Developed and integrated a Pix2PixUnet model for image-to-image translation within the NVIDIA/physicsnemo repository, focusing on expanding the project’s deep learning capabilities. The work involved designing the network architecture, implementing initialization routines, and defining metadata to support optimized inference and deployment. Using Python and PyTorch, the integration included creating a dedicated pix2pixunet.py module and updating package exports to ensure seamless packaging and downstream usability. No bug fixes were addressed during this period, as efforts centered on feature delivery and deployment readiness. This contribution established a foundation for further experimentation and optimization in computer vision pipelines leveraging image translation models.