diffusers/pr_14407/zh/_app/immutable/nodes/58.DFGvXw9o.js

import"../chunks/DsnmJJEf.js";import{i as N,h as C,C as z,H as c,a as l,b as x,E as q,s as F}from"../chunks/DdZvggmf.js";import{p as Q,o as D,s,f as r,a as n,b as L,c as t,n as H}from"../chunks/BbekZcyp.js";import{D as Y}from"../chunks/Bje6zuSL.js";import{H as p}from"../chunks/BcnRgdDK.js";const A='{"title":"加载调度器与模型","local":"加载调度器与模型","sections":[{"title":"加载调度器","local":"加载调度器","sections":[],"depth":2},{"title":"调度器对比","local":"调度器对比","sections":[],"depth":2},{"title":"模型加载","local":"模型加载","sections":[],"depth":2}],"depth":1}';var P=t('<meta name="hf:doc:metadata"/>'),$=t("<p><code>LMSDiscreteScheduler</code>通常能生成比默认调度器更高质量的图像。</p> <!>",1),K=t("<p><code>EulerDiscreteScheduler</code>仅需30步即可生成高质量图像。</p> <!>",1),O=t("<p><code>EulerAncestralDiscreteScheduler</code>同样可在30步内生成高质量图像。</p> <!>",1),ss=t("<p><code>DPMSolverMultistepScheduler</code>在速度与质量间取得平衡，仅需20步即可生成优质图像。</p> <!>",1),ls=t("<!> <!> <!> <!>",1),es=t('<p></p> <!> <!> <!> <p>Diffusion管道是由可互换的调度器(schedulers)和模型(models)组成的集合，可通过混合搭配来定制特定用例的流程。调度器封装了整个去噪过程（如去噪步数和寻找去噪样本的算法），其本身不包含可训练参数，因此内存占用极低。模型则主要负责从含噪输入到较纯净样本的前向传播过程。</p> <p>本指南将展示如何加载调度器和模型来自定义流程。我们将全程使用<a href="https://hf.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow">stable-diffusion-v1-5/stable-diffusion-v1-5</a>检查点，首先加载基础管道：</p> <!> <p>通过<code>pipeline.scheduler</code>属性可查看当前管道使用的调度器：</p> <!> <!> <p>调度器通过配置文件定义，同一配置文件可被多种调度器共享。使用<code>SchedulerMixin.from_pretrained()</code>方法加载时，需指定<code>subfolder</code>参数以定位配置文件在仓库中的正确子目录。</p> <p>例如加载<code>DDIMScheduler</code>：</p> <!> <p>然后将新调度器传入管道：</p> <!> <!> <p>不同调度器各有优劣，难以定量评估哪个最适合您的流程。通常需要在去噪速度与质量之间权衡。我们建议尝试多种调度器以找到最佳方案。通过<code>pipeline.scheduler.compatibles</code>属性可查看兼容当前管道的所有调度器。</p> <p>下面我们使用相同提示词和随机种子，对比<code>LMSDiscreteScheduler</code>、<code>EulerDiscreteScheduler</code>、<code>EulerAncestralDiscreteScheduler</code>和<code>DPMSolverMultistepScheduler</code>的表现：</p> <!> <p>使用<code>from_config()</code>方法加载不同调度器的配置来切换管道调度器：</p> <!> <div class="flex gap-4"><div><img class="rounded-xl" src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_lms.png"/> <figcaption class="mt-2 text-center text-sm text-gray-500">LMSDiscreteScheduler</figcaption></div> <div><img class="rounded-xl" src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_euler_discrete.png"/> <figcaption class="mt-2 text-center text-sm text-gray-500">EulerDiscreteScheduler</figcaption></div></div> <div class="flex gap-4"><div><img class="rounded-xl" src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_euler_ancestral.png"/> <figcaption class="mt-2 text-center text-sm text-gray-500">EulerAncestralDiscreteScheduler</figcaption></div> <div><img class="rounded-xl" src="https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/diffusers_docs/astronaut_dpm.png"/> <figcaption class="mt-2 text-center text-sm text-gray-500">DPMSolverMultistepScheduler</figcaption></div></div> <p>多数生成图像质量相近，实际选择需根据具体场景测试多种调度器进行比较。</p> <!> <p>通过<code>ModelMixin.from_pretrained()</code>方法加载模型，该方法会下载并缓存模型权重和配置的最新版本。若本地缓存已存在最新文件，则直接复用缓存而非重复下载。</p> <p>通过<code>subfolder</code>参数可从子目录加载模型。例如<a href="https://hf.co/stable-diffusion-v1-5/stable-diffusion-v1-5" rel="nofollow">stable-diffusion-v1-5/stable-diffusion-v1-5</a>的模型权重存储在<a href="https://hf.co/stable-diffusion-v1-5/stable-diffusion-v1-5/tree/main/unet" rel="nofollow">unet</a>子目录中：</p> <!> <p>也可直接从<a href="https://huggingface.co/google/ddpm-cifar10-32/tree/main" rel="nofollow">仓库</a>加载：</p> <!> <p>加载和保存模型变体时，需在<code>ModelMixin.from_pretrained()</code>和<code>ModelMixin.save_pretrained()</code>中指定<code>variant</code>参数：</p> <!> <p>使用<code>from_pretrained()</code>的<code>dtype</code>参数指定模型加载精度：</p> <!