diffusers/main/en/_app/immutable/nodes/50.41480d63.js

import{s as Vt,o as Nt,n as F}from"../chunks/scheduler.8c3d61f6.js";import{S as Rt,i as Ft,g as p,s as r,r as h,A as Lt,h as m,f as o,c as l,j as M,u as _,x as I,k as $,y as d,a as c,v as b,d as y,t as v,w}from"../chunks/index.da70eac4.js";import{T as xt}from"../chunks/Tip.1d9b8c37.js";import{D as Z}from"../chunks/Docstring.ee4b6913.js";import{C as Ge}from"../chunks/CodeBlock.00a903b3.js";import{E as Ae}from"../chunks/ExampleCodeBlock.f7bd2c1f.js";import{H as Xt,E as St}from"../chunks/EditOnGithub.1e64e623.js";function Qt(x){let n,u="Examples:",a,s,f;return s=new Ge({props:{code:"aW1wb3J0JTIwdG9yY2glMEFmcm9tJTIwZGlmZnVzZXJzJTIwaW1wb3J0JTIwQW11c2VkUGlwZWxpbmUlMEElMEFwaXBlJTIwJTNEJTIwQW11c2VkUGlwZWxpbmUuZnJvbV9wcmV0cmFpbmVkKCUyMmFtdXNlZCUyRmFtdXNlZC01MTIlMjIlMkMlMjB2YXJpYW50JTNEJTIyZnAxNiUyMiUyQyUyMHRvcmNoX2R0eXBlJTNEdG9yY2guZmxvYXQxNiklMEFwaXBlJTIwJTNEJTIwcGlwZS50byglMjJjdWRhJTIyKSUwQSUwQXByb21wdCUyMCUzRCUyMCUyMmElMjBwaG90byUyMG9mJTIwYW4lMjBhc3Ryb25hdXQlMjByaWRpbmclMjBhJTIwaG9yc2UlMjBvbiUyMG1hcnMlMjIlMEFpbWFnZSUyMCUzRCUyMHBpcGUocHJvbXB0KS5pbWFnZXMlNUIwJTVE",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> AmusedPipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = AmusedPipeline.from_pretrained(<span class="hljs-string">&quot;amused/amused-512&quot;</span>, variant=<span class="hljs-string">&quot;fp16&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 photo of an astronaut riding a horse on mars&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>image = pipe(prompt).images[<span class="hljs-number">0</span>]`,wrap:!1}}),{c(){n=p("p"),n.textContent=u,a=r(),h(s.$$.fragment)},l(t){n=m(t,"P",{"data-svelte-h":!0}),I(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=l(t),_(s.$$.fragment,t)},m(t,g){c(t,n,g),c(t,a,g),b(s,t,g),f=!0},p:F,i(t){f||(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(o(n),o(a)),w(s,t)}}}function qt(x){let n,u=`⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes
precedent.`;return{c(){n=p("p"),n.textContent=u},l(a){n=m(a,"P",{"data-svelte-h":!0}),I(n)!=="svelte-17p1lpg"&&(n.textContent=u)},m(a,s){c(a,n,s)},p:F,d(a){a&&o(n)}}}function zt(x){let n,u="Examples:",a,s,f;return s=new Ge({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> DiffusionPipeline
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> xformers.ops <span class="hljs-keyword">import</span> MemoryEfficientAttentionFlashAttentionOp

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;stabilityai/stable-diffusion-2-1&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>pipe.enable_xformers_memory_efficient_attention(attention_op=MemoryEfficientAttentionFlashAttentionOp)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Workaround for not accepting attention shape using VAE for Flash Attention</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.vae.enable_xformers_memory_efficient_attention(attention_op=<span class="hljs-literal">None</span>)`,wrap:!1}}),{c(){n=p("p"),n.textContent=u,a=r(),h(s.$$.fragment)},l(t){n=m(t,"P",{"data-svelte-h":!0}),I(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=l(t),_(s.$$.fragment,t)},m(t,g){c(t,n,g),c(t,a,g),b(s,t,g),f=!0},p:F,i(t){f||(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(o(n),o(a)),w(s,t)}}}function Ht(x){let n,u="Examples:",a,s,f;return s=new Ge({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> AmusedImg2ImgPipeline
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = AmusedImg2ImgPipeline.from_pretrained(
<span class="hljs-meta">... </span>    <span class="hljs-string">&quot;amused/amused-512&quot;</span>, variant=<span class="hljs-string">&quot;fp16&quot;</span>, torch_dtype=torch.float16
<span class="hljs-meta">... </span>)
<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;winter mountains&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>input_image = (
<span class="hljs-meta">... </span>    load_image(
<span class="hljs-meta">... </span>        <span class="hljs-string">&quot;https://huggingface.co/datasets/diffusers/docs-images/resolve/main/open_muse/mountains.jpg&quot;</span>
<span class="hljs-meta">... </span>    )
<span class="hljs-meta">... </span>    .resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))
<span class="hljs-meta">... </span>    .convert(<span class="hljs-string">&quot;RGB&quot;</span>)
<span class="hljs-meta">... </span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>image = pipe(prompt, input_image).images[<span class="hljs-number">0</span>]`,wrap:!1}}),{c(){n=p("p"),n.textContent=u,a=r(),h(s.$$.fragment)},l(t){n=m(t,"P",{"data-svelte-h":!0}),I(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=l(t),_(s.$$.fragment,t)},m(t,g){c(t,n,g),c(t,a,g),b(s,t,g),f=!0},p:F,i(t){f||(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(o(n),o(a)),w(s,t)}}}function Yt(x){let n,u=`⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes
precedent.`;return{c(){n=p("p"),n.textContent=u},l(a){n=m(a,"P",{"data-svelte-h":!0}),I(n)!=="svelte-17p1lpg"&&(n.textContent=u)},m(a,s){c(a,n,s)},p:F,d(a){a&&o(n)}}}function Ot(x){let n,u="Examples:",a,s,f;return s=new Ge({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> DiffusionPipeline
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> xformers.ops <span class="hljs-keyword">import</span> MemoryEfficientAttentionFlashAttentionOp

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;stabilityai/stable-diffusion-2-1&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>pipe.enable_xformers_memory_efficient_attention(attention_op=MemoryEfficientAttentionFlashAttentionOp)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Workaround for not accepting attention shape using VAE for Flash Attention</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.vae.enable_xformers_memory_efficient_attention(attention_op=<span class="hljs-literal">None</span>)`,wrap:!1}}),{c(){n=p("p"),n.textContent=u,a=r(),h(s.$$.fragment)},l(t){n=m(t,"P",{"data-svelte-h":!0}),I(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=l(t),_(s.$$.fragment,t)},m(t,g){c(t,n,g),c(t,a,g),b(s,t,g),f=!0},p:F,i(t){f||(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(o(n),o(a)),w(s,t)}}}function Dt(x){let n,u="Examples:",a,s,f;return s=new Ge({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> AmusedInpaintPipeline
