Buckets:

hf-doc-build/doc-dev / diffusers /pr_11686 /en /using-diffusers /textual_inversion_inference.html
download
raw
11.5 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Textual Inversion&quot;,&quot;local&quot;:&quot;textual-inversion&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
<link href="/docs/diffusers/pr_11686/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/entry/start.2b9667fb.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/chunks/scheduler.8c3d61f6.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/chunks/singletons.756349ae.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/chunks/index.0997d446.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/chunks/paths.8d5937da.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/entry/app.a2a6117e.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/chunks/index.da70eac4.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/nodes/0.a31d0923.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/nodes/313.ffe714af.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/chunks/CodeBlock.a9c4becf.js">
<link rel="modulepreload" href="/docs/diffusers/pr_11686/en/_app/immutable/chunks/getInferenceSnippets.d00e08ac.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Textual Inversion&quot;,&quot;local&quot;:&quot;textual-inversion&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <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> <p data-svelte-h="svelte-1lyyk6k"><a href="https://huggingface.co/papers/2208.01618" rel="nofollow">Textual Inversion</a> is a method for generating personalized images of a concept. It works by fine-tuning a models word embeddings on 3-5 images of the concept (for example, pixel art) that is associated with a unique token (<code>&lt;sks&gt;</code>). This allows you to use the <code>&lt;sks&gt;</code> token in your prompt to trigger the model to generate pixel art images.</p> <p data-svelte-h="svelte-zeb7ev">Textual Inversion weights are very lightweight and typically only a few KBs because they’re only word embeddings. However, this also means the word embeddings need to be loaded after loading a model with <a href="/docs/diffusers/pr_11686/en/api/pipelines/overview#diffusers.DiffusionPipeline.from_pretrained">from_pretrained()</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 class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
pipeline = AutoPipelineForText2Image.from_pretrained(
<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>,
torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1layhnv">Load the word embeddings with <a href="/docs/diffusers/pr_11686/en/api/loaders/textual_inversion#diffusers.loaders.TextualInversionLoaderMixin.load_textual_inversion">load_textual_inversion()</a> and include the unique token in the prompt to activate its generation.</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 class=""><!-- HTML_TAG_START -->pipeline.load_textual_inversion(<span class="hljs-string">&quot;sd-concepts-library/gta5-artwork&quot;</span>)
prompt = <span class="hljs-string">&quot;A cute brown bear eating a slice of pizza, stunning color scheme, masterpiece, illustration, &lt;gta5-artwork&gt; style&quot;</span>
pipeline(prompt).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-vwb4li"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_txt_embed.png"></div> <p data-svelte-h="svelte-9fjq1k">Textual Inversion can also be trained to learn <em>negative embeddings</em> to steer generation away from unwanted characteristics such as “blurry” or “ugly”. It is useful for improving image quality.</p> <p data-svelte-h="svelte-19ybne4">EasyNegative is a widely used negative embedding that contains multiple learned negative concepts. Load the negative embeddings and specify the file name and token associated with the negative embeddings. Pass the token to <code>negative_prompt</code> in your pipeline to activate 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 class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
pipeline = AutoPipelineForText2Image.from_pretrained(
<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&quot;</span>,
torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_textual_inversion(
<span class="hljs-string">&quot;EvilEngine/easynegative&quot;</span>,
weight_name=<span class="hljs-string">&quot;easynegative.safetensors&quot;</span>,
token=<span class="hljs-string">&quot;easynegative&quot;</span>
)
prompt = <span class="hljs-string">&quot;A cute brown bear eating a slice of pizza, stunning color scheme, masterpiece, illustration&quot;</span>
negative_prompt = <span class="hljs-string">&quot;easynegative&quot;</span>
pipeline(prompt, negative_prompt).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-j6euo"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png"></div> <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/textual_inversion_inference.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
{
__sveltekit_o82a48 = {
assets: "/docs/diffusers/pr_11686/en",
base: "/docs/diffusers/pr_11686/en",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/diffusers/pr_11686/en/_app/immutable/entry/start.2b9667fb.js"),
import("/docs/diffusers/pr_11686/en/_app/immutable/entry/app.a2a6117e.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 313],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
11.5 kB
·
Xet hash:
17f44d0d2d5b3e8e2d3d1c280344fe865927e06e032010a72b4af7ea5c5e1493

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