Buckets:

hf-doc-build
/

doc-dev

hf-doc-build/doc-dev / diffusers /main /en /_app /immutable /nodes /56.33340941.js

rtrm's picture

3 months ago

68.2 kB

	import{s as fo,o as uo,n as L}from"../chunks/scheduler.8c3d61f6.js";import{S as ho,i as go,g as l,s as i,r as _,A as _o,h as p,f as m,c as r,j as R,u as b,x as c,k as X,y as o,a as g,v as w,d as y,t as v,w as $}from"../chunks/index.da70eac4.js";import{T as gt}from"../chunks/Tip.1d9b8c37.js";import{D as z}from"../chunks/Docstring.ee4b6913.js";import{C as D}from"../chunks/CodeBlock.00a903b3.js";import{E as Y}from"../chunks/ExampleCodeBlock.f7bd2c1f.js";import{H as _t,E as bo}from"../chunks/EditOnGithub.1e64e623.js";function wo(x){let n,u='Check out the <a href="../../tutorials/autopipeline">AutoPipeline</a> tutorial to learn how to use this API!';return{c(){n=l("p"),n.innerHTML=u},l(a){n=p(a,"P",{"data-svelte-h":!0}),c(n)!=="svelte-1npomoi"&&(n.innerHTML=u)},m(a,s){g(a,n,s)},p:L,d(a){a&&m(n)}}}function yo(x){let n,u="If you get the error message below, you need to finetune the weights for your downstream task:",a,s,f;return s=new D({props:{code:"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",highlighted:`Some weights <span class="hljs-keyword">of</span> UNet2DConditionModel were <span class="hljs-keyword">not</span> initialized <span class="hljs-built_in">from</span> <span class="hljs-keyword">the</span> model checkpoint <span class="hljs-keyword">at</span> runwayml/stable-diffusion-v1<span class="hljs-number">-5</span> <span class="hljs-keyword">and</span> are newly initialized because <span class="hljs-keyword">the</span> shapes did <span class="hljs-keyword">not</span> match:
	- conv_in.weight: found shape torch.Size([<span class="hljs-number">320</span>, <span class="hljs-number">4</span>, <span class="hljs-number">3</span>, <span class="hljs-number">3</span>]) <span class="hljs-keyword">in</span> <span class="hljs-keyword">the</span> checkpoint <span class="hljs-keyword">and</span> torch.Size([<span class="hljs-number">320</span>, <span class="hljs-number">9</span>, <span class="hljs-number">3</span>, <span class="hljs-number">3</span>]) <span class="hljs-keyword">in</span> <span class="hljs-keyword">the</span> model instantiated
	You should probably TRAIN this model <span class="hljs-keyword">on</span> <span class="hljs-title">a</span> <span class="hljs-title">down-stream</span> <span class="hljs-title">task</span> <span class="hljs-title">to</span> <span class="hljs-title">be</span> <span class="hljs-title">able</span> <span class="hljs-title">to</span> <span class="hljs-title">use</span> <span class="hljs-title">it</span> <span class="hljs-title">for</span> <span class="hljs-title">predictions</span> <span class="hljs-title">and</span> <span class="hljs-title">inference</span>.`,wrap:!1}}),{c(){n=l("p"),n.textContent=u,a=i(),_(s.$$.fragment)},l(t){n=p(t,"P",{"data-svelte-h":!0}),c(n)!=="svelte-xueb0m"&&(n.textContent=u),a=r(t),b(s.$$.fragment,t)},m(t,h){g(t,n,h),g(t,a,h),w(s,t,h),f=!0},p:L,i(t){f\|\|(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(m(n),m(a)),$(s,t)}}}function vo(x){let n,u=`To use private or <a href="https://huggingface.co/docs/hub/models-gated#gated-models" rel="nofollow">gated</a> models, log-in with
	<code>huggingface-cli login</code>.`;return{c(){n=l("p"),n.innerHTML=u},l(a){n=p(a,"P",{"data-svelte-h":!0}),c(n)!=="svelte-x73rgs"&&(n.innerHTML=u)},m(a,s){g(a,n,s)},p:L,d(a){a&&m(n)}}}function $o(x){let n,u="Examples:",a,s,f;return s=new D({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEF1dG9QaXBlbGluZUZvclRleHQySW1hZ2UlMEElMEFwaXBlbGluZSUyMCUzRCUyMEF1dG9QaXBlbGluZUZvclRleHQySW1hZ2UuZnJvbV9wcmV0cmFpbmVkKCUyMnJ1bndheW1sJTJGc3RhYmxlLWRpZmZ1c2lvbi12MS01JTIyKSUwQWltYWdlJTIwJTNEJTIwcGlwZWxpbmUocHJvbXB0KS5pbWFnZXMlNUIwJTVE",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image

	<span class="hljs-meta">>>> </span>pipeline = AutoPipelineForText2Image.from_pretrained(<span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>)
	<span class="hljs-meta">>>> </span>image = pipeline(prompt).images[<span class="hljs-number">0</span>]`,wrap:!1}}),{c(){n=l("p"),n.textContent=u,a=i(),_(s.$$.fragment)},l(t){n=p(t,"P",{"data-svelte-h":!0}),c(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=r(t),b(s.$$.fragment,t)},m(t,h){g(t,n,h),g(t,a,h),w(s,t,h),f=!0},p:L,i(t){f\|\|(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(m(n),m(a)),$(s,t)}}}function xo(x){let n,u;return n=new D({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEF1dG9QaXBlbGluZUZvclRleHQySW1hZ2UlMkMlMjBBdXRvUGlwZWxpbmVGb3JJbWFnZTJJbWFnZSUwQSUwQXBpcGVfaTJpJTIwJTNEJTIwQXV0b1BpcGVsaW5lRm9ySW1hZ2UySW1hZ2UuZnJvbV9wcmV0cmFpbmVkKCUwQSUyMCUyMCUyMCUyMCUyMnJ1bndheW1sJTJGc3RhYmxlLWRpZmZ1c2lvbi12MS01JTIyJTJDJTIwcmVxdWlyZXNfc2FmZXR5X2NoZWNrZXIlM0RGYWxzZSUwQSklMEElMEFwaXBlX3QyaSUyMCUzRCUyMEF1dG9QaXBlbGluZUZvclRleHQySW1hZ2UuZnJvbV9waXBlKHBpcGVfaTJpKSUwQWltYWdlJTIwJTNEJTIwcGlwZV90MmkocHJvbXB0KS5pbWFnZXMlNUIwJTVE",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image, AutoPipelineForImage2Image

	<span class="hljs-meta">>>> </span>pipe_i2i = AutoPipelineForImage2Image.from_pretrained(
	<span class="hljs-meta">... </span> <span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>, requires_safety_checker=<span class="hljs-literal">False</span>
	<span class="hljs-meta">... </span>)

