Since the acquisition of a large amount of defect data is expensive and time-consuming, the limited availability of defective samples impairs the accuracy and generalizability of defect detection methods. Although defect generation approaches have been explored for data augmentation, they usually suffer from either a lack of realism or limited diversity. To address these challenges, we propose a two-stage controllable few-shot defective image generation network, namely, DefectSynth, which models both the shape and appearance of defects. The first stage aims to generate continuous defect masks even with a few real masks. To this end, we propose a Hybrid Mask Interpolation (HMI) module, which performs interpolation in the image or latent space. The second stage is used to synthesize the defective appearance. We first fine-tune the pre-trained ControlNet, which is then used together with a pre-trained stable diffusion model to synthesize defective images. Given a mask generated in the first stage and a text prompt, they are integrated with a defect-free image to synthesize a high-fidelity defective image. To alleviate the issue of generation of indistinct defects with existing methods, we propose a Selective Attention Enhancement (SAE) mechanism that highlights the details of defects. We also design a Similarity-Based Feature Fusion (SFF) module to merge different local features, thereby further enriching the appearance diversity of defects. Using the defect data generated by DefectSynth, the classification accuracy on MVTec-AD has been improved from 44.03\% to 66.70\% compared with the baseline without synthetic data augmentation, while the F1-Score values computed on GDXray and DeepCrack for small-defect localization have been increased from 70.48\% to 76.64\% and from 70.08\% to 83.27\%, respectively. These performance gains should be due to the fact that our method is able to generate realistic and diverse defective images by modeling both the shape and appearance of defects.