Abstract: Embodiments of generation of candidate video elements are disclosed, including: receiving a requested video element type for a video creator user; deriving representative data associated with a set of seed videos; generating a prompt based at least in part on the requested video element type, the representative data associated with the set of seed videos, and a random input; inputting the prompt into a large language model that has been customized for the video creator user; and presenting a set of candidate video elements that has been output by the large language model.