer2DModel.forward.timestep",description:`<strong>timestep</strong> (<code>torch.LongTensor</code>) &#x2014;
Used to indicate denoising step.`,name:"timestep"},{anchor:"diffusers.CogView3PlusTransformer2DModel.forward.original_size",description:`<strong>original_size</strong> (<code>torch.Tensor</code>) &#x2014;
CogView3 uses SDXL-like micro-conditioning for original image size as explained in section 2.2 of
<a href="https://huggingface.co/papers/2307.01952" rel="nofollow">https://huggingface.co/papers/2307.01952</a>.`,name:"original_size"},{anchor:"diffusers.CogView3PlusTransformer2DModel.forward.target_size",description:`<strong>target_size</strong> (<code>torch.Tensor</code>) &#x2014;
CogView3 uses SDXL-like micro-conditioning for target image size as explained in section 2.2 of
<a href="https://huggingface.co/papers/2307.01952" rel="nofollow">https://huggingface.co/papers/2307.01952</a>.`,name:"target_size"},{anchor:"diffusers.CogView3PlusTransformer2DModel.forward.crop_coords",description:`<strong>crop_coords</strong> (<code>torch.Tensor</code>) &#x2014;
CogView3 uses SDXL-like micro-conditioning for crop coordinates as explained in section 2.2 of
<a href="https://huggingface.co/papers/2307.01952" rel="nofollow">https://huggingface.co/papers/2307.01952</a>.`,name:"crop_coords"},{anchor:"diffusers.CogView3PlusTransformer2DModel.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>~models.transformer_2d.Transformer2DModelOutput</code> instead of a plain
tuple.`,name:"return_dict"}],source:"https://github.com/huggingface/diffusers/blob/vr_10312/src/diffusers/models/transformers/transformer_cogview3plus.py#L294",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>The denoised latents using provided inputs as conditioning.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>torch.Tensor</code> or <code>~models.transformer_2d.Transformer2DModelOutput</code></p>
`}}),x=new oe({props:{name:"set_attn_processor",anchor:"diffusers.CogView3PlusTransformer2DModel.set_attn_processor",parameters:[{name:"processor",val:": typing.Union[diffusers.models.attention_processor.AttnProcessor, diffusers.models.attention_processor.CustomDiffusionAttnProcessor, diffusers.models.attention_processor.AttnAddedKVProcessor, diffusers.models.attention_processor.AttnAddedKVProcessor2_0, diffusers.models.attention_processor.JointAttnProcessor2_0, diffusers.models.attention_processor.PAGJointAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGJointAttnProcessor2_0, diffusers.models.attention_processor.FusedJointAttnProcessor2_0, diffusers.models.attention_processor.AllegroAttnProcessor2_0, diffusers.models.attention_processor.AuraFlowAttnProcessor2_0, diffusers.models.attention_processor.FusedAuraFlowAttnProcessor2_0, diffusers.models.attention_processor.FluxAttnProcessor2_0, diffusers.models.attention_processor.FluxAttnProcessor2_0_NPU, diffusers.models.attention_processor.FusedFluxAttnProcessor2_0, diffusers.models.attention_processor.FusedFluxAttnProcessor2_0_NPU, diffusers.models.attention_processor.CogVideoXAttnProcessor2_0, diffusers.models.attention_processor.FusedCogVideoXAttnProcessor2_0, diffusers.models.attention_processor.XFormersAttnAddedKVProcessor, diffusers.models.attention_processor.XFormersAttnProcessor, diffusers.models.attention_processor.XLAFlashAttnProcessor2_0, diffusers.models.attention_processor.AttnProcessorNPU, diffusers.models.attention_processor.AttnProcessor2_0, diffusers.models.attention_processor.MochiVaeAttnProcessor2_0, diffusers.models.attention_processor.MochiAttnProcessor2_0, diffusers.models.attention_processor.StableAudioAttnProcessor2_0, diffusers.models.attention_processor.HunyuanAttnProcessor2_0, diffusers.models.attention_processor.FusedHunyuanAttnProcessor2_0, diffusers.models.attention_processor.PAGHunyuanAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGHunyuanAttnProcessor2_0, diffusers.models.attention_processor.LuminaAttnProcessor2_0, diffusers.models.attention_processor.FusedAttnProcessor2_0, diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor, diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0, diffusers.models.attention_processor.SlicedAttnProcessor, diffusers.models.attention_processor.SlicedAttnAddedKVProcessor, diffusers.models.attention_processor.SanaLinearAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGSanaLinearAttnProcessor2_0, diffusers.models.attention_processor.PAGIdentitySanaLinearAttnProcessor2_0, diffusers.models.attention_processor.SanaMultiscaleLinearAttention, diffusers.models.attention_processor.SanaMultiscaleAttnProcessor2_0, diffusers.models.attention_processor.SanaMultiscaleAttentionProjection, diffusers.models.attention_processor.IPAdapterAttnProcessor, diffusers.models.attention_processor.IPAdapterAttnProcessor2_0, diffusers.models.attention_processor.IPAdapterXFormersAttnProcessor, diffusers.models.attention_processor.SD3IPAdapterJointAttnProcessor2_0, diffusers.models.attention_processor.PAGIdentitySelfAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGIdentitySelfAttnProcessor2_0, diffusers.models.attention_processor.LoRAAttnProcessor, diffusers.models.attention_processor.LoRAAttnProcessor2_0, diffusers.models.attention_processor.LoRAXFormersAttnProcessor, diffusers.models.attention_processor.LoRAAttnAddedKVProcessor, typing.Dict[str, typing.Union[diffusers.models.attention_processor.AttnProcessor, diffusers.models.attention_processor.CustomDiffusionAttnProcessor, diffusers.models.attention_processor.AttnAddedKVProcessor, diffusers.models.attention_processor.AttnAddedKVProcessor2_0, diffusers.models.attention_processor.JointAttnProcessor2_0, diffusers.models.attention_processor.PAGJointAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGJointAttnProcessor2_0, diffusers.models.attention_processor.FusedJointAttnProcessor2_0, diffusers.models.attention_processor.AllegroAttnProcessor2_0, diffusers.models.attention_processor.AuraFlowAttnProcessor2_0, diffusers.models.attention_processor.FusedAuraFlowAttnProcessor2_0, diffusers.models.attention_processor.FluxAttnProcessor2_0, diffusers.models.attention_processor.FluxAttnProcessor2_0_NPU, diffusers.models.attention_processor.FusedFluxAttnProcessor2_0, diffusers.models.attention_processor.FusedFluxAttnProcessor2_0_NPU, diffusers.models.attention_processor.CogVideoXAttnProcessor2_0, diffusers.models.attention_processor.FusedCogVideoXAttnProcessor2_0, diffusers.models.attention_processor.XFormersAttnAddedKVProcessor, diffusers.models.attention_processor.XFormersAttnProcessor, diffusers.models.attention_processor.XLAFlashAttnProcessor2_0, diffusers.models.attention_processor.AttnProcessorNPU, diffusers.