--- lang: en title: "Nara AI models: 22 bundled AI vision capabilities" url: https://nabrio.com/nara/ai-models canonical: https://nabrio.com/nara/ai-models updated: 2026-10-27 publisher: Nabrio Co., Ltd. (nabrio.com) --- # AI models bundled with Nara Nara’s model manager ships more than 60 model families, downloaded and checksum-verified, then loaded on demand. Custom models from Reva deploy with no configuration, third-party ONNX models run where compatible nodes exist, and promptable models detect or segment objects described in words, with no training. ## Bundled AI capabilities As of model pack 261018. Example model names are for technical readers. - [General object detection](https://nabrio.com#general-object-detection.md) — General object detection pack: Detects common objects such as people, vehicles, animals, bags and phones. - [People detection](https://nabrio.com#people-detection.md) — PeopleNet, RT-DETRv4: Detects people robustly in crowded or difficult scenes. - [Object tracking and analytics](https://nabrio.com#object-tracking.md) — Built-in tracker: Tracks objects across frames for line-crossing counts, zone counts, dwell time, heatmaps and abandoned objects. - [Person re-identification (ReID)](https://nabrio.com#person-reid.md) — FastReID, PersonViT, ReIdentificationNet: Recognises the same person across cameras and over time, without faces. - [Face detection and recognition](https://nabrio.com#face-recognition.md) — RetinaFace, SCRFD, YuNet, ArcFace, EdgeFace, SFace: Finds faces and matches them against a known-face gallery. - [Face anti-spoofing and quality](https://nabrio.com#face-anti-spoofing.md) — MiniFASNetV2, eDifFIQA: Rejects photos and screens, and scores face image quality. - [Facial expression](https://nabrio.com#facial-expression.md) — AffectNet-7, OpenCV FER: Classifies expressions such as happy, sad, angry and surprised. - [Age and gender estimation](https://nabrio.com#age-gender.md) — MiVOLO, UniFace: Estimates demographics for anonymous analytics. - [Pose estimation](https://nabrio.com#pose-estimation.md) — RTMPose, RTMO, MoveNet: Body keypoints for posture and gesture. - [Head pose and gaze](https://nabrio.com#head-pose-gaze.md) — 6DRepNet360, UniFace HeadPose: Where a person is looking, for attention and engagement. - [Action and behaviour recognition](https://nabrio.com#action-recognition.md) — ST-GCN Fall, PoseC3D, SlowFast, VideoMAE: Falls, fights or violence, and other actions from pose or video. - [Crowd counting](https://nabrio.com#crowd-counting.md) — PET crowd point: Estimates people counts in dense crowds. - [Fire and smoke detection](https://nabrio.com#fire-smoke.md) — Fire/smoke detection pack: Detects flames and smoke in camera views. - [PPE detection](https://nabrio.com#ppe-detection.md) — Nabrio PPE models: Helmets, vests, masks, hairnets, gloves, coats and other PPE on each person. - [Weapon detection](https://nabrio.com#weapon-detection.md) — Nabrio weapon models: Firearms and knives, with tracking of the people involved. - [Vehicle make and model recognition](https://nabrio.com#vehicle-make-model.md) — Nabrio vehicle models: Identifies a car’s brand and model. - [Licence plate detection](https://nabrio.com#licence-plate-detection.md) — Number plate detection pack: Finds number plates for recognition. - [OCR (text reading)](https://nabrio.com#ocr.md) — PP-OCRv5 / v6, CRNN, DB: Reads printed text, including Thai. - [Barcode and QR code reading](https://nabrio.com#barcode-qr.md) — Built-in code reader: Reads 1D and 2D codes. - [Promptable detection and segmentation](https://nabrio.com#promptable-detection.md) — LocateAnything 3B, SAM 3.1: Finds or outlines anything described in words, with no training. - [Image similarity and matching](https://nabrio.com#image-similarity.md) — DINOv3, LightGlue: Compares images or finds a reference object. - [AI decisions (language and vision-language)](https://nabrio.com#ai-decisions.md) — Decider, OmniJev: Answers custom questions about text, images and video, such as “Is the work area tidy?” ## Classic vision tools Not every task needs deep learning. Nara also includes colour detection and thresholds, circle and contour detection, feature matching, crop, rotate, perspective correction, brightness, contrast and white balance. ## About 160 nodes in Nara 2.0 Grouped as in the editor. The full reference is on help.nabrio.com. - **Triggers**: On deploy, time interval, recurring schedule, dashboard action, webhook, WebSocket message - **I/O**: IP camera (single and multi), Basler, webcam, media files; Modbus read/write; MQTT publish; HTTP request; TCP/IP client; email; Microsoft Teams; Telegram; Patlite and Primus tower lights; export image or text - **Vision / AI**: Object, people, face, pose, fire, plate, OCR and code nodes; trackers with line and zone counters, dwell time, heatmap and abandoned-object detection; ReID; promptable detection and segmentation; auto-labelling - **Process**: Maths, rounding, moving-window statistics, JSON and XML parsing, arrays and objects, text templates, time deltas, the AI Decision node - **Operation**: