Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /v0.18.2 /en /api /schedulers /vq_diffusion.html
rtrm's picture
rtrm
download
raw
56.1 kB
<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;vqdiffusionscheduler&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;overview&quot;,&quot;title&quot;:&quot;Overview&quot;},{&quot;local&quot;:&quot;diffusers.VQDiffusionScheduler&quot;,&quot;title&quot;:&quot;VQDiffusionScheduler&quot;}],&quot;title&quot;:&quot;VQDiffusionScheduler&quot;}" data-svelte="svelte-1phssyn">
 <link rel="modulepreload" href="/docs/diffusers/v0.18.2/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
 <link rel="modulepreload" href="/docs/diffusers/v0.18.2/en/_app/start-hf-doc-builder.js">
 <link rel="modulepreload" href="/docs/diffusers/v0.18.2/en/_app/chunks/vendor-hf-doc-builder.js">
 <link rel="modulepreload" href="/docs/diffusers/v0.18.2/en/_app/chunks/paths-hf-doc-builder.js">
 <link rel="modulepreload" href="/docs/diffusers/v0.18.2/en/_app/pages/__layout.svelte-hf-doc-builder.js">
 <link rel="modulepreload" href="/docs/diffusers/v0.18.2/en/_app/pages/api/schedulers/vq_diffusion.mdx-hf-doc-builder.js">
 <link rel="modulepreload" href="/docs/diffusers/v0.18.2/en/_app/chunks/Docstring-hf-doc-builder.js">
 <link rel="modulepreload" href="/docs/diffusers/v0.18.2/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
<h1 class="relative group"><a id="vqdiffusionscheduler" 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="#vqdiffusionscheduler"><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>VQDiffusionScheduler
 </span></h1>
<h2 class="relative group"><a id="overview" 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="#overview"><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>Overview
 </span></h2>
<p>Original paper can be found <a href="https://arxiv.org/abs/2111.14822" rel="nofollow">here</a></p>
<h2 class="relative group"><a id="diffusers.VQDiffusionScheduler" 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.VQDiffusionScheduler"><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>VQDiffusionScheduler
 </span></h2>
<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.VQDiffusionScheduler"><!-- HTML_TAG_START --><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">class</span> <span class="font-medium">diffusers.</span><span class="font-semibold">VQDiffusionScheduler</span></span></h3><!-- HTML_TAG_END -->
 <a id="diffusers.VQDiffusionScheduler" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.VQDiffusionScheduler"><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/v0.18.2/src/diffusers/schedulers/scheduling_vq_diffusion.py#L106" 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-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">num_vec_classes<span class="opacity-60">: int</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">num_train_timesteps<span class="opacity-60">: int = 100</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">alpha_cum_start<span class="opacity-60">: float = 0.99999</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">alpha_cum_end<span class="opacity-60">: float = 9e-06</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">gamma_cum_start<span class="opacity-60">: float = 9e-06</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">gamma_cum_end<span class="opacity-60">: float = 0.99999</span></span>
 </span>
 <span>)</span>
 </p>
<div class="!mb-10 relative docstring-details ">
 <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p>
 <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.num_vec_classes" class="header-link block pr-0.5 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.VQDiffusionScheduler.num_vec_classes"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>num_vec_classes</strong> (<code>int</code>) &#x2014;
The number of classes of the vector embeddings of the latent pixels. Includes the class for the masked
latent pixel.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.num_train_timesteps" class="header-link block pr-0.5 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.VQDiffusionScheduler.num_train_timesteps"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>num_train_timesteps</strong> (<code>int</code>) &#x2014;
Number of diffusion steps used to train the model.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.alpha_cum_start" class="header-link block pr-0.5 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.VQDiffusionScheduler.alpha_cum_start"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>alpha_cum_start</strong> (<code>float</code>) &#x2014;
The starting cumulative alpha value.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.alpha_cum_end" class="header-link block pr-0.5 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.VQDiffusionScheduler.alpha_cum_end"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>alpha_cum_end</strong> (<code>float</code>) &#x2014;
The ending cumulative alpha value.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.gamma_cum_start" class="header-link block pr-0.5 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.VQDiffusionScheduler.gamma_cum_start"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>gamma_cum_start</strong> (<code>float</code>) &#x2014;
The starting cumulative gamma value.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.gamma_cum_end" class="header-link block pr-0.5 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.VQDiffusionScheduler.gamma_cum_end"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>gamma_cum_end</strong> (<code>float</code>) &#x2014;
The ending cumulative gamma value.<!-- HTML_TAG_END -->
 </span></span>
 </li></ul>
</div></div>
<p>The VQ-diffusion transformer outputs predicted probabilities of the initial unnoised image.</p>
<p>The VQ-diffusion scheduler converts the transformer’s output into a sample for the unnoised image at the previous
diffusion timestep.</p>
<p><a href="/docs/diffusers/v0.18.2/en/api/configuration#diffusers.ConfigMixin">~ConfigMixin</a> takes care of storing all config attributes that are passed in the scheduler’s <code>__init__</code>
function, such as <code>num_train_timesteps</code>. They can be accessed via <code>scheduler.config.num_train_timesteps</code>.
