Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /main /fr /api /pipelines /wan_animate_2.html
mishig's picture
mishig
download
raw
38.5 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/main/en/_app/immutable/entry/start.D3LnKZ4R.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/BF9UNEM9.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DPnyVmXs.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/entry/app.C0rBoMxR.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DSGUT_OW.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/C045MWWx.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.DTZsP_3B.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/IaDvMxLQ.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/nodes/258.DUKYyN3T.js" rel="modulepreload">
<link href="/docs/diffusers/main/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/main/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> de l’équipe Alibaba Wan anime une image de personnage de référence avec le mouvement d’une vidéo pilote. La vidéo pilote est traitée par segments de longueur fixe : chaque segment exécute un passage d’extraction de référence qui met en cache les K/V du segment pilote dans chaque couche du transformer, effectue le débruitage par rapport à ce cache et est décodé dans la boucle, car le segment suivant est conditionné par les trames de fin décodées du segment précédent.</p> <p>Deux préréglages sont disponibles : le point de contrôle de base effectue l'échantillonnage avec un guidage sans classifieur, tandis que le point de contrôle distillé effectue l'échantillonnage en quelques étapes sans celui-ci (son guideur est fixé à <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> Copié</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>Pour le point de contrôle distillé, chargez <code>Wan-AI/Wan2.2-Animate-2-14B-Distilled-Diffusers</code> de la même manière — rien d’autre ne change. Chaque préréglage porte ses propres valeurs par défaut d’échantillonnage (40 étapes pour le point de contrôle de base, 10 pour le distillé), et aucun argument <code>guidance_scale</code> n’existe nulle part : le guidage est géré par le composant guider du pipeline (guidage sans classifieur à 3.0 pour le préréglage de base, désactivé pour le distillé).</p> <p><code>height</code> et <code>width</code> (valeurs par défaut 800 et 640) définissent la <em>surface</em> cible de la vidéo générée ; la taille réelle des images conserve le ratio d’aspect de l’image de référence, et les images de pilotage sont encadrées (letterbox) en conséquence. Les entrées qui correspondent déjà à la taille de letterbox cible passent à travers la prétraitement sans modification, ce qui permet également d’effectuer la prétraitement entièrement en dehors du 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">classe</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/main/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 pour l'animation de personnages 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">classe</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/main/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 pour le modèle distillé Wan-Animate-2, qui effectue l'échantillonnage en peu d'étapes sans guidage sans classifieur.</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">classe</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/main/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>Blocs de pipeline modulaires pour l'animation de personnages Wan-Animate-2 : une image de référence du personnage et une vidéo de pilotage produisent une vidéo du personnage suivant le mouvement de pilotage.</p> <p>Composants :
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>Entrées :
prompt (<code>str</code>) :
Le prompt ou les prompts pour guider la génération d'image.
negative_prompt (<code>str</code>, <em>facultatif</em>) :
Le prompt ou les prompts à ne pas utiliser pour guider la génération d'image.
prompt_ref (<code>str</code>, <em>facultatif</em>, par défaut 人物动作的参考视频) :
Le prompt de référence pour le contexte de la vidéo de pilotage
max_sequence_length (<code>int</code>, <em>facultatif</em>, par défaut 512) :
Longueur de séquence maximale pour l'encodage du prompt.
image (<code>Image | list</code>) :
L'image de référence contenant le personnage à animer.
height (<code>int</code>, <em>facultatif</em>, par défaut 800) :
Avec <code>width</code>, la <em>surface</em> cible de la vidéo générée ; le ratio d'aspect provient de <code>image</code>.
Remplacée par la hauteur de frame résolue.
width (<code>int</code>, <em>facultatif</em>, par défaut 640) :
Voir <code>height</code>. Remplacée par la largeur de frame résolue.
driving_video (<code>list</code>) :
La vidéo de pilotage qui fournit le mouvement, dans n'importe quel format accepté par <code>VideoProcessor.preprocess_video</code>.
driving_video_fps (<code>float</code>, <em>facultatif</em>) :
Le taux de frames auquel <code>driving_video</code> a été capturé — <code>load_video(..., return_fps=True)</code> le signale. Lorsqu'il est défini,
les frames de pilotage sont rééchantillonnées à partir de celui-ci vers <code>fps</code> ; lorsqu'il est <code>None</code>, elles sont utilisées telles quelles.
