Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"ControlNet","local":"controlnet","sections":[{"title":"Multi-ControlNet","local":"multi-controlnet","sections":[],"depth":2},{"title":"guess_mode","local":"guessmode","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/diffusers/pr_12411/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/entry/start.3e0bd2b6.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/scheduler.53228c21.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/singletons.65de65e1.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/index.e93d0901.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/paths.d8aaea9f.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/entry/app.075ca386.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/preload-helper.a3bbca49.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/index.100fac89.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/nodes/0.64b9a56d.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/nodes/328.559ccb5a.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/CopyLLMTxtMenu.c51e21f1.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/IconCopy.38cf8f56.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.5af3dadc.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/CodeBlock.d30a6509.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_12411/en/_app/immutable/chunks/HfOption.fad27e59.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"ControlNet","local":"controlnet","sections":[{"title":"Multi-ControlNet","local":"multi-controlnet","sections":[],"depth":2},{"title":"guess_mode","local":"guessmode","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 max-sm:gap-0.5 h-6 max-sm:h-5 px-2 max-sm:px-1.5 text-[11px] max-sm:text-[9px] 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"><svg class="w-3 h-3 max-sm:w-2.5 max-sm:h-2.5" 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-6 max-sm:h-5 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 w-3 h-3 max-sm:w-2.5 max-sm:h-2.5 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="controlnet" 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="#controlnet"><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>ControlNet</span></h1> <p data-svelte-h="svelte-1n3ntx6"><a href="https://huggingface.co/papers/2302.05543" rel="nofollow">ControlNet</a> is an adapter that enables controllable generation such as generating an image of a cat in a <em>specific pose</em> or following the lines in a sketch of a <em>specific</em> cat. It works by adding a smaller network of “zero convolution” layers and progressively training these to avoid disrupting with the original model. The original model parameters are frozen to avoid retraining it.</p> <p data-svelte-h="svelte-1qp3bo6">A ControlNet is conditioned on extra visual information or “structural controls” (canny edge, depth maps, human pose, etc.) that can be combined with text prompts to generate images that are guided by the visual input.</p> <blockquote class="tip" data-svelte-h="svelte-17w1v3e"><p>ControlNets are available to many models such as <a href="../api/pipelines/controlnet_flux">Flux</a>, <a href="../api/pipelines/controlnet_hunyuandit">Hunyuan-DiT</a>, <a href="../api/pipelines/controlnet_sd3">Stable Diffusion 3</a>, and more. The examples in this guide use Flux and Stable Diffusion XL.</p></blockquote> <p data-svelte-h="svelte-stonke">Load a ControlNet conditioned on a specific control, such as canny edge, and pass it to the pipeline in <a href="/docs/diffusers/pr_12411/en/api/pipelines/overview#diffusers.DiffusionPipeline.from_pretrained">from_pretrained()</a>.</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 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">inpainting </div></div> <div class="language-select"><p data-svelte-h="svelte-odtmr5">Generate a canny image with <a href="https://github.com/opencv/opencv-python" rel="nofollow">opencv-python</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 --><span class="hljs-keyword">import</span> cv2 | |
| <span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np | |
| <span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image | |
| <span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image | |
| original_image = load_image( | |
| <span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png"</span> | |
| ) | |
| image = np.array(original_image) | |
| low_threshold = <span class="hljs-number">100</span> | |
| high_threshold = <span class="hljs-number">200</span> | |
| image = cv2.Canny(image, low_threshold, high_threshold) | |
| image = image[:, :, <span class="hljs-literal">None</span>] | |
| image = np.concatenate([image, image, image], axis=<span class="hljs-number">2</span>) | |
| canny_image = Image.fromarray(image)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-zjofbt">Pass the canny image to the pipeline. Use the <code>controlnet_conditioning_scale</code> parameter to determine how much weight to assign to the control.</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.utils <span class="hljs-keyword">import</span> load_image | |
| <span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> FluxControlNetPipeline, FluxControlNetModel | |
| controlnet = FluxControlNetModel.from_pretrained( | |
| <span class="hljs-string">"InstantX/FLUX.1-dev-Controlnet-Canny"</span>, torch_dtype=torch.bfloat16 | |
| ) | |
| pipeline = FluxControlNetPipeline.from_pretrained( | |
| <span class="hljs-string">"black-forest-labs/FLUX.1-dev"</span>, controlnet=controlnet, torch_dtype=torch.bfloat16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| prompt = <span class="hljs-string">""" | |
| A photorealistic overhead image of a cat reclining sideways in a flamingo pool floatie holding a margarita. | |
| The cat is floating leisurely in the pool and completely relaxed and happy. | |
| """</span> | |
| pipeline( | |
| prompt, | |
| control_image=canny_image, | |
| controlnet_conditioning_scale=<span class="hljs-number">0.5</span>, | |
| num_inference_steps=<span class="hljs-number">50</span>, | |
| guidance_scale=<span class="hljs-number">3.5</span>, | |