models.attention_processor.AttnProcessor2_0, diffusers.models.attention_processor.MochiVaeAttnProcessor2_0, diffusers.models.attention_processor.MochiAttnProcessor2_0, diffusers.models.attention_processor.StableAudioAttnProcessor2_0, diffusers.models.attention_processor.HunyuanAttnProcessor2_0, diffusers.models.attention_processor.FusedHunyuanAttnProcessor2_0, diffusers.models.attention_processor.PAGHunyuanAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGHunyuanAttnProcessor2_0, diffusers.models.attention_processor.LuminaAttnProcessor2_0, diffusers.models.attention_processor.FusedAttnProcessor2_0, diffusers.models.attention_processor.CustomDiffusionXFormersAttnProcessor, diffusers.models.attention_processor.CustomDiffusionAttnProcessor2_0, diffusers.models.attention_processor.SlicedAttnProcessor, diffusers.models.attention_processor.SlicedAttnAddedKVProcessor, diffusers.models.attention_processor.SanaLinearAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGSanaLinearAttnProcessor2_0, diffusers.models.attention_processor.PAGIdentitySanaLinearAttnProcessor2_0, diffusers.models.attention_processor.SanaMultiscaleLinearAttention, diffusers.models.attention_processor.SanaMultiscaleAttnProcessor2_0, diffusers.models.attention_processor.SanaMultiscaleAttentionProjection, diffusers.models.attention_processor.IPAdapterAttnProcessor, diffusers.models.attention_processor.IPAdapterAttnProcessor2_0, diffusers.models.attention_processor.IPAdapterXFormersAttnProcessor, diffusers.models.attention_processor.SD3IPAdapterJointAttnProcessor2_0, diffusers.models.attention_processor.PAGIdentitySelfAttnProcessor2_0, diffusers.models.attention_processor.PAGCFGIdentitySelfAttnProcessor2_0, diffusers.models.attention_processor.LoRAAttnProcessor, diffusers.models.attention_processor.LoRAAttnProcessor2_0, diffusers.models.attention_processor.LoRAXFormersAttnProcessor, diffusers.models.attention_processor.LoRAAttnAddedKVProcessor]]]"}],parametersDescription:[{anchor:"diffusers.CogView3PlusTransformer2DModel.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/vr_10312/src/diffusers/models/transformers/transformer_cogview3plus.py#L256"}}),$=new ce({props:{title:"Transformer2DModelOutput",local:"diffusers.models.modeling_outputs.Transformer2DModelOutput",headingTag:"h2"}}),V=new oe({props:{name:"class diffusers.models.modeling_outputs.Transformer2DModelOutput",anchor:"diffusers.models.modeling_outputs.Transformer2DModelOutput",parameters:[{name:"sample",val:": torch.Tensor"}],parametersDescription:[{anchor:"diffusers.models.modeling_outputs.Transformer2DModelOutput.sample",description:`<strong>sample</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, num_channels, height, width)</code> or <code>(batch size, num_vector_embeds - 1, num_latent_pixels)</code> if <a href="/docs/diffusers/pr_10312/en/api/models/transformer2d#diffusers.Transformer2DModel">Transformer2DModel</a> is discrete) &#x2014;
The hidden states output conditioned on the <code>encoder_hidden_states</code> input. If discrete, returns probability
