Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / diffusers /pr_15015 /en /using-diffusers /image_quality.html
HuggingFaceDocBuilder's picture
HuggingFaceDocBuilder
download
raw
13.4 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;FreeU&quot;,&quot;local&quot;:&quot;freeu&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Next steps&quot;,&quot;local&quot;:&quot;next-steps&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/main/en/_app/immutable/entry/start.DWxCGgMM.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/Cqlf-ARl.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.CS5rEiWu.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.DH-BrFQc.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/13.BbApVE8q.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/ULGFB-9v.js" rel="modulepreload">
<!--1d8qs2v--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;FreeU&quot;,&quot;local&quot;:&quot;freeu&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Next steps&quot;,&quot;local&quot;:&quot;next-steps&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: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div 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>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="freeu" 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="#freeu"><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>FreeU</span></h1><!--]--><!----> <p><a href="https://huggingface.co/papers/2309.11497" rel="nofollow">FreeU</a> improves image detail by rebalancing how much the UNet decoder draws from backbone features versus skip-connection features. Skip connections can drown out the backbone’s semantic features, which produces unnatural detail in the output. FreeU needs no training, and you can turn it on or off at inference time for text-to-image and text-to-video pipelines.</p> <blockquote class="note"><p>FreeU only works with UNet-based pipelines like Stable Diffusion, SDXL, and AnimateDiff. It isn’t supported by transformer-based pipelines like Flux or Qwen-Image.</p></blockquote> <p>Use the <a href="/docs/diffusers/pr_15015/en/api/pipelines/overview#diffusers.StableDiffusionMixin.enable_freeu">enable_freeu()</a> method on your pipeline and configure the scaling factors. <code>b1</code> and <code>b2</code> amplify the backbone features, and <code>s1</code> and <code>s2</code> dampen the skip features. The <code>1</code> and <code>2</code> refer to the first two upsampling stages of the UNet decoder. See the <a href="https://github.com/ChenyangSi/FreeU#parameters" rel="nofollow">FreeU</a> repository for reference hyperparameters for different models.</p> <p>Start with the repository values for a model. To tune for other models, keep <code>s1=0.9</code> and <code>s2=0.2</code> and adjust <code>b1</code> and <code>b2</code> first. Setting all four factors to <code>1.0</code> is the same as disabling FreeU. Larger <code>b</code> values strengthen the effect but can oversmooth fine texture, and lowering <code>s1</code> and <code>s2</code> counteracts that.</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> Copied</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.float16,
).to(<span class="hljs-string">&quot;cuda&quot;</span>) <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
pipeline.enable_freeu(s1=<span class="hljs-number">0.9</span>, s2=<span class="hljs-number">0.2</span>, b1=<span class="hljs-number">1.3</span>, b2=<span class="hljs-number">1.4</span>)
generator = torch.Generator(device=<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(<span class="hljs-number">13</span>)
prompt = <span class="hljs-string">&quot;A squirrel eating a burger&quot;</span>
image = pipeline(prompt, generator=generator).images[<span class="hljs-number">0</span>]
image<!----></pre></div><!----> <div class="flex gap-4"><div><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl-no-freeu.png"/> <figcaption class="mt-2 text-center text-sm text-gray-500">FreeU disabled</figcaption></div> <div><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl-freeu.png"/> <figcaption class="mt-2 text-center text-sm text-gray-500">FreeU enabled</figcaption></div></div> <p>Call the <a href="/docs/diffusers/pr_15015/en/api/pipelines/overview#diffusers.StableDiffusionMixin.disable_freeu">disable_freeu()</a> method to disable FreeU.</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> Copied</div><!----></button><!----></div> <pre class="language-py "><!---->pipeline.disable_freeu()<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="next-steps" 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="#next-steps"><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>Next steps</span></h2><!--]--><!----> <ul><li>See the <a href="/docs/diffusers/pr_15015/en/api/pipelines/overview#diffusers.StableDiffusionMixin.enable_freeu">enable_freeu()</a> API reference for the full parameter descriptions.</li> <li>Try FreeU on video with <a href="../api/pipelines/animatediff">AnimateDiff</a>.</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/using-diffusers/image_quality.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_13xinqp = {
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.DWxCGgMM.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.CS5rEiWu.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 13],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
13.4 kB
·
Xet hash:
4ad62779a80e33512bde57f148e16e5d658381344576a9f40776ebe45f4edeb1

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