Tendem
Mini toolsParis
By Bagel LABS
Paris demonstrates that high quality text to image generation does not require a centralized GPU cluster. The team trains a set of expert diffusion models independently, with no gradient, parameter, or activation synchronization during pretraining. This zero communication recipe lets volunteers or heterogeneous nodes contribute compute, avoids dependencies on NVLink or InfiniBand, and scales with simple orchestration. In experiments, the approach reports large efficiency gains versus conventional pipelines while maintaining competitive visual quality, and the weights are released for open use. In practice, Paris is a practical foundation for creative tools and research that want modern diffusion images and a training method that works across scattered hardware.
Image
Gen 4
Overview
Paris by Bagel Labs is an open weight text to image diffusion model trained entirely through decentralized computation. It uses multiple expert models trained in isolation with zero cross device communication, so it can be trained on fragmented compute without specialized interconnects, while aiming for strong image quality at lower cost.
About Bagel LABS
Bagel Labs is an AI research company creating open-source, decentralized foundation models like Paris, aiming to make superintelligence accessible and community-driven.
Website:
bagel.com
Last updated: October 15, 2025
