diffusers/main/en/_app/immutable/nodes/55.3dca5704.js

import{s as me,o as ce,n as de}from"../chunks/scheduler.8c3d61f6.js";import{S as ue,i as fe,g as d,s as i,r as b,A as ge,h as m,f as o,c as l,j as z,u as x,x as L,k as D,y as f,a as r,v as $,d as P,t as T,w as F}from"../chunks/index.da70eac4.js";import{T as _e}from"../chunks/Tip.1d9b8c37.js";import{D as oe}from"../chunks/Docstring.ee4b6913.js";import{C as he}from"../chunks/CodeBlock.00a903b3.js";import{E as we}from"../chunks/ExampleCodeBlock.f7bd2c1f.js";import{H as pe,E as ve}from"../chunks/EditOnGithub.1e64e623.js";function be(J){let n,w='AuraFlow can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out <a href="https://huggingface.co/blog/sd3#memory-optimizations-for-sd3" rel="nofollow">this section</a> for more details.';return{c(){n=d("p"),n.innerHTML=w},l(s){n=m(s,"P",{"data-svelte-h":!0}),L(n)!=="svelte-q1wg22"&&(n.innerHTML=w)},m(s,p){r(s,n,p)},p:de,d(s){s&&o(n)}}}function xe(J){let n,w="Examples:",s,p,c;return p=new he({props:{code:"aW1wb3J0JTIwdG9yY2glMEFmcm9tJTIwZGlmZnVzZXJzJTIwaW1wb3J0JTIwQXVyYUZsb3dQaXBlbGluZSUwQSUwQXBpcGUlMjAlM0QlMjBBdXJhRmxvd1BpcGVsaW5lLmZyb21fcHJldHJhaW5lZCglMjJmYWwlMkZBdXJhRmxvdyUyMiUyQyUyMHRvcmNoX2R0eXBlJTNEdG9yY2guZmxvYXQxNiklMEFwaXBlJTIwJTNEJTIwcGlwZS50byglMjJjdWRhJTIyKSUwQXByb21wdCUyMCUzRCUyMCUyMkElMjBjYXQlMjBob2xkaW5nJTIwYSUyMHNpZ24lMjB0aGF0JTIwc2F5cyUyMGhlbGxvJTIwd29ybGQlMjIlMEFpbWFnZSUyMCUzRCUyMHBpcGUocHJvbXB0KS5pbWFnZXMlNUIwJTVEJTBBaW1hZ2Uuc2F2ZSglMjJhdXJhX2Zsb3cucG5nJTIyKQ==",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AuraFlowPipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = AuraFlowPipeline.from_pretrained(<span class="hljs-string">&quot;fal/AuraFlow&quot;</span>, torch_dtype=torch.float16)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>prompt = <span class="hljs-string">&quot;A cat holding a sign that says hello world&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>image = pipe(prompt).images[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;aura_flow.png&quot;</span>)`,wrap:!1}}),{c(){n=d("p"),n.textContent=w,s=i(),b(p.$$.fragment)},l(a){n=m(a,"P",{"data-svelte-h":!0}),L(n)!=="svelte-kvfsh7"&&(n.textContent=w),s=l(a),x(p.$$.fragment,a)},m(a,g){r(a,n,g),r(a,s,g),$(p,a,g),c=!0},p:de,i(a){c||(P(p.$$.fragment,a),c=!0)},o(a){T(p.$$.fragment,a),c=!1},d(a){a&&(o(n),o(s)),F(p,a)}}}function $e(J){let n,w,s,p,c,a,g,ae='AuraFlow is inspired by <a href="../pipelines/stable_diffusion/stable_diffusion_3.md">Stable Diffusion 3</a> and is by far the largest text-to-image generation model that comes with an Apache 2.0 license. This model achieves state-of-the-art results on the <a href="https://github.com/djghosh13/geneval" rel="nofollow">GenEval</a> benchmark.',B,M,re='It was developed by the Fal team and more details about it can be found in <a href="https://blog.fal.ai/auraflow/" rel="nofollow">this blog post</a>.',H,A,X,I,S,_,C,V,u,E,Y,U,se="Function invoked when calling the pipeline for generation.",K,y,ee,N,ie=`Returns: <a href="/docs/diffusers/main/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput">ImagePipelineOutput</a> or <code>tuple</code>:
If <code>return_dict</code> is <code>True</code>, <a href="/docs/diffusers/main/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput">ImagePipelineOutput</a> is returned, otherwise a <code>tuple</code> is returned
