Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Batch inference","local":"batch-inference","sections":[{"title":"Deterministic generation","local":"deterministic-generation","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/diffusers/pr_12403/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/entry/start.33959e67.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/scheduler.8c3d61f6.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/singletons.46d5608c.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/index.0997d446.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/paths.0dc9c45f.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/entry/app.87796ad1.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/index.da70eac4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/nodes/0.9198881c.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/nodes/294.9d9e6b66.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/CodeBlock.a9c4becf.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/getInferenceSnippets.ea1775db.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12403/en/_app/immutable/chunks/HfOption.6c3b4e77.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Batch inference","local":"batch-inference","sections":[{"title":"Deterministic generation","local":"deterministic-generation","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="batch-inference" 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="#batch-inference"><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>Batch inference</span></h1> <p data-svelte-h="svelte-1gcbm5z">Batch inference processes multiple prompts at a time to increase throughput. It is more efficient because processing multiple prompts at once maximizes GPU usage versus processing a single prompt and underutilizing the GPU.</p> <p data-svelte-h="svelte-19m5zxe">The downside is increased latency because you must wait for the entire batch to complete, and more GPU memory is required for large batches.</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white">text-to-image </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm">image-to-image </div></div> <div class="language-select"><p data-svelte-h="svelte-1u13a2m">For text-to-image, pass a list of prompts to the pipeline.</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">"stabilityai/stable-diffusion-xl-base-1.0"</span>, | |
| torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| prompts = [ | |
| <span class="hljs-string">"cinematic photo of A beautiful sunset over mountains, 35mm photograph, film, professional, 4k, highly detailed"</span>, | |
| <span class="hljs-string">"cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain"</span>, | |
| <span class="hljs-string">"pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics"</span> | |
| ] | |
| images = pipeline( | |
| prompt=prompts, | |
| ).images | |
| fig, axes = plt.subplots(<span class="hljs-number">2</span>, <span class="hljs-number">2</span>, figsize=(<span class="hljs-number">12</span>, <span class="hljs-number">12</span>)) | |
| axes = axes.flatten() | |
| <span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(images): | |
| axes[i].imshow(image) | |
| axes[i].set_title(<span class="hljs-string">f"Image <span class="hljs-subst">{i+<span class="hljs-number">1</span>}</span>"</span>) | |
| axes[i].axis(<span class="hljs-string">'off'</span>) | |
| plt.tight_layout() | |
| plt.show()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1wlqa91">To generate multiple variations of one prompt, use the <code>num_images_per_prompt</code> argument.</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">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt | |
| <span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline | |
| pipeline = DiffusionPipeline.from_pretrained( | |
| <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>, | |
| torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| images = pipeline( | |
| prompt=<span class="hljs-string">"pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics"</span>, | |
| num_images_per_prompt=<span class="hljs-number">4</span> | |
| ).images | |
| fig, axes = plt.subplots(<span class="hljs-number">2</span>, <span class="hljs-number">2</span>, figsize=(<span class="hljs-number">12</span>, <span class="hljs-number">12</span>)) | |
| axes = axes.flatten() | |
| <span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(images): | |
| axes[i].imshow(image) | |
| axes[i].set_title(<span class="hljs-string">f"Image <span class="hljs-subst">{i+<span class="hljs-number">1</span>}</span>"</span>) | |
| axes[i].axis(<span class="hljs-string">'off'</span>) | |
| plt.tight_layout() | |
| plt.show()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1tfp3na">Combine both approaches to generate different variations of different prompts.</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 -->images = pipeline( | |
| prompt=prompts, | |
| num_images_per_prompt=<span class="hljs-number">2</span>, | |
| ).images | |
| fig, axes = plt.subplots(<span class="hljs-number">2</span>, <span class="hljs-number">2</span>, figsize=(<span class="hljs-number">12</span>, <span class="hljs-number">12</span>)) | |
| axes = axes.flatten() | |
| <span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(images): | |
| axes[i].imshow(image) | |
| axes[i].set_title(<span class="hljs-string">f"Image <span class="hljs-subst">{i+<span class="hljs-number">1</span>}</span>"</span>) | |
| axes[i].axis(<span class="hljs-string">'off'</span>) | |
| plt.tight_layout() | |
| plt.show()<!-- HTML_TAG_END --></pre></div> </div> <h2 class="relative group"><a id="deterministic-generation" 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="#deterministic-generation"><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>Deterministic generation</span></h2> <p data-svelte-h="svelte-agd9mv">Enable reproducible batch generation by passing a list of <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow">Generator’s</a> to the pipeline and tie each <code>Generator</code> to a seed to reuse it.</p> <p data-svelte-h="svelte-1j6y6ag">Use a list comprehension to iterate over the batch size specified in <code>range()</code> to create a unique <code>Generator</code> object for each image in the batch.</p> <p data-svelte-h="svelte-vrwtho">Don’t multiply the <code>Generator</code> by the batch size because that only creates one <code>Generator</code> object that is used sequentially for each image in the batch.</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 -->generator = [torch.Generator(device=<span class="hljs-string">"cuda"</span>).manual_seed(<span class="hljs-number">0</span>)] * <span class="hljs-number">3</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-c466x0">Pass the <code>generator</code> to the pipeline.</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">"stabilityai/stable-diffusion-xl-base-1.0"</span>, | |
| torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| generator = [torch.Generator(device=<span class="hljs-string">"cuda"</span>).manual_seed(i) <span class="hljs-keyword">for</span> i <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(<span class="hljs-number">3</span>)] | |
| prompts = [ | |
| <span class="hljs-string">"cinematic photo of A beautiful sunset over mountains, 35mm photograph, film, professional, 4k, highly detailed"</span>, | |
| <span class="hljs-string">"cinematic film still of a cat basking in the sun on a roof in Turkey, highly detailed, high budget hollywood movie, cinemascope, moody, epic, gorgeous, film grain"</span>, | |
| <span class="hljs-string">"pixel-art a cozy coffee shop interior, low-res, blocky, pixel art style, 8-bit graphics"</span> | |
| ] | |
| images = pipeline( | |
| prompt=prompts, | |
| generator=generator | |
| ).images | |
| fig, axes = plt.subplots(<span class="hljs-number">2</span>, <span class="hljs-number">2</span>, figsize=(<span class="hljs-number">12</span>, <span class="hljs-number">12</span>)) | |
| axes = axes.flatten() | |
| <span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(images): | |
| axes[i].imshow(image) | |
| axes[i].set_title(<span class="hljs-string">f"Image <span class="hljs-subst">{i+<span class="hljs-number">1</span>}</span>"</span>) | |
| axes[i].axis(<span class="hljs-string">'off'</span>) | |
| plt.tight_layout() | |
| plt.show()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1njy55c">You can use this to iteratively select an image associated with a seed and then improve on it by crafting a more detailed prompt.</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/using-diffusers/batched_inference.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_g87enx = { | |
| assets: "/docs/diffusers/pr_12403/en", | |
| base: "/docs/diffusers/pr_12403/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/pr_12403/en/_app/immutable/entry/start.33959e67.js"), | |
| import("/docs/diffusers/pr_12403/en/_app/immutable/entry/app.87796ad1.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 294], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 19.5 kB
- Xet hash:
- b22a0b764f25daa9dc4acf346a472dbaf20a5c414d1ee068072faa96a79da893
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.