Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Load LoRAs for inference","local":"load-loras-for-inference","sections":[{"title":"Merge adapters","local":"merge-adapters","sections":[{"title":"Customize adapters strength","local":"customize-adapters-strength","sections":[],"depth":3}],"depth":2},{"title":"Manage active adapters","local":"manage-active-adapters","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/entry/start.21e27d66.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/scheduler.8c3d61f6.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/singletons.1db06f6d.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.0997d446.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/paths.085e8bc8.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/entry/app.de4fb612.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.da70eac4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/nodes/0.f6117ae5.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/nodes/204.9e63732b.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/Tip.1d9b8c37.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/CodeBlock.00a903b3.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/DocNotebookDropdown.02900f6b.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/EditOnGithub.1e64e623.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Load LoRAs for inference","local":"load-loras-for-inference","sections":[{"title":"Merge adapters","local":"merge-adapters","sections":[{"title":"Customize adapters strength","local":"customize-adapters-strength","sections":[],"depth":3}],"depth":2},{"title":"Manage active adapters","local":"manage-active-adapters","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <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> <h1 class="relative group"><a id="load-loras-for-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="#load-loras-for-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>Load LoRAs for inference</span></h1> <p data-svelte-h="svelte-16bta26">There are many adapter types (with <a href="https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora" rel="nofollow">LoRAs</a> being the most popular) trained in different styles to achieve different effects. You can even combine multiple adapters to create new and unique images.</p> <p data-svelte-h="svelte-1ieiu2">In this tutorial, you’ll learn how to easily load and manage adapters for inference with the 🤗 <a href="https://huggingface.co/docs/peft/index" rel="nofollow">PEFT</a> integration in 🤗 Diffusers. You’ll use LoRA as the main adapter technique, so you’ll see the terms LoRA and adapter used interchangeably.</p> <p data-svelte-h="svelte-k7bd5g">Let’s first install all the required libraries.</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 -->!pip install -q transformers accelerate peft diffusers<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1tmqr11">Now, load a pipeline with a <a href="../api/pipelines/stable_diffusion/stable_diffusion_xl">Stable Diffusion XL (SDXL)</a> checkpoint:</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">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline | |
| <span class="hljs-keyword">import</span> torch | |
| pipe_id = <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span> | |
| pipe = DiffusionPipeline.from_pretrained(pipe_id, torch_dtype=torch.float16).to(<span class="hljs-string">"cuda"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-y3qsvz">Next, load a <a href="https://huggingface.co/CiroN2022/toy-face" rel="nofollow">CiroN2022/toy-face</a> adapter with the <a href="/docs/diffusers/main/en/api/loaders/lora#diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights">load_lora_weights()</a> method. With the 🤗 PEFT integration, you can assign a specific <code>adapter_name</code> to the checkpoint, which lets you easily switch between different LoRA checkpoints. Let’s call this adapter <code>"toy"</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 class=""><!-- HTML_TAG_START -->pipe.load_lora_weights(<span class="hljs-string">"CiroN2022/toy-face"</span>, weight_name=<span class="hljs-string">"toy_face_sdxl.safetensors"</span>, adapter_name=<span class="hljs-string">"toy"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-edxce6">Make sure to include the token <code>toy_face</code> in the prompt and then you can perform inference:</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 -->prompt = <span class="hljs-string">"toy_face of a hacker with a hoodie"</span> | |