where the first element is a list with the generated images.`,te,k,j,ne,G,le="Encodes the prompt into text encoder hidden states.",Z,q,Q,O,W;return c=new pe({props:{title:"AuraFlow",local:"auraflow",headingTag:"h1"}}),A=new _e({props:{$$slots:{default:[be]},$$scope:{ctx:J}}}),I=new pe({props:{title:"AuraFlowPipeline",local:"diffusers.AuraFlowPipeline",headingTag:"h2"}}),C=new oe({props:{name:"class diffusers.AuraFlowPipeline",anchor:"diffusers.AuraFlowPipeline",parameters:[{name:"tokenizer",val:": T5Tokenizer"},{name:"text_encoder",val:": UMT5EncoderModel"},{name:"vae",val:": AutoencoderKL"},{name:"transformer",val:": AuraFlowTransformer2DModel"},{name:"scheduler",val:": FlowMatchEulerDiscreteScheduler"}],parametersDescription:[{anchor:"diffusers.AuraFlowPipeline.tokenizer",description:`<strong>tokenizer</strong> (<code>T5TokenizerFast</code>) &#x2014;
Tokenizer of class
<a href="https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Tokenizer" rel="nofollow">T5Tokenizer</a>.`,name:"tokenizer"},{anchor:"diffusers.AuraFlowPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>T5EncoderModel</code>) &#x2014;
Frozen text-encoder. AuraFlow uses
<a href="https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel" rel="nofollow">T5</a>, specifically the
<a href="https://huggingface.co/EleutherAI/pile-t5-xl" rel="nofollow">EleutherAI/pile-t5-xl</a> variant.`,name:"text_encoder"},{anchor:"diffusers.AuraFlowPipeline.vae",description:`<strong>vae</strong> (<a href="/docs/diffusers/main/en/api/models/autoencoderkl#diffusers.AutoencoderKL">AutoencoderKL</a>) &#x2014;
Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.`,name:"vae"},{anchor:"diffusers.AuraFlowPipeline.transformer",description:`<strong>transformer</strong> (<a href="/docs/diffusers/main/en/api/models/aura_flow_transformer2d#diffusers.AuraFlowTransformer2DModel">AuraFlowTransformer2DModel</a>) &#x2014;
Conditional Transformer (MMDiT and DiT) architecture to denoise the encoded image latents.`,name:"transformer"},{anchor:"diffusers.AuraFlowPipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/main/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler">FlowMatchEulerDiscreteScheduler</a>) &#x2014;
A scheduler to be used in combination with <code>transformer</code> to denoise the encoded image latents.`,name:"scheduler"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/aura_flow/pipeline_aura_flow.py#L107"}}),E=new oe({props:{name:"__call__",anchor:"diffusers.AuraFlowPipeline.__call__",parameters:[{name:"prompt",val:": Union = None"},{name:"negative_prompt",val:": Union = None"},{name:"num_inference_steps",val:": int = 50"},{name:"timesteps",val:": List = None"},{name:"sigmas",val:": List = None"},{name:"guidance_scale",val:": float = 3.5"},{name:"num_images_per_prompt",val:": Optional = 1"},{name:"height",val:": Optional = 1024"},{name:"width",val:": Optional = 1024"},{name:"generator",val:": Union = None"},{name:"latents",val:": Optional = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"prompt_attention_mask",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"negative_prompt_attention_mask",val:": Optional = None"},{name:"max_sequence_length",val:": int = 256"},{name:"output_type",val:": Optional = 'pil'"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.AuraFlowPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide the image generation. If not defined, one has to pass <code>prompt_embeds</code>.
