Buckets:

HuggingFaceDocBuilder's picture
download
raw
25.6 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Stable Diffusion 2&quot;,&quot;local&quot;:&quot;stable-diffusion-2&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Text-to-image&quot;,&quot;local&quot;:&quot;text-to-image&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Inpainting&quot;,&quot;local&quot;:&quot;inpainting&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Super-resolution&quot;,&quot;local&quot;:&quot;super-resolution&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Depth-to-image&quot;,&quot;local&quot;:&quot;depth-to-image&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;: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.745a3c77.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/scheduler.53228c21.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/singletons.eb110f1f.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.e93d0901.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/paths.e9d507e4.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/entry/app.ff1b270b.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/preload-helper.5c375679.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/index.100fac89.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/nodes/0.5fbcc707.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/196.d18fe4a9.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/CopyLLMTxtMenu.37908ba4.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/globals.7f7f1b26.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/IconCopy.38cf8f56.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.0a9663c0.js">
<link rel="modulepreload" href="/docs/diffusers/main/en/_app/immutable/chunks/CodeBlock.d30a6509.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Stable Diffusion 2&quot;,&quot;local&quot;:&quot;stable-diffusion-2&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Text-to-image&quot;,&quot;local&quot;:&quot;text-to-image&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Inpainting&quot;,&quot;local&quot;:&quot;inpainting&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Super-resolution&quot;,&quot;local&quot;:&quot;super-resolution&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Depth-to-image&quot;,&quot;local&quot;:&quot;depth-to-image&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;: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="stable-diffusion-2" 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="#stable-diffusion-2"><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>Stable Diffusion 2</span></h1> <p data-svelte-h="svelte-b1fked">Stable Diffusion 2 is a text-to-image <em>latent diffusion</em> model built upon the work of the original <a href="https://stability.ai/blog/stable-diffusion-public-release" rel="nofollow">Stable Diffusion</a>, and it was led by Robin Rombach and Katherine Crowson from <a href="https://stability.ai/" rel="nofollow">Stability AI</a> and <a href="https://laion.ai/" rel="nofollow">LAION</a>.</p> <p data-svelte-h="svelte-14ofdwv"><em>The Stable Diffusion 2.0 release includes robust text-to-image models trained using a brand new text encoder (OpenCLIP), developed by LAION with support from Stability AI, which greatly improves the quality of the generated images compared to earlier V1 releases. The text-to-image models in this release can generate images with default resolutions of both 512x512 pixels and 768x768 pixels.
These models are trained on an aesthetic subset of the <a href="https://laion.ai/blog/laion-5b/" rel="nofollow">LAION-5B dataset</a> created by the DeepFloyd team at Stability AI, which is then further filtered to remove adult content using <a href="https://openreview.net/forum?id=M3Y74vmsMcY" rel="nofollow">LAION’s NSFW filter</a>.</em></p> <p data-svelte-h="svelte-m1ataf">For more details about how Stable Diffusion 2 works and how it differs from the original Stable Diffusion, please refer to the official <a href="https://stability.ai/blog/stable-diffusion-v2-release" rel="nofollow">announcement post</a>.</p> <p data-svelte-h="svelte-1fyxemw">The architecture of Stable Diffusion 2 is more or less identical to the original <a href="./text2img">Stable Diffusion model</a> so check out it’s API documentation for how to use Stable Diffusion 2. We recommend using the <a href="/docs/diffusers/main/en/api/schedulers/multistep_dpm_solver#diffusers.DPMSolverMultistepScheduler">DPMSolverMultistepScheduler</a> as it gives a reasonable speed/quality trade-off and can be run with as little as 20 steps.</p> <p data-svelte-h="svelte-lmvyuh">Stable Diffusion 2 is available for tasks like text-to-image, inpainting, super-resolution, and depth-to-image:</p> <table data-svelte-h="svelte-14nbvv4"><thead><tr><th>Task</th> <th>Repository</th></tr></thead> <tbody><tr><td>text-to-image (512x512)</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-2-base" rel="nofollow">stabilityai/stable-diffusion-2-base</a></td></tr> <tr><td>text-to-image (768x768)</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-2" rel="nofollow">stabilityai/stable-diffusion-2</a></td></tr> <tr><td>inpainting</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-2-inpainting" rel="nofollow">stabilityai/stable-diffusion-2-inpainting</a></td></tr> <tr><td>super-resolution</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler" rel="nofollow">stable-diffusion-x4-upscaler</a></td></tr> <tr><td>depth-to-image</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-2-depth" rel="nofollow">stabilityai/stable-diffusion-2-depth</a></td></tr></tbody></table> <p data-svelte-h="svelte-1y4j0tz">Here are some examples for how to use Stable Diffusion 2 for each task:</p> <blockquote class="tip" data-svelte-h="svelte-plkvnd"><p>Make sure to check out the Stable Diffusion <a href="overview#tips">Tips</a> section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!</p> <p>If you’re interested in using one of the official checkpoints for a task, explore the <a href="https://huggingface.co/CompVis" rel="nofollow">CompVis</a> and <a href="https://huggingface.co/stabilityai" rel="nofollow">Stability AI</a> Hub organizations!</p></blockquote> <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> <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, DPMSolverMultistepScheduler
