Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"ConsisID","local":"consisid","sections":[{"title":"Optimización de memoria","local":"memory-optimization","sections":[],"depth":3},{"title":"Cargar puntos de control del modelo","local":"load-model-checkpoints","sections":[],"depth":2},{"title":"Texto a video que preserva la identidad","local":"identity-preserving-text-to-video","sections":[],"depth":2},{"title":"Recursos","local":"resources","sections":[],"depth":2},{"title":"ConsisIDPipeline","local":"diffusers.ConsisIDPipeline","sections":[],"depth":2},{"title":"ConsisIDPipelineOutput","local":"diffusers.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput","sections":[],"depth":2}],"depth":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/158.64L-lLIL.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/bKdwVYpU.js" rel="modulepreload"> | |
| <!--19rjct6--><meta name="hf:doc:metadata" content="{"title":"ConsisID","local":"consisid","sections":[{"title":"Memory optimization","local":"memory-optimization","sections":[],"depth":3},{"title":"Load Model Checkpoints","local":"load-model-checkpoints","sections":[],"depth":2},{"title":"Identity-Preserving Text-to-Video","local":"identity-preserving-text-to-video","sections":[],"depth":2},{"title":"Resources","local":"resources","sections":[],"depth":2},{"title":"ConsisIDPipeline","local":"diffusers.ConsisIDPipeline","sections":[],"depth":2},{"title":"ConsisIDPipelineOutput","local":"diffusers.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput","sections":[],"depth":2}],"depth":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="consisid" 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="#consisid"><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><!---->ConsisID<!----></span></h1><!--]--><!----> <div class="flex flex-wrap space-x-1"><img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/></div> <p><a href="https://huggingface.co/papers/2411.17440" rel="nofollow">Generación de texto a video que preserva la identidad mediante descomposición de frecuencia</a> de la Universidad de Pekín & la Universidad de Rochester & etc., por Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyang Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan.</p> <p>El resumen del artículo es:</p> <p><em>La generación de texto a video que preserva la identidad (IPT2V) tiene como objetivo crear videos de alta fidelidad con una identidad humana consistente. Es una tarea importante en la generación de video, pero sigue siendo un problema abierto para los modelos generativos. Este artículo impulsa la frontera técnica de IPT2V en dos direcciones que no han sido resueltas en la literatura: (1) un pipeline sin ajuste (tuning-free) que evita el tedioso ajuste fino caso por caso, y (2) un esquema de control basado en Diffusion Transformer (DiT) que preserva la identidad y es consciente de la frecuencia. Para lograr estos objetivos, proponemos <strong>ConsisID</strong>, un modelo controlable IPT2V basado en DiT y sin ajuste (tuning-free) para mantener la <strong>id</strong>entidad humana <strong>consis</strong>tente en el video generado. Inspirado en hallazgos previos en el análisis de frecuencias de transformers de visión/difusión, emplea señales de control de identidad en el dominio de la frecuencia, donde las características faciales pueden descomponerse en características globales de baja frecuencia (p. ej., perfil, proporciones) y características intrínsecas de alta frecuencia (p. ej., marcadores de identidad que permanecen sin afectación por cambios de pose). Primero, desde una perspectiva de baja frecuencia, introducimos un extractor facial global, que codifica la imagen de referencia y los puntos clave faciales en un espacio latente, generando características enriquecidas con información de baja frecuencia. Estas características se integran luego en las capas superficiales de la red para aliviar los desafíos de entrenamiento asociados con DiT. Segundo, desde una perspectiva de alta frecuencia, diseñamos un extractor facial local para capturar detalles de alta frecuencia e inyectarlos en los bloques del transformer, mejorando la capacidad del modelo para preservar características de grano fino. Para aprovechar la información de frecuencia para la preservación de la identidad, proponemos una estrategia de entrenamiento jerárquica, transformando un modelo de generación de video preentrenado estándar en un modelo IPT2V. Experimentos extensos demuestran que nuestro esquema heurístico consciente de la frecuencia proporciona una solución de control óptima para modelos basados en DiT. Gracias a este esquema, nuestro <strong>ConsisID</strong> logra excelentes resultados en la generación de videos de alta calidad que preservan la identidad, dando pasos hacia un IPT2V más efectivo. El peso del modelo de ConsID está disponible públicamente en <a href="https://github.com/PKU-YuanGroup/ConsisID" rel="nofollow">https://github.com/PKU-YuanGroup/ConsisID</a>.