Buckets:

rtrm's picture
download
raw
12.2 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;AutoPipeline&quot;,&quot;local&quot;:&quot;autopipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
<link href="/docs/diffusers/pr_12279/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/entry/start.ed15a022.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/chunks/scheduler.8c3d61f6.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/chunks/singletons.fac34a67.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/chunks/index.0997d446.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/chunks/paths.b33f1b92.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/entry/app.c8a6450e.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/chunks/index.da70eac4.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/nodes/0.2b10a71c.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/nodes/288.9064f8fd.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/chunks/CodeBlock.a9c4becf.js">
<link rel="modulepreload" href="/docs/diffusers/pr_12279/en/_app/immutable/chunks/getInferenceSnippets.7d4354d6.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;AutoPipeline&quot;,&quot;local&quot;:&quot;autopipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="autopipeline" 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="#autopipeline"><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>AutoPipeline</span></h1> <p data-svelte-h="svelte-15pjr1q"><a href="../api/models/auto_model">AutoPipeline</a> is a <em>task-and-model</em> pipeline that automatically selects the correct pipeline subclass based on the task. It handles the complexity of loading different pipeline subclasses without needing to know the specific pipeline subclass name.</p> <p data-svelte-h="svelte-rw0wib">This is unlike <a href="/docs/diffusers/pr_12279/en/api/pipelines/overview#diffusers.DiffusionPipeline">DiffusionPipeline</a>, a <em>model-only</em> pipeline that automatically selects the pipeline subclass based on the model.</p> <p data-svelte-h="svelte-vsr23l"><a href="/docs/diffusers/pr_12279/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForImage2Image">AutoPipelineForImage2Image</a> returns a specific pipeline subclass, (for example, <a href="/docs/diffusers/pr_12279/en/api/pipelines/stable_diffusion/stable_diffusion_xl#diffusers.StableDiffusionXLImg2ImgPipeline">StableDiffusionXLImg2ImgPipeline</a>), which can only be used for image-to-image tasks.</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> AutoPipelineForImage2Image
pipeline = AutoPipelineForImage2Image.from_pretrained(
<span class="hljs-string">&quot;RunDiffusion/Juggernaut-XL-v9&quot;</span>, torch_dtype=torch.bfloat16, device_map=<span class="hljs-string">&quot;cuda&quot;</span>,
)
<span class="hljs-built_in">print</span>(pipeline)
<span class="hljs-string">&quot;StableDiffusionXLImg2ImgPipeline {
&quot;</span>_class_name<span class="hljs-string">&quot;: &quot;</span>StableDiffusionXLImg2ImgPipeline<span class="hljs-string">&quot;,
...
&quot;</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-swziwg">Loading the same model with <a href="/docs/diffusers/pr_12279/en/api/pipelines/overview#diffusers.DiffusionPipeline">DiffusionPipeline</a> returns the <a href="/docs/diffusers/pr_12279/en/api/pipelines/stable_diffusion/stable_diffusion_xl#diffusers.StableDiffusionXLPipeline">StableDiffusionXLPipeline</a> subclass. It can be used for text-to-image, image-to-image, or inpainting tasks depending on the inputs.</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> DiffusionPipeline
pipeline = DiffusionPipeline.from_pretrained(
<span class="hljs-string">&quot;RunDiffusion/Juggernaut-XL-v9&quot;</span>, torch_dtype=torch.bfloat16, device_map=<span class="hljs-string">&quot;cuda&quot;</span>,
)
<span class="hljs-built_in">print</span>(pipeline)
<span class="hljs-string">&quot;StableDiffusionXLPipeline {
&quot;</span>_class_name<span class="hljs-string">&quot;: &quot;</span>StableDiffusionXLPipeline<span class="hljs-string">&quot;,
...
&quot;</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1jztso9">Check the <a href="https://github.com/huggingface/diffusers/blob/130fd8df54f24ffb006d84787b598d8adc899f23/src/diffusers/pipelines/auto_pipeline.py#L114" rel="nofollow">mappings</a> to see whether a model is supported or not.</p> <p data-svelte-h="svelte-72na4b">Trying to load an unsupported model returns an error.</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> AutoPipelineForImage2Image
pipeline = AutoPipelineForImage2Image.from_pretrained(
<span class="hljs-string">&quot;openai/shap-e-img2img&quot;</span>, torch_dtype=torch.float16,
)
<span class="hljs-string">&quot;ValueError: AutoPipeline can&#x27;t find a pipeline linked to ShapEImg2ImgPipeline for None&quot;</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-qy8qsh">There are three types of <a href="../api/models/auto_model">AutoPipeline</a> classes, <a href="/docs/diffusers/pr_12279/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForText2Image">AutoPipelineForText2Image</a>, <a href="/docs/diffusers/pr_12279/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForImage2Image">AutoPipelineForImage2Image</a> and <a href="/docs/diffusers/pr_12279/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForInpainting">AutoPipelineForInpainting</a>. Each of these classes have a predefined mapping, linking a pipeline to their task-specific subclass.</p> <p data-svelte-h="svelte-2yc98p">When <a href="/docs/diffusers/pr_12279/en/api/pipelines/auto_pipeline#diffusers.AutoPipelineForText2Image.from_pretrained">from_pretrained()</a> is called, it extracts the class name from the <code>model_index.json</code> file and selects the appropriate pipeline subclass for the task based on the mapping.</p> <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/tutorials/autopipeline.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_yj4xmk = {
assets: "/docs/diffusers/pr_12279/en",
base: "/docs/diffusers/pr_12279/en",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/diffusers/pr_12279/en/_app/immutable/entry/start.ed15a022.js"),
import("/docs/diffusers/pr_12279/en/_app/immutable/entry/app.c8a6450e.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 288],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
12.2 kB
·
Xet hash:
13ad28c57a6aac4328dd69c934867019fd1b2e78fe8c23d431b4ce70004d06f7

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