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = AmusedInpaintPipeline.from_pretrained(
<span class="hljs-meta">... </span>    <span class="hljs-string">&quot;amused/amused-512&quot;</span>, variant=<span class="hljs-string">&quot;fp16&quot;</span>, torch_dtype=torch.float16
<span class="hljs-meta">... </span>)
<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;fall mountains&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>input_image = (
<span class="hljs-meta">... </span>    load_image(
<span class="hljs-meta">... </span>        <span class="hljs-string">&quot;https://huggingface.co/datasets/diffusers/docs-images/resolve/main/open_muse/mountains_1.jpg&quot;</span>
<span class="hljs-meta">... </span>    )
<span class="hljs-meta">... </span>    .resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))
<span class="hljs-meta">... </span>    .convert(<span class="hljs-string">&quot;RGB&quot;</span>)
<span class="hljs-meta">... </span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>mask = (
<span class="hljs-meta">... </span>    load_image(
<span class="hljs-meta">... </span>        <span class="hljs-string">&quot;https://huggingface.co/datasets/diffusers/docs-images/resolve/main/open_muse/mountains_1_mask.png&quot;</span>
<span class="hljs-meta">... </span>    )
<span class="hljs-meta">... </span>    .resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))
<span class="hljs-meta">... </span>    .convert(<span class="hljs-string">&quot;L&quot;</span>)
<span class="hljs-meta">... </span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe(prompt, input_image, mask).images[<span class="hljs-number">0</span>].save(<span class="hljs-string">&quot;out.png&quot;</span>)`,wrap:!1}}),{c(){n=p("p"),n.textContent=u,a=r(),h(s.$$.fragment)},l(t){n=m(t,"P",{"data-svelte-h":!0}),I(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=l(t),_(s.$$.fragment,t)},m(t,g){c(t,n,g),c(t,a,g),b(s,t,g),f=!0},p:F,i(t){f||(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(o(n),o(a)),w(s,t)}}}function Kt(x){let n,u=`⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes
precedent.`;return{c(){n=p("p"),n.textContent=u},l(a){n=m(a,"P",{"data-svelte-h":!0}),I(n)!=="svelte-17p1lpg"&&(n.textContent=u)},m(a,s){c(a,n,s)},p:F,d(a){a&&o(n)}}}function en(x){let n,u="Examples:",a,s,f;return s=new Ge({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> DiffusionPipeline
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> xformers.ops <span class="hljs-keyword">import</span> MemoryEfficientAttentionFlashAttentionOp

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = DiffusionPipeline.from_pretrained(<span class="hljs-string">&quot;stabilityai/stable-diffusion-2-1&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>pipe.enable_xformers_memory_efficient_attention(attention_op=MemoryEfficientAttentionFlashAttentionOp)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Workaround for not accepting attention shape using VAE for Flash Attention</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.vae.enable_xformers_memory_efficient_attention(attention_op=<span class="hljs-literal">None</span>)`,wrap:!1}}),{c(){n=p("p"),n.textContent=u,a=r(),h(s.$$.fragment)},l(t){n=m(t,"P",{"data-svelte-h":!0}),I(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=l(t),_(s.$$.fragment,t)},m(t,g){c(t,n,g),c(t,a,g),b(s,t,g),f=!0},p:F,i(t){f||(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(o(n),o(a)),w(s,t)}}}function tn(x){let n,u,a,s,f,t,g,Mt='aMUSEd was introduced in <a href="https://huggingface.co/papers/2401.01808" rel="nofollow">aMUSEd: An Open MUSE Reproduction</a> by Suraj Patil, William Berman, Robin Rombach, and Patrick von Platen.',Ee,se,$t='Amused is a lightweight text to image model based off of the <a href="https://arxiv.org/abs/2301.00704" rel="nofollow">MUSE</a> architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.',Be,oe,Tt="Amused is a vqvae token based transformer that can generate an image in fewer forward passes than many diffusion models. In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at larger batch sizes.",Xe,ae,Jt="The abstract from the paper is:",Ve,ie,jt="<em>We present aMUSEd, an open-source, lightweight masked image model (MIM) for text-to-image generation based on MUSE. With 10 percent of MUSE’s parameters, aMUSEd is focused on fast image generation. We believe MIM is under-explored compared to latent diffusion, the prevailing approach for text-to-image generation. Compared to latent diffusion, MIM requires fewer inference steps and is more interpretable. Additionally, MIM can be fine-tuned to learn additional styles with only a single image. We hope to encourage further exploration of MIM by demonstrating its effectiveness on large-scale text-to-image generation and releasing reproducible training code. We also release checkpoints for two models which directly produce images at 256x256 and 512x512 resolutions.</em>",Ne,re,Ut='<thead><tr><th>Model</th> <th>Params</th></tr></thead> <tbody><tr><td><a href="https://huggingface.co/amused/amused-256" rel="nofollow">amused-256</a></td> <td>603M</td></tr> <tr><td><a href="https://huggingface.co/amused/amused-512" rel="nofollow">amused-512</a></td> <td>608M</td></tr></tbody>',Re,le,Fe,T,de,Ye,B,ce,Oe,Me,kt="The call function to the pipeline for generation.",De,L,Ke,U,pe,et,$e,Wt=`Enable memory efficient attention from <a href="https://facebookresearch.github.io/xformers/" rel="nofollow">xFormers</a>. When this
option is enabled, you should observe lower GPU memory usage and a potential speed up during inference. Speed
up during training is not guaranteed.`,tt,S,nt,Q,st,q,me,ot,Te,Zt='Disable memory efficient attention from <a href="https://facebookresearch.github.io/xformers/" rel="nofollow">xFormers</a>.',Le,J,fe,at,X,ue,it,Je,Pt="The call function to the pipeline for generation.",rt,z,lt,k,ge,dt,je,At=`Enable memory efficient attention from <a href="https://facebookresearch.github.io/xformers/" rel="nofollow">xFormers</a>. When this
option is enabled, you should observe lower GPU memory usage and a potential speed up during inference. Speed
up during training is not guaranteed.`,ct,H,pt,Y,mt,O,he,ft,Ue,Gt='Disable memory efficient attention from <a href="https://facebookresearch.github.io/xformers/" rel="nofollow">xFormers</a>.',Se,j,_e,ut,V,be,gt,ke,Ct="The call function to the pipeline for generation.",ht,D,_t,W,ye,bt,We,Et=`Enable memory efficient attention from <a href="https://facebookresearch.github.io/xformers/" rel="nofollow">xFormers</a>. When this
