Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /main /id /optimization /overview.html
mishig's picture
mishig
download
raw
18.2 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Ikhtisar&quot;,&quot;local&quot;:&quot;overview&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Jalur pemula&quot;,&quot;local&quot;:&quot;starter-path&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Teknik optimasi&quot;,&quot;local&quot;:&quot;optimization-techniques&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/main/en/_app/immutable/entry/start.B6roO9Zr.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/CjYFLaCl.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/Cc4T7sti.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/entry/app.CxxEVG8A.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/C8F28shN.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/BTnLXsn-.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DnVIJfC5.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/nodes/0.CmHT0Edy.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/C7Ky3Ped.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/nodes/10.B5TmysUP.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/D2YP2_0L.js" rel="modulepreload">
<!--h94dja--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Overview&quot;,&quot;local&quot;:&quot;overview&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Starter path&quot;,&quot;local&quot;:&quot;starter-path&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Optimization techniques&quot;,&quot;local&quot;:&quot;optimization-techniques&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
<link href="/docs/diffusers/main/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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><!----></span> <span dir="auto">Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <!--[0--><h1 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 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><!---->Ikhtisar<!----></span></h1><!--]--><!----> <p>Inferensi difusi sangat mahal secara komputasi, dan Anda sering kali menjalankan <a href="/docs/diffusers/main/id/api/pipelines/overview#diffusers.DiffusionPipeline">DiffusionPipeline</a> lebih dari sekali sebelum menyukai hasilnya. Halaman ini memberikan gambaran umum tentang teknik optimasi Diffusers utama, apa yang dilakukan, dan kapan harus menggunakannya.</p> <!--[1--><h2 class="relative group"><a id="starter-path" 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="#starter-path"><span><svg 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><!---->Jalur pemula<!----></span></h2><!--]--><!----> <p>Ketika model muat di satu GPU, mulai dengan beban dasar ini. Atur <code>dtype</code> dan letakkan pipeline di akselerator. Gunakan model CPU offload hanya ketika memori terbatas. Anda juga bisa mempercepat inferensi dengan langkah yang lebih sedikit atau scheduler yang lebih cepat.</p> <p>Saat Anda mengabaikan <code>dtype</code>, Diffusers memuat komponen dalam <code>float32</code>. Sampaikan <code>dtype=torch.bfloat16</code> (atau <code>torch.float16</code> jika bfloat16 tidak didukung), lalu letakkan pipeline pada akselerator dengan <code>pipeline.to("cuda")</code>.</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 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> Disalin</div><!----></button><!----></div> <pre class="language-py "><!----><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;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
dtype=torch.bfloat16,
)
pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>) <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;</span>
prompt = <span class="hljs-string">&quot;&quot;&quot;
cinematic film still of a cat sipping a margarita in a pool in Palm Springs, California
highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain
&quot;&quot;&quot;</span>
pipeline(prompt).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <p>Jika pipeline tidak muat, atau memori terbatas, panggil <a href="/docs/diffusers/main/id/api/pipelines/overview#diffusers.DiffusionPipeline.enable_model_cpu_offload">enable_model_cpu_offload()</a> alih-alih menyimpan semuanya di GPU. Fungsi ini menempatkan model aktif di GPU dan menyimpan komponen lainnya di CPU.</p> <p>Lewati langkah ini jika model muat. Offloading lebih lambat jika tidak diperlukan.</p> <p>Untuk lebih banyak opsi offloading, lihat <a href="./memory#offloading">Kurangi penggunaan memori</a>.</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 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> Disalin</div><!----></button><!----></div> <pre class="language-py "><!---->pipeline = DiffusionPipeline.from_pretrained(
