Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /v0.43.0 /es /api /pipelines /wan_animate_2.html
mishig's picture
mishig
download
raw
38.3 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Wan-Animate-2&quot;,&quot;local&quot;:&quot;wan-animate-2&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;WanAnimate2ModularPipeline&quot;,&quot;local&quot;:&quot;diffusers.WanAnimate2ModularPipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;WanAnimate2DistilledModularPipeline&quot;,&quot;local&quot;:&quot;diffusers.WanAnimate2DistilledModularPipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;WanAnimate2Blocks&quot;,&quot;local&quot;:&quot;diffusers.WanAnimate2Blocks&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;WanAnimate2DistilledBlocks&quot;,&quot;local&quot;:&quot;diffusers.WanAnimate2DistilledBlocks&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/entry/start.1gaXe03k.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/BObs6oQO.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/DPnyVmXs.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/entry/app.BwdYRbCn.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/DSGUT_OW.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/C045MWWx.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/6tuJ3nyi.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/nodes/0.CornNeQR.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/IaDvMxLQ.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/nodes/258.6JqFTll0.js" rel="modulepreload">
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/chunks/bKdwVYpU.js" rel="modulepreload">
<!--1nkjp63--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Wan-Animate-2&quot;,&quot;local&quot;:&quot;wan-animate-2&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;WanAnimate2ModularPipeline&quot;,&quot;local&quot;:&quot;diffusers.WanAnimate2ModularPipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;WanAnimate2DistilledModularPipeline&quot;,&quot;local&quot;:&quot;diffusers.WanAnimate2DistilledModularPipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;WanAnimate2Blocks&quot;,&quot;local&quot;:&quot;diffusers.WanAnimate2Blocks&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;WanAnimate2DistilledBlocks&quot;,&quot;local&quot;:&quot;diffusers.WanAnimate2DistilledBlocks&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
<link href="/docs/diffusers/v0.43.0/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <!--[0--><h1 class="relative group"><a id="wan-animate-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="#wan-animate-2"><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><!---->Wan-Animate-2<!----></span></h1><!--]--><!----> <p><a href="https://github.com/Wan-Video/Wan2.2" rel="nofollow">Wan-Animate-2</a> del equipo Alibaba Wan anima una imagen de referencia de un personaje con el movimiento de un video de conducción. El video de conducción se procesa en segmentos de longitud fija: cada segmento ejecuta una pasada de extracción de referencia que almacena en caché los K/V del segmento de conducción en cada capa del transformer, realiza el desruido contra esa caché y se decodifica dentro del bucle porque el siguiente segmento se condiciona a los fotogramas finales decodificados del segmento anterior.</p> <p>Hay dos presets disponibles: el checkpoint base muestrea con classifier-free guidance, y el checkpoint destilado muestrea en pocos pasos sin él (su guider está fijado en <code>guidance_scale=1.0</code>).</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg 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-python "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ModularPipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> export_to_video, load_image, load_video
pipe = ModularPipeline.from_pretrained(<span class="hljs-string">&quot;Wan-AI/Wan2.2-Animate-2-14B-Diffusers&quot;</span>)
pipe.load_components(dtype=torch.bfloat16)
<span class="hljs-comment"># The transformer weights and the per-segment reference KV cache do not co-reside on one 80 GB</span>
<span class="hljs-comment"># card at the default resolution, so stream the transformer&#x27;s blocks. Compiling the blocks is</span>
<span class="hljs-comment"># required as the in-context attention runs on the flex backend</span>
pipe.transformer.enable_group_offload(
onload_device=torch.device(<span class="hljs-string">&quot;cuda&quot;</span>),
offload_device=torch.device(<span class="hljs-string">&quot;cpu&quot;</span>),
offload_type=<span class="hljs-string">&quot;block_level&quot;</span>,
use_stream=<span class="hljs-literal">True</span>,
)
pipe.text_encoder.to(<span class="hljs-string">&quot;cuda&quot;</span>) <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
pipe.image_encoder.to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipe.vae.to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipe.transformer.compile_repeated_blocks(fullgraph=<span class="hljs-literal">False</span>)
<span class="hljs-comment"># The first demo from the official repository: https://github.com/Wan-Video/Wan-Animate-2</span>
demo = <span class="hljs-string">&quot;https://raw.githubusercontent.com/Wan-Video/Wan-Animate-2/main/examples/demo1&quot;</span>
