Machine Learning (ML) systems require representative and diverse datasets to accurately learn the objective task. In supervised learning data needs to be accurately annotated, which is an expensive and error-prone process. We present a method for generating synthetic data tailored to the use-case achieving excellent performance in a real-world usecase. We provide a method for producing automatically annotated synthetic visual data of multi rotor unmanned aerial vehicles (UAV) and other airborne objects in a simulated environment with a high degree of scene diversity, from collection of 3D models to generation of annotated synthetic datasets (synthsets). In our data generation framework SynRender we introduce a novel method of using Neural Radiance Field (NeRF) methods to capture photo-realistic high-fidelity 3D-models of multirotor UAVs in order to automate data generation for an object detection task in diverse environments. By producing data tailored to the real-world setting, our NeRF-derived results show an advantage over generic 3D asset collection-based methods where the domain gap between the simulated and real-world is unacceptably large. In the spirit of keeping research open and accessible to the research community we release our dataset VISER DroneDiversity used in this project, where visual images, annotated boxes, instance segmentation and depth maps are all generated for each image sample.