diffusers/pr_12229/en/_app/immutable/nodes/66.fa2422ce.js

import{s as Le,n as Ce,o as je}from"../chunks/scheduler.53228c21.js";import{S as Ie,i as ze,e as d,s as t,c as u,h as Ge,a,d as s,b as r,f as $,g as p,j as D,k as _,l as o,m as f,n as h,t as g,o as A,p as P}from"../chunks/index.100fac89.js";import{C as Ve}from"../chunks/CopyLLMTxtMenu.05adabe5.js";import{D as J}from"../chunks/Docstring.2192d6da.js";import{H as ke,E as He}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.6cf479e3.js";function qe(De){let b,B,R,W,x,Y,S,Z,M,Te='The Transformer model introduced in <a href="https://hf.co/papers/2403.03206" rel="nofollow">Stable Diffusion 3</a>. Its novelty lies in the MMDiT transformer block.',ee,w,oe,n,F,ae,H,ve='The Transformer model introduced in <a href="https://huggingface.co/papers/2403.03206" rel="nofollow">Stable Diffusion 3</a>.',ce,T,k,fe,q,ye=`Sets the attention processor to use <a href="https://huggingface.co/blog/reformer#2-chunked-feed-forward-layers" rel="nofollow">feed forward
chunking</a>.`,le,v,L,me,E,$e='The <a href="/docs/diffusers/pr_12229/en/api/models/sd3_transformer2d#diffusers.SD3Transformer2DModel">SD3Transformer2DModel</a> forward method.',ue,l,C,pe,N,xe=`Enables fused QKV projections. 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.`,_e,j,Se="<p>&gt; This API is 🧪 experimental.</p>",he,y,I,ge,X,Me="Sets the attention processor to use to compute attention.",Ae,m,z,Pe,K,we="Disables the fused QKV projection if enabled.",be,G,Fe="<p>&gt; This API is 🧪 experimental.</p>",se,V,te,Q,re;return x=new Ve({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),S=new ke({props:{title:"SD3 Transformer Model",local:"sd3-transformer-model",headingTag:"h1"}}),w=new ke({props:{title:"SD3Transformer2DModel",local:"diffusers.SD3Transformer2DModel",headingTag:"h2"}}),F=new J({props:{name:"class diffusers.SD3Transformer2DModel",anchor:"diffusers.SD3Transformer2DModel",parameters:[{name:"sample_size",val:": int = 128"},{name:"patch_size",val:": int = 2"},{name:"in_channels",val:": int = 16"},{name:"num_layers",val:": int = 18"},{name:"attention_head_dim",val:": int = 64"},{name:"num_attention_heads",val:": int = 18"},{name:"joint_attention_dim",val:": int = 4096"},{name:"caption_projection_dim",val:": int = 1152"},{name:"pooled_projection_dim",val:": int = 2048"},{name:"out_channels",val:": int = 16"},{name:"pos_embed_max_size",val:": int = 96"},{name:"dual_attention_layers",val:": typing.Tuple[int, ...] = ()"},{name:"qk_norm",val:": typing.Optional[str] = None"}],parametersDescription:[{anchor:"diffusers.SD3Transformer2DModel.sample_size",description:`<strong>sample_size</strong> (<code>int</code>, defaults to <code>128</code>) &#x2014;
The width/height of the latents. This is fixed during training since it is used to learn a number of
position embeddings.`,name:"sample_size"},{anchor:"diffusers.SD3Transformer2DModel.patch_size",description:`<strong>patch_size</strong> (<code>int</code>, defaults to <code>2</code>) &#x2014;
Patch size to turn the input data into small patches.`,name:"patch_size"},{anchor:"diffusers.SD3Transformer2DModel.in_channels",description:`<strong>in_channels</strong> (<code>int</code>, defaults to <code>16</code>) &#x2014;
The number of latent channels in the input.`,name:"in_channels"},{anchor:"diffusers.SD3Transformer2DModel.num_layers",description:`<strong>num_layers</strong> (<code>int</code>, defaults to <code>18</code>) &#x2014;
The number of layers of transformer blocks to use.`,name:"num_layers"},{anchor:"diffusers.SD3Transformer2DModel.attention_head_dim",description:`<strong>attention_head_dim</strong> (<code>int</code>, defaults to <code>64</code>) &#x2014;