image = load_image(<span class="hljs-string">f&quot;<span class="hljs-subst">{demo}</span>/reference.png&quot;</span>)
driving_video, driving_video_fps = load_video(<span class="hljs-string">f&quot;<span class="hljs-subst">{demo}</span>/template.mp4&quot;</span>, return_fps=<span class="hljs-literal">True</span>)
prompt = <span class="hljs-string">&quot;人物外观描述：一只银灰色虎斑纹的小猫，拥有圆润的脸庞、竖立的耳朵和巨大的圆形眼睛。它身穿一套深蓝色的制服套装，包括一件带有金色纽扣的西装外套和一条百褶裙。外套里面搭配着白色衬衫，领口处系着一个红色的蝴蝶结，袖口露出白色的衬衫边缘。背景描述：背景为纯白色，光线均匀明亮，无其他杂物或装饰。&quot;</span>
videos = pipe(
image=image,
driving_video=driving_video,
driving_video_fps=driving_video_fps,
prompt=prompt,
output=<span class="hljs-string">&quot;videos&quot;</span>,
)
export_to_video(videos[<span class="hljs-number">0</span>], <span class="hljs-string">&quot;output.mp4&quot;</span>, fps=<span class="hljs-number">24</span>)<!----></pre></div><!----> <p>Para el checkpoint destilado, carga <code>Wan-AI/Wan2.2-Animate-2-14B-Distilled-Diffusers</code> de la misma manera: no cambia nada más. Cada preset incluye sus propios valores predeterminados de muestreo (40 pasos para el checkpoint base y 10 para el destilado) y no existe ningún argumento <code>guidance_scale</code> en ninguna parte: la guía la gestiona el componente guider de la pipeline (guía libre de clasificador en 3.0 para el preset base y desactivada para el destilado).</p> <p><code>height</code> y <code>width</code> (valores por defecto 800 y 640) definen el <em>área</em> objetivo del video generado; el tamaño real del cuadro mantiene la relación de aspecto de la imagen de referencia, y los cuadros de conducción se ajustan con barras laterales (letterbox) a ese tamaño. Las entradas que ya están en el tamaño de letterbox objetivo pasan por la preprocesación sin modificaciones, por lo que la preprocesación también puede realizarse por completo fuera de la pipeline.</p> <!--[1--><h2 class="relative group"><a id="diffusers.WanAnimate2ModularPipeline" 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="#diffusers.WanAnimate2ModularPipeline"><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><!---->WanAnimate2ModularPipeline<!----></span></h2><!--]--><!----> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="diffusers.WanAnimate2ModularPipeline"><!----><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">clase</span> <span class="font-medium">diffusers.</span><span class="font-semibold">WanAnimate2ModularPipeline</span></span></h3><!----> <a id="diffusers.WanAnimate2ModularPipeline" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.WanAnimate2ModularPipeline"><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><!----></a> <!--[0--><a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/modular_pipelines/wan_animate_2/modular_pipeline.py#L23" target="_blank"><span>&lt;</span> <span class="hidden md:block mx-0.5 hover:!underline">source</span> <span>></span></a><!--]--></span> <!--[0--><p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span> <!--[--><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">blocks<span class="opacity-60">: diffusers.modular_pipelines.modular_pipeline.ModularPipelineBlocks | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">pretrained_model_name_or_path<span class="opacity-60">: str | os.PathLike | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">components_manager<span class="opacity-60">: diffusers.modular_pipelines.components_manager.ComponentsManager | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">collection<span class="opacity-60">: str | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">workflow<span class="opacity-60">: str | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">modular_config_dict<span class="opacity-60">: dict[str, typing.Any] | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">config_dict<span class="opacity-60">: dict[str, typing.Any] | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">**kwargs<span class="opacity-60"></span></span></span><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>Un ModularPipeline para la animación de personajes de Wan-Animate-2.</p></div> <!--[1--><h2 class="relative group"><a id="diffusers.WanAnimate2DistilledModularPipeline" 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="#diffusers.WanAnimate2DistilledModularPipeline"><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><!---->WanAnimate2DistilledModularPipeline<!----></span></h2><!--]--><!----> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="diffusers.WanAnimate2DistilledModularPipeline"><!----><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">clase</span> <span class="font-medium">diffusers.</span><span class="font-semibold">WanAnimate2DistilledModularPipeline</span></span></h3><!----> <a id="diffusers.WanAnimate2DistilledModularPipeline" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.WanAnimate2DistilledModularPipeline"><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><!----></a> <!--[0--><a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/modular_pipelines/wan_animate_2/modular_pipeline.py#L62" target="_blank"><span>&lt;</span> <span class="hidden md:block mx-0.5 hover:!underline">source</span> <span>></span></a><!