Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / optimum-intel /pr_1908 /en /openvino /tutorials /diffusers.html

HuggingFaceDocBuilder

19 days ago

download

raw

49.9 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Generate images with Diffusion models","local":"generate-images-with-diffusion-models","sections":[{"title":"Stable Diffusion","local":"stable-diffusion","sections":[{"title":"Text-to-Image","local":"text-to-image","sections":[],"depth":3},{"title":"Text-to-Image with Textual Inversion","local":"text-to-image-with-textual-inversion","sections":[],"depth":3},{"title":"Image-to-Image","local":"image-to-image","sections":[],"depth":3}],"depth":2},{"title":"Stable Diffusion XL","local":"stable-diffusion-xl","sections":[{"title":"Text-to-Image","local":"text-to-image","sections":[],"depth":3},{"title":"Text-to-Image with Textual Inversion","local":"text-to-image-with-textual-inversion","sections":[],"depth":3},{"title":"Image-to-Image","local":"image-to-image","sections":[],"depth":3},{"title":"Refining the image output","local":"refining-the-image-output","sections":[],"depth":3}],"depth":2},{"title":"Latent Consistency Models","local":"latent-consistency-models","sections":[{"title":"Text-to-Image","local":"text-to-image","sections":[],"depth":3}],"depth":2}],"depth":1}"/>
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/entry/start.CatJ25dz.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/chunks/B-VqpFX9.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/chunks/Cbbc2wwc.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/entry/app.KpdgG_wN.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/chunks/DeDI0Q53.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/chunks/6YgYxE4i.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/chunks/B9oc0ti6.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/nodes/0.CgngmqY0.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/chunks/CczWW-MX.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/nodes/9.RDjQi7TX.js" rel="modulepreload">
	<link href="/docs/optimum.intel/pr_1908/en/_app/immutable/chunks/yrm_jVWY.js" rel="modulepreload">
	<!--jryu49--><meta name="hf:doc:metadata" content="{"title":"Generate images with Diffusion models","local":"generate-images-with-diffusion-models","sections":[{"title":"Stable Diffusion","local":"stable-diffusion","sections":[{"title":"Text-to-Image","local":"text-to-image","sections":[],"depth":3},{"title":"Text-to-Image with Textual Inversion","local":"text-to-image-with-textual-inversion","sections":[],"depth":3},{"title":"Image-to-Image","local":"image-to-image","sections":[],"depth":3}],"depth":2},{"title":"Stable Diffusion XL","local":"stable-diffusion-xl","sections":[{"title":"Text-to-Image","local":"text-to-image","sections":[],"depth":3},{"title":"Text-to-Image with Textual Inversion","local":"text-to-image-with-textual-inversion","sections":[],"depth":3},{"title":"Image-to-Image","local":"image-to-image","sections":[],"depth":3},{"title":"Refining the image output","local":"refining-the-image-output","sections":[],"depth":3}],"depth":2},{"title":"Latent Consistency Models","local":"latent-consistency-models","sections":[{"title":"Text-to-Image","local":"text-to-image","sections":[],"depth":3}],"depth":2}],"depth":1}"/><!---->
	<link href="/docs/optimum.intel/pr_1908/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="generate-images-with-diffusion-models" 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="#generate-images-with-diffusion-models"><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>Generate images with Diffusion models</span></h1><!--]--><!----> <!--[1--><h2 class="relative group"><a id="stable-diffusion" 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="#stable-diffusion"><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>Stable Diffusion</span></h2><!--]--><!----> <p>Stable Diffusion models can also be used when running inference with OpenVINO. When Stable Diffusion models
	are exported to the OpenVINO format, they are decomposed into different components that are later combined during inference:</p> <ul><li>The text encoder</li> <li>The U-NET</li> <li>The VAE encoder</li> <li>The VAE decoder</li></ul> <table><thead><tr><th>Task</th><th>Auto Class</th></tr></thead><tbody><tr><td><code>text-to-image</code></td><td><code>OVStableDiffusionPipeline</code></td></tr><tr><td><code>image-to-image</code></td><td><code>OVStableDiffusionImg2ImgPipeline</code></td></tr><tr><td><code>inpaint</code></td><td><code>OVStableDiffusionInpaintPipeline</code></td></tr></tbody></table> <!--[2--><h3 class="relative group"><a id="text-to-image" 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="#text-to-image"><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>Text-to-Image</span></h3><!--]--><!----> <p>Here is an example of how you can load an OpenVINO Stable Diffusion model and run inference using OpenVINO Runtime:</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-python "><!----><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVStableDiffusionPipeline

