diffusers/pr_12595/en/_app/immutable/nodes/65.c4cbc5e7.js

import{s as Ge,n as Ve,o as Ne}from"../chunks/scheduler.53228c21.js";import{S as He,i as ze,e as a,s as o,c as u,h as Oe,a as d,d as s,b as r,f as D,g as _,j as h,k as g,l as t,m as c,n as A,t as P,o as x,p as b}from"../chunks/index.100fac89.js";import{C as je}from"../chunks/CopyLLMTxtMenu.7aefc1a4.js";import{D as Q}from"../chunks/Docstring.d6cb35e8.js";import{H as Ie,E as Xe}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.3722da43.js";function Ee(Te){let v,Y,B,Z,$,ee,M,te,w,ye='A Transformer model for image-like data from <a href="https://huggingface.co/papers/2310.00426" rel="nofollow">PixArt-Alpha</a> and <a href="https://huggingface.co/papers/2403.04692" rel="nofollow">PixArt-Sigma</a>.',oe,F,se,n,k,fe,z,De=`A 2D Transformer model as introduced in PixArt family of models (<a href="https://huggingface.co/papers/2310.00426" rel="nofollow">https://huggingface.co/papers/2310.00426</a>,
<a href="https://huggingface.co/papers/2403.04692" rel="nofollow">https://huggingface.co/papers/2403.04692</a>).`,ce,T,C,le,O,$e='The <a href="/docs/diffusers/pr_12595/en/api/models/pixart_transformer2d#diffusers.PixArtTransformer2DModel">PixArtTransformer2DModel</a> forward method.',me,l,L,pe,j,Me=`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.`,ue,S,we="<p>&gt; This API is 🧪 experimental.</p>",_e,y,I,he,X,Fe="Sets the attention processor to use to compute attention.",ge,m,G,Ae,E,ke="Disables custom attention processors and sets the default attention implementation.",Pe,K,Ce="Safe to just use <code>AttnProcessor()</code> as PixArt doesn’t have any exotic attention processors in default model.",xe,p,V,be,q,Le="Disables the fused QKV projection if enabled.",ve,N,Se="<p>&gt; This API is 🧪 experimental.</p>",re,H,ne,W,ie;return $=new je({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),M=new Ie({props:{title:"PixArtTransformer2DModel",local:"pixarttransformer2dmodel",headingTag:"h1"}}),F=new Ie({props:{title:"PixArtTransformer2DModel",local:"diffusers.PixArtTransformer2DModel",headingTag:"h2"}}),k=new Q({props:{name:"class diffusers.PixArtTransformer2DModel",anchor:"diffusers.PixArtTransformer2DModel",parameters:[{name:"num_attention_heads",val:": int = 16"},{name:"attention_head_dim",val:": int = 72"},{name:"in_channels",val:": int = 4"},{name:"out_channels",val:": typing.Optional[int] = 8"},{name:"num_layers",val:": int = 28"},{name:"dropout",val:": float = 0.0"},{name:"norm_num_groups",val:": int = 32"},{name:"cross_attention_dim",val:": typing.Optional[int] = 1152"},{name:"attention_bias",val:": bool = True"},{name:"sample_size",val:": int = 128"},{name:"patch_size",val:": int = 2"},{name:"activation_fn",val:": str = 'gelu-approximate'"},{name:"num_embeds_ada_norm",val:": typing.Optional[int] = 1000"},{name:"upcast_attention",val:": bool = False"},{name:"norm_type",val:": str = 'ada_norm_single'"},{name:"norm_elementwise_affine",val:": bool = False"},{name:"norm_eps",val:": float = 1e-06"},{name:"interpolation_scale",val:": typing.Optional[int] = None"},{name:"use_additional_conditions",val:": typing.Optional[bool] = None"},{name:"caption_channels",val:": typing.Optional[int] = None"},{name:"attention_type",val:": typing.Optional[str] = 'default'"}],parametersDescription:[{anchor:"diffusers.PixArtTransformer2DModel.num_attention_heads",description:"<strong>num_attention_heads</strong> (int, optional, defaults to 16) &#x2014; The number of heads to use for multi-head attention.",name:"num_attention_heads"},{anchor:"diffusers.PixArtTransformer2DModel.attention_head_dim",description:"<strong>attention_head_dim</strong> (int, optional, defaults to 72) &#x2014; The number of channels in each head.",name:"attention_head_dim"},{anchor:"diffusers.PixArtTransformer2DModel.in_channels",description:"<strong>in_channels</strong> (int, defaults to 4) &#x2014; The number of channels in the input.",name:"in_channels"},{anchor:"diffusers.PixArtTransformer2DModel.out_channels",description:`<strong>out_channels</strong> (int, optional) &#x2014;
