Buckets:

mishig's picture
download
raw
43.3 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;ConsisID&quot;,&quot;local&quot;:&quot;consisid&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Optimasi memori&quot;,&quot;local&quot;:&quot;memory-optimization&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Muat Poin Pemeriksaan Model&quot;,&quot;local&quot;:&quot;load-model-checkpoints&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Teks-ke-Video yang Menjaga Identitas&quot;,&quot;local&quot;:&quot;identity-preserving-text-to-video&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Sumber daya&quot;,&quot;local&quot;:&quot;resources&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ConsisIDPipeline&quot;,&quot;local&quot;:&quot;diffusers.ConsisIDPipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ConsisIDPipelineOutput&quot;,&quot;local&quot;:&quot;diffusers.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput&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/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="{&quot;title&quot;:&quot;ConsisID&quot;,&quot;local&quot;:&quot;consisid&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Memory optimization&quot;,&quot;local&quot;:&quot;memory-optimization&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Load Model Checkpoints&quot;,&quot;local&quot;:&quot;load-model-checkpoints&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Identity-Preserving Text-to-Video&quot;,&quot;local&quot;:&quot;identity-preserving-text-to-video&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Resources&quot;,&quot;local&quot;:&quot;resources&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ConsisIDPipeline&quot;,&quot;local&quot;:&quot;diffusers.ConsisIDPipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;ConsisIDPipelineOutput&quot;,&quot;local&quot;:&quot;diffusers.pipelines.consisid.pipeline_output.ConsisIDPipelineOutput&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="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">Generasi Teks-ke-Video yang Mempertahankan Identitas melalui Dekomposisi Frekuensi</a> dari Peking University &amp; University of Rochester &amp; lainnya, oleh Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyang Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan.</p> <p>Abstrak dari makalah tersebut adalah:</p> <p><em>Generasi teks-ke-video yang mempertahankan identitas (IPT2V) bertujuan untuk membuat video ber-fidelitas tinggi dengan identitas manusia yang konsisten. Ini adalah tugas penting dalam generasi video, tetapi masih menjadi masalah terbuka bagi model generatif. Kertas ini mendorong batas teknis IPT2V dalam dua arah yang belum terselesaikan dalam literatur: (1) pipeline tanpa penyetelan (tuning-free) tanpa penyetelan ulang (finetuning) yang melelahkan untuk setiap kasus, dan (2) skema kontrol berbasis Diffusion Transformer (DiT) yang mempertahankan identitas dan peka terhadap frekuensi. Untuk mencapai tujuan ini, kami mengusulkan <strong>ConsisID</strong>, model IPT2V yang dapat dikendalikan dan berbasis DiT tanpa penyetelan (tuning-free) untuk menjaga <strong>id</strong>entitas manusia tetap <strong>consis</strong>ten dalam video yang dihasilkan. Terinspirasi oleh temuan sebelumnya dalam analisis frekuensi dari transformer visi/difusi, model ini menggunakan sinyal kontrol identitas di domain frekuensi, di mana fitur wajah dapat didekomposisi menjadi fitur global berfrekuensi rendah (misalnya, profil, proporsi) dan fitur intrinsik berfrekuensi tinggi (misalnya, penanda identitas yang tidak terpengaruh oleh perubahan pose). Pertama, dari perspektif frekuensi rendah, kami memperkenalkan ekstraktor wajah global, yang mengkodekan gambar referensi dan titik-titik kunci wajah ke dalam ruang laten, menghasilkan fitur yang diperkaya dengan informasi frekuensi rendah. Fitur-fitur ini kemudian diintegrasikan ke dalam lapisan dangkal jaringan untuk meredakan tantangan pelatihan yang terkait dengan DiT. Kedua, dari perspektif frekuensi tinggi, kami merancang ekstraktor wajah lokal untuk menangkap detail frekuensi tinggi dan menyuntikkannya ke dalam blok transformer, meningkatkan kemampuan model untuk mempertahankan fitur berbutir halus. Untuk memanfaatkan informasi frekuensi untuk pelestarian identitas, kami mengusulkan strategi pelatihan hierarkis, yang mengubah model generasi video pra-dilatih biasa menjadi model IPT2V. Eksperimen ekstensif menunjukkan bahwa skema heuristik peka-frekuensi kami menyediakan solusi kontrol optimal untuk model berbasis DiT. Berkat skema ini, <strong>ConsisID</strong> kami mencapai hasil yang sangat baik dalam menghasilkan video berkualitas tinggi yang mempertahankan identitas, melangkah menuju IPT2V yang lebih efektif. Bobot model ConsisID tersedia secara publik di <a href="https://github.com/PKU-YuanGroup/ConsisID" rel="nofollow">https://github.com/PKU-YuanGroup/ConsisID</a>.