Lightroom Classic now has an AI Assisted Culling feature that can scan a whole shoot and tell you which frames actually meet your standards. When you are staring at rows of nearly identical portraits after a long session, that kind of help can keep you from wasting hours on basic sorting.
Coming to you from Aaron Nace with Phlearn, this clear video walks you through how AI Assisted Culling plugs right into the import screen in Lightroom Classic. Nace starts by dragging a folder of sample images into the app and turning on the new assisted option so the software can analyze everything at once. The AI checks whether the subject is in focus, whether the eyes are in focus, and whether the eyes are open, then marks each file with a green check or a red X so you instantly see which shots pass the technical test. You also see how the panel can automatically reject things like documents, receipts, or badly exposed frames so clutter and misfires never even hit the catalog. The whole idea is that your catalog only fills up with images that are at least usable, instead of every single frame you happened to fire.
Nace then shows how you can push this much further than a simple yes-or-no filter. In the import dialog, you can drag a slider that controls how strict “subject in focus” really is, which lets you decide whether an 81 focus score is acceptable or whether only the absolute sharpest shots make the cut. If you like to keep more options, you can loosen those settings and let slightly softer images in when expression or moment might matter more than pixel perfection. The video also makes it clear that the AI does not override your taste; you can still manually check or uncheck any thumbnail, even when the software disagrees with you. That balance between automation and control is what turns this from a gimmick into something you can actually rely on in day-to-day editing.
Once the imports are set, Nace moves into how Assisted Culling works inside the Library module, where the same focus and eyes-open checks are available alongside stacking and batch tools. You see auto stacking group images by capture time so separate shoots on a single memory card fall into their own clusters, and you can also stack by visual similarity when you have long bursts of nearly identical poses. Clicking the stack number expands the group, and menu options let you expand, collapse, or unstack everything when you want to compare frames more closely. From there, Nace uses batch actions to apply white flags to selected keepers and black reject flags to the misses, with optional star ratings or color labels when you want even more structure. You still see moments where he overrides the AI on a case-by-case basis, which is useful if you sometimes prefer an image with slightly less focus but better energy.
The video also walks through how to actually land on your favorites once the AI has done its part. Nace brings up the Library Filter bar, switches to the attribute section, and filters by flags so only picked or rejected images appear while you make decisions. He then uses survey view to compare small sets of similar portraits side by side, dropping weaker frames one at a time until only a single favorite remains, and assigns a five-star rating to crown that final choice. Keyboard shortcuts like N for survey view, the slash key for the filter bar, and number keys for ratings help speed the process along without feeling complicated. You even get a glimpse of how this culling step connects to AI-driven masking, denoising, lens blur, and color tools in Lightroom Classic and Photoshop later in the edit. Check out the video above for the full rundown from Nace.
No comments yet