Monet Paintings Reimagined: Training a DCGAN on Impressionist Art

Author(s): Clément Delteil

Originally published on Towards AI.

Exploring the Boundaries of Creativity and Technology

San Giorgio Maggiore at Dusk — Claude Monet — Public Domain

Midjourney, DALL-E [1], and Stable Diffusion [2] are now taking the spotlight for image generation based on prompts, and for a good reason, because the results are amazing. But at the level of an individual and not an organization like Open-AI, what is possible to generate by training a model from scratch, and what can we learn along the way? Through this educational project and article, this is the question we will try to answer.

For that purpose, let’s implement a generative model. More precisely, let’s implement a Deep Convolutional Generative… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI