FLAME 2023 Open — derived numerical model Model: Max Planck Institute for Intelligent Systems / Max-Planck-Gesellschaft. Li, T.; Bolkart, T.; Black, M. J.; Li, H.; Romero, J. Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics (SIGGRAPH Asia), 36(6), 194:1–194:17, 2017. https://flame.is.tue.mpg.de/ Model license: Creative Commons Attribution 4.0 International. https://creativecommons.org/licenses/by/4.0/ https://flame.is.tue.mpg.de/modellicense.html#open-model-license Numerical extraction redistributed by LangerFace, commit b4fa47458cf3faa6c9f1eaa2ee71fef09d1cee15. See UPSTREAM-NOTICE.md. https://github.com/jwj1342/LangerFace Source binary SHA256: bd54372750ae5aa312ac63134de9f03eacfa8a6da09cea92d376bb0c66127361 The upstream declares extraction from flame2023_Open.pkl. No authenticated comparison against the full MPI archive was performed. Foldface changes: local multiview fitting of the first 60 identity and 50 expression components, fitted cameras and normalization. The printable head is derived from the FLAME skin alone (scripts/build-head.mjs): the skin is cut on its median plane, simplified by quadric edge collapses along facial contours traced between FLAME's own MediaPipe and 68-point landmark embeddings, then mirrored. Neck/eye articulations and pose corrective blendshapes are not included in this compact extraction. No texture model or pretrained face-reconstruction network is included.