Original size 763x1080

film nostalgia

PROTECT STATUS: not protected
Longread translated automatically

Project Concept

An experiment to train a generative neural network to reproduce the visual language of classic black-and-white film photography. This study explores the possibility of preserving analog aesthetics while generating new scenes using Stable Diffusion XL.

Source images for training

To train our model, I selected archival photographs by George Hendrik Breitner from the Rijksmuseum collection. These are genuine analog prints from the late 19th to early 20th century, characterized by the soft focus of the lens, tonal gradients, and inherent photographic texture.

Resulting Image Series

The final series included images created from text prompts:1. Big Ben, London — outside photo in analog_bw, Big-Ben London.2. Architectural motif variation — outside photo in analog_bw, old houses_05.3. Pyramids of Egypt — outside photo in analog_bw, pyramids egypt.4. Pyramid image variation — outside photo in analog_bw, pyramids egypt_05.5. Forest landscape — outside photo in analog_bw, forest.6. Wheat field — outside photo in analog_bw, wheat fields.7. Three birch trees in a field — outside photo in analog_bw, three birch trees in the fields.8. Architecture of St. Isaac’s Cathedral — outside photo in analog_bw, St. Isaac’s Cathedral, Saint-petersburg.

big
Original size 1024x1024
Original size 1024x1024
Original size 1024x1024
Original size 1024x1024
Original size 1024x1024
film nostalgia
Project created at 28.10.2026
We use cookies to improve the operation of the website and to enhance its usability. More detailed information on the use of cookies can be fo...
Show more