If, switch/case, for and while loops, count-to, delay, stop, functions (series or parallel), procedure order, Python script - **Data**: Variables and arrays, database tables (create, read, filter, insert, modify, delete) Advanced industrial nodes, such as industrial cameras, PLC and robot connectivity, are Professional Nodes, and their availability depends on your tier. ## Capability reference | Capability | What it does | Example models | | --- | --- | --- | | General object detection | Detects common objects such as people, vehicles, animals, bags and phones. | General object detection pack | | People detection | Detects people robustly in crowded or difficult scenes. | PeopleNet, RT-DETRv4 | | Object tracking and analytics | Tracks objects across frames for line-crossing counts, zone counts, dwell time, heatmaps and abandoned objects. | Built-in tracker | | Person re-identification (ReID) | Recognises the same person across cameras and over time, without faces. | FastReID, PersonViT, ReIdentificationNet | | Face detection and recognition | Finds faces and matches them against a known-face gallery. | RetinaFace, SCRFD, YuNet, ArcFace, EdgeFace, SFace | | Face anti-spoofing and quality | Rejects photos and screens, and scores face image quality. | MiniFASNetV2, eDifFIQA | | Facial expression | Classifies expressions such as happy, sad, angry and surprised. | AffectNet-7, OpenCV FER | | Age and gender estimation | Estimates demographics for anonymous analytics. | MiVOLO, UniFace | | Pose estimation | Body keypoints for posture and gesture. | RTMPose, RTMO, MoveNet | | Head pose and gaze | Where a person is looking, for attention and engagement. | 6DRepNet360, UniFace HeadPose | | Action and behaviour recognition | Falls, fights or violence, and other actions from pose or video. | ST-GCN Fall, PoseC3D, SlowFast, VideoMAE | | Crowd counting | Estimates people counts in dense crowds. | PET crowd point | | Fire and smoke detection | Detects flames and smoke in camera views. | Fire/smoke detection pack | | PPE detection | Helmets, vests, masks, hairnets, gloves, coats and other PPE on each person. | Nabrio PPE models | | Weapon detection | Firearms and knives, with tracking of the people involved. | Nabrio weapon models | | Vehicle make and model recognition | Identifies a car’s brand and model. | Nabrio vehicle models | | Licence plate detection | Finds number plates for recognition. | Number plate detection pack | | OCR (text reading) | Reads printed text, including Thai. | PP-OCRv5 / v6, CRNN, DB | | Barcode and QR code reading | Reads 1D and 2D codes. | Built-in code reader | | Promptable detection and segmentation | Finds or outlines anything described in words, with no training. | LocateAnything 3B, SAM 3.1 | | Image similarity and matching | Compares images or finds a reference object. | DINOv3, LightGlue | | AI decisions (language and vision-language) | Answers custom questions about text, images and video, such as “Is the work area tidy?” | Decider, OmniJev | Use cases that use these models: [Item and pallet counting](https://nabrio.com/use-cases/item-and-pallet-counting.md), [Visual quality inspection](https://nabrio.com/use-cases/visual-quality-inspection.md), [Defect detection and rejection](https://nabrio.com/use-cases/defect-detection-and-rejection.md), [Foreign object detection](https://nabrio.com/use-cases/foreign-object-detection.md), [Assembly verification](https://nabrio.com/use-cases/assembly-verification.md), [Sorting and grading](https://nabrio.com/use-cases/sorting-and-grading.md), [Robot and AMR orchestration](https://nabrio.com/use-cases/robot-and-amr-orchestration.md), [Gauge reading](https://nabrio.com/use-cases/gauge-reading.md), [Machine status monitoring](https://nabrio.com/use-cases/machine-status-monitoring.md), [Barcode and label inspection](https://nabrio.com/use-cases/barcode-and-label-inspection.md), [PPE detection](https://nabrio.com/use-cases/ppe-detection.md), [Danger zone monitoring](https://nabrio.com/use-cases/danger-zone-monitoring.md), [People counting](https://nabrio.com/use-cases/people-counting.md), [Heatmaps and dwell time](https://nabrio.com/use-cases/footfall-heatmaps-and-dwell-time.md), [Visitor demographics](https://nabrio.com/use-cases/visitor-demographics.md), [Staff presence monitoring](https://nabrio.com/use-cases/staff-presence-monitoring.md), [Queue monitoring](https://nabrio.com/use-cases/queue-monitoring.md), [Traffic monitoring](https://nabrio.com/use-cases/traffic-monitoring.md), [Traffic violation detection](https://nabrio.com/use-cases/traffic-violation-detection.md), [Fire and smoke detection](https://nabrio.com/use-cases/fire-and-smoke-detection.md), [Fall detection](https://nabrio.com/use-cases/fall-detection.md), [Licence plate recognition](https://nabrio.com/use-cases/licence-plate-recognition.md), [Intrusion detection](https://nabrio.com/use-cases/intrusion-detection.md), [Face recognition access control](https://nabrio.com/use-cases/face-recognition-access-control.md), [Occupancy-based energy control](https://nabrio.com/use-cases/occupancy-based-energy-control.md).