	<span class="hljs-meta">>>> </span>pipe_t2i = AutoPipelineForText2Image.from_pipe(pipe_i2i)
	<span class="hljs-meta">>>> </span>image = pipe_t2i(prompt).images[<span class="hljs-number">0</span>]`,wrap:!1}}),{c(){_(n.$$.fragment)},l(a){b(n.$$.fragment,a)},m(a,s){w(n,a,s),u=!0},p:L,i(a){u\|\|(y(n.$$.fragment,a),u=!0)},o(a){v(n.$$.fragment,a),u=!1},d(a){$(n,a)}}}function To(x){let n,u="If you get the error message below, you need to finetune the weights for your downstream task:",a,s,f;return s=new D({props:{code:"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",highlighted:`Some weights <span class="hljs-keyword">of</span> UNet2DConditionModel were <span class="hljs-keyword">not</span> initialized <span class="hljs-built_in">from</span> <span class="hljs-keyword">the</span> model checkpoint <span class="hljs-keyword">at</span> runwayml/stable-diffusion-v1<span class="hljs-number">-5</span> <span class="hljs-keyword">and</span> are newly initialized because <span class="hljs-keyword">the</span> shapes did <span class="hljs-keyword">not</span> match:
	- conv_in.weight: found shape torch.Size([<span class="hljs-number">320</span>, <span class="hljs-number">4</span>, <span class="hljs-number">3</span>, <span class="hljs-number">3</span>]) <span class="hljs-keyword">in</span> <span class="hljs-keyword">the</span> checkpoint <span class="hljs-keyword">and</span> torch.Size([<span class="hljs-number">320</span>, <span class="hljs-number">9</span>, <span class="hljs-number">3</span>, <span class="hljs-number">3</span>]) <span class="hljs-keyword">in</span> <span class="hljs-keyword">the</span> model instantiated
	You should probably TRAIN this model <span class="hljs-keyword">on</span> <span class="hljs-title">a</span> <span class="hljs-title">down-stream</span> <span class="hljs-title">task</span> <span class="hljs-title">to</span> <span class="hljs-title">be</span> <span class="hljs-title">able</span> <span class="hljs-title">to</span> <span class="hljs-title">use</span> <span class="hljs-title">it</span> <span class="hljs-title">for</span> <span class="hljs-title">predictions</span> <span class="hljs-title">and</span> <span class="hljs-title">inference</span>.`,wrap:!1}}),{c(){n=l("p"),n.textContent=u,a=i(),_(s.$$.fragment)},l(t){n=p(t,"P",{"data-svelte-h":!0}),c(n)!=="svelte-xueb0m"&&(n.textContent=u),a=r(t),b(s.$$.fragment,t)},m(t,h){g(t,n,h),g(t,a,h),w(s,t,h),f=!0},p:L,i(t){f\|\|(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(m(n),m(a)),$(s,t)}}}function Io(x){let n,u=`To use private or <a href="https://huggingface.co/docs/hub/models-gated#gated-models" rel="nofollow">gated</a> models, log-in with
	<code>huggingface-cli login</code>.`;return{c(){n=l("p"),n.innerHTML=u},l(a){n=p(a,"P",{"data-svelte-h":!0}),c(n)!=="svelte-x73rgs"&&(n.innerHTML=u)},m(a,s){g(a,n,s)},p:L,d(a){a&&m(n)}}}function Mo(x){let n,u="Examples:",a,s,f;return s=new D({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEF1dG9QaXBlbGluZUZvckltYWdlMkltYWdlJTBBJTBBcGlwZWxpbmUlMjAlM0QlMjBBdXRvUGlwZWxpbmVGb3JJbWFnZTJJbWFnZS5mcm9tX3ByZXRyYWluZWQoJTIycnVud2F5bWwlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTUlMjIpJTBBaW1hZ2UlMjAlM0QlMjBwaXBlbGluZShwcm9tcHQlMkMlMjBpbWFnZSkuaW1hZ2VzJTVCMCU1RA==",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForImage2Image

	<span class="hljs-meta">>>> </span>pipeline = AutoPipelineForImage2Image.from_pretrained(<span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>)
	<span class="hljs-meta">>>> </span>image = pipeline(prompt, image).images[<span class="hljs-number">0</span>]`,wrap:!1}}),{c(){n=l("p"),n.textContent=u,a=i(),_(s.$$.fragment)},l(t){n=p(t,"P",{"data-svelte-h":!0}),c(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=r(t),b(s.$$.fragment,t)},m(t,h){g(t,n,h),g(t,a,h),w(s,t,h),f=!0},p:L,i(t){f\|\|(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(m(n),m(a)),$(s,t)}}}function jo(x){let n,u="Examples:",a,s,f;return s=new D({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEF1dG9QaXBlbGluZUZvclRleHQySW1hZ2UlMkMlMjBBdXRvUGlwZWxpbmVGb3JJbWFnZTJJbWFnZSUwQSUwQXBpcGVfdDJpJTIwJTNEJTIwQXV0b1BpcGVsaW5lRm9yVGV4dDJJbWFnZS5mcm9tX3ByZXRyYWluZWQoJTBBJTIwJTIwJTIwJTIwJTIycnVud2F5bWwlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTUlMjIlMkMlMjByZXF1aXJlc19zYWZldHlfY2hlY2tlciUzREZhbHNlJTBBKSUwQSUwQXBpcGVfaTJpJTIwJTNEJTIwQXV0b1BpcGVsaW5lRm9ySW1hZ2UySW1hZ2UuZnJvbV9waXBlKHBpcGVfdDJpKSUwQWltYWdlJTIwJTNEJTIwcGlwZV9pMmkocHJvbXB0JTJDJTIwaW1hZ2UpLmltYWdlcyU1QjAlNUQ=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image, AutoPipelineForImage2Image

	<span class="hljs-meta">>>> </span>pipe_t2i = AutoPipelineForText2Image.from_pretrained(
	<span class="hljs-meta">... </span> <span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>, requires_safety_checker=<span class="hljs-literal">False</span>
	<span class="hljs-meta">... </span>)

	<span class="hljs-meta">>>> </span>pipe_i2i = AutoPipelineForImage2Image.from_pipe(pipe_t2i)
	<span class="hljs-meta">>>> </span>image = pipe_i2i(prompt, image).images[<span class="hljs-number">0</span>]`,wrap:!1}}),{c(){n=l("p"),n.textContent=u,a=i(),_(s.$$.fragment)},l(t){n=p(t,"P",{"data-svelte-h":!0}),c(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=r(t),b(s.$$.fragment,t)},m(t,h){g(t,n,h),g(t,a,h),w(s,t,h),f=!0},p:L,i(t){f\|\|(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(m(n),m(a)),$(s,t)}}}function Uo(x){let n,u="If you get the error message below, you need to finetune the weights for your downstream task:",a,s,f;return s=new D({props:{code:"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",highlighted:`Some weights <span class="hljs-keyword">of</span> UNet2DConditionModel were <span class="hljs-keyword">not</span> initialized <span class="hljs-built_in">from</span> <span class="hljs-keyword">the</span> model checkpoint <span class="hljs-keyword">at</span> runwayml/stable-diffusion-v1<span class="hljs-number">-5</span> <span class="hljs-keyword">and</span> are newly initialized because <span class="hljs-keyword">the</span> shapes did <span class="hljs-keyword">not</span> match:
	- conv_in.weight: found shape torch.Size([<span class="hljs-number">320</span>, <span class="hljs-number">4</span>, <span class="hljs-number">3</span>, <span class="hljs-number">3</span>]) <span class="hljs-keyword">in</span> <span class="hljs-keyword">the</span> checkpoint <span class="hljs-keyword">and</span> torch.Size([<span class="hljs-number">320</span>, <span class="hljs-number">9</span>, <span class="hljs-number">3</span>, <span class="hljs-number">3</span>]) <span class="hljs-keyword">in</span> <span class="hljs-keyword">the</span> model instantiated
	You should probably TRAIN this model <span class="hljs-keyword">on</span> <span class="hljs-title">a</span> <span class="hljs-title">down-stream</span> <span class="hljs-title">task</span> <span class="hljs-title">to</span> <span class="hljs-title">be</span> <span class="hljs-title">able</span> <span class="hljs-title">to</span> <span class="hljs-title">use</span> <span class="hljs-title">it</span> <span class="hljs-title">for</span> <span class="hljs-title">predictions</span> <span class="hljs-title">and</span> <span class="hljs-title">inference</span>.`,wrap:!1}}),{c(){n=l("p"),n.textContent=u,a=i(),_(s.$$.fragment)},l(t){n=p(t,"P",{"data-svelte-h":!0}),c(n)!=="svelte-xueb0m"&&(n.textContent=u),a=r(t),b(s.$$.fragment,t)},m(t,h){g(t,n,h),g(t,a,h),w(s,t,h),f=!0},p:L,i(t){f\|\|(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(m(n),m(a)),$(s,t)}}}function Po(x){let n,u=`To use private or <a href="https://huggingface.co/docs/hub/models-gated#gated-models" rel="nofollow">gated</a> models, log-in with
	<code>huggingface-cli login</code>.`;return{c(){n=l("p"),n.innerHTML=u},l(a){n=p(a,"P",{"data-svelte-h":!0}),c(n)!=="svelte-x73rgs"&&(n.innerHTML=u)},m(a,s){g(a,n,s)},p:L,d(a){a&&m(n)}}}function ko(x){let n,u="Examples:",a,s,f;return s=new D({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEF1dG9QaXBlbGluZUZvcklucGFpbnRpbmclMEElMEFwaXBlbGluZSUyMCUzRCUyMEF1dG9QaXBlbGluZUZvcklucGFpbnRpbmcuZnJvbV9wcmV0cmFpbmVkKCUyMnJ1bndheW1sJTJGc3RhYmxlLWRpZmZ1c2lvbi12MS01JTIyKSUwQWltYWdlJTIwJTNEJTIwcGlwZWxpbmUocHJvbXB0JTJDJTIwaW1hZ2UlM0Rpbml0X2ltYWdlJTJDJTIwbWFza19pbWFnZSUzRG1hc2tfaW1hZ2UpLmltYWdlcyU1QjAlNUQ=",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForInpainting

