This paper proposes a novel low-light image enhancement method called CLIP-Fourier Guided Wavelet Diffusion (CFWD). The method leverages multimodal visual-language information in the frequency domain space created by multiple wavelet transforms to guide the enhancement process. Multi-scale supervision across different modalities facilitates the alignment of image features with semantic features during the wavelet diffusion process, effectively bridging the gap between degraded and normal domains. Additionally, the method combines the Fourier transform based on the wavelet transform and constructs a Hybrid High Frequency Perception Module (HFPM) with significant perception of detailed features. This module avoids the diversity confusion of the wavelet diffusion process by guiding the fine-grained structure recovery of the enhancement results to achieve favorable metric and perceptually oriented enhancement. Extensive quantitative and qualitative experiments on publicly available real-world benchmarks show that the proposed method outperforms existing state-of-the-art methods, achieving significant progress in image quality and noise suppression. The project code is available at https://github.com/hejh8/CFWD. The paper discusses the challenges of low-light image enhancement, including unstable image quality recovery and unsatisfactory visual perception. It also explores the use of diffusion models for image restoration and the integration of visual-language information for better feature alignment. The proposed method combines wavelet diffusion with CLIP and Fourier transform to achieve high-quality visual enhancement and metric results. The method is evaluated on various datasets, including LOLv1, LOLv2-Real_captured, LSRW, BAID, LIME, and DICM. The results show that the proposed method achieves state-of-the-art performance in terms of PSNR, SSIM, LPIPS, and FID metrics. The method is also effective in unpaired datasets, demonstrating better generalization and visual perception. The paper concludes that the proposed method significantly improves the visual quality and metric performance of low-light image enhancement.This paper proposes a novel low-light image enhancement method called CLIP-Fourier Guided Wavelet Diffusion (CFWD). The method leverages multimodal visual-language information in the frequency domain space created by multiple wavelet transforms to guide the enhancement process. Multi-scale supervision across different modalities facilitates the alignment of image features with semantic features during the wavelet diffusion process, effectively bridging the gap between degraded and normal domains. Additionally, the method combines the Fourier transform based on the wavelet transform and constructs a Hybrid High Frequency Perception Module (HFPM) with significant perception of detailed features. This module avoids the diversity confusion of the wavelet diffusion process by guiding the fine-grained structure recovery of the enhancement results to achieve favorable metric and perceptually oriented enhancement. Extensive quantitative and qualitative experiments on publicly available real-world benchmarks show that the proposed method outperforms existing state-of-the-art methods, achieving significant progress in image quality and noise suppression. The project code is available at https://github.com/hejh8/CFWD. The paper discusses the challenges of low-light image enhancement, including unstable image quality recovery and unsatisfactory visual perception. It also explores the use of diffusion models for image restoration and the integration of visual-language information for better feature alignment. The proposed method combines wavelet diffusion with CLIP and Fourier transform to achieve high-quality visual enhancement and metric results. The method is evaluated on various datasets, including LOLv1, LOLv2-Real_captured, LSRW, BAID, LIME, and DICM. The results show that the proposed method achieves state-of-the-art performance in terms of PSNR, SSIM, LPIPS, and FID metrics. The method is also effective in unpaired datasets, demonstrating better generalization and visual perception. The paper concludes that the proposed method significantly improves the visual quality and metric performance of low-light image enhancement.