</em></p> <blockquote class="tip"><p>Pastikan untuk melihat <a href="../../using-diffusers/schedulers">panduan</a> Schedulers untuk mempelajari cara mengeksplorasi tradeoff antara kecepatan dan kualitas scheduler, serta lihat bagian <a href="../../using-diffusers/loading#reusing-models-in-multiple-pipelines">reuse components across pipelines</a> untuk mempelajari cara memuat komponen yang sama secara efisien ke dalam beberapa pipeline.</p></blockquote> <p>Pipeline ini disumbangkan oleh <a href="https://github.com/SHYuanBest" rel="nofollow">SHYuanBest</a>. Basis kode aslinya dapat ditemukan <a href="https://github.com/PKU-YuanGroup/ConsisID" rel="nofollow">di sini</a>. Bobot aslinya dapat ditemukan di bawah <a href="https://huggingface.co/BestWishYsh" rel="nofollow">hf.co/BestWishYsh</a>.</p> <p>Terdapat dua checkpoint resmi ConsisID untuk text-to-video yang mempertahankan identitas.</p> <table><thead><tr><th align="center">checkpoints</th><th align="center">dtype inferensi yang direkomendasikan</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><!---->Optimasi memori<!----></span></h3><!--]--><!----> <p>ConsisID membutuhkan sekitar 44 GB memori GPU untuk mendekode 49 frame (6 detik video pada 8 FPS) dengan resolusi output 720x480 (W x H), sehingga tidak dapat dijalankan pada GPU konsumen atau Colab T4 tier gratis. Optimasi memori berikut dapat digunakan untuk mengurangi jejak memori. Untuk replikasi, Anda dapat merujuk pada skrip <a href="https://gist.github.com/SHYuanBest/bc4207c36f454f9e969adbb50eaf8258" rel="nofollow">ini</a>.</p> <table><thead><tr><th align="left">Fitur (tumpuk yang sebelumnya)</th><th align="left">Memori Maksimum yang Dialokasikan</th><th align="left">Memori Maksimum yang Dipesan</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><!---->Muat Poin Pemeriksaan Model<!----></span></h2><!--]--><!----> <p>Bobot model mungkin disimpan di subfolder terpisah di Hub atau secara lokal, dalam hal ini, Anda harus menggunakan metode <a href="/docs/diffusers/main/id/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> Disalin</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">&quot;BestWishYsh/ConsisID-preview&quot;</span>, local_dir=<span class="hljs-string">&quot;BestWishYsh/ConsisID-preview&quot;</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">&quot;BestWishYsh/ConsisID-preview&quot;</span>, device=<span class="hljs-string">&quot;cuda&quot;</span>, dtype=torch.bfloat16) <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
<span class="hljs-comment"># Load consisid base model</span>
pipe = ConsisIDPipeline.from_pretrained(<span class="hljs-string">&quot;BestWishYsh/ConsisID-preview&quot;</span>, dtype=torch.bfloat16)
pipe.to(<span class="hljs-string">&quot;cuda&quot;</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><!---->Teks-ke-Video yang Menjaga Identitas<!----></span></h2><!--]--><!----> <p>Untuk teks-ke-video yang mempertahankan identitas, berikan prompt teks dan gambar yang menampilkan wajah dengan jelas (misalnya, lebih baik setengah badan atau seluruh badan). Secara default, ConsisID menghasilkan video 720x480 untuk hasil terbaik.</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> Disalin</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">&quot;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&#x27;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&#x27;s path, adding depth to the scene. The lighting highlights the boy&#x27;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.&quot;</span>
image = <span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/consisid/consisid_input.png?download=true&quot;</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">&quot;cuda&quot;</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">&quot;cuda&quot;</span>).manual_seed(<span class="hljs-number">42</span>))
export_to_video(video.frames[<span class="hljs-number">0</span>], <span class="hljs-string">&quot;output.mp4&quot;</span>, fps=<span class="hljs-number">8</span>)<!----></pre></div><!----> <table><tbody><tr><th style="text-align: center;">Gambar Wajah</th><th style="text-align: center;">Video</th><th style="text-align: center;">Deskripsi</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>Video ini, dengan gaya animasi yang indah dan terukur, menampilkan seorang wanita percaya diri yang menunggang kuda melintasi padang terbuka di hutan yang rimbun. Ekspresinya fokus namun tenang saat ia menyesuaikan topi bertepi lebarnya dengan tangan yang terlatih. Ia mengenakan gaun bohemian yang longgar, yang bergerak anggun mengikuti irama kuda, dengan kain yang mengalir mulus dalam gerakan animasi. Cahaya matahari yang tembus celah pepohonan menyaring ke bawah, menciptakan pola lembut bergaya lukisan di lantai hutan. Posturnya anggun, menunjukkan kontrol dan keanggunan saat ia memandu kuda dengan mudah. Gaya animasi yang lembut dan mengalir ini menambah nuansa mimpi pada adegan, dengan sikap tenang wanita tersebut dan lingkungan yang damai membangkitkan rasa kebebasan dan harmoni.