Buckets:

hf-doc-build
/

doc

Files
xet
hf-doc-build/doc / diffusers /main /es /using-diffusers /controlnet.html
mishig
3 days ago
download
raw
42.3 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;ControlNet&quot;,&quot;local&quot;:&quot;controlnet&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Multi-ControlNet&quot;,&quot;local&quot;:&quot;multi-controlnet&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Modo de conjetura&quot;,&quot;local&quot;:&quot;guess-mode&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
		<link href="/docs/diffusers/main/en/_app/immutable/entry/start.0S0_iEoG.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/I9eooN77.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/Bupkjr9f.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/CyvZ3FS5.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/l0QnnOED.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DnVIJfC5.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/nodes/0.DteTvmQZ.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/CoSrdQax.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/nodes/391.CRavWgDP.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DSPDl1gz.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/D5eijdnr.js" rel="modulepreload">
		<!--18lijse--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;ControlNet&quot;,&quot;local&quot;:&quot;controlnet&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Multi-ControlNet&quot;,&quot;local&quot;:&quot;multi-controlnet&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Guess mode&quot;,&quot;local&quot;:&quot;guess-mode&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
		<link href="/docs/diffusers/main/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" 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 dir="auto">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> <!--[-1--><!--]--></div><!----> <!--[0--><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 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><a href="https://huggingface.co/papers/2302.05543" rel="nofollow">ControlNet</a> dirige un modelo de difusión preentrenado mediante una imagen de control estructural (bordes, profundidad o pose) mientras se mantiene un prompt de texto. Congela el modelo base y añade una red paralela cuyos residuos guían al desruidador, lo que permite controlar el diseño sin necesidad de afinar el modelo.</p> <p>Carga un ControlNet para el control que necesites (por ejemplo, canny) y pásalo como <code>controlnet=</code> a <a href="/docs/diffusers/main/es/api/pipelines/overview#diffusers.DiffusionPipeline.from_pretrained">from_pretrained()</a>. Usa <code>controlnet_conditioning_scale</code> para establecer la fuerza con la que el control dirige la generación.</p> <blockquote class="tip"><p>ControlNets están disponibles para muchos modelos, como <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> y más. Los ejemplos de esta guía utilizan Flux y Stable Diffusion XL. Para T2I-Adapter en puntos de control antiguos de la familia Stable Diffusion, consulte <a href="./legacy_adapters#t2i-adapter">Adaptadores heredados</a>. Prefiera ControlNet para nuevo trabajo de generación controlable.</p></blockquote> <p>Las pestañas de abajo muestran ControlNet para texto a imagen, imagen a imagen y relleno (inpainting).</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">texto a imagen</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"><div><p>Genera una imagen canny con <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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!----><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">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png&quot;</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)<!----></pre></div><!----> <p>Pasa la imagen canny a la pipeline. Usa el parámetro <code>controlnet_conditioning_scale</code> para determinar cuánto peso asignar al 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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!----><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">&quot;InstantX/FLUX.1-dev-Controlnet-Canny&quot;</span>, dtype=torch.bfloat16
)
pipeline = FluxControlNetPipeline.from_pretrained(
    <span class="hljs-string">&quot;black-forest-labs/FLUX.1-dev&quot;</span>, controlnet=controlnet, dtype=torch.bfloat16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>

prompt = <span class="hljs-string">&quot;&quot;&quot;
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.
&quot;&quot;&quot;</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>]<!----></pre></div><!----> <div style="display: flex; gap: 10px; justify-content: space-around; align-items: flex-end;"><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;">imagen original</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;">imagen canny</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;">imagen generada</figcaption></figure></div><!----></div><!----> <div hidden=""><p>Genera un mapa de profundidad con un pipeline de estimación de profundidad de Transformers.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> torch
<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> transformers <span class="hljs-keyword">import</span> DPTImageProcessor, DPTForDepthEstimation
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ControlNetModel, StableDiffusionXLControlNetImg2ImgPipeline, AutoencoderKL
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image


device = <span class="hljs-string">&quot;cuda&quot;</span>  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
depth_estimator = DPTForDepthEstimation.from_pretrained(<span class="hljs-string">&quot;Intel/dpt-hybrid-midas&quot;</span>).to(device)
feature_extractor = DPTImageProcessor.from_pretrained(<span class="hljs-string">&quot;Intel/dpt-hybrid-midas&quot;</span>)