| lora_scale = <span class="hljs-number">0.9</span> | |
| image = pipe( | |
| prompt, num_inference_steps=<span class="hljs-number">30</span>, cross_attention_kwargs={<span class="hljs-string">"scale"</span>: lora_scale}, generator=torch.manual_seed(<span class="hljs-number">0</span>) | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-pa1jxn"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_8_1.png" alt="toy-face"></p> <p data-svelte-h="svelte-yg68i8">With the <code>adapter_name</code> parameter, it is really easy to use another adapter for inference! Load the <a href="https://huggingface.co/nerijs/pixel-art-xl" rel="nofollow">nerijs/pixel-art-xl</a> adapter that has been fine-tuned to generate pixel art images and call it <code>"pixel"</code>.</p> <p data-svelte-h="svelte-tv28ux">The pipeline automatically sets the first loaded adapter (<code>"toy"</code>) as the active adapter, but you can activate the <code>"pixel"</code> adapter with the <code>~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters</code> method:</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 -->pipe.load_lora_weights(<span class="hljs-string">"nerijs/pixel-art-xl"</span>, weight_name=<span class="hljs-string">"pixel-art-xl.safetensors"</span>, adapter_name=<span class="hljs-string">"pixel"</span>) | |
| pipe.set_adapters(<span class="hljs-string">"pixel"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ardgqv">Make sure you include the token <code>pixel art</code> in your prompt to generate a pixel art image:</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 -->prompt = <span class="hljs-string">"a hacker with a hoodie, pixel art"</span> | |
| image = pipe( | |
| prompt, num_inference_steps=<span class="hljs-number">30</span>, cross_attention_kwargs={<span class="hljs-string">"scale"</span>: lora_scale}, generator=torch.manual_seed(<span class="hljs-number">0</span>) | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ixqz7s"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_12_1.png" alt="pixel-art"></p> <h2 class="relative group"><a id="merge-adapters" 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="#merge-adapters"><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>Merge adapters</span></h2> <p data-svelte-h="svelte-upv9sj">You can also merge different adapter checkpoints for inference to blend their styles together.</p> <p data-svelte-h="svelte-1jfd4f2">Once again, use the <code>~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters</code> method to activate the <code>pixel</code> and <code>toy</code> adapters and specify the weights for how they should be merged.</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 -->pipe.set_adapters([<span class="hljs-string">"pixel"</span>, <span class="hljs-string">"toy"</span>], adapter_weights=[<span class="hljs-number">0.5</span>, <span class="hljs-number">1.0</span>])<!-- HTML_TAG_END --></pre></div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1efkoll">LoRA checkpoints in the diffusion community are almost always obtained with <a href="https://huggingface.co/docs/diffusers/main/en/training/dreambooth" rel="nofollow">DreamBooth</a>. DreamBooth training often relies on “trigger” words in the input text prompts in order for the generation results to look as expected. When you combine multiple LoRA checkpoints, it’s important to ensure the trigger words for the corresponding LoRA checkpoints are present in the input text prompts.</p></div> <p data-svelte-h="svelte-1rn1ec0">Remember to use the trigger words for <a href="https://hf.co/CiroN2022/toy-face" rel="nofollow">CiroN2022/toy-face</a> and <a href="https://hf.co/nerijs/pixel-art-xl" rel="nofollow">nerijs/pixel-art-xl</a> (these are found in their repositories) in the prompt to generate an image.</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 -->prompt = <span class="hljs-string">"toy_face of a hacker with a hoodie, pixel art"</span> | |
| image = pipe( | |
