Opposites

Amsterdam Centraal Station railway station, Netherlands, May 2026

Frames from a video at AmsterdamCentraal railway station are split in 16 tiles that are fed to the YOLO image recognition model and classified using a long list of concepts, the opposite concept in this space is then selected as a prompt to resynthesize the tile with Stable Diffusion img2img, this is repeated for each frame in the short video. The soundtrack is made with YOLO neural network activations from video frames, injected into Meta's MusicGen model.

#abstract #abstractstreet #urbanphotography #videoart #computationalart #Amsterdam #Netherlands #amsterdamcentraal #railwaystation

Kruisende paden / crossing paths

Amsterdam Centraal Station railway station, Netherlands, May 2026

People walking past were segmented out of a video using YOLO and SAM2 and then composited into a new video. The soundtrack is made with YOLO neural network activations from video frames, injected into Meta's MusicGen model.

#abstract #abstractstreet #urbanphotography #videoart #computationalart #Amsterdam #Netherlands

de-embedding

Amsterdam, March 2026
Activations in the first layer of the YOLO (You Only Look Once) object detection AI model determine from which video frame to load pixels.

#urbanphotography #computationalart #generativeart #yolo #computervision #abstractstreet #amsterdam #video

Zebra

Polar-transformed slit-scan photo, Stuttgart, Germany, July 2025

#slitscan #polartransform #computationalart #abstract #urbanphotography #stuttgart #germany

Moments of reflection

A video from a train window around Hilversum, Netherlands is interpreted frame by frame by Stable Diffusion without a prompt. The frames of the resulting video rendered as slices though a volume.

#traintrip #hilversum #abstractlandscape #computationalart

Sunset cube

Timelapse of a Tokyo sunset rendered as a volume.
Shinagawa, Tokyo, Japan, January 2026

#videoart #computationalart #abstractlandscape #cityscape #tokyo #japan #sunset

Holographic

Slit-scan video of people moving in Amsterdam Centraal railway station in August 2021, rendered as a volume, the transparency of pixels is determined by activations of a layer of the Ultralytics YOLO model run on the video. The music is generated by activations of a neural layer of OpenAI's CLIP image description model injected into Facebook's MusicGen generative model for 3 second chunks of this video.

#generativeart #computationalart #slitscan #videoart #abstractstreet #amsterdamcentraal #amsterdam #netherlands #deeplearningart

Timeslices

People walking in front of Tokyo's Shinagawa station, January 2026.

Video rendered as a width x height x time volume and cut up in 100 semitransparent slices.

#videoprocessing #computationalart #slitscan #3d #tokyo #abstractstreet #japan #video #videoart