Buckets:
| <meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{"local":"bentoml-integration-guide","sections":[{"local":"prerequisites","title":"Prerequisites"},{"local":"import-a-diffusion-model","title":"Import a diffusion model"},{"local":"turn-a-diffusion-model-into-a-restful-service-with-bentoml","title":"Turn a diffusion model into a RESTful service with BentoML"},{"local":"package-a-bentoml-service-for-cloud-deployment","title":"Package a BentoML Service for cloud deployment"}],"title":"BentoML Integration Guide"}" data-svelte="svelte-1phssyn"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/start-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/vendor-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/paths-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/pages/__layout.svelte-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/pages/optimization/bentoml.mdx-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/IconCopyLink-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/CodeBlock-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/chunks/DocNotebookDropdown-hf-doc-builder.js"> | |
| <h1 class="relative group"><a id="bentoml-integration-guide" 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="#bentoml-integration-guide"><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>BentoML Integration Guide | |
| </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><a href="https://github.com/bentoml/BentoML/" rel="nofollow">BentoML</a> is an open-source framework designed for building, | |
| shipping, and scaling AI applications. It allows users to easily package and serve diffusion models | |
| for production, ensuring reliable and efficient deployments. It features out-of-the-box operational | |
| management tools like monitoring and tracing, and facilitates the deployment to various cloud platforms | |
| with ease. BentoML’s distributed architecture and the separation of API server logic from | |
| model inference logic enable efficient scaling of deployments, even with budget constraints. | |
| As a result, integrating it with Diffusers provides a valuable tool for real-world deployments.</p> | |
| <p>This tutorial demonstrates how to integrate BentoML with Diffusers.</p> | |
| <h2 class="relative group"><a id="prerequisites" 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="#prerequisites"><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>Prerequisites | |
| </span></h2> | |
| <ul><li>Install <a href="https://huggingface.co/docs/diffusers/installation" rel="nofollow">Diffusers</a>.</li> | |
| <li>Install BentoML by running <code>pip install bentoml</code>. For more information, see the <a href="https://docs.bentoml.com" rel="nofollow">BentoML documentation</a>.</li></ul> | |
| <h2 class="relative group"><a id="import-a-diffusion-model" 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="#import-a-diffusion-model"><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>Import a diffusion model | |
| </span></h2> | |
| <p>First, you need to prepare the model. BentoML has its own <a href="https://docs.bentoml.com/en/latest/concepts/model.html" rel="nofollow">Model Store</a> | |
| for model management. Create a <code>download_model.py</code> file as below to import a diffusion model into BentoML’s Model | |
| Store:</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> bentoml | |
| bentoml.diffusers.import_model( | |
| <span class="hljs-string">"sd2.1"</span>, <span class="hljs-comment"># Model tag in the BentoML Model Store</span> | |
| <span class="hljs-string">"stabilityai/stable-diffusion-2-1"</span>, <span class="hljs-comment"># Hugging Face model identifier</span> | |
| )<!-- HTML_TAG_END --></pre></div> | |
| <p>This code snippet downloads the Stable Diffusion 2.1 model (using it’s repo id | |
| <code>stabilityai/stable-diffusion-2-1</code>) from the Hugging Face Hub (or use the cached download | |
| files if the model is already downloaded) and imports it into the BentoML Model | |
| Store with the name <code>sd2.1</code>.</p> | |
| <p>For models already fine-tuned and stored on disk, you can provide the path instead of | |
| the repo id.</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> bentoml | |
| bentoml.diffusers.import_model( | |
| <span class="hljs-string">"sd2.1-local"</span>, | |
| <span class="hljs-string">"./local_stable_diffusion_2.1/"</span>, | |
| )<!-- HTML_TAG_END --></pre></div> | |
| <p>You can view the model in the Model Store:</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-attribute">bentoml</span> models list | |
| <span class="hljs-attribute">Tag</span> Module Size Creation Time | |
| <span class="hljs-attribute">sd2</span>.<span class="hljs-number">1</span>:ysrlmubascajwnry bentoml.diffusers <span class="hljs-number">33</span>.<span class="hljs-number">85</span> GiB <span class="hljs-number">2023</span>-<span class="hljs-number">07</span>-<span class="hljs-number">12</span> <span class="hljs-number">16</span>:<span class="hljs-number">47</span>:<span class="hljs-number">44</span> <!-- HTML_TAG_END --></pre></div> | |
