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

/

Mannerism

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

AI Art Styles

This entry documents how a generative image model rendered Mannerism 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
Mannerism, Lake Kenogamissi, thin prompt
Thin prompt
Mannerism, Lake Kenogamissi, thick prompt
Thick prompt
Times Square
Mannerism, Times Square, thin prompt
Thin prompt
Mannerism, 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.

Mannerism, a style originating in late Italian Renaissance, features exaggerated proportions, highly stylized poses, and a lack of clear perspective. This style often displays asymmetrical or unnaturally elegant compositions, privileging tension and instability over the balance and clarity of earlier Renaissance art. To replicate this style, distort proportions, challenge symmetry, leverage complex and unusual poses, and play with perspective to generate tension and instability.

About this movement

Background on Mannerism is available at its Wikipedia entry. The images above are not offered as an account of Mannerism 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.