diffusers/pr_12595/en/_app/immutable/nodes/55.60be89dd.js

import{s as Ne,n as Xe,o as Ke}from"../chunks/scheduler.53228c21.js";import{S as Ue,i as Je,e as i,s as o,c as f,h as Re,a,d as r,b as s,f as D,g as u,j as m,k as _,l as t,m as l,n as p,t as h,o as g,p as A}from"../chunks/index.100fac89.js";import{C as Oe}from"../chunks/CopyLLMTxtMenu.7aefc1a4.js";import{D as q}from"../chunks/Docstring.d6cb35e8.js";import{H as qe,E as Be}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.3722da43.js";function Qe(we){let b,ee,Y,te,M,oe,H,se,w,Ce='A Diffusion Transformer model for 2D data from <a href="https://github.com/Tencent/HunyuanDiT" rel="nofollow">Hunyuan-DiT</a>.',ne,C,re,n,F,me,N,Fe="HunYuanDiT: Diffusion model with a Transformer backbone.",_e,X,ke="Inherit ModelMixin and ConfigMixin to be compatible with the sampler StableDiffusionPipeline of diffusers.",pe,T,k,he,K,Le=`Sets the attention processor to use <a href="https://huggingface.co/blog/reformer#2-chunked-feed-forward-layers" rel="nofollow">feed forward
chunking</a>.`,ge,v,L,Ae,U,ze='The <a href="/docs/diffusers/pr_12595/en/api/models/hunyuan_transformer2d#diffusers.HunyuanDiT2DModel">HunyuanDiT2DModel</a> forward method.',ye,y,z,Pe,J,Se=`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.`,be,S,Ie="<p>&gt; This API is 🧪 experimental.</p>",De,x,I,Te,R,Ge="Sets the attention processor to use to compute attention.",ve,$,G,xe,O,Ve="Disables custom attention processors and sets the default attention implementation.",$e,P,V,Me,B,je="Disables the fused QKV projection if enabled.",He,j,Ee="<p>&gt; This API is 🧪 experimental.</p>",ie,E,ae,Z,de;return M=new Oe({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),H=new qe({props:{title:"HunyuanDiT2DModel",local:"hunyuandit2dmodel",headingTag:"h1"}}),C=new qe({props:{title:"HunyuanDiT2DModel",local:"diffusers.HunyuanDiT2DModel",headingTag:"h2"}}),F=new q({props:{name:"class diffusers.HunyuanDiT2DModel",anchor:"diffusers.HunyuanDiT2DModel",parameters:[{name:"num_attention_heads",val:": int = 16"},{name:"attention_head_dim",val:": int = 88"},{name:"in_channels",val:": typing.Optional[int] = None"},{name:"patch_size",val:": typing.Optional[int] = None"},{name:"activation_fn",val:": str = 'gelu-approximate'"},{name:"sample_size",val:" = 32"},{name:"hidden_size",val:" = 1152"},{name:"num_layers",val:": int = 28"},{name:"mlp_ratio",val:": float = 4.0"},{name:"learn_sigma",val:": bool = True"},{name:"cross_attention_dim",val:": int = 1024"},{name:"norm_type",val:": str = 'layer_norm'"},{name:"cross_attention_dim_t5",val:": int = 2048"},{name:"pooled_projection_dim",val:": int = 1024"},{name:"text_len",val:": int = 77"},{name:"text_len_t5",val:": int = 256"},{name:"use_style_cond_and_image_meta_size",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.HunyuanDiT2DModel.num_attention_heads",description:`<strong>num_attention_heads</strong> (<code>int</code>, <em>optional</em>, defaults to 16) &#x2014;
The number of heads to use for multi-head attention.`,name:"num_attention_heads"},{anchor:"diffusers.HunyuanDiT2DModel.attention_head_dim",description:`<strong>attention_head_dim</strong> (<code>int</code>, <em>optional</em>, defaults to 88) &#x2014;
The number of channels in each head.`,name:"attention_head_dim"},{anchor:"diffusers.HunyuanDiT2DModel.in_channels",description:`<strong>in_channels</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The number of channels in the input and output (specify if the input is <strong>continuous</strong>).`,name:"in_channels"},{anchor:"diffusers.HunyuanDiT2DModel.patch_size",description:`<strong>patch_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The size of the patch to use for the input.`,name:"patch_size"},{anchor:"diffusers.HunyuanDiT2DModel.activation_fn",description:`<strong>activation_fn</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;geglu&quot;</code>) &#x2014;
