diffusers/pr_13743/en/_app/immutable/nodes/175.ea078f0f.js

import{s as xe,o as Ne,n as Me}from"../chunks/scheduler.53228c21.js";import{S as Ie,i as Ee,e as p,s,c as b,h as $e,a as m,d as n,b as a,f as S,g as v,j as T,k as G,l,m as r,n as x,t as N,o as M,p as I}from"../chunks/index.100fac89.js";import{D as oe}from"../chunks/Docstring.d920a7a5.js";import{C as we}from"../chunks/CodeBlock.0adb3827.js";import{E as Pe}from"../chunks/ExampleCodeBlock.2d05959e.js";import{H as de,E as Te}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.afd26599.js";function ke(Z){let i,k="Examples:",f,u,g;return u=new we({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> NucleusMoEImagePipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = NucleusMoEImagePipeline.from_pretrained(<span class="hljs-string">&quot;NucleusAI/NucleusMoE-Image&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-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, num_inference_steps=<span class="hljs-number">50</span>).images[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;nucleus_moe.png&quot;</span>)`,lang:"py",wrap:!1}}),{c(){i=p("p"),i.textContent=k,f=s(),b(u.$$.fragment)},l(o){i=m(o,"P",{"data-svelte-h":!0}),T(i)!=="svelte-kvfsh7"&&(i.textContent=k),f=a(o),v(u.$$.fragment,o)},m(o,_){r(o,i,_),r(o,f,_),x(u,o,_),g=!0},p:Me,i(o){g||(N(u.$$.fragment,o),g=!0)},o(o){M(u.$$.fragment,o),g=!1},d(o){o&&(n(i),n(f)),I(u,o)}}}function ye(Z){let i,k,f,u,g,o,_,ue='<a href="https://huggingface.co/NucleusAI/NucleusMoE-Image" rel="nofollow">NucleusMoE-Image</a> is a text-to-image model that pairs a single-stream DiT with Mixture-of-Experts feed-forward layers, cross-attention to a Qwen3-VL text encoder, and a flow-matching Euler discrete scheduler.',F,$,ge='<p>Make sure to check out the Schedulers <a href="../../using-diffusers/schedulers">guide</a> to learn how to explore the tradeoff between scheduler speed and quality, and see the <a href="../../using-diffusers/loading#reuse-a-pipeline">reuse components across pipelines</a> section to learn how to efficiently load the same components into multiple pipelines.</p>',H,y,z,c,C,se,J,_e="Pipeline for text-to-image generation using NucleusMoE.",ae,D,fe=`This pipeline uses a single-stream DiT with Mixture-of-Experts feed-forward layers, cross-attention to a Qwen3-VL
text encoder, and a flow-matching Euler discrete scheduler.`,re,h,q,ie,Q,he="Function invoked when calling the pipeline for generation.",le,w,ce,P,j,pe,A,be="Encode text prompt(s) into embeddings using the Qwen3-VL text encoder.",Y,V,K,E,L,me,O,ve="Output class for NucleusMoE Image pipelines.",R,U,X,W,ee;return g=new de({props:{title:"NucleusMoE-Image",local:"nucleusmoe-image",headingTag:"h1"}}),y=new de({props:{title:"NucleusMoEImagePipeline",local:"diffusers.NucleusMoEImagePipeline",headingTag:"h2"}}),C=new oe({props:{name:"class diffusers.NucleusMoEImagePipeline",anchor:"diffusers.NucleusMoEImagePipeline",parameters:[{name:"transformer",val:": NucleusMoEImageTransformer2DModel"},{name:"scheduler",val:": FlowMatchEulerDiscreteScheduler"},{name:"vae",val:": AutoencoderKLQwenImage"},{name:"text_encoder",val:": Qwen3VLForConditionalGeneration"},{name:"processor",val:": Qwen3VLProcessor"}],parametersDescription:[{anchor:"diffusers.NucleusMoEImagePipeline.transformer",description:`<strong>transformer</strong> (<code>NucleusMoEImageTransformer2DModel</code>) &#x2014;
Conditional Transformer (MMDiT) architecture to denoise the encoded image latents.`,name:"transformer"},{anchor:"diffusers.NucleusMoEImagePipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/pr_13743/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.NucleusMoEImagePipeline.vae",description:`<strong>vae</strong> (<a href="/docs/diffusers/pr_13743/en/api/models/autoencoderkl_qwenimage#diffusers.AutoencoderKLQwenImage">AutoencoderKLQwenImage</a>) &#x2014;
Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.`,name:"vae"},{anchor:"diffusers.NucleusMoEImagePipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>Qwen3VLForConditionalGeneration</code>) &#x2014;