	model_id = <span class="hljs-string">"echarlaix/stable-diffusion-v1-5-openvino"</span>
	pipeline = OVStableDiffusionPipeline.from_pretrained(model_id)
	prompt = <span class="hljs-string">"sailing ship in storm by Rembrandt"</span>
	images = pipeline(prompt).images<!----></pre></div><!----> <p>To load your PyTorch model and convert it to OpenVINO on the fly, you can set <code>export=True</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->model_id = <span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>
	pipeline = OVStableDiffusionPipeline.from_pretrained(model_id, export=<span class="hljs-literal">True</span>)
	<span class="hljs-comment"># Don't forget to save the exported model</span>
	pipeline.save_pretrained(<span class="hljs-string">"openvino-sd-v1-5"</span>)<!----></pre></div><!----> <p>To further speed up inference, the model can be statically reshaped :</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-python "><!----><span class="hljs-comment"># Define the shapes related to the inputs and desired outputs</span>
	batch_size, num_images, height, width = <span class="hljs-number">1</span>, <span class="hljs-number">1</span>, <span class="hljs-number">512</span>, <span class="hljs-number">512</span>
	<span class="hljs-comment"># Statically reshape the model</span>
	pipeline.reshape(batch_size=batch_size, height=height, width=width, num_images_per_prompt=num_images)
	<span class="hljs-comment"># Compile the model before the first inference</span>
	pipeline.<span class="hljs-built_in">compile</span>()

	<span class="hljs-comment"># Run inference</span>
	images = pipeline(prompt, height=height, width=width, num_images_per_prompt=num_images).images<!----></pre></div><!----> <p>In case you want to change any parameters such as the outputs height or width, you’ll need to statically reshape your model once again.</p> <div class="flex justify-center"><img src="https://huggingface.co/datasets/optimum/documentation-images/resolve/main/intel/openvino/stable_diffusion_v1_5_sail_boat_rembrandt.png"/></div> <!--[2--><h3 class="relative group"><a id="text-to-image-with-textual-inversion" 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="#text-to-image-with-textual-inversion"><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>Text-to-Image with Textual Inversion</span></h3><!--]--><!----> <p>Here is an example of how you can load an OpenVINO Stable Diffusion model with pre-trained textual inversion embeddings and run inference using OpenVINO Runtime:</p> <p>First, you can run original pipeline without textual inversion</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-python "><!----><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVStableDiffusionPipeline
	<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np

	model_id = <span class="hljs-string">"echarlaix/stable-diffusion-v1-5-openvino"</span>
	prompt = <span class="hljs-string">"A <cat-toy> back-pack"</span>
	<span class="hljs-comment"># Set a random seed for better comparison</span>
	np.random.seed(<span class="hljs-number">42</span>)

	pipeline = OVStableDiffusionPipeline.from_pretrained(model_id, export=<span class="hljs-literal">False</span>, <span class="hljs-built_in">compile</span>=<span class="hljs-literal">False</span>)
	pipeline.<span class="hljs-built_in">compile</span>()
	image1 = pipeline(prompt, num_inference_steps=<span class="hljs-number">50</span>).images[<span class="hljs-number">0</span>]
	image1.save(<span class="hljs-string">"stable_diffusion_v1_5_without_textual_inversion.png"</span>)<!----></pre></div><!----> <p>Then, you can load <a href="https://huggingface.co/sd-concepts-library/cat-toy" rel="nofollow">sd-concepts-library/cat-toy</a> textual inversion embedding and run pipeline with same prompt again</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-python "><!----><span class="hljs-comment"># Reset stable diffusion pipeline</span>
	pipeline.clear_requests()

	<span class="hljs-comment"># Load textual inversion into stable diffusion pipeline</span>
	pipeline.load_textual_inversion(<span class="hljs-string">"sd-concepts-library/cat-toy"</span>, <span class="hljs-string">"<cat-toy>"</span>)

	<span class="hljs-comment"># Compile the model before the first inference</span>
	pipeline.<span class="hljs-built_in">compile</span>()
	image2 = pipeline(prompt, num_inference_steps=<span class="hljs-number">50</span>).images[<span class="hljs-number">0</span>]
	image2.save(<span class="hljs-string">"stable_diffusion_v1_5_with_textual_inversion.png"</span>)<!----></pre></div><!----> <p>The left image shows the generation result of original stable diffusion v1.5, the right image shows the generation result of stable diffusion v1.5 with textual inversion.</p> <table><thead><tr><th></th><th></th></tr></thead><tbody><tr><td><img src="https://huggingface.co/datasets/optimum/documentation-images/resolve/main/intel/openvino/textual_inversion/stable_diffusion_v1_5_without_textual_inversion.png"/></td><td><img src="https://huggingface.co/datasets/optimum/documentation-images/resolve/main/intel/openvino/textual_inversion/stable_diffusion_v1_5_with_textual_inversion.png"/></td></tr></tbody></table> <!--[2--><h3 class="relative group"><a id="image-to-image" 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="#image-to-image"><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>Image-to-Image</span></h3><!--]--><!----> <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-python "><!----><span class="hljs-keyword">import</span> requests
	<span class="hljs-keyword">import</span> torch
	<span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
	<span class="hljs-keyword">from</span> io <span class="hljs-keyword">import</span> BytesIO
	<span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVStableDiffusionImg2ImgPipeline