	<span class="hljs-meta">>>> </span>pipeline = AutoPipelineForInpainting.from_pretrained(<span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>)
	<span class="hljs-meta">>>> </span>image = pipeline(prompt, image=init_image, mask_image=mask_image).images[<span class="hljs-number">0</span>]`,wrap:!1}}),{c(){n=l("p"),n.textContent=u,a=i(),_(s.$$.fragment)},l(t){n=p(t,"P",{"data-svelte-h":!0}),c(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=r(t),b(s.$$.fragment,t)},m(t,h){g(t,n,h),g(t,a,h),w(s,t,h),f=!0},p:L,i(t){f\|\|(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(m(n),m(a)),$(s,t)}}}function Fo(x){let n,u="Examples:",a,s,f;return s=new D({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image, AutoPipelineForInpainting

	<span class="hljs-meta">>>> </span>pipe_t2i = AutoPipelineForText2Image.from_pretrained(
	<span class="hljs-meta">... </span> <span class="hljs-string">"DeepFloyd/IF-I-XL-v1.0"</span>, requires_safety_checker=<span class="hljs-literal">False</span>
	<span class="hljs-meta">... </span>)

	<span class="hljs-meta">>>> </span>pipe_inpaint = AutoPipelineForInpainting.from_pipe(pipe_t2i)
	<span class="hljs-meta">>>> </span>image = pipe_inpaint(prompt, image=init_image, mask_image=mask_image).images[<span class="hljs-number">0</span>]`,wrap:!1}}),{c(){n=l("p"),n.textContent=u,a=i(),_(s.$$.fragment)},l(t){n=p(t,"P",{"data-svelte-h":!0}),c(n)!=="svelte-kvfsh7"&&(n.textContent=u),a=r(t),b(s.$$.fragment,t)},m(t,h){g(t,n,h),g(t,a,h),w(s,t,h),f=!0},p:L,i(t){f\|\|(y(s.$$.fragment,t),f=!0)},o(t){v(s.$$.fragment,t),f=!1},d(t){t&&(m(n),m(a)),$(s,t)}}}function Jo(x){let n,u,a,s,f,t,h,$n="The <code>AutoPipeline</code> is designed to make it easy to load a checkpoint for a task without needing to know the specific pipeline class. Based on the task, the <code>AutoPipeline</code> automatically retrieves the correct pipeline class from the checkpoint <code>model_index.json</code> file.",it,N,rt,re,lt,k,le,bt,ye,xn=`<a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForText2Image">AutoPipelineForText2Image</a> is a generic pipeline class that instantiates a text-to-image pipeline class. The
	specific underlying pipeline class is automatically selected from either the
	<a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForText2Image.from_pretrained">from_pretrained()</a> or <a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForText2Image.from_pipe">from_pipe()</a> methods.`,wt,ve,Tn="This class cannot be instantiated using <code>__init__()</code> (throws an error).",yt,$e,In="Class attributes:",vt,xe,Mn=`<li><strong>config_name</strong> (<code>str</code>) — The configuration filename that stores the class and module names of all the
	diffusion pipeline’s components.</li>`,$t,T,pe,xt,Te,jn="Instantiates a text-to-image Pytorch diffusion pipeline from pretrained pipeline weight.",Tt,Ie,Un="The from_pretrained() method takes care of returning the correct pipeline class instance by:",It,Me,Pn=`<li>Detect the pipeline class of the pretrained_model_or_path based on the _class_name property of its
	config object</li> <li>Find the text-to-image pipeline linked to the pipeline class using pattern matching on pipeline class
	name.</li>`,Mt,je,kn='If a <code>controlnet</code> argument is passed, it will instantiate a <a href="/docs/diffusers/main/en/api/pipelines/controlnet#diffusers.StableDiffusionControlNetPipeline">StableDiffusionControlNetPipeline</a> object.',jt,Ue,Fn="The pipeline is set in evaluation mode (<code>model.eval()</code>) by default.",Ut,Q,Pt,E,kt,q,Ft,A,de,Jt,Pe,Jn="Instantiates a text-to-image Pytorch diffusion pipeline from another instantiated diffusion pipeline class.",Zt,ke,Zn=`The from_pipe() method takes care of returning the correct pipeline class instance by finding the text-to-image
	pipeline linked to the pipeline class using pattern matching on pipeline class name.`,Ct,Fe,Cn=`All the modules the pipeline contains will be used to initialize the new pipeline without reallocating
	additional memory.`,Gt,Je,Gn="The pipeline is set in evaluation mode (<code>model.eval()</code>) by default.",At,K,pt,ce,dt,F,me,Wt,Ze,An=`<a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForImage2Image">AutoPipelineForImage2Image</a> is a generic pipeline class that instantiates an image-to-image pipeline class. The
	specific underlying pipeline class is automatically selected from either the
	<a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForImage2Image.from_pretrained">from_pretrained()</a> or <a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForImage2Image.from_pipe">from_pipe()</a> methods.`,Bt,Ce,Wn="This class cannot be instantiated using <code>__init__()</code> (throws an error).",Ht,Ge,Bn="Class attributes:",St,Ae,Hn=`<li><strong>config_name</strong> (<code>str</code>) — The configuration filename that stores the class and module names of all the
	diffusion pipeline’s components.</li>`,Vt,I,fe,Lt,We,Sn="Instantiates a image-to-image Pytorch diffusion pipeline from pretrained pipeline weight.",Rt,Be,Vn="The from_pretrained() method takes care of returning the correct pipeline class instance by:",Xt,He,Ln=`<li>Detect the pipeline class of the pretrained_model_or_path based on the _class_name property of its
	config object</li> <li>Find the image-to-image pipeline linked to the pipeline class using pattern matching on pipeline class
	name.</li>`,zt,Se,Rn=`If a <code>controlnet</code> argument is passed, it will instantiate a <a href="/docs/diffusers/main/en/api/pipelines/controlnet#diffusers.StableDiffusionControlNetImg2ImgPipeline">StableDiffusionControlNetImg2ImgPipeline</a>
	object.`,Yt,Ve,Xn="The pipeline is set in evaluation mode (<code>model.eval()</code>) by default.",Dt,O,Nt,ee,Qt,te,Et,W,ue,qt,Le,zn="Instantiates a image-to-image Pytorch diffusion pipeline from another instantiated diffusion pipeline class.",Kt,Re,Yn=`The from_pipe() method takes care of returning the correct pipeline class instance by finding the
	image-to-image pipeline linked to the pipeline class using pattern matching on pipeline class name.`,Ot,Xe,Dn=`All the modules the pipeline contains will be used to initialize the new pipeline without reallocating
	additional memory.`,en,ze,Nn="The pipeline is set in evaluation mode (<code>model.eval()</code>) by default.",tn,ne,ct,he,mt,J,ge,nn,Ye,Qn=`<a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForInpainting">AutoPipelineForInpainting</a> is a generic pipeline class that instantiates an inpainting pipeline class. The
	specific underlying pipeline class is automatically selected from either the
	<a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForInpainting.from_pretrained">from_pretrained()</a> or <a href="/docs/diffusers/main/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForInpainting.from_pipe">from_pipe()</a> methods.`,on,De,En="This class cannot be instantiated using <code>__init__()</code> (throws an error).",an,Ne,qn="Class attributes:",sn,Qe,Kn=`<li><strong>config_name</strong> (<code>str</code>) — The configuration filename that stores the class and module names of all the
	diffusion pipeline’s components.</li>`,rn,M,_e,ln,Ee,On="Instantiates a inpainting Pytorch diffusion pipeline from pretrained pipeline weight.",pn,qe,eo="The from_pretrained() method takes care of returning the correct pipeline class instance by:",dn,Ke,to=`<li>Detect the pipeline class of the pretrained_model_or_path based on the _class_name property of its