<span class="hljs-keyword">def</span> <span class="hljs-title function_">get_depth_map</span>(<span class="hljs-params">image</span>):
    image = feature_extractor(images=image, return_tensors=<span class="hljs-string">&quot;pt&quot;</span>).pixel_values.to(device)
    <span class="hljs-keyword">with</span> torch.no_grad(), torch.autocast(device):
        depth_map = depth_estimator(image).predicted_depth

    depth_map = torch.nn.functional.interpolate(
        depth_map.unsqueeze(<span class="hljs-number">1</span>),
        size=(<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>),
        mode=<span class="hljs-string">&quot;bicubic&quot;</span>,
        align_corners=<span class="hljs-literal">False</span>,
    )
    depth_min = torch.amin(depth_map, dim=[<span class="hljs-number">1</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>], keepdim=<span class="hljs-literal">True</span>)
    depth_max = torch.amax(depth_map, dim=[<span class="hljs-number">1</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>], keepdim=<span class="hljs-literal">True</span>)
    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
    image = torch.cat([depth_map] * <span class="hljs-number">3</span>, dim=<span class="hljs-number">1</span>)
    image = image.permute(<span class="hljs-number">0</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>, <span class="hljs-number">1</span>).cpu().numpy()[<span class="hljs-number">0</span>]
    image = Image.fromarray((image * <span class="hljs-number">255.0</span>).clip(<span class="hljs-number">0</span>, <span class="hljs-number">255</span>).astype(np.uint8))
    <span class="hljs-keyword">return</span> image

image = load_image(
    <span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png&quot;</span>
).resize((<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>))
depth_image = get_depth_map(image)<!----></pre></div><!----> <p>Pasa el mapa de profundidad a la pipeline. Usa el parámetro <code>controlnet_conditioning_scale</code> para determinar cuánto peso asignar al 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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->controlnet = ControlNetModel.from_pretrained(
    <span class="hljs-string">&quot;diffusers/controlnet-depth-sdxl-1.0-small&quot;</span>,
    dtype=torch.float16,
)
vae = AutoencoderKL.from_pretrained(<span class="hljs-string">&quot;madebyollin/sdxl-vae-fp16-fix&quot;</span>, dtype=torch.float16)
pipeline = StableDiffusionXLControlNetImg2ImgPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
    controlnet=controlnet,
    vae=vae,
    dtype=torch.float16,
).to(device)

prompt = <span class="hljs-string">&quot;&quot;&quot;
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.
&quot;&quot;&quot;</span>
controlnet_conditioning_scale = <span class="hljs-number">0.5</span>
pipeline(
    prompt,
    image=image,
    control_image=depth_image,
    controlnet_conditioning_scale=controlnet_conditioning_scale,
    strength=<span class="hljs-number">0.99</span>,
    num_inference_steps=<span class="hljs-number">100</span>,
).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <div style="display: flex; gap: 10px; justify-content: space-around; align-items: flex-end;"><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;">imagen original</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_depth_image.png" width="300" alt="Depth map"/> <figcaption style="text-align: center;">mapa de profundidad</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_depth_cat.png" width="300" alt="Generated image (ControlNet + prompt)"/> <figcaption style="text-align: center;">imagen generada</figcaption></figure></div><!----></div><!----> <div hidden=""><p>Genere una imagen de máscara que marque qué píxeles reemplazar y pásela como <code>mask_image</code> junto con la imagen de 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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> cv2
<span class="hljs-keyword">import</span> torch
<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
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionXLControlNetInpaintPipeline, ControlNetModel

init_image = load_image(
    <span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png&quot;</span>
)
init_image = init_image.resize((<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>))
mask_image = load_image(
    <span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat_mask.png&quot;</span>
)
mask_image = mask_image.resize((<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>))