option is enabled, you should observe lower GPU memory usage and a potential speed up during inference. Speed
up during training is not guaranteed.`,yt,K,vt,ee,wt,te,ve,It,Ze,Bt='Disable memory efficient attention from <a href="https://facebookresearch.github.io/xformers/" rel="nofollow">xFormers</a>.',Qe,we,qe,Ce,ze;return f=new Xt({props:{title:"aMUSEd",local:"amused",headingTag:"h1"}}),le=new Xt({props:{title:"AmusedPipeline",local:"diffusers.AmusedPipeline",headingTag:"h2"}}),de=new Z({props:{name:"class diffusers.AmusedPipeline",anchor:"diffusers.AmusedPipeline",parameters:[{name:"vqvae",val:": VQModel"},{name:"tokenizer",val:": CLIPTokenizer"},{name:"text_encoder",val:": CLIPTextModelWithProjection"},{name:"transformer",val:": UVit2DModel"},{name:"scheduler",val:": AmusedScheduler"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/amused/pipeline_amused.py#L42"}}),ce=new Z({props:{name:"__call__",anchor:"diffusers.AmusedPipeline.__call__",parameters:[{name:"prompt",val:": Union = None"},{name:"height",val:": Optional = None"},{name:"width",val:": Optional = None"},{name:"num_inference_steps",val:": int = 12"},{name:"guidance_scale",val:": float = 10.0"},{name:"negative_prompt",val:": Union = None"},{name:"num_images_per_prompt",val:": Optional = 1"},{name:"generator",val:": Optional = None"},{name:"latents",val:": Optional = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"encoder_hidden_states",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"negative_encoder_hidden_states",val:": Optional = None"},{name:"output_type",val:" = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"callback",val:": Optional = None"},{name:"callback_steps",val:": int = 1"},{name:"cross_attention_kwargs",val:": Optional = None"},{name:"micro_conditioning_aesthetic_score",val:": int = 6"},{name:"micro_conditioning_crop_coord",val:": Tuple = (0, 0)"},{name:"temperature",val:": Union = (2, 0)"}],parametersDescription:[{anchor:"diffusers.AmusedPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide image generation. If not defined, you need to pass <code>prompt_embeds</code>.`,name:"prompt"},{anchor:"diffusers.AmusedPipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to <code>self.transformer.config.sample_size * self.vae_scale_factor</code>) &#x2014;
The height in pixels of the generated image.`,name:"height"},{anchor:"diffusers.AmusedPipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to <code>self.unet.config.sample_size * self.vae_scale_factor</code>) &#x2014;
The width in pixels of the generated image.`,name:"width"},{anchor:"diffusers.AmusedPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 16) &#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.AmusedPipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 10.0) &#x2014;
A higher guidance scale value encourages the model to generate images closely linked to the text
<code>prompt</code> at the expense of lower image quality. Guidance scale is enabled when <code>guidance_scale &gt; 1</code>.`,name:"guidance_scale"},{anchor:"diffusers.AmusedPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass <code>negative_prompt_embeds</code> instead. Ignored when not using guidance (<code>guidance_scale &lt; 1</code>).`,name:"negative_prompt"},{anchor:"diffusers.AmusedPipeline.__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.AmusedPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>, <em>optional</em>) &#x2014;
A <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow"><code>torch.Generator</code></a> to make
generation deterministic.`,name:"generator"},{anchor:"diffusers.AmusedPipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.IntTensor</code>, <em>optional</em>) &#x2014;
Pre-generated tokens representing latent vectors in <code>self.vqvae</code>, to be used as inputs for image
gneration. If not provided, the starting latents will be completely masked.`,name:"latents"},{anchor:"diffusers.AmusedPipeline.__call__.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 (prompt weighting). If not
provided, text embeddings are generated from the <code>prompt</code> input argument. A single vector from the
pooled and projected final hidden states.`,name:"prompt_embeds"},{anchor:"diffusers.AmusedPipeline.__call__.encoder_hidden_states",description:`<strong>encoder_hidden_states</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.`,name:"encoder_hidden_states"},{anchor:"diffusers.AmusedPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, <code>negative_prompt_embeds</code> are generated from the <code>negative_prompt</code> input argument.`,name:"negative_prompt_embeds"},{anchor:"diffusers.AmusedPipeline.__call__.negative_encoder_hidden_states",description:`<strong>negative_encoder_hidden_states</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Analogous to <code>encoder_hidden_states</code> for the positive prompt.`,name:"negative_encoder_hidden_states"},{anchor:"diffusers.AmusedPipeline.__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>PIL.Image</code> or <code>np.array</code>.`,name:"output_type"},{anchor:"diffusers.AmusedPipeline.__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 <a href="/docs/diffusers/main/en/api/pipelines/stable_diffusion/depth2img#diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutput">StableDiffusionPipelineOutput</a> instead of a
plain tuple.`,name:"return_dict"},{anchor:"diffusers.AmusedPipeline.__call__.callback",description:`<strong>callback</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
A function that calls every <code>callback_steps</code> steps during inference. The function is called with the
following arguments: <code>callback(step: int, timestep: int, latents: torch.Tensor)</code>.`,name:"callback"},{anchor:"diffusers.AmusedPipeline.__call__.callback_steps",description:`<strong>callback_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
The frequency at which the <code>callback</code> function is called. If not specified, the callback is called at
every step.`,name:"callback_steps"},{anchor:"diffusers.AmusedPipeline.__call__.cross_attention_kwargs",description:`<strong>cross_attention_kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
