diffusers/v0.37.1/en/_app/immutable/nodes/116.daa014dc.js

import{s as Fe,o as He,n as Ze}from"../chunks/scheduler.53228c21.js";import{S as qe,i as Re,e as l,s as o,c as b,h as Ye,a as d,d as n,b as a,f as X,g as v,j as g,k as Q,l as r,m as s,n as w,t as y,o as x,p as T}from"../chunks/index.100fac89.js";import{C as ze}from"../chunks/CopyLLMTxtMenu.0b55cb5b.js";import{D as Te}from"../chunks/Docstring.30334b5e.js";import{C as Ee}from"../chunks/CodeBlock.d30a6509.js";import{E as Ae}from"../chunks/ExampleCodeBlock.b9320027.js";import{H as me,E as De}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.9588cb3a.js";function Ve(O){let c,k="Examples:",B,h,_;return h=new Ee({props:{code:"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",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> BriaPipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = BriaPipeline.from_pretrained(<span class="hljs-string">&quot;briaai/BRIA-3.2&quot;</span>, torch_dtype=torch.bfloat16)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-comment"># BRIA&#x27;s T5 text encoder is sensitive to precision. We need to cast it to bfloat16 and keep the final layer in float32.</span>

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.text_encoder = pipe.text_encoder.to(dtype=torch.bfloat16)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">for</span> block <span class="hljs-keyword">in</span> pipe.text_encoder.encoder.block:
<span class="hljs-meta">... </span>    block.layer[-<span class="hljs-number">1</span>].DenseReluDense.wo.to(dtype=torch.float32)
<span class="hljs-comment"># BRIA&#x27;s VAE is not supported in mixed precision, so we use float32.</span>

<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">if</span> pipe.vae.config.shift_factor == <span class="hljs-number">0</span>:
<span class="hljs-meta">... </span>    pipe.vae.to(dtype=torch.float32)

<span class="hljs-meta">&gt;&gt;&gt; </span>prompt = <span class="hljs-string">&quot;Photorealistic food photography of a stack of fluffy pancakes on a white plate, with maple syrup being poured over them. On top of the pancakes are the words &#x27;BRIA 3.2&#x27; in bold, yellow, 3D letters. The background is dark and out of focus.&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;bria.png&quot;</span>)`,wrap:!1}}),{c(){c=l("p"),c.textContent=k,B=o(),b(h.$$.fragment)},l(i){c=d(i,"P",{"data-svelte-h":!0}),g(c)!=="svelte-kvfsh7"&&(c.textContent=k),B=a(i),v(h.$$.fragment,i)},m(i,M){s(i,c,M),s(i,B,M),w(h,i,M),_=!0},p:Ze,i(i){_||(y(h.$$.fragment,i),_=!0)},o(i){x(h.$$.fragment,i),_=!1},d(i){i&&(n(c),n(B)),T(h,i)}}}function Se(O){let c,k,B,h,_,i,M,K,I,Me=`Bria 3.2 is the next-generation commercial-ready text-to-image model. With just 4 billion parameters, it provides exceptional aesthetics and text rendering, evaluated to provide on par results to leading open-source models, and outperforming other licensed models.
In addition to being built entirely on licensed data, 3.2 provides several advantages for enterprise and commercial use:`,ee,P,Be="<li>Efficient Compute - the model is X3 smaller than the equivalent models in the market (4B parameters vs 12B parameters other open source models)</li> <li>Architecture Consistency: Same architecture as 3.1—ideal for users looking to upgrade without disruption.</li> <li>Fine-tuning Speedup: 2x faster fine-tuning on L40S and A100.</li>",te,C,$e=`Original model checkpoints for Bria 3.2 can be found <a href="https://huggingface.co/briaai/BRIA-3.2" rel="nofollow">here</a>.
