谷歌旗下聊天机器人Bard近日宣布，其功能再次升级，新增图像生成功能。此前，Bard以语言处理技能著称，如今，它不仅能进行语言处理，还可以根据用户提供的描述免费生成“高质量、逼真的图像输出”。这项功能在全球受支持的地区免费提供，使用的是谷歌Imagen 2模型，但需要英语指令进行操作。
此次Bard的图像生成功能，是人工智能技术在图像领域的一次重要突破。它意味着，用户可以更直观地通过语言描述，来实现图像的创作和生成。这对于内容创作、设计等领域来说，无疑提供了一种全新的可能。
据悉，Bard的图像生成功能将在全球范围内受支持的地区免费提供，用户只需通过英语指令，就能轻松实现个性化图像的生成。这将极大地丰富Bard的应用场景，提升用户体验。
Title: Google’s Bard chatbot adds image generation capability
Keywords: Bard, image generation, artificial intelligence
News Content:
Google’s chatbot Bard recently announced that its functionality has been upgraded to include image generation. Previously known for its language processing skills, Bard can now generate “high-quality, realistic images” based on user descriptions for free. This feature is available in supported regions worldwide, powered by the Google Imagen 2 model, but requires English instructions for operation.
The image generation capability of Bard is a significant breakthrough in the field of artificial intelligence for image creation. It means that users can intuitively achieve image production and generation through language descriptions. This offers a whole new possibility for content creation, design, and other fields.
It is reported that Bard’s image generation feature will be available for free in supported regions worldwide, allowing users to easily generate personalized images through English instructions. This will greatly enrich the application scenarios of Bard and enhance the user experience.
【来源】https://www.ithome.com/0/748/511.htm
Views: 1