A kwargs dictionary that if specified is passed along to the <code>AttentionProcessor</code> as defined in
<a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py" rel="nofollow"><code>self.processor</code></a>.`,name:"cross_attention_kwargs"},{anchor:"diffusers.AmusedPipeline.__call__.micro_conditioning_aesthetic_score",description:`<strong>micro_conditioning_aesthetic_score</strong> (<code>int</code>, <em>optional</em>, defaults to 6) &#x2014;
The targeted aesthetic score according to the laion aesthetic classifier. See
<a href="https://laion.ai/blog/laion-aesthetics/" rel="nofollow">https://laion.ai/blog/laion-aesthetics/</a> and the micro-conditioning section of
<a href="https://arxiv.org/abs/2307.01952" rel="nofollow">https://arxiv.org/abs/2307.01952</a>.`,name:"micro_conditioning_aesthetic_score"},{anchor:"diffusers.AmusedPipeline.__call__.micro_conditioning_crop_coord",description:`<strong>micro_conditioning_crop_coord</strong> (<code>Tuple[int]</code>, <em>optional</em>, defaults to (0, 0)) &#x2014;
The targeted height, width crop coordinates. See the micro-conditioning section of
<a href="https://arxiv.org/abs/2307.01952" rel="nofollow">https://arxiv.org/abs/2307.01952</a>.`,name:"micro_conditioning_crop_coord"},{anchor:"diffusers.AmusedPipeline.__call__.temperature",description:`<strong>temperature</strong> (<code>Union[int, Tuple[int, int], List[int]]</code>, <em>optional</em>, defaults to (2, 0)) &#x2014;
Configures the temperature scheduler on <code>self.scheduler</code> see <code>AmusedScheduler#set_timesteps</code>.`,name:"temperature"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/amused/pipeline_amused.py#L72",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>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.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><a
  href="/docs/diffusers/main/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput"
>ImagePipelineOutput</a> or <code>tuple</code></p>
`}}),L=new Ae({props:{anchor:"diffusers.AmusedPipeline.__call__.example",$$slots:{default:[Qt]},$$scope:{ctx:x}}}),pe=new Z({props:{name:"enable_xformers_memory_efficient_attention",anchor:"diffusers.AmusedPipeline.enable_xformers_memory_efficient_attention",parameters:[{name:"attention_op",val:": Optional = None"}],parametersDescription:[{anchor:"diffusers.AmusedPipeline.enable_xformers_memory_efficient_attention.attention_op",description:`<strong>attention_op</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
Override the default <code>None</code> operator for use as <code>op</code> argument to the
<a href="https://facebookresearch.github.io/xformers/components/ops.html#xformers.ops.memory_efficient_attention" rel="nofollow"><code>memory_efficient_attention()</code></a>
function of xFormers.`,name:"attention_op"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_utils.py#L1587"}}),S=new xt({props:{warning:!0,$$slots:{default:[qt]},$$scope:{ctx:x}}}),Q=new Ae({props:{anchor:"diffusers.AmusedPipeline.enable_xformers_memory_efficient_attention.example",$$slots:{default:[zt]},$$scope:{ctx:x}}}),me=new Z({props:{name:"disable_xformers_memory_efficient_attention",anchor:"diffusers.AmusedPipeline.disable_xformers_memory_efficient_attention",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_utils.py#L1622"}}),fe=new Z({props:{name:"class diffusers.AmusedImg2ImgPipeline",anchor:"diffusers.AmusedImg2ImgPipeline",parameters:[{name:"vqvae",val:": VQModel"},{name:"tokenizer",val:": CLIPTokenizer"},{name:"text_encoder",val:": CLIPTextModelWithProjection"},{name:"transformer",val:": UVit2DModel"},{name:"scheduler",val:": AmusedScheduler"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/amused/pipeline_amused_img2img.py#L52"}}),ue=new Z({props:{name:"__call__",anchor:"diffusers.AmusedImg2ImgPipeline.__call__",parameters:[{name:"prompt",val:": Union = None"},{name:"image",val:": Union = None"},{name:"strength",val:": float = 0.5"},{name:"num_inference_steps",val:": int = 12"},{name:"guidance_scale",val:": float = 10.0"},{name:"negative_prompt",val:": Union = None"},{name:"num_images_per_prompt",val:": Optional = 1"},{name:"generator",val:": Optional = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"encoder_hidden_states",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"negative_encoder_hidden_states",val:": Optional = None"},{name:"output_type",val:" = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"callback",val:": Optional = None"},{name:"callback_steps",val:": int = 1"},{name:"cross_attention_kwargs",val:": Optional = None"},{name:"micro_conditioning_aesthetic_score",val:": int = 6"},{name:"micro_conditioning_crop_coord",val:": Tuple = (0, 0)"},{name:"temperature",val:": Union = (2, 0)"}],parametersDescription:[{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide image generation. If not defined, you need to pass <code>prompt_embeds</code>.`,name:"prompt"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.image",description:`<strong>image</strong> (<code>torch.Tensor</code>, <code>PIL.Image.Image</code>, <code>np.ndarray</code>, <code>List[torch.Tensor]</code>, <code>List[PIL.Image.Image]</code>, or <code>List[np.ndarray]</code>) &#x2014;
<code>Image</code>, numpy array or tensor representing an image batch to be used as the starting point. For both
numpy array and pytorch tensor, the expected value range is between <code>[0, 1]</code> If it&#x2019;s a tensor or a list
or tensors, the expected shape should be <code>(B, C, H, W)</code> or <code>(C, H, W)</code>. If it is a numpy array or a
list of arrays, the expected shape should be <code>(B, H, W, C)</code> or <code>(H, W, C)</code> It can also accept image
latents as <code>image</code>, but if passing latents directly it is not encoded again.`,name:"image"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.strength",description:`<strong>strength</strong> (<code>float</code>, <em>optional</em>, defaults to 0.5) &#x2014;
Indicates extent to transform the reference <code>image</code>. Must be between 0 and 1. <code>image</code> is used as a
starting point and more noise is added the higher the <code>strength</code>. The number of denoising steps depends
on the amount of noise initially added. When <code>strength</code> is 1, added noise is maximum and the denoising
process runs for the full number of iterations specified in <code>num_inference_steps</code>. A value of 1