</em></p> <blockquote class="tip"><p>Asegúrate de consultar la <a href="../../using-diffusers/schedulers">guía de Schedulers</a> para aprender a explorar el equilibrio entre la velocidad y la calidad del scheduler, y consulta la sección <a href="../../using-diffusers/loading#reusing-models-in-multiple-pipelines">reutilizar componentes entre pipelines</a> para aprender a cargar eficientemente los mismos componentes en múltiples pipelines.</p></blockquote> <p>Este pipeline fue aportado por <a href="https://github.com/SHYuanBest" rel="nofollow">SHYuanBest</a>. La base de código original se puede encontrar <a href="https://github.com/PKU-YuanGroup/ConsisID" rel="nofollow">aquí</a>. Los pesos originales se pueden encontrar en <a href="https://huggingface.co/BestWishYsh" rel="nofollow">hf.co/BestWishYsh</a>.</p> <p>Hay dos puntos de control oficiales de ConsisID para la generación de texto a video que preserva la identidad.</p> <table><thead><tr><th align="center">puntos de control</th><th align="center">dtype de inferencia recomendado</th></tr></thead><tbody><tr><td align="center"><a href="https://huggingface.co/BestWishYsh/ConsisID-preview" rel="nofollow"><code>BestWishYsh/ConsisID-preview</code></a></td><td align="center">torch.bfloat16</td></tr><tr><td align="center"><a href="https://huggingface.co/BestWishYsh/ConsisID-preview" rel="nofollow"><code>BestWishYsh/ConsisID-1.5</code></a></td><td align="center">torch.bfloat16</td></tr></tbody></table> <!--[2--><h3 class="relative group"><a id="memory-optimization" 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="#memory-optimization"><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><!---->Optimización de memoria<!----></span></h3><!--]--><!----> <p>ConsisID requiere aproximadamente 44 GB de memoria de GPU para decodificar 49 fotogramas (6 segundos de video a 8 FPS) con una resolución de salida de 720x480 (W x H), lo que impide su ejecución en GPUs de consumo o en T4 de Colab de nivel gratuito. Se pueden utilizar las siguientes optimizaciones de memoria para reducir la huella de memoria. Para la replicación, puede consultar este <a href="https://gist.github.com/SHYuanBest/bc4207c36f454f9e969adbb50eaf8258" rel="nofollow">script</a>.</p> <table><thead><tr><th align="left">Característica (superponer la anterior)</th><th align="left">Memoria máxima asignada</th><th align="left">Memoria máxima reservada</th></tr></thead><tbody><tr><td align="left">-</td><td align="left">37 GB</td><td align="left">44 GB</td></tr><tr><td align="left">enable_model_cpu_offload</td><td align="left">22 GB</td><td align="left">25 GB</td></tr><tr><td align="left">enable_sequential_cpu_offload</td><td align="left">16 GB</td><td align="left">22 GB</td></tr><tr><td align="left">vae.enable_slicing</td><td align="left">16 GB</td><td align="left">22 GB</td></tr><tr><td align="left">vae.enable_tiling</td><td align="left">5 GB</td><td align="left">7 GB</td></tr></tbody></table> <!--[1--><h2 class="relative group"><a id="load-model-checkpoints" 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="#load-model-checkpoints"><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><!---->Cargar puntos de control del modelo<!----></span></h2><!--]--><!----> <p>Los pesos del modelo pueden estar almacenados en subcarpetas separadas en el Hub o localmente, en cuyo caso, debe utilizar el método <a href="/docs/diffusers/main/es/api/pipelines/overview#diffusers.DiffusionPipeline.from_pretrained">from_pretrained()</a>.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copiado</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-comment"># !pip install consisid_eva_clip insightface facexlib</span> | |
| <span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ConsisIDPipeline | |
| <span class="hljs-keyword">from</span> diffusers.pipelines.consisid.consisid_utils <span class="hljs-keyword">import</span> prepare_face_models, process_face_embeddings_infer | |
| <span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> snapshot_download | |
| <span class="hljs-comment"># Download ckpts</span> | |
| snapshot_download(repo_id=<span class="hljs-string">"BestWishYsh/ConsisID-preview"</span>, local_dir=<span class="hljs-string">"BestWishYsh/ConsisID-preview"</span>) | |
| <span class="hljs-comment"># Load face helper model to preprocess input face image</span> | |
