Find the shots worth a closer look
Make a first pass using sharpness metrics or local MUSIQ image-quality scores. Set a threshold that fits this shoot.
CLASSIC METRICS / AI QUALITYFind the better shot in a burst.
Make room for every perspective.
Get help with your first pass and similar-view selection.
Stay in Lightroom. Make more time for the creative work.

Let culling narrow the field.
Let your eye make the final call.
Make a first pass using sharpness metrics or local MUSIQ image-quality scores. Set a threshold that fits this shoot.
CLASSIC METRICS / AI QUALITYKeep the top 1–9 qualifying photos per conservative group. Each group retains at least one; if none passes the threshold, the highest-ranked photo is kept for manual review. Capture time, camera information, and visual geometry help separate groups.
RANK WITHIN GROUPS · PRESERVE OTHER VIEWSSelect photos, set your criteria, and view results in the native workflow. Preserve existing ratings or allow increases only.
NATIVE REVIEW / STAR RATINGSUse a 30-second, 2-minute, 10-minute, or unlimited capture interval. After analysis, merge groups, split photos into separate groups, or edit group numbers inside Lightroom. Saved revisions reuse existing scores without rerunning AI.
Changing thresholds, retention counts, or grouping settings can reuse scores and features. A complete cache hit skips JPEG export and AI scoring. Photo or develop changes invalidate the cache; the numeric and feature cache is capped at 256 MB.
English, Simplified and Traditional Chinese, Japanese, German, French, Spanish, Brazilian Portuguese, and Thai. Follow Lightroom automatically or choose a language manually. Applying a language keeps your settings and does not start analysis.
Click a sample to compare similar shots.
Actual analysis runs locally through the Lightroom plugin.

Select a set of photos to review in Lightroom Classic.
Choose sharpness, AI image quality, or selection within similar views. Set your threshold and how many to keep.
Analyze exported JPEG copies locally. Routine analysis runs offline, without uploading your photos.
Starting analysis applies your configured rating action without another confirmation. Review results in Lightroom afterward. Manual regrouping only recalculates suggestions; applying revised ratings requires confirmation.
Analysis uses exported JPEG copies. After ratings are applied and results are saved, eligible analysis copies can be removed while reports, settings, and logs are retained.
For Apple Silicon Macs running macOS 14 or later + Lightroom Classic.
Model and runtime included.
Choose either channel regardless of language or region. Downloads are hosted externally.
USD Current test release: free. No paid plan is available yet.
Region selection does not change the page language or download options.Use an Apple Silicon Mac with macOS 14 or later and Lightroom Classic. Keep the complete plugin folder with its bundled runtime and model.
In File → Plug-in Manager, remove the old plugin registration and add the complete LRSmartCulling.lrplugin folder. Enable only one instance and restart Lightroom after upgrading.
Select photos and open cullnest: Culling Settings. Choose a condition, retention count (1–9), rating action, and existing-rating policy. Start Culling runs analysis and applies those settings directly. Review results through Results / Groups / Cleanup.
Clear about what it can—and cannot—do.
The complete model and runtime are included. Routine analysis runs locally, offline, without photo uploads.
Culling does not delete originals. Existing ratings are preserved by default; you can also allow rating increases only. Review your rating settings before starting. Cleanup only removes eligible analysis JPEG copies under the protection rules.
It cannot reliably identify those semantic view categories. The plugin uses feature matching and geometric checks to form conservative groups. Uncertain matches stay in separate groups, and photos in different groups do not compete.
V1.3 has recorded native runtime, grouping, cache, cleanup, and multilingual regression tests. Settings windows have been checked in Lightroom. Full grouping edits were mainly tested with SDK simulations and an eight-photo pipeline; real catalog ratings were not changed in these tests. Start with a small set.
Questions about purchasing, installation, or photo selection? Send me an email.