<span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
dtype=torch.bfloat16,
)
pipeline.enable_model_cpu_offload()<!----></pre></div><!----> <p>Latensi lebih rendah dengan <code>num_inference_steps</code> yang lebih sedikit atau scheduler yang lebih cepat seperti <a href="/docs/diffusers/main/id/api/schedulers/multistep_dpm_solver#diffusers.DPMSolverMultistepScheduler">DPMSolverMultistepScheduler</a>. Hal itu biasanya mempercepat proses generasi, tetapi dapat mengurangi kualitas gambar dibandingkan scheduler yang lebih lambat namun berkualitas lebih tinggi. Lihat <a href="#optimization-techniques">teknik optimasi</a> di bawah untuk teknik kecepatan lainnya.</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 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> Disalin</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> time
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DPMSolverMultistepScheduler
pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config)
start_time = time.perf_counter()
image = pipeline(prompt, num_inference_steps=<span class="hljs-number">25</span>).images[<span class="hljs-number">0</span>]
end_time = time.perf_counter()
<span class="hljs-built_in">print</span>(<span class="hljs-string">f&quot;Image generation took <span class="hljs-subst">{end_time - start_time:<span class="hljs-number">.3</span>f}</span> seconds&quot;</span>)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="optimization-techniques" 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="#optimization-techniques"><span><svg 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><!---->Teknik optimasi<!----></span></h2><!--]--><!----> <p>Ketika jalur awal tidak cukup, gunakan teknik-teknik ini. Jika inferensi terlalu lambat, mulai dengan <code>torch.compile</code>, caching, atau backend attention. Jika Anda kehabisan memori, mulai dengan offloading atau kuantisasi.</p> <p>Inferensi yang lebih cepat:</p> <ul><li><a href="./fp16#torchcompile">torch.compile</a> — Mengompilasi UNet, transformer, atau VAE menjadi kernel yang dioptimalkan.</li> <li><a href="./fp16#regional-compilation">Kompilasi regional</a> — Kompilasi blok yang berulang untuk memangkas latensi cold-start <code>torch.compile</code> dan menggunakan kembali artefak yang dikompilasi.</li> <li><a href="./cache">Caching</a> — Memanfaatkan kembali nilai perantara di antara langkah-langkah denoising ketika Anda menginginkan kecepatan lebih tinggi dan dapat mengalokasikan memori lebih banyak.</li> <li><a href="./attention_backends">Backend perhatian</a> — Ganti implementasi perhatian Diffusers melalui API terpadu ketika perhatian menjadi hambatan utama.</li> <li><a href="./fp16#kernels">Kernels</a> — Muat kernel komputasi Hub yang dioptimalkan (attention dan operasi CUDA khusus seperti RMSNorm atau RoPE) ketika Anda membutuhkan percepatan spesifik perangkat keras di luar PyTorch standar.</li></ul> <p>Memori lebih sedikit:</p> <ul><li><a href="./memory#offloading">Offloading</a> — Pindahkan model atau lapisan yang tidak aktif ke CPU dengan offloading CPU, model, atau grup.</li> <li><a href="../quantization/overview">Kuantisasi</a> — Muat bobot yang lebih kecil untuk memangkas memori (beberapa backend juga mempercepat inferensi). <a href="../quantization/gguf">GGUF</a> adalah titik awal yang umum.</li> <li><a href="./memory#vae-slicing">VAE slicing</a> dan <a href="./memory#vae-tiling">VAE tiling</a> — Dekode batch besar atau gambar resolusi tinggi secara bertahap untuk menurunkan memori puncak.</li></ul> <p>Keduanya:</p> <ul><li><a href="./speed-memory-optims">Kuantisasi, kompilasi, dan offload</a> — Gabungkan kuantisasi, <code>torch.compile</code>, dan offloading ketika satu teknik saja tidak cukup.</li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/diffusers/blob/main/docs/source/en/optimization/overview.md" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
<script>
{
__sveltekit_kft2r9 = {
base: "/docs/diffusers/main/en",
assets: "/docs/diffusers/main/en"
};
const element = document.currentScript.parentElement;
Promise.all([
import("/docs/diffusers/main/en/_app/immutable/entry/start.B6roO9Zr.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.CxxEVG8A.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 10],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
18.2 kB
·
Xet hash:
7c1f271ea38a371437e23f751a65a87ae42ad27b8de6c6056872362c4e73821d

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