Objectives: To evaluate how photon-counting CT (PCCT) reproducibly quantifies lung density compared to conventional CT (energy-integrating CT or EICT) and assess the relevance of image quality. Methods: In this retrospective analysis of a prospective study, subjects underwent acquisitions using EICT and PCCT systems (August-December 2021) on the same day. PCCT projections were reconstructed with 4 kernels and 2 voxel sizes using 2024 reconstruction software (ReconCT, Siemens). PCCT and EICT data were compared using lung density measurements: percentage of low-attenuation areas <−950 Hounsfield unit (HU) (LAA-950), 15th percentile of lung density histogram (Perc15), and mean lung density (MLD). Measurement reproducibility and its relation to image quality parameters (modulation transfer function and noise) were analyzed. Results: Fifty-four subjects (mean age, 67.4 years ± 9.6, 30 female) were studied. PCCT images had the closest agreement to EICT under identical voxel size and similar kernels, yielding lower LAA-950 (−0.9% ± 2.7, P < 0.05), higher Perc15 (1.4 HU ± 7.9, P > 0.05), and higher MLD (2.4 HU ± 10.8, P > 0.05). At higher PCCT resolution (1024 × 1024 matrix, 0.2 mm slice thickness), the smoother quantitative kernel (Qr36) improved agreement, with differences of −0.5% ± 3.0, −0.1 HU ± 9.8, and 2.8 HU ± 11.1, for LAA-950, Perc15, and MLD (P > 0.05). Image quality parameters strongly correlated with density measurements (RPerc152=85.3%). Conclusions: PCCT yields reproducible lung density measurements comparable to EICT, with optimal reproducibility dependent on optimized reconstruction parameters and explainable by image quality parameters. Advances in knowledge: Lung density reproducibility is critical for integrating PCCT into EICT-based workflows. In our study, PCCT aligned more closely with EICT using similar kernels at identical voxel sizes, or smoother kernels at smaller voxel sizes.