Enhancing interior design with AI-enhanced prompts and stable diffusion

Abstract

Traditional interior design CAD tools often fall short in terms of user-friendliness and inclusivity, leading to user frustration and dissatisfaction. In response, RoomVision AI leverages advanced Generative AI technology to transform the landscape of interior design. Users can input either a sketch or image of an interior alongside a textual description of their aesthetic preferences. This user-centric web application bridges the communication gap between users and CAD tools through natural language refinement using ChatGPT 3.5 Turbo. By integrating these refined prompts into the Stable Diffusion model, users can effortlessly explore interior design concepts. For a personalized experience, ControlNet enhances the Stable Diffusion model, maintaining fidelity to reference images and ensuring generated concepts align with the input structure.

RoomVision AI empowers users of all proficiency levels, promising an inclusive and creative future for interior design. The advantages include ease of use, realistic and personalized result generation, and a way to conceptualize a user’s design preferences that can be used for their interior design process. The results of the user feedback survey unequivocally affirm RoomVision AI's advantages, with the average response indicating strong agreement on the web application's user-centric design and satisfaction with the generated concepts. The web application signifies a significant step towards redefining interior design practices for a more inclusive and creative future.