20.500.12556/RUL-181922 Diff-FIT generating facial composites with diffusion models Facialcomposites, or police sketches, are essential tools in law enforcement for reconstructing the appearance of suspects from eyewitness descriptions. Traditionally, forensic artists manually produce these composites through intensive and time-consuming collaboration with witnesses. To improve the efficiency of this process, automated approaches have leveraged advancements in deep learning and generative modeling. However, the application of recent diffusion models has remained unexplored, despite their unparalleled text-guided synthesis capabilities. To this end, we present Diff-FIT (Diffusion Facial Identification Technique), a novel multi-pipeline framework for generating photorealistic facial composites in only a few steps with pretrained diffusion models. Diff-FIT enables rapid generation of initial composites from textual descriptions, followed by intuitive sequential edits including global image-to-image translation, local text-based inpainting, and drag-based geometric transformations. Through experiments across multiple latent diffusion models and sampling parameters we determine the configuration that best balances image quality, diversity, image-text alignment, and identity consistency. In a user study involving biometric experts and non-experts, Diff-FIT achieves comparable real-world utility to state-of-the art systems in both subjective evaluations and identification rates with generated facial composites, while enabling greater variation and flexibility through description-based generation and diverse editing pipelines for adding distinct facial features. The source code Diff-FIT framework is publicly available at: https://github.com/matemato/Diff-FIT deep generative models image-based biometrics diffusion models facial composites globoki generativni modeli slikovna biometrija difuzijski modeli fotoroboti true false true Angleški jezik Slovenski jezik Članek v reviji 2026-04-20 09:43:08 2026-04-20 09:43:09 2026-04-21 04:42:28 0000-00-00 00:00:00 2026 0 0 Str. 41650 - 41670 Vol. 14 2026 0000-00-00 Zaloznikova Objavljeno apc 0000-00-00 0000-00-00 0000-00-00 004.932.2:004.8 2169-3536 10.1109/ACCESS.2026.3672229 271510531 RAZ_Tomasevic_Darian_2026.pdf RAZ_Tomasevic_Darian_2026.pdf 1 8331E2BB047220FFEEB9AD44437FF6F2 f1486786918ebf0fad26c0b1c0214c4ae595514cf84c8eb83bc2d0c22c24d90e 1486105f-3c8e-11f1-b0ab-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=232717 https://ieeexplore.ieee.org/document/11426945 1 573c9b12-3c8c-11f1-b0ab-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=232713 Fakulteta za računalništvo in informatiko Fakulteta za elektrotehniko 0 0 0