	model_id = <span class="hljs-string">"runwayml/stable-diffusion-v1-5"</span>
	pipeline = OVStableDiffusionImg2ImgPipeline.from_pretrained(model_id, export=<span class="hljs-literal">True</span>)

	url = <span class="hljs-string">"https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"</span>
	response = requests.get(url)
	init_image = Image.<span class="hljs-built_in">open</span>(BytesIO(response.content)).convert(<span class="hljs-string">"RGB"</span>)
	init_image = init_image.resize((<span class="hljs-number">768</span>, <span class="hljs-number">512</span>))
	prompt = <span class="hljs-string">"A fantasy landscape, trending on artstation"</span>
	image = pipeline(prompt=prompt, image=init_image, strength=<span class="hljs-number">0.75</span>, guidance_scale=<span class="hljs-number">7.5</span>).images[<span class="hljs-number">0</span>]
	image.save(<span class="hljs-string">"fantasy_landscape.png"</span>)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="stable-diffusion-xl" 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="#stable-diffusion-xl"><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>Stable Diffusion XL</span></h2><!--]--><!----> <table><thead><tr><th>Task</th><th>Auto Class</th></tr></thead><tbody><tr><td><code>text-to-image</code></td><td><code>OVStableDiffusionXLPipeline</code></td></tr><tr><td><code>image-to-image</code></td><td><code>OVStableDiffusionXLImg2ImgPipeline</code></td></tr></tbody></table> <!--[2--><h3 class="relative group"><a id="text-to-image" 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="#text-to-image"><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>Text-to-Image</span></h3><!--]--><!----> <p>Here is an example of how you can load a SDXL OpenVINO model from <a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0" rel="nofollow">stabilityai/stable-diffusion-xl-base-1.0</a> and run inference using OpenVINO Runtime:</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-python "><!----><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVStableDiffusionXLPipeline

	model_id = <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>
	base = OVStableDiffusionXLPipeline.from_pretrained(model_id)
	prompt = <span class="hljs-string">"train station by Caspar David Friedrich"</span>
	image = base(prompt).images[<span class="hljs-number">0</span>]
	image.save(<span class="hljs-string">"train_station.png"</span>)<!----></pre></div><!----> <table><thead><tr><th></th><th></th></tr></thead><tbody><tr><td><img src="https://huggingface.co/datasets/optimum/documentation-images/resolve/main/intel/openvino/sd_xl/train_station_friedrich.png"/></td><td><img src="https://huggingface.co/datasets/optimum/documentation-images/resolve/main/intel/openvino/sd_xl/train_station_friedrich_2.png"/></td></tr></tbody></table> <!--[2--><h3 class="relative group"><a id="text-to-image-with-textual-inversion" 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="#text-to-image-with-textual-inversion"><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>Text-to-Image with Textual Inversion</span></h3><!--]--><!----> <p>Here is an example of how you can load an SDXL OpenVINO model from <a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0" rel="nofollow">stabilityai/stable-diffusion-xl-base-1.0</a> with pre-trained textual inversion embeddings and run inference using OpenVINO Runtime:</p> <p>First, you can run original pipeline without textual inversion</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-python "><!----><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVStableDiffusionXLPipeline
	<span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np

	model_id = <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>
	prompt = <span class="hljs-string">"charturnerv2, multiple views of the same character in the same outfit, a character turnaround wearing a red jacket and black shirt, best quality, intricate details."</span>
	<span class="hljs-comment"># Set a random seed for better comparison</span>
	np.random.seed(<span class="hljs-number">112</span>)

	base = OVStableDiffusionXLPipeline.from_pretrained(model_id, export=<span class="hljs-literal">False</span>, <span class="hljs-built_in">compile</span>=<span class="hljs-literal">False</span>)
	base.<span class="hljs-built_in">compile</span>()
	image1 = base(prompt, num_inference_steps=<span class="hljs-number">50</span>).images[<span class="hljs-number">0</span>]
	image1.save(<span class="hljs-string">"sdxl_without_textual_inversion.png"</span>)<!----></pre></div><!----> <p>Then, you can load <a href="https://civitai.com/models/3036/charturner-character-turnaround-helper-for-15-and-21" rel="nofollow">charturnerv2</a> textual inversion embedding and run pipeline with same prompt again</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-python "><!----><span class="hljs-comment"># Reset stable diffusion pipeline</span>
	base.clear_requests()

	<span class="hljs-comment"># Load textual inversion into stable diffusion pipeline</span>
	base.load_textual_inversion(<span class="hljs-string">"./charturnerv2.pt"</span>, <span class="hljs-string">"charturnerv2"</span>)