The number of channels in the output. Specify this parameter if the output channel number differs from the
input.`,name:"out_channels"},{anchor:"diffusers.PixArtTransformer2DModel.num_layers",description:"<strong>num_layers</strong> (int, optional, defaults to 28) &#x2014; The number of layers of Transformer blocks to use.",name:"num_layers"},{anchor:"diffusers.PixArtTransformer2DModel.dropout",description:"<strong>dropout</strong> (float, optional, defaults to 0.0) &#x2014; The dropout probability to use within the Transformer blocks.",name:"dropout"},{anchor:"diffusers.PixArtTransformer2DModel.norm_num_groups",description:`<strong>norm_num_groups</strong> (int, optional, defaults to 32) &#x2014;
Number of groups for group normalization within Transformer blocks.`,name:"norm_num_groups"},{anchor:"diffusers.PixArtTransformer2DModel.cross_attention_dim",description:`<strong>cross_attention_dim</strong> (int, optional) &#x2014;
The dimensionality for cross-attention layers, typically matching the encoder&#x2019;s hidden dimension.`,name:"cross_attention_dim"},{anchor:"diffusers.PixArtTransformer2DModel.attention_bias",description:`<strong>attention_bias</strong> (bool, optional, defaults to True) &#x2014;
Configure if the Transformer blocks&#x2019; attention should contain a bias parameter.`,name:"attention_bias"},{anchor:"diffusers.PixArtTransformer2DModel.sample_size",description:`<strong>sample_size</strong> (int, defaults to 128) &#x2014;
The width of the latent images. This parameter is fixed during training.`,name:"sample_size"},{anchor:"diffusers.PixArtTransformer2DModel.patch_size",description:`<strong>patch_size</strong> (int, defaults to 2) &#x2014;
Size of the patches the model processes, relevant for architectures working on non-sequential data.`,name:"patch_size"},{anchor:"diffusers.PixArtTransformer2DModel.activation_fn",description:`<strong>activation_fn</strong> (str, optional, defaults to &#x201C;gelu-approximate&#x201D;) &#x2014;
Activation function to use in feed-forward networks within Transformer blocks.`,name:"activation_fn"},{anchor:"diffusers.PixArtTransformer2DModel.num_embeds_ada_norm",description:`<strong>num_embeds_ada_norm</strong> (int, optional, defaults to 1000) &#x2014;
Number of embeddings for AdaLayerNorm, fixed during training and affects the maximum denoising steps during
inference.`,name:"num_embeds_ada_norm"},{anchor:"diffusers.PixArtTransformer2DModel.upcast_attention",description:`<strong>upcast_attention</strong> (bool, optional, defaults to False) &#x2014;
If true, upcasts the attention mechanism dimensions for potentially improved performance.`,name:"upcast_attention"},{anchor:"diffusers.PixArtTransformer2DModel.norm_type",description:`<strong>norm_type</strong> (str, optional, defaults to &#x201C;ada_norm_zero&#x201D;) &#x2014;
Specifies the type of normalization used, can be &#x2018;ada_norm_zero&#x2019;.`,name:"norm_type"},{anchor:"diffusers.PixArtTransformer2DModel.norm_elementwise_affine",description:`<strong>norm_elementwise_affine</strong> (bool, optional, defaults to False) &#x2014;