> <p>也可使用<a href="https://docs.pytorch.org/docs/stable/generated/torch.Tensor.to.html" rel="nofollow">torch.Tensor.to</a>方法即时转换精度，但会转换所有权重（不同于<code>dtype</code>参数会保留<code>_keep_in_fp32_modules</code>中的层）。这对某些必须保持fp32精度的层尤为重要（参见<a href="https://github.com/huggingface/diffusers/blob/f864a9a352fa4a220d860bfdd1782e3e5af96382/src/diffusers/models/transformers/transformer_wan.py#L374" rel="nofollow">示例</a>）。</p> <!> <p></p>',1);function is(B,I){Q(I,!1),D(()=>{new URLSearchParams(window.location.search).get("fw")}),N();var h=es();C("alcvz4",i=>{var d=P();F(d,"content",A),n(i,d)});var M=s(r(h),2);z(M,{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"});var y=s(M,2);Y(y,{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;",options:[{label:"Mixed",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers_doc/zh/schedulers.ipynb"},{label:"PyTorch",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers_doc/zh/pytorch/schedulers.ipynb"},{label:"TensorFlow",value:"https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers_doc/zh/tensorflow/schedulers.ipynb"},{label:"Mixed",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/zh/schedulers.ipynb"},{label:"PyTorch",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/zh/pytorch/schedulers.ipynb"},{label:"TensorFlow",value:"https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/main/diffusers_doc/zh/tensorflow/schedulers.ipynb"}]});var m=s(y,2);c(m,{title:"加载调度器与模型",local:"加载调度器与模型",headingTag:"h1"});var f=s(m,6);l(f,{code:"aW1wb3J0JTIwdG9yY2glMEFmcm9tJTIwZGlmZnVzZXJzJTIwaW1wb3J0JTIwRGlmZnVzaW9uUGlwZWxpbmUlMEElMEFwaXBlbGluZSUyMCUzRCUyMERpZmZ1c2lvblBpcGVsaW5lLmZyb21fcHJldHJhaW5lZCglMEElMjAlMjAlMjAlMjAlMjJzdGFibGUtZGlmZnVzaW9uLXYxLTUlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTUlMjIlMkMlMjBkdHlwZSUzRHRvcmNoLmZsb2F0MTYlMkMlMjB1c2Vfc2FmZXRlbnNvcnMlM0RUcnVlJTBBKS50byglMjJjdWRhJTIyKQ==",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, dtype=torch.float16, use_safetensors=<span class="hljs-literal">True</span>
).to(<span class="hljs-string">&quot;cuda&quot;</span>)`,lang:"python",wrap:!1});var b=s(f,4);l(b,{code:"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",highlighted:`pipeline.scheduler
PNDMScheduler {
  <span class="hljs-string">&quot;_class_name&quot;</span>: <span class="hljs-string">&quot;PNDMScheduler&quot;</span>,
  <span class="hljs-string">&quot;_diffusers_version&quot;</span>: <span class="hljs-string">&quot;0.21.4&quot;</span>,
  <span class="hljs-string">&quot;beta_end&quot;</span>: <span class="hljs-number">0.012</span>,
  <span class="hljs-string">&quot;beta_schedule&quot;</span>: <span class="hljs-string">&quot;scaled_linear&quot;</span>,
  <span class="hljs-string">&quot;beta_start&quot;</span>: <span class="hljs-number">0.00085</span>,
  <span class="hljs-string">&quot;clip_sample&quot;</span>: false,
  <span class="hljs-string">&quot;num_train_timesteps&quot;</span>: <span class="hljs-number">1000</span>,
  <span class="hljs-string">&quot;set_alpha_to_one&quot;</span>: false,
  <span class="hljs-string">&quot;skip_prk_steps&quot;</span>: true,
  <span class="hljs-string">&quot;steps_offset&quot;</span>: <span class="hljs-number">1</span>,
  <span class="hljs-string">&quot;timestep_spacing&quot;</span>: <span class="hljs-string">&quot;leading&quot;</span>,
  <span class="hljs-string">&quot;trained_betas&quot;</span>: null
}`,lang:"python",wrap:!1});var g=s(b,2);c(g,{title:"加载调度器",local:"加载调度器",headingTag:"h2"});var Z=s(g,6);l(Z,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMERESU1TY2hlZHVsZXIlMkMlMjBEaWZmdXNpb25QaXBlbGluZSUwQSUwQWRkaW0lMjAlM0QlMjBERElNU2NoZWR1bGVyLmZyb21fcHJldHJhaW5lZCglMjJzdGFibGUtZGlmZnVzaW9uLXYxLTUlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTUlMjIlMkMlMjBzdWJmb2xkZXIlM0QlMjJzY2hlZHVsZXIlMjIp",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDIMScheduler, DiffusionPipeline