<span class="hljs-keyword">def</span> <span class="hljs-title function_">make_canny_condition</span>(<span class="hljs-params">image</span>):
    image = np.array(image)
    image = cv2.Canny(image, <span class="hljs-number">100</span>, <span class="hljs-number">200</span>)
    image = image[:, :, <span class="hljs-literal">None</span>]
    image = np.concatenate([image, image, image], axis=<span class="hljs-number">2</span>)
    image = Image.fromarray(image)
    <span class="hljs-keyword">return</span> image

control_image = make_canny_condition(init_image)<!----></pre></div><!----> <p>Pasa la máscara y la imagen de control a la pipeline. Usa el parámetro <code>controlnet_conditioning_scale</code> para determinar cuánto peso asignar al 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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!---->controlnet = ControlNetModel.from_pretrained(
    <span class="hljs-string">&quot;diffusers/controlnet-canny-sdxl-1.0&quot;</span>, dtype=torch.float16
)
pipeline = StableDiffusionXLControlNetInpaintPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, controlnet=controlnet, dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
pipeline(
    <span class="hljs-string">&quot;a cute and fluffy bunny rabbit&quot;</span>,
    num_inference_steps=<span class="hljs-number">100</span>,
    strength=<span class="hljs-number">0.99</span>,
    controlnet_conditioning_scale=<span class="hljs-number">0.5</span>,
    image=init_image,
    mask_image=mask_image,
    control_image=control_image,
).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <div style="display: flex; gap: 10px; justify-content: space-around; align-items: flex-end;"><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;">imagen original</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat_mask.png" width="300" alt="Mask image"/> <figcaption style="text-align: center;">imagen de máscara</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl_rabbit_inpaint.png" width="300" alt="Generated image (ControlNet + prompt)"/> <figcaption style="text-align: center;">imagen generada</figcaption></figure></div><!----></div><!----><!----></div><!----> <!--[1--><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 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>Compón varios ControlNets (por ejemplo, canny + depth) pasándolos como una lista. Enmascara las regiones superpuestas cuando sea posible y ajusta cada <code>controlnet_conditioning_scale</code>. Crea <code>canny_image</code> con OpenCV Canny (como en text-to-image) y <code>depth_image</code> con DPT (como en image-to-image). Redimensiona cada imagen de control al tamaño del pipeline antes de llamar al pipeline.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> cv2
<span class="hljs-keyword">import</span> torch
<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> transformers <span class="hljs-keyword">import</span> DPTImageProcessor, DPTForDepthEstimation
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionXLControlNetPipeline, ControlNetModel, AutoencoderKL
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

original_image = load_image(
    <span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/non-enhanced-prompt.png&quot;</span>
)
image = np.array(original_image)
canny_image = Image.fromarray(
    np.concatenate([cv2.Canny(image, <span class="hljs-number">100</span>, <span class="hljs-number">200</span>)[:, :, <span class="hljs-literal">None</span>]] * <span class="hljs-number">3</span>, axis=<span class="hljs-number">2</span>)
)

device = <span class="hljs-string">&quot;cuda&quot;</span>  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
depth_estimator = DPTForDepthEstimation.from_pretrained(<span class="hljs-string">&quot;Intel/dpt-hybrid-midas&quot;</span>).to(device)
feature_extractor = DPTImageProcessor.from_pretrained(<span class="hljs-string">&quot;Intel/dpt-hybrid-midas&quot;</span>)

<span class="hljs-keyword">def</span> <span class="hljs-title function_">get_depth_map</span>(<span class="hljs-params">image</span>):
    image = feature_extractor(images=image, return_tensors=<span class="hljs-string">&quot;pt&quot;</span>).pixel_values.to(device)
    <span class="hljs-keyword">with</span> torch.no_grad(), torch.autocast(device):
        depth_map = depth_estimator(image).predicted_depth

    depth_map = torch.nn.functional.interpolate(
        depth_map.unsqueeze(<span class="hljs-number">1</span>),
        size=(<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>),
        mode=<span class="hljs-string">&quot;bicubic&quot;</span>,
        align_corners=<span class="hljs-literal">False</span>,
    )
    depth_min = torch.amin(depth_map, dim=[<span class="hljs-number">1</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>], keepdim=<span class="hljs-literal">True</span>)
    depth_max = torch.amax(depth_map, dim=[<span class="hljs-number">1</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>], keepdim=<span class="hljs-literal">True</span>)
    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
    image = torch.cat([depth_map] * <span class="hljs-number">3</span>, dim=<span class="hljs-number">1</span>)
    image = image.permute(<span class="hljs-number">0</span>, <span class="hljs-number">2</span>, <span class="hljs-number">3</span>, <span class="hljs-number">1</span>).cpu().numpy()[<span class="hljs-number">0</span>]
    image = Image.fromarray((image * <span class="hljs-number">255.0</span>).clip(<span class="hljs-number">0</span>, <span class="hljs-number">255</span>).astype(np.uint8))
    <span class="hljs-keyword">return</span> image