	config object</li> <li>Find the inpainting pipeline linked to the pipeline class using pattern matching on pipeline class name.</li>`,cn,Oe,no=`If a <code>controlnet</code> argument is passed, it will instantiate a <a href="/docs/diffusers/main/en/api/pipelines/controlnet#diffusers.StableDiffusionControlNetInpaintPipeline">StableDiffusionControlNetInpaintPipeline</a>
	object.`,mn,et,oo="The pipeline is set in evaluation mode (<code>model.eval()</code>) by default.",fn,oe,un,ae,hn,se,gn,B,be,_n,tt,ao="Instantiates a inpainting Pytorch diffusion pipeline from another instantiated diffusion pipeline class.",bn,nt,so=`The from_pipe() method takes care of returning the correct pipeline class instance by finding the inpainting
	pipeline linked to the pipeline class using pattern matching on pipeline class name.`,wn,ot,io=`All the modules the pipeline class contain will be used to initialize the new pipeline without reallocating
	additional memory.`,yn,at,ro="The pipeline is set in evaluation mode (<code>model.eval()</code>) by default.",vn,ie,ft,we,ut,st,ht;return f=new _t({props:{title:"AutoPipeline",local:"autopipeline",headingTag:"h1"}}),N=new gt({props:{warning:!1,$$slots:{default:[wo]},$$scope:{ctx:x}}}),re=new _t({props:{title:"AutoPipelineForText2Image",local:"diffusers.AutoPipelineForText2Image",headingTag:"h2"}}),le=new z({props:{name:"class diffusers.AutoPipelineForText2Image",anchor:"diffusers.AutoPipelineForText2Image",parameters:[{name:"args",val:""},{name:"kwargs",val:""}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L220"}}),pe=new z({props:{name:"from_pretrained",anchor:"diffusers.AutoPipelineForText2Image.from_pretrained",parameters:[{name:"pretrained_model_or_path",val:""},{name:"*kwargs",val:""}],parametersDescription:[{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.pretrained_model_or_path",description:`<strong>pretrained_model_or_path</strong> (<code>str</code> or <code>os.PathLike</code>, <em>optional</em>) —
	Can be either:</p>
	<ul>
	<li>A string, the <em>repo id</em> (for example <code>CompVis/ldm-text2im-large-256</code>) of a pretrained pipeline
	hosted on the Hub.</li>
	<li>A path to a <em>directory</em> (for example <code>./my_pipeline_directory/</code>) containing pipeline weights
	saved using
	<a href="/docs/diffusers/main/en/api/pipelines/overview#diffusers.DiffusionPipeline.save_pretrained">save_pretrained()</a>.</li>
	</ul>`,name:"pretrained_model_or_path"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.torch_dtype",description:`<strong>torch_dtype</strong> (<code>str</code> or <code>torch.dtype</code>, <em>optional</em>) —
	Override the default <code>torch.dtype</code> and load the model with another dtype. If “auto” is passed, the
	dtype is automatically derived from the model’s weights.`,name:"torch_dtype"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) —
	Whether or not to force the (re-)download of the model weights and configuration files, overriding the
	cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) —
	Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
	is not used.`,name:"cache_dir"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) —
	A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.output_loading_info(bool,",description:`<strong>output_loading_info(<code>bool</code>,</strong> <em>optional</em>, defaults to <code>False</code>) —
	Whether or not to also return a dictionary containing missing keys, unexpected keys and error messages.`,name:"output_loading_info(bool,"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) —
	Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
	won’t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) —
	The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
	<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"main"</code>) —
	The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
	allowed by Git.`,name:"revision"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.custom_revision",description:`<strong>custom_revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"main"</code>) —
	The specific model version to use. It can be a branch name, a tag name, or a commit id similar to
	<code>revision</code> when loading a custom pipeline from the Hub. It can be a 🤗 Diffusers version when loading a
	custom pipeline from GitHub, otherwise it defaults to <code>"main"</code> when loading from the Hub.`,name:"custom_revision"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.mirror",description:`<strong>mirror</strong> (<code>str</code>, <em>optional</em>) —
	Mirror source to resolve accessibility issues if you’re downloading a model in China. We do not
	guarantee the timeliness or safety of the source, and you should refer to the mirror site for more
	information.`,name:"mirror"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.device_map",description:`<strong>device_map</strong> (<code>str</code> or <code>Dict[str, Union[int, str, torch.device]]</code>, <em>optional</em>) —
	A map that specifies where each submodule should go. It doesn’t need to be defined for each
	parameter/buffer name; once a given module name is inside, every submodule of it will be sent to the
	same device.</p>
	<p>Set <code>device_map="auto"</code> to have 🤗 Accelerate automatically compute the most optimized <code>device_map</code>. For
	more information about each option see <a href="https://hf.co/docs/accelerate/main/en/usage_guides/big_modeling#designing-a-device-map" rel="nofollow">designing a device
	map</a>.`,name:"device_map"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.max_memory",description:`<strong>max_memory</strong> (<code>Dict</code>, <em>optional</em>) —
	A dictionary device identifier for the maximum memory. Will default to the maximum memory available for
	each GPU and the available CPU RAM if unset.`,name:"max_memory"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.offload_folder",description:`<strong>offload_folder</strong> (<code>str</code> or <code>os.PathLike</code>, <em>optional</em>) —
	The path to offload weights if device_map contains the value <code>"disk"</code>.`,name:"offload_folder"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.offload_state_dict",description:`<strong>offload_state_dict</strong> (<code>bool</code>, <em>optional</em>) —
	If <code>True</code>, temporarily offloads the CPU state dict to the hard drive to avoid running out of CPU RAM if
	the weight of the CPU state dict + the biggest shard of the checkpoint does not fit. Defaults to <code>True</code>
	when there is some disk offload.`,name:"offload_state_dict"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code> if torch version >= 1.9.0 else <code>False</code>) —
	Speed up model loading only loading the pretrained weights and not initializing the weights. This also
	tries to not use more than 1x model size in CPU memory (including peak memory) while loading the model.
	Only supported for PyTorch >= 1.9.0. If you are using an older version of PyTorch, setting this
	argument to <code>True</code> will raise an error.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.use_safetensors",description:`<strong>use_safetensors</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>None</code>) —
	If set to <code>None</code>, the safetensors weights are downloaded if they’re available <strong>and</strong> if the