| face_helper_1, face_helper_2, face_clip_model, face_main_model, eva_transform_mean, eva_transform_std = prepare_face_models(<span class="hljs-string">"BestWishYsh/ConsisID-preview"</span>, device=<span class="hljs-string">"cuda"</span>, dtype=torch.bfloat16) <span class="hljs-comment"># or "mps", "xpu", "cpu"</span> | |
| <span class="hljs-comment"># Load consisid base model</span> | |
| pipe = ConsisIDPipeline.from_pretrained(<span class="hljs-string">"BestWishYsh/ConsisID-preview"</span>, dtype=torch.bfloat16) | |
| pipe.to(<span class="hljs-string">"cuda"</span>)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="identity-preserving-text-to-video" 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="#identity-preserving-text-to-video"><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><!---->Texto a video que preserva la identidad<!----></span></h2><!--]--><!----> <p>Para la generación de texto a video que preserva la identidad, pase un prompt de texto y una imagen que contenga un rostro claro (por ejemplo, preferiblemente de medio cuerpo o cuerpo completo). De forma predeterminada, ConsisID genera un video de 720x480 para obtener los mejores resultados.</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">from</span> diffusers.utils <span class="hljs-keyword">import</span> export_to_video | |
| prompt = <span class="hljs-string">"The video captures a boy walking along a city street, filmed in black and white on a classic 35mm camera. His expression is thoughtful, his brow slightly furrowed as if he's lost in contemplation. The film grain adds a textured, timeless quality to the image, evoking a sense of nostalgia. Around him, the cityscape is filled with vintage buildings, cobblestone sidewalks, and softly blurred figures passing by, their outlines faint and indistinct. Streetlights cast a gentle glow, while shadows play across the boy's path, adding depth to the scene. The lighting highlights the boy's subtle smile, hinting at a fleeting moment of curiosity. The overall cinematic atmosphere, complete with classic film still aesthetics and dramatic contrasts, gives the scene an evocative and introspective feel."</span> | |
| image = <span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_input.png?download=true"</span> | |
| id_cond, id_vit_hidden, image, face_kps = process_face_embeddings_infer(face_helper_1, face_clip_model, face_helper_2, eva_transform_mean, eva_transform_std, face_main_model, <span class="hljs-string">"cuda"</span>, torch.bfloat16, image, is_align_face=<span class="hljs-literal">True</span>) | |
| video = pipe(image=image, prompt=prompt, num_inference_steps=<span class="hljs-number">50</span>, guidance_scale=<span class="hljs-number">6.0</span>, use_dynamic_cfg=<span class="hljs-literal">False</span>, id_vit_hidden=id_vit_hidden, id_cond=id_cond, kps_cond=face_kps, generator=torch.Generator(<span class="hljs-string">"cuda"</span>).manual_seed(<span class="hljs-number">42</span>)) | |
| export_to_video(video.frames[<span class="hljs-number">0</span>], <span class="hljs-string">"output.mp4"</span>, fps=<span class="hljs-number">8</span>)<!----></pre></div><!----> <table><tbody><tr><th style="text-align: center;">Imagen facial</th><th style="text-align: center;">Video</th><th style="text-align: center;">Descripción</th></tr><tr><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_image_0.png?download=true" style="height: auto; width: 600px;"/></td><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_output_0.gif?download=true" style="height: auto; width: 2000px;"/></td><td>El video, en un estilo animado bellamente elaborado, muestra a una mujer segura de sí misma montando a caballo a través de un claro boscoso y exuberante. Su expresión es concentrada pero serena mientras ajusta su sombrero de ala ancha con una mano experta. Viste un vestido bohemio y fluido, que se mueve con gracia al ritmo del caballo, con la tela fluyendo de manera fluida en el movimiento animado. La luz solar moteada se filtra a través de los árboles, proyectando patrones suaves y pictóricos en el suelo del bosque. Su postura es elegante, mostrando tanto control como elegancia mientras guía al caballo con facilidad. El estilo suave y fluido de la animación añade una calidad onírica a la escena, con la actitud serena de la mujer y el entorno pacífico evocando una sensación de libertad y armonía.