instead.`,name:"prompt"},{anchor:"diffusers.AuraFlowPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts not to guide the image generation. If not defined, one has to pass
<code>negative_prompt_embeds</code> instead. Ignored when not using guidance (i.e., ignored if <code>guidance_scale</code> is
less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.AuraFlowPipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to self.transformer.config.sample_size * self.vae_scale_factor) &#x2014;
The height in pixels of the generated image. This is set to 1024 by default for best results.`,name:"height"},{anchor:"diffusers.AuraFlowPipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to self.transformer.config.sample_size * self.vae_scale_factor) &#x2014;
The width in pixels of the generated image. This is set to 1024 by default for best results.`,name:"width"},{anchor:"diffusers.AuraFlowPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 50) &#x2014;
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference.`,name:"num_inference_steps"},{anchor:"diffusers.AuraFlowPipeline.__call__.sigmas",description:`<strong>sigmas</strong> (<code>List[float]</code>, <em>optional</em>) &#x2014;
Custom sigmas used to override the timestep spacing strategy of the scheduler. If <code>sigmas</code> is passed,
<code>num_inference_steps</code> and <code>timesteps</code> must be <code>None</code>.`,name:"sigmas"},{anchor:"diffusers.AuraFlowPipeline.__call__.timesteps",description:`<strong>timesteps</strong> (<code>List[int]</code>, <em>optional</em>) &#x2014;
Custom timesteps to use for the denoising process with schedulers which support a <code>timesteps</code> argument
in their <code>set_timesteps</code> method. If not defined, the default behavior when <code>num_inference_steps</code> is
passed will be used. Must be in descending order.`,name:"timesteps"},{anchor:"diffusers.AuraFlowPipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 5.0) &#x2014;
Guidance scale as defined in <a href="https://arxiv.org/abs/2207.12598" rel="nofollow">Classifier-Free Diffusion Guidance</a>.
<code>guidance_scale</code> is defined as <code>w</code> of equation 2. of <a href="https://arxiv.org/pdf/2205.11487.pdf" rel="nofollow">Imagen
Paper</a>. Guidance scale is enabled by setting <code>guidance_scale &gt; 1</code>. Higher guidance scale encourages to generate images that are closely linked to the text <code>prompt</code>,
usually at the expense of lower image quality.`,name:"guidance_scale"},{anchor:"diffusers.AuraFlowPipeline.__call__.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
The number of images to generate per prompt.`,name:"num_images_per_prompt"},{anchor:"diffusers.AuraFlowPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code> or <code>List[torch.Generator]</code>, <em>optional</em>) &#x2014;
One or a list of <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow">torch generator(s)</a>
to make generation deterministic.`,name:"generator"},{anchor:"diffusers.AuraFlowPipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.FloatTensor</code>, <em>optional</em>) &#x2014;
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor will ge generated by sampling using the supplied random <code>generator</code>.`,name:"latents"},{anchor:"diffusers.AuraFlowPipeline.__call__.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.FloatTensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt weighting. If not
