The paper introduces Text-IF, a novel approach for degradation-aware and interactive image fusion that leverages semantic text guidance. Image fusion aims to combine information from different source images to create a comprehensive and representative image, but existing methods often struggle with low-quality source images and lack the ability to address multiple subjective and objective needs. Text-IF extends classical image fusion to a text-guided version, addressing degradation and interaction issues. It uses a text semantic encoder and a semantic interaction fusion decoder to process all-in-one infrared and visible images, achieving multi-modal image and information fusion. Extensive experiments show that Text-IF outperforms state-of-the-art methods in image fusion performance and degradation treatment. The method is flexible and can generate high-quality, user-required fusion results without prior expertise or predefined rules. The code is available at https://github.com/XunpengYi/Text-IF.The paper introduces Text-IF, a novel approach for degradation-aware and interactive image fusion that leverages semantic text guidance. Image fusion aims to combine information from different source images to create a comprehensive and representative image, but existing methods often struggle with low-quality source images and lack the ability to address multiple subjective and objective needs. Text-IF extends classical image fusion to a text-guided version, addressing degradation and interaction issues. It uses a text semantic encoder and a semantic interaction fusion decoder to process all-in-one infrared and visible images, achieving multi-modal image and information fusion. Extensive experiments show that Text-IF outperforms state-of-the-art methods in image fusion performance and degradation treatment. The method is flexible and can generate high-quality, user-required fusion results without prior expertise or predefined rules. The code is available at https://github.com/XunpengYi/Text-IF.