Buckets:

hf-doc-build
/

doc

Files

xet

hf-doc-build/doc / diffusers /main /en /using-diffusers /lcm.html

rtrm

17 days ago

download

raw

24.1 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Performing inference with LCM","local":"performing-inference-with-lcm","sections":[{"title":"Text-to-image","local":"text-to-image","sections":[],"depth":2},{"title":"Image-to-image","local":"image-to-image","sections":[],"depth":2},{"title":"LoRA","local":"lora","sections":[{"title":"Text-to-image","local":"text-to-image","sections":[],"depth":3},{"title":"Image-to-image","local":"image-to-image","sections":[],"depth":3}],"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.0fc360d2.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/scheduler.182ea377.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/singletons.f91ab6fa.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/paths.817c3ef4.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/entry/app.aa1da0ff.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.1ea56653.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/nodes/0.539cdc53.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/171.3e9a24e4.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/Heading.660e5dfb.js">
	<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/CodeBlock.82c2494b.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Performing inference with LCM","local":"performing-inference-with-lcm","sections":[{"title":"Text-to-image","local":"text-to-image","sections":[],"depth":2},{"title":"Image-to-image","local":"image-to-image","sections":[],"depth":2},{"title":"LoRA","local":"lora","sections":[{"title":"Text-to-image","local":"text-to-image","sections":[],"depth":3},{"title":"Image-to-image","local":"image-to-image","sections":[],"depth":3}],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="performing-inference-with-lcm" 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="#performing-inference-with-lcm"><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>Performing inference with LCM</span></h1> <p data-svelte-h="svelte-z8g6w0">Latent Consistency Models (LCM) enable quality image generation in typically 2-4 steps making it possible to use diffusion models in almost real-time settings.</p> <p data-svelte-h="svelte-d9zkw1">From the <a href="https://latent-consistency-models.github.io/" rel="nofollow">official website</a>:</p> <blockquote data-svelte-h="svelte-9ngsrn"><p>LCMs can be distilled from any pre-trained Stable Diffusion (SD) in only 4,000 training steps (~32 A100 GPU Hours) for generating high quality 768 x 768 resolution images in 2~4 steps or even one step, significantly accelerating text-to-image generation. We employ LCM to distill the Dreamshaper-V7 version of SD in just 4,000 training iterations.</p></blockquote> <p data-svelte-h="svelte-yzou0e">For a more technical overview of LCMs, refer to <a href="https://huggingface.co/papers/2310.04378" rel="nofollow">the paper</a>.</p> <p data-svelte-h="svelte-f8mmps">This guide shows how to perform inference with LCMs for text-to-image and image-to-image generation tasks. It will also cover performing inference with LoRA checkpoints.</p> <h2 class="relative group"><a id="text-to-image" 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="#text-to-image"><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>Text-to-image</span></h2> <p data-svelte-h="svelte-1hzha47">You’ll use the <a href="/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_xl#diffusers.StableDiffusionXLPipeline">StableDiffusionXLPipeline</a> here changing the <code>unet</code>. The UNet was distilled from the SDXL UNet using the framework introduced in LCM. Another important component is the scheduler: <a href="/docs/diffusers/main/en/api/schedulers/lcm#diffusers.LCMScheduler">LCMScheduler</a>. Together with the distilled UNet and the scheduler, LCM enables a fast inference workflow overcoming the slow iterative nature of diffusion models.</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, UNet2DConditionModel, LCMScheduler
	<span class="hljs-keyword">import</span> torch

	unet = UNet2DConditionModel.from_pretrained(
	<span class="hljs-string">"latent-consistency/lcm-sdxl"</span>,
	torch_dtype=torch.float16,
	variant=<span class="hljs-string">"fp16"</span>,
	)
	pipe = DiffusionPipeline.from_pretrained(
	<span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>, unet=unet, torch_dtype=torch.float16
	).to(<span class="hljs-string">"cuda"</span>)
	pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)

	prompt = <span class="hljs-string">"Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"</span>

	generator = torch.manual_seed(<span class="hljs-number">0</span>)
	image = pipe(
	prompt=prompt, num_inference_steps=<span class="hljs-number">4</span>, generator=generator, guidance_scale=<span class="hljs-number">8.0</span>
	).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1xlop1"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_intro.png"></p> <p data-svelte-h="svelte-n61tgz">Notice that we use only 4 steps for generation which is way less than what’s typically used for standard SDXL.</p> <p data-svelte-h="svelte-k48bzl">Some details to keep in mind:</p> <ul data-svelte-h="svelte-j6mcv0"><li>To perform classifier-free guidance, batch size is usually doubled inside the pipeline. LCM, however, applies guidance using guidance embeddings, so the batch size does not have to be doubled in this case. This leads to a faster inference time, with the drawback that negative prompts don’t have any effect on the denoising process.</li> <li>The UNet was trained using the [3., 13.] guidance scale range. So, that is the ideal range for <code>guidance_scale</code>. However, disabling <code>guidance_scale</code> using a value of 1.0 is also effective in most cases.</li></ul> <h2 class="relative group"><a id="image-to-image" 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="#image-to-image"><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>Image-to-image</span></h2> <p data-svelte-h="svelte-faqh5e">The findings above apply to image-to-image tasks too. Let’s look at how we can perform image-to-image generation with LCMs:</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> AutoPipelineForImage2Image, UNet2DConditionModel, LCMScheduler
	<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image
	<span class="hljs-keyword">import</span> torch

