Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Stable Video Diffusion","local":"stable-video-diffusion","sections":[{"title":"torch.compile","local":"torchcompile","sections":[],"depth":2},{"title":"Reduce memory usage","local":"reduce-memory-usage","sections":[],"depth":2},{"title":"Micro-conditioning","local":"micro-conditioning","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/diffusers/pr_11636/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/entry/start.466e85ea.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/scheduler.53228c21.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/singletons.d4686aef.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/index.e93d0901.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/paths.d6d4c93d.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/entry/app.af21971c.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/preload-helper.fb439119.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/index.100fac89.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/nodes/0.faaa9cdc.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/nodes/354.9a2aa09a.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/CopyLLMTxtMenu.8a16ebe2.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/IconCopy.38cf8f56.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.83a5c0e1.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/CodeBlock.d30a6509.js"> | |
| <link rel="modulepreload" href="/docs/diffusers/pr_11636/en/_app/immutable/chunks/DocNotebookDropdown.74a16910.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Stable Video Diffusion","local":"stable-video-diffusion","sections":[{"title":"torch.compile","local":"torchcompile","sections":[],"depth":2},{"title":"Reduce memory usage","local":"reduce-memory-usage","sections":[],"depth":2},{"title":"Micro-conditioning","local":"micro-conditioning","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> <div class="flex space-x-1 " style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"> </button> </div> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"> </button> </div></div> <h1 class="relative group"><a id="stable-video-diffusion" 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-video-diffusion"><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 Video Diffusion</span></h1> <p data-svelte-h="svelte-6831zo"><a href="https://huggingface.co/papers/2311.15127" rel="nofollow">Stable Video Diffusion (SVD)</a> is a powerful image-to-video generation model that can generate 2-4 second high resolution (576x1024) videos conditioned on an input image.</p> <p data-svelte-h="svelte-9hcj9z">This guide will show you how to use SVD to generate short videos from images.</p> <p data-svelte-h="svelte-cwruts">Before you begin, make sure you have the following libraries installed:</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-comment"># Colab에서 필요한 라이브러리를 설치하기 위해 주석을 제외하세요</span> | |
| !pip install -q -U diffusers transformers accelerate<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-iibvlr">The are two variants of this model, <a href="https://huggingface.co/stabilityai/stable-video-diffusion-img2vid" rel="nofollow">SVD</a> and <a href="https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt" rel="nofollow">SVD-XT</a>. The SVD checkpoint is trained to generate 14 frames and the SVD-XT checkpoint is further finetuned to generate 25 frames.</p> <p data-svelte-h="svelte-u5kxxd">You’ll use the SVD-XT checkpoint for this guide.</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> StableVideoDiffusionPipeline | |
| <span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, export_to_video | |
| pipe = StableVideoDiffusionPipeline.from_pretrained( | |
| <span class="hljs-string">"stabilityai/stable-video-diffusion-img2vid-xt"</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span> | |
| ) | |
| pipe.enable_model_cpu_offload() | |
| <span class="hljs-comment"># Load the conditioning image</span> | |
| image = load_image(<span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png"</span>) | |
| image = image.resize((<span class="hljs-number">1024</span>, <span class="hljs-number">576</span>)) | |
| generator = torch.manual_seed(<span class="hljs-number">42</span>) | |
| frames = pipe(image, decode_chunk_size=<span class="hljs-number">8</span>, generator=generator).frames[<span class="hljs-number">0</span>] | |
| export_to_video(frames, <span class="hljs-string">"generated.mp4"</span>, fps=<span class="hljs-number">7</span>)<!-- HTML_TAG_END --></pre></div> <div class="flex gap-4" data-svelte-h="svelte-25rdw"><div><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png"> <figcaption class="mt-2 text-center text-sm text-gray-500">"source image of a rocket"</figcaption></div> <div><img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/output_rocket.gif"> <figcaption class="mt-2 text-center text-sm text-gray-500">"generated video from source image"</figcaption></div></div> <h2 class="relative group"><a id="torchcompile" 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="#torchcompile"><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>torch.compile</span></h2> <p data-svelte-h="svelte-1g0qdyz">You can gain a 20-25% speedup at the expense of slightly increased memory by <a href="../optimization/fp16#torchcompile">compiling</a> the UNet.</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-deletion">- pipe.enable_model_cpu_offload()</span> | |
