Loading video...

Video Failed to Load

Go Home

🚀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...

128,597 views • 1 year ago •via X (Twitter)

31 Comments

Mike's profile picture
Mike1 year ago

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

Emily's profile picture
Emily1 year ago

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

Lincoln 🇿🇦's profile picture
Lincoln 🇿🇦1 year ago

Well Done

rob - comfyui's profile picture
rob - comfyui1 year ago

Curious how this compares to generations with fantasyportrait+multitalk

prince tarlue's profile picture
prince tarlue1 year ago

Did I hear rick?

無限 💀 acc/acc's profile picture
無限 💀 acc/acc1 year ago

Freaking awesome :) Will dig in soon.

Rijn's profile picture
Rijn1 year ago

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

Alex Veremeyenko's profile picture
Alex Veremeyenko1 year ago

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

The90sPope's profile picture
The90sPope1 year ago

This is great, WAN team is not joking around

Hyperstack's profile picture
Hyperstack1 year ago

Massive news for creators everywhere 👏

Tomasz Proshowski's profile picture
Tomasz Proshowski1 year ago

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

Peter Hacks's profile picture
Peter Hacks1 year ago

amazing Wan2.2 S2V🥳

sandrom's profile picture
sandrom1 year ago

@higgsfield_ai can you add s2v? ☺️

〽️ClementeEstropajo's profile picture
〽️ClementeEstropajo1 year ago

Chinese aren't playing, thanks!!

𝐙𝐞𝐧𝐠 💜's profile picture
𝐙𝐞𝐧𝐠 💜1 year ago

Amazing feature!!

David Emechete's profile picture
David Emechete1 year ago

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

Chath Kay's profile picture
Chath Kay1 year ago

Omfg

Alkebulan Angel's profile picture
Alkebulan Angel1 year ago

Wow it's here

Rishav Dash's profile picture
Rishav Dash1 year ago

@wasim_madha

Mr. Ånand's profile picture
Mr. Ånand1 year ago

Wohoo! Awesome

R. Dumas's profile picture
R. Dumas1 year ago

Motion control avancé et consistance longue durée, c’est l’équivalent IA du passage du N&B à la couleur au cinéma ! Curieux de voir comment nos villes et contenus vont se réinventer avec ces outils.

Mykhailo Sorochuk's profile picture
Mykhailo Sorochuk1 year ago

Can't wait to see what creators do with this. Looks like a true game changer for immersive storytelling!

Dave more's profile picture
Dave more1 year ago

We love china

Nikhil's profile picture
Nikhil1 year ago

Wow... This just defined the future of content generation.

MetaDJ's profile picture
MetaDJ1 year ago

Amazing ✨

AK's profile picture
AK1 year ago

Does it work with music?

Naidu A S's profile picture
Naidu A S1 year ago

This is going to be great

RobbyGTV's profile picture
RobbyGTV1 year ago

@AskVenice

Dheepan Ratnam's profile picture
Dheepan Ratnam1 year ago

wow excellent new tool to play with

Arindam Majumder 𝕏's profile picture
Arindam Majumder 𝕏1 year ago

Woah! Amazing🤩🤩

Nora Smith's profile picture
Nora Smith1 year ago

🌇

Related Videos

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.

Kanika

17,726 views • 5 months ago

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,430 views • 1 year ago