By using this website, you agree to our Privacy Policy and Terms of Use.
Accept
Craftium.AICraftium.AICraftium.AI
  • Home
  • News
  • Knowledge base
  • Catalog
  • Blog
Font ResizerAa
Craftium.AICraftium.AI
Font ResizerAa
Пошук
  • Home
  • News
  • Catalog
  • Collections
  • Blog
Follow US
  • Terms of Use
  • Privacy Policy
  • Copyright
  • Feedback
© 2024-2026 Craftium.AI.

Alibaba introduced Live Avatar for creating interactive avatars online

The new system allows communication with virtual characters in real-time and supports high frame rate video streaming

Eleni Karasidi
Eleni Karasidi
Published: 09.12.2025
News
358 Views
Frame from generated video
Frame from generated video
SHARE

The company Alibaba presented the Live Avatar technology for creating interactive avatars in real-time. It is based on a diffusion AI model with 14 billion parameters and supports streaming video generation at 20 frames per second. Live Avatar requires five H800 graphics processors, which provide four-stage sampling.

Users can interact with avatars through microphones and cameras, communicating in real-time. Possible use cases include live online broadcasts, interactive games, educational platforms, and the creation of virtual companions.

Читайте також

Illustrative image
Seedance 2.0 creates a wave of celebrity videos online
Alibaba released Qwen 3.5 for application automation
Google updated Veo 3.1 for creating videos from images

The streaming feature allows Live Avatar to be used for various types of interactive videos and communication. The technology opens up new possibilities for creating personalized experiences online.

Currently, powerful equipment is required to launch Live Avatar, but Alibaba plans further optimization. The project is available on GitHub for developers who want to try the new technology.

Google Vids received an update with realistic AI avatars for videos
Alibaba introduced the open model Qwen-Image 2512 for image generation
Alibaba released Qwen-Image-Layered for layered image generation
Alibaba Model Can Clone Voice from 3 Seconds of Audio
Adobe Firefly receives a text-based video editor and new AI models
TAGGED:AI avatarsAlibabaVideo generation
Leave a Comment

Leave a Reply Cancel reply

Follow us

XFollow
YoutubeSubscribe
TelegramFollow
MediumFollow

Popular News

Читайте також

Frame of video generated in Runway Gen-4
News

Runway presented five new features for AI video models

14.12.2025
Illustrative image
News

Disney invests a billion in OpenAI to create videos with characters

12.12.2025
Z-Image-Turbo
News

Alibaba released the lightweight Z-Image-Turbo model for uncensored image generation

08.12.2025

Craftium AI is a team that closely follows the development of generative AI, applies it in their creative work, and eagerly shares their own discoveries.

Navigation

  • News
  • Reviews
  • Collections
  • Blog

Useful

  • Terms of Use
  • Privacy Policy
  • Copyright
  • Feedback

Subscribe for AI news, tips, and guides to ignite creativity and enhance productivity.

By subscribing, you accept our Privacy Policy and Terms of Use.

Craftium.AICraftium.AI
Follow US
© 2024-2026 Craftium.AI
Subscribe
Level Up with AI!
Get inspired with impactful news, smart tips and creative guides delivered directly to your inbox.

By subscribing, you accept our Privacy Policy and Terms of Use.

Welcome Back!

Sign in to your account

Username or Email Address
Password

Lost your password?