ddim = DDIMScheduler.from_pretrained(<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, subfolder=<span class="hljs-string">&quot;scheduler&quot;</span>)`,lang:"python",wrap:!1});var U=s(Z,4);l(U,{code:"cGlwZWxpbmUlMjAlM0QlMjBEaWZmdXNpb25QaXBlbGluZS5mcm9tX3ByZXRyYWluZWQoJTBBJTIwJTIwJTIwJTIwJTIyc3RhYmxlLWRpZmZ1c2lvbi12MS01JTJGc3RhYmxlLWRpZmZ1c2lvbi12MS01JTIyJTJDJTIwc2NoZWR1bGVyJTNEZGRpbSUyQyUyMGR0eXBlJTNEdG9yY2guZmxvYXQxNiUyQyUyMHVzZV9zYWZldGVuc29ycyUzRFRydWUlMEEpLnRvKCUyMmN1ZGElMjIp",highlighted:`pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, scheduler=ddim, dtype=torch.float16, use_safetensors=<span class="hljs-literal">True</span>
).to(<span class="hljs-string">&quot;cuda&quot;</span>)`,lang:"python",wrap:!1});var J=s(U,2);c(J,{title:"调度器对比",local:"调度器对比",headingTag:"h2"});var j=s(J,6);l(j,{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, dtype=torch.float16, use_safetensors=<span class="hljs-literal">True</span>
).to(<span class="hljs-string">&quot;cuda&quot;</span>)

prompt = <span class="hljs-string">&quot;A photograph of an astronaut riding a horse on Mars, high resolution, high definition.&quot;</span>
generator = torch.Generator(device=<span class="hljs-string">&quot;cuda&quot;</span>).manual_seed(<span class="hljs-number">8</span>)`,lang:"python",wrap:!1});var G=s(j,4);x(G,{id:"schedulers",options:["LMSDiscreteScheduler","EulerDiscreteScheduler","EulerAncestralDiscreteScheduler","DPMSolverMultistepScheduler"],children:(i,d)=>{var R=ls(),_=r(R);p(_,{id:"schedulers",option:"LMSDiscreteScheduler",children:(a,u)=>{var e=$(),o=s(r(e),2);l(o,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMExNU0Rpc2NyZXRlU2NoZWR1bGVyJTBBJTBBcGlwZWxpbmUuc2NoZWR1bGVyJTIwJTNEJTIwTE1TRGlzY3JldGVTY2hlZHVsZXIuZnJvbV9jb25maWcocGlwZWxpbmUuc2NoZWR1bGVyLmNvbmZpZyklMEFpbWFnZSUyMCUzRCUyMHBpcGVsaW5lKHByb21wdCUyQyUyMGdlbmVyYXRvciUzRGdlbmVyYXRvcikuaW1hZ2VzJTVCMCU1RCUwQWltYWdl",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> LMSDiscreteScheduler

