Blown windows
The defect bracketing exists to solve. Measured as the share of the frame clipped to pure white.
Free Preview
Listing Photo Checker
Drop the photos you are about to publish and see what a buyer's screen will show. Every finding is measured from the pixels, and every one names the fix.
Drop your listing photos here
or click to browse
JPG, PNG or WEBP · Up to 40 photos · Max 15 MB each
How do you tell whether a listing photo is good enough?
A listing photo fails on things that can be measured: underexposure, blur, a milky black point, blown highlights where the windows are. This checker measures every photo you upload on each of those, says what is wrong in plain words, and points at the tool that fixes it. The check and the report on your worst photo are free; the full report on the set is one credit.
Last updated:
How the check works
Measured, not guessed
- 01
Drop the set
Up to 40 photos. Every measurement is computed from the pixels, and an AI model only reads what each room is, so an empty one can be offered staging.
- 02
Each frame is measured
Exposure, black point, clipped highlights, detail in the brightest region, shadow depth and sharpness, against what a delivered listing photo looks like.
- 03
See your worst photo free
The photo with the most problems is reported in full. Every finding on every other photo is one credit for the whole set.
What it checks
Only things that can be measured from the file
Exposure
Average brightness against the 124 to 152 band a delivered listing photo sits in, and the black point that tells bright from milky.
Window detail
Whether the brightest region still carries texture, or whether the glass went to paper white.
Sharpness
Detail in the sharpest parts of the frame, so a plain white wall is not mistaken for a soft photo. Catches missed focus, camera shake and small files scaled up.
File and framing
Resolution against portal minimums, and orientation against how portals lay a listing out.
The set as a whole
How many photos there are, and whether any of them fits a portal's landscape hero slot.
Why a checklist beats an opinion
Every photographer has been told a photo is too dark by someone who could not say how dark, or by how much. A number settles it. The point of measuring rather than judging is that you can disagree with a threshold, look at the value, and decide for yourself — and that the same photo gets the same answer twice.
- 1
- credit per full report
- 40
- photos per check
- 124–152
- target brightness
Checker questions
What the report can and cannot tell you
Does this use AI?
The findings do not. Every finding is a statistic computed from the pixels, so it is repeatable and you can check it yourself; a model would let a report be confidently wrong, which is the one thing a checklist must not be. AI is used for one thing: recognising what each photo shows, such as an empty room or an exterior, so the report can suggest what to do with it. Those suggestions never change a finding or the score. Visitors get them on a limited number of photos a day; signed-in users get them on every photo.
Why does it not tell me if a photo is crooked?
Because the measurement was not good enough to ship. It was built, tested against photos rotated by known amounts, and was wrong by up to three degrees, with a confidence signal that did not track when it was wrong. Telling someone with a level photo to rotate it is worse than saying nothing.
Why is there no colour cast check?
The obvious measurement reads the scene rather than the photograph. On a test set the strongest green readings came from a lawn and a garden, which are photos full of grass rather than photos with a cast. A real cast test has to read the light off surfaces that should be neutral. That measurement exists, but it has not been tested against enough listing photos to put on a report.
Why is a white room not flagged as washed out?
Because brightness alone cannot tell a milky photo from a white room. An earlier version flagged every frame averaging above 168, and on a test set of real listing photos that caught about a third of them, most of them well-shot empty rooms. The check now also reads the black point: a correctly exposed white room still has dark tones in it, and a milky one does not.
What does it cost?
Checking a set is free, and so is the full report on its worst photo. Every finding on the other photos is one credit for the whole set, whether it holds 3 photos or 40. If nothing is locked, nothing is charged, and a check that fails charges nothing.
Is my listing set stored?
The photos are measured in the request and not kept. A reduced copy of each photo is sent to an AI model to recognise the room, and we do not store it. The measurements, findings and room types are kept for 24 hours so the report can be unlocked after you sign in, then deleted.
What is the score out of 100?
A blunt summary: every photo starts at 100 and each finding takes a fixed bite. It is there to order a set and give you a headline. The findings are the substance.
Found something to fix?
Every finding names the tool that addresses it. Blown windows go to bracket merge, everything else to the enhancer.
Open the studio