Intrinsically disordered proteins and regions (collectively IDRs) are found across all kingdoms of life and have critical roles in virtually every eukaryotic cellular process1. IDRs exist in a broad ensemble of structurally distinct conformations. This structural plasticity facilitates diverse molecular recognition and function2,3,4. Here we combine advances in physics-based force fields with the power of multi-modal generative deep learning to develop STARLING, a framework for rapid generation of accurate IDR ensembles and ensemble-aware representations from sequence. STARLING supports environmental conditioning across ionic strengths and demonstrates proof of concept for the interpolative ability of generative models beyond their training domain. Moreover, we enable ensemble refinement under experimental constraints using a Bayesian maximum-entropy reweighting scheme. Beyond ensemble characterization, STARLING sequence representations can be used in multiple ways.…