快科技4月15日消息,微软近日正式推出新款文生图模型MAI-Image-2-Efficient,这是其旗舰模型MAI-Image-2的升级版本,主打低成本和高效率,已正式投入商业使用。
该模型生成速度提升22%,整体效率提升4倍,成本直接降低41%。具体定价为:每百万文本输入词元(token)5美元(约合34.2元人民币),每百万图像输出19.50美元(约合133.4元人民币)。
微软表示,MAI-Image-2-Efficient以近一半的价格提供生产级质量,速度比头部云厂商的顶级模型快约40%。
微软采用双模型策略,两款独立的文生图模型各有侧重。MAI-Image-2-Efficient被定位为量产主力模型,适合需要批量生成、速度与严格成本控制的场景,尤其擅长生成产品实拍图和UI原型图,能够很好处理标题、标签等短文本,并可无缝融入交互式工作流。
而MAI-Image-2则更注重高保真需求,适合照片级写实场景、动漫或插画等风格化效果,以及更长、更复杂的图像内文字生成,能精准理解并输出贴合详细提示词的内容。
目前MAI-Image-2-Efficient可在微软Foundry和MAIPlayground中使用,微软还承诺很快会将其集成到Copilot和必应等服务中。

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.