Menu

TOMAS LAURENZO

Hommage Numérique

 

Introduction

Hommage Numérique is an experimental short film that draws inspiration from the daring aesthetics of early 20th century avant-garde filmmakers such as Marcel Duchamp, Dudley Murphy, Walter Ruttman, Viking Eggeling, Len Lye, and especially Hans Richter, among many others.

These artists developed a cinematographic practice that was naturally able to comfortably ignore the borders that separate abstract from figurative art; storytelling from symbolism; or retinal art from conceptual art. Their enthusiasm was firmly rooted in western history of visual arts. Even more astounding was their intellectual and conceptual hubris, from which their squarely ignored any potential difference, or tension between technological and artistic creativity.

Their blending of technical virtuosity, fearless experimentation and sustained innovation produced audiovisual masterpieces, still relevant nowadays.

Hans Richter‘s Rhythmus 21 (1921), Len Lye’s A Colour Box (1935), Walter Ruttmann‘s Lichtspiel Opus I (1921), or Viking Eggeling‘s Symphonie diagonale (1924) are nothing but examples of this extraordinarily large corpus of abstract masterworks produced between 1920 and 1940.

With footage entirely created using AI, in an era where powerful, usually private, and always obscure tools impose the sadly misnamed “AI aesthetics” brand of artworks, Hommage Numérique shows that technology-infused art remains boundless, subversive, and free.

With this short film, by including (and artistically intervening) elements of their iconic cinematographic language, I hope to succeed in paying a respectful tribute to the many pioneering artists who have explored these territories with their cinema.

Their works continue to inspire, move, and amaze us.

Technical description

Hommage Numérique is an abstract short film created entirely by editing AI-generated footage.

To generate these animations, two state-of-the-art Generative AI techniques were used: Text-to-Image and Stable Video Diffusion.

Text-to-image transforms a text input (aka ‘prompt’) into a numeric representation, which then uses to condition a generative image model. Several models were employed in this project, mainly Stable Diffusion (open source) and DALL-e (closed source).

Once a still image was generated, another open-source model, Stable Video Diffusion, was used to generate an animation conditioned by the input image. While no textual prompt was used, the model’s parameters were heavily adjusted with goals purely aesthetic.

Due to the computational cost of running Stable Video Diffusion, the animations produced had the extremely low frame-rate of seven frames-per-second (FPS).

Utilizing Resolve’s Speed Warp –an AI model that leverages optical flow to interpolate between subsequent frames– the resulting AI-generated footage is at 30 FPS-

An abstract narrative

Once the all the videos were generated, the film’s edited using a non-linear editor. This editing follows a very loose narrative, in which the film steadily gains complexity over time.

Initially, the takes are flat (bi-dimensional) and relatively static. Soon movement appears, followed by the addition of simple, mostly regular, three-dimensional shapes.

This increasing in visual complexity reaches a first climax when the whole scene is shown as a coherent whole. A loosely figurative three-dimensional scene is shown. Order reigns, and all drawn elements obey the coherence that geometry requires. Almost as if recorded by a camera.

This taming of the visual imagery, however, explodes. A geometric disruption taking the form of anthropocentric., surreal-yet-figurative imagery. A stacatto of first-planes of faces, with an apparent push-in that relentlessly and somewhat urgently brings them closer.

These faces have many eyes –a reference to Hans Richter’s Filmstudie (1926)– and, not unlike my experience with in Richter’s work– suggest the ever-present potential subversion of roles. Art that observes the audience being the artists? A cinephile smorgasbord standing on the broad shoulders of Antheil’s music (see #4, below).

Acknowledgements

All the sounds used in this project have been ‘found’ and are royalty-free:

  1. 4k green screen TV: https://link.laurenzo.net/noise_1

  2. 24framemedia: https://link.laurenzo.net/noise_2

  3. Editing Elements: https://link.laurenzo.net/noise_3

  4. Most importantly, the music used at the end was taken from the abstract film Ballet Mécanique (1924) by Fernand Léger and Dudley Murphy, with cinematographic input from Man Ray. The film was scored by American avant-garde composer, pianist, author, writer, and inventor George Antheil.

    Ballet Mécanique, itself a masterful combination of abstract and figurative forms, was a significant source of inspiration for this work. It can be watched free of charge at: http://link.laurenzo.net/ballet.

  5. I would also like to thank Cluster.uy, a high-performance computing platform created by University of the Republic (Uruguay) in collaboration with the Uruguayan Government. I was only able to use these resources thanks to Prof. Javier Baliosian (Chair of Computer Science at University of the Republic). Prof. Baliosian’s research group kindly took care of the computational costs and time this project required.