essentially ignores <code>image</code>.`,name:"strength"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 12) &#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.AmusedImg2ImgPipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 10.0) &#x2014;
A higher guidance scale value encourages the model to generate images closely linked to the text
<code>prompt</code> at the expense of lower image quality. Guidance scale is enabled when <code>guidance_scale &gt; 1</code>.`,name:"guidance_scale"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass <code>negative_prompt_embeds</code> instead. Ignored when not using guidance (<code>guidance_scale &lt; 1</code>).`,name:"negative_prompt"},{anchor:"diffusers.AmusedImg2ImgPipeline.__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.AmusedImg2ImgPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>, <em>optional</em>) &#x2014;
A <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow"><code>torch.Generator</code></a> to make
generation deterministic.`,name:"generator"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.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 (prompt weighting). If not
provided, text embeddings are generated from the <code>prompt</code> input argument. A single vector from the
pooled and projected final hidden states.`,name:"prompt_embeds"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.encoder_hidden_states",description:`<strong>encoder_hidden_states</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.`,name:"encoder_hidden_states"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, <code>negative_prompt_embeds</code> are generated from the <code>negative_prompt</code> input argument.`,name:"negative_prompt_embeds"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.negative_encoder_hidden_states",description:`<strong>negative_encoder_hidden_states</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Analogous to <code>encoder_hidden_states</code> for the positive prompt.`,name:"negative_encoder_hidden_states"},{anchor:"diffusers.AmusedImg2ImgPipeline.__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>PIL.Image</code> or <code>np.array</code>.`,name:"output_type"},{anchor:"diffusers.AmusedImg2ImgPipeline.__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 <a href="/docs/diffusers/main/en/api/pipelines/stable_diffusion/depth2img#diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutput">StableDiffusionPipelineOutput</a> instead of a
plain tuple.`,name:"return_dict"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.callback",description:`<strong>callback</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
A function that calls every <code>callback_steps</code> steps during inference. The function is called with the
following arguments: <code>callback(step: int, timestep: int, latents: torch.Tensor)</code>.`,name:"callback"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.callback_steps",description:`<strong>callback_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
The frequency at which the <code>callback</code> function is called. If not specified, the callback is called at
every step.`,name:"callback_steps"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.cross_attention_kwargs",description:`<strong>cross_attention_kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
A kwargs dictionary that if specified is passed along to the <code>AttentionProcessor</code> as defined in
<a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py" rel="nofollow"><code>self.processor</code></a>.`,name:"cross_attention_kwargs"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.micro_conditioning_aesthetic_score",description:`<strong>micro_conditioning_aesthetic_score</strong> (<code>int</code>, <em>optional</em>, defaults to 6) &#x2014;
The targeted aesthetic score according to the laion aesthetic classifier. See
<a href="https://laion.ai/blog/laion-aesthetics/" rel="nofollow">https://laion.ai/blog/laion-aesthetics/</a> and the micro-conditioning section of
<a href="https://arxiv.org/abs/2307.01952" rel="nofollow">https://arxiv.org/abs/2307.01952</a>.`,name:"micro_conditioning_aesthetic_score"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.micro_conditioning_crop_coord",description:`<strong>micro_conditioning_crop_coord</strong> (<code>Tuple[int]</code>, <em>optional</em>, defaults to (0, 0)) &#x2014;
The targeted height, width crop coordinates. See the micro-conditioning section of
<a href="https://arxiv.org/abs/2307.01952" rel="nofollow">https://arxiv.org/abs/2307.01952</a>.`,name:"micro_conditioning_crop_coord"},{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.temperature",description:`<strong>temperature</strong> (<code>Union[int, Tuple[int, int], List[int]]</code>, <em>optional</em>, defaults to (2, 0)) &#x2014;
Configures the temperature scheduler on <code>self.scheduler</code> see <code>AmusedScheduler#set_timesteps</code>.`,name:"temperature"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/amused/pipeline_amused_img2img.py#L87",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>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.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><a
  href="/docs/diffusers/main/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput"
>ImagePipelineOutput</a> or <code>tuple</code></p>
`}}),z=new Ae({props:{anchor:"diffusers.AmusedImg2ImgPipeline.__call__.example",$$slots:{default:[Ht]},$$scope:{ctx:x}}}),ge=new Z({props:{name:"enable_xformers_memory_efficient_attention",anchor:"diffusers.AmusedImg2ImgPipeline.enable_xformers_memory_efficient_attention",parameters:[{name:"attention_op",val:": Optional = None"}],parametersDescription:[{anchor:"diffusers.AmusedImg2ImgPipeline.enable_xformers_memory_efficient_attention.attention_op",description:`<strong>attention_op</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
Override the default <code>None</code> operator for use as <code>op</code> argument to the
<a href="https://facebookresearch.github.io/xformers/components/ops.html#xformers.ops.memory_efficient_attention" rel="nofollow"><code>memory_efficient_attention()</code></a>