| ).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <div style="display: flex; gap: 10px; justify-content: space-around; align-items: flex-end;" data-svelte-h="svelte-y2w2wd"><figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png" width="300" alt="Generated image (prompt only)"> <figcaption style="text-align: center;">original image</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat.png" width="300" alt="Control image (Canny edges)"> <figcaption style="text-align: center;">canny image</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat-generated.png" width="300" alt="Generated image (ControlNet + prompt)"> <figcaption style="text-align: center;">generated image</figcaption></figure></div> </div> <h2 class="relative group"><a id="multi-controlnet" 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="#multi-controlnet"><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>Multi-ControlNet</span></h2> <p data-svelte-h="svelte-11jp78z">You can compose multiple ControlNet conditionings, such as canny image and a depth map, to create a <em>MultiControlNet</em>. For the best rersults, you should mask conditionings so they don’t overlap and experiment with different <code>controlnet_conditioning_scale</code> parameters to adjust how much weight is assigned to each control input.</p> <p data-svelte-h="svelte-ueyms4">The example below composes a canny image and depth map.</p> <p data-svelte-h="svelte-1yb2pw9">Pass the ControlNets as a list to the pipeline and resize the images to the expected input size.</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> StableDiffusionXLControlNetPipeline, ControlNetModel, AutoencoderKL | |
| controlnets = [ | |
| ControlNetModel.from_pretrained( | |
| <span class="hljs-string">"diffusers/controlnet-depth-sdxl-1.0-small"</span>, torch_dtype=torch.float16 | |
| ), | |
| ControlNetModel.from_pretrained( | |
| <span class="hljs-string">"diffusers/controlnet-canny-sdxl-1.0"</span>, torch_dtype=torch.float16, | |
| ), | |
| ] | |
| vae = AutoencoderKL.from_pretrained(<span class="hljs-string">"madebyollin/sdxl-vae-fp16-fix"</span>, torch_dtype=torch.float16) | |
| pipeline = StableDiffusionXLControlNetPipeline.from_pretrained( | |
| <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>, controlnet=controlnets, vae=vae, torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| prompt = <span class="hljs-string">""" | |
| a relaxed rabbit sitting on a striped towel next to a pool with a tropical drink nearby, | |
| bright sunny day, vacation scene, 35mm photograph, film, professional, 4k, highly detailed | |
| """</span> | |
| negative_prompt = <span class="hljs-string">"lowres, bad anatomy, worst quality, low quality, deformed, ugly"</span> | |
| images = [canny_image.resize((<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>)), depth_image.resize((<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>))] | |
| pipeline( | |
| prompt, | |
| negative_prompt=negative_prompt, | |
| image=images, | |
| num_inference_steps=<span class="hljs-number">100</span>, | |
| controlnet_conditioning_scale=[<span class="hljs-number">0.5</span>, <span class="hljs-number">0.5</span>], | |
| strength=<span class="hljs-number">0.7</span>, | |
| ).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <div style="display: flex; gap: 10px; justify-content: space-around; align-items: flex-end;" data-svelte-h="svelte-1ols1y"><figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat.png" width="300" alt="Generated image (prompt only)"> <figcaption style="text-align: center;">canny image</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/multicontrolnet_depth.png" width="300" alt="Control image (Canny edges)"> <figcaption style="text-align: center;">depth map</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_multi_controlnet.png" width="300" alt="Generated image (ControlNet + prompt)"> <figcaption style="text-align: center;">generated image</figcaption></figure></div> <h2 class="relative group"><a id="guessmode" 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="#guessmode"><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>guess_mode</span></h2> <p data-svelte-h="svelte-1cijut3"><a href="https://github.com/lllyasviel/ControlNet/discussions/188" rel="nofollow">Guess mode</a> generates an image from <strong>only</strong> the control input (canny edge, depth map, pose, etc.) and without guidance from a prompt. It adjusts the scale of the ControlNet’s output residuals by a fixed ratio depending on block depth. The earlier <code>DownBlock</code> is only scaled by <code>0.1</code> and the <code>MidBlock</code> is fully scaled by <code>1.0</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 --><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_iamge | |
| <span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionXLControlNetPipeline, ControlNetModel | |
| controlnet = ControlNetModel.from_pretrained( | |
| <span class="hljs-string">"diffusers/controlnet-canny-sdxl-1.0"</span>, torch_dtype=torch.float16 | |
| ) | |
| pipeline = StableDiffusionXLControlNetPipeline.from_pretrained( | |
| <span class="hljs-string">"stabilityai/stable-diffusion-xl-base-1.0"</span>, | |
| controlnet=controlnet, | |
| torch_dtype=torch.float16 | |
| ).to(<span class="hljs-string">"cuda"</span>) | |
| canny_image = load_image(<span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat.png"</span>) | |
| pipeline( | |
| <span class="hljs-string">""</span>, | |
| image=canny_image, | |
| guess_mode=<span class="hljs-literal">True</span> | |
| ).images[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <div style="display: flex; gap: 10px; justify-content: space-around; align-items: flex-end;" data-svelte-h="svelte-193ffwv"><figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat.png" width="300" alt="Control image (Canny edges)"> <figcaption style="text-align: center;">canny image</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guess_mode.png" width="300" alt="Generated image (Guess mode)"> <figcaption style="text-align: center;">generated image</figcaption></figure></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/using-diffusers/controlnet.md" target="_blank"><svg class="mr-1" 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="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_r19zh6 = { | |
| assets: "/docs/diffusers/pr_12411/en", | |
| base: "/docs/diffusers/pr_12411/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/pr_12411/en/_app/immutable/entry/start.3e0bd2b6.js"), | |
| import("/docs/diffusers/pr_12411/en/_app/immutable/entry/app.075ca386.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 328], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 25.4 kB
- Xet hash:
- 59514e5edb4fef19ac139b38651c77d134198b1c211c99cd27bf6df6fa849029
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.