diffusers/v0.12.0/en/using-diffusers/reproducibility.html

<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;reproducibility&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;inference&quot;,&quot;title&quot;:&quot;Inference&quot;},{&quot;local&quot;:&quot;randomness-utilities&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;diffusers.utils.randn_tensor&quot;,&quot;title&quot;:&quot;randn_tensor&quot;}],&quot;title&quot;:&quot;Randomness utilities&quot;}],&quot;title&quot;:&quot;Reproducibility&quot;}" data-svelte="svelte-1phssyn">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/start-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/chunks/vendor-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/chunks/paths-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/pages/__layout.svelte-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/pages/using-diffusers/reproducibility.mdx-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/chunks/Tip-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/chunks/Docstring-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.12.0/en/_app/chunks/CodeBlock-hf-doc-builder.js"> 






<h1 class="relative group"><a id="reproducibility" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#reproducibility"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>Reproducibility
	</span></h1>

<p>Before reading about reproducibility for Diffusers, it is strongly recommended to take a look at
<a href="https://pytorch.org/docs/stable/notes/randomness.html" rel="nofollow">PyTorch’s statement about reproducibility</a>.</p>
<p>PyTorch states that </p>
<blockquote><p><em>completely reproducible results are not guaranteed across PyTorch releases, individual commits, or different platforms.</em>
While one can never expect the same results across platforms, one can expect results to be reproducible
across releases, platforms, etc… within a certain tolerance. However, this tolerance strongly varies
depending on the diffusion pipeline and checkpoint.</p></blockquote>
<p>In the following, we show how to best control sources of randomness for diffusion models.</p>
<h2 class="relative group"><a id="inference" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#inference"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>Inference
	</span></h2>

<p>During inference, diffusion pipelines heavily rely on random sampling operations, such as the creating the
gaussian noise tensors to be denoised and adding noise to the scheduling step.</p>
<p>Let’s have a look at an example. We run the <a href="./api/pipelines/ddim.mdx">DDIM pipeline</a>
for just two inference steps and return a numpy tensor to look into the numerical values of the output.</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDIMPipeline
<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np

model_id = <span class="hljs-string">&quot;google/ddpm-cifar10-32&quot;</span>

<span class="hljs-comment"># load model and scheduler</span>
ddim = DDIMPipeline.from_pretrained(model_id)

<span class="hljs-comment"># run pipeline for just two steps and return numpy tensor</span>
image = ddim(num_inference_steps=<span class="hljs-number">2</span>, output_type=<span class="hljs-string">&quot;np&quot;</span>).images
<span class="hljs-built_in">print</span>(np.<span class="hljs-built_in">abs</span>(image).<span class="hljs-built_in">sum</span>())<!-- HTML_TAG_END --></pre></div>
<p>Running the above prints a value of 1464.2076, but running it again prints a different
value of 1495.1768. What is going on here? Every time the pipeline is run, gaussian noise
is created and step-wise denoised. To create the gaussian noise with <a href="https://pytorch.org/docs/stable/generated/torch.randn.html" rel="nofollow"><code>torch.randn</code></a>, a different random seed is taken every time, thus leading to a different result.
This is a desired property of diffusion pipelines, as it means that the pipeline can create a different random image every time it is run. In many cases, one would like to generate the exact same image of a certain
run, for which case an instance of a <a href="https://pytorch.org/docs/stable/generated/torch.randn.html" rel="nofollow">PyTorch generator</a> has to be passed:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDIMPipeline
<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np

model_id = <span class="hljs-string">&quot;google/ddpm-cifar10-32&quot;</span>

<span class="hljs-comment"># load model and scheduler</span>
ddim = DDIMPipeline.from_pretrained(model_id)

<span class="hljs-comment"># create a generator for reproducibility</span>
generator = torch.Generator(device=<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(<span class="hljs-number">0</span>)

<span class="hljs-comment"># run pipeline for just two steps and return numpy tensor</span>
image = ddim(num_inference_steps=<span class="hljs-number">2</span>, output_type=<span class="hljs-string">&quot;np&quot;</span>, generator=generator).images
<span class="hljs-built_in">print</span>(np.<span class="hljs-built_in">abs</span>(image).<span class="hljs-built_in">sum</span>())<!-- HTML_TAG_END --></pre></div>
<p>Running the above always prints a value of 1491.1711 - also upon running it again because we
define the generator object to be passed to all random functions of the pipeline.</p>
<p>If you run this code snippet on your specific hardware and version, you should get a similar, if not the same, result.</p>