The number of channels in each head.`,name:"attention_head_dim"},{anchor:"diffusers.SD3Transformer2DModel.num_attention_heads",description:`<strong>num_attention_heads</strong> (<code>int</code>, defaults to <code>18</code>) &#x2014;
The number of heads to use for multi-head attention.`,name:"num_attention_heads"},{anchor:"diffusers.SD3Transformer2DModel.joint_attention_dim",description:`<strong>joint_attention_dim</strong> (<code>int</code>, defaults to <code>4096</code>) &#x2014;
The embedding dimension to use for joint text-image attention.`,name:"joint_attention_dim"},{anchor:"diffusers.SD3Transformer2DModel.caption_projection_dim",description:`<strong>caption_projection_dim</strong> (<code>int</code>, defaults to <code>1152</code>) &#x2014;
The embedding dimension of caption embeddings.`,name:"caption_projection_dim"},{anchor:"diffusers.SD3Transformer2DModel.pooled_projection_dim",description:`<strong>pooled_projection_dim</strong> (<code>int</code>, defaults to <code>2048</code>) &#x2014;
The embedding dimension of pooled text projections.`,name:"pooled_projection_dim"},{anchor:"diffusers.SD3Transformer2DModel.out_channels",description:`<strong>out_channels</strong> (<code>int</code>, defaults to <code>16</code>) &#x2014;
The number of latent channels in the output.`,name:"out_channels"},{anchor:"diffusers.SD3Transformer2DModel.pos_embed_max_size",description:`<strong>pos_embed_max_size</strong> (<code>int</code>, defaults to <code>96</code>) &#x2014;
The maximum latent height/width of positional embeddings.`,name:"pos_embed_max_size"},{anchor:"diffusers.SD3Transformer2DModel.dual_attention_layers",description:`<strong>dual_attention_layers</strong> (<code>Tuple[int, ...]</code>, defaults to <code>()</code>) &#x2014;
The number of dual-stream transformer blocks to use.`,name:"dual_attention_layers"},{anchor:"diffusers.SD3Transformer2DModel.qk_norm",description:`<strong>qk_norm</strong> (<code>str</code>, <em>optional</em>, defaults to <code>None</code>) &#x2014;
The normalization to use for query and key in the attention layer. If <code>None</code>, no normalization is used.`,name:"qk_norm"}],source:"https://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/models/transformers/transformer_sd3.py#L249"}}),k=new J({props:{name:"enable_forward_chunking",anchor:"diffusers.SD3Transformer2DModel.enable_forward_chunking",parameters:[{name:"chunk_size",val:": typing.Optional[int] = None"},{name:"dim",val:": int = 0"}],parametersDescription:[{anchor:"diffusers.SD3Transformer2DModel.enable_forward_chunking.chunk_size",description:`<strong>chunk_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The chunk size of the feed-forward layers. If not specified, will run feed-forward layer individually
over each tensor of dim=<code>dim</code>.`,name:"chunk_size"},{anchor:"diffusers.SD3Transformer2DModel.enable_forward_chunking.dim",description:`<strong>dim</strong> (<code>int</code>, <em>optional</em>, defaults to <code>0</code>) &#x2014;
The dimension over which the feed-forward computation should be chunked. Choose between dim=0 (batch)
or dim=1 (sequence length).`,name:"dim"}],source:"https://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/models/transformers/transformer_sd3.py#L345"}}),L=new J({props:{name:"forward",anchor:"diffusers.SD3Transformer2DModel.forward",parameters:[{name:"hidden_states",val:": Tensor"},{name:"encoder_hidden_states",val:": Tensor = None"},{name:"pooled_projections",val:": Tensor = None"},{name:"timestep",val:": LongTensor = None"},{name:"block_controlnet_hidden_states",val:": typing.List = None"},{name:"joint_attention_kwargs",val:": typing.Optional[typing.Dict[str, typing.Any]] = None"},{name:"return_dict",val:": bool = True"},{name:"skip_layers",val:": typing.Optional[typing.List[int]] = None"}],parametersDescription:[{anchor:"diffusers.SD3Transformer2DModel.forward.hidden_states",description:`<strong>hidden_states</strong> (<code>torch.Tensor</code> of shape <code>(batch size, channel, height, width)</code>) &#x2014;
