Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Load adapters","local":"load-adapters","sections":[{"title":"LoRA","local":"lora","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/optimum.neuron/pr_1097/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/entry/start.82e2ff17.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/scheduler.56725da7.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/singletons.2080b4fc.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/paths.90dabf70.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/entry/app.9b0c0103.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/preload-helper.9dba61fb.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/index.18a26576.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/nodes/0.912aab06.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/nodes/30.7ddb578b.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/CopyLLMTxtMenu.fb3856d8.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.a16844e0.js"> | |
| <link rel="modulepreload" href="/docs/optimum.neuron/pr_1097/en/_app/immutable/chunks/CodeBlock.2d00672f.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Load adapters","local":"load-adapters","sections":[{"title":"LoRA","local":"lora","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" 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></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="load-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="#load-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>Load adapters</span></h1> <p data-svelte-h="svelte-1p7c5ip">There are several training techniques for personalizing diffusion models to generate images of a specific subject or images in certain styles. Each of these training methods produces a different type of adapter. Some of the adapters generate an entirely new model, while other adapters only modify a smaller set of embeddings or weights. This means the loading process for each adapter is also different.</p> <p data-svelte-h="svelte-3y0v6y">This guide will show you how to load LoRA weights.</p> <h2 class="relative group"><a id="lora" 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="#lora"><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>LoRA</span></h2> <p data-svelte-h="svelte-w90myx">Low-Rank Adaptation is the fastest way for Stable Diffusion to adapt the styles of the generated images. In Optimum Neuron, we support using one or multiple LoRA adapters by fusing their parameters into the original parameters of the text encoder(s) and the unet during the compilation. Here below is an example of compiling stable diffusion models with LoRA adapters of your choice and using the compiled artifacts to generate styled images:</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> LCMScheduler | |
| <span class="hljs-keyword">from</span> optimum.neuron <span class="hljs-keyword">import</span> NeuronStableDiffusionPipeline | |
| model_id = <span class="hljs-string">"Lykon/dreamshaper-7"</span> | |
| adapter_id = <span class="hljs-string">"latent-consistency/lcm-lora-sdv1-5"</span> | |
| input_shapes = {<span class="hljs-string">"batch_size"</span>: <span class="hljs-number">1</span>, <span class="hljs-string">"height"</span>: <span class="hljs-number">512</span>, <span class="hljs-string">"width"</span>: <span class="hljs-number">512</span>, <span class="hljs-string">"num_images_per_prompt"</span>: <span class="hljs-number">1</span>} | |
| compiler_args = {<span class="hljs-string">"auto_cast"</span>: <span class="hljs-string">"matmul"</span>, <span class="hljs-string">"auto_cast_type"</span>: <span class="hljs-string">"bf16"</span>} | |
| <span class="hljs-comment"># Compile</span> | |
| pipe = NeuronStableDiffusionPipeline.from_pretrained( | |
| model_id, | |
| export=<span class="hljs-literal">True</span>, | |
| inline_weights_to_neff=<span class="hljs-literal">True</span>, <span class="hljs-comment"># caveat: performance drop if neff/weights separated, will be improved by a future Neuron sdk release.</span> | |
| lora_model_ids=adapter_id, | |
| lora_weight_names=<span class="hljs-string">"pytorch_lora_weights.safetensors"</span>, | |
| lora_adapter_names=<span class="hljs-string">"lcm"</span>, | |
| **input_shapes, | |
| **compiler_args, | |
| ) | |
| pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config) | |
| <span class="hljs-comment"># Save locally or upload to the HuggingFace Hub</span> | |
| pipe.save_pretrained(<span class="hljs-string">"dreamshaper_7_lcm_lora_neuron/"</span>) | |
| <span class="hljs-comment"># Inference</span> | |
| prompt = <span class="hljs-string">"Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"</span> | |
| image = pipe(prompt, num_inference_steps=<span class="hljs-number">4</span>, guidance_scale=<span class="hljs-number">0</span>).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <img src="https://raw.githubusercontent.com/huggingface/optimum-neuron/main/docs/assets/guides/models/03-sd-lora.png" width="256" height="256" alt="stable diffusion generated image with LoRA adapter."> <p data-svelte-h="svelte-1wos5lv">Are there any other diffusion features that you want us to support in 🤗<code>Optimum-neuron</code>? Please file an issue to <a href="https://github.com/huggingface/optimum-neuron" rel="nofollow"><code>Optimum-neuron</code> Github repo</a> or discuss with us on <a href="https://discuss.huggingface.co/c/optimum/" rel="nofollow">HuggingFace’s community forum</a>, cheers 🤗 !</p> <p></p> | |
| <script> | |
| { | |
| __sveltekit_19pvy0q = { | |
| assets: "/docs/optimum.neuron/pr_1097/en", | |
| base: "/docs/optimum.neuron/pr_1097/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/optimum.neuron/pr_1097/en/_app/immutable/entry/start.82e2ff17.js"), | |
| import("/docs/optimum.neuron/pr_1097/en/_app/immutable/entry/app.9b0c0103.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 30], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 12.1 kB
- Xet hash:
- cb599bc9b57503d7ca827a238b6388aafd5c1dad3255bc99aac9a8d43fe52c5d
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.