If true, enables element-wise affine parameters in the normalization layers.`,name:"norm_elementwise_affine"},{anchor:"diffusers.PixArtTransformer2DModel.norm_eps",description:`<strong>norm_eps</strong> (float, optional, defaults to 1e-6) &#x2014;
A small constant added to the denominator in normalization layers to prevent division by zero.`,name:"norm_eps"},{anchor:"diffusers.PixArtTransformer2DModel.interpolation_scale",description:"<strong>interpolation_scale</strong> (int, optional) &#x2014; Scale factor to use during interpolating the position embeddings.",name:"interpolation_scale"},{anchor:"diffusers.PixArtTransformer2DModel.use_additional_conditions",description:"<strong>use_additional_conditions</strong> (bool, optional) &#x2014; If we&#x2019;re using additional conditions as inputs.",name:"use_additional_conditions"},{anchor:"diffusers.PixArtTransformer2DModel.attention_type",description:"<strong>attention_type</strong> (str, optional, defaults to &#x201C;default&#x201D;) &#x2014; Kind of attention mechanism to be used.",name:"attention_type"},{anchor:"diffusers.PixArtTransformer2DModel.caption_channels",description:`<strong>caption_channels</strong> (int, optional, defaults to None) &#x2014;
Number of channels to use for projecting the caption embeddings.`,name:"caption_channels"},{anchor:"diffusers.PixArtTransformer2DModel.use_linear_projection",description:`<strong>use_linear_projection</strong> (bool, optional, defaults to False) &#x2014;
Deprecated argument. Will be removed in a future version.`,name:"use_linear_projection"},{anchor:"diffusers.PixArtTransformer2DModel.num_vector_embeds",description:`<strong>num_vector_embeds</strong> (bool, optional, defaults to False) &#x2014;
Deprecated argument. Will be removed in a future version.`,name:"num_vector_embeds"}],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/pixart_transformer_2d.py#L32"}}),C=new Q({props:{name:"forward",anchor:"diffusers.PixArtTransformer2DModel.forward",parameters:[{name:"hidden_states",val:": Tensor"},{name:"encoder_hidden_states",val:": typing.Optional[torch.Tensor] = None"},{name:"timestep",val:": typing.Optional[torch.LongTensor] = None"},{name:"added_cond_kwargs",val:": typing.Dict[str, torch.Tensor] = None"},{name:"cross_attention_kwargs",val:": typing.Dict[str, typing.Any] = None"},{name:"attention_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"encoder_attention_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.PixArtTransformer2DModel.forward.hidden_states",description:`<strong>hidden_states</strong> (<code>torch.FloatTensor</code> of shape <code>(batch size, channel, height, width)</code>) &#x2014;
Input <code>hidden_states</code>.`,name:"hidden_states"},{anchor:"diffusers.PixArtTransformer2DModel.forward.encoder_hidden_states",description:`<strong>encoder_hidden_states</strong> (<code>torch.FloatTensor</code> of shape <code>(batch size, sequence len, embed dims)</code>, <em>optional</em>) &#x2014;
Conditional embeddings for cross attention layer. If not given, cross-attention defaults to
self-attention.`,name:"encoder_hidden_states"},{anchor:"diffusers.PixArtTransformer2DModel.forward.timestep",description:`<strong>timestep</strong> (<code>torch.LongTensor</code>, <em>optional</em>) &#x2014;