function of xFormers.`,name:"attention_op"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_utils.py#L1587"}}),H=new xt({props:{warning:!0,$$slots:{default:[Yt]},$$scope:{ctx:x}}}),Y=new Ae({props:{anchor:"diffusers.AmusedImg2ImgPipeline.enable_xformers_memory_efficient_attention.example",$$slots:{default:[Ot]},$$scope:{ctx:x}}}),he=new Z({props:{name:"disable_xformers_memory_efficient_attention",anchor:"diffusers.AmusedImg2ImgPipeline.disable_xformers_memory_efficient_attention",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_utils.py#L1622"}}),_e=new Z({props:{name:"class diffusers.AmusedInpaintPipeline",anchor:"diffusers.AmusedInpaintPipeline",parameters:[{name:"vqvae",val:": VQModel"},{name:"tokenizer",val:": CLIPTokenizer"},{name:"text_encoder",val:": CLIPTextModelWithProjection"},{name:"transformer",val:": UVit2DModel"},{name:"scheduler",val:": AmusedScheduler"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/amused/pipeline_amused_inpaint.py#L60"}}),be=new Z({props:{name:"__call__",anchor:"diffusers.AmusedInpaintPipeline.__call__",parameters:[{name:"prompt",val:": Union = None"},{name:"image",val:": Union = None"},{name:"mask_image",val:": Union = None"},{name:"strength",val:": float = 1.0"},{name:"num_inference_steps",val:": int = 12"},{name:"guidance_scale",val:": float = 10.0"},{name:"negative_prompt",val:": Union = None"},{name:"num_images_per_prompt",val:": Optional = 1"},{name:"generator",val:": Optional = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"encoder_hidden_states",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"negative_encoder_hidden_states",val:": Optional = None"},{name:"output_type",val:" = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"callback",val:": Optional = None"},{name:"callback_steps",val:": int = 1"},{name:"cross_attention_kwargs",val:": Optional = None"},{name:"micro_conditioning_aesthetic_score",val:": int = 6"},{name:"micro_conditioning_crop_coord",val:": Tuple = (0, 0)"},{name:"temperature",val:": Union = (2, 0)"}],parametersDescription:[{anchor:"diffusers.AmusedInpaintPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide image generation. If not defined, you need to pass <code>prompt_embeds</code>.`,name:"prompt"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.image",description:`<strong>image</strong> (<code>torch.Tensor</code>, <code>PIL.Image.Image</code>, <code>np.ndarray</code>, <code>List[torch.Tensor]</code>, <code>List[PIL.Image.Image]</code>, or <code>List[np.ndarray]</code>) &#x2014;
<code>Image</code>, numpy array or tensor representing an image batch to be used as the starting point. For both
numpy array and pytorch tensor, the expected value range is between <code>[0, 1]</code> If it&#x2019;s a tensor or a list
or tensors, the expected shape should be <code>(B, C, H, W)</code> or <code>(C, H, W)</code>. If it is a numpy array or a
list of arrays, the expected shape should be <code>(B, H, W, C)</code> or <code>(H, W, C)</code> It can also accept image
latents as <code>image</code>, but if passing latents directly it is not encoded again.`,name:"image"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.mask_image",description:`<strong>mask_image</strong> (<code>torch.Tensor</code>, <code>PIL.Image.Image</code>, <code>np.ndarray</code>, <code>List[torch.Tensor]</code>, <code>List[PIL.Image.Image]</code>, or <code>List[np.ndarray]</code>) &#x2014;
<code>Image</code>, numpy array or tensor representing an image batch to mask <code>image</code>. White pixels in the mask
are repainted while black pixels are preserved. If <code>mask_image</code> is a PIL image, it is converted to a
single channel (luminance) before use. If it&#x2019;s a numpy array or pytorch tensor, it should contain one
color channel (L) instead of 3, so the expected shape for pytorch tensor would be <code>(B, 1, H, W)</code>, <code>(B, H, W)</code>, <code>(1, H, W)</code>, <code>(H, W)</code>. And for numpy array would be for <code>(B, H, W, 1)</code>, <code>(B, H, W)</code>, <code>(H, W, 1)</code>, or <code>(H, W)</code>.`,name:"mask_image"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.strength",description:`<strong>strength</strong> (<code>float</code>, <em>optional</em>, defaults to 1.0) &#x2014;
Indicates extent to transform the reference <code>image</code>. Must be between 0 and 1. <code>image</code> is used as a
starting point and more noise is added the higher the <code>strength</code>. The number of denoising steps depends
on the amount of noise initially added. When <code>strength</code> is 1, added noise is maximum and the denoising
process runs for the full number of iterations specified in <code>num_inference_steps</code>. A value of 1
essentially ignores <code>image</code>.`,name:"strength"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 16) &#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.AmusedInpaintPipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 10.0) &#x2014;
A higher guidance scale value encourages the model to generate images closely linked to the text
<code>prompt</code> at the expense of lower image quality. Guidance scale is enabled when <code>guidance_scale &gt; 1</code>.`,name:"guidance_scale"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass <code>negative_prompt_embeds</code> instead. Ignored when not using guidance (<code>guidance_scale &lt; 1</code>).`,name:"negative_prompt"},{anchor:"diffusers.AmusedInpaintPipeline.__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.AmusedInpaintPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code>, <em>optional</em>) &#x2014;
A <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow"><code>torch.Generator</code></a> to make
generation deterministic.`,name:"generator"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.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 (prompt weighting). If not
provided, text embeddings are generated from the <code>prompt</code> input argument. A single vector from the