depth_image = get_depth_map(original_image.resize((<span class="hljs-number">1024</span>, <span class="hljs-number">1024</span>)))

controlnets = [
    ControlNetModel.from_pretrained(
        <span class="hljs-string">&quot;diffusers/controlnet-canny-sdxl-1.0&quot;</span>, dtype=torch.float16
    ),
    ControlNetModel.from_pretrained(
        <span class="hljs-string">&quot;diffusers/controlnet-depth-sdxl-1.0-small&quot;</span>, dtype=torch.float16
    ),
]

vae = AutoencoderKL.from_pretrained(<span class="hljs-string">&quot;madebyollin/sdxl-vae-fp16-fix&quot;</span>, dtype=torch.float16)
pipeline = StableDiffusionXLControlNetPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, controlnet=controlnets, vae=vae, dtype=torch.float16
).to(device)

prompt = <span class="hljs-string">&quot;&quot;&quot;
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
&quot;&quot;&quot;</span>
negative_prompt = <span class="hljs-string">&quot;lowres, bad anatomy, worst quality, low quality, deformed, ugly&quot;</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>],
).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <div style="display: flex; gap: 10px; justify-content: space-around; align-items: flex-end;"><figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat.png" width="300" alt="Canny image"/> <figcaption style="text-align: center;">imagen canny</figcaption></figure> <figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/multicontrolnet_depth.png" width="300" alt="Depth map"/> <figcaption style="text-align: center;">mapa de profundidad</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;">imagen generada</figcaption></figure></div> <!--[1--><h2 class="relative group"><a id="guess-mode" 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="#guess-mode"><span><svg 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><!---->Modo de conjetura<!----></span></h2><!--]--><!----> <p><a href="https://github.com/lllyasviel/ControlNet/discussions/188" rel="nofollow">Guess mode</a> genera una imagen a partir de un control por sí solo cuando no se dispone de un prompt de texto (o no se desea usar uno). Escala los residuales de ControlNet según la profundidad del bloque, desde aproximadamente <code>0.1</code> en los bloques de bajada iniciales hasta <code>1.0</code> en el bloque intermedio. Esto evita que las capas iniciales sobre-restringan la generación, mientras que los bloques más profundos siguen aportando la estructura.</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 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> Copiado</div><!----></button><!----></div> <pre class="language-py "><!----><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> StableDiffusionXLControlNetPipeline, ControlNetModel

controlnet = ControlNetModel.from_pretrained(
  <span class="hljs-string">&quot;diffusers/controlnet-canny-sdxl-1.0&quot;</span>, dtype=torch.float16
)
pipeline = StableDiffusionXLControlNetPipeline.from_pretrained(
  <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
  controlnet=controlnet,
  dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>

canny_image = load_image(<span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat.png&quot;</span>)
pipeline(
  <span class="hljs-string">&quot;&quot;</span>,
  image=canny_image,
  guess_mode=<span class="hljs-literal">True</span>
).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <div style="display: flex; gap: 10px; justify-content: space-around; align-items: flex-end;"><figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/canny-cat.png" width="300" alt="Canny image"/> <figcaption style="text-align: center;">imagen canny</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;">imagen generada</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><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
			
			<script>
				{
					__sveltekit_1qsdbwf = {
						base: "/docs/diffusers/main/en",
						assets: "/docs/diffusers/main/en"
					};
					const element = document.currentScript.parentElement;
					Promise.all([
						import("/docs/diffusers/main/en/_app/immutable/entry/start.0S0_iEoG.js"),
						import("/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 391],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>
		
Xet Storage Details

Size:: 42.3 kB
Xet hash:: c2fb08e1dfdc89d76c62982c795a26abd3f921bc3ac5fc43f9aae879f16510ff
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.