	safetensors library is installed. If set to <code>True</code>, the model is forcibly loaded from safetensors
	weights. If set to <code>False</code>, safetensors weights are not loaded.`,name:"use_safetensors"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.kwargs",description:`<strong>kwargs</strong> (remaining dictionary of keyword arguments, <em>optional</em>) —
	Can be used to overwrite load and saveable variables (the pipeline components of the specific pipeline
	class). The overwritten components are passed directly to the pipelines <code>__init__</code> method. See example
	below for more information.`,name:"kwargs"},{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.variant",description:`<strong>variant</strong> (<code>str</code>, <em>optional</em>) —
	Load weights from a specified variant filename such as <code>"fp16"</code> or <code>"ema"</code>. This is ignored when
	loading <code>from_flax</code>.`,name:"variant"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L245"}}),Q=new Y({props:{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.example",$$slots:{default:[yo]},$$scope:{ctx:x}}}),E=new gt({props:{$$slots:{default:[vo]},$$scope:{ctx:x}}}),q=new Y({props:{anchor:"diffusers.AutoPipelineForText2Image.from_pretrained.example-2",$$slots:{default:[$o]},$$scope:{ctx:x}}}),de=new z({props:{name:"from_pipe",anchor:"diffusers.AutoPipelineForText2Image.from_pipe",parameters:[{name:"pipeline",val:""},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.AutoPipelineForText2Image.from_pipe.pipeline",description:`<strong>pipeline</strong> (<code>DiffusionPipeline</code>) —
	an instantiated <code>DiffusionPipeline</code> object`,name:"pipeline"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L391"}}),K=new Y({props:{anchor:"diffusers.AutoPipelineForText2Image.from_pipe.example",$$slots:{default:[xo]},$$scope:{ctx:x}}}),ce=new _t({props:{title:"AutoPipelineForImage2Image",local:"diffusers.AutoPipelineForImage2Image",headingTag:"h2"}}),me=new z({props:{name:"class diffusers.AutoPipelineForImage2Image",anchor:"diffusers.AutoPipelineForImage2Image",parameters:[{name:"args",val:""},{name:"kwargs",val:""}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L506"}}),fe=new z({props:{name:"from_pretrained",anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained",parameters:[{name:"pretrained_model_or_path",val:""},{name:"*kwargs",val:""}],parametersDescription:[{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.pretrained_model_or_path",description:`<strong>pretrained_model_or_path</strong> (<code>str</code> or <code>os.PathLike</code>, <em>optional</em>) —
	Can be either:</p>
	<ul>
	<li>A string, the <em>repo id</em> (for example <code>CompVis/ldm-text2im-large-256</code>) of a pretrained pipeline
	hosted on the Hub.</li>
	<li>A path to a <em>directory</em> (for example <code>./my_pipeline_directory/</code>) containing pipeline weights
	saved using
	<a href="/docs/diffusers/main/en/api/pipelines/overview#diffusers.DiffusionPipeline.save_pretrained">save_pretrained()</a>.</li>
	</ul>`,name:"pretrained_model_or_path"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.torch_dtype",description:`<strong>torch_dtype</strong> (<code>str</code> or <code>torch.dtype</code>, <em>optional</em>) —
	Override the default <code>torch.dtype</code> and load the model with another dtype. If “auto” is passed, the
	dtype is automatically derived from the model’s weights.`,name:"torch_dtype"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) —
	Whether or not to force the (re-)download of the model weights and configuration files, overriding the
	cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) —
	Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
	is not used.`,name:"cache_dir"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) —
	A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.output_loading_info(bool,",description:`<strong>output_loading_info(<code>bool</code>,</strong> <em>optional</em>, defaults to <code>False</code>) —
	Whether or not to also return a dictionary containing missing keys, unexpected keys and error messages.`,name:"output_loading_info(bool,"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) —
	Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
	won’t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) —
	The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
	<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"main"</code>) —
	The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
	allowed by Git.`,name:"revision"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.custom_revision",description:`<strong>custom_revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"main"</code>) —
	The specific model version to use. It can be a branch name, a tag name, or a commit id similar to
	<code>revision</code> when loading a custom pipeline from the Hub. It can be a 🤗 Diffusers version when loading a
	custom pipeline from GitHub, otherwise it defaults to <code>"main"</code> when loading from the Hub.`,name:"custom_revision"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.mirror",description:`<strong>mirror</strong> (<code>str</code>, <em>optional</em>) —
	Mirror source to resolve accessibility issues if you’re downloading a model in China. We do not
	guarantee the timeliness or safety of the source, and you should refer to the mirror site for more
	information.`,name:"mirror"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.device_map",description:`<strong>device_map</strong> (<code>str</code> or <code>Dict[str, Union[int, str, torch.device]]</code>, <em>optional</em>) —
	A map that specifies where each submodule should go. It doesn’t need to be defined for each
	parameter/buffer name; once a given module name is inside, every submodule of it will be sent to the
	same device.</p>
	<p>Set <code>device_map="auto"</code> to have 🤗 Accelerate automatically compute the most optimized <code>device_map</code>. For
	more information about each option see <a href="https://hf.co/docs/accelerate/main/en/usage_guides/big_modeling#designing-a-device-map" rel="nofollow">designing a device
	map</a>.`,name:"device_map"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.max_memory",description:`<strong>max_memory</strong> (<code>Dict</code>, <em>optional</em>) —
	A dictionary device identifier for the maximum memory. Will default to the maximum memory available for
	each GPU and the available CPU RAM if unset.`,name:"max_memory"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.offload_folder",description:`<strong>offload_folder</strong> (<code>str</code> or <code>os.PathLike</code>, <em>optional</em>) —
	The path to offload weights if device_map contains the value <code>"disk"</code>.`,name:"offload_folder"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.offload_state_dict",description:`<strong>offload_state_dict</strong> (<code>bool</code>, <em>optional</em>) —
	If <code>True</code>, temporarily offloads the CPU state dict to the hard drive to avoid running out of CPU RAM if
	the weight of the CPU state dict + the biggest shard of the checkpoint does not fit. Defaults to <code>True</code>
	when there is some disk offload.`,name:"offload_state_dict"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code> if torch version >= 1.9.0 else <code>False</code>) —
	Speed up model loading only loading the pretrained weights and not initializing the weights. This also
