The paper introduces Segment Any Cell (SAC), an innovative framework that enhances the Segmentation Anything Model (SAM) for nuclei segmentation in medical imaging. SAC addresses the critical challenge of generating high-quality, informative prompts, which is crucial for improving the performance of SAM in specialized tasks. The framework integrates Low-Rank Adaptation (LoRA) within the attention layer of the Transformer to enhance the fine-tuning process, outperforming existing state-of-the-art (SOTA) methods. Additionally, SAC introduces an auto-prompt generator that automatically produces effective prompts to guide the segmentation process, making it easier to use and more efficient. Extensive experiments on the MoNuSeg and 2018 Data Science Bowl (DSB) datasets demonstrate the superiority of SAC in nuclei segmentation tasks, outperforming both SOTA methods and advanced SAM adaptation techniques. The contributions of SAC include a novel prompt generation strategy, automated adaptability for diverse segmentation tasks, the innovative application of Low-Rank Attention Adaptation in SAM, and a versatile framework for semantic segmentation challenges.The paper introduces Segment Any Cell (SAC), an innovative framework that enhances the Segmentation Anything Model (SAM) for nuclei segmentation in medical imaging. SAC addresses the critical challenge of generating high-quality, informative prompts, which is crucial for improving the performance of SAM in specialized tasks. The framework integrates Low-Rank Adaptation (LoRA) within the attention layer of the Transformer to enhance the fine-tuning process, outperforming existing state-of-the-art (SOTA) methods. Additionally, SAC introduces an auto-prompt generator that automatically produces effective prompts to guide the segmentation process, making it easier to use and more efficient. Extensive experiments on the MoNuSeg and 2018 Data Science Bowl (DSB) datasets demonstrate the superiority of SAC in nuclei segmentation tasks, outperforming both SOTA methods and advanced SAM adaptation techniques. The contributions of SAC include a novel prompt generation strategy, automated adaptability for diverse segmentation tasks, the innovative application of Low-Rank Attention Adaptation in SAM, and a versatile framework for semantic segmentation challenges.