Wan 2.2 S2V 14B
This repository features the Wan2.2-S2V-14B model, designed for audio-driven cinematic video generation. It was introduced in the paper: Wan-S2V: Audio-Driven Cinematic Video Generation
Fuente del modelo
- Tipo
- Other
- Tamaño del archivo
- 484 MB–10,6 GB
- Versión
- vRevision dab4e9c
- Actualizado
- 16 sept 2026
- Publicador
- @Wan-AI
- Descargas
- 10,7 mil
- Parámetros
- 14B
- Fuente
- Hugging Face
Extracto de la fuente
This repository features the Wan2.2-S2V-14B model, designed for audio-driven cinematic video generation. It was introduced in the paper: Wan-S2V: Audio-Driven Cinematic Video Generation
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 30 ago
Artefactos del modelo
9 artefactos
Artefactos del modelo
9 artefactosdiffusion_pytorch_model-00001-of-00004.safetensors
safetensors · 9,28 GB · SHA-256 5fb54febf10b…6d43 · Hugging Face
Descargardiffusion_pytorch_model-00002-of-00004.safetensors
safetensors · 9,21 GB · SHA-256 922928094d8e…6f01 · Hugging Face
Descargardiffusion_pytorch_model-00003-of-00004.safetensors
safetensors · 9,27 GB · SHA-256 017fab8d2845…24fc · Hugging Face
Descargardiffusion_pytorch_model-00004-of-00004.safetensors
safetensors · 2,58 GB · SHA-256 5c194909066b…c6c0 · Hugging Face
Descargarwav2vec2-large-xlsr-53-english/flax_model.msgpack
msgpack · 1,18 GB · SHA-256 0d3842440388…aa40 · Hugging Face
Descargarwav2vec2-large-xlsr-53-english/model.safetensors
safetensors · 1,18 GB · SHA-256 6144f8464c6a…9875 · Hugging Face
Descargarwav2vec2-large-xlsr-53-english/pytorch_model.bin
bin · 1,18 GB · SHA-256 7b7688644eee…29bf · Hugging Face
DescargarExtractos de fuentes
3 extractos
Extractos de fuentes
3 extractos--- license: apache-2.0 pipeline_tag: image-to-video library_name: diffusers language: - es --- # Wan2.2-S2V-14B: Audio-Driven Cinematic Video Generation This repository features the **Wan2.2-S2V-14B** model, designed for audio-driven cinematic video generation. It was introduced in the paper: [**Wan-S2V: Audio-Driven Cinematic Video Generation**](https://huggingface.co/papers/2508.18621) <p align="center"> <img src="assets/logo.png" width="400"/> <p> <p align="center"> 💜 <a href="https://wan.video"><b>Wan Homepage</b></a>    ｜    🖥️ <a href="https://github.com/Wan-Video/Wan2.2">GitHub</a>    |   🤗 <a href="https://huggingface.co/Wan-AI/">Hugging Face Organization</a>   |   🤖 <a href="https://modelscope.cn/organization/Wan-AI">ModelScope Organization</a>   |    📑 <a href="https://huggingface.co/papers/2508.18621">Wan-S2V Paper</a>    |    📑 <a href="https://arxiv.org/abs/2503.20314">Wan2.2 Base Paper</a>    | 🌐 <a href="https://humanaigc.github.io/wan-s2v-webpage">Project Page</a>    |    📑 <a href="https://wan.video/welcome?spm=a2ty_o02.30011076.0.0.6c9ee41eCcluqg">Blog</a>    |    💬 <a href="https://discord.gg/AKNgpMK4Yj">Discord</a>   <br> 📕 <a href="https://alidocs.dingtalk.com/i/nodes/jb9Y4gmKWrx9eo4dCql9LlbYJGXn6lpz">使用指南(中文)</a>   |    📘 <a href="https://alidocs.dingtalk.com/i/nodes/EpGBa2Lm8aZxe5myC99MelA2WgN7R35y">User Guide(English)</a>   |   💬 <a href="https://gw.alicdn.com/imgextra/i2/O1CN01tqjWFi1ByuyehkTSB_!!6000000000015-0-tps-611-1279.jpg">WeChat(微信)</a>   <br> ## Abstract (Wan-S2V Paper) Current state-of-the-art (SOTA) methods for audio-driven character animation demonstrate promising performance for scenarios primarily involving speech and singing. However, they often fall short in more complex film and television productions, which demand sophisticated elements such as nuanced character interactions, realistic body movements, and dynamic camera work. To address this long-standing challenge of achieving film-level character animation, we propose an audio-driven model, which we refere to as Wan-S2V, built upon Wan. Our model achieves significantly enhanced expressiveness and fidelity in cinematic contexts compared to existing approaches. We conducted e...
Source context: 10714 downloads · 464 likes · Pipeline image-to-video · Library diffusers · Repo Wan-AI/Wan2.2-S2V-14B
Source context: 64270 downloads · 448 likes · Pipeline image-to-video · Library diffusers · Repo Wan-AI/Wan2.2-S2V-14B