Activation function to use in feed-forward.`,name:"activation_fn"},{anchor:"diffusers.HunyuanDiT2DModel.sample_size",description:`<strong>sample_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The width of the latent images. This is fixed during training since it is used to learn a number of
position embeddings.`,name:"sample_size"},{anchor:"diffusers.HunyuanDiT2DModel.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.HunyuanDiT2DModel.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The number of dimension in the clip text embedding.`,name:"cross_attention_dim"},{anchor:"diffusers.HunyuanDiT2DModel.hidden_size",description:`<strong>hidden_size</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The size of hidden layer in the conditioning embedding layers.`,name:"hidden_size"},{anchor:"diffusers.HunyuanDiT2DModel.num_layers",description:`<strong>num_layers</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
The number of layers of Transformer blocks to use.`,name:"num_layers"},{anchor:"diffusers.HunyuanDiT2DModel.mlp_ratio",description:`<strong>mlp_ratio</strong> (<code>float</code>, <em>optional</em>, defaults to 4.0) &#x2014;
The ratio of the hidden layer size to the input size.`,name:"mlp_ratio"},{anchor:"diffusers.HunyuanDiT2DModel.learn_sigma",description:`<strong>learn_sigma</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to predict variance.`,name:"learn_sigma"},{anchor:"diffusers.HunyuanDiT2DModel.cross_attention_dim_t5",description:`<strong>cross_attention_dim_t5</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The number dimensions in t5 text embedding.`,name:"cross_attention_dim_t5"},{anchor:"diffusers.HunyuanDiT2DModel.pooled_projection_dim",description:`<strong>pooled_projection_dim</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The size of the pooled projection.`,name:"pooled_projection_dim"},{anchor:"diffusers.HunyuanDiT2DModel.text_len",description:`<strong>text_len</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The length of the clip text embedding.`,name:"text_len"},{anchor:"diffusers.HunyuanDiT2DModel.text_len_t5",description:`<strong>text_len_t5</strong> (<code>int</code>, <em>optional</em>) &#x2014;
The length of the T5 text embedding.`,name:"text_len_t5"},{anchor:"diffusers.HunyuanDiT2DModel.use_style_cond_and_image_meta_size",description:`<strong>use_style_cond_and_image_meta_size</strong> (<code>bool</code>,  <em>optional</em>) &#x2014;
Whether or not to use style condition and image meta size. True for version &lt;=1.1, False for version &gt;= 1.2`,name:"use_style_cond_and_image_meta_size"}],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/hunyuan_transformer_2d.py#L203"}}),k=new q({props:{name:"enable_forward_chunking",anchor:"diffusers.HunyuanDiT2DModel.enable_forward_chunking",parameters:[{name:"chunk_size",val:": typing.Optional[int] = None"},{name:"dim",val:": int = 0"}],parametersDescription:[{anchor:"diffusers.HunyuanDiT2DModel.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.HunyuanDiT2DModel.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_12595/src/diffusers/models/transformers/hunyuan_transformer_2d.py#L532"}}),L=new q({props:{name:"forward",anchor:"diffusers.HunyuanDiT2DModel.forward",parameters:[{name:"hidden_states",val:""},{name:"timestep",val:""},{name:"encoder_hidden_states",val:" = None"},{name:"text_embedding_mask",val:" = None"},{name:"encoder_hidden_states_t5",val:" = None"},{name:"text_embedding_mask_t5",val:" = None"},{name:"image_meta_size",val:" = None"},{name:"style",val:" = None"},{name:"image_rotary_emb",val:" = None"},{name:"controlnet_block_samples",val:" = None"},{name:"return_dict",val:" = True"}],parametersDescription:[{anchor:"diffusers.HunyuanDiT2DModel.forward.hidden_states",description:`<strong>hidden_states</strong> (<code>torch.Tensor</code> of shape <code>(batch size, dim, height, width)</code>) &#x2014;
