gen‑ai.news
← Back
Multimodal

Uniting LED Volumes and Live Visual Chaos: Cinematographer Bradford Lipson on 'Rolling Loud'

Uniting LED Volumes and Live Visual Chaos: Cinematographer Bradford Lipson on 'Rolling Loud'

Filming a scripted comedy inside one of North America's largest hip-hop festivals presented a straightforward problem: you cannot ask tens of thousands of people to reset a take. For Rolling Loud, director Jeremy Garelick and cinematographer Bradford Lipson settled on a two-part strategy - capture the real festival as it happened, then use an LED volume stage to place actors inside that captured world for the scenes requiring controlled performance work.

The production spent three days at Rolling Loud in Miami with a first unit shooting on Sony VENICE 2 cameras with Zeiss Supreme Prime Radiance lenses, alongside drone and gimbal platforms including the DJI Ronin 4D and DJI Inspire 3. Simultaneously, camera arrays provided by Sam Nicholson and Stargate Studios recorded the crowds, performances, and environments that would later become the LED volume plates. VFX supervisor Matthew Whelan drove the breakdown of which sequences would benefit from virtual production and exactly where the arrays needed to be positioned at any given time.

The centerpiece sequence - Owen Wilson's character performing onstage with Travis Scott - combined festival footage with a later shoot on the volume, and it grew more complicated when rain began falling during the live Miami filming. Rather than work around it, Garelick folded the rain into the performance. That decision meant the volume shoot had to reproduce not just the stage geometry and concert lighting, but the way shifting colored lights played through falling rain and across wet surfaces. Lipson's team used pixel-mapped Creamsource Vortex 8 fixtures and Kino Flo Mimik lights to extend and reinforce the illumination coming off the LED walls, while the art department physically recreated a portion of the stage so Wilson had something tangible to interact with.

Lipson is candid that the technology only works when it stops being visible. Matching perspective, lens choice, camera height, movement, and the volatile color changes of concert lighting across two shooting environments - months apart - required the controlled volume work to deliberately inherit the imperfections of live-event photography. The goal, as he describes it, was never to invent the world of Rolling Loud but to capture it accurately enough that the story could continue unfolding inside it.

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
Multimodal

Google’s new SynthID website can identify AI-generated media

Google has launched a public-facing website for SynthID, its AI watermarking technology, allowing anyone to upload and check whether an image, video, or audio clip was generated by AI. The tool extends SynthID beyond its previous developer and enterprise integrations, putting detection capabilities directly in the hands of everyday users. This marks a notable step toward accessible, practical tools for identifying synthetic media in the wild.

Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model
Multimodal

Reka AI's omni-model Rho-1 handles text, images, video, and robot control in a single model

Reka AI has released Rho-1, a 19-billion-parameter model that handles text, images, video, and robot control actions within a single neural network. Rather than routing different tasks to specialized subsystems, it processes all modalities as tokens in one shared context window. The model was trained on 320 H100 GPUs over roughly three months, using considerably less compute than many leading models today.

AMD Acquires World Labs for $8.2 Billion, Bringing Fei-Fei Li Onboard
Multimodal

AMD Acquires World Labs for $8.2 Billion, Bringing Fei-Fei Li Onboard

AMD has agreed to acquire World Labs, the spatial intelligence startup founded by AI pioneer Fei-Fei Li, for $8.2 billion. Li will join AMD as Executive Vice President and Chief Scientist, reporting to CEO Lisa Su. The deal gives AMD an in-house AI research unit built around world models that generate and simulate 3D environments.