A new open-source AI model called Pyramid Flow generates high-quality video clips of up to ten seconds in length. It was developed by researchers from Peking University, Beijing University of Posts and Telecommunications, and Kuaishou Technology, as reported by Carl Franzen. Pyramid Flow uses a novel technique where an AI model creates videos in multiple steps, most of them in low resolution. Only the final version is rendered in full resolution.
The model is available as code on Hugging Face and Github, where it can also be tested, but requires a powerful computer. Pyramid Flow is open-source and can be used commercially. It aims to be a free alternative to paid offerings such as Runway Gen-3 Alpha or Luma’s Dream Machine. According to the developers, the video quality is comparable to that of commercial offerings.