Intangible introduces spatial intelligence for AI video creation

Moonvalley secures major funding for ethical AI video tools

Director PJ Accetturo details rapid AI commercial workflow

A camera tour of ASC's 100 year history

No-code 3D creation allows users to drag and drop objects from a library of 5,000+ assets, set up cameras, and control scenes without learning complex software like Unity or Blender.

The platform uses spatial intelligence to ground AI models in structured 3D environments, providing better coherence and continuity between video frames compared to traditional text-only prompts.

Users can switch between edit and visualization modes, where the latter opens panels to define lighting, atmosphere, time of day, and visual styles like photorealism or film noir.

Current limitations include sluggish web performance and the system ultimately relies on Kling's rendering engine rather than native 3D-to-video generation, which may disappoint advanced 3D artists.

The founding team includes veterans from major tech and entertainment companies who believe this approach will democratize 3D creation for filmmakers, marketers, and event planners.

Premium Display Quality: Features a daylight-viewable 19-inch 1920x1080 touchscreen with stunning 1200-nit brightness and 10-bit color depth, covering the DCI-P3 color gamut for perfect visibility even in direct sunlight.

Professional Recording Capabilities: Capture content in multiple high-end formats, including ProRes RAW (up to 6Kp30), ProRes 422, and DNxHR up to 4K60p, with multi-channel recording for complete production flexibility.

Complete Connectivity: Equipped with four 12G-SDI inputs, HDMI 2.0 connectivity, signal cross-conversion, and professional audio support including dual XLR inputs with +48V phantom power.

Advanced Production Tools: Access essential monitoring features including waveform, vectorscope, false color, focus peaking, anamorphic de-squeeze, and comprehensive LUT support for both SDR and HDR workflows – tools typically found only in much more expensive systems.

Trusted Across The Industry: Used on hundreds of productions, from the latest season of The Last of Us to capturing hundreds of camera feeds for MrBeast videos.

The company recently launched Marey, its flagship AI video model that creates HD clips up to 30 seconds with fine-grained controls for camera angles, motion, and scene configuration targeting professional filmmakers and studios.

Moonvalley differentiates itself by using only licensed training data, directly addressing copyright controversies that plague competitors who rely on scraped public datasets containing unlicensed content.

Strategic backing from CAA and Comcast signals Hollywood's interest in AI tools that respect creators' intellectual property rights, as both companies represent major content creators and media properties.

The startup's team includes former researchers from Google DeepMind, Meta, Microsoft, and animation studios like Disney and DreamWorks, bringing deep expertise in both AI development and entertainment production.

Beyond video generation, Moonvalley plans to expand API access for developers and build enterprise features requested by studio partners, positioning itself as a production-ready alternative to consumer-focused AI video tools.

Script development starts with collaborative writing, where PJ worked with head writer Nate Dern and director Theo Dudley to create content around historical underdogs, then crowdsourced alternative lines from their writer network to avoid "doing comedy in a vacuum."

Prompt engineering becomes the critical step where each script line gets converted into detailed Veo 3 prompts using ChatGPT, with PJ requesting only 2-3 prompts at a time in code block format and ensuring each prompt fully describes the scene independently for consistency.

Batch processing in Veo 3 allows running up to 5 prompts simultaneously in fast mode at $0.20 each, with a "leapfrog" workflow where creators work on refining next shots while others process to maximize efficiency.

Character consistency and emotional intensity get achieved through Veo 3's latest features and specific prompting techniques, like using "screaming at the top of their lungs" or all caps for dialogue to intensify character reactions.

Final assembly requires minimal additional work since Veo 3 generates high-quality footage, but professional editing still adds the crucial "sauce" through sound design, color grading, and timing adjustments.