Text encoder for computing prompt embeddings.`,name:"text_encoder"},{anchor:"diffusers.NucleusMoEImagePipeline.processor",description:`<strong>processor</strong> (<code>Qwen3VLProcessor</code>) &#x2014;
Processor for tokenizing text inputs.`,name:"processor"}],source:"https://github.com/huggingface/diffusers/blob/vr_13743/src/diffusers/pipelines/nucleusmoe_image/pipeline_nucleusmoe_image.py#L132"}}),q=new oe({props:{name:"__call__",anchor:"diffusers.NucleusMoEImagePipeline.__call__",parameters:[{name:"prompt",val:": str | list[str] = None"},{name:"negative_prompt",val:": str | list[str] = None"},{name:"guidance_scale",val:": float = 4.0"},{name:"height",val:": int | None = None"},{name:"width",val:": int | None = None"},{name:"num_inference_steps",val:": int = 50"},{name:"sigmas",val:": list[float] | None = None"},{name:"num_images_per_prompt",val:": int = 1"},{name:"max_sequence_length",val:": int | None = None"},{name:"return_index",val:": int | None = None"},{name:"generator",val:": torch._C.Generator | list[torch._C.Generator] | None = None"},{name:"latents",val:": torch.Tensor | None = None"},{name:"prompt_embeds",val:": torch.Tensor | None = None"},{name:"prompt_embeds_mask",val:": torch.Tensor | None = None"},{name:"negative_prompt_embeds",val:": torch.Tensor | None = None"},{name:"negative_prompt_embeds_mask",val:": torch.Tensor | 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, dict], NoneType]] = None"},{name:"callback_on_step_end_tensor_inputs",val:": list = ['latents']"}],parametersDescription:[{anchor:"diffusers.NucleusMoEImagePipeline.__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>.`,name:"prompt"},{anchor:"diffusers.NucleusMoEImagePipeline.__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, an empty string is used when
<code>true_cfg_scale &gt; 1</code>.`,name:"negative_prompt"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.true_cfg_scale",description:`<strong>true_cfg_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 4.0) &#x2014;
Classifier-free guidance scale. Values greater than 1 enable CFG.`,name:"true_cfg_scale"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to <code>self.default_sample_size * self.vae_scale_factor</code>) &#x2014;
The height in pixels of the generated image.`,name:"height"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to <code>self.default_sample_size * self.vae_scale_factor</code>) &#x2014;
The width in pixels of the generated image.`,name:"width"},{anchor:"diffusers.NucleusMoEImagePipeline.__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.`,name:"num_inference_steps"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.sigmas",description:`<strong>sigmas</strong> (<code>list[float]</code>, <em>optional</em>) &#x2014;
Custom sigmas for the denoising schedule. If not defined, a linear schedule is used.`,name:"sigmas"},{anchor:"diffusers.NucleusMoEImagePipeline.__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.NucleusMoEImagePipeline.__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 torch generators to make generation deterministic.`,name:"generator"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated noisy latents to be used as inputs for image generation.`,name:"latents"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings.`,name:"prompt_embeds"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.prompt_embeds_mask",description:`<strong>prompt_embeds_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Attention mask for pre-generated text embeddings.`,name:"prompt_embeds_mask"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.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.NucleusMoEImagePipeline.__call__.negative_prompt_embeds_mask",description:`<strong>negative_prompt_embeds_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Attention mask for pre-generated negative text embeddings.`,name:"negative_prompt_embeds_mask"},{anchor:"diffusers.NucleusMoEImagePipeline.__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 generated image. Choose between <code>&quot;pil&quot;</code>, <code>&quot;np&quot;</code>, or <code>&quot;latent&quot;</code>.`,name:"output_type"},{anchor:"diffusers.NucleusMoEImagePipeline.__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>NucleusMoEImagePipelineOutput</code> instead of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.attention_kwargs",description:`<strong>attention_kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