--]--></span> <!--[0--><p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span> <!--[--><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">blocks<span class="opacity-60">: diffusers.modular_pipelines.modular_pipeline.ModularPipelineBlocks | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">pretrained_model_name_or_path<span class="opacity-60">: str | os.PathLike | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">components_manager<span class="opacity-60">: diffusers.modular_pipelines.components_manager.ComponentsManager | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">collection<span class="opacity-60">: str | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">workflow<span class="opacity-60">: str | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">modular_config_dict<span class="opacity-60">: dict[str, typing.Any] | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">config_dict<span class="opacity-60">: dict[str, typing.Any] | None = None</span></span></span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">**kwargs<span class="opacity-60"></span></span></span><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>Un ModularPipeline para el modelo Wan-Animate-2 destilado, que muestrea en pocos pasos sin guía libre de clasificador.</p></div> <!--[1--><h2 class="relative group"><a id="diffusers.WanAnimate2Blocks" 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="#diffusers.WanAnimate2Blocks"><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><!---->WanAnimate2Blocks<!----></span></h2><!--]--><!----> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="diffusers.WanAnimate2Blocks"><!----><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">clase</span> <span class="font-medium">diffusers.</span><span class="font-semibold">WanAnimate2Blocks</span></span></h3><!----> <a id="diffusers.WanAnimate2Blocks" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.WanAnimate2Blocks"><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><!----></a> <!--[0--><a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/modular_pipelines/wan_animate_2/modular_blocks_wan_animate_2.py#L252" target="_blank"><span>&lt;</span> <span class="hidden md:block mx-0.5 hover:!underline">source</span> <span>></span></a><!--]--></span> <!--[0--><p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span> <!--[--><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>Bloques de pipeline modulares para la animación de personajes de Wan-Animate-2: una imagen de referencia del personaje y un video de conducción producen un video del personaje siguiendo el movimiento de conducción.</p> <p>Componentes:
text_encoder (<code>UMT5EncoderModel</code>) tokenizer (<code>AutoTokenizer</code>) image_processor (<code>WanAnimate2VideoProcessor</code>)
image_encoder (<code>CLIPVisionModel</code>) video_processor (<code>WanAnimate2VideoProcessor</code>) vae (<code>AutoencoderKLWan</code>)
transformer (<code>WanAnimate2Transformer3DModel</code>) scheduler (<code>SchedulerMixin</code>) guider (<code>ClassifierFreeGuidance</code>)</p> <p>Entradas:
prompt (<code>str</code>):
El prompt o prompts para guiar la generación de imágenes.
negative_prompt (<code>str</code>, <em>opcional</em>):
El prompt o prompts que no deben guiar la generación de imágenes.
prompt_ref (<code>str</code>, <em>opcional</em>, predeterminado a 人物动作的参考视频):
El prompt de referencia para el contexto del video de conducción
max_sequence_length (<code>int</code>, <em>opcional</em>, predeterminado a 512):
Longitud máxima de secuencia para la codificación del prompt.
image (<code>Image | list</code>):
La imagen de referencia que contiene el personaje a animar.
height (<code>int</code>, <em>opcional</em>, predeterminado a 800):
Junto con <code>width</code>, el <em>área</em> objetivo del video generado; la relación de aspecto proviene de <code>image</code>.
Sobrescrito con la altura de cuadro resuelta.
width (<code>int</code>, <em>opcional</em>, predeterminado a 640):
Ver <code>height</code>. Sobrescrito con el ancho de cuadro resuelto.
driving_video (<code>list</code>):
El video de conducción que proporciona el movimiento, en cualquier formato aceptado por <code>VideoProcessor.preprocess_video</code>.
driving_video_fps (<code>float</code>, <em>opcional</em>):
La tasa de cuadros a la que se capturó <code>driving_video</code> — <code>load_video(..., return_fps=True)</code> la informa. Cuando se establece,
los cuadros de conducción se remuestrean desde ella a <code>fps</code>; cuando es <code>None</code>, se usan tal cual.
fps (<code>int</code>, <em>opcional</em>, predeterminado a 24):
La tasa de cuadros a la que el modelo genera
segment_frame_length (<code>int</code>, <em>opcional</em>, predeterminado a 81):
El número de cuadros en cada segmento de inferencia
prev_segment_conditioning_frames (<code>int</code>, <em>opcional</em>, predeterminado a 1):
El número de cuadros de condicionamiento llevados desde el segmento anterior
generator (<code>Generator</code>, <em>opcional</em>):
Generador de Torch para generación determinista.
num_inference_steps (<code>int</code>, <em>opcional</em>, predeterminado a 40):
El número de pasos de desruido.