pipeline.scheduler = LMSDiscreteScheduler.from_config(pipeline.scheduler.config)
image = pipeline(prompt, generator=generator).images[<span class="hljs-number">0</span>]
image`,lang:"python",wrap:!1}),n(a,e)},$$slots:{default:!0}});var S=s(_,2);p(S,{id:"schedulers",option:"EulerDiscreteScheduler",children:(a,u)=>{var e=K(),o=s(r(e),2);l(o,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEV1bGVyRGlzY3JldGVTY2hlZHVsZXIlMEElMEFwaXBlbGluZS5zY2hlZHVsZXIlMjAlM0QlMjBFdWxlckRpc2NyZXRlU2NoZWR1bGVyLmZyb21fY29uZmlnKHBpcGVsaW5lLnNjaGVkdWxlci5jb25maWcpJTBBaW1hZ2UlMjAlM0QlMjBwaXBlbGluZShwcm9tcHQlMkMlMjBnZW5lcmF0b3IlM0RnZW5lcmF0b3IpLmltYWdlcyU1QjAlNUQlMEFpbWFnZQ==",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> EulerDiscreteScheduler

pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)
image = pipeline(prompt, generator=generator).images[<span class="hljs-number">0</span>]
image`,lang:"python",wrap:!1}),n(a,e)},$$slots:{default:!0}});var k=s(S,2);p(k,{id:"schedulers",option:"EulerAncestralDiscreteScheduler",children:(a,u)=>{var e=O(),o=s(r(e),2);l(o,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEV1bGVyQW5jZXN0cmFsRGlzY3JldGVTY2hlZHVsZXIlMEElMEFwaXBlbGluZS5zY2hlZHVsZXIlMjAlM0QlMjBFdWxlckFuY2VzdHJhbERpc2NyZXRlU2NoZWR1bGVyLmZyb21fY29uZmlnKHBpcGVsaW5lLnNjaGVkdWxlci5jb25maWcpJTBBaW1hZ2UlMjAlM0QlMjBwaXBlbGluZShwcm9tcHQlMkMlMjBnZW5lcmF0b3IlM0RnZW5lcmF0b3IpLmltYWdlcyU1QjAlNUQlMEFpbWFnZQ==",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> EulerAncestralDiscreteScheduler

pipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(pipeline.scheduler.config)
image = pipeline(prompt, generator=generator).images[<span class="hljs-number">0</span>]
image`,lang:"python",wrap:!1}),n(a,e)},$$slots:{default:!0}});var X=s(k,2);p(X,{id:"schedulers",option:"DPMSolverMultistepScheduler",children:(a,u)=>{var e=ss(),o=s(r(e),2);l(o,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMERQTVNvbHZlck11bHRpc3RlcFNjaGVkdWxlciUwQSUwQXBpcGVsaW5lLnNjaGVkdWxlciUyMCUzRCUyMERQTVNvbHZlck11bHRpc3RlcFNjaGVkdWxlci5mcm9tX2NvbmZpZyhwaXBlbGluZS5zY2hlZHVsZXIuY29uZmlnKSUwQWltYWdlJTIwJTNEJTIwcGlwZWxpbmUocHJvbXB0JTJDJTIwZ2VuZXJhdG9yJTNEZ2VuZXJhdG9yKS5pbWFnZXMlNUIwJTVEJTBBaW1hZ2U=",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DPMSolverMultistepScheduler

pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
image = pipeline(prompt, generator=generator).images[<span class="hljs-number">0</span>]
image`,lang:"python",wrap:!1}),n(a,e)},$$slots:{default:!0}}),n(i,R)},$$slots:{default:!0}});var v=s(G,8);c(v,{title:"模型加载",local:"模型加载",headingTag:"h2"});var w=s(v,6);l(w,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMFVOZXQyRENvbmRpdGlvbk1vZGVsJTBBJTBBdW5ldCUyMCUzRCUyMFVOZXQyRENvbmRpdGlvbk1vZGVsLmZyb21fcHJldHJhaW5lZCglMjJzdGFibGUtZGlmZnVzaW9uLXYxLTUlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTUlMjIlMkMlMjBzdWJmb2xkZXIlM0QlMjJ1bmV0JTIyJTJDJTIwdXNlX3NhZmV0ZW5zb3JzJTNEVHJ1ZSk=",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> UNet2DConditionModel

unet = UNet2DConditionModel.from_pretrained(<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, subfolder=<span class="hljs-string">&quot;unet&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)`,lang:"python",wrap:!1});var T=s(w,4);l(T,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMFVOZXQyRE1vZGVsJTBBJTBBdW5ldCUyMCUzRCUyMFVOZXQyRE1vZGVsLmZyb21fcHJldHJhaW5lZCglMjJnb29nbGUlMkZkZHBtLWNpZmFyMTAtMzIlMjIlMkMlMjB1c2Vfc2FmZXRlbnNvcnMlM0RUcnVlKQ==",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> UNet2DModel

unet = UNet2DModel.from_pretrained(<span class="hljs-string">&quot;google/ddpm-cifar10-32&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>)`,lang:"python",wrap:!1});var V=s(T,4);l(V,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMFVOZXQyRENvbmRpdGlvbk1vZGVsJTBBJTBBdW5ldCUyMCUzRCUyMFVOZXQyRENvbmRpdGlvbk1vZGVsLmZyb21fcHJldHJhaW5lZCglMEElMjAlMjAlMjAlMjAlMjJzdGFibGUtZGlmZnVzaW9uLXYxLTUlMkZzdGFibGUtZGlmZnVzaW9uLXYxLTUlMjIlMkMlMjBzdWJmb2xkZXIlM0QlMjJ1bmV0JTIyJTJDJTIwdmFyaWFudCUzRCUyMm5vbl9lbWElMjIlMkMlMjB1c2Vfc2FmZXRlbnNvcnMlM0RUcnVlJTBBKSUwQXVuZXQuc2F2ZV9wcmV0cmFpbmVkKCUyMi4lMkZsb2NhbC11bmV0JTIyJTJDJTIwdmFyaWFudCUzRCUyMm5vbl9lbWElMjIp",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> UNet2DConditionModel

unet = UNet2DConditionModel.from_pretrained(
    <span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>, subfolder=<span class="hljs-string">&quot;unet&quot;</span>, variant=<span class="hljs-string">&quot;non_ema&quot;</span>, use_safetensors=<span class="hljs-literal">True</span>
)
unet.save_pretrained(<span class="hljs-string">&quot;./local-unet&quot;</span>, variant=<span class="hljs-string">&quot;non_ema&quot;</span>)`,lang:"python",wrap:!1});var W=s(V,4);l(W,{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEF1dG9Nb2RlbCUwQSUwQXVuZXQlMjAlM0QlMjBBdXRvTW9kZWwuZnJvbV9wcmV0cmFpbmVkKCUwQSUyMCUyMCUyMCUyMCUyMnN0YWJpbGl0eWFpJTJGc3RhYmxlLWRpZmZ1c2lvbi14bC1iYXNlLTEuMCUyMiUyQyUyMHN1YmZvbGRlciUzRCUyMnVuZXQlMjIlMkMlMjBkdHlwZSUzRHRvcmNoLmZsb2F0MTYlMEEp",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoModel

unet = AutoModel.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, subfolder=<span class="hljs-string">&quot;unet&quot;</span>, dtype=torch.float16
)`,lang:"python",wrap:!1});var E=s(W,4);q(E,{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/zh/using-diffusers/schedulers.md"}),H(2),n(B,h),L()}export{is as component};