<a href="/docs/diffusers/v0.18.2/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a> provides general loading and saving functionality via the <a href="/docs/diffusers/v0.18.2/en/api/schedulers/overview#diffusers.SchedulerMixin.save_pretrained">SchedulerMixin.save_pretrained()</a> and
<a href="/docs/diffusers/v0.18.2/en/api/schedulers/overview#diffusers.SchedulerMixin.from_pretrained">from_pretrained()</a> functions.</p>
<p>For more details, see the original paper: <a href="https://arxiv.org/abs/2111.14822" rel="nofollow">https://arxiv.org/abs/2111.14822</a></p>
<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.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class"><!-- 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>log_Q_t_transitioning_to_known_class</span></h4><!-- HTML_TAG_END -->
 <a id="diffusers.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class"><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/v0.18.2/src/diffusers/schedulers/scheduling_vq_diffusion.py#L379" 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-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">t<span class="opacity-60">: torch.int32</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">x_t<span class="opacity-60">: LongTensor</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">log_onehot_x_t<span class="opacity-60">: FloatTensor</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">cumulative<span class="opacity-60">: bool</span></span>
 </span>
 <span>)</span>
 <span class="font-bold">→</span>
 <span class="rounded hover:bg-gray-400 cursor-pointer"><!-- HTML_TAG_START --><span><code>torch.FloatTensor</code> of shape <code>(batch size, num classes - 1, num latent pixels)</code></span><!-- HTML_TAG_END --></span></p>
<div class="!mb-10 relative docstring-details ">
 <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p>
 <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.t" class="header-link block pr-0.5 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.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.t"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>t</strong> (torch.Long) &#x2014;
The timestep that determines which transition matrix is used.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.x_t" class="header-link block pr-0.5 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.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.x_t"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>x_t</strong> (<code>torch.LongTensor</code> of shape <code>(batch size, num latent pixels)</code>) &#x2014;
The classes of each latent pixel at time <code>t</code>.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.log_onehot_x_t" class="header-link block pr-0.5 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.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.log_onehot_x_t"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>log_onehot_x_t</strong> (<code>torch.FloatTensor</code> of shape <code>(batch size, num classes, num latent pixels)</code>) &#x2014;
The log one-hot vectors of <code>x_t</code><!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.cumulative" class="header-link block pr-0.5 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.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.cumulative"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>cumulative</strong> (<code>bool</code>) &#x2014;
If cumulative is <code>False</code>, we use the single step transition matrix <code>t-1</code>-&gt;<code>t</code>. If cumulative is <code>True</code>,
we use the cumulative transition matrix <code>0</code>-&gt;<code>t</code>.<!-- HTML_TAG_END -->
 </span></span>
 </li></ul>
<div id="diffusers.VQDiffusionScheduler.log_Q_t_transitioning_to_known_class.returns" class="flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800 rounded "><p class="text-base">Returns</p>
 <!-- HTML_TAG_START -->
<p><code>torch.FloatTensor</code> of shape <code>(batch size, num classes - 1, num latent pixels)</code></p>
<!-- HTML_TAG_END -->
 <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700"></span></div>
 <p class="text-base"><!-- HTML_TAG_START -->
<p>Each <em>column</em> of the returned matrix is a <em>row</em> of log probabilities of the complete probability
transition matrix.</p>
<p>When non cumulative, returns <code>self.num_classes - 1</code> rows because the initial latent pixel cannot be
masked.</p>
<p>Where:</p>
<ul>
<li><code>q_n</code> is the probability distribution for the forward process of the <code>n</code>th latent pixel.</li>
<li>C_0 is a class of a latent pixel embedding</li>
<li>C_k is the class of the masked latent pixel</li>
</ul>
<p>non-cumulative result (omitting logarithms):</p>
<CodeBlock
code={`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`}
 highlighted={`q<span class="hljs-constructor">_0(<span class="hljs-params">x_t</span> | <span class="hljs-params">x_</span>{<span class="hljs-params">t</span>-1\} = C_0)</span><span class="hljs-operator"> ... </span>q<span class="hljs-constructor">_n(<span class="hljs-params">x_t</span> | <span class="hljs-params">x_</span>{<span class="hljs-params">t</span>-1\} = C_0)</span>
 . . .
 . . .
