PulseAugur
EN
LIVE 21:11:36
中文(ZH) 生数科技正式发布Vidu S1实时交互模型

Shengshu Technology launches Vidu S1 for real-time interactive video generation

Shengshu Technology has launched Vidu S1, a new real-time interactive AI model for video generation. This model enables continuous interaction and control through voice commands, allowing users to influence character actions and expressions in real-time. Vidu S1 supports high-definition resolution (540P) and frame rates (25FPS, up to 42FPS), and can create personalized interactive characters from a single image, moving beyond traditional offline video generation to a more dynamic and responsive experience. AI

IMPACT Enables more dynamic and responsive AI-driven video content, potentially impacting areas like virtual companions, interactive streaming, and gaming NPCs.

RANK_REASON New model release from an AI lab. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on 36氪 (36Kr) →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Shengshu Technology launches Vidu S1 for real-time interactive video generation

COVERAGE [2]

  1. 雷峰网 (Leiphone) TIER_1 中文(ZH) ·

    Shengshu Technology Releases Vidu S1, Ushering in a New Era of "Real-time Interaction" for Video Generation

    <p>7月3日,在2026全球数字经济大会人工智能融合应用发展论坛,生数科技创始人朱军发表题为《通用世界模型,推动数字世界与物理世界统一的新范式》的主题演讲,并正式发布面向实时交互场景的新一代模型——Vidu S1 实时交互模型。大会期间,北京软件和信息服务业协会(BSIA)正式发布《2025年北京市数字经济标杆企业评价报告》,生数科技凭借在技术创新与产业应用方面的突出表现,成功入选“新模式新应用标杆企业”。</p><p style="text-align: center;"><img src="https://static.leiphone.com/u…

  2. 36氪 (36Kr) TIER_1 中文(ZH) ·

    Shengshu Technology Officially Releases Vidu S1 Real-time Interaction Model

    36氪获悉,生数科技正式发布Vidu S1实时交互模型,提供实时可交互的新一代视频生成能力,模型支持实时视频通话和语音控制视频走向。同时,Vidu S1支持540P(960x540)高清分辨率、25FPS帧率(最高支持42FPS),可基于真人、动漫、萌宠等任意初始形象及个性化音色,快速创建专属交互角色。