谷歌于本周二推出了一款名为 VideoPoet 的大语言模型，这款模型被认为是革命性的 zero-shot 视频生成工具。VideoPoet 既可以生成视频，也可以生成图像，同时还能进行风格迁移和视频转语音等操作。从效果上看，它可以构建多样化且流畅的运动。
这款模型集成了谷歌在自然语言处理和计算机视觉领域的最新技术，能够实现对视频和图像的无中生有，同时也具备了视频转语音的功能。它的推出，将极大地推动视频生成技术的发展，为人们提供更加多样化和流畅的视频体验。
值得注意的是，VideoPoet 的推出也标志着谷歌在人工智能领域方面的最新进展。在过去几年中，谷歌已经在计算机视觉和自然语言处理等领域取得了很大的进展，从语音识别、图像识别、自然语言处理等方面都有不错的表现。
总的来说，VideoPoet 的推出将极大地推动视频生成技术的发展，为人们带来更加多样化和流畅的视频体验。同时，它也展示了谷歌在人工智能领域方面的最新进展，为人们带来了更多的期待。
新闻翻译：
Google has just announced the launch of a new large-scale video generation model, which is considered revolutionary for zero-shot video generation. VideoPoet can generate both videos and images, as well as perform style transfer and video-to-speech operations. In terms of effect, it can build various and smooth motion.
This model integrates the latest technologies that Google has made strides in the field of natural language processing and computer vision, allowing for the creation of both videos and images from scratch. It also supports video-to-speech functionality, making it an exciting development in the field of video generation technology.
It’s worth noting that the launch of VideoPoet also marks Google’s latest advancements in the field of artificial intelligence. Over the past few years, Google has made significant progress in areas such as speech recognition, image recognition, and natural language processing.
Overall, the launch of VideoPoet will significantly push the boundaries of video generation technology, providing users with a wider range of diverse and smooth video experiences. At the same time, it also showcases Google’s latest advancements in the field of artificial intelligence, bringing more expectations to the table.
【来源】https://www.jiqizhixin.com//articles/2023-12-20-8
Views: 1