Drag-guided diffusion models for vehicle image generation
This work addresses the limitation of diffusion models in enforcing engineering constraints for vehicle design, though it is incremental as a proof-of-concept.
The paper tackled the problem of generating vehicle images with minimized drag coefficients by integrating physics-based guidance into Stable Diffusion, achieving the ability to optimize a performance metric during image generation.
Denoising diffusion models trained at web-scale have revolutionized image generation. The application of these tools to engineering design is an intriguing possibility, but is currently limited by their inability to parse and enforce concrete engineering constraints. In this paper, we take a step towards this goal by proposing physics-based guidance, which enables optimization of a performance metric (as predicted by a surrogate model) during the generation process. As a proof-of-concept, we add drag guidance to Stable Diffusion, which allows this tool to generate images of novel vehicles while simultaneously minimizing their predicted drag coefficients.