pooled and projected final hidden states.`,name:"prompt_embeds"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.encoder_hidden_states",description:`<strong>encoder_hidden_states</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.`,name:"encoder_hidden_states"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, <code>negative_prompt_embeds</code> are generated from the <code>negative_prompt</code> input argument.`,name:"negative_prompt_embeds"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.negative_encoder_hidden_states",description:`<strong>negative_encoder_hidden_states</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Analogous to <code>encoder_hidden_states</code> for the positive prompt.`,name:"negative_encoder_hidden_states"},{anchor:"diffusers.AmusedInpaintPipeline.__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>PIL.Image</code> or <code>np.array</code>.`,name:"output_type"},{anchor:"diffusers.AmusedInpaintPipeline.__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 <a href="/docs/diffusers/main/en/api/pipelines/stable_diffusion/depth2img#diffusers.pipelines.stable_diffusion.StableDiffusionPipelineOutput">StableDiffusionPipelineOutput</a> instead of a
plain tuple.`,name:"return_dict"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.callback",description:`<strong>callback</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
A function that calls every <code>callback_steps</code> steps during inference. The function is called with the
following arguments: <code>callback(step: int, timestep: int, latents: torch.Tensor)</code>.`,name:"callback"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.callback_steps",description:`<strong>callback_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
The frequency at which the <code>callback</code> function is called. If not specified, the callback is called at
every step.`,name:"callback_steps"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.cross_attention_kwargs",description:`<strong>cross_attention_kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
A kwargs dictionary that if specified is passed along to the <code>AttentionProcessor</code> as defined in
<a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py" rel="nofollow"><code>self.processor</code></a>.`,name:"cross_attention_kwargs"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.micro_conditioning_aesthetic_score",description:`<strong>micro_conditioning_aesthetic_score</strong> (<code>int</code>, <em>optional</em>, defaults to 6) &#x2014;
The targeted aesthetic score according to the laion aesthetic classifier. See
<a href="https://laion.ai/blog/laion-aesthetics/" rel="nofollow">https://laion.ai/blog/laion-aesthetics/</a> and the micro-conditioning section of
<a href="https://arxiv.org/abs/2307.01952" rel="nofollow">https://arxiv.org/abs/2307.01952</a>.`,name:"micro_conditioning_aesthetic_score"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.micro_conditioning_crop_coord",description:`<strong>micro_conditioning_crop_coord</strong> (<code>Tuple[int]</code>, <em>optional</em>, defaults to (0, 0)) &#x2014;
The targeted height, width crop coordinates. See the micro-conditioning section of
<a href="https://arxiv.org/abs/2307.01952" rel="nofollow">https://arxiv.org/abs/2307.01952</a>.`,name:"micro_conditioning_crop_coord"},{anchor:"diffusers.AmusedInpaintPipeline.__call__.temperature",description:`<strong>temperature</strong> (<code>Union[int, Tuple[int, int], List[int]]</code>, <em>optional</em>, defaults to (2, 0)) &#x2014;
Configures the temperature scheduler on <code>self.scheduler</code> see <code>AmusedScheduler#set_timesteps</code>.`,name:"temperature"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/amused/pipeline_amused_inpaint.py#L103",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p>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.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><a
  href="/docs/diffusers/main/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput"
>ImagePipelineOutput</a> or <code>tuple</code></p>
`}}),D=new Ae({props:{anchor:"diffusers.AmusedInpaintPipeline.__call__.example",$$slots:{default:[Dt]},$$scope:{ctx:x}}}),ye=new Z({props:{name:"enable_xformers_memory_efficient_attention",anchor:"diffusers.AmusedInpaintPipeline.enable_xformers_memory_efficient_attention",parameters:[{name:"attention_op",val:": Optional = None"}],parametersDescription:[{anchor:"diffusers.AmusedInpaintPipeline.enable_xformers_memory_efficient_attention.attention_op",description:`<strong>attention_op</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
Override the default <code>None</code> operator for use as <code>op</code> argument to the
<a href="https://facebookresearch.github.io/xformers/components/ops.html#xformers.ops.memory_efficient_attention" rel="nofollow"><code>memory_efficient_attention()</code></a>
function of xFormers.`,name:"attention_op"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_utils.py#L1587"}}),K=new xt({props:{warning:!0,$$slots:{default:[Kt]},$$scope:{ctx:x}}}),ee=new Ae({props:{anchor:"diffusers.AmusedInpaintPipeline.enable_xformers_memory_efficient_attention.example",$$slots:{default:[en]},$$scope:{ctx:x}}}),ve=new Z({props:{name:"disable_xformers_memory_efficient_attention",anchor:"diffusers.AmusedInpaintPipeline.disable_xformers_memory_efficient_attention",parameters:[],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_utils.py#L1622"}}),we=new St({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/amused.md"}}),{c(){n=p("meta"),u=r(),a=p("p"),s=r(),h(f.$$.fragment),t=r(),g=p("p"),g.innerHTML=Mt,Ee=r(),se=p("p"),se.innerHTML=$t,Be=r(),oe=p("p"),oe.textContent=Tt,Xe=r(),ae=p("p"),ae.textContent=Jt,Ve=r(),ie=p("p"),ie.innerHTML=jt,Ne=r(),re=p("table"),re.innerHTML=Ut,Re=r(),h(le.$$.fragment),Fe=r(),T=p("div"),h(de.$$.fragment),Ye=r(),B=p("div"),h(ce.$$.fragment),Oe=r(),Me=p("p"),Me.textContent=kt,De=r(),h(L.$$.fragment),Ke=r(),U=p("div"),h(pe.$$.fragment),et=r(),$e=p("p"),$e.innerHTML=Wt,tt=r(),h(S.$$.fragment),nt=r(),h(Q.$$.fragment),st=r(),q=p("div"),h(me.$$.fragment),ot=r(),Te=p("p"),Te.innerHTML=Zt,Le=r(),J=p("div"),h(fe.$$.fragment),at=r(),X=p("div"),h(ue.$$.fragment),it=r(),Je=p("p"),Je.textContent=Pt,rt=r(),h(z.$$.fragment),lt=r(),k=p("div"),h(ge.$$.fragment),dt=r(),je=p("p"),je.innerHTML=At,ct=r(),h(H.$$.fragment),pt=r(),h(Y.$$.fragment),mt=r(),O=p("div"),h(he.$$.fragment),ft=r(),Ue=p("p"),Ue.innerHTML=Gt,Se=r(),j=p("div"),h(_e.$$.fragment),ut=r(),V=p("div"),h(be.$$.fragment),gt=r(),ke=p("p"),ke.textContent=Ct,ht=r(),h(D.$$.fragment),_t=r(),W=p("div"),h(ye.$$.fragment),bt=r(),We=p("p"),We.innerHTML=Et,yt=r(),h(K.$$.fragment),vt=r(),h(ee.$$.fragment),wt=r(),te=p("div"),h(ve.$$.fragment),It=r(),Ze=p("p"),Ze.innerHTML=Bt,Qe=r(),h(we.