Github repo for Bria 3.2 can be found <a href="https://github.com/Bria-AI/BRIA-3.2" rel="nofollow">here</a>.`,ne,j,ke='If you want to learn more about the Bria platform, and get free traril access, please visit <a href="https://bria.ai" rel="nofollow">bria.ai</a>.',oe,G,ae,U,Ie='<em>As the model is gated, before using it with diffusers you first need to go to the <a href="https://huggingface.co/briaai/BRIA-3.2" rel="nofollow">Bria 3.2 Hugging Face page</a>, fill in the form and accept the gate. Once you are in, you need to login so that your system knows you’ve accepted the gate.</em>',se,J,Pe="Use the command below to log in:",ie,N,re,L,le,m,E,fe,R,Ce="Based on FluxPipeline with several changes:",ue,Y,je="<li>no pooled embeddings</li> <li>We use zero padding for prompts</li> <li>No guidance embedding since this is not a distilled version</li>",ge,p,F,he,z,Ge="Function invoked when calling the pipeline for generation.",_e,A,Ue=`&lt;&lt;&lt;&lt;&lt;&lt;&lt; HEAD
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.`,be,H,ve,D,Je=`Guidance scale as defined in <a href="https://huggingface.co/papers/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://huggingface.co/papers/2205.11487" 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.
negative_prompt (<code>str</code> or <code>list[str]</code>, <em>optional</em>):`,we,V,Ne=`<blockquote><blockquote><blockquote><blockquote><blockquote><blockquote><p>main
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>).
num_images_per_prompt (<code>int</code>, <em>optional</em>, defaults to 1):
The number of images to generate per prompt.
generator (<code>torch.Generator</code> or <code>list[torch.Generator]</code>, <em>optional</em>):
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.
latents (<code>torch.FloatTensor</code>, <em>optional</em>):
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 be generated by sampling using the supplied random <code>generator</code>.
prompt_embeds (<code>torch.FloatTensor</code>, <em>optional</em>):
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.
negative_prompt_embeds (<code>torch.FloatTensor</code>, <em>optional</em>):
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.
output_type (<code>str</code>, <em>optional</em>, defaults to <code>&quot;pil&quot;</code>):
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>.
return_dict (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>):
Whether or not to return a <code>~pipelines.bria.BriaPipelineOutput</code> instead of a plain tuple.
attention_kwargs (<code>dict</code>, <em>optional</em>):
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>.
callback_on_step_end (<code>Callable</code>, <em>optional</em>):
A function that calls at the end of each denoising steps during the inference. The function is
called with the following arguments: <code>callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)</code>. <code>callback_kwargs</code> will include a list of all tensors as
specified by <code>callback_on_step_end_tensor_inputs</code>.
callback_on_step_end_tensor_inputs (<code>list</code>, <em>optional</em>):
The list of tensor inputs for the <code>callback_on_step_end</code> function. The tensors specified in the
list will be passed as <code>callback_kwargs</code> argument. You will only be able to include variables
listed in the <code>._callback_tensor_inputs</code> attribute of your pipeline class.