<span class="hljs-keyword">import</span> torch
repo_id = <span class="hljs-string">&quot;stabilityai/stable-diffusion-2-base&quot;</span>
pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
prompt = <span class="hljs-string">&quot;High quality photo of an astronaut riding a horse in space&quot;</span>
image = pipe(prompt, num_inference_steps=<span class="hljs-number">25</span>).images[<span class="hljs-number">0</span>]
image<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="inpainting" 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="#inpainting"><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>Inpainting</span></h2> <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> DiffusionPipeline, DPMSolverMultistepScheduler
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, make_image_grid
img_url = <span class="hljs-string">&quot;https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png&quot;</span>
mask_url = <span class="hljs-string">&quot;https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png&quot;</span>
init_image = load_image(img_url).resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))
mask_image = load_image(mask_url).resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))
repo_id = <span class="hljs-string">&quot;stabilityai/stable-diffusion-2-inpainting&quot;</span>
pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
prompt = <span class="hljs-string">&quot;Face of a yellow cat, high resolution, sitting on a park bench&quot;</span>
image = pipe(prompt=prompt, image=init_image, mask_image=mask_image, num_inference_steps=<span class="hljs-number">25</span>).images[<span class="hljs-number">0</span>]
make_image_grid([init_image, mask_image, image], rows=<span class="hljs-number">1</span>, cols=<span class="hljs-number">3</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="super-resolution" 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="#super-resolution"><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>Super-resolution</span></h2> <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> StableDiffusionUpscalePipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, make_image_grid
<span class="hljs-keyword">import</span> torch
<span class="hljs-comment"># load model and scheduler</span>
model_id = <span class="hljs-string">&quot;stabilityai/stable-diffusion-x4-upscaler&quot;</span>
pipeline = StableDiffusionUpscalePipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipeline = pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-comment"># let&#x27;s download an image</span>
url = <span class="hljs-string">&quot;https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd2-upscale/low_res_cat.png&quot;</span>
low_res_img = load_image(url)
low_res_img = low_res_img.resize((<span class="hljs-number">128</span>, <span class="hljs-number">128</span>))
prompt = <span class="hljs-string">&quot;a white cat&quot;</span>
upscaled_image = pipeline(prompt=prompt, image=low_res_img).images[<span class="hljs-number">0</span>]
make_image_grid([low_res_img.resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>)), upscaled_image.resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))], rows=<span class="hljs-number">1</span>, cols=<span class="hljs-number">2</span>)<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="depth-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="#depth-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>Depth-to-image</span></h2> <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> StableDiffusionDepth2ImgPipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, make_image_grid
pipe = StableDiffusionDepth2ImgPipeline.from_pretrained(
<span class="hljs-string">&quot;stabilityai/stable-diffusion-2-depth&quot;</span>,
torch_dtype=torch.float16,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
url = <span class="hljs-string">&quot;http://images.cocodataset.org/val2017/000000039769.jpg&quot;</span>
init_image = load_image(url)
prompt = <span class="hljs-string">&quot;two tigers&quot;</span>
negative_prompt = <span class="hljs-string">&quot;bad, deformed, ugly, bad anotomy&quot;</span>
image = pipe(prompt=prompt, image=init_image, negative_prompt=negative_prompt, strength=<span class="hljs-number">0.7</span>).images[<span class="hljs-number">0</span>]
make_image_grid([init_image, image], rows=<span class="hljs-number">1</span>, cols=<span class="hljs-number">2</span>)<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_2.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_1seqhzr = {
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.745a3c77.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.ff1b270b.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 196],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
25.6 kB
·
Xet hash:
326f4d42463dcaa23e2cc8d780f5516070c01f83dfd340d0faa7e46b56fd0a01

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