Kwargs passed to the attention processor.`,name:"attention_kwargs"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.callback_on_step_end",description:`<strong>callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
A function called at the end of each denoising step.`,name:"callback_on_step_end"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.callback_on_step_end_tensor_inputs",description:`<strong>callback_on_step_end_tensor_inputs</strong> (<code>list</code>, <em>optional</em>) &#x2014;
Tensor inputs for the <code>callback_on_step_end</code> function.`,name:"callback_on_step_end_tensor_inputs"},{anchor:"diffusers.NucleusMoEImagePipeline.__call__.max_sequence_length",description:`<strong>max_sequence_length</strong> (<code>int</code>, defaults to 512) &#x2014;
Maximum sequence length for the text prompt.`,name:"max_sequence_length"}],source:"https://github.com/huggingface/diffusers/blob/vr_13743/src/diffusers/pipelines/nucleusmoe_image/pipeline_nucleusmoe_image.py#L379",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


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


<p><code>NucleusMoEImagePipelineOutput</code> or <code>tuple</code></p>
`}}),w=new Pe({props:{anchor:"diffusers.NucleusMoEImagePipeline.__call__.example",$$slots:{default:[ke]},$$scope:{ctx:Z}}}),j=new oe({props:{name:"encode_prompt",anchor:"diffusers.NucleusMoEImagePipeline.encode_prompt",parameters:[{name:"prompt",val:": str | list[str] = None"},{name:"device",val:": torch.device | None = None"},{name:"num_images_per_prompt",val:": int = 1"},{name:"prompt_embeds",val:": torch.Tensor | None = None"},{name:"prompt_embeds_mask",val:": torch.Tensor | None = None"},{name:"max_sequence_length",val:": int | None = None"},{name:"return_index",val:": int | None = None"}],parametersDescription:[{anchor:"diffusers.NucleusMoEImagePipeline.encode_prompt.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>list[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to encode.`,name:"prompt"},{anchor:"diffusers.NucleusMoEImagePipeline.encode_prompt.device",description:`<strong>device</strong> (<code>torch.device</code>, <em>optional</em>) &#x2014;
Torch device for the resulting tensors.`,name:"device"},{anchor:"diffusers.NucleusMoEImagePipeline.encode_prompt.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, defaults to 1) &#x2014;
Number of images to generate per prompt.`,name:"num_images_per_prompt"},{anchor:"diffusers.NucleusMoEImagePipeline.encode_prompt.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. Skips encoding when provided.`,name:"prompt_embeds"},{anchor:"diffusers.NucleusMoEImagePipeline.encode_prompt.prompt_embeds_mask",description:`<strong>prompt_embeds_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Attention mask for pre-generated embeddings.`,name:"prompt_embeds_mask"},{anchor:"diffusers.NucleusMoEImagePipeline.encode_prompt.max_sequence_length",description:`<strong>max_sequence_length</strong> (<code>int</code>, defaults to 1024) &#x2014;
Maximum token length for the encoded prompt.`,name:"max_sequence_length"}],source:"https://github.com/huggingface/diffusers/blob/vr_13743/src/diffusers/pipelines/nucleusmoe_image/pipeline_nucleusmoe_image.py#L187"}}),V=new de({props:{title:"NucleusMoEImagePipelineOutput",local:"diffusers.pipelines.nucleusmoe_image.pipeline_output.NucleusMoEImagePipelineOutput",headingTag:"h2"}}),L=new oe({props:{name:"class diffusers.pipelines.nucleusmoe_image.pipeline_output.NucleusMoEImagePipelineOutput",anchor:"diffusers.pipelines.nucleusmoe_image.pipeline_output.NucleusMoEImagePipelineOutput",parameters:[{name:"images",val:": list[PIL.Image.Image] | numpy.ndarray"}],parametersDescription:[{anchor:"diffusers.pipelines.nucleusmoe_image.pipeline_output.NucleusMoEImagePipelineOutput.images",description:`<strong>images</strong> (<code>list[PIL.Image.Image]</code> or <code>np.ndarray</code>) &#x2014;