</td></tr><tr><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_image_1.png?download=true" style="height: auto; width: 600px;"/></td><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_output_1.gif?download=true" style="height: auto; width: 2000px;"/></td><td>El video, en un estilo animado cautivador, muestra a una mujer de pie en el centro de un bosque nevado, con los ojos entrecerrados en concentración mientras extiende la mano hacia adelante. Lleva un manto azul oscuro, su aliento es visible en el aire frío, que se representa con trazos suaves y etéreos. Una leve sonrisa se dibuja en sus labios mientras invoca un destello de magia de hielo, observando con enfoque cómo los árboles y el suelo circundantes comienzan a brillar y congelarse, cubiertos de delicados cristales de hielo. El movimiento fluido de la animación da vida a la magia, con la escarcha extendiéndose hacia afuera en patrones intrincados y brillantes. El entorno está pintado con tonos suaves, similares a la acuarela, lo que realza la atmósfera mágica y onírica. El ambiente general es sereno pero poderoso, con el aire invernal silencioso amplificando la delicada belleza de la escena congelada.</td></tr><tr><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_image_2.png?download=true" style="height: auto; width: 600px;"/></td><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_output_2.gif?download=true" style="height: auto; width: 2000px;"/></td><td>La animación presenta un retrato lúdico de un vendedor de globos de pie en una brisa suave, capturado con pinceladas suaves y difusas que evocan la sensación de una serena primavera. Su rostro está enmarcado por una sonrisa amable, sus ojos entrecerrados ligeramente contra el sol, mientras algunos mechones de cabello ondean con el viento. Viste una camisa ligera de color pastel, y los globos a su alrededor se mecen con el viento, añadiendo un sentido de juego a la escena. El fondo se difumina suavemente, con indicios de un vibrante mercado o parque, realzando el ambiente ligero, pero tierno, del momento.</td></tr><tr><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_image_3.png?download=true" style="height: auto; width: 600px;"/></td><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_output_3.gif?download=true" style="height: auto; width: 2000px;"/></td><td>El video captura a un niño caminando por una calle de la ciudad, filmado en blanco y negro con una cámara clásica de 35 mm. Su expresión es pensativa, con el ceño ligeramente fruncido, como si estuviera absorto en la contemplación. El grano de la película añade una calidad texturizada y atemporal a la imagen, evocando una sensación de nostalgia. A su alrededor, el paisaje urbano está lleno de edificios vintage, aceras de adoquines y figuras suavemente desenfocadas que pasan, con contornos tenues e imprecisos. Las farolas proyectan un resplandor suave, mientras las sombras juegan a lo largo del camino del niño, añadiendo profundidad a la escena. La iluminación resalta la sutil sonrisa del niño, insinuando un fugaz momento de curiosidad. La atmósfera cinematográfica general, completa con la estética de fotogramas de cine clásico y contrastes dramáticos, le otorga a la escena un tono evocador e introspectivo.</td></tr><tr><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_image_4.png?download=true" style="height: auto; width: 600px;"/></td><td><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_output_4.gif?download=true" style="height: auto; width: 2000px;"/></td><td>El video muestra a un bebé con una capa de superhéroe de colores vivos, de pie con confianza y los brazos levantados en una pose poderosa. El bebé tiene una expresión decidida, con los ojos muy abiertos y los labios apretados en concentración, como si estuviera listo para aceptar un desafío. El entorno parece juguetón, con juguetes de colores esparcidos por todas partes y una alfombra suave bajo sus pies, mientras la luz del sol entra por una ventana cercana, destacando la capa que ondea y añadiendo a la impresión de heroísmo. La atmósfera general es ligera y divertida, con las expresiones del bebé capturando una mezcla de inocencia y un adorable intento de valentía, como si realmente estuviera listo para salvar el día.</td></tr></tbody></table> <!--[1--><h2 class="relative group"><a id="resources" 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="#resources"><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><!---->Recursos<!----></span></h2><!--]--><!----> <p>Obtenga más información sobre ConsisID con los siguientes recursos.</p> <ul><li>Un <a href="https://www.youtube.com/watch?v=PhlgC-bI5SQ" rel="nofollow">video</a> que demuestra las funciones principales de ConsisID.</li> <li>El artículo de investigación, <a href="https://hf.co/papers/2411.17440" rel="nofollow">Identity-Preserving Text-to-Video Generation by Frequency Decomposition</a>, para más detalles.</li></ul> <!--[1--><h2 class="relative group"><a id="diffusers.ConsisIDPipeline" 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.ConsisIDPipeline"><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><!---->ConsisIDPipeline<!----></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.ConsisIDPipeline"><!