腾讯公司近日携手清华大学和香港科技大学，共同发布了名为“Follow-Your-Click”的图生视频模型。该模型能够将静态图片转换为动态视频，只需用户点击图片中的特定区域，并输入简短的提示词即可实现。这项技术为视频制作提供了新的可能性，极大地简化了动画的生成过程。
腾讯的混元大模型团队一直致力于探索多模态技术，此次推出的新模型是其研究成果之一。多模态技术是指能够理解和处理多种类型的数据，如文本、图像和声音等的技术。“Follow-Your-Click”模型不仅展示了腾讯在人工智能领域的创新能力，也预示着未来视频内容创作的便捷性和趣味性将得到进一步提升。
英文标题: Click-to-Video Technology Unveiled by Tencent
英文关键词: Tencent, Click-to-Video, Multi-Modal Technology
英文新闻内容:
Tencent has recently joined forces with Tsinghua University and the Hong Kong University of Science and Technology to launch a click-to-video model called “Follow-Your-Click.” This innovative model transforms static images into dynamic videos by allowing users to click on specific areas within the image and input short prompts. The technology simplifies the animation creation process, offering new possibilities for video production.
Tencent’s ChaosGPT model team has been actively exploring multi-modal technology, and this new model is a result of their research efforts. Multi-modal technology refers to the ability to understand and process various types of data, such as text, images, and sound. The “Follow-Your-Click” model demonstrates Tencent’s innovative capabilities in artificial intelligence and foreshadows further enhancements in the convenience and fun of video content creation.
【来源】https://www.chinastarmarket.cn/detail/1620642
Views: 1