Used to indicate denoising step. Optional timestep to be applied as an embedding in <code>AdaLayerNorm</code>.`,name:"timestep"},{anchor:"diffusers.PixArtTransformer2DModel.forward.added_cond_kwargs",description:"<strong>added_cond_kwargs</strong> &#x2014; (<code>Dict[str, Any]</code>, <em>optional</em>): Additional conditions to be used as inputs.",name:"added_cond_kwargs"},{anchor:"diffusers.PixArtTransformer2DModel.forward.cross_attention_kwargs",description:`<strong>cross_attention_kwargs</strong> ( <code>Dict[str, Any]</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:"cross_attention_kwargs"},{anchor:"diffusers.PixArtTransformer2DModel.forward.attention_mask",description:`<strong>attention_mask</strong> ( <code>torch.Tensor</code>, <em>optional</em>) &#x2014;
An attention mask of shape <code>(batch, key_tokens)</code> is applied to <code>encoder_hidden_states</code>. If <code>1</code> the mask
is kept, otherwise if <code>0</code> it is discarded. Mask will be converted into a bias, which adds large
negative values to the attention scores corresponding to &#x201C;discard&#x201D; tokens.`,name:"attention_mask"},{anchor:"diffusers.PixArtTransformer2DModel.forward.encoder_attention_mask",description:`<strong>encoder_attention_mask</strong> ( <code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Cross-attention mask applied to <code>encoder_hidden_states</code>. Two formats supported:</p>
<ul>
<li>Mask <code>(batch, sequence_length)</code> True = keep, False = discard.</li>
<li>Bias <code>(batch, 1, sequence_length)</code> 0 = keep, -10000 = discard.</li>
</ul>
<p>If <code>ndim == 2</code>: will be interpreted as a mask, then converted into a bias consistent with the format
above. This bias will be added to the cross-attention scores.`,name:"encoder_attention_mask"},{anchor:"diffusers.PixArtTransformer2DModel.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 <a href="/docs/diffusers/pr_12595/en/api/models/unet2d-cond#diffusers.models.unets.unet_2d_condition.UNet2DConditionOutput">UNet2DConditionOutput</a> instead of a plain
tuple.`,name:"return_dict"}],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/pixart_transformer_2d.py#L287",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>
`}}),L=new Q({props:{name:"fuse_qkv_projections",anchor:"diffusers.PixArtTransformer2DModel.fuse_qkv_projections",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/pixart_transformer_2d.py#L256"}}),I=new Q({props:{name:"set_attn_processor",anchor:"diffusers.PixArtTransformer2DModel.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.PixArtTransformer2DModel.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/pixart_transformer_2d.py#L213"}}),G=new Q({props:{name:"set_default_attn_processor",anchor:"diffusers.PixArtTransformer2DModel.set_default_attn_processor",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/pixart_transformer_2d.py#L247"}}),V=new Q({props:{name:"unfuse_qkv_projections",anchor:"diffusers.PixArtTransformer2DModel.unfuse_qkv_projections",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12595/src/diffusers/models/transformers/pixart_transformer_2d.py#L278"}}),H=new Xe({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/models/pixart_transformer2d.md"}}),{c(){v=a("meta"),Y=o(),B=a("p"),Z=o(),u($.$$.fragment),ee=o(),u(M.$$.fragment),te=o(),w=a("p"),w.innerHTML=ye,oe=o(),u(F.$$.fragment),se=o(),n=a("div"),u(k.$$.fragment),fe=o(),z=a("p"),z.innerHTML=De,ce=o(),T=a("div"),u(C.$$.fragment),le=o(),O=a("p"),O.innerHTML=$e,me=o(),l=a("div"),u(L.$$.fragment),pe=o(),j=a("p"),j.textContent=Me,ue=o(),S=a("blockquote"),S.innerHTML=we,_e=o(),y=a("div"),u(I.$$.fragment),he=o(),X=a("p"),X.textContent=Fe,ge=o(),m=a("div"),u(G.$$.fragment),Ae=o(),E=a("p"),E.textContent=ke,Pe=o(),K=a("p"),K.innerHTML=Ce,xe=o(),p=a("div"),u(V.