distributions for the unnoised latent pixels.`,name:"sample"}],source:"https://github.com/huggingface/diffusers/blob/vr_10312/src/diffusers/models/modeling_outputs.py#L20"}}),F=new ve({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/models/cogview3plus_transformer2d.md"}}),{c(){f=d("meta"),Z=t(),R=d("p"),k=t(),m(w.$$.fragment),E=t(),b=d("p"),b.innerHTML=le,J=t(),M=d("p"),M.textContent=me,N=t(),m(v.$$.fragment),j=t(),m(C.$$.fragment),W=t(),i=d("div"),m(D.$$.fragment),te=t(),L=d("p"),L.innerHTML=ue,re=t(),P=d("div"),m(y.$$.fragment),ne=t(),z=d("p"),z.innerHTML=pe,ie=t(),A=d("div"),m(x.$$.fragment),de=t(),S=d("p"),S.textContent=_e,K=t(),m($.$$.fragment),O=t(),l=d("div"),m(V.$$.fragment),ae=t(),G=d("p"),G.innerHTML=ge,q=t(),m(F.$$.fragment),Y=t(),H=d("p"),this.h()},l(e){const s=be("svelte-u9bgzb",document.head);f=a(s,"META",{name:!0,content:!0}),s.forEach(o),Z=r(e),R=a(e,"P",{}),I(R).forEach(o),k=r(e),u(w.$$.fragment,e),E=r(e),b=a(e,"P",{"data-svelte-h":!0}),X(b)!=="svelte-1vlmqph"&&(b.innerHTML=le),J=r(e),M=a(e,"P",{"data-svelte-h":!0}),X(M)!=="svelte-1vuni30"&&(M.textContent=me),N=r(e),u(v.$$.fragment,e),j=r(e),u(C.$$.fragment,e),W=r(e),i=a(e,"DIV",{class:!0});var T=I(i);u(D.$$.fragment,T),te=r(T),L=a(T,"P",{"data-svelte-h":!0}),X(L)!=="svelte-1y8vmfa"&&(L.innerHTML=ue),re=r(T),P=a(T,"DIV",{class:!0});var Q=I(P);u(y.$$.fragment,Q),ne=r(Q),z=a(Q,"P",{"data-svelte-h":!0}),X(z)!=="svelte-rqzsmp"&&(z.innerHTML=pe),Q.forEach(o),ie=r(T),A=a(T,"DIV",{class:!0});var ee=I(A);u(x.$$.fragment,ee),de=r(ee),S=a(ee,"P",{"data-svelte-h":!0}),X(S)!=="svelte-1o77hl2"&&(S.textContent=_e),ee.forEach(o),T.forEach(o),K=r(e),u($.$$.fragment,e),O=r(e),l=a(e,"DIV",{class:!0});var se=I(l);u(V.$$.fragment,se),ae=r(se),G=a(se,"P",{"data-svelte-h":!0}),X(G)!=="svelte-yagord"&&(G.innerHTML=ge),se.forEach(o),q=r(e),u(F.$$.fragment,e),Y=r(e),H=a(e,"P",{}),I(H).forEach(o),this.h()},h(){U(f,"name","hf:doc:metadata"),U(f,"content",De),U(P,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),U(A,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),U(i,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),U(l,"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,s){c(document.head,f),n(e,Z,s),n(e,R,s),n(e,k,s),p(w,e,s),n(e,E,s),n(e,b,s),n(e,J,s),n(e,M,s),n(e,N,s),p(v,e,s),n(e,j,s),p(C,e,s),n(e,W,s),n(e,i,s),p(D,i,null),c(i,te),c(i,L),c(i,re),c(i,P),p(y,P,null),c(P,ne),c(P,z),c(i,ie),c(i,A),p(x,A,null),c(A,de),c(A,S),n(e,K,s),p($,e,s),n(e,O,s),n(e,l,s),p(V,l,null),c(l,ae),c(l,G),n(e,q,s),p(F,e,s),n(e,Y,s),n(e,H,s),B=!0},p:Pe,i(e){B||(_(w.$$.fragment,e),_(v.$$.fragment,e),_(C.$$.fragment,e),_(D.$$.fragment,e),_(y.$$.fragment,e),_(x.$$.fragment,e),_($.$$.fragment,e),_(V.$$.fragment,e),_(F.$$.fragment,e),B=!0)},o(e){g(w.$$.fragment,e),g(v.$$.fragment,e),g(C.$$.fragment,e),g(D.$$.fragment,e),g(y.$$.fragment,e),g(x.$$.fragment,e),g($.$$.fragment,e),g(V.$$.fragment,e),g(F.$$.fragment,e),B=!1},d(e){e&&(o(Z),o(R),o(k),o(E),o(b),o(J),o(M),o(N),o(j),o(W),o(i),o(K),o(O),o(l),o(q),o(Y),o(H)),o(f),h(w,e),h(v,e),h(C,e),h(D),h(y),h(x),h($,e),h(V),h(F,e)}}}const De='{"title":"CogView3PlusTransformer2DModel","local":"cogview3plustransformer2dmodel","sections":[{"title":"CogView3PlusTransformer2DModel","local":"diffusers.CogView3PlusTransformer2DModel","sections":[],"depth":2},{"title":"Transformer2DModelOutput","local":"diffusers.models.modeling_outputs.Transformer2DModelOutput","sections":[],"depth":2}],"depth":1}';function ye(fe){return Ae(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ze extends Te{constructor(f){super(),we(this,f,ye,Ce,he,{})}}export{ze as component};