The input tensor.`,name:"hidden_states"},{anchor:"diffusers.HunyuanDiT2DModel.forward.timestep",description:`<strong>timestep</strong> ( <code>torch.LongTensor</code>, <em>optional</em>) &#x2014;
Used to indicate denoising step.`,name:"timestep"},{anchor:"diffusers.HunyuanDiT2DModel.forward.encoder_hidden_states",description:`<strong>encoder_hidden_states</strong> ( <code>torch.Tensor</code> of shape <code>(batch size, sequence len, embed dims)</code>, <em>optional</em>) &#x2014;
Conditional embeddings for cross attention layer. This is the output of <code>BertModel</code>.`,name:"encoder_hidden_states"},{anchor:"diffusers.HunyuanDiT2DModel.forward.text_embedding_mask",description:`<strong>text_embedding_mask</strong> &#x2014; torch.Tensor
An attention mask of shape <code>(batch, key_tokens)</code> is applied to <code>encoder_hidden_states</code>. This is the output
of <code>BertModel</code>.`,name:"text_embedding_mask"},{anchor:"diffusers.HunyuanDiT2DModel.forward.encoder_hidden_states_t5",description:`<strong>encoder_hidden_states_t5</strong> ( <code>torch.Tensor</code> of shape <code>(batch size, sequence len, embed dims)</code>, <em>optional</em>) &#x2014;
Conditional embeddings for cross attention layer. This is the output of T5 Text Encoder.`,name:"encoder_hidden_states_t5"},{anchor:"diffusers.HunyuanDiT2DModel.forward.text_embedding_mask_t5",description:`<strong>text_embedding_mask_t5</strong> &#x2014; torch.Tensor
An attention mask of shape <code>(batch, key_tokens)</code> is applied to <code>encoder_hidden_states</code>. This is the output
of T5 Text Encoder.`,name:"text_embedding_mask_t5"},{anchor:"diffusers.HunyuanDiT2DModel.forward.image_meta_size",description:`<strong>image_meta_size</strong> (torch.Tensor) &#x2014;
Conditional embedding indicate the image sizes`,name:"image_meta_size"},{anchor:"diffusers.HunyuanDiT2DModel.forward.style",description:`<strong>style</strong> &#x2014; torch.Tensor:
Conditional embedding indicate the style`,name:"style"},{anchor:"diffusers.HunyuanDiT2DModel.forward.image_rotary_emb",description:`<strong>image_rotary_emb</strong> (<code>torch.Tensor</code>) &#x2014;
The image rotary embeddings to apply on query and key tensors during attention calculation.`,name:"image_rotary_emb"},{anchor:"diffusers.HunyuanDiT2DModel.forward.return_dict",description:`<strong>return_dict</strong> &#x2014; bool
Whether to return a dictionary.`,name:"return_dict"}],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/hunyuan_transformer_2d.py#L419"}}),z=new q({props:{name:"fuse_qkv_projections",anchor:"diffusers.HunyuanDiT2DModel.fuse_qkv_projections",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/hunyuan_transformer_2d.py#L322"}}),I=new q({props:{name:"set_attn_processor",anchor:"diffusers.HunyuanDiT2DModel.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.HunyuanDiT2DModel.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_12595/src/diffusers/models/transformers/hunyuan_transformer_2d.py#L379"}}),G=new q({props:{name:"set_default_attn_processor",anchor:"diffusers.HunyuanDiT2DModel.set_default_attn_processor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/hunyuan_transformer_2d.py#L413"}}),V=new q({props:{name:"unfuse_qkv_projections",anchor:"diffusers.HunyuanDiT2DModel.unfuse_qkv_projections",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/hunyuan_transformer_2d.py#L344"}}),E=new Be({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/models/hunyuan_transformer2d.md"}}),{c(){b=i("meta"),ee=o(),Y=i("p"),te=o(),f(M.$$.fragment),oe=o(),f(H.$$.fragment),se=o(),w=i("p"),w.innerHTML=Ce,ne=o(),f(C.$$.fragment),re=o(),n=i("div"),f(F.$$.fragment),me=o(),N=i("p"),N.textContent=Fe,_e=o(),X=i("p"),X.textContent=ke,pe=o(),T=i("div"),f(k.$$.fragment),he=o(),K=i("p"),K.innerHTML=Le,ge=o(),v=i("div"),f(L.$$.fragment),Ae=o(),U=i("p"),U.innerHTML=ze,ye=o(),y=i("div"),f(z.$$.fragment),Pe=o(),J=i("p"),J.textContent=Se,be=o(),S=i("blockquote"),S.innerHTML=Ie,De=o(),x=i("div"),f(I.$$.fragment),Te=o(),R=i("p"),R.textContent=Ge,ve=o(),$=i("div"),f(G.