</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>Video tersebut, dengan gaya animasi yang memikat, menampilkan seorang wanita berdiri di tengah hutan bersalju, matanya menyipit dalam konsentrasi saat ia mengulurkan tangannya ke depan. Ia mengenakan jubah biru tua, napasnya terlihat di udara dingin yang digambarkan dengan goresan lembut dan etereal. Senyum samar terukir di bibirnya saat ia memanggil secercah sihir es, mengamati dengan fokus saat pohon-pohon dan tanah di sekitarnya mulai berkilau dan membeku, tertutup kristal es yang halus. Gerak animasi yang mengalir membuat sihir itu terasa hidup, dengan embun beku yang menyebar ke luar dalam pola rumit yang berkilauan. Lingkungan digambarkan dengan nuansa lembut seperti cat air, meningkatkan suasana magis yang seperti mimpi. Suasana keseluruhan tenang namun kuat, dengan udara musim dingin yang sunyi memperkuat keindahan halus dari adegan yang membeku tersebut.</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>Animasi ini menampilkan potret imajinatif seorang penjual balon yang berdiri di tengah angin sepoi-sepoi, digambar dengan goresan kuas lembut dan berkabut yang membangkitkan nuansa hari musim semi yang tenang. Wajahnya dihiasi senyum lembut, matanya sedikit menyipit melawan sinar matahari, sementara beberapa helai rambutnya berkibar tertiup angin. Ia mengenakan kemeja berwarna pastel yang ringan, dan balon-balon di sekelilingnya bergoyang tertiup angin, menambah kesan ceria pada adegan. Latar belakangnya buram secara halus, dengan sentuhan pasar atau taman yang hidup, sehingga memperkuat suasana yang ringan namun penuh kelembutan pada momen tersebut.</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>Video ini menangkap seorang anak laki-laki yang berjalan di sepanjang jalan kota, difilmkan dalam hitam putih menggunakan kamera 35mm klasik. Ekspresinya tampak penuh pikiran, alisnya sedikit berkerut seolah ia tenggelam dalam kontemplasi. Butiran film (film grain) menambah kualitas bertekstur dan abadi pada gambar, membangkitkan rasa nostalgia. Di sekelilingnya, pemandangan kota dipenuhi bangunan bergaya vintage, trotoar berbatu, dan siluet orang-orang yang lewat dengan lembut dan buram, dengan garis luar yang samar dan tidak jelas. Lampu jalan memancarkan cahaya yang lembut, sementara bayangan bermain di sepanjang jalan anak laki-laki tersebut, menambah kedalaman pada adegan. Pencahayaan menyoroti senyum halus anak laki-laki itu, mengisyaratkan momen singkat rasa ingin tahu. Suasana sinematik secara keseluruhan, lengkap dengan estetika still film klasik dan kontras dramatis, memberikan nuansa yang evokatif dan introspektif pada adegan tersebut.</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>Video ini menampilkan bayi yang mengenakan jubah pahlawan super berwarna cerah, berdiri dengan percaya diri dengan kedua tangan terangkat dalam pose yang kuat. Bayi itu memiliki tatapan yang penuh tekad, dengan mata terbuka lebar dan bibir terkatup dalam konsentrasi, seolah-olah siap menghadapi tantangan. Pengaturannya tampak menyenangkan, dengan mainan-mainan berwarna-warni berserakan di sekitar dan karpet lembut di bawah kaki, sementara sinar matahari masuk melalui jendela di dekatnya, menyoroti jubah yang berkibar dan menambah kesan kepahlawanan. Suasana keseluruhan ringan dan menyenangkan, dengan ekspresi bayi yang menangkap campuran antara kepolosan dan upaya keberanian yang menggemaskan, seolah-olah benar-benar siap menyelamatkan hari.</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><!---->Sumber daya<!----></span></h2><!--]--><!----> <p>Pelajari lebih lanjut tentang ConsisID dengan sumber daya berikut.</p> <ul><li>Sebuah <a href="https://www.youtube.com/watch?v=PhlgC-bI5SQ" rel="nofollow">video</a> yang mendemonstrasikan fitur utama ConsisID.</li> <li>Makalah penelitian, <a href="https://hf.co/papers/2411.17440" rel="nofollow">Identity-Preserving Text-to-Video Generation by Frequency Decomposition</a> untuk detail lebih lanjut.</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">kelas</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>&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">*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>Panggil self sebagai fungsi.</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">kelas</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>&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-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">Parameter <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>, atau list[list[PIL.Image.Image]]) —
daftar output video - Dapat berupa daftar bersarang dengan panjang <code>batch_size,</code> di mana setiap sub-daftar berisi
urutan gambar PIL yang telah didenois dengan panjang <code>num_frames.</code> Dapat juga berupa array NumPy atau tensor Torch dengan bentuk
<code>(batch_size, num_frames, channels, height, width)</code>.<!----></span></span></li><!--]--></ul><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>Kelas output untuk pipeline 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:
43.3 kB
·
Xet hash:
22acfe8f5c5c60441c79ad82e3a21b132fe2e173af76ff500011807ae42de36a

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