Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

by [unverified] · free · Last verified 2026-06-21T03:07:51.060Z

We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters across various benchmarks, while requiring significantly less training compute. For example, Lens requires only about 19....