$$.fragment),xe=o(),O=i("p"),O.textContent=Ve,$e=o(),P=i("div"),f(V.$$.fragment),Me=o(),B=i("p"),B.textContent=je,He=o(),j=i("blockquote"),j.innerHTML=Ee,ie=o(),f(E.$$.fragment),ae=o(),Z=i("p"),this.h()},l(e){const d=Re("svelte-u9bgzb",document.head);b=a(d,"META",{name:!0,content:!0}),d.forEach(r),ee=s(e),Y=a(e,"P",{}),D(Y).forEach(r),te=s(e),u(M.$$.fragment,e),oe=s(e),u(H.$$.fragment,e),se=s(e),w=a(e,"P",{"data-svelte-h":!0}),m(w)!=="svelte-nkajjv"&&(w.innerHTML=Ce),ne=s(e),u(C.$$.fragment,e),re=s(e),n=a(e,"DIV",{class:!0});var c=D(n);u(F.$$.fragment,c),me=s(c),N=a(c,"P",{"data-svelte-h":!0}),m(N)!=="svelte-rv6x8u"&&(N.textContent=Fe),_e=s(c),X=a(c,"P",{"data-svelte-h":!0}),m(X)!=="svelte-wuyqug"&&(X.textContent=ke),pe=s(c),T=a(c,"DIV",{class:!0});var ce=D(T);u(k.$$.fragment,ce),he=s(ce),K=a(ce,"P",{"data-svelte-h":!0}),m(K)!=="svelte-2m23sy"&&(K.innerHTML=Le),ce.forEach(r),ge=s(c),v=a(c,"DIV",{class:!0});var le=D(v);u(L.$$.fragment,le),Ae=s(le),U=a(le,"P",{"data-svelte-h":!0}),m(U)!=="svelte-1ddoizd"&&(U.innerHTML=ze),le.forEach(r),ye=s(c),y=a(c,"DIV",{class:!0});var Q=D(y);u(z.$$.fragment,Q),Pe=s(Q),J=a(Q,"P",{"data-svelte-h":!0}),m(J)!=="svelte-1254b9i"&&(J.textContent=Se),be=s(Q),S=a(Q,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),m(S)!=="svelte-6y4o4y"&&(S.innerHTML=Ie),Q.forEach(r),De=s(c),x=a(c,"DIV",{class:!0});var fe=D(x);u(I.$$.fragment,fe),Te=s(fe),R=a(fe,"P",{"data-svelte-h":!0}),m(R)!=="svelte-1o77hl2"&&(R.textContent=Ge),fe.forEach(r),ve=s(c),$=a(c,"DIV",{class:!0});var ue=D($);u(G.$$.fragment,ue),xe=s(ue),O=a(ue,"P",{"data-svelte-h":!0}),m(O)!=="svelte-1lxcwhv"&&(O.textContent=Ve),ue.forEach(r),$e=s(c),P=a(c,"DIV",{class:!0});var W=D(P);u(V.$$.fragment,W),Me=s(W),B=a(W,"P",{"data-svelte-h":!0}),m(B)!=="svelte-1vhtc74"&&(B.textContent=je),He=s(W),j=a(W,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),m(j)!=="svelte-6y4o4y"&&(j.innerHTML=Ee),W.forEach(r),c.forEach(r),ie=s(e),u(E.$$.fragment,e),ae=s(e),Z=a(e,"P",{}),D(Z).forEach(r),this.h()},h(){_(b,"name","hf:doc:metadata"),_(b,"content",We),_(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"),_(S,"class","warning"),_(y,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_(x,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_($,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_(j,"class","warning"),_(P,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),_(n,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(e,d){t(document.head,b),l(e,ee,d),l(e,Y,d),l(e,te,d),p(M,e,d),l(e,oe,d),p(H,e,d),l(e,se,d),l(e,w,d),l(e,ne,d),p(C,e,d),l(e,re,d),l(e,n,d),p(F,n,null),t(n,me),t(n,N),t(n,_e),t(n,X),t(n,pe),t(n,T),p(k,T,null),t(T,he),t(T,K),t(n,ge),t(n,v),p(L,v,null),t(v,Ae),t(v,U),t(n,ye),t(n,y),p(z,y,null),t(y,Pe),t(y,J),t(y,be),t(y,S),t(n,De),t(n,x),p(I,x,null),t(x,Te),t(x,R),t(n,ve),t(n,$),p(G,$,null),t($,xe),t($,O),t(n,$e),t(n,P),p(V,P,null),t(P,Me),t(P,B),t(P,He),t(P,j),l(e,ie,d),p(E,e,d),l(e,ae,d),l(e,Z,d),de=!0},p:Xe,i(e){de||(h(M.$$.fragment,e),h(H.$$.fragment,e),h(C.$$.fragment,e),h(F.$$.fragment,e),h(k.$$.fragment,e),h(L.$$.fragment,e),h(z.$$.fragment,e),h(I.$$.fragment,e),h(G.$$.fragment,e),h(V.$$.fragment,e),h(E.$$.fragment,e),de=!0)},o(e){g(M.$$.fragment,e),g(H.$$.fragment,e),g(C.$$.fragment,e),g(F.$$.fragment,e),g(k.$$.fragment,e),g(L.$$.fragment,e),g(z.$$.fragment,e),g(I.$$.fragment,e),g(G.$$.fragment,e),g(V.$$.fragment,e),g(E.$$.fragment,e),de=!1},d(e){e&&(r(ee),r(Y),r(te),r(oe),r(se),r(w),r(ne),r(re),r(n),r(ie),r(ae),r(Z)),r(b),A(M,e),A(H,e),A(C,e),A(F),A(k),A(L),A(z),A(I),A(G),A(V),A(E,e)}}}const We='{"title":"HunyuanDiT2DModel","local":"hunyuandit2dmodel","sections":[{"title":"HunyuanDiT2DModel","local":"diffusers.HunyuanDiT2DModel","sections":[],"depth":2}],"depth":1}';function Ye(we){return Ke(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class nt extends Ue{constructor(b){super(),Je(this,b,Ye,Qe,Ne,{})}}export{nt as component};