 . . .
q<span class="hljs-constructor">_0(<span class="hljs-params">x_t</span> | <span class="hljs-params">x_</span>{<span class="hljs-params">t</span>-1\} = C_k)</span><span class="hljs-operator"> ... </span>q<span class="hljs-constructor">_n(<span class="hljs-params">x_t</span> | <span class="hljs-params">x_</span>{<span class="hljs-params">t</span>-1\} = C_k)</span>`}
 />
<p>cumulative result (omitting logarithms):</p>
<CodeBlock
code={`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`}
 highlighted={`q<span class="hljs-constructor">_0_cumulative(<span class="hljs-params">x_t</span> | <span class="hljs-params">x_0</span> = C_0)</span><span class="hljs-operator"> ... </span>q<span class="hljs-constructor">_n_cumulative(<span class="hljs-params">x_t</span> | <span class="hljs-params">x_0</span> = C_0)</span>
 . . .
 . . .
 . . .
q<span class="hljs-constructor">_0_cumulative(<span class="hljs-params">x_t</span> | <span class="hljs-params">x_0</span> = C_{<span class="hljs-params">k</span>-1\})</span><span class="hljs-operator"> ... </span>q<span class="hljs-constructor">_n_cumulative(<span class="hljs-params">x_t</span> | <span class="hljs-params">x_0</span> = C_{<span class="hljs-params">k</span>-1\})</span>`}
 />
<!-- HTML_TAG_END --></p>
 </div></div>
<p>Returns the log probabilities of the rows from the (cumulative or non-cumulative) transition matrix for each
latent pixel in <code>x_t</code>.</p>
<p>See equation (7) for the complete non-cumulative transition matrix. The complete cumulative transition matrix
is the same structure except the parameters (alpha, beta, gamma) are the cumulative analogs.</p></div>
<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.VQDiffusionScheduler.q_posterior"><!-- 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>q_posterior</span></h4><!-- HTML_TAG_END -->
 <a id="diffusers.VQDiffusionScheduler.q_posterior" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.VQDiffusionScheduler.q_posterior"><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/v0.18.2/src/diffusers/schedulers/scheduling_vq_diffusion.py#L260" 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">log_p_x_0<span class="opacity-60"></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">x_t<span class="opacity-60"></span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">t<span class="opacity-60"></span></span>
 </span>
 <span>)</span>
 <span class="font-bold">→</span>
 <span class="rounded hover:bg-gray-400 cursor-pointer"><!-- HTML_TAG_START --><span><code>torch.FloatTensor</code> of shape <code>(batch size, num classes, num latent pixels)</code></span><!-- HTML_TAG_END --></span></p>
<div class="!mb-10 relative docstring-details ">
 <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p>
 <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.q_posterior.t" class="header-link block pr-0.5 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.VQDiffusionScheduler.q_posterior.t"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>t</strong> (torch.Long) &#x2014;
The timestep that determines which transition matrix is used.<!-- HTML_TAG_END -->
 </span></span>
 </li></ul>
<div id="diffusers.VQDiffusionScheduler.q_posterior.returns" class="flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800 rounded "><p class="text-base">Returns</p>
 <!-- HTML_TAG_START -->
<p><code>torch.FloatTensor</code> of shape <code>(batch size, num classes, num latent pixels)</code></p>
<!-- HTML_TAG_END -->
 <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700"></span></div>
 <p class="text-base"><!-- HTML_TAG_START -->
<p>The log probabilities for the predicted classes of the image at timestep <code>t-1</code>. I.e. Equation (11).</p>
<!-- HTML_TAG_END --></p>
 </div></div>
<p>Calculates the log probabilities for the predicted classes of the image at timestep <code>t-1</code>. I.e. Equation (11).</p>
<p>Instead of directly computing equation (11), we use Equation (5) to restate Equation (11) in terms of only
forward probabilities.</p>
<p>Equation (11) stated in terms of forward probabilities via Equation (5):</p>
<p>Where:</p>
<ul><li>the sum is over x<em>0 = {C_0 … C</em>{k-1}} (classes for x_0)</li></ul>
<p>p(x<em>{t-1} | x_t) = sum( q(x_t | x</em>{t-1}) <em>q(x_{t-1} | x_0) </em> p(x_0) / q(x_t | x_0) )</p></div>
<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.VQDiffusionScheduler.set_timesteps"><!-- 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>set_timesteps</span></h4><!-- HTML_TAG_END -->
 <a id="diffusers.VQDiffusionScheduler.set_timesteps" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.VQDiffusionScheduler.set_timesteps"><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/v0.18.2/src/diffusers/schedulers/scheduling_vq_diffusion.py#L190" 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-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">num_inference_steps<span class="opacity-60">: int</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">device<span class="opacity-60">: typing.Union[str, torch.device] = None</span></span>
 </span>
 <span>)</span>
 </p>
<div class="!mb-10 relative docstring-details ">
 <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p>
