Something to Measure Against

Something to Measure Against

What this makes

Hand it a photograph of one thing and it puts exactly one ordinary object beside it — a coin, a hand-sized cup, a matchbox — so a viewer can read the size instead of guessing it. Two fields.

You are given ONE photograph of ONE object. Return ONE image: the same object with one everyday thing beside it, so its size stops being a guess. Follow every line. Replace only the FIELDS block; everything after it is fixed.

First — do you have the photograph and the fields?

Say what this makes before you ask anything, in one or two sentences of their own words. Someone who has just pasted this has no idea what they are being asked for, and questions arriving cold are questions answered badly.

If no photograph is attached, stop and ask for one. This template has nothing to work on without it, and an object generated from the description instead is a different object that resembles the answer.

If either field below still has braces around it, stop and ask. Put both questions in one short message, and show the example under each one so they can see the shape of a useful answer. Wait for the replies, then work. Never fill a brace yourself: a value you invented is a value nobody asked for.

Ask in whatever language they are writing to you in. Translate the questions and the examples; do not make someone read English to tell you what they want.

If the photograph is attached and both fields are filled in, ignore this and carry on.

Fields — replace these two lines only

• The object, in three or four words: {what is in the photograph}
• The thing beside it, and which side: {one everyday object of undisputed size, and left or right}

The law everything else follows from

You can only see the face the photograph gave you.

So this template builds around the object and asks nothing of the object itself. It never turns it, opens it, tilts it or shows another side — you would have to invent that side, and not inventing it is the whole promise. If what you are about to do needs a face the photograph never showed, you are doing the wrong thing.

The object — carried through untouched

• Silhouette, proportions, and the position of every part.
• Colour, finish and material, including how light behaves on it: matt stays matt, gloss keeps its highlights where they were.
• Every existing mark, seam, join, chip and irregularity, including the ones that look like faults. They are how someone recognises their own thing.
• Any lettering already on the object stays exactly as photographed — same words, same letterforms, same position. You are not setting it again.

Nothing is added to the object: no label, no cap, no strap, no second copy of it, and no adjustment of its colour "to suit the scene".

The camera — it did not move

• Same eye line, same distance, same focal length.
• The object fills the same share of the frame within a twentieth, and sits in the same place in it.
• Perspective is unchanged: an ellipse that read nearly flat still reads nearly flat, a face that read square still reads square.

Check it by overlay. Stack the two frames. The object's outline should land on itself. Bigger, smaller, higher, or more from above means the camera moved — go again.

The ground — it must not swallow the object

Whatever you build, the surface behind and beneath the object differs from the object in at least two of these three: value, temperature, texture.

A sand-coloured object on sand-coloured linen under warm light is one object photographed inside itself. It looks tasteful as a thumbnail and vanishes at size, and it is the standing failure of this genre — scenery chosen to flatter the product rather than to show it.

The light — it comes from somewhere

• One dominant source, with a direction and a height you have decided.
• Every shadow in the frame agrees with it, including the object's own.
• The contact shadow starts where the object meets the ground and is darkest there. A detached shadow is an object pasted onto a picture.

The treatment — one known thing, beside it

Add exactly one everyday object whose size a viewer already knows.

• One. Not a pair, not a scatter. A second reference makes the viewer compare the references to each other instead of to the subject.
• In the same plane. It stands on the same surface, at the same distance from the camera, so the comparison is not distorted by perspective. Slightly behind is fine; nearer the lens is not.
• Not touching. A small gap, so the two silhouettes read separately.
• Sharp and whole. Fully in frame, in focus, unobscured. A reference you cannot see all of is a reference you cannot measure with.
• Smaller in the frame than the subject, unless the subject really is the smaller thing — in which case that is exactly what the picture has to show.
• Its real size, honestly. The ratio between the two is the entire content of this picture. Making the subject look bigger by shrinking the reference is the one lie this treatment can tell.

Everything else in the frame — surface, background, light — stays as it was.

Never

• Lettering, numerals, logos, labels, watermarks, price flashes, badges or packaging copy anywhere in the picture, in any script. Words already on the object are the only words allowed, and they stay as photographed.
• Hands, faces, figures, or any part of a person.
• A border, frame, vignette or sticker laid over the picture.
• A second copy of the object, a reflection showing a side that was never photographed, or a view into a part the photograph did not show.

What it should read as

The same shot with one thing set down next to the subject, the way anyone photographing something small actually does it.