We propose an automatic layout method for indoor scenes that effectively satisfies specific constraints. Our approach involves enhancing the existing scene representation method to accommodate complex constraints, including the precise placement of doors, windows, and user-specified furniture. To achieve this, we construct a conditional vector that encapsulates the necessary constraints. Moreover, our automatically constrained layout approach is implemented by training a conditional variational autoencoder model. Given the constraints and randomly sampled vectors, the decoder module can generate diversified reasonable indoor layout results. Evaluations show that our model outperforms the existing methods. Furthermore, our model exhibits a lower parameter count and faster execution speed compared with the existing approaches.