$$.fragment),be=o(),q=a("p"),q.textContent=Le,ve=o(),N=a("blockquote"),N.innerHTML=Se,re=o(),u(H.$$.fragment),ne=o(),W=a("p"),this.h()},l(e){const i=Oe("svelte-u9bgzb",document.head);v=d(i,"META",{name:!0,content:!0}),i.forEach(s),Y=r(e),B=d(e,"P",{}),D(B).forEach(s),Z=r(e),_($.$$.fragment,e),ee=r(e),_(M.$$.fragment,e),te=r(e),w=d(e,"P",{"data-svelte-h":!0}),h(w)!=="svelte-p8z7gn"&&(w.innerHTML=ye),oe=r(e),_(F.$$.fragment,e),se=r(e),n=d(e,"DIV",{class:!0});var f=D(n);_(k.$$.fragment,f),fe=r(f),z=d(f,"P",{"data-svelte-h":!0}),h(z)!=="svelte-1v9f4ml"&&(z.innerHTML=De),ce=r(f),T=d(f,"DIV",{class:!0});var ae=D(T);_(C.$$.fragment,ae),le=r(ae),O=d(ae,"P",{"data-svelte-h":!0}),h(O)!=="svelte-elpakd"&&(O.innerHTML=$e),ae.forEach(s),me=r(f),l=d(f,"DIV",{class:!0});var U=D(l);_(L.$$.fragment,U),pe=r(U),j=d(U,"P",{"data-svelte-h":!0}),h(j)!=="svelte-1254b9i"&&(j.textContent=Me),ue=r(U),S=d(U,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),h(S)!=="svelte-6y4o4y"&&(S.innerHTML=we),U.forEach(s),_e=r(f),y=d(f,"DIV",{class:!0});var de=D(y);_(I.$$.fragment,de),he=r(de),X=d(de,"P",{"data-svelte-h":!0}),h(X)!=="svelte-1o77hl2"&&(X.textContent=Fe),de.forEach(s),ge=r(f),m=d(f,"DIV",{class:!0});var J=D(m);_(G.$$.fragment,J),Ae=r(J),E=d(J,"P",{"data-svelte-h":!0}),h(E)!=="svelte-1lxcwhv"&&(E.textContent=ke),Pe=r(J),K=d(J,"P",{"data-svelte-h":!0}),h(K)!=="svelte-1vivlhg"&&(K.innerHTML=Ce),J.forEach(s),xe=r(f),p=d(f,"DIV",{class:!0});var R=D(p);_(V.$$.fragment,R),be=r(R),q=d(R,"P",{"data-svelte-h":!0}),h(q)!=="svelte-1vhtc74"&&(q.textContent=Le),ve=r(R),N=d(R,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),h(N)!=="svelte-6y4o4y"&&(N.innerHTML=Se),R.forEach(s),f.forEach(s),re=r(e),_(H.$$.fragment,e),ne=r(e),W=d(e,"P",{}),D(W).forEach(s),this.h()},h(){g(v,"name","hf:doc:metadata"),g(v,"content",Ke),g(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),g(S,"class","warning"),g(l,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),g(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(m,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),g(N,"class","warning"),g(p,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),g(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){t(document.head,v),c(e,Y,i),c(e,B,i),c(e,Z,i),A($,e,i),c(e,ee,i),A(M,e,i),c(e,te,i),c(e,w,i),c(e,oe,i),A(F,e,i),c(e,se,i),c(e,n,i),A(k,n,null),t(n,fe),t(n,z),t(n,ce),t(n,T),A(C,T,null),t(T,le),t(T,O),t(n,me),t(n,l),A(L,l,null),t(l,pe),t(l,j),t(l,ue),t(l,S),t(n,_e),t(n,y),A(I,y,null),t(y,he),t(y,X),t(n,ge),t(n,m),A(G,m,null),t(m,Ae),t(m,E),t(m,Pe),t(m,K),t(n,xe),t(n,p),A(V,p,null),t(p,be),t(p,q),t(p,ve),t(p,N),c(e,re,i),A(H,e,i),c(e,ne,i),c(e,W,i),ie=!0},p:Ve,i(e){ie||(P($.$$.fragment,e),P(M.$$.fragment,e),P(F.$$.fragment,e),P(k.$$.fragment,e),P(C.$$.fragment,e),P(L.$$.fragment,e),P(I.$$.fragment,e),P(G.$$.fragment,e),P(V.$$.fragment,e),P(H.$$.fragment,e),ie=!0)},o(e){x($.$$.fragment,e),x(M.$$.fragment,e),x(F.$$.fragment,e),x(k.$$.fragment,e),x(C.$$.fragment,e),x(L.$$.fragment,e),x(I.$$.fragment,e),x(G.$$.fragment,e),x(V.$$.fragment,e),x(H.$$.fragment,e),ie=!1},d(e){e&&(s(Y),s(B),s(Z),s(ee),s(te),s(w),s(oe),s(se),s(n),s(re),s(ne),s(W)),s(v),b($,e),b(M,e),b(F,e),b(k),b(C),b(L),b(I),b(G),b(V),b(H,e)}}}const Ke='{"title":"PixArtTransformer2DModel","local":"pixarttransformer2dmodel","sections":[{"title":"PixArtTransformer2DModel","local":"diffusers.PixArtTransformer2DModel","sections":[],"depth":2}],"depth":1}';function qe(Te){return Ne(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class We extends He{constructor(v){super(),ze(this,v,qe,Ee,Ge,{})}}export{We as component};