CUNY · QUEENS COLLEGE · DEPT. OF SOCIOLOGY

40.74° N · 73.82° W

Joseph Nathan Cohen

Sociologist at Queens College in the City University of New York

Posts

/

Impressionism

How generative AI renders Impressionism: thin and thick prompts compared across two subjects.

AI Art Styles

This entry documents how a generative image model rendered Impressionism when the movement was named in a prompt. It forms part of a survey of 60 art movements generated in February 2024.

The images

Two subjects are held constant across the series: Lake Kenogamissi in Northern Ontario, and Times Square in New York City. Each is rendered twice. A thin prompt names the movement and nothing else. A thick prompt supplies a generated description of the movement’s visual characteristics.

Lake Kenogamissi
Impressionism, Lake Kenogamissi, thin prompt
Thin prompt
Impressionism, Lake Kenogamissi, thick prompt
Thick prompt
Times Square
Impressionism, Times Square, thin prompt
Thin prompt
Impressionism, Times Square, thick prompt
Thick prompt

The thick descriptor

The following description was generated by GPT-4 and supplied to the image model as the thick prompt.

Impressionism, a 19th-century art style, is characterized by small, visible brush strokes, open compositions, ordinary subjects, and unusual visual angles. Artists focused intensely on accurately capturing light and its changing qualities, using “broken” strokes of pure, unmixed colour for a vibrant effect. Painting usually occurred in outdoor settings to capture transient effects of natural lighting. Movement and a sense of immediacy was often captured in these artworks, too.

About this movement

Background on Impressionism is available at its Wikipedia entry. The images above are not offered as an account of Impressionism as art historians understand it. They record what a commercial image model produced when asked for the style by name.

About this series

This entry is part of a survey, described in the series introduction. The full set of 60 movements is browsable in the Art Styles index. The survey used text-to-image generation, in which composition varies alongside the style itself.

Share / Cite

Joseph Nathan Cohen Avatar

Associate Professor of Sociology at Queens College, CUNY. Writes about household finance, culture, and the tools social scientists use to measure economic life.