Inspiration

Modern event and wedding photographers shoot between 2,000 and 5,000 uncompressed RAW captures (200GB to 1TB+) per assignment. However, delivering final albums requires a grueling initial step: manual photo culling. Photographers spend days zooming into burst shots at 100% crop just to discard out-of-focus frames, blinking eyes, and shutter misfires.

While cloud-based AI culling software exists, it introduces severe friction:

  1. Network Bandwidth & Ingestion Bottlenecks: Uploading hundreds of gigabytes of uncompressed RAW files (CR3, ARW, NEF) takes hours or days on standard internet connections.
  2. Recurring Cloud Costs & Data Privacy: Subscription fees escalate with storage volume, and uploading unreleased client portraits to public clouds creates client confidentiality concerns.
  3. Local Storage Disconnection: Raw media already resides safely on high-throughput local NAS storage, making remote uploads redundant.

We built LensCull AI to transform the UGREEN AI NAS into an autonomous, on-premise photo culling workstation that triages high-volume RAW shoots directly where the files live—at multi-gigabit local speeds with zero cloud exposure.

What it does

LensCull AI is an autonomous, declarative orchestration skill for UGREEN AI NAS (UGOS) designed to streamline post-shoot intake:

  • Zero-Upload Ingestion: Discovers uncompressed RAW directories directly on NAS storage via file-agent (ug-filemgr), enforcing strict read-only intake to guarantee master camera files are never altered or deleted.
  • On-Device Vision & Facial Triage: Batches embedded previews through media-agent (ug-video) in bounded sliding windows (15–20 images) to evaluate pupil sharpness, detect closed eyes/blinks, assess composition, and cluster high-speed burst sequences.
  • Deterministic Classification: Scores and sorts assets into three clean tiers based on clear quality heuristics:
    • Accepted (5 Stars / Green): Pin-sharp focus, genuine expressions, open eyes, best frame of a burst sequence.
    • Candidate (3 Stars / Yellow): Clean alternate compositions preserved for client proofing.
    • Rejected (1 Star / Red): Blinks, defocus, severe exposure clipping, and redundant burst frames.
  • Human-in-the-Loop Safeguards: Enforces a strict waiting_approval state before modifying any metadata, presenting an interactive culling breakdown table to the photographer for explicit confirmation.
  • Dual Non-Destructive Outputs: Automatically generates curated smart albums via photo-agent (ug-photo) in the native UGOS gallery and compiles an audit ledger markdown report with standardized YAML frontmatter into {target_folder}/Culling_Reports/.

How we built it

  • Uliya Skill Standard v2.0.0: Developed strictly under the official UGREEN Uliya framework using declarative workflow graphs in SKILL.md without disallowed binaries or external script dependencies.
  • Native Expert Delegation: Mapped CLI capabilities to registered UGOS sub-agents:
    • ug-photo → photo-agent for gallery indexing and curated album assembly.
    • ug-video → media-agent for bounded visual analysis and facial blink evaluation.
    • ug-filemgr → file-agent for directory scanning and audit ledger persistence.
  • Modular Quality Specifications: Isolated scoring matrices and output templates inside references/culling-rubric.md and references/culling-report-template.md.
  • Finite-State Machine (FSM) Lifecycle: Comprehensive coverage of all lifecycle states (completed, failed, cancelled, waiting_user, and waiting_approval).
  • Verified Codebase: Achieved an audited static-pass (0 errors, 0 warnings) against the official check-skill.mjs test suite in an isolated Docker sandbox.

Challenges we ran into

  • Hardware Memory Throttling: Attempting to triage thousands of RAW files concurrently risks exhausting system RAM. We resolved this by engineering a bounded sliding-window mechanism (15–20 items per batch) with partial state preservation.
  • Sandboxed Path Escalation Rules: The Uliya runtime prohibits direct Linux root filesystem access (SECURITY_DIRECT_FILE_ACCESS). We refactored all file persistence logic to execute strictly via relative paths grounded in the user-provided target_folder.
  • Artistic Intent vs. Defect Detection: Distinguishing between an accidental motion blur and an intentional slow-shutter panning shot or moody silhouette required engineering a FLAGGED_CREATIVE_REVIEW exception pipeline so creative shots are never falsely rejected.

Accomplishments that we're proud of

  • Eliminating cloud upload wait times entirely by processing photography culling on local NAS storage.
  • Delivering a verified, linter-compliant skill package meeting UGREEN's highest security and formatting standards.
  • Ensuring complete data sovereignty and peace of mind for wedding and commercial photographers handling sensitive client media.

What we learned

  • The architectural efficiency of edge AI NAS: how combining local NPU/GPU compute with multi-terabyte internal bus speeds unlocks use cases that are impractical in cloud-only environments.
  • Best practices in writing declarative multi-agent workflows with deterministic human-in-the-loop gates.

What's next for LensCull AI

  • Round 2 Hardware Benchmarking: Profiling embedded JPEG decoding and batch facial tagging directly on physical UGREEN AI NAS iDX6011 Pro hardware.
  • Sidecar .xmp Sync: Exporting industry-standard Lightroom and Capture One rating tags directly into sidecar metadata files for instant desktop editing import.
  • Subject-Specific Grouping: Integrating local face clustering to sort wedding photos automatically by key VIPs (Bride, Groom, Family, Guests).

Built With

Share this project:

Updates

Submission history