Input <code>hidden_states</code>.`,name:"hidden_states"},{anchor:"diffusers.SD3Transformer2DModel.forward.encoder_hidden_states",description:`<strong>encoder_hidden_states</strong> (<code>torch.Tensor</code> of shape <code>(batch size, sequence_len, embed_dims)</code>) &#x2014;
Conditional embeddings (embeddings computed from the input conditions such as prompts) to use.`,name:"encoder_hidden_states"},{anchor:"diffusers.SD3Transformer2DModel.forward.pooled_projections",description:`<strong>pooled_projections</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, projection_dim)</code>) &#x2014;
Embeddings projected from the embeddings of input conditions.`,name:"pooled_projections"},{anchor:"diffusers.SD3Transformer2DModel.forward.timestep",description:`<strong>timestep</strong> (<code>torch.LongTensor</code>) &#x2014;
Used to indicate denoising step.`,name:"timestep"},{anchor:"diffusers.SD3Transformer2DModel.forward.block_controlnet_hidden_states",description:`<strong>block_controlnet_hidden_states</strong> (<code>list</code> of <code>torch.Tensor</code>) &#x2014;
A list of tensors that if specified are added to the residuals of transformer blocks.`,name:"block_controlnet_hidden_states"},{anchor:"diffusers.SD3Transformer2DModel.forward.joint_attention_kwargs",description:`<strong>joint_attention_kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
A kwargs dictionary that if specified is passed along to the <code>AttentionProcessor</code> as defined under
<code>self.processor</code> in
<a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py" rel="nofollow">diffusers.models.attention_processor</a>.`,name:"joint_attention_kwargs"},{anchor:"diffusers.SD3Transformer2DModel.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"},{anchor:"diffusers.SD3Transformer2DModel.forward.skip_layers",description:`<strong>skip_layers</strong> (<code>list</code> of <code>int</code>, <em>optional</em>) &#x2014;
A list of layer indices to skip during the forward pass.`,name:"skip_layers"}],source:"https://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/models/transformers/transformer_sd3.py#L478",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>If <code>return_dict</code> is True, an <code>~models.transformer_2d.Transformer2DModelOutput</code> is returned, otherwise a
<code>tuple</code> where the first element is the sample tensor.</p>
`}}),C=new J({props:{name:"fuse_qkv_projections",anchor:"diffusers.SD3Transformer2DModel.fuse_qkv_projections",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/models/transformers/transformer_sd3.py#L447"}}),I=new J({props:{name:"set_attn_processor",anchor:"diffusers.SD3Transformer2DModel.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.SD3Transformer2DModel.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_12229/src/diffusers/models/transformers/transformer_sd3.py#L412"}}),z=new J({props:{name:"unfuse_qkv_projections",anchor:"diffusers.SD3Transformer2DModel.unfuse_qkv_projections",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12229/src/diffusers/models/transformers/transformer_sd3.py#L469"}}),V=new He({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/models/sd3_transformer2d.md"}}),{c(){b=d("meta"),B=t(),R=d("p"),W=t(),u(x.$$.fragment),Y=t(),u(S.$$.fragment),Z=t(),M=d("p"),M.innerHTML=Te,ee=t(),u(w.$$.fragment),oe=t(),n=d("div"),u(F.$$.fragment),ae=t(),H=d("p"),H.innerHTML=ve,ce=t(),T=d("div"),u(k.$$.fragment),fe=t(),q=d("p"),q.innerHTML=ye,le=t(),v=d("div"),u(L.