----><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">ConsisIDPipeline</span></span></h3><!----> <a id="diffusers.ConsisIDPipeline" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.ConsisIDPipeline"><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/utils/dummy_torch_and_transformers_and_opencv_objects.py#L5" target="_blank"><span><</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">*args<span class="opacity-60"></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><!----> <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.ConsisIDPipeline.__call__"><!----><h4 class="!m-0"><span class="flex-1 rounded-xl py-0.5 break-all bg-gradient-to-r from-blue-50/60 to-white dark:from-gray-900 dark:to-gray-950 text-blue-700 dark:text-blue-300 font-medium px-2"><svg width="1em" height="1em" viewBox="0 0 32 33" class="mr-1 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg"><path d="M5.80566 18.3545C4.90766 17.4565 4.90766 16.0005 5.80566 15.1025L14.3768 6.53142C15.2748 5.63342 16.7307 5.63342 17.6287 6.53142L26.1999 15.1025C27.0979 16.0005 27.0979 17.4565 26.1999 18.3545L17.6287 26.9256C16.7307 27.8236 15.2748 27.8236 14.3768 26.9256L5.80566 18.3545Z" fill="currentColor" fill-opacity="0.25"/><path fill-rule="evenodd" clip-rule="evenodd" d="M16.4801 13.9619C16.4801 12.9761 16.7467 12.5436 16.9443 12.3296C17.1764 12.078 17.5731 11.8517 18.2275 11.707C18.8821 11.5623 19.638 11.5342 20.4038 11.5582C20.7804 11.57 21.1341 11.5932 21.4719 11.6156L21.5263 11.6193C21.8195 11.6389 22.1626 11.6618 22.4429 11.6618V7.40825C22.3209 7.40825 22.1219 7.39596 21.7544 7.37149C21.4202 7.34925 20.9976 7.32115 20.5371 7.30672C19.6286 7.27824 18.4672 7.29779 17.3093 7.55377C16.1512 7.8098 14.8404 8.33724 13.8181 9.4452C12.7612 10.5907 12.2266 12.1236 12.2266 13.9619V15.0127H10.6836V19.2662H12.2266V26.6332H16.4801V19.2662H20.3394V15.0127H16.4801V13.9619Z" fill="currentColor"/></svg>__call__</span></h4><!----> <a id="diffusers.ConsisIDPipeline.__call__" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.ConsisIDPipeline.__call__"><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> <!--[-1--><!--]--></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">*args<span class="opacity-60"></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>Llamar a self como una función.</p></div></div> <!--[1--><h2 class="relative group"><a id="diffusers.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput" 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.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput"><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><!---->ConsisIDPipelineOutput<!----></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.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput"><!----><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.pipelines.consisid.pipeline_output.</span><span class="font-semibold">ConsisIDPipelineOutput</span></span></h3><!----> <a id="diffusers.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput"><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/pipelines/consisid/pipeline_output.py#L9" target="_blank"><span><</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-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">frames<span class="opacity-60">: Tensor</span></span></span><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[0--><p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800">Parámetros <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p> <ul class="px-2"><!--[--><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput.frames" class="header-link block pr-0.5 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.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput.frames"><span><svg class="text-smd" 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><!----><strong>frames</strong> (<code>torch.Tensor</code>, <code>np.ndarray</code> o list[list[PIL.Image.Image]]) — | |
| lista de salidas de video. Puede ser una lista anidada de longitud <code>batch_size,</code> donde cada sublista contiene | |
| secuencias de imágenes PIL desruidas de longitud <code>num_frames.</code> También puede ser un array de NumPy o un tensor de Torch de forma | |
| <code>(batch_size, num_frames, channels, height, width)</code>.<!----></span></span></li><!--]--></ul><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>Clase de salida para las tuberías de ConsisID.</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/consisid.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, 158], | |
| data: [null,null], | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 43.7 kB
- Xet hash:
- 4c40cc64aba3a0b6bd7bb6c69e7d9d64b5ef0098f8c38cdbf7f88aa9d82a9e7f
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.