Abstract The direct imaging of an Earth-like exoplanet will require sub-nanometric wave-front control across large light-collecting apertures to reject host starlight and detect the faint planetary signal. Current adaptive optics systems, which use wave-front sensors that reimage the telescope pupil, face two challenges that prevent this level of control: non-common-path aberrations, caused by differences between the sensing and science arms of the instrument; and petaling modes: discontinuous phase aberrations caused by pupil fragmentation, especially relevant for the upcoming 30 m class telescopes. Such aberrations drastically impact the capabilities of high-contrast instruments. To address these issues, we can add a second-stage wave-front sensor to the science focal plane. One promising architecture uses the photonic lantern (PL): a waveguide that efficiently couples aberrated light into single-mode fibers (SMFs). In turn, SMF-confined light can be stably injected into high-resolution spectrographs, enabling direct exoplanet characterization and precision radial velocity measurements; simultaneously, the PL can be used for focal-plane wave-front sensing. We present a real-time experimental demonstration of the PL wave-front sensor on the Subaru/SCExAO testbed. Our system is stable out to around ±400 nm of low-order Zernike wave-front error and can correct petaling modes. When injecting ∼30 nm rms of low-order time-varying error, we achieve ∼10× rejection at 1 s timescales; further refinements to the control law and lantern fabrication process should make sub-nanometric wave-front control possible. In the future, novel sensors like the PL wave-front sensor may prove to be critical in resolving the wave-front control challenges posed by exoplanet direct imaging.