gen‑ai.news
← Back
Video

Runway News | How VOIDZ Went From 15-Second VFX Shots to 95-Second Documentary Films

Runway News | How VOIDZ Went From 15-Second VFX Shots to 95-Second Documentary Films

VOIDZ has operated anonymously in the mixed-reality space since 2018, building a body of work that blends footage of the physical world with digitally constructed imagery. For most of that period, the format was constrained - individual shots running around 15 seconds, each functioning as a self-contained visual statement. The new film Ends Meat represents a different kind of ambition: a 95-second work with 15 distinct surreal interventions woven through it.

The film was built using Runway, and its construction reflects how the toolset available to independent artists has shifted. Sustaining a consistent visual language and level of craft across nearly 100 seconds of heavily manipulated footage is a different challenge than producing a single striking moment. Ends Meat suggests that VOIDZ has found a working method that scales - one where generative tools handle the technical weight of visual effects work that would previously have required a larger team or production budget.

Mixed-reality work occupies an interesting position in the broader conversation about AI-generated imagery. It is not purely synthetic - it anchors itself in real-world footage - but it uses generation and manipulation to push that footage somewhere it could not go on its own. For artists like VOIDZ, this hybrid approach has always been central to the practice, predating the current wave of accessible generative video tools by several years.

What makes Ends Meat worth noting is less the individual effects and more what the overall arc of VOIDZ's work implies about where independent filmmaking is heading. The jump from a 15-second VFX clip to a 95-second film with 15 interventions is not just a difference in duration - it is a difference in narrative and structural thinking. As tools like Runway continue to develop, the ceiling for what a single artist can produce without a studio infrastructure keeps rising, and projects like this one serve as a practical illustration of where that ceiling currently sits.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

No image
Video

Runway’s WorldPrompt and the Engineering of Real-Time Worlds

Runway's WorldPrompt system powers its Gen World Models 2 (GWM 2), enabling real-time generation of video and audio through persistent context and timed actions. Rather than producing discrete clips, the model maintains a continuous understanding of an environment as it unfolds. The approach marks a notable shift in how world models can be steered interactively.

Gemini 3.8 Live with Live Avatar gives Google’s AI a face
Video

Gemini 3.8 Live with Live Avatar gives Google’s AI a face

Google has updated Gemini Live with an animated avatar that lip-syncs and displays facial expressions in real time during conversations. Called Live Avatar, the feature is currently limited to Gemini Enterprise customers and supports 97 languages without degrading video quality. It marks Google's latest step toward giving its AI assistant a visible, expressive presence.

No image
Video

Introducing Gemini 3.8 Live with Live Avatar

Google DeepMind has introduced Gemini 3.8 Live, an updated multimodal model paired with a new Live Avatar feature that generates an animated, talking on-screen presence during real-time conversations. The combination allows users to interact with a responsive visual agent rather than a purely voice-based interface. The release marks another step in Google's effort to make AI interactions feel more immediate and embodied.