Google Vids 推出 Gemini Omni 和个人虚拟形象，将 AI 视频引入 Workspace
Google Vids 推出 Gemini Omni 和个人虚拟形象，围绕工作场所视频应如何变革提出了两个相互关联的设想。前者可将普通提示词转化为视频创作和编辑指令。后者则能让员工的数字化形象朗读输入的脚本，无需再次进行拍摄。 此次更新于 7 月 16 日发布，推动 Google Vids…
Read the full articleYou might also wanna read
Untitled
humanoid.guide·2h ago
Interview with Jon Roberts of Inteq: ‘The software layer is where automation investment is won or lost’
Robotics & Automation News·2h ago
Interview with Scott Zerkle of Panasonic Connect: ‘AI is only as good as the data it receives’
Robotics & Automation News·3h ago
Strider Robotics demonstrates 40 kg payload quadruped robot as commercial pilots begin
Robotics & Automation News·3h ago
Humanoid AI puts HMND 01 humanoid on wheels for industry
humanoid.guide·4h ago
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
arxiviq.substack.com·4h ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.