Skip navigation
🚀Introducing Wan2.2-S2V — a 14B parameter model designed for film-grade, audio-driven human…
0:00 / 1:04

🚀Introducing Wan2.2-S2V — a 14B parameter model designed for film-grade, audio-driven human…

Wan

@Alibaba_Wan32K followers

Visit on X
1,377 likesDownloadOriginal post

128,597 views

🚀Introducing Wan2.2-S2V — a 14B parameter model designed for film-grade, audio-driven human animation. 🎬Going beyond basic talking heads to deliver professional-level quality for film, TV, and digital content. And it’s open-source! ✨ Key features: 🔹 Long-video dynamic consistency 🔹 Cinema-quality audio-to-video generation 🔹 Advanced motion and environment control via instruction Perfect for filmmakers, content creators, and developers crafting immersive AI-powered stories. Try it now : Github: Project: Hugging Face Demo: Modelscope Demo: Hugging Face Weights: ModelScope Weights:

31 Comments

Comments from the original post on X (Twitter)

  • Mike's profile picture

    @WorldsByMike

    15 second limit? That’s crazy. Can’t wait to give it a whirl.

    8 likes

  • Emily's profile picture

    @IamEmily2050

    Good progress, thank you. Next, please, it is time to scale the model 😭😭😭

    7 likes

  • Lincoln 🇿🇦's profile picture

    @Presidentlin

    Well Done

    2 likes

  • rob - comfyui's profile picture

    @hellorob

    Curious how this compares to generations with fantasyportrait+multitalk

    2 likes

  • prince tarlue's profile picture

    @krashoutPK

    Did I hear rick?

    1 like

  • 無限 💀 acc/acc's profile picture

    @c0nsumption_

    Freaking awesome :) Will dig in soon.

    1 like

  • Rijn's profile picture

    @RijnHartman

    A step in the right direction but seems off with the audio

    1 like

  • Alex Veremeyenko's profile picture

    @alex_verem

    this is a game changer, excited to see how it elevates storytelling in media. can't wait to test it out

    1 like

  • The90sPope's profile picture

    @TheReal90sPope

    This is great, WAN team is not joking around

    1 like

  • Hyperstack's profile picture

    @Hyperstackcloud

    Massive news for creators everywhere 👏

  • Tomasz Proshowski's profile picture

    @TomaszP37544946

    Congratulations 👏👏👏👏 you've been doing a extraordinary marvelous job Thank you

  • Peter Hacks's profile picture

    @gallifreywho123

    amazing Wan2.2 S2V🥳

  • sandrom's profile picture

    @sandrom303

    @higgsfield_ai can you add s2v? ☺️

  • 〽️ClementeEstropajo's profile picture

    @ClemenEstropajo

    Chinese aren't playing, thanks!!

  • 𝐙𝐞𝐧𝐠 💜's profile picture

    @zeng_wt

    Amazing feature!!

  • David Emechete's profile picture

    @Hiswordxray

    Can you do a fight choreography AI model? It would be really great for creating action scenes

  • Chath Kay's profile picture

    @chathkay

    Omfg

  • Alkebulan Angel's profile picture

    @AlkebulanAxwi

    Wow it's here

  • Rishav Dash's profile picture

    @RishavDash1

    @wasim_madha

  • Mr. Ånand's profile picture

    @Astrodevil_

    Wohoo! Awesome