| <h2 class="relative group"><a id="turn-a-diffusion-model-into-a-restful-service-with-bentoml" 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="#turn-a-diffusion-model-into-a-restful-service-with-bentoml"><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>Turn a diffusion model into a RESTful service with BentoML | |
| </span></h2> | |
| <p>Once the diffusion model is in BentoML’s Model Store, you can implement a text-to-image | |
| service with it. The Stable Diffusion model accepts various arguments | |
| in addition to the required prompt to guide the image generation process. | |
| To validate these input arguments, use BentoML’s <a href="https://github.com/pydantic/pydantic" rel="nofollow">pydantic</a> integration. | |
| Create a <code>sdargs.py</code> file with an example pydantic 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 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> typing <span class="hljs-keyword">as</span> t | |
| <span class="hljs-keyword">from</span> pydantic <span class="hljs-keyword">import</span> BaseModel | |
| <span class="hljs-keyword">class</span> <span class="hljs-title class_">SDArgs</span>(<span class="hljs-title class_ inherited__">BaseModel</span>): | |
| prompt: <span class="hljs-built_in">str</span> | |
| negative_prompt: t.<span class="hljs-type">Optional</span>[<span class="hljs-built_in">str</span>] = <span class="hljs-literal">None</span> | |
| height: t.<span class="hljs-type">Optional</span>[<span class="hljs-built_in">int</span>] = <span class="hljs-number">512</span> | |
| width: t.<span class="hljs-type">Optional</span>[<span class="hljs-built_in">int</span>] = <span class="hljs-number">512</span> | |
| <span class="hljs-keyword">class</span> <span class="hljs-title class_">Config</span>: | |
| extra = <span class="hljs-string">"allow"</span><!-- HTML_TAG_END --></pre></div> | |
| <p>This pydantic model requires a string field <code>prompt</code> and three optional fields: <code>height</code>, <code>width</code>, and <code>negative_prompt</code>, | |
| each with corresponding types. The <code>extra = "allow"</code> line supports adding additional fields not defined in the <code>SDArgs</code> class. | |
| In a real-world scenario, you may define all the desired fields and not allow extra ones.</p> | |
| <p>Next, create a BentoML Service file that defines a Stable Diffusion service:</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> bentoml | |
| <span class="hljs-keyword">from</span> bentoml.io <span class="hljs-keyword">import</span> Image, JSON | |
| <span class="hljs-keyword">from</span> sdargs <span class="hljs-keyword">import</span> SDArgs | |
| bento_model = bentoml.diffusers.get(<span class="hljs-string">"sd2.1:latest"</span>) | |
| sd21_runner = bento_model.to_runner(name=<span class="hljs-string">"sd21-runner"</span>) | |
| svc = bentoml.Service(<span class="hljs-string">"stable-diffusion-21"</span>, runners=[sd21_runner]) | |
| <span class="hljs-meta">@svc.api(<span class="hljs-params"><span class="hljs-built_in">input</span>=JSON(<span class="hljs-params">pydantic_model=SDArgs</span>), output=Image(<span class="hljs-params"></span>)</span>)</span> | |
| <span class="hljs-keyword">async</span> <span class="hljs-keyword">def</span> <span class="hljs-title function_">txt2img</span>(<span class="hljs-params">input_data</span>): | |
| kwargs = input_data.<span class="hljs-built_in">dict</span>() | |
| res = <span class="hljs-keyword">await</span> sd21_runner.async_run(**kwargs) | |
| images = res[<span class="hljs-number">0</span>] | |
| <span class="hljs-keyword">return</span> images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> | |
| <p>Save the file as <code>service.py</code>, and spin up a BentoML Service endpoint using:</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">bentoml </span>serve service:svc<!-- HTML_TAG_END --></pre></div> | |
| <p>An HTTP server with <code>/txt2img</code> endpoint that accepts a JSON dictionary should be up at | |
| port 3000. Go to <<a href="http://127.0.0.1:3000%3E" rel="nofollow">http://127.0.0.1:3000></a> in your web browser to access the Swagger UI.</p> | |
| <p>You can also test the text-to-image generation using <code>curl</code> and write the returned image to | |
| <code>output.jpg</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 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 -->curl <span class="hljs-operator">-</span><span class="hljs-type">X</span> <span class="hljs-type">POST</span> http:<span class="hljs-comment">//127.0.0.1:3000/txt2img \</span> | |
| <span class="hljs-operator">-</span><span class="hljs-type">H</span> '<span class="hljs-type">Content</span><span class="hljs-operator">-</span><span class="hljs-type">Type</span>: application<span class="hljs-operator">/</span>json' \ | |