max_sequence_length (<code>int</code> defaults to 256): Maximum sequence length to use with the <code>prompt</code>.</p></blockquote></blockquote></blockquote></blockquote></blockquote></blockquote>`,ye,$,xe,S,Z,de,q,pe,W,ce;return _=new ze({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),M=new me({props:{title:"Bria 3.2",local:"bria-32",headingTag:"h1"}}),G=new me({props:{title:"Usage",local:"usage",headingTag:"h2"}}),N=new Ee({props:{code:"aGYlMjBhdXRoJTIwbG9naW4=",highlighted:"hf auth login",wrap:!1}}),L=new me({props:{title:"BriaPipeline",local:"diffusers.BriaPipeline",headingTag:"h2"}}),E=new Te({props:{name:"class diffusers.BriaPipeline",anchor:"diffusers.BriaPipeline",parameters:[{name:"transformer",val:": BriaTransformer2DModel"},{name:"scheduler",val:": diffusers.schedulers.scheduling_flow_match_euler_discrete.FlowMatchEulerDiscreteScheduler | diffusers.schedulers.scheduling_utils.KarrasDiffusionSchedulers"},{name:"vae",val:": AutoencoderKL"},{name:"text_encoder",val:": T5EncoderModel"},{name:"tokenizer",val:": T5TokenizerFast"},{name:"image_encoder",val:": CLIPVisionModelWithProjection = None"},{name:"feature_extractor",val:": CLIPImageProcessor = None"}],parametersDescription:[{anchor:"diffusers.BriaPipeline.transformer",description:`<strong>transformer</strong> (<a href="/docs/diffusers/v0.37.1/en/api/models/bria_transformer#diffusers.BriaTransformer2DModel">BriaTransformer2DModel</a>) &#x2014;
Conditional Transformer (MMDiT) architecture to denoise the encoded image latents.`,name:"transformer"},{anchor:"diffusers.BriaPipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/v0.37.1/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"},{anchor:"diffusers.BriaPipeline.vae",description:`<strong>vae</strong> (<a href="/docs/diffusers/v0.37.1/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.BriaPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>T5EncoderModel</code>) &#x2014;
Frozen text-encoder. Bria uses
<a href="https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel" rel="nofollow">T5</a>, specifically the
<a href="https://huggingface.co/google/t5-v1_1-xxl" rel="nofollow">t5-v1_1-xxl</a> variant.`,name:"text_encoder"},{anchor:"diffusers.BriaPipeline.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"}],source:"https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/pipelines/bria/pipeline_bria.py#L89"}}),F=new Te({props:{name:"__call__",anchor:"diffusers.BriaPipeline.__call__",parameters:[{name:"prompt",val:": str | list[str] = None"},{name:"height",val:": int | None = None"},{name:"width",val:": int | None = None"},{name:"num_inference_steps",val:": int = 30"},{name:"timesteps",val:": list = None"},{name:"guidance_scale",val:": float = 5"},{name:"negative_prompt",val:": str | list[str] | None = None"},{name:"num_images_per_prompt",val:": int | None = 1"},{name:"generator",val:": torch._C.Generator | list[torch._C.Generator] | None = None"},{name:"latents",val:": torch.FloatTensor | None = None"},{name:"prompt_embeds",val:": torch.FloatTensor | None = None"},{name:"negative_prompt_embeds",val:": torch.FloatTensor | None = None"},{name:"output_type",val:": str | None = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"attention_kwargs",val:": dict[str, typing.Any] | None = None"},{name:"callback_on_step_end",val:": typing.Optional[typing.Callable[[int, int], NoneType]] = None"},{name:"callback_on_step_end_tensor_inputs",val:": list = ['latents']"},{name:"max_sequence_length",val:": int = 128"},{name:"clip_value",val:": None | float = None"},{name:"normalize",val:": bool = False"}],parametersDescription:[{anchor:"diffusers.BriaPipeline.__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.BriaPipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to self.unet.config.sample_size * self.vae_scale_factor) &#x2014;
The height in pixels of the generated image. This is set to 1024 by default for the best