provided, text embeddings will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds"},{anchor:"diffusers.AuraFlowPipeline.__call__.prompt_attention_mask",description:`<strong>prompt_attention_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated attention mask for text embeddings.`,name:"prompt_attention_mask"},{anchor:"diffusers.AuraFlowPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.FloatTensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, negative_prompt_embeds will be generated from <code>negative_prompt</code> input
argument.`,name:"negative_prompt_embeds"},{anchor:"diffusers.AuraFlowPipeline.__call__.negative_prompt_attention_mask",description:`<strong>negative_prompt_attention_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated attention mask for negative text embeddings.`,name:"negative_prompt_attention_mask"},{anchor:"diffusers.AuraFlowPipeline.__call__.output_type",description:`<strong>output_type</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;pil&quot;</code>) &#x2014;
The output format of the generate image. Choose between
<a href="https://pillow.readthedocs.io/en/stable/" rel="nofollow">PIL</a>: <code>PIL.Image.Image</code> or <code>np.array</code>.`,name:"output_type"},{anchor:"diffusers.AuraFlowPipeline.__call__.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>~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput</code> instead
of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.AuraFlowPipeline.__call__.max_sequence_length",description:"<strong>max_sequence_length</strong> (<code>int</code> defaults to 256) &#x2014; Maximum sequence length to use with the <code>prompt</code>.",name:"max_sequence_length"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/aura_flow/pipeline_aura_flow.py#L383"}}),y=new we({props:{anchor:"diffusers.AuraFlowPipeline.__call__.example",$$slots:{default:[xe]},$$scope:{ctx:J}}}),j=new oe({props:{name:"encode_prompt",anchor:"diffusers.AuraFlowPipeline.encode_prompt",parameters:[{name:"prompt",val:": Union"},{name:"negative_prompt",val:": Union = None"},{name:"do_classifier_free_guidance",val:": bool = True"},{name:"num_images_per_prompt",val:": int = 1"},{name:"device",val:": Optional = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"prompt_attention_mask",val:": Optional = None"},{name:"negative_prompt_attention_mask",val:": Optional = None"},{name:"max_sequence_length",val:": int = 256"}],parametersDescription:[{anchor:"diffusers.AuraFlowPipeline.encode_prompt.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
prompt to be encoded`,name:"prompt"},{anchor:"diffusers.AuraFlowPipeline.encode_prompt.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt not to guide the image generation. If not defined, one has to pass <code>negative_prompt_embeds</code>
instead. Ignored when not using guidance (i.e., ignored if <code>guidance_scale</code> is less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.AuraFlowPipeline.encode_prompt.do_classifier_free_guidance",description:`<strong>do_classifier_free_guidance</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
whether to use classifier free guidance or not`,name:"do_classifier_free_guidance"},{anchor:"diffusers.AuraFlowPipeline.encode_prompt.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
number of images that should be generated per prompt
device &#x2014; (<code>torch.device</code>, <em>optional</em>):
torch device to place the resulting embeddings on`,name:"num_images_per_prompt"},{anchor:"diffusers.AuraFlowPipeline.encode_prompt.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt weighting. If not