| prompt, num_inference_steps=<span class="hljs-number">30</span>, cross_attention_kwargs={<span class="hljs-string">"scale"</span>: <span class="hljs-number">1.0</span>}, generator=torch.manual_seed(<span class="hljs-number">0</span>) | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-azw8sd"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_16_1.png" alt="toy-face-pixel-art"></p> <p data-svelte-h="svelte-1vwq5xu">Impressive! As you can see, the model generated an image that mixed the characteristics of both adapters.</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-11f9n2w">Through its PEFT integration, Diffusers also offers more efficient merging methods which you can learn about in the <a href="../using-diffusers/merge_loras">Merge LoRAs</a> guide!</p></div> <p data-svelte-h="svelte-sa6xd8">To return to only using one adapter, use the <code>~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters</code> method to activate the <code>"toy"</code> adapter:</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 -->pipe.set_adapters(<span class="hljs-string">"toy"</span>) | |
| prompt = <span class="hljs-string">"toy_face of a hacker with a hoodie"</span> | |
| lora_scale = <span class="hljs-number">0.9</span> | |
| image = pipe( | |
| prompt, num_inference_steps=<span class="hljs-number">30</span>, cross_attention_kwargs={<span class="hljs-string">"scale"</span>: lora_scale}, generator=torch.manual_seed(<span class="hljs-number">0</span>) | |
| ).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-13ixjsp">Or to disable all adapters entirely, use the <code>~diffusers.loaders.UNet2DConditionLoadersMixin.disable_lora</code> method to return the base 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 class=""><!-- HTML_TAG_START -->pipe.disable_lora() | |
| prompt = <span class="hljs-string">"toy_face of a hacker with a hoodie"</span> | |
| image = pipe(prompt, num_inference_steps=<span class="hljs-number">30</span>, generator=torch.manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-if1nej"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_20_1.png" alt="no-lora"></p> <h3 class="relative group"><a id="customize-adapters-strength" 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="#customize-adapters-strength"><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>Customize adapters strength</span></h3> <p data-svelte-h="svelte-1fwkvtc">For even more customization, you can control how strongly the adapter affects each part of the pipeline. For this, pass a dictionary with the control strengths (called “scales”) to <code>~diffusers.loaders.UNet2DConditionLoadersMixin.set_adapters</code>.</p> <p data-svelte-h="svelte-1np0ppf">For example, here’s how you can turn on the adapter for the <code>down</code> parts, but turn it off for the <code>mid</code> and <code>up</code> parts:</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 -->pipe.enable_lora() <span class="hljs-comment"># enable lora again, after we disabled it above</span> | |
| prompt = <span class="hljs-string">"toy_face of a hacker with a hoodie, pixel art"</span> | |
| adapter_weight_scales = { <span class="hljs-string">"unet"</span>: { <span class="hljs-string">"down"</span>: <span class="hljs-number">1</span>, <span class="hljs-string">"mid"</span>: <span class="hljs-number">0</span>, <span class="hljs-string">"up"</span>: <span class="hljs-number">0</span>} } | |
| pipe.set_adapters(<span class="hljs-string">"pixel"</span>, adapter_weight_scales) | |
| image = pipe(prompt, num_inference_steps=<span class="hljs-number">30</span>, generator=torch.manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-124uws4"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_down.png" alt="block-lora-text-and-down"></p> <p data-svelte-h="svelte-er7or2">Let’s see how turning off the <code>down</code> part and turning on the <code>mid</code> and <code>up</code> part respectively changes the image.</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 -->adapter_weight_scales = { <span class="hljs-string">"unet"</span>: { <span class="hljs-string">"down"</span>: <span class="hljs-number">0</span>, <span class="hljs-string">"mid"</span>: <span class="hljs-number">1</span>, <span class="hljs-string">"up"</span>: <span class="hljs-number">0</span>} } | |
| pipe.set_adapters(<span class="hljs-string">"pixel"</span>, adapter_weight_scales) | |
| image = pipe(prompt, num_inference_steps=<span class="hljs-number">30</span>, generator=torch.manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-2dcllg"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_mid.png" alt="block-lora-text-and-mid"></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 -->adapter_weight_scales = { <span class="hljs-string">"unet"</span>: { <span class="hljs-string">"down"</span>: <span class="hljs-number">0</span>, <span class="hljs-string">"mid"</span>: <span class="hljs-number">0</span>, <span class="hljs-string">"up"</span>: <span class="hljs-number">1</span>} } | |
