Could artificial intelligence win the next Weather Photographer of the Year competition?

It is a premise that would have been met with derision several years ago, but the recent rise of diffusion models and their ability to produce hyper-realistic images now prompts us to engage seriously with the title question. Here, we use three diffusion models - DALLE-2, Midjourney and Stable Diffusion - to explore whether neural networks can produce realistic photographs of weather phenomena, and how to use their strengths in a manner that might win a weather photography competition. Finally, we invite the reader to take part in a test and judge which photos were previous finalists, and which were artificial intelligence (AI)-generated. The image in this graphical abstract was generated by DALLE-2 using the prompt: 'Award-winning photograph of large waves crashing into a lighthouse in Devon during the peak winds of Storm Eunice'.