 <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.set_timesteps.num_inference_steps" class="header-link block pr-0.5 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.VQDiffusionScheduler.set_timesteps.num_inference_steps"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>num_inference_steps</strong> (<code>int</code>) &#x2014;
the number of diffusion steps used when generating samples with a pre-trained model.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.set_timesteps.device" class="header-link block pr-0.5 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.VQDiffusionScheduler.set_timesteps.device"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>device</strong> (<code>str</code> or <code>torch.device</code>) &#x2014;
device to place the timesteps and the diffusion process parameters (alpha, beta, gamma) on.<!-- HTML_TAG_END -->
 </span></span>
 </li></ul>
</div></div>
<p>Sets the discrete timesteps used for the diffusion chain. Supporting function to be run before inference.</p></div>
<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.VQDiffusionScheduler.step"><!-- 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>step</span></h4><!-- HTML_TAG_END -->
 <a id="diffusers.VQDiffusionScheduler.step" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.VQDiffusionScheduler.step"><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/v0.18.2/src/diffusers/schedulers/scheduling_vq_diffusion.py#L212" 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">model_output<span class="opacity-60">: FloatTensor</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">timestep<span class="opacity-60">: torch.int64</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">sample<span class="opacity-60">: LongTensor</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.Optional[torch._C.Generator] = None</span></span>
 </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">return_dict<span class="opacity-60">: bool = True</span></span>
 </span>
 <span>)</span>
 <span class="font-bold">→</span>
 <span class="rounded hover:bg-gray-400 cursor-pointer"><!-- HTML_TAG_START --><span><code>~schedulers.scheduling_utils.VQDiffusionSchedulerOutput</code> or <code>tuple</code></span><!-- HTML_TAG_END --></span></p>
<div class="!mb-10 relative docstring-details ">
 <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p>
 <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.step.t" class="header-link block pr-0.5 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.VQDiffusionScheduler.step.t"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>t</strong> (<code>torch.long</code>) &#x2014;
The timestep that determines which transition matrices are used.</p>
<p>x_t &#x2014; (<code>torch.LongTensor</code> of shape <code>(batch size, num latent pixels)</code>):
The classes of each latent pixel at time <code>t</code></p>
<p>generator &#x2014; (<code>torch.Generator</code> or None):
RNG for the noise applied to p(x_{t-1} | x_t) before it is sampled from.<!-- HTML_TAG_END -->
 </span></span>
 </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.VQDiffusionScheduler.step.return_dict" class="header-link block pr-0.5 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.VQDiffusionScheduler.step.return_dict"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>return_dict</strong> (<code>bool</code>) &#x2014;
option for returning tuple rather than VQDiffusionSchedulerOutput class<!-- HTML_TAG_END -->
 </span></span>
 </li></ul>
<div id="diffusers.VQDiffusionScheduler.step.returns" class="flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800 rounded "><p class="text-base">Returns</p>
 <!-- HTML_TAG_START -->
<p><code>~schedulers.scheduling_utils.VQDiffusionSchedulerOutput</code> or <code>tuple</code></p>
<!-- HTML_TAG_END -->
 <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700"></span></div>
 <p class="text-base"><!-- HTML_TAG_START -->
<p><code>~schedulers.scheduling_utils.VQDiffusionSchedulerOutput</code> if <code>return_dict</code> is True, otherwise a <code>tuple</code>.
When returning a tuple, the first element is the sample tensor.</p>
<!-- HTML_TAG_END --></p>
 </div></div>
<p>Predict the sample at the previous timestep via the reverse transition distribution i.e. Equation (11). See the
docstring for <code>self.q_posterior</code> for more in depth docs on how Equation (11) is computed.</p></div></div>
<script type="module" data-hydrate="1t9nu2r">
 import { start } from "/docs/diffusers/v0.18.2/en/_app/start-hf-doc-builder.js";
 start({
 target: document.querySelector('[data-hydrate="1t9nu2r"]').parentNode,
 paths: {"base":"/docs/diffusers/v0.18.2/en","assets":"/docs/diffusers/v0.18.2/en"},
 session: {},
 route: false,
 spa: false,
 trailing_slash: "never",
 hydrate: {
 status: 200,
 error: null,
 nodes: [
 import("/docs/diffusers/v0.18.2/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
 import("/docs/diffusers/v0.18.2/en/_app/pages/api/schedulers/vq_diffusion.mdx-hf-doc-builder.js")
 ],
 params: {}
 }
 });
 </script>

Xet Storage Details

Size:
56.1 kB
·
Xet hash:
706bf3f0d4f62ff770bde026a08761da8b08a7bbf3f9611d5890b3e21ec0a7ee

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