List of denoised PIL images of length <code>batch_size</code> or numpy array of shape <code>(batch_size, height, width, num_channels)</code>. PIL images or numpy array present the denoised images of the diffusion pipeline.`,name:"images"}],source:"https://github.com/huggingface/diffusers/blob/vr_13743/src/diffusers/pipelines/nucleusmoe_image/pipeline_output.py#L10"}}),U=new Te({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/nucleusmoe_image.md"}}),{c(){i=p("meta"),k=s(),f=p("p"),u=s(),b(g.$$.fragment),o=s(),_=p("p"),_.innerHTML=ue,F=s(),$=p("blockquote"),$.innerHTML=ge,H=s(),b(y.$$.fragment),z=s(),c=p("div"),b(C.$$.fragment),se=s(),J=p("p"),J.textContent=_e,ae=s(),D=p("p"),D.textContent=fe,re=s(),h=p("div"),b(q.$$.fragment),ie=s(),Q=p("p"),Q.textContent=he,le=s(),b(w.$$.fragment),ce=s(),P=p("div"),b(j.$$.fragment),pe=s(),A=p("p"),A.textContent=be,Y=s(),b(V.$$.fragment),K=s(),E=p("div"),b(L.$$.fragment),me=s(),O=p("p"),O.textContent=ve,R=s(),b(U.$$.fragment),X=s(),W=p("p"),this.h()},l(e){const t=$e("svelte-u9bgzb",document.head);i=m(t,"META",{name:!0,content:!0}),t.forEach(n),k=a(e),f=m(e,"P",{}),S(f).forEach(n),u=a(e),v(g.$$.fragment,e),o=a(e),_=m(e,"P",{"data-svelte-h":!0}),T(_)!=="svelte-o5eiol"&&(_.innerHTML=ue),F=a(e),$=m(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),T($)!=="svelte-r1jcqf"&&($.innerHTML=ge),H=a(e),v(y.$$.fragment,e),z=a(e),c=m(e,"DIV",{class:!0});var d=S(c);v(C.$$.fragment,d),se=a(d),J=m(d,"P",{"data-svelte-h":!0}),T(J)!=="svelte-bqcdeu"&&(J.textContent=_e),ae=a(d),D=m(d,"P",{"data-svelte-h":!0}),T(D)!=="svelte-1y6qedp"&&(D.textContent=fe),re=a(d),h=m(d,"DIV",{class:!0});var B=S(h);v(q.$$.fragment,B),ie=a(B),Q=m(B,"P",{"data-svelte-h":!0}),T(Q)!=="svelte-v78lg8"&&(Q.textContent=he),le=a(B),v(w.$$.fragment,B),B.forEach(n),ce=a(d),P=m(d,"DIV",{class:!0});var te=S(P);v(j.$$.fragment,te),pe=a(te),A=m(te,"P",{"data-svelte-h":!0}),T(A)!=="svelte-13p179q"&&(A.textContent=be),te.forEach(n),d.forEach(n),Y=a(e),v(V.$$.fragment,e),K=a(e),E=m(e,"DIV",{class:!0});var ne=S(E);v(L.$$.fragment,ne),me=a(ne),O=m(ne,"P",{"data-svelte-h":!0}),T(O)!=="svelte-10afgv6"&&(O.textContent=ve),ne.forEach(n),R=a(e),v(U.$$.fragment,e),X=a(e),W=m(e,"P",{}),S(W).forEach(n),this.h()},h(){G(i,"name","hf:doc:metadata"),G(i,"content",Ce),G($,"class","tip"),G(h,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),G(P,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),G(c,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),G(E,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(e,t){l(document.head,i),r(e,k,t),r(e,f,t),r(e,u,t),x(g,e,t),r(e,o,t),r(e,_,t),r(e,F,t),r(e,$,t),r(e,H,t),x(y,e,t),r(e,z,t),r(e,c,t),x(C,c,null),l(c,se),l(c,J),l(c,ae),l(c,D),l(c,re),l(c,h),x(q,h,null),l(h,ie),l(h,Q),l(h,le),x(w,h,null),l(c,ce),l(c,P),x(j,P,null),l(P,pe),l(P,A),r(e,Y,t),x(V,e,t),r(e,K,t),r(e,E,t),x(L,E,null),l(E,me),l(E,O),r(e,R,t),x(U,e,t),r(e,X,t),r(e,W,t),ee=!0},p(e,[t]){const d={};t&2&&(d.$$scope={dirty:t,ctx:e}),w.$set(d)},i(e){ee||(N(g.$$.fragment,e),N(y.$$.fragment,e),N(C.$$.fragment,e),N(q.$$.fragment,e),N(w.$$.fragment,e),N(j.$$.fragment,e),N(V.$$.fragment,e),N(L.$$.fragment,e),N(U.$$.fragment,e),ee=!0)},o(e){M(g.$$.fragment,e),M(y.$$.fragment,e),M(C.$$.fragment,e),M(q.$$.fragment,e),M(w.$$.fragment,e),M(j.$$.fragment,e),M(V.$$.fragment,e),M(L.$$.fragment,e),M(U.$$.fragment,e),ee=!1},d(e){e&&(n(k),n(f),n(u),n(o),n(_),n(F),n($),n(H),n(z),n(c),n(Y),n(K),n(E),n(R),n(X),n(W)),n(i),I(g,e),I(y,e),I(C),I(q),I(w),I(j),I(V,e),I(L),I(U,e)}}}const Ce='{"title":"NucleusMoE-Image","local":"nucleusmoe-image","sections":[{"title":"NucleusMoEImagePipeline","local":"diffusers.NucleusMoEImagePipeline","sections":[],"depth":2},{"title":"NucleusMoEImagePipelineOutput","local":"diffusers.pipelines.nucleusmoe_image.pipeline_output.NucleusMoEImagePipelineOutput","sections":[],"depth":2}],"depth":1}';function qe(Z){return Ne(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class De extends Ie{constructor(i){super(),Ee(this,i,qe,ye,xe,{})}}export{De as component};