Generating artistic images from textual inputs using Artificial Intelligence.
Duchampian art made by A.I. DALL-Emades experiments with cutting-edge ML models like DALL-E, ruDALL-E and CLIP by Open AI to generate images of mysterious objects resembling 20th century industrial design with relevant art titles. In this project we are attempting to create a DALL-E like tool or some combination of ‘VAQ + Transformers’ based tool to be utilised by the art community. Considering Marcel Duchamp’s original approach, a machine learning based workflow which combines ‘text-prompt engineering’ plus ‘model-stacking’ method can yield interesting results.
Example : "A Clock in the style of Lamp"
Example : "A kettle in a form of women’s heels"
Example : "Triangular kettle on table top"