photography · 2022–today · also: AI photo look, Generated gloss
A recognisable look of images made by generative models: smooth, evenly lit, over-detailed and glossy. The look is named here so that a brief can ask for it or, more often, avoid it.
Core thesis
A generated image can pass for a photograph at a glance, and its tells are the numbers that no real camera and no real scene would give together.
Design principles
Name the tells: skin with no pores at 100%, hair as a smooth mass, and eyes with a perfect catchlight.
Name the light: a soft wrap with a key-to-fill ratio of 1.5:1 or less, and no clear light source.
Name the lens: a claimed 85mm f/1.4 look at all distances, with a blur that has no stepped depth.
Name the grade: glossy, saturated, a teal-orange split and no grain.
Name the failures: hands with extra or merged fingers, text that reads as nonsense and reflections that do not match.
Use the look on purpose, in a label, or avoid it in a brief by adding the real numbers of a style.
Anti-patterns
Passing a generated image as a documentary photograph
Skin smoothing past the point of pores
Impossible lens blur that ignores distance
Text in the image that is not checked
Using the look for a scene that must be true, such as news or evidence
Copying the face or the style of a living artist by name