| pipe.set_adapters(<span class="hljs-string">"pixel"</span>, adapter_weight_scales) | |
| image = pipe(prompt, num_inference_steps=<span class="hljs-number">30</span>, generator=torch.manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1fp87nu"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_up.png" alt="block-lora-text-and-up"></p> <p data-svelte-h="svelte-1319h4o">Looks cool!</p> <p data-svelte-h="svelte-1uxos2u">This is a really powerful feature. You can use it to control the adapter strengths down to per-transformer level. And you can even use it for multiple adapters.</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 -->adapter_weight_scales_toy = <span class="hljs-number">0.5</span> | |
| adapter_weight_scales_pixel = { | |
| <span class="hljs-string">"unet"</span>: { | |
| <span class="hljs-string">"down"</span>: <span class="hljs-number">0.9</span>, <span class="hljs-comment"># all transformers in the down-part will use scale 0.9</span> | |
| <span class="hljs-comment"># "mid" # because, in this example, "mid" is not given, all transformers in the mid part will use the default scale 1.0</span> | |
| <span class="hljs-string">"up"</span>: { | |
| <span class="hljs-string">"block_0"</span>: <span class="hljs-number">0.6</span>, <span class="hljs-comment"># all 3 transformers in the 0th block in the up-part will use scale 0.6</span> | |
| <span class="hljs-string">"block_1"</span>: [<span class="hljs-number">0.4</span>, <span class="hljs-number">0.8</span>, <span class="hljs-number">1.0</span>], <span class="hljs-comment"># the 3 transformers in the 1st block in the up-part will use scales 0.4, 0.8 and 1.0 respectively</span> | |
| } | |
| } | |
| } | |
| pipe.set_adapters([<span class="hljs-string">"toy"</span>, <span class="hljs-string">"pixel"</span>], [adapter_weight_scales_toy, adapter_weight_scales_pixel]) | |
| image = pipe(prompt, num_inference_steps=<span class="hljs-number">30</span>, generator=torch.manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>] | |
| image<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-16fuaxk"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/peft_integration/diffusers_peft_lora_inference_block_mixed.png" alt="block-lora-mixed"></p> <h2 class="relative group"><a id="manage-active-adapters" 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="#manage-active-adapters"><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>Manage active adapters</span></h2> <p data-svelte-h="svelte-vav6dv">You have attached multiple adapters in this tutorial, and if you’re feeling a bit lost on what adapters have been attached to the pipeline’s components, use the <a href="/docs/diffusers/main/en/api/loaders/lora#diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters">get_active_adapters()</a> method to check the list of active adapters:</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 -->active_adapters = pipe.get_active_adapters() | |
| active_adapters | |
| [<span class="hljs-string">"toy"</span>, <span class="hljs-string">"pixel"</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-iw3cil">You can also get the active adapters of each pipeline component with <a href="/docs/diffusers/main/en/api/loaders/lora#diffusers.loaders.lora_base.LoraBaseMixin.get_list_adapters">get_list_adapters()</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 -->list_adapters_component_wise = pipe.get_list_adapters() | |
| list_adapters_component_wise | |
| {<span class="hljs-string">"text_encoder"</span>: [<span class="hljs-string">"toy"</span>, <span class="hljs-string">"pixel"</span>], <span class="hljs-string">"unet"</span>: [<span class="hljs-string">"toy"</span>, <span class="hljs-string">"pixel"</span>], <span class="hljs-string">"text_encoder_2"</span>: [<span class="hljs-string">"toy"</span>, <span class="hljs-string">"pixel"</span>]}<!-- HTML_TAG_END --></pre></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/tutorials/using_peft_for_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_1eu7tzz = { | |
| assets: "/docs/diffusers/main/en", | |
| base: "/docs/diffusers/main/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/main/en/_app/immutable/entry/start.21e27d66.js"), | |
| import("/docs/diffusers/main/en/_app/immutable/entry/app.de4fb612.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 204], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 44.3 kB
- Xet hash:
- dbcca9a30cb6b042e58f30357ed464cb5458d334c90a6305b6b878a7eba9f2e0
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.