results.`,name:"height"},{anchor:"diffusers.BriaPipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to self.unet.config.sample_size * self.vae_scale_factor) &#x2014;
The width in pixels of the generated image. This is set to 1024 by default for the best
results.`,name:"width"},{anchor:"diffusers.BriaPipeline.__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.BriaPipeline.__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.BriaPipeline.__call__.guidance_scale",description:"<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 5.0) &#x2014;",name:"guidance_scale"}],source:"https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/pipelines/bria/pipeline_bria.py#L448",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~pipelines.bria.BriaPipelineOutput</code> if
<code>return_dict</code> is True, otherwise a <code>tuple</code>. When returning a tuple, the first element is a list
with the generated images.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~pipelines.bria.BriaPipelineOutput</code> or <code>tuple</code></p>
`}}),H=new me({props:{title:"negative_prompt ( str or list[str] , optional ):",local:"negativeprompt--str-or-liststr--optional-",headingTag:"h1"}}),$=new Ae({props:{anchor:"diffusers.BriaPipeline.__call__.example",$$slots:{default:[Ve]},$$scope:{ctx:O}}}),Z=new Te({props:{name:"encode_prompt",anchor:"diffusers.BriaPipeline.encode_prompt",parameters:[{name:"prompt",val:": str | list[str]"},{name:"device",val:": torch.device | None = None"},{name:"num_images_per_prompt",val:": int = 1"},{name:"do_classifier_free_guidance",val:": bool = True"},{name:"negative_prompt",val:": str | list[str] | None = None"},{name:"prompt_embeds",val:": torch.FloatTensor | None = None"},{name:"negative_prompt_embeds",val:": torch.FloatTensor | None = None"},{name:"max_sequence_length",val:": int = 128"},{name:"lora_scale",val:": float | None = None"}],parametersDescription:[{anchor:"diffusers.BriaPipeline.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.BriaPipeline.encode_prompt.device",description:`<strong>device</strong> &#x2014; (<code>torch.device</code>):
torch device`,name:"device"},{anchor:"diffusers.BriaPipeline.encode_prompt.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>) &#x2014;
number of images that should be generated per prompt`,name:"num_images_per_prompt"},{anchor:"diffusers.BriaPipeline.encode_prompt.do_classifier_free_guidance",description:`<strong>do_classifier_free_guidance</strong> (<code>bool</code>) &#x2014;
whether to use classifier free guidance or not`,name:"do_classifier_free_guidance"},{anchor:"diffusers.BriaPipeline.encode_prompt.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.BriaPipeline.encode_prompt.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.BriaPipeline.encode_prompt.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"}],source:"https://github.com/huggingface/diffusers/blob/v0.37.1/src/diffusers/pipelines/bria/pipeline_bria.py#L146"}}),q=new De({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/bria_3_2.md"}}),{c(){c=l("meta"),k=o(),B=l("p"),h=o(),b(_.$$.fragment),i=o(),b(M.$$.fragment),K=o(),I=l("p"),I.textContent=Me,ee=o(),P=l("ul"),P.innerHTML=Be,te=o(),C=l("p"),C.innerHTML=$e,ne=o(),j=l("p"),j.innerHTML=ke,oe=o(),b(G.$$.fragment),ae=o(),U=l("p"),U.innerHTML=Ie,se=o(),J=l("p"),J.textContent=Pe,ie=o(),b(N.$$.fragment),re=o(),b(L.$$.fragment),le=o(),m=l("div"),b(E.$$.fragment),fe=o(),R=l("p"),R.textContent=Ce,ue=o(),Y=l("ul"),Y.innerHTML=je,ge=o(),p=l("div"),b(F.$$.fragment),he=o(),z=l("p"),z.textContent=Ge,_e=o(),A=l("p"),A.innerHTML=Ue,be=o(),b(H.