This article presents a comprehensive dataset for cotton leaf disease detection, which is crucial for agricultural research, precision farming, and disease management. The dataset, sourced from field surveys conducted from October 2023 to January 2024, includes 2137 original images and 7000 augmented images, covering eight categories of cotton leaf conditions such as bacterial blight, curl virus, herbicide growth damage, and healthy leaves. The images were captured under diverse environmental conditions to ensure a comprehensive representation of disease manifestations. The dataset is designed to support the development of accurate machine learning models for early disease detection, reducing manual inspections, and facilitating timely interventions. The Inception V3 model, trained on this dataset, achieved an overall accuracy of 96.03%, demonstrating the dataset's potential in advancing automated disease detection in cotton agriculture. The study highlights the importance of data augmentation and deep learning techniques in improving model performance and robustness. The dataset is publicly available and can be used to foster global collaboration, contribute to the development of disease-resistant cotton varieties, and promote sustainable farming practices.This article presents a comprehensive dataset for cotton leaf disease detection, which is crucial for agricultural research, precision farming, and disease management. The dataset, sourced from field surveys conducted from October 2023 to January 2024, includes 2137 original images and 7000 augmented images, covering eight categories of cotton leaf conditions such as bacterial blight, curl virus, herbicide growth damage, and healthy leaves. The images were captured under diverse environmental conditions to ensure a comprehensive representation of disease manifestations. The dataset is designed to support the development of accurate machine learning models for early disease detection, reducing manual inspections, and facilitating timely interventions. The Inception V3 model, trained on this dataset, achieved an overall accuracy of 96.03%, demonstrating the dataset's potential in advancing automated disease detection in cotton agriculture. The study highlights the importance of data augmentation and deep learning techniques in improving model performance and robustness. The dataset is publicly available and can be used to foster global collaboration, contribute to the development of disease-resistant cotton varieties, and promote sustainable farming practices.