Skip to content
@TaoLiveAIGC

TaoLiveAIGC

TaoLiveAIGC Team from Taobao, Alibaba.

🍑 TaoLiveAIGC Team

Taobao & Tmall Group

We are the TaoLiveAIGC Team at Taobao & Tmall, Alibaba Group, building next-generation digital humans for live commerce. Our work spans speech, LLMs, video generation, and multimodal intelligence, enabling natural and real-time interaction at scale.

💻 Research Projects

🎙️ TTS

  • Qwen3-TTS-TBLive: Live-Streaming Domain-adaption Built on Qwen3-TTS-1.7B Base model
    Project Page Hugging Face

🧠 Large Language Model

🎥 Video Generation

  • 🚀TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation
    arXiv Project Page Hugging Face GitHub Stars

  • 🚀TaoMate-FVSR: Audio-Guided Facial Video Restoration
    arXiv Project Page Hugging Face GitHub Stars

  • 🚀TaoMate-H3: TaoMate training with MiniMax H3. Streaming video generation with 3-step LoRA.
    Hugging Face ModelScope GitHub Stars

    • 🤩2026/11/10: We introduce the first streaming Ref2AV model, TaoMate-R1. Image and video references guide three-step generation of video and sound together. arXiv
    • 🤩2026/10/15: We release the first streaming FL2AV model. Have fun! ❤️
    • 🤩2026/09/08: We first migrate MiniMax H3 to TaoMate (T2AV) for streaming, with the complete streaming FL2AV and Ref2AV on the way, please stay tuned.
  • TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation
    arXiv Project Page Hugging Face GitHub Stars

  • TBDub: Production-Oriented Visual Dubbing
    arXiv Project Page GitHub Stars Hugging Face License

  • 🚀AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars
    arXiv Hugging Face GitHub Stars

  • CoInteract: Spatially-Structured Co-Generation for Interactive Human-Object Video Synthesis
    arXiv Project Page Hugging Face GitHub Stars

🌐 Multimodal Large Language Model

  • 🚀TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming
    arXiv Hugging Face Hugging Face GitHub Stars

Popular repositories Loading

  1. TaoMate-H3 TaoMate-H3 Public

    Python 855 78

  2. TaoMate TaoMate Public

    a real-time digital-human model for long-form audio-video generation

    Python 520 47

  3. TLive-Omni TLive-Omni Public

    TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

    Python 343 13

  4. AptAvatar AptAvatar Public

    Official Implementation of AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars

    Python 241 6

  5. TaoMate-FVSR TaoMate-FVSR Public

    Audio-guided facial video restoration and visual dubbing demos

    Python 115 22

  6. TBDub TBDub Public

    Python 54 9

Repositories

Showing 10 of 12 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…