$$.fragment),ve=o(),D=l("p"),D.innerHTML=Je,we=o(),V=l("blockquote"),V.innerHTML=Ne,ye=o(),b($.$$.fragment),xe=o(),S=l("div"),b(Z.$$.fragment),de=o(),b(q.$$.fragment),pe=o(),W=l("p"),this.h()},l(e){const t=Ye("svelte-u9bgzb",document.head);c=d(t,"META",{name:!0,content:!0}),t.forEach(n),k=a(e),B=d(e,"P",{}),X(B).forEach(n),h=a(e),v(_.$$.fragment,e),i=a(e),v(M.$$.fragment,e),K=a(e),I=d(e,"P",{"data-svelte-h":!0}),g(I)!=="svelte-1fachwa"&&(I.textContent=Me),ee=a(e),P=d(e,"UL",{"data-svelte-h":!0}),g(P)!=="svelte-1txl75c"&&(P.innerHTML=Be),te=a(e),C=d(e,"P",{"data-svelte-h":!0}),g(C)!=="svelte-1pirafh"&&(C.innerHTML=$e),ne=a(e),j=d(e,"P",{"data-svelte-h":!0}),g(j)!=="svelte-m9lr6p"&&(j.innerHTML=ke),oe=a(e),v(G.$$.fragment,e),ae=a(e),U=d(e,"P",{"data-svelte-h":!0}),g(U)!=="svelte-xrh9ni"&&(U.innerHTML=Ie),se=a(e),J=d(e,"P",{"data-svelte-h":!0}),g(J)!=="svelte-12sg8l0"&&(J.textContent=Pe),ie=a(e),v(N.$$.fragment,e),re=a(e),v(L.$$.fragment,e),le=a(e),m=d(e,"DIV",{class:!0});var u=X(m);v(E.$$.fragment,u),fe=a(u),R=d(u,"P",{"data-svelte-h":!0}),g(R)!=="svelte-18cwt80"&&(R.textContent=Ce),ue=a(u),Y=d(u,"UL",{"data-svelte-h":!0}),g(Y)!=="svelte-ubdgrr"&&(Y.innerHTML=je),ge=a(u),p=d(u,"DIV",{class:!0});var f=X(p);v(F.$$.fragment,f),he=a(f),z=d(f,"P",{"data-svelte-h":!0}),g(z)!=="svelte-v78lg8"&&(z.textContent=Ge),_e=a(f),A=d(f,"P",{"data-svelte-h":!0}),g(A)!=="svelte-8vsdxl"&&(A.innerHTML=Ue),be=a(f),v(H.$$.fragment,f),ve=a(f),D=d(f,"P",{"data-svelte-h":!0}),g(D)!=="svelte-9z0zma"&&(D.innerHTML=Je),we=a(f),V=d(f,"BLOCKQUOTE",{"data-svelte-h":!0}),g(V)!=="svelte-14k9vc8"&&(V.innerHTML=Ne),ye=a(f),v($.$$.fragment,f),f.forEach(n),xe=a(u),S=d(u,"DIV",{class:!0});var Le=X(S);v(Z.$$.fragment,Le),Le.forEach(n),u.forEach(n),de=a(e),v(q.$$.fragment,e),pe=a(e),W=d(e,"P",{}),X(W).forEach(n),this.h()},h(){Q(c,"name","hf:doc:metadata"),Q(c,"content",We),Q(p,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),Q(S,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),Q(m,"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){r(document.head,c),s(e,k,t),s(e,B,t),s(e,h,t),w(_,e,t),s(e,i,t),w(M,e,t),s(e,K,t),s(e,I,t),s(e,ee,t),s(e,P,t),s(e,te,t),s(e,C,t),s(e,ne,t),s(e,j,t),s(e,oe,t),w(G,e,t),s(e,ae,t),s(e,U,t),s(e,se,t),s(e,J,t),s(e,ie,t),w(N,e,t),s(e,re,t),w(L,e,t),s(e,le,t),s(e,m,t),w(E,m,null),r(m,fe),r(m,R),r(m,ue),r(m,Y),r(m,ge),r(m,p),w(F,p,null),r(p,he),r(p,z),r(p,_e),r(p,A),r(p,be),w(H,p,null),r(p,ve),r(p,D),r(p,we),r(p,V),r(p,ye),w($,p,null),r(m,xe),r(m,S),w(Z,S,null),s(e,de,t),w(q,e,t),s(e,pe,t),s(e,W,t),ce=!0},p(e,[t]){const u={};t&2&&(u.$$scope={dirty:t,ctx:e}),$.$set(u)},i(e){ce||(y(_.$$.fragment,e),y(M.$$.fragment,e),y(G.$$.fragment,e),y(N.$$.fragment,e),y(L.$$.fragment,e),y(E.$$.fragment,e),y(F.$$.fragment,e),y(H.$$.fragment,e),y($.$$.fragment,e),y(Z.$$.fragment,e),y(q.$$.fragment,e),ce=!0)},o(e){x(_.$$.fragment,e),x(M.$$.fragment,e),x(G.$$.fragment,e),x(N.$$.fragment,e),x(L.$$.fragment,e),x(E.$$.fragment,e),x(F.$$.fragment,e),x(H.$$.fragment,e),x($.$$.fragment,e),x(Z.$$.fragment,e),x(q.$$.fragment,e),ce=!1},d(e){e&&(n(k),n(B),n(h),n(i),n(K),n(I),n(ee),n(P),n(te),n(C),n(ne),n(j),n(oe),n(ae),n(U),n(se),n(J),n(ie),n(re),n(le),n(m),n(de),n(pe),n(W)),n(c),T(_,e),T(M,e),T(G,e),T(N,e),T(L,e),T(E),T(F),T(H),T($),T(Z),T(q,e)}}}const We='{"title":"Bria 3.2","local":"bria-32","sections":[{"title":"Usage","local":"usage","sections":[],"depth":2},{"title":"BriaPipeline","local":"diffusers.BriaPipeline","sections":[],"depth":2}],"depth":1}';function Xe(O){return He(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class at extends qe{constructor(c){super(),Re(this,c,Xe,Se,Fe,{})}}export{at as component};