diffusers/v0.19.3/en/using-diffusers/textual_inversion_inference.html

<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;textual-inversion&quot;,&quot;title&quot;:&quot;Textual inversion&quot;}" data-svelte="svelte-1phssyn">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/start-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/vendor-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/paths-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/pages/__layout.svelte-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/pages/using-diffusers/textual_inversion_inference.mdx-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/CodeBlock-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.19.3/en/_app/chunks/DocNotebookDropdown-hf-doc-builder.js"> 





<h1 class="relative group"><a id="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="#textual-inversion"><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>Textual inversion
	</span></h1>



<div class="flex space-x-1 absolute z-10 right-0 top-0">
	<div class="relative colab-dropdown ">
	<button class="  " type="button">
		
				<img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg">
			</button>
	
	
	
	</div>
	<div class="relative colab-dropdown ">
	<button class="  " type="button">
		
				<img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg">
			</button>
	
	
	
	</div></div>
<p>The <a href="/docs/diffusers/v0.19.3/en/api/pipelines/stable_diffusion/text2img#diffusers.StableDiffusionPipeline">StableDiffusionPipeline</a> supports textual inversion, a technique that enables a model like Stable Diffusion to learn a new concept from just a few sample images. This gives you more control over the generated images and allows you to tailor the model towards specific concepts. You can get started quickly with a collection of community created concepts in the <a href="https://huggingface.co/spaces/sd-concepts-library/stable-diffusion-conceptualizer" rel="nofollow">Stable Diffusion Conceptualizer</a>.</p>
<p>This guide will show you how to run inference with textual inversion using a pre-learned concept from the Stable Diffusion Conceptualizer. If you’re interested in teaching a model new concepts with textual inversion, take a look at the <a href="./training/text_inversion">Textual Inversion</a> training guide.</p>
<p>Login to your Hugging Face account:</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 class="" 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><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> notebook_login

notebook_login()<!-- HTML_TAG_END --></pre></div>
<p>Import the necessary libraries, and create a helper function to visualize the generated images:</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 class="" 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><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> os
<span class="hljs-keyword">import</span> torch

<span class="hljs-keyword">import</span> PIL
<span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image

<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionPipeline
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer


<span class="hljs-keyword">def</span> <span class="hljs-title function_">image_grid</span>(<span class="hljs-params">imgs, rows, cols</span>):
    <span class="hljs-keyword">assert</span> <span class="hljs-built_in">len</span>(imgs) == rows * cols

    w, h = imgs[<span class="hljs-number">0</span>].size
    grid = Image.new(<span class="hljs-string">&quot;RGB&quot;</span>, size=(cols * w, rows * h))
    grid_w, grid_h = grid.size

    <span class="hljs-keyword">for</span> i, img <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(imgs):
        grid.paste(img, box=(i % cols * w, i // cols * h))
    <span class="hljs-keyword">return</span> grid<!-- HTML_TAG_END --></pre></div>
<p>Pick a Stable Diffusion checkpoint and a pre-learned concept from the <a href="https://huggingface.co/spaces/sd-concepts-library/stable-diffusion-conceptualizer" rel="nofollow">Stable Diffusion Conceptualizer</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 class="" 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><!-- HTML_TAG_START -->pretrained_model_name_or_path = <span class="hljs-string">&quot;runwayml/stable-diffusion-v1-5&quot;</span>
repo_id_embeds = <span class="hljs-string">&quot;sd-concepts-library/cat-toy&quot;</span><!-- HTML_TAG_END --></pre></div>
<p>Now you can load a pipeline, and pass the pre-learned concept to it:</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 class="" 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><!-- HTML_TAG_START -->pipeline = StableDiffusionPipeline.from_pretrained(pretrained_model_name_or_path, torch_dtype=torch.float16).to(<span class="hljs-string">&quot;cuda&quot;</span>)

pipeline.load_textual_inversion(repo_id_embeds)<!-- HTML_TAG_END --></pre></div>
<p>Create a prompt with the pre-learned concept by using the special placeholder token <code>&lt;cat-toy&gt;</code>, and choose the number of samples and rows of images you’d like to generate:</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 class="" 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><!-- HTML_TAG_START -->prompt = <span class="hljs-string">&quot;a grafitti in a favela wall with a &lt;cat-toy&gt; on it&quot;</span>

num_samples = <span class="hljs-number">2</span>
num_rows = <span class="hljs-number">2</span><!-- HTML_TAG_END --></pre></div>
<p>Then run the pipeline (feel free to adjust the parameters like <code>num_inference_steps</code> and <code>guidance_scale</code> to see how they affect image quality), save the generated images and visualize them with the helper function you created at the beginning:</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 class="" 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><!-- HTML_TAG_START -->all_images = []
<span class="hljs-keyword">for</span> _ <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(num_rows):
    images = pipe(prompt, num_images_per_prompt=num_samples, num_inference_steps=<span class="hljs-number">50</span>, guidance_scale=<span class="hljs-number">7.5</span>).images
    all_images.extend(images)

grid = image_grid(all_images, num_samples, num_rows)
grid<!-- HTML_TAG_END --></pre></div>
<div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/textual_inversion_inference.png"></div>


		<script type="module" data-hydrate="1c6hoxy">
		import { start } from "/docs/diffusers/v0.19.3/en/_app/start-hf-doc-builder.js";
		start({
			target: document.querySelector('[data-hydrate="1c6hoxy"]').parentNode,
			paths: {"base":"/docs/diffusers/v0.19.3/en","assets":"/docs/diffusers/v0.19.3/en"},
			session: {},
			route: false,
			spa: false,
			trailing_slash: "never",
			hydrate: {
				status: 200,
				error: null,
				nodes: [
					import("/docs/diffusers/v0.19.3/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
						import("/docs/diffusers/v0.19.3/en/_app/pages/using-diffusers/textual_inversion_inference.mdx-hf-doc-builder.js")
				],
				params: {}
			}
		});
	</script>