<div class="course-tip  bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p>It might be a bit unintuitive at first to pass <code>generator</code> objects to the pipelines instead of
just integer values representing the seed, but this is the recommended design when dealing with
probabilistic models in PyTorch as generators are <em>random states</em> that are advanced and can thus be
passed to multiple pipelines in a sequence.</p></div>
<p>Great! Now, we know how to write reproducible pipelines, but it gets a bit trickier since the above example only runs on the CPU. How do we also achieve reproducibility on GPU?
In short, one should not expect full reproducibility across different hardware when running pipelines on GPU
as matrix multiplications are less deterministic on GPU than on CPU and diffusion pipelines tend to require
a lot of matrix multiplications. Let’s see what we can do to keep the randomness within limits across
different GPU hardware.</p>
<p>To achieve maximum speed performance, it is recommended to create the generator directly on GPU when running
the pipeline on GPU:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDIMPipeline
<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np

model_id = <span class="hljs-string">&quot;google/ddpm-cifar10-32&quot;</span>

<span class="hljs-comment"># load model and scheduler</span>
ddim = DDIMPipeline.from_pretrained(model_id)
ddim.to(<span class="hljs-string">&quot;cuda&quot;</span>)

<span class="hljs-comment"># create a generator for reproducibility</span>
generator = torch.Generator(device=<span class="hljs-string">&quot;cuda&quot;</span>).manual_seed(<span class="hljs-number">0</span>)

<span class="hljs-comment"># run pipeline for just two steps and return numpy tensor</span>
image = ddim(num_inference_steps=<span class="hljs-number">2</span>, output_type=<span class="hljs-string">&quot;np&quot;</span>, generator=generator).images
<span class="hljs-built_in">print</span>(np.<span class="hljs-built_in">abs</span>(image).<span class="hljs-built_in">sum</span>())<!-- HTML_TAG_END --></pre></div>
<p>Running the above now prints a value of 1389.8634 - even though we’re using the exact same seed!
This is unfortunate as it means we cannot reproduce the results we achieved on GPU, also on CPU.
Nevertheless, it should be expected since the GPU uses a different random number generator than the CPU.</p>
<p>To circumvent this problem, we created a <a href="#diffusers.utils.randn_tensor"><code>randn_tensor</code></a> function, which can create random noise
on the CPU and then move the tensor to GPU if necessary. The function is used everywhere inside the pipelines allowing the user to <strong>always</strong> pass a CPU generator even if the pipeline is run on GPU:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DDIMPipeline
<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np

model_id = <span class="hljs-string">&quot;google/ddpm-cifar10-32&quot;</span>

<span class="hljs-comment"># load model and scheduler</span>
ddim = DDIMPipeline.from_pretrained(model_id)
ddim.to(<span class="hljs-string">&quot;cuda&quot;</span>)

<span class="hljs-comment"># create a generator for reproducibility</span>
generator = torch.manual_seed(<span class="hljs-number">0</span>)

<span class="hljs-comment"># run pipeline for just two steps and return numpy tensor</span>
image = ddim(num_inference_steps=<span class="hljs-number">2</span>, output_type=<span class="hljs-string">&quot;np&quot;</span>, generator=generator).images
<span class="hljs-built_in">print</span>(np.<span class="hljs-built_in">abs</span>(image).<span class="hljs-built_in">sum</span>())<!-- HTML_TAG_END --></pre></div>
<p>Running the above now prints a value of 1491.1713, much closer to the value of 1491.1711 when
the pipeline is fully run on the CPU.</p>


<div class="course-tip  bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p>As a consequence, we recommend always passing a CPU generator if Reproducibility is important.
The loss of performance is often neglectable, but one can be sure to generate much more similar
values than if the pipeline would have been run on CPU.</p></div>
<p>Finally, we noticed that more complex pipelines, such as <a href="/docs/diffusers/v0.12.0/en/api/pipelines/unclip#diffusers.UnCLIPPipeline">UnCLIPPipeline</a> are often extremely
susceptible to precision error propagation and thus one cannot expect even similar results across
different GPU hardware or PyTorch versions. In such cases, one has to make sure to run
exactly the same hardware and PyTorch version for full Reproducibility.</p>
<h2 class="relative group"><a id="randomness-utilities" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#randomness-utilities"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>Randomness utilities
	</span></h2>

<h3 class="relative group"><a id="diffusers.utils.randn_tensor" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#diffusers.utils.randn_tensor"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>randn_tensor
	</span></h3>

