A Collaborative Project with an End Times Feel

February 02, 2025  •  Leave a Comment

Rumble TownEnd of times. Image Crack to video.
At Eovaldi Art Science, we're exploring how technology can transform art. Our latest project, "Rumble Town," took inspiration from the opening scene of Alfred Hitchcock's "Psycho" to craft an eerie, surreal vibe. Here's the journey:

The Photo: "Crack"

"Crack" is a photograph by Robert Eovaldi, taken at the intertidal zone of the Pacific Ocean on California's central coast. (https://www.eovaldiartscience.com/california-cool/h6a5e9b31).

From Photo to Video

Using RunwayML’s Image to Video Gen3, they animated "Crack," giving it movement. This technology leverages advanced algorithms that can interpret both text and mathematical prompts alongside image data to generate video content. Here's how it works:

- Text Prompts: By feeding the AI with descriptive text, like "neon-lit intertidal zone at night," the system can understand the intended mood, lighting, and atmosphere. This text acts as a guide for the AI to mimic styles or elements from other works, or to create a completely new visual narrative.

- Mathematical Prompts: These involve parameters or equations that control aspects like movement speed, light intensity, color gradients, and the flow of particles or effects within the video. For instance, a mathematical formula might dictate how the neon lights reflect and refract over the water's surface, creating a more dynamic and fluid visual experience.

- Image Data: The original photograph provides the foundational visual data. Algorithms analyze the image for textures, colors, patterns, and spatial relationships. This data is then manipulated or expanded upon to introduce motion where there was none, essentially animating static elements like waves, rocks, and the sky.

- AI Synthesis: Combining these inputs, the AI synthesizes video by predicting how static images would move over time. It learns from vast datasets of video content, understanding how light, shadows, and objects interact in motion. This allows for the transformation of "Crack" into a scene with neon lighting and shadowy dwellings where clandestine, hedonistic gatherings occur, evoking the moral decay prophesied in the Christian understanding of the end times.

They chose this method to infuse the scene with an atmosphere that not only reflects the original's depth but also paints a picture of revelry and sin amidst the foreboding signs of the apocalypse.

Rumble Town

Inspired by Hitchcock's opening, "Rumble Town" was created to evoke a sense of impending doom. The video narrative blends the past with a foreboding future, crafting a haunting landscape where time seems to be running out, capturing the essence of tribulation and judgment.

The Process

This project involved a collaboration between Robert Eovaldi and his son, Benjamin Eovaldi. They used Image to Video Generative AI to transform Robert's photo, "Crack" which does provoke thought and emotion, with its rugged depth and allure, into something eerie, sinful, and reflective of the end times.

NFT on OpenSea

The "Rumble Town" video has been minted as an NFT. [You can view and explore it here](https://opensea.io/assets/ethereum/0x2cad2409af9a2baabb096ec5d5dc892e726d3e2e/3/).

Looking Ahead

This experiment in blending art with technology opens up new avenues for storytelling. We're curious about where this direction might lead next, especially in illustrating complex theological themes like sin and redemption.

Thanks for following this creative process.

— Benjamin VanLocke
Science Writer, Eovaldi Art Science

 

 


Comments

No comments posted.
Loading...

Archive
January February March April May June July August September October November (1) December (3)
January February (1) March (1) April May June (1) July August (2) September (1) October (3) November December
January February March April May June July August September October November (1) December
January February March April May June July August September October November December
January February March (1) April May June July August September October (3) November (7) December (2)
January (3) February March April May (1) June July (1) August September October (2) November (2) December (1)
January February (2) March April (1) May June July August September October November December (1)
January February March April May June July August September October (4) November (44) December (30)
January (15) February (8) March (2) April May June (3) July (1) August September October November December (6)
January (4) February March April May June July August September October November December
January February (1) March April (1) May (17) June (21) July (88) August September October November December