	tries to not use more than 1x model size in CPU memory (including peak memory) while loading the model.
	Only supported for PyTorch >= 1.9.0. If you are using an older version of PyTorch, setting this
	argument to <code>True</code> will raise an error.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.use_safetensors",description:`<strong>use_safetensors</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>None</code>) —
	If set to <code>None</code>, the safetensors weights are downloaded if they’re available <strong>and</strong> if the
	safetensors library is installed. If set to <code>True</code>, the model is forcibly loaded from safetensors
	weights. If set to <code>False</code>, safetensors weights are not loaded.`,name:"use_safetensors"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.kwargs",description:`<strong>kwargs</strong> (remaining dictionary of keyword arguments, <em>optional</em>) —
	Can be used to overwrite load and saveable variables (the pipeline components of the specific pipeline
	class). The overwritten components are passed directly to the pipelines <code>__init__</code> method. See example
	below for more information.`,name:"kwargs"},{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.variant",description:`<strong>variant</strong> (<code>str</code>, <em>optional</em>) —
	Load weights from a specified variant filename such as <code>"fp16"</code> or <code>"ema"</code>. This is ignored when
	loading <code>from_flax</code>.`,name:"variant"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L531"}}),O=new Y({props:{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.example",$$slots:{default:[To]},$$scope:{ctx:x}}}),ee=new gt({props:{$$slots:{default:[Io]},$$scope:{ctx:x}}}),te=new Y({props:{anchor:"diffusers.AutoPipelineForImage2Image.from_pretrained.example-2",$$slots:{default:[Mo]},$$scope:{ctx:x}}}),ue=new z({props:{name:"from_pipe",anchor:"diffusers.AutoPipelineForImage2Image.from_pipe",parameters:[{name:"pipeline",val:""},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.AutoPipelineForImage2Image.from_pipe.pipeline",description:`<strong>pipeline</strong> (<code>DiffusionPipeline</code>) —
	an instantiated <code>DiffusionPipeline</code> object`,name:"pipeline"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L683"}}),ne=new Y({props:{anchor:"diffusers.AutoPipelineForImage2Image.from_pipe.example",$$slots:{default:[jo]},$$scope:{ctx:x}}}),he=new _t({props:{title:"AutoPipelineForInpainting",local:"diffusers.AutoPipelineForInpainting",headingTag:"h2"}}),ge=new z({props:{name:"class diffusers.AutoPipelineForInpainting",anchor:"diffusers.AutoPipelineForInpainting",parameters:[{name:"args",val:""},{name:"kwargs",val:""}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L804"}}),_e=new z({props:{name:"from_pretrained",anchor:"diffusers.AutoPipelineForInpainting.from_pretrained",parameters:[{name:"pretrained_model_or_path",val:""},{name:"*kwargs",val:""}],parametersDescription:[{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.pretrained_model_or_path",description:`<strong>pretrained_model_or_path</strong> (<code>str</code> or <code>os.PathLike</code>, <em>optional</em>) —
	Can be either:</p>
	<ul>
	<li>A string, the <em>repo id</em> (for example <code>CompVis/ldm-text2im-large-256</code>) of a pretrained pipeline
	hosted on the Hub.</li>
	<li>A path to a <em>directory</em> (for example <code>./my_pipeline_directory/</code>) containing pipeline weights
	saved using
	<a href="/docs/diffusers/main/en/api/pipelines/overview#diffusers.DiffusionPipeline.save_pretrained">save_pretrained()</a>.</li>
	</ul>`,name:"pretrained_model_or_path"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.torch_dtype",description:`<strong>torch_dtype</strong> (<code>str</code> or <code>torch.dtype</code>, <em>optional</em>) —
	Override the default <code>torch.dtype</code> and load the model with another dtype. If “auto” is passed, the
	dtype is automatically derived from the model’s weights.`,name:"torch_dtype"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) —
	Whether or not to force the (re-)download of the model weights and configuration files, overriding the
	cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) —
	Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
	is not used.`,name:"cache_dir"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) —
	A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.output_loading_info(bool,",description:`<strong>output_loading_info(<code>bool</code>,</strong> <em>optional</em>, defaults to <code>False</code>) —
	Whether or not to also return a dictionary containing missing keys, unexpected keys and error messages.`,name:"output_loading_info(bool,"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) —
	Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
	won’t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) —
	The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
	<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"main"</code>) —
	The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
	allowed by Git.`,name:"revision"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.custom_revision",description:`<strong>custom_revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"main"</code>) —
	The specific model version to use. It can be a branch name, a tag name, or a commit id similar to
	<code>revision</code> when loading a custom pipeline from the Hub. It can be a 🤗 Diffusers version when loading a
	custom pipeline from GitHub, otherwise it defaults to <code>"main"</code> when loading from the Hub.`,name:"custom_revision"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.mirror",description:`<strong>mirror</strong> (<code>str</code>, <em>optional</em>) —
	Mirror source to resolve accessibility issues if you’re downloading a model in China. We do not
	guarantee the timeliness or safety of the source, and you should refer to the mirror site for more
	information.`,name:"mirror"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.device_map",description:`<strong>device_map</strong> (<code>str</code> or <code>Dict[str, Union[int, str, torch.device]]</code>, <em>optional</em>) —
	A map that specifies where each submodule should go. It doesn’t need to be defined for each
	parameter/buffer name; once a given module name is inside, every submodule of it will be sent to the
	same device.</p>
	<p>Set <code>device_map="auto"</code> to have 🤗 Accelerate automatically compute the most optimized <code>device_map</code>. For
	more information about each option see <a href="https://hf.co/docs/accelerate/main/en/usage_guides/big_modeling#designing-a-device-map" rel="nofollow">designing a device
	map</a>.`,name:"device_map"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.max_memory",description:`<strong>max_memory</strong> (<code>Dict</code>, <em>optional</em>) —
	A dictionary device identifier for the maximum memory. Will default to the maximum memory available for
	each GPU and the available CPU RAM if unset.`,name:"max_memory"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.offload_folder",description:`<strong>offload_folder</strong> (<code>str</code> or <code>os.PathLike</code>, <em>optional</em>) —
	The path to offload weights if device_map contains the value <code>"disk"</code>.`,name:"offload_folder"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.offload_state_dict",description:`<strong>offload_state_dict</strong> (<code>bool</code>, <em>optional</em>) —