	unet = UNet2DConditionModel.from_pretrained(
	<span class="hljs-string">"latent-consistency/lcm-sdxl"</span>,
	torch_dtype=torch.float16,
	variant=<span class="hljs-string">"fp16"</span>,
	)
	pipe = AutoPipelineForImage2Image.from_pretrained(
	<span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>, unet=unet, torch_dtype=torch.float16
	).to(<span class="hljs-string">"cuda"</span>)
	pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)

	prompt = <span class="hljs-string">"High altitude snowy mountains"</span>
	image = load_image(
	<span class="hljs-string">"https://huggingface.co/datasets/sayakpaul/sample-datasets/resolve/main/snowy_mountains.jpeg"</span>
	)

	generator = torch.manual_seed(<span class="hljs-number">0</span>)
	image = pipe(
	prompt=prompt,
	image=image,
	num_inference_steps=<span class="hljs-number">4</span>,
	generator=generator,
	guidance_scale=<span class="hljs-number">8.0</span>,
	).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ip1f65"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_i2i.png"></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-17hfqpq">It is possible to generalize the LCM framework to use with <a href="../training/lora.md">LoRA</a>. It effectively eliminates the need to conduct expensive fine-tuning runs as LoRA training concerns just a few number of parameters compared to full fine-tuning. During inference, the <a href="/docs/diffusers/main/en/api/schedulers/lcm#diffusers.LCMScheduler">LCMScheduler</a> comes to the advantage as it enables very few-steps inference without compromising the quality.</p> <p data-svelte-h="svelte-762c0q">We recommend to disable <code>guidance_scale</code> by setting it 0. The model is trained to follow prompts accurately
	even without using guidance scale. You can however, still use guidance scale in which case we recommend
	using values between 1.0 and 2.0.</p> <h3 class="relative group"><a id="text-to-image" 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="#text-to-image"><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>Text-to-image</span></h3> <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, LCMScheduler
	<span class="hljs-keyword">import</span> torch

	model_id = <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>
	lcm_lora_id = <span class="hljs-string">"latent-consistency/lcm-lora-sdxl"</span>

	pipe = DiffusionPipeline.from_pretrained(model_id, variant=<span class="hljs-string">"fp16"</span>, torch_dtype=torch.float16).to(<span class="hljs-string">"cuda"</span>)

	pipe.load_lora_weights(lcm_lora_id)
	pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)

	prompt = <span class="hljs-string">"close-up photography of old man standing in the rain at night, in a street lit by lamps, leica 35mm summilux"</span>
	image = pipe(
	prompt=prompt,
	num_inference_steps=<span class="hljs-number">4</span>,
	guidance_scale=<span class="hljs-number">0</span>, <span class="hljs-comment"># set guidance scale to 0 to disable it</span>
	).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1bt9nqr"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lora_lcm.png"></p> <h3 class="relative group"><a id="image-to-image" 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="#image-to-image"><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>Image-to-image</span></h3> <p data-svelte-h="svelte-1babs9h">Extending LCM LoRA to image-to-image is possible:</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> StableDiffusionXLImg2ImgPipeline, LCMScheduler
	<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image
	<span class="hljs-keyword">import</span> torch

	model_id = <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>
	lcm_lora_id = <span class="hljs-string">"latent-consistency/lcm-lora-sdxl"</span>

	pipe = StableDiffusionXLImg2ImgPipeline.from_pretrained(model_id, variant=<span class="hljs-string">"fp16"</span>, torch_dtype=torch.float16).to(<span class="hljs-string">"cuda"</span>)

	pipe.load_lora_weights(lcm_lora_id)
	pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)

	prompt = <span class="hljs-string">"close-up photography of old man standing in the rain at night, in a street lit by lamps, leica 35mm summilux"</span>

	image = load_image(<span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lora_lcm.png"</span>)

	image = pipe(
	prompt=prompt,
	image=image,
	num_inference_steps=<span class="hljs-number">4</span>,
	guidance_scale=<span class="hljs-number">0</span>, <span class="hljs-comment"># set guidance scale to 0 to disable it</span>
	).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ddcini"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lcm/lcm_lora_i2i.png"></p> <p></p>

	<script>
	{
	__sveltekit_2qzlx4 = {
	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.0fc360d2.js"),
	import("/docs/diffusers/main/en/_app/immutable/entry/app.aa1da0ff.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 171],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 24.1 kB
Xet hash:: 78535486f87b497a907c836da95d3f1681180635ba48736b3d71002cc75df265

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