fps (<code>int</code>, <em>facultatif</em>, par défaut 24) :
Le taux de frames auquel le modèle génère
segment_frame_length (<code>int</code>, <em>facultatif</em>, par défaut 81) :
Le nombre de frames dans chaque segment d'inférence
prev_segment_conditioning_frames (<code>int</code>, <em>facultatif</em>, par défaut 1) :
Le nombre de frames de conditionnement repris du segment précédent
generator (<code>Generator</code>, <em>facultatif</em>) :
Générateur Torch pour une génération déterministe.
num_inference_steps (<code>int</code>, <em>facultatif</em>, par défaut 40) :
Le nombre d'étapes de débruitage.
*<em>denoiser_input_fields (<code>None</code>,</em>facultatif<em>) :
entrées conditionnelles du modèle pour le débruiteur : par exemple prompt_embeds, negative_prompt_embeds, etc.
output_type (<code>str</code>,</em>facultatif*, par défaut np) :
Le type de sortie des vidéos décodées</p> <p>Sorties :
vidéos (<code>list</code>) :
Les vidéos générées.</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">classe</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/main/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>Blocs de pipeline modulaires pour l'animation de personnages Wan-Animate-2 distillés, avec un échantillonnage en peu d'étapes sans guidage sans classifieur.</p> <p>Composants :
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>Entrées :
prompt (<code>str</code>) :
Le prompt ou les prompts pour guider la génération d'image.
negative_prompt (<code>str</code>, <em>facultatif</em>) :
Le prompt ou les prompts à ne pas utiliser pour guider la génération d'image.
prompt_ref (<code>str</code>, <em>facultatif</em>, par défaut 人物动作的参考视频) :
Le prompt de référence pour le contexte de la vidéo de pilotage
max_sequence_length (<code>int</code>, <em>facultatif</em>, par défaut 512) :
Longueur de séquence maximale pour l'encodage du prompt.
image (<code>Image | list</code>) :
L'image de référence contenant le personnage à animer.
height (<code>int</code>, <em>facultatif</em>, par défaut 800) :
Avec <code>width</code>, la <em>surface</em> cible de la vidéo générée ; le ratio d'aspect provient de <code>image</code>.
Remplacée par la hauteur de frame résolue.
width (<code>int</code>, <em>facultatif</em>, par défaut 640) :
Voir <code>height</code>. Remplacée par la largeur de frame résolue.
driving_video (<code>list</code>) :
La vidéo de pilotage qui fournit le mouvement, dans n'importe quel format accepté par <code>VideoProcessor.preprocess_video</code>.
driving_video_fps (<code>float</code>, <em>facultatif</em>) :
Le taux de frames auquel <code>driving_video</code> a été capturé — <code>load_video(..., return_fps=True)</code> le signale. Lorsqu'il est défini,
les frames de pilotage sont rééchantillonnées à partir de celui-ci vers <code>fps</code> ; lorsqu'il est <code>None</code>, elles sont utilisées telles quelles.
fps (<code>int</code>, <em>facultatif</em>, par défaut 24) :
Le taux de frames auquel le modèle génère
segment_frame_length (<code>int</code>, <em>facultatif</em>, par défaut 81) :
Le nombre de frames dans chaque segment d'inférence
prev_segment_conditioning_frames (<code>int</code>, <em>facultatif</em>, par défaut 1) :
Le nombre de frames de conditionnement repris du segment précédent
generator (<code>Generator</code>, <em>facultatif</em>) :
Générateur Torch pour une génération déterministe.
num_inference_steps (<code>int</code>, <em>facultatif</em>, par défaut 10) :
Le nombre d'étapes de débruitage.
*<em>denoiser_input_fields (<code>None</code>,</em>facultatif<em>) :
entrées conditionnelles du modèle pour le débruiteur : par exemple prompt_embeds, negative_prompt_embeds, etc.
output_type (<code>str</code>,</em>facultatif*, par défaut np) :
Le type de sortie des vidéos décodées</p> <p>Sorties :
vidéos (<code>list</code>) :
Les vidéos générées.</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_g37pnb = {
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.D3LnKZ4R.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.C0rBoMxR.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 258],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
38.5 kB
·
Xet hash:
1c49d1712e3f19773758739c176cc5f271916f032322d4564ef18f4aada62943

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