	If <code>True</code>, temporarily offloads the CPU state dict to the hard drive to avoid running out of CPU RAM if
	the weight of the CPU state dict + the biggest shard of the checkpoint does not fit. Defaults to <code>True</code>
	when there is some disk offload.`,name:"offload_state_dict"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code> if torch version >= 1.9.0 else <code>False</code>) —
	Speed up model loading only loading the pretrained weights and not initializing the weights. This also
	tries to not use more than 1x model size in CPU memory (including peak memory) while loading the model.
	Only supported for PyTorch >= 1.9.0. If you are using an older version of PyTorch, setting this
	argument to <code>True</code> will raise an error.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.use_safetensors",description:`<strong>use_safetensors</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>None</code>) —
	If set to <code>None</code>, the safetensors weights are downloaded if they’re available <strong>and</strong> if the
	safetensors library is installed. If set to <code>True</code>, the model is forcibly loaded from safetensors
	weights. If set to <code>False</code>, safetensors weights are not loaded.`,name:"use_safetensors"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.kwargs",description:`<strong>kwargs</strong> (remaining dictionary of keyword arguments, <em>optional</em>) —
	Can be used to overwrite load and saveable variables (the pipeline components of the specific pipeline
	class). The overwritten components are passed directly to the pipelines <code>__init__</code> method. See example
	below for more information.`,name:"kwargs"},{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.variant",description:`<strong>variant</strong> (<code>str</code>, <em>optional</em>) —
	Load weights from a specified variant filename such as <code>"fp16"</code> or <code>"ema"</code>. This is ignored when
	loading <code>from_flax</code>.`,name:"variant"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L829"}}),oe=new Y({props:{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.example",$$slots:{default:[Uo]},$$scope:{ctx:x}}}),ae=new gt({props:{$$slots:{default:[Po]},$$scope:{ctx:x}}}),se=new Y({props:{anchor:"diffusers.AutoPipelineForInpainting.from_pretrained.example-2",$$slots:{default:[ko]},$$scope:{ctx:x}}}),be=new z({props:{name:"from_pipe",anchor:"diffusers.AutoPipelineForInpainting.from_pipe",parameters:[{name:"pipeline",val:""},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.AutoPipelineForInpainting.from_pipe.pipeline",description:`<strong>pipeline</strong> (<code>DiffusionPipeline</code>) —
	an instantiated <code>DiffusionPipeline</code> object`,name:"pipeline"}],source:"https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/auto_pipeline.py#L979"}}),ie=new Y({props:{anchor:"diffusers.AutoPipelineForInpainting.from_pipe.example",$$slots:{default:[Fo]},$$scope:{ctx:x}}}),we=new bo({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/auto_pipeline.md"}}),{c(){n=l("meta"),u=i(),a=l("p"),s=i(),_(f.$$.fragment),t=i(),h=l("p"),h.innerHTML=$n,it=i(),_(N.$$.fragment),rt=i(),_(re.$$.fragment),lt=i(),k=l("div"),_(le.$$.fragment),bt=i(),ye=l("p"),ye.innerHTML=xn,wt=i(),ve=l("p"),ve.innerHTML=Tn,yt=i(),$e=l("p"),$e.textContent=In,vt=i(),xe=l("ul"),xe.innerHTML=Mn,$t=i(),T=l("div"),_(pe.$$.fragment),xt=i(),Te=l("p"),Te.textContent=jn,Tt=i(),Ie=l("p"),Ie.textContent=Un,It=i(),Me=l("ol"),Me.innerHTML=Pn,Mt=i(),je=l("p"),je.innerHTML=kn,jt=i(),Ue=l("p"),Ue.innerHTML=Fn,Ut=i(),_(Q.$$.fragment),Pt=i(),_(E.$$.fragment),kt=i(),_(q.$$.fragment),Ft=i(),A=l("div"),_(de.$$.fragment),Jt=i(),Pe=l("p"),Pe.textContent=Jn,Zt=i(),ke=l("p"),ke.textContent=Zn,Ct=i(),Fe=l("p"),Fe.textContent=Cn,Gt=i(),Je=l("p"),Je.innerHTML=Gn,At=i(),_(K.$$.fragment),pt=i(),_(ce.$$.fragment),dt=i(),F=l("div"),_(me.$$.fragment),Wt=i(),Ze=l("p"),Ze.innerHTML=An,Bt=i(),Ce=l("p"),Ce.innerHTML=Wn,Ht=i(),Ge=l("p"),Ge.textContent=Bn,St=i(),Ae=l("ul"),Ae.innerHTML=Hn,Vt=i(),I=l("div"),_(fe.$$.fragment),Lt=i(),We=l("p"),We.textContent=Sn,Rt=i(),Be=l("p"),Be.textContent=Vn,Xt=i(),He=l("ol"),He.innerHTML=Ln,zt=i(),Se=l("p"),Se.innerHTML=Rn,Yt=i(),Ve=l("p"),Ve.innerHTML=Xn,Dt=i(),_(O.$$.fragment),Nt=i(),_(ee.$$.fragment),Qt=i(),_(te.$$.fragment),Et=i(),W=l("div"),_(ue.$$.fragment),qt=i(),Le=l("p"),Le.textContent=zn,Kt=i(),Re=l("p"),Re.textContent=Yn,Ot=i(),Xe=l("p"),Xe.textContent=Dn,en=i(),ze=l("p"),ze.innerHTML=Nn,tn=i(),_(ne.$$.fragment),ct=i(),_(he.$$.fragment),mt=i(),J=l("div"),_(ge.$$.fragment),nn=i(),Ye=l("p"),Ye.innerHTML=Qn,on=i(),De=l("p"),De.innerHTML=En,an=i(),Ne=l("p"),Ne.textContent=qn,sn=i(),Qe=l("ul"),Qe.innerHTML=Kn,rn=i(),M=l("div"),_(_e.$$.fragment),ln=i(),Ee=l("p"),Ee.textContent=On,pn=i(),qe=l("p"),qe.textContent=eo,dn=i(),Ke=l("ol"),Ke.innerHTML=to,cn=i(),Oe=l("p"),Oe.innerHTML=no,mn=i(),et=l("p"),et.innerHTML=oo,fn=i(),_(oe.$$.fragment),un=i(),_(ae.$$.fragment),hn=i(),_(se.$$.fragment),gn=i(),B=l("div"),_(be.$$.fragment),_n=i(),tt=l("p"),tt.textContent=ao,bn=i(),nt=l("p"),nt.textContent=so,wn=i(),ot=l("p"),ot.textContent=io,yn=i(),at=l("p"),at.innerHTML=ro,vn=i(),_(ie.$$.fragment),ft=i(),_(we.$$.fragment),ut=i(),st=l("p"),this.h()},l(e){const d=_o("svelte-u9bgzb",document.head);n=p(d,"META",{name:!0,content:!0}),d.forEach(m),u=r(e),a=p(e,"P",{}),R(a).forEach(m),s=r(e),b(f.$$.fragment,e),t=r(e),h=p(e,"P",{"data-svelte-h":!0}),c(h)!=="svelte-10ft6k8"&&(h.innerHTML=$n),it=r(e),b(N.$$.fragment,e),rt=r(e),b(re.$$.fragment,e),lt=r(e),k=p(e,"DIV",{class:!0});var Z=R(k);b(le.$$.fragment,Z),bt=r(Z),ye=p(Z,"P",{"data-svelte-h":!0}),c(ye)!=="svelte-19frpyg"&&(ye.innerHTML=xn),wt=r(Z),ve=p(Z,"P",{"data-svelte-h":!0}),c(ve)!=="svelte-13laq45"&&(ve.innerHTML=Tn),yt=r(Z),$e=p(Z,"P",{"data-svelte-h":!0}),c($e)!=="svelte-wz8va1"&&($e.textContent=In),vt=r(Z),xe=p(Z,"UL",{"data-svelte-h":!0}),c(xe)!=="svelte-56flce"&&(xe.innerHTML=Mn),$t=r(Z),T=p(Z,"DIV",{class:!0});var j=R(T);b(pe.$$.fragment,j),xt=r(j),Te=p(j,"P",{"data-svelte-h":!0}),c(Te)!=="svelte-73gcl"&&(Te.textContent=jn),Tt=r(j),Ie=p(j,"P",{"data-svelte-h":!0}),c(Ie)!=="svelte-3eelph"&&(Ie.textContent=Un),It=r(j),Me=p(j,"OL",{"data-svelte-h":!0}),c(Me)!=="svelte-rrjsq6"&&(Me.innerHTML=Pn),Mt=r(j),je=p(j,"P",{"data-svelte-h":!0}),c(je)!=="svelte-thxdws"&&(je.innerHTML=kn),jt=r(j),Ue=p(j,"P",{"data-svelte-h":!0}),c(Ue)!=="svelte-1p5vgmd"&&(Ue.innerHTML=Fn),Ut=r(j),b(Q.$$.fragment,j),Pt=r(j),b(E.$$.fragment,j),kt=r(j),b(q.$$.fragment,j),j.forEach(m),Ft=r(Z),A=p(Z,"DIV",{class:!0});var H=R(A);b(de.$$.fragment,H),Jt=r(H),Pe=p(H,"P",{"data-svelte-h":!0}),c(Pe)!=="svelte-6rlsyn"&&(Pe.textContent=Jn),Zt=r(H),ke=p(H,"P",{"data-svelte-h":!0}),c(ke)!=="svelte-1im6dea"&&(ke.textContent=Zn),Ct=r(H),Fe=p(H,"P",{"data-svelte-h":!0}),c(Fe)!=="svelte-1u0ofey"&&(Fe.textContent=Cn),Gt=r(H),Je=p(H,"P",{"data-svelte-h":!0}),c(Je)!=="svelte-1p5vgmd"&&(Je.innerHTML=Gn),At=r(H),b(K.$$.fragment,H),H.forEach(m),Z.forEach(m),pt=r(e),b(ce.$$.fragment,e),dt=r(e),F=p(e,"DIV",{class:!0});var C=R(F);b(me.$$.fragment,C),Wt=r(C),Ze=p(C,"P",{"data-svelte-h":!0}),c(Ze)!=="svelte-tofcle"&&(Ze.innerHTML=An),Bt=r(C),Ce=p(C,"P",{"data-svelte-h":!0}),c(Ce)!=="svelte-13laq45"&&(Ce.innerHTML=Wn),Ht=r(C),Ge=p(C,"P",{"data-svelte-h":!0}),c(Ge)!=="svelte-wz8va1"&&(Ge.textContent=Bn),St=r(C),Ae=p(C,"UL",{"data-svelte-h":!0}),c(Ae)!