*<em>denoiser_input_fields (<code>None</code>,</em>opcional<em>):
entradas condicionales del modelo para el desruidador: p. ej. prompt_embeds, negative_prompt_embeds, etc.
output_type (<code>str</code>,</em>opcional*, predeterminado a np):
El tipo de salida de los videos decodificados</p> <p>Salidas:
videos (<code>list</code>):
Los videos generados.</p></div> <!--[1--><h2 class="relative group"><a id="diffusers.WanAnimate2DistilledBlocks" 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="#diffusers.WanAnimate2DistilledBlocks"><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><!---->WanAnimate2DistilledBlocks<!----></span></h2><!--]--><!----> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="diffusers.WanAnimate2DistilledBlocks"><!----><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">clase</span> <span class="font-medium">diffusers.</span><span class="font-semibold">WanAnimate2DistilledBlocks</span></span></h3><!----> <a id="diffusers.WanAnimate2DistilledBlocks" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.WanAnimate2DistilledBlocks"><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><!----></a> <!--[0--><a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/modular_pipelines/wan_animate_2/modular_blocks_wan_animate_2_distilled.py#L254" target="_blank"><span>&lt;</span> <span class="hidden md:block mx-0.5 hover:!underline">source</span> <span>></span></a><!--]--></span> <!--[0--><p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span> <!--[--><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>Bloques de pipeline modulares para la animación de personajes de Wan-Animate-2 destilado, con muestreo en pocos pasos sin guía libre de clasificador.</p> <p>Componentes:
text_encoder (<code>UMT5EncoderModel</code>) tokenizer (<code>AutoTokenizer</code>) image_processor (<code>WanAnimate2VideoProcessor</code>)
image_encoder (<code>CLIPVisionModel</code>) video_processor (<code>WanAnimate2VideoProcessor</code>) vae (<code>AutoencoderKLWan</code>)
transformer (<code>WanAnimate2Transformer3DModel</code>) scheduler (<code>SchedulerMixin</code>) guider (<code>ClassifierFreeGuidance</code>)</p> <p>Entradas:
prompt (<code>str</code>):
El prompt o prompts para guiar la generación de imágenes.
negative_prompt (<code>str</code>, <em>opcional</em>):
El prompt o prompts que no deben guiar la generación de imágenes.
prompt_ref (<code>str</code>, <em>opcional</em>, predeterminado a 人物动作的参考视频):
El prompt de referencia para el contexto del video de conducción
max_sequence_length (<code>int</code>, <em>opcional</em>, predeterminado a 512):
Longitud máxima de secuencia para la codificación del prompt.
image (<code>Image | list</code>):
La imagen de referencia que contiene el personaje a animar.
height (<code>int</code>, <em>opcional</em>, predeterminado a 800):
Junto con <code>width</code>, el <em>área</em> objetivo del video generado; la relación de aspecto proviene de <code>image</code>.
Sobrescrito con la altura de cuadro resuelta.
width (<code>int</code>, <em>opcional</em>, predeterminado a 640):
Ver <code>height</code>. Sobrescrito con el ancho de cuadro resuelto.
driving_video (<code>list</code>):
El video de conducción que proporciona el movimiento, en cualquier formato aceptado por <code>VideoProcessor.preprocess_video</code>.
driving_video_fps (<code>float</code>, <em>opcional</em>):
La tasa de cuadros a la que se capturó <code>driving_video</code> — <code>load_video(..., return_fps=True)</code> la informa. Cuando se establece,
los cuadros de conducción se remuestrean desde ella a <code>fps</code>; cuando es <code>None</code>, se usan tal cual.
fps (<code>int</code>, <em>opcional</em>, predeterminado a 24):
La tasa de cuadros a la que el modelo genera
segment_frame_length (<code>int</code>, <em>opcional</em>, predeterminado a 81):
El número de cuadros en cada segmento de inferencia
prev_segment_conditioning_frames (<code>int</code>, <em>opcional</em>, predeterminado a 1):
El número de cuadros de condicionamiento llevados desde el segmento anterior
generator (<code>Generator</code>, <em>opcional</em>):
Generador de Torch para generación determinista.
num_inference_steps (<code>int</code>, <em>opcional</em>, predeterminado a 10):
El número de pasos de desruido.
*<em>denoiser_input_fields (<code>None</code>,</em>opcional<em>):
entradas condicionales del modelo para el desruidador: p. ej. prompt_embeds, negative_prompt_embeds, etc.
output_type (<code>str</code>,</em>opcional*, predeterminado a np):
El tipo de salida de los videos decodificados</p> <p>Salidas:
videos (<code>list</code>):
Los videos generados.</p></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/wan_animate_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><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
<script>
{
__sveltekit_ywq9g6 = {
base: "/docs/diffusers/v0.43.0/en",
assets: "/docs/diffusers/v0.43.0/en"
};
const element = document.currentScript.parentElement;
Promise.all([
import("/docs/diffusers/v0.43.0/en/_app/immutable/entry/start.1gaXe03k.js"),
import("/docs/diffusers/v0.43.0/en/_app/immutable/entry/app.BwdYRbCn.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 258],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
38.3 kB
·
Xet hash:
f6023324794f892455ae294c63f2c0dac064b1a90c12f2e650983d51b7d17c6e

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