| <span class="hljs-operator">-</span>d <span class="hljs-string">"{<span class="hljs-subst">\"</span>prompt<span class="hljs-subst">\"</span>:<span class="hljs-subst">\"</span>a black cat<span class="hljs-subst">\"</span>, <span class="hljs-subst">\"</span>height<span class="hljs-subst">\"</span>:768, <span class="hljs-subst">\"</span>width<span class="hljs-subst">\"</span>:768}"</span> \ | |
| <span class="hljs-operator">--</span>output output.jpg<!-- HTML_TAG_END --></pre></div> | |
| <h2 class="relative group"><a id="package-a-bentoml-service-for-cloud-deployment" 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="#package-a-bentoml-service-for-cloud-deployment"><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>Package a BentoML Service for cloud deployment | |
| </span></h2> | |
| <p>To deploy a BentoML Service, you need to pack it into a BentoML | |
| <a href="https://docs.bentoml.com/en/latest/concepts/bento.html" rel="nofollow">Bento</a>, a file archive with all the source code, | |
| models, data files, and dependencies. This can be done by providing a <code>bentofile.yaml</code> file as follows:</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-attr">service:</span> <span class="hljs-string">"service.py:svc"</span> | |
| <span class="hljs-attr">include:</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-string">"service.py"</span> | |
| <span class="hljs-attr">python:</span> | |
| <span class="hljs-attr">packages:</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-string">torch</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-string">transformers</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-string">accelerate</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-string">diffusers</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-string">triton</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-string">xformers</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-string">pydantic</span> | |
| <span class="hljs-attr">docker:</span> | |
| <span class="hljs-attr">distro:</span> <span class="hljs-string">debian</span> | |
| <span class="hljs-attr">cuda_version:</span> <span class="hljs-string">"11.6"</span><!-- HTML_TAG_END --></pre></div> | |
| <p>The <code>bentofile.yaml</code> file contains <a href="https://docs.bentoml.com/en/latest/concepts/bento.html#bento-build-options" rel="nofollow">Bento build | |
| options</a>, | |
| such as package dependencies and Docker options.</p> | |
| <p>Then you build a Bento using:</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-attribute">bentoml build</span><!-- HTML_TAG_END --></pre></div> | |
| <p>The output looks like:</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 -->Successfully <span class="hljs-keyword">built </span><span class="hljs-keyword">Bento(tag="stable-diffusion-21:crkuh7a7rw5bcasc"). | |
| </span> | |
| Possible next steps: | |
| * Containerize your <span class="hljs-keyword">Bento </span>with `<span class="hljs-keyword">bentoml </span>containerize`: | |
| $ <span class="hljs-keyword">bentoml </span>containerize stable-<span class="hljs-keyword">diffusion-21:crkuh7a7rw5bcasc | |
| </span> | |
| * Push to <span class="hljs-keyword">BentoCloud </span>with `<span class="hljs-keyword">bentoml </span>push`: | |
| $ <span class="hljs-keyword">bentoml </span>push stable-<span class="hljs-keyword">diffusion-21:crkuh7a7rw5bcasc</span><!-- HTML_TAG_END --></pre></div> | |
| <p>You can create a Docker image based on the Bento by running the following command and deploy it to a cloud provider.</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-attribute">bentoml</span> containerize stable-diffusion-<span class="hljs-number">21</span>:crkuh7a7rw5bcasc<!-- HTML_TAG_END --></pre></div> | |
| <p>If you want an end-to-end solution for deploying and managing models, you can push the Bento to <a href="https://github.com/bentoml/Yatai" rel="nofollow">Yatai</a> or | |
| <a href="https://bentoml.com/cloud" rel="nofollow">BentoCloud</a> for a distributed deployment.</p> | |
| <p>For more information about BentoML’s integration with Diffusers, see the <a href="https://docs.bentoml.com/en/latest/frameworks/diffusers.html" rel="nofollow">BentoML Diffusers | |
| Guide</a>.</p> | |
| <script type="module" data-hydrate="u9oox0"> | |
| import { start } from "/docs/diffusers/main/en/_app/start-hf-doc-builder.js"; | |
| start({ | |
| target: document.querySelector('[data-hydrate="u9oox0"]').parentNode, | |
| paths: {"base":"/docs/diffusers/main/en","assets":"/docs/diffusers/main/en"}, | |
| session: {}, | |
| route: false, | |
| spa: false, | |
| trailing_slash: "never", | |
| hydrate: { | |
| status: 200, | |
| error: null, | |
| nodes: [ | |
| import("/docs/diffusers/main/en/_app/pages/__layout.svelte-hf-doc-builder.js"), | |
| import("/docs/diffusers/main/en/_app/pages/optimization/bentoml.mdx-hf-doc-builder.js") | |
| ], | |
| params: {} | |
| } | |
| }); | |
| </script> | |
Xet Storage Details
- Size:
- 32.9 kB
- Xet hash:
- fb4fa4d0a7c718ef33d3fa4672cf7d3c6534df824532152154a1e7396ccf436d
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.