=="svelte-56flce"&&(Ae.innerHTML=Hn),Vt=r(C),I=p(C,"DIV",{class:!0});var U=R(I);b(fe.$$.fragment,U),Lt=r(U),We=p(U,"P",{"data-svelte-h":!0}),c(We)!=="svelte-ehfuat"&&(We.textContent=Sn),Rt=r(U),Be=p(U,"P",{"data-svelte-h":!0}),c(Be)!=="svelte-3eelph"&&(Be.textContent=Vn),Xt=r(U),He=p(U,"OL",{"data-svelte-h":!0}),c(He)!=="svelte-1pj7v4w"&&(He.innerHTML=Ln),zt=r(U),Se=p(U,"P",{"data-svelte-h":!0}),c(Se)!=="svelte-1myktl6"&&(Se.innerHTML=Rn),Yt=r(U),Ve=p(U,"P",{"data-svelte-h":!0}),c(Ve)!=="svelte-1p5vgmd"&&(Ve.innerHTML=Xn),Dt=r(U),b(O.$$.fragment,U),Nt=r(U),b(ee.$$.fragment,U),Qt=r(U),b(te.$$.fragment,U),U.forEach(m),Et=r(C),W=p(C,"DIV",{class:!0});var S=R(W);b(ue.$$.fragment,S),qt=r(S),Le=p(S,"P",{"data-svelte-h":!0}),c(Le)!=="svelte-10ckmdb"&&(Le.textContent=zn),Kt=r(S),Re=p(S,"P",{"data-svelte-h":!0}),c(Re)!=="svelte-3o5yim"&&(Re.textContent=Yn),Ot=r(S),Xe=p(S,"P",{"data-svelte-h":!0}),c(Xe)!=="svelte-1u0ofey"&&(Xe.textContent=Dn),en=r(S),ze=p(S,"P",{"data-svelte-h":!0}),c(ze)!=="svelte-1p5vgmd"&&(ze.innerHTML=Nn),tn=r(S),b(ne.$$.fragment,S),S.forEach(m),C.forEach(m),ct=r(e),b(he.$$.fragment,e),mt=r(e),J=p(e,"DIV",{class:!0});var G=R(J);b(ge.$$.fragment,G),nn=r(G),Ye=p(G,"P",{"data-svelte-h":!0}),c(Ye)!=="svelte-d7r9em"&&(Ye.innerHTML=Qn),on=r(G),De=p(G,"P",{"data-svelte-h":!0}),c(De)!=="svelte-13laq45"&&(De.innerHTML=En),an=r(G),Ne=p(G,"P",{"data-svelte-h":!0}),c(Ne)!=="svelte-wz8va1"&&(Ne.textContent=qn),sn=r(G),Qe=p(G,"UL",{"data-svelte-h":!0}),c(Qe)!=="svelte-56flce"&&(Qe.innerHTML=Kn),rn=r(G),M=p(G,"DIV",{class:!0});var P=R(M);b(_e.$$.fragment,P),ln=r(P),Ee=p(P,"P",{"data-svelte-h":!0}),c(Ee)!=="svelte-1fjqdar"&&(Ee.textContent=On),pn=r(P),qe=p(P,"P",{"data-svelte-h":!0}),c(qe)!=="svelte-3eelph"&&(qe.textContent=eo),dn=r(P),Ke=p(P,"OL",{"data-svelte-h":!0}),c(Ke)!=="svelte-fu4x5s"&&(Ke.innerHTML=to),cn=r(P),Oe=p(P,"P",{"data-svelte-h":!0}),c(Oe)!=="svelte-v2bk1g"&&(Oe.innerHTML=no),mn=r(P),et=p(P,"P",{"data-svelte-h":!0}),c(et)!=="svelte-1p5vgmd"&&(et.innerHTML=oo),fn=r(P),b(oe.$$.fragment,P),un=r(P),b(ae.$$.fragment,P),hn=r(P),b(se.$$.fragment,P),P.forEach(m),gn=r(G),B=p(G,"DIV",{class:!0});var V=R(B);b(be.$$.fragment,V),_n=r(V),tt=p(V,"P",{"data-svelte-h":!0}),c(tt)!=="svelte-1ass5kx"&&(tt.textContent=ao),bn=r(V),nt=p(V,"P",{"data-svelte-h":!0}),c(nt)!=="svelte-1jvxxhk"&&(nt.textContent=so),wn=r(V),ot=p(V,"P",{"data-svelte-h":!0}),c(ot)!=="svelte-16h1ngl"&&(ot.textContent=io),yn=r(V),at=p(V,"P",{"data-svelte-h":!0}),c(at)!=="svelte-1p5vgmd"&&(at.innerHTML=ro),vn=r(V),b(ie.$$.fragment,V),V.forEach(m),G.forEach(m),ft=r(e),b(we.$$.fragment,e),ut=r(e),st=p(e,"P",{}),R(st).forEach(m),this.h()},h(){X(n,"name","hf:doc:metadata"),X(n,"content",Zo),X(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(A,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),X(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),X(I,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),X(W,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),X(F,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),X(M,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),X(B,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),X(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,d){o(document.head,n),g(e,u,d),g(e,a,d),g(e,s,d),w(f,e,d),g(e,t,d),g(e,h,d),g(e,it,d),w(N,e,d),g(e,rt,d),w(re,e,d),g(e,lt,d),g(e,k,d),w(le,k,null),o(k,bt),o(k,ye),o(k,wt),o(k,ve),o(k,yt),o(k,$e),o(k,vt),o(k,xe),o(k,$t),o(k,T),w(pe,T,null),o(T,xt),o(T,Te),o(T,Tt),o(T,Ie),o(T,It),o(T,Me),o(T,Mt),o(T,je),o(T,jt),o(T,Ue),o(T,Ut),w(Q,T,null),o(T,Pt),w(E,T,null),o(T,kt),w(q,T,null),o(k,Ft),o(k,A),w(de,A,null),o(A,Jt),o(A,Pe),o(A,Zt),o(A,ke),o(A,Ct),o(A,Fe),o(A,Gt),o(A,Je),o(A,At),w(K,A,null),g(e,pt,d),w(ce,e,d),g(e,dt,d),g(e,F,d),w(me,F,null),o(F,Wt),o(F,Ze),o(F,Bt),o(F,Ce),o(F,Ht),o(F,Ge),o(F,St),o(F,Ae),o(F,Vt),o(F,I),w(fe,I,null),o(I,Lt),o(I,We),o(I,Rt),o(I,Be),o(I,Xt),o(I,He),o(I,zt),o(I,Se),o(I,Yt),o(I,Ve),o(I,Dt),w(O,I,null),o(I,Nt),w(ee,I,null),o(I,Qt),w(te,I,null),o(F,Et),o(F,W),w(ue,W,null),o(W,qt),o(W,Le),o(W,Kt),o(W,Re),o(W,Ot),o(W,Xe),o(W,en),o(W,ze),o(W,tn),w(ne,W,null),g(e,ct,d),w(he,e,d),g(e,mt,d),g(e,J,d),w(ge,J,null),o(J,nn),o(J,Ye),o(J,on),o(J,De),o(J,an),o(J,Ne),o(J,sn),o(J,Qe),o(J,rn),o(J,M),w(_e,M,null),o(M,ln),o(M,Ee),o(M,pn),o(M,qe),o(M,dn),o(M,Ke),o(M,cn),o(M,Oe),o(M,mn),o(M,et),o(M,fn),w(oe,M,null),o(M,un),w(ae,M,null),o(M,hn),w(se,M,null),o(J,gn),o(J,B),w(be,B,null),o(B,_n),o(B,tt),o(B,bn),o(B,nt),o(B,wn),o(B,ot),o(B,yn),o(B,at),o(B,vn),w(ie,B,null),g(e,ft,d),w(we,e,d),g(e,ut,d),g(e,st,d),ht=!0},p(e,[d]){const Z={};d&2&&(Z.$$scope={dirty:d,ctx:e}),N.$set(Z);const j={};d&2&&(j.$$scope={dirty:d,ctx:e}),Q.$set(j);const H={};d&2&&(H.$$scope={dirty:d,ctx:e}),E.$set(H);const C={};d&2&&(C.$$scope={dirty:d,ctx:e}),q.$set(C);const U={};d&2&&(U.$$scope={dirty:d,ctx:e}),K.$set(U);const S={};d&2&&(S.$$scope={dirty:d,ctx:e}),O.$set(S);const G={};d&2&&(G.$$scope={dirty:d,ctx:e}),ee.$set(G);const P={};d&2&&(P.$$scope={dirty:d,ctx:e}),te.$set(P);const V={};d&2&&(V.$$scope={dirty:d,ctx:e}),ne.$set(V);const lo={};d&2&&(lo.$$scope={dirty:d,ctx:e}),oe.$set(lo);const po={};d&2&&(po.$$scope={dirty:d,ctx:e}),ae.$set(po);const co={};d&2&&(co.$$scope={dirty:d,ctx:e}),se.$set(co);const mo={};d&2&&(mo.$$scope={dirty:d,ctx:e}),ie.$set(mo)},i(e){ht\|\|(y(f.$$.fragment,e),y(N.$$.fragment,e),y(re.$$.fragment,e),y(le.$$.fragment,e),y(pe.$$.fragment,e),y(Q.$$.fragment,e),y(E.$$.fragment,e),y(q.$$.fragment,e),y(de.$$.fragment,e),y(K.$$.fragment,e),y(ce.$$.fragment,e),y(me.$$.fragment,e),y(fe.$$.fragment,e),y(O.$$.fragment,e),y(ee.$$.fragment,e),y(te.$$.fragment,e),y(ue.$$.fragment,e),y(ne.$$.fragment,e),y(he.$$.fragment,e),y(ge.$$.fragment,e),y(_e.$$.fragment,e),y(oe.$$.fragment,e),y(ae.$$.fragment,e),y(se.$$.fragment,e),y(be.$$.fragment,e),y(ie.$$.fragment,e),y(we.$$.fragment,e),ht=!0)},o(e){v(f.$$.fragment,e),v(N.$$.fragment,e),v(re.$$.fragment,e),v(le.$$.fragment,e),v(pe.$$.fragment,e),v(Q.$$.fragment,e),v(E.$$.fragment,e),v(q.$$.fragment,e),v(de.$$.fragment,e),v(K.$$.fragment,e),v(ce.$$.fragment,e),v(me.$$.fragment,e),v(fe.$$.fragment,e),v(O.$$.fragment,e),v(ee.$$.fragment,e),v(te.$$.fragment,e),v(ue.$$.fragment,e),v(ne.$$.fragment,e),v(he.$$.fragment,e),v(ge.$$.fragment,e),v(_e.$$.fragment,e),v(oe.$$.fragment,e),v(ae.$$.fragment,e),v(se.$$.fragment,e),v(be.$$.fragment,e),v(ie.$$.fragment,e),v(we.$$.fragment,e),ht=!1},d(e){e&&(m(u),m(a),m(s),m(t),m(h),m(it),m(rt),m(lt),m(k),m(pt),m(dt),m(F),m(ct),m(mt),m(J),m(ft),m(ut),m(st)),m(n),$(f,e),$(N,e),$(re,e),$(le),$(pe),$(Q),$(E),$(q),$(de),$(K),$(ce,e),$(me),$(fe),$(O),$(ee),$(te),$(ue),$(ne),$(he,e),$(ge),$(_e),$(oe),$(ae),$(se),$(be),$(ie),$(we,e)}}}const Zo='{"title":"AutoPipeline","local":"autopipeline","sections":[{"title":"AutoPipelineForText2Image","local":"diffusers.AutoPipelineForText2Image","sections":[],"depth":2},{"title":"AutoPipelineForImage2Image","local":"diffusers.AutoPipelineForImage2Image","sections":[],"depth":2},{"title":"AutoPipelineForInpainting","local":"diffusers.AutoPipelineForInpainting","sections":[],"depth":2}],"depth":1}';function Co(x){return uo(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Lo extends ho{constructor(n){super(),go(this,n,Co,Jo,fo,{})}}export{Lo as component};

Xet Storage Details

Size:: 68.2 kB
Xet hash:: 2d5e57275ce016c0af8161352b7bcd9004b2dc9be37dbc8c67c26d2b54a2bc20

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.