provided, text embeddings will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds"},{anchor:"diffusers.AuraFlowPipeline.encode_prompt.prompt_attention_mask",description:`<strong>prompt_attention_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated attention mask for text embeddings.`,name:"prompt_attention_mask"},{anchor:"diffusers.AuraFlowPipeline.encode_prompt.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings.`,name:"negative_prompt_embeds"},{anchor:"diffusers.AuraFlowPipeline.encode_prompt.negative_prompt_attention_mask",description:`<strong>negative_prompt_attention_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated attention mask for negative text embeddings.`,name:"negative_prompt_attention_mask"},{anchor:"diffusers.AuraFlowPipeline.encode_prompt.max_sequence_length",description:"<strong>max_sequence_length</strong> (<code>int</code>, defaults to 256) &#x2014; Maximum sequence length to use for the prompt.",name:"max_sequence_length"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/aura_flow/pipeline_aura_flow.py#L205"}}),q=new ve({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/aura_flow.md"}}),{c(){n=d("meta"),w=i(),s=d("p"),p=i(),b(c.$$.fragment),a=i(),g=d("p"),g.innerHTML=ae,B=i(),M=d("p"),M.innerHTML=re,H=i(),b(A.$$.fragment),X=i(),b(I.$$.fragment),S=i(),_=d("div"),b(C.$$.fragment),V=i(),u=d("div"),b(E.$$.fragment),Y=i(),U=d("p"),U.textContent=se,K=i(),b(y.$$.fragment),ee=i(),N=d("p"),N.innerHTML=ie,te=i(),k=d("div"),b(j.$$.fragment),ne=i(),G=d("p"),G.textContent=le,Z=i(),b(q.$$.fragment),Q=i(),O=d("p"),this.h()},l(e){const t=ge("svelte-u9bgzb",document.head);n=m(t,"META",{name:!0,content:!0}),t.forEach(o),w=l(e),s=m(e,"P",{}),z(s).forEach(o),p=l(e),x(c.$$.fragment,e),a=l(e),g=m(e,"P",{"data-svelte-h":!0}),L(g)!=="svelte-1tqsx8f"&&(g.innerHTML=ae),B=l(e),M=m(e,"P",{"data-svelte-h":!0}),L(M)!=="svelte-1tuv1oa"&&(M.innerHTML=re),H=l(e),x(A.$$.fragment,e),X=l(e),x(I.$$.fragment,e),S=l(e),_=m(e,"DIV",{class:!0});var v=z(_);x(C.$$.fragment,v),V=l(v),u=m(v,"DIV",{class:!0});var h=z(u);x(E.$$.fragment,h),Y=l(h),U=m(h,"P",{"data-svelte-h":!0}),L(U)!=="svelte-v78lg8"&&(U.textContent=se),K=l(h),x(y.$$.fragment,h),ee=l(h),N=m(h,"P",{"data-svelte-h":!0}),L(N)!=="svelte-e17ang"&&(N.innerHTML=ie),h.forEach(o),te=l(v),k=m(v,"DIV",{class:!0});var R=z(k);x(j.$$.fragment,R),ne=l(R),G=m(R,"P",{"data-svelte-h":!0}),L(G)!=="svelte-16q0ax1"&&(G.textContent=le),R.forEach(o),v.forEach(o),Z=l(e),x(q.$$.fragment,e),Q=l(e),O=m(e,"P",{}),z(O).forEach(o),this.h()},h(){D(n,"name","hf:doc:metadata"),D(n,"content",Pe),D(u,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),D(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),D(_,"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,t){f(document.head,n),r(e,w,t),r(e,s,t),r(e,p,t),$(c,e,t),r(e,a,t),r(e,g,t),r(e,B,t),r(e,M,t),r(e,H,t),$(A,e,t),r(e,X,t),$(I,e,t),r(e,S,t),r(e,_,t),$(C,_,null),f(_,V),f(_,u),$(E,u,null),f(u,Y),f(u,U),f(u,K),$(y,u,null),f(u,ee),f(u,N),f(_,te),f(_,k),$(j,k,null),f(k,ne),f(k,G),r(e,Z,t),$(q,e,t),r(e,Q,t),r(e,O,t),W=!0},p(e,[t]){const v={};t&2&&(v.$$scope={dirty:t,ctx:e}),A.$set(v);const h={};t&2&&(h.$$scope={dirty:t,ctx:e}),y.$set(h)},i(e){W||(P(c.$$.fragment,e),P(A.$$.fragment,e),P(I.$$.fragment,e),P(C.$$.fragment,e),P(E.$$.fragment,e),P(y.$$.fragment,e),P(j.$$.fragment,e),P(q.$$.fragment,e),W=!0)},o(e){T(c.$$.fragment,e),T(A.$$.fragment,e),T(I.$$.fragment,e),T(C.$$.fragment,e),T(E.$$.fragment,e),T(y.$$.fragment,e),T(j.$$.fragment,e),T(q.$$.fragment,e),W=!1},d(e){e&&(o(w),o(s),o(p),o(a),o(g),o(B),o(M),o(H),o(X),o(S),o(_),o(Z),o(Q),o(O)),o(n),F(c,e),F(A,e),F(I,e),F(C),F(E),F(y),F(j),F(q,e)}}}const Pe='{"title":"AuraFlow","local":"auraflow","sections":[{"title":"AuraFlowPipeline","local":"diffusers.AuraFlowPipeline","sections":[],"depth":2}],"depth":1}';function Te(J){return ce(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Ee extends ue{constructor(n){super(),fe(this,n,Te,$e,me,{})}}export{Ee as component};