Buckets:

hf-doc-build/doc / diffusers /v0.2.4 /en /schedulers.html
rtrm's picture
download
raw
7.36 kB
<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;schedulers&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;api&quot;,&quot;title&quot;:&quot;API&quot;},{&quot;local&quot;:&quot;examples&quot;,&quot;title&quot;:&quot;Examples&quot;}],&quot;title&quot;:&quot;Schedulers&quot;}" data-svelte="svelte-1phssyn">
<link rel="modulepreload" href="/docs/diffusers/v0.2.4/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
<link rel="modulepreload" href="/docs/diffusers/v0.2.4/en/_app/start-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.2.4/en/_app/chunks/vendor-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.2.4/en/_app/chunks/paths-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.2.4/en/_app/pages/__layout.svelte-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.2.4/en/_app/pages/schedulers.mdx-hf-doc-builder.js">
<link rel="modulepreload" href="/docs/diffusers/v0.2.4/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
<h1 class="relative group"><a id="schedulers" 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="#schedulers"><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>Schedulers
</span></h1>
<p>The base class [‘SchedulerMixin’] implements low level utilities used by multiple schedulers.
At a high level:</p>
<ul><li>Schedulers are the algorithms to use diffusion models in inference as well as for training. They include the noise schedules and define algorithm-specific diffusion steps.</li>
<li>Schedulers can be used interchangable between diffusion models in inference to find the preferred tradef-off between speed and generation quality.</li>
<li>Schedulers are available in numpy, but can easily be transformed into PyTorch.</li></ul>
<h2 class="relative group"><a id="api" 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="#api"><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>API
</span></h2>
<ul><li>Schedulers should provide one or more <code>def step(...)</code> functions that should be called iteratively to unroll the diffusion loop during
the forward pass.</li>
<li>Schedulers should be framework-agonstic, but provide a simple functionality to convert the scheduler into a specific framework, such as PyTorch
with a <code>set_format(...)</code> method.</li></ul>
<h2 class="relative group"><a id="examples" 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="#examples"><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>Examples
</span></h2>
<ul><li>The [‘DDPMScheduler’] was proposed in <a href="https://arxiv.org/abs/2006.11239" rel="nofollow">Denoising Diffusion Probabilistic Models</a> and can be found in <a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddpm.py" rel="nofollow">scheduling_ddpm.py</a>.
An example of how to use this scheduler can be found in <a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_ddpm.py" rel="nofollow">pipeline_ddpm.py</a>.</li>
<li>The [‘DDIMScheduler’] was proposed in <a href="https://arxiv.org/abs/2010.02502" rel="nofollow">Denoising Diffusion Implicit Models</a> and can be found in <a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddim.py" rel="nofollow">scheduling_ddim.py</a>. An example of how to use this scheduler can be found in <a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_ddim.py" rel="nofollow">pipeline_ddim.py</a>.</li>
<li>The [‘PNDMScheduler’] was proposed in <a href="https://arxiv.org/abs/2202.09778" rel="nofollow">Pseudo Numerical Methods for Diffusion Models on Manifolds</a> and can be found in <a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_pndm.py" rel="nofollow">scheduling_pndm.py</a>. An example of how to use this scheduler can be found in <a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/pipeline_pndm.py" rel="nofollow">pipeline_pndm.py</a>.</li></ul>
<script type="module" data-hydrate="1fpvc0u">
import { start } from "/docs/diffusers/v0.2.4/en/_app/start-hf-doc-builder.js";
start({
target: document.querySelector('[data-hydrate="1fpvc0u"]').parentNode,
paths: {"base":"/docs/diffusers/v0.2.4/en","assets":"/docs/diffusers/v0.2.4/en"},
session: {},
route: false,
spa: false,
trailing_slash: "never",
hydrate: {
status: 200,
error: null,
nodes: [
import("/docs/diffusers/v0.2.4/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
import("/docs/diffusers/v0.2.4/en/_app/pages/schedulers.mdx-hf-doc-builder.js")
],
params: {}
}
});
</script>

Xet Storage Details

Size:
7.36 kB
·
Xet hash:
6edf2cc0f1cefa2320c6401a0d3c5ece049238a733a2fa56b3aaf395e75ad993

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