<div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8">

<div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="diffusers.utils.randn_tensor"><!-- HTML_TAG_START --><h4 class="!m-0"><span class="flex-1 rounded-xl py-0.5 break-all bg-gradient-to-r from-blue-50/60 to-white dark:from-gray-900 dark:to-gray-950 text-blue-700 dark:text-blue-300 font-medium px-2"><svg width="1em" height="1em" viewBox="0 0 32 33" class="mr-1 inline-block -mt-0.5"  xmlns="http://www.w3.org/2000/svg"><path d="M5.80566 18.3545C4.90766 17.4565 4.90766 16.0005 5.80566 15.1025L14.3768 6.53142C15.2748 5.63342 16.7307 5.63342 17.6287 6.53142L26.1999 15.1025C27.0979 16.0005 27.0979 17.4565 26.1999 18.3545L17.6287 26.9256C16.7307 27.8236 15.2748 27.8236 14.3768 26.9256L5.80566 18.3545Z" fill="currentColor" fill-opacity="0.25"/><path fill-rule="evenodd" clip-rule="evenodd" d="M16.4801 13.9619C16.4801 12.9761 16.7467 12.5436 16.9443 12.3296C17.1764 12.078 17.5731 11.8517 18.2275 11.707C18.8821 11.5623 19.638 11.5342 20.4038 11.5582C20.7804 11.57 21.1341 11.5932 21.4719 11.6156L21.5263 11.6193C21.8195 11.6389 22.1626 11.6618 22.4429 11.6618V7.40825C22.3209 7.40825 22.1219 7.39596 21.7544 7.37149C21.4202 7.34925 20.9976 7.32115 20.5371 7.30672C19.6286 7.27824 18.4672 7.29779 17.3093 7.55377C16.1512 7.8098 14.8404 8.33724 13.8181 9.4452C12.7612 10.5907 12.2266 12.1236 12.2266 13.9619V15.0127H10.6836V19.2662H12.2266V26.6332H16.4801V19.2662H20.3394V15.0127H16.4801V13.9619Z" fill="currentColor"/></svg>diffusers.utils.randn_tensor</span></h4><!-- HTML_TAG_END -->
		<a id="diffusers.utils.randn_tensor" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.utils.randn_tensor"><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></a>
		<a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/v0.12.0/src/diffusers/utils/torch_utils.py#L29" target="_blank"><span>&lt;</span>
				<span class="hidden md:block mx-0.5 hover:!underline">source</span>
				<span>&gt;</span></a></span>
	<p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span>
			<span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">shape<span class="opacity-60">: typing.Union[typing.Tuple, typing.List]</span></span>
				</span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">generator<span class="opacity-60">: typing.Union[typing.List[ForwardRef(&#39;torch.Generator&#39;)], ForwardRef(&#39;torch.Generator&#39;), NoneType] = None</span></span>
				</span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">device<span class="opacity-60">: typing.Optional[ForwardRef(&#39;torch.device&#39;)] = None</span></span>
				</span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">dtype<span class="opacity-60">: typing.Optional[ForwardRef(&#39;torch.dtype&#39;)] = None</span></span>
				</span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">layout<span class="opacity-60">: typing.Optional[ForwardRef(&#39;torch.layout&#39;)] = None</span></span>
				</span>
			<span>)</span>
			</p>

	
	<div class="!mb-10 relative docstring-details ">
		
		
		
		</div></div>
<p>This is a helper function that allows to create random tensors on the desired <code>device</code> with the desired <code>dtype</code>. When
passing a list of generators one can seed each batched size individually. If CPU generators are passed the tensor
will always be created on CPU.</p></div>


		<script type="module" data-hydrate="zd652r">
		import { start } from "/docs/diffusers/v0.12.0/en/_app/start-hf-doc-builder.js";
		start({
			target: document.querySelector('[data-hydrate="zd652r"]').parentNode,
			paths: {"base":"/docs/diffusers/v0.12.0/en","assets":"/docs/diffusers/v0.12.0/en"},
			session: {},
			route: false,
			spa: false,
			trailing_slash: "never",
			hydrate: {
				status: 200,
				error: null,
				nodes: [
					import("/docs/diffusers/v0.12.0/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
						import("/docs/diffusers/v0.12.0/en/_app/pages/using-diffusers/reproducibility.mdx-hf-doc-builder.js")
				],
				params: {}
			}
		});
	</script>