$$.fragment),qe=r(),Ce=p("p"),this.h()},l(e){const i=Lt("svelte-u9bgzb",document.head);n=m(i,"META",{name:!0,content:!0}),i.forEach(o),u=l(e),a=m(e,"P",{}),M(a).forEach(o),s=l(e),_(f.$$.fragment,e),t=l(e),g=m(e,"P",{"data-svelte-h":!0}),I(g)!=="svelte-1lfaywv"&&(g.innerHTML=Mt),Ee=l(e),se=m(e,"P",{"data-svelte-h":!0}),I(se)!=="svelte-97ks8s"&&(se.innerHTML=$t),Be=l(e),oe=m(e,"P",{"data-svelte-h":!0}),I(oe)!=="svelte-1s2g8lw"&&(oe.textContent=Tt),Xe=l(e),ae=m(e,"P",{"data-svelte-h":!0}),I(ae)!=="svelte-1cwsb16"&&(ae.textContent=Jt),Ve=l(e),ie=m(e,"P",{"data-svelte-h":!0}),I(ie)!=="svelte-t2fzna"&&(ie.innerHTML=jt),Ne=l(e),re=m(e,"TABLE",{"data-svelte-h":!0}),I(re)!=="svelte-186adnx"&&(re.innerHTML=Ut),Re=l(e),_(le.$$.fragment,e),Fe=l(e),T=m(e,"DIV",{class:!0});var P=M(T);_(de.$$.fragment,P),Ye=l(P),B=m(P,"DIV",{class:!0});var N=M(B);_(ce.$$.fragment,N),Oe=l(N),Me=m(N,"P",{"data-svelte-h":!0}),I(Me)!=="svelte-50j04k"&&(Me.textContent=kt),De=l(N),_(L.$$.fragment,N),N.forEach(o),Ke=l(P),U=m(P,"DIV",{class:!0});var A=M(U);_(pe.$$.fragment,A),et=l(A),$e=m(A,"P",{"data-svelte-h":!0}),I($e)!=="svelte-e03q3e"&&($e.innerHTML=Wt),tt=l(A),_(S.$$.fragment,A),nt=l(A),_(Q.$$.fragment,A),A.forEach(o),st=l(P),q=m(P,"DIV",{class:!0});var Ie=M(q);_(me.$$.fragment,Ie),ot=l(Ie),Te=m(Ie,"P",{"data-svelte-h":!0}),I(Te)!=="svelte-1vfte1e"&&(Te.innerHTML=Zt),Ie.forEach(o),P.forEach(o),Le=l(e),J=m(e,"DIV",{class:!0});var G=M(J);_(fe.$$.fragment,G),at=l(G),X=m(G,"DIV",{class:!0});var R=M(X);_(ue.$$.fragment,R),it=l(R),Je=m(R,"P",{"data-svelte-h":!0}),I(Je)!=="svelte-50j04k"&&(Je.textContent=Pt),rt=l(R),_(z.$$.fragment,R),R.forEach(o),lt=l(G),k=m(G,"DIV",{class:!0});var C=M(k);_(ge.$$.fragment,C),dt=l(C),je=m(C,"P",{"data-svelte-h":!0}),I(je)!=="svelte-e03q3e"&&(je.innerHTML=At),ct=l(C),_(H.$$.fragment,C),pt=l(C),_(Y.$$.fragment,C),C.forEach(o),mt=l(G),O=m(G,"DIV",{class:!0});var xe=M(O);_(he.$$.fragment,xe),ft=l(xe),Ue=m(xe,"P",{"data-svelte-h":!0}),I(Ue)!=="svelte-1vfte1e"&&(Ue.innerHTML=Gt),xe.forEach(o),G.forEach(o),Se=l(e),j=m(e,"DIV",{class:!0});var E=M(j);_(_e.$$.fragment,E),ut=l(E),V=m(E,"DIV",{class:!0});var Pe=M(V);_(be.$$.fragment,Pe),gt=l(Pe),ke=m(Pe,"P",{"data-svelte-h":!0}),I(ke)!=="svelte-50j04k"&&(ke.textContent=Ct),ht=l(Pe),_(D.$$.fragment,Pe),Pe.forEach(o),_t=l(E),W=m(E,"DIV",{class:!0});var ne=M(W);_(ye.$$.fragment,ne),bt=l(ne),We=m(ne,"P",{"data-svelte-h":!0}),I(We)!=="svelte-e03q3e"&&(We.innerHTML=Et),yt=l(ne),_(K.$$.fragment,ne),vt=l(ne),_(ee.$$.fragment,ne),ne.forEach(o),wt=l(E),te=m(E,"DIV",{class:!0});var He=M(te);_(ve.$$.fragment,He),It=l(He),Ze=m(He,"P",{"data-svelte-h":!0}),I(Ze)!=="svelte-1vfte1e"&&(Ze.innerHTML=Bt),He.forEach(o),E.forEach(o),Qe=l(e),_(we.$$.fragment,e),qe=l(e),Ce=m(e,"P",{}),M(Ce).forEach(o),this.h()},h(){$(n,"name","hf:doc:metadata"),$(n,"content",nn),$(B,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(U,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(q,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(X,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(O,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(J,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(V,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(W,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(te,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(j,"class","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){d(document.head,n),c(e,u,i),c(e,a,i),c(e,s,i),b(f,e,i),c(e,t,i),c(e,g,i),c(e,Ee,i),c(e,se,i),c(e,Be,i),c(e,oe,i),c(e,Xe,i),c(e,ae,i),c(e,Ve,i),c(e,ie,i),c(e,Ne,i),c(e,re,i),c(e,Re,i),b(le,e,i),c(e,Fe,i),c(e,T,i),b(de,T,null),d(T,Ye),d(T,B),b(ce,B,null),d(B,Oe),d(B,Me),d(B,De),b(L,B,null),d(T,Ke),d(T,U),b(pe,U,null),d(U,et),d(U,$e),d(U,tt),b(S,U,null),d(U,nt),b(Q,U,null),d(T,st),d(T,q),b(me,q,null),d(q,ot),d(q,Te),c(e,Le,i),c(e,J,i),b(fe,J,null),d(J,at),d(J,X),b(ue,X,null),d(X,it),d(X,Je),d(X,rt),b(z,X,null),d(J,lt),d(J,k),b(ge,k,null),d(k,dt),d(k,je),d(k,ct),b(H,k,null),d(k,pt),b(Y,k,null),d(J,mt),d(J,O),b(he,O,null),d(O,ft),d(O,Ue),c(e,Se,i),c(e,j,i),b(_e,j,null),d(j,ut),d(j,V),b(be,V,null),d(V,gt),d(V,ke),d(V,ht),b(D,V,null),d(j,_t),d(j,W),b(ye,W,null),d(W,bt),d(W,We),d(W,yt),b(K,W,null),d(W,vt),b(ee,W,null),d(j,wt),d(j,te),b(ve,te,null),d(te,It),d(te,Ze),c(e,Qe,i),b(we,e,i),c(e,qe,i),c(e,Ce,i),ze=!0},p(e,[i]){const P={};i&2&&(P.$$scope={dirty:i,ctx:e}),L.$set(P);const N={};i&2&&(N.$$scope={dirty:i,ctx:e}),S.$set(N);const A={};i&2&&(A.$$scope={dirty:i,ctx:e}),Q.$set(A);const Ie={};i&2&&(Ie.$$scope={dirty:i,ctx:e}),z.$set(Ie);const G={};i&2&&(G.$$scope={dirty:i,ctx:e}),H.$set(G);const R={};i&2&&(R.$$scope={dirty:i,ctx:e}),Y.$set(R);const C={};i&2&&(C.$$scope={dirty:i,ctx:e}),D.$set(C);const xe={};i&2&&(xe.$$scope={dirty:i,ctx:e}),K.$set(xe);const E={};i&2&&(E.$$scope={dirty:i,ctx:e}),ee.$set(E)},i(e){ze||(y(f.$$.fragment,e),y(le.$$.fragment,e),y(de.$$.fragment,e),y(ce.$$.fragment,e),y(L.$$.fragment,e),y(pe.$$.fragment,e),y(S.$$.fragment,e),y(Q.$$.fragment,e),y(me.$$.fragment,e),y(fe.$$.fragment,e),y(ue.$$.fragment,e),y(z.$$.fragment,e),y(ge.$$.fragment,e),y(H.$$.fragment,e),y(Y.$$.fragment,e),y(he.$$.fragment,e),y(_e.$$.fragment,e),y(be.$$.fragment,e),y(D.$$.fragment,e),y(ye.$$.fragment,e),y(K.$$.fragment,e),y(ee.$$.fragment,e),y(ve.$$.fragment,e),y(we.$$.fragment,e),ze=!0)},o(e){v(f.$$.fragment,e),v(le.$$.fragment,e),v(de.$$.fragment,e),v(ce.$$.fragment,e),v(L.$$.fragment,e),v(pe.$$.fragment,e),v(S.$$.fragment,e),v(Q.$$.fragment,e),v(me.$$.fragment,e),v(fe.$$.fragment,e),v(ue.$$.fragment,e),v(z.$$.fragment,e),v(ge.$$.fragment,e),v(H.$$.fragment,e),v(Y.$$.fragment,e),v(he.$$.fragment,e),v(_e.$$.fragment,e),v(be.$$.fragment,e),v(D.$$.fragment,e),v(ye.$$.fragment,e),v(K.$$.fragment,e),v(ee.$$.fragment,e),v(ve.$$.fragment,e),v(we.$$.fragment,e),ze=!1},d(e){e&&(o(u),o(a),o(s),o(t),o(g),o(Ee),o(se),o(Be),o(oe),o(Xe),o(ae),o(Ve),o(ie),o(Ne),o(re),o(Re),o(Fe),o(T),o(Le),o(J),o(Se),o(j),o(Qe),o(qe),o(Ce)),o(n),w(f,e),w(le,e),w(de),w(ce),w(L),w(pe),w(S),w(Q),w(me),w(fe),w(ue),w(z),w(ge),w(H),w(Y),w(he),w(_e),w(be),w(D),w(ye),w(K),w(ee),w(ve),w(we,e)}}}const nn='{"title":"aMUSEd","local":"amused","sections":[{"title":"AmusedPipeline","local":"diffusers.AmusedPipeline","sections":[],"depth":2}],"depth":1}';function sn(x){return Nt(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class mn extends Rt{constructor(n){super(),Ft(this,n,sn,tn,Vt,{})}}export{mn as component};