| <span class="hljs-addition">+ pipe.to("cuda")</span> | |
| <span class="hljs-addition">+ pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)</span><!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="reduce-memory-usage" 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="#reduce-memory-usage"><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>Reduce memory usage</span></h2> <p data-svelte-h="svelte-1aihuum">Video generation is very memory intensive because you’re essentially generating <code>num_frames</code> all at once, similar to text-to-image generation with a high batch size. To reduce the memory requirement, there are multiple options that trade-off inference speed for lower memory requirement:</p> <ul data-svelte-h="svelte-carvgs"><li>enable model offloading: each component of the pipeline is offloaded to the CPU once it’s not needed anymore.</li> <li>enable feed-forward chunking: the feed-forward layer runs in a loop instead of running a single feed-forward with a huge batch size.</li> <li>reduce <code>decode_chunk_size</code>: the VAE decodes frames in chunks instead of decoding them all together. Setting <code>decode_chunk_size=1</code> decodes one frame at a time and uses the least amount of memory (we recommend adjusting this value based on your GPU memory) but the video might have some flickering.</li></ul> <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-deletion">- pipe.enable_model_cpu_offload()</span> | |
| <span class="hljs-deletion">- frames = pipe(image, decode_chunk_size=8, generator=generator).frames[0]</span> | |
| <span class="hljs-addition">+ pipe.enable_model_cpu_offload()</span> | |
| <span class="hljs-addition">+ pipe.unet.enable_forward_chunking()</span> | |
| <span class="hljs-addition">+ frames = pipe(image, decode_chunk_size=2, generator=generator, num_frames=25).frames[0]</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1dz5kg5">Using all these tricks together should lower the memory requirement to less than 8GB VRAM.</p> <h2 class="relative group"><a id="micro-conditioning" 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="#micro-conditioning"><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>Micro-conditioning</span></h2> <p data-svelte-h="svelte-crombe">Stable Diffusion Video also accepts micro-conditioning, in addition to the conditioning image, which allows more control over the generated video:</p> <ul data-svelte-h="svelte-hs8jkz"><li><code>fps</code>: the frames per second of the generated video.</li> <li><code>motion_bucket_id</code>: the motion bucket id to use for the generated video. This can be used to control the motion of the generated video. Increasing the motion bucket id increases the motion of the generated video.</li> <li><code>noise_aug_strength</code>: the amount of noise added to the conditioning image. The higher the values the less the video resembles the conditioning image. Increasing this value also increases the motion of the generated video.</li></ul> <p data-svelte-h="svelte-3jffic">For example, to generate a video with more motion, use the <code>motion_bucket_id</code> and <code>noise_aug_strength</code> micro-conditioning parameters:</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> StableVideoDiffusionPipeline | |
| <span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, export_to_video | |
| pipe = StableVideoDiffusionPipeline.from_pretrained( | |
| <span class="hljs-string">"stabilityai/stable-video-diffusion-img2vid-xt"</span>, torch_dtype=torch.float16, variant=<span class="hljs-string">"fp16"</span> | |
| ) | |
| pipe.enable_model_cpu_offload() | |
| <span class="hljs-comment"># Load the conditioning image</span> | |
| image = load_image(<span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png"</span>) | |
| image = image.resize((<span class="hljs-number">1024</span>, <span class="hljs-number">576</span>)) | |
| generator = torch.manual_seed(<span class="hljs-number">42</span>) | |
| frames = pipe(image, decode_chunk_size=<span class="hljs-number">8</span>, generator=generator, motion_bucket_id=<span class="hljs-number">180</span>, noise_aug_strength=<span class="hljs-number">0.1</span>).frames[<span class="hljs-number">0</span>] | |
| export_to_video(frames, <span class="hljs-string">"generated.mp4"</span>, fps=<span class="hljs-number">7</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-19qaph4"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/output_rocket_with_conditions.gif"></p> <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/svd.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_1t8nfoz = { | |
| assets: "/docs/diffusers/pr_11636/en", | |
| base: "/docs/diffusers/pr_11636/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/diffusers/pr_11636/en/_app/immutable/entry/start.466e85ea.js"), | |
| import("/docs/diffusers/pr_11636/en/_app/immutable/entry/app.af21971c.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 354], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 24.9 kB
- Xet hash:
- 189d6561eb942cf014fc101c0d5c9a5d0acc142e6f22769d54e7e3ce70b870a7
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.