🎬 WHAT REMAINS – AI Film

0 comments

vadimlasca159.6523 days agoHive.Blog2 min read

🎬 WHAT REMAINS – AI Film

A few months ago, my friend and musician Daniel Damborghini, with whom I had collaborated before, asked me to create visuals for several beats he composed with my brother Chapis Lasca.

Some of those tracks felt so cinematic that I proposed turning them into a mockumentary: a modern, dystopian, apocalyptic version of Powaqqatsi, Koyaanisqatsi or Baraka —but built entirely with AI-generated imagery and video.

🌍 Concept

I developed the idea from scratch, imagining impossible shots reflecting today’s global issues:

Environment
Technological failures
Digital dependence
Wars and migrations
Health and social control
Artificial Intelligence itself

The goal was to build a narrative as coherent as possible, not just an experiment with tools.

🛠 Tools & Workflow

The images were mainly generated with:

Midjourney → more artistic and dramatic
Flux (ComfyUI) → limited but highly prompt-responsive
Gemini via Whisk → more realistic but less expressive

For upscaling:

Magnific (until credits ran out)
Topaz Gigapixel AI & Topaz Photo AI

For animation:

Early tests: Moonvalley Marey (inconsistent, even with motion transfer from phone refs)
Main tool: Seedance Pro on Krea (+ Seedance in Higgsfield and OpenArt)
Additional tests: Veo3 (Flow), Runway, Luma Labs Dream Machine, Wan 2.2

Post-production fixes included Kling 2.1, Nano Banana, and Topaz Video AI / Starlight to clean problematic clips.

🎨 Postproduction

Editing & grading: DaVinci Resolve
Voiceover: a custom-designed AI voice (no gender/age), created with ElevenLabs

The process lasted two months, during which I tested almost every image, video, and voice generation tool currently available.

🎶 Music

The project was produced by Daniel Damborghini, with original music by Daniel Damborghini & Chapis Lasca.
Their soundtrack became the backbone and emotional pulse of the film.