$$.fragment),me=t(),E=d("p"),E.innerHTML=$e,ue=t(),l=d("div"),u(C.$$.fragment),pe=t(),N=d("p"),N.textContent=xe,_e=t(),j=d("blockquote"),j.innerHTML=Se,he=t(),y=d("div"),u(I.$$.fragment),ge=t(),X=d("p"),X.textContent=Me,Ae=t(),m=d("div"),u(z.$$.fragment),Pe=t(),K=d("p"),K.textContent=we,be=t(),G=d("blockquote"),G.innerHTML=Fe,se=t(),u(V.$$.fragment),te=t(),Q=d("p"),this.h()},l(e){const i=Ge("svelte-u9bgzb",document.head);b=a(i,"META",{name:!0,content:!0}),i.forEach(s),B=r(e),R=a(e,"P",{}),$(R).forEach(s),W=r(e),p(x.$$.fragment,e),Y=r(e),p(S.$$.fragment,e),Z=r(e),M=a(e,"P",{"data-svelte-h":!0}),D(M)!=="svelte-hv1bl6"&&(M.innerHTML=Te),ee=r(e),p(w.$$.fragment,e),oe=r(e),n=a(e,"DIV",{class:!0});var c=$(n);p(F.$$.fragment,c),ae=r(c),H=a(c,"P",{"data-svelte-h":!0}),D(H)!=="svelte-18dv5mn"&&(H.innerHTML=ve),ce=r(c),T=a(c,"DIV",{class:!0});var ne=$(T);p(k.$$.fragment,ne),fe=r(ne),q=a(ne,"P",{"data-svelte-h":!0}),D(q)!=="svelte-2m23sy"&&(q.innerHTML=ye),ne.forEach(s),le=r(c),v=a(c,"DIV",{class:!0});var ie=$(v);p(L.$$.fragment,ie),me=r(ie),E=a(ie,"P",{"data-svelte-h":!0}),D(E)!=="svelte-7vmisx"&&(E.innerHTML=$e),ie.forEach(s),ue=r(c),l=a(c,"DIV",{class:!0});var U=$(l);p(C.$$.fragment,U),pe=r(U),N=a(U,"P",{"data-svelte-h":!0}),D(N)!=="svelte-1254b9i"&&(N.textContent=xe),_e=r(U),j=a(U,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),D(j)!=="svelte-6y4o4y"&&(j.innerHTML=Se),U.forEach(s),he=r(c),y=a(c,"DIV",{class:!0});var de=$(y);p(I.$$.fragment,de),ge=r(de),X=a(de,"P",{"data-svelte-h":!0}),D(X)!=="svelte-1o77hl2"&&(X.textContent=Me),de.forEach(s),Ae=r(c),m=a(c,"DIV",{class:!0});var O=$(m);p(z.$$.fragment,O),Pe=r(O),K=a(O,"P",{"data-svelte-h":!0}),D(K)!=="svelte-1vhtc74"&&(K.textContent=we),be=r(O),G=a(O,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),D(G)!=="svelte-6y4o4y"&&(G.innerHTML=Fe),O.forEach(s),c.forEach(s),se=r(e),p(V.$$.fragment,e),te=r(e),Q=a(e,"P",{}),$(Q).forEach(s),this.h()},h(){_(b,"name","hf:doc:metadata"),_(b,"content",Ee),_(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_(v,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_(j,"class","warning"),_(l,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_(y,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_(G,"class","warning"),_(m,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_(n,"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,i){o(document.head,b),f(e,B,i),f(e,R,i),f(e,W,i),h(x,e,i),f(e,Y,i),h(S,e,i),f(e,Z,i),f(e,M,i),f(e,ee,i),h(w,e,i),f(e,oe,i),f(e,n,i),h(F,n,null),o(n,ae),o(n,H),o(n,ce),o(n,T),h(k,T,null),o(T,fe),o(T,q),o(n,le),o(n,v),h(L,v,null),o(v,me),o(v,E),o(n,ue),o(n,l),h(C,l,null),o(l,pe),o(l,N),o(l,_e),o(l,j),o(n,he),o(n,y),h(I,y,null),o(y,ge),o(y,X),o(n,Ae),o(n,m),h(z,m,null),o(m,Pe),o(m,K),o(m,be),o(m,G),f(e,se,i),h(V,e,i),f(e,te,i),f(e,Q,i),re=!0},p:Ce,i(e){re||(g(x.$$.fragment,e),g(S.$$.fragment,e),g(w.$$.fragment,e),g(F.$$.fragment,e),g(k.$$.fragment,e),g(L.$$.fragment,e),g(C.$$.fragment,e),g(I.$$.fragment,e),g(z.$$.fragment,e),g(V.$$.fragment,e),re=!0)},o(e){A(x.$$.fragment,e),A(S.$$.fragment,e),A(w.$$.fragment,e),A(F.$$.fragment,e),A(k.$$.fragment,e),A(L.$$.fragment,e),A(C.$$.fragment,e),A(I.$$.fragment,e),A(z.$$.fragment,e),A(V.$$.fragment,e),re=!1},d(e){e&&(s(B),s(R),s(W),s(Y),s(Z),s(M),s(ee),s(oe),s(n),s(se),s(te),s(Q)),s(b),P(x,e),P(S,e),P(w,e),P(F),P(k),P(L),P(C),P(I),P(z),P(V,e)}}}const Ee='{"title":"SD3 Transformer Model","local":"sd3-transformer-model","sections":[{"title":"SD3Transformer2DModel","local":"diffusers.SD3Transformer2DModel","sections":[],"depth":2}],"depth":1}';function Ne(De){return je(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Re extends Ie{constructor(b){super(),ze(this,b,Ne,qe,Le,{})}}export{Re as component};