Bagel Labs is an AI research lab that trains frontier diffusion models across commodity hardware instead of one uniform GPU cluster. Our method, Distributed Diffusion Models or DDM, trains many smaller expert models independently with no gradient synchronization, and a lightweight router combines them at inference. Paris-1 proved the idea on images and Paris-2 proved it on video, where three 11B experts and a router beat a monolithic baseline trained on the same compute by more than 5...