	<span class="hljs-comment"># Compile the model before the first inference</span>
	base.<span class="hljs-built_in">compile</span>()
	image2 = base(prompt, num_inference_steps=<span class="hljs-number">50</span>).images[<span class="hljs-number">0</span>]
	image2.save(<span class="hljs-string">"sdxl_with_textual_inversion.png"</span>)<!----></pre></div><!----> <!--[2--><h3 class="relative group"><a id="image-to-image" 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="#image-to-image"><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>Image-to-Image</span></h3><!--]--><!----> <p>Here is an example of how you can load a PyTorch SDXL model, convert it to OpenVINO on-the-fly and run inference using OpenVINO Runtime for <em>image-to-image</em>:</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-python "><!----><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVStableDiffusionXLImg2ImgPipeline
	<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

	model_id = <span class="hljs-string">"stabilityai/stable-diffusion-xl-refiner-1.0"</span>
	pipeline = OVStableDiffusionXLImg2ImgPipeline.from_pretrained(model_id, export=<span class="hljs-literal">True</span>)

	url = <span class="hljs-string">"https://huggingface.co/datasets/optimum/documentation-images/resolve/main/intel/openvino/sd_xl/castle_friedrich.png"</span>
	image = load_image(url).convert(<span class="hljs-string">"RGB"</span>)
	prompt = <span class="hljs-string">"medieval castle by Caspar David Friedrich"</span>
	image = pipeline(prompt, image=image).images[<span class="hljs-number">0</span>]
	<span class="hljs-comment"># Don't forget to save your OpenVINO model so that you can load it without exporting it with `export=True`</span>
	pipeline.save_pretrained(<span class="hljs-string">"openvino-sd-xl-refiner-1.0"</span>)<!----></pre></div><!----> <!--[2--><h3 class="relative group"><a id="refining-the-image-output" 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="#refining-the-image-output"><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>Refining the image output</span></h3><!--]--><!----> <p>The image can be refined by making use of a model like <a href="https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0" rel="nofollow">stabilityai/stable-diffusion-xl-refiner-1.0</a>. In this case, you only have to output the latents from the base model.</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-python "><!----><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVStableDiffusionXLImg2ImgPipeline

	model_id = <span class="hljs-string">"stabilityai/stable-diffusion-xl-refiner-1.0"</span>
	refiner = OVStableDiffusionXLImg2ImgPipeline.from_pretrained(model_id, export=<span class="hljs-literal">True</span>)

	image = base(prompt=prompt, output_type=<span class="hljs-string">"latent"</span>).images[<span class="hljs-number">0</span>]
	image = refiner(prompt=prompt, image=image[<span class="hljs-literal">None</span>, :]).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="latent-consistency-models" 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="#latent-consistency-models"><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>Latent Consistency Models</span></h2><!--]--><!----> <table><thead><tr><th>Task</th><th>Auto Class</th></tr></thead><tbody><tr><td><code>text-to-image</code></td><td><code>OVLatentConsistencyModelPipeline</code></td></tr></tbody></table> <!--[2--><h3 class="relative group"><a id="text-to-image" 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="#text-to-image"><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>Text-to-Image</span></h3><!--]--><!----> <p>Here is an example of how you can load a Latent Consistency Model (LCM) from <a href="https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7" rel="nofollow">SimianLuo/LCM_Dreamshaper_v7</a> and run inference using OpenVINO :</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-python "><!----><span class="hljs-keyword">from</span> optimum.intel <span class="hljs-keyword">import</span> OVLatentConsistencyModelPipeline

	model_id = <span class="hljs-string">"SimianLuo/LCM_Dreamshaper_v7"</span>
	pipeline = OVLatentConsistencyModelPipeline.from_pretrained(model_id, export=<span class="hljs-literal">True</span>)
	prompt = <span class="hljs-string">"sailing ship in storm by Leonardo da Vinci"</span>
	images = pipeline(prompt, num_inference_steps=<span class="hljs-number">4</span>, guidance_scale=<span class="hljs-number">8.0</span>).images<!----></pre></div><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->

	<script>
	{
	__sveltekit_1ofgn6n = {
	base: "/docs/optimum.intel/pr_1908/en",
	assets: "/docs/optimum.intel/pr_1908/en"
	};

	const element = document.currentScript.parentElement;

	Promise.all([
	import("/docs/optimum.intel/pr_1908/en/_app/immutable/entry/start.CatJ25dz.js"),
	import("/docs/optimum.intel/pr_1908/en/_app/immutable/entry/app.KpdgG_wN.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 9],
	data: [null,null],
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 49.9 kB
Xet